High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 94	99.23 7	99.69 1	98.88 62	97.32 42	99.53 23	99.47 20	97.81 3	99.94 8	98.47 39	99.72 55	99.74 37

FOURS1					99.82 1	98.66 24	99.69 1	98.95 46	97.46 34	99.39 30

CS-MVS		98.44 41	98.49 21	98.31 110	99.08 107	96.73 113	99.67 3	98.47 179	97.17 55	98.94 54	99.10 86	95.73 44	99.13 204	98.71 24	99.49 100	99.09 158

CS-MVS-test		98.49 35	98.50 20	98.46 96	99.20 92	97.05 99	99.64 4	98.50 173	97.45 35	98.88 61	99.14 81	95.25 64	99.15 201	98.83 22	99.56 90	99.20 139

EC-MVSNet		98.21 58	98.11 56	98.49 93	98.34 179	97.26 91	99.61 5	98.43 188	96.78 74	98.87 62	98.84 123	93.72 98	99.01 225	98.91 20	99.50 98	99.19 143

mvsmamba		96.57 142	96.32 141	97.32 187	96.60 316	96.43 129	99.54 6	97.98 268	96.49 88	95.20 224	98.64 150	90.82 163	98.55 275	97.97 67	93.65 274	96.98 266

HPM-MVS		98.36 50	98.10 57	99.13 48	99.74 7	97.82 68	99.53 7	98.80 93	94.63 182	98.61 84	98.97 105	95.13 70	99.77 106	97.65 91	99.83 15	99.79 19
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVSFormer		97.57 94	97.49 84	97.84 145	98.07 207	95.76 168	99.47 8	98.40 192	94.98 165	98.79 67	98.83 125	92.34 119	98.41 298	96.91 123	99.59 80	99.34 116

test_djsdf		96.00 165	95.69 169	96.93 212	95.72 351	95.49 177	99.47 8	98.40 192	94.98 165	94.58 238	97.86 224	89.16 196	98.41 298	96.91 123	94.12 261	96.88 280

HPM-MVS_fast		98.38 47	98.13 54	99.12 50	99.75 3	97.86 64	99.44 10	98.82 81	94.46 191	98.94 54	99.20 67	95.16 68	99.74 111	97.58 96	99.85 6	99.77 27

nrg030		96.28 156	95.72 163	97.96 141	96.90 299	98.15 54	99.39 11	98.31 209	95.47 136	94.42 248	98.35 179	92.09 131	98.69 263	97.50 104	89.05 337	97.04 263

APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 33	98.96 16	99.39 11	98.93 50	97.38 39	99.41 28	99.54 8	96.66 18	99.84 67	98.86 21	99.85 6	99.87 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
3Dnovator+	94.38 6	97.43 103	96.78 120	99.38 18	97.83 227	98.52 28	99.37 13	98.71 116	97.09 62	92.99 309	99.13 82	89.36 190	99.89 47	96.97 120	99.57 84	99.71 49

FIs		96.51 144	96.12 148	97.67 164	97.13 285	97.54 76	99.36 14	99.22 23	95.89 114	94.03 269	98.35 179	91.98 134	98.44 289	96.40 148	92.76 291	97.01 264

FC-MVSNet-test		96.42 148	96.05 150	97.53 174	96.95 294	97.27 87	99.36 14	99.23 20	95.83 118	93.93 272	98.37 177	92.00 133	98.32 307	96.02 160	92.72 292	97.00 265

3Dnovator	94.51 5	97.46 98	96.93 112	99.07 53	97.78 230	97.64 71	99.35 16	99.06 34	97.02 64	93.75 282	99.16 77	89.25 193	99.92 31	97.22 113	99.75 45	99.64 71

sasdasda		97.67 83	97.23 98	98.98 59	98.70 143	98.38 35	99.34 17	98.39 194	96.76 76	97.67 140	97.40 266	92.26 122	99.49 159	98.28 52	96.28 230	99.08 162

GeoE		96.58 141	96.07 149	98.10 132	98.35 174	95.89 164	99.34 17	98.12 245	93.12 259	96.09 204	98.87 120	89.71 183	98.97 227	92.95 259	98.08 174	99.43 109

canonicalmvs		97.67 83	97.23 98	98.98 59	98.70 143	98.38 35	99.34 17	98.39 194	96.76 76	97.67 140	97.40 266	92.26 122	99.49 159	98.28 52	96.28 230	99.08 162

CP-MVS		98.57 27	98.36 30	99.19 40	99.66 26	97.86 64	99.34 17	98.87 69	95.96 110	98.60 85	99.13 82	96.05 33	99.94 8	97.77 81	99.86 1	99.77 27

EPP-MVSNet		97.46 98	97.28 96	97.99 138	98.64 152	95.38 182	99.33 21	98.31 209	93.61 237	97.19 157	99.07 95	94.05 94	99.23 191	96.89 127	98.43 161	99.37 114

MGCFI-Net		97.62 88	97.19 101	98.92 64	98.66 149	98.20 49	99.32 22	98.38 198	96.69 81	97.58 149	97.42 265	92.10 130	99.50 158	98.28 52	96.25 233	99.08 162

XVS		98.70 14	98.49 21	99.34 23	99.70 22	98.35 42	99.29 23	98.88 62	97.40 36	98.46 90	99.20 67	95.90 41	99.89 47	97.85 76	99.74 49	99.78 21

X-MVStestdata		94.06 292	92.30 315	99.34 23	99.70 22	98.35 42	99.29 23	98.88 62	97.40 36	98.46 90	43.50 408	95.90 41	99.89 47	97.85 76	99.74 49	99.78 21

tttt0517		96.07 162	95.51 174	97.78 151	98.41 170	94.84 211	99.28 25	94.33 388	94.26 197	97.64 145	98.64 150	84.05 307	99.47 166	95.34 182	97.60 191	99.03 169

mPP-MVS		98.51 33	98.26 43	99.25 35	99.75 3	98.04 59	99.28 25	98.81 86	96.24 99	98.35 100	99.23 62	95.46 51	99.94 8	97.42 107	99.81 16	99.77 27

test_vis1_n		95.47 192	95.13 192	96.49 252	97.77 231	90.41 331	99.27 27	98.11 248	96.58 85	99.66 15	99.18 73	67.00 390	99.62 137	99.21 15	99.40 113	99.44 107

test_fmvs1_n		95.90 172	95.99 154	95.63 296	98.67 148	88.32 367	99.26 28	98.22 225	96.40 94	99.67 14	99.26 57	73.91 377	99.70 119	99.02 18	99.50 98	98.87 184

MSP-MVS		98.74 13	98.55 17	99.29 29	99.75 3	98.23 47	99.26 28	98.88 62	97.52 29	99.41 28	98.78 131	96.00 35	99.79 98	97.79 80	99.59 80	99.85 10
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
v7n		94.19 279	93.43 292	96.47 255	95.90 346	94.38 235	99.26 28	98.34 205	91.99 298	92.76 314	97.13 282	88.31 219	98.52 280	89.48 333	87.70 351	96.52 326

iter_conf05_11		98.04 63	97.94 64	98.34 107	98.60 156	96.38 133	99.24 31	98.57 151	95.90 113	98.99 52	98.79 130	92.97 107	99.47 166	98.58 27	99.85 6	99.17 149

WR-MVS_H		95.05 221	94.46 225	96.81 221	96.86 301	95.82 166	99.24 31	99.24 17	93.87 214	92.53 322	96.84 317	90.37 172	98.24 317	93.24 249	87.93 349	96.38 339

HFP-MVS		98.63 17	98.40 26	99.32 28	99.72 12	98.29 45	99.23 33	98.96 45	96.10 107	98.94 54	99.17 74	96.06 32	99.92 31	97.62 93	99.78 33	99.75 35

region2R		98.61 18	98.38 28	99.29 29	99.74 7	98.16 53	99.23 33	98.93 50	96.15 104	98.94 54	99.17 74	95.91 39	99.94 8	97.55 100	99.79 29	99.78 21

ACMMPR		98.59 21	98.36 30	99.29 29	99.74 7	98.15 54	99.23 33	98.95 46	96.10 107	98.93 58	99.19 72	95.70 45	99.94 8	97.62 93	99.79 29	99.78 21

QAPM		96.29 154	95.40 175	98.96 62	97.85 226	97.60 74	99.23 33	98.93 50	89.76 349	93.11 306	99.02 98	89.11 198	99.93 25	91.99 286	99.62 75	99.34 116

MP-MVS		98.33 55	98.01 61	99.28 32	99.75 3	98.18 51	99.22 37	98.79 98	96.13 105	97.92 126	99.23 62	94.54 80	99.94 8	96.74 140	99.78 33	99.73 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Vis-MVSNet		97.42 104	97.11 104	98.34 107	98.66 149	96.23 141	99.22 37	99.00 39	96.63 84	98.04 112	99.21 65	88.05 228	99.35 180	96.01 161	99.21 121	99.45 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CSCG		97.85 74	97.74 71	98.20 121	99.67 25	95.16 194	99.22 37	99.32 11	93.04 262	97.02 166	98.92 116	95.36 57	99.91 39	97.43 106	99.64 72	99.52 86

SDMVSNet		96.85 130	96.42 136	98.14 124	99.30 68	96.38 133	99.21 40	99.23 20	95.92 111	95.96 210	98.76 137	85.88 268	99.44 173	97.93 70	95.59 245	98.60 209

OpenMVS	93.04 13	95.83 176	95.00 199	98.32 109	97.18 282	97.32 84	99.21 40	98.97 42	89.96 345	91.14 342	99.05 97	86.64 254	99.92 31	93.38 245	99.47 103	97.73 243

DTE-MVSNet		93.98 294	93.26 297	96.14 275	96.06 340	94.39 234	99.20 42	98.86 75	93.06 261	91.78 336	97.81 232	85.87 269	97.58 355	90.53 313	86.17 367	96.46 336

Vis-MVSNet (Re-imp)		96.87 129	96.55 131	97.83 146	98.73 138	95.46 178	99.20 42	98.30 215	94.96 167	96.60 186	98.87 120	90.05 177	98.59 273	93.67 239	98.60 150	99.46 104

test_fmvs2		93.43 301	93.58 284	92.95 356	96.97 293	83.91 383	99.19 44	97.24 325	95.74 123	95.20 224	98.27 191	69.65 383	98.72 262	96.26 151	93.73 271	96.24 344

ZNCC-MVS		98.49 35	98.20 52	99.35 22	99.73 11	98.39 34	99.19 44	98.86 75	95.77 120	98.31 103	99.10 86	95.46 51	99.93 25	97.57 99	99.81 16	99.74 37

IS-MVSNet		97.22 113	96.88 114	98.25 116	98.85 131	96.36 136	99.19 44	97.97 269	95.39 140	97.23 156	98.99 104	91.11 159	98.93 237	94.60 207	98.59 151	99.47 100

PEN-MVS		94.42 265	93.73 277	96.49 252	96.28 331	94.84 211	99.17 47	99.00 39	93.51 239	92.23 330	97.83 230	86.10 264	97.90 341	92.55 272	86.92 362	96.74 294

PS-MVSNAJss		96.43 147	96.26 144	96.92 215	95.84 349	95.08 199	99.16 48	98.50 173	95.87 116	93.84 278	98.34 183	94.51 81	98.61 270	96.88 129	93.45 280	97.06 262

dcpmvs_2		98.08 60	98.59 14	96.56 244	99.57 33	90.34 333	99.15 49	98.38 198	96.82 73	99.29 34	99.49 17	95.78 43	99.57 142	98.94 19	99.86 1	99.77 27

APD-MVS_3200maxsize		98.53 32	98.33 39	99.15 46	99.50 41	97.92 63	99.15 49	98.81 86	96.24 99	99.20 38	99.37 38	95.30 60	99.80 88	97.73 83	99.67 63	99.72 45

TSAR-MVS + MP.		98.78 11	98.62 13	99.24 36	99.69 24	98.28 46	99.14 51	98.66 131	96.84 71	99.56 20	99.31 51	96.34 25	99.70 119	98.32 50	99.73 52	99.73 42
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
anonymousdsp		95.42 197	94.91 204	96.94 211	95.10 367	95.90 163	99.14 51	98.41 190	93.75 220	93.16 302	97.46 259	87.50 241	98.41 298	95.63 176	94.03 263	96.50 331

jajsoiax		95.45 195	95.03 198	96.73 224	95.42 363	94.63 221	99.14 51	98.52 166	95.74 123	93.22 300	98.36 178	83.87 312	98.65 268	96.95 122	94.04 262	96.91 276

PS-CasMVS		94.67 245	93.99 256	96.71 225	96.68 313	95.26 189	99.13 54	99.03 37	93.68 231	92.33 328	97.95 217	85.35 277	98.10 325	93.59 241	88.16 348	96.79 288

CPTT-MVS		97.72 79	97.32 95	98.92 64	99.64 28	97.10 98	99.12 55	98.81 86	92.34 287	98.09 108	99.08 94	93.01 105	99.92 31	96.06 158	99.77 35	99.75 35

SR-MVS-dyc-post		98.54 31	98.35 32	99.13 48	99.49 45	97.86 64	99.11 56	98.80 93	96.49 88	99.17 41	99.35 44	95.34 58	99.82 76	97.72 84	99.65 68	99.71 49

RE-MVS-def			98.34 35		99.49 45	97.86 64	99.11 56	98.80 93	96.49 88	99.17 41	99.35 44	95.29 61		97.72 84	99.65 68	99.71 49

CP-MVSNet		94.94 232	94.30 233	96.83 219	96.72 310	95.56 173	99.11 56	98.95 46	93.89 212	92.42 327	97.90 220	87.19 245	98.12 324	94.32 217	88.21 346	96.82 287

SteuartSystems-ACMMP		98.90 9	98.75 10	99.36 21	99.22 89	98.43 33	99.10 59	98.87 69	97.38 39	99.35 32	99.40 31	97.78 5	99.87 58	97.77 81	99.85 6	99.78 21
Skip Steuart: Steuart Systems R&D Blog.
SR-MVS		98.57 27	98.35 32	99.24 36	99.53 36	98.18 51	99.09 60	98.82 81	96.58 85	99.10 46	99.32 49	95.39 54	99.82 76	97.70 89	99.63 73	99.72 45

GST-MVS		98.43 43	98.12 55	99.34 23	99.72 12	98.38 35	99.09 60	98.82 81	95.71 126	98.73 75	99.06 96	95.27 62	99.93 25	97.07 117	99.63 73	99.72 45

K. test v3		92.55 318	91.91 321	94.48 336	95.64 353	89.24 349	99.07 62	94.88 382	94.04 202	86.78 374	97.59 251	77.64 356	97.64 352	92.08 281	89.43 332	96.57 316

test2506		94.44 264	93.91 261	96.04 278	99.02 111	88.99 355	99.06 63	79.47 413	96.96 67	98.36 98	99.26 57	77.21 358	99.52 156	96.78 138	99.04 127	99.59 79

test0726					99.72 12	99.25 2	99.06 63	98.88 62	97.62 24	99.56 20	99.50 15	97.42 9

test_vis1_n_1920		96.71 135	96.84 116	96.31 269	99.11 104	89.74 340	99.05 65	98.58 149	98.08 12	99.87 1	99.37 38	78.48 346	99.93 25	99.29 14	99.69 60	99.27 129

test_fmvs3		87.17 353	87.06 356	87.50 371	91.21 392	75.66 396	99.05 65	96.61 361	92.79 272	88.85 363	92.78 388	43.72 403	93.49 394	93.95 229	84.56 371	93.34 388

v8		94.47 262	93.77 273	96.57 243	96.36 328	94.83 213	99.05 65	98.19 230	91.92 300	93.16 302	96.97 305	88.82 209	98.48 282	91.69 294	87.79 350	96.39 338

test1111		95.94 169	95.78 160	96.41 262	98.99 118	90.12 335	99.04 68	92.45 399	96.99 66	98.03 113	99.27 56	81.40 324	99.48 164	96.87 132	99.04 127	99.63 73

SF-MVS		98.59 21	98.32 40	99.41 17	99.54 35	98.71 22	99.04 68	98.81 86	95.12 156	99.32 33	99.39 32	96.22 26	99.84 67	97.72 84	99.73 52	99.67 65

PHI-MVS		98.34 53	98.06 58	99.18 42	99.15 100	98.12 57	99.04 68	99.09 31	93.32 248	98.83 66	99.10 86	96.54 21	99.83 69	97.70 89	99.76 41	99.59 79

ECVR-MVS		95.95 167	95.71 166	96.65 230	99.02 111	90.86 321	99.03 71	91.80 400	96.96 67	98.10 107	99.26 57	81.31 325	99.51 157	96.90 126	99.04 127	99.59 79

TranMVSNet+NR-MVSNet		95.14 216	94.48 223	97.11 200	96.45 325	96.36 136	99.03 71	99.03 37	95.04 162	93.58 285	97.93 218	88.27 220	98.03 331	94.13 223	86.90 363	96.95 270

ACMMP		98.23 57	97.95 63	99.09 52	99.74 7	97.62 73	99.03 71	99.41 6	95.98 109	97.60 148	99.36 42	94.45 85	99.93 25	97.14 114	98.85 139	99.70 53
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
SED-MVS		99.09 1	98.91 4	99.63 4	99.71 19	99.24 5	99.02 74	98.87 69	97.65 22	99.73 10	99.48 18	97.53 7	99.94 8	98.43 43	99.81 16	99.70 53

OPU-MVS				99.37 20	99.24 87	99.05 14	99.02 74				99.16 77	97.81 3	99.37 179	97.24 112	99.73 52	99.70 53

EIA-MVS		97.75 77	97.58 77	98.27 112	98.38 171	96.44 128	99.01 76	98.60 141	95.88 115	97.26 155	97.53 256	94.97 74	99.33 182	97.38 109	99.20 122	99.05 168

Anonymous20231211		94.10 288	93.26 297	96.61 237	99.11 104	94.28 238	99.01 76	98.88 62	86.43 373	92.81 312	97.57 253	81.66 323	98.68 266	94.83 198	89.02 339	96.88 280

test_cas_vis1_n_1920		97.38 107	97.36 93	97.45 177	98.95 121	93.25 280	99.00 78	98.53 162	97.70 20	99.77 7	99.35 44	84.71 292	99.85 63	98.57 28	99.66 65	99.26 131

mvs_tets		95.41 199	95.00 199	96.65 230	95.58 355	94.42 232	99.00 78	98.55 158	95.73 125	93.21 301	98.38 176	83.45 316	98.63 269	97.09 116	94.00 265	96.91 276

baseline		97.64 86	97.44 89	98.25 116	98.35 174	96.20 142	99.00 78	98.32 207	96.33 98	98.03 113	99.17 74	91.35 151	99.16 198	98.10 61	98.29 169	99.39 112

v10		94.29 273	93.55 286	96.51 251	96.39 327	94.80 215	98.99 81	98.19 230	91.35 317	93.02 308	96.99 303	88.09 225	98.41 298	90.50 314	88.41 345	96.33 342

PGM-MVS		98.49 35	98.23 48	99.27 34	99.72 12	98.08 58	98.99 81	99.49 5	95.43 138	99.03 47	99.32 49	95.56 48	99.94 8	96.80 137	99.77 35	99.78 21

LPG-MVS_test		95.62 187	95.34 181	96.47 255	97.46 258	93.54 264	98.99 81	98.54 160	94.67 180	94.36 251	98.77 133	85.39 275	99.11 208	95.71 172	94.15 259	96.76 291

test_fmvsmvis_n_1920		98.44 41	98.51 18	98.23 118	98.33 181	96.15 145	98.97 84	99.15 28	98.55 7	98.45 93	99.55 6	94.26 91	99.97 1	99.65 7	99.66 65	98.57 214

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 12	99.25 2	98.97 84	98.58 149	97.62 24	99.45 25	99.46 24	97.42 9	99.94 8	98.47 39	99.81 16	99.69 56
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 84	98.88 62					99.94 8	98.47 39	99.81 16	99.84 12

tfpnnormal		93.66 297	92.70 307	96.55 248	96.94 295	95.94 157	98.97 84	99.19 24	91.04 328	91.38 340	97.34 268	84.94 285	98.61 270	85.45 365	89.02 339	95.11 367

V42		94.78 238	94.14 244	96.70 227	96.33 330	95.22 192	98.97 84	98.09 255	92.32 289	94.31 254	97.06 294	88.39 218	98.55 275	92.90 261	88.87 341	96.34 340

test_fmvsm_n_1920		98.87 10	99.01 3	98.45 97	99.42 55	96.43 129	98.96 89	99.36 9	98.63 5	99.86 2	99.51 13	95.91 39	99.97 1	99.72 5	99.75 45	98.94 179

test_fmvsmconf0.01_n		97.86 72	97.54 82	98.83 69	95.48 359	96.83 108	98.95 90	98.60 141	98.58 6	98.93 58	99.55 6	88.57 212	99.91 39	99.54 11	99.61 76	99.77 27

SMA-MVS		98.58 23	98.25 44	99.56 8	99.51 39	99.04 15	98.95 90	98.80 93	93.67 233	99.37 31	99.52 11	96.52 22	99.89 47	98.06 63	99.81 16	99.76 34
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
pm-mvs1		93.94 295	93.06 299	96.59 240	96.49 323	95.16 194	98.95 90	98.03 265	92.32 289	91.08 343	97.84 227	84.54 297	98.41 298	92.16 279	86.13 369	96.19 347

Anonymous20240521		91.18 330	90.44 331	93.42 347	93.70 382	88.47 364	98.94 93	97.56 295	88.46 364	89.56 357	95.08 369	77.15 361	96.97 366	83.92 374	89.55 329	94.82 372

VPA-MVSNet		95.75 179	95.11 195	97.69 161	97.24 274	97.27 87	98.94 93	99.23 20	95.13 155	95.51 217	97.32 270	85.73 270	98.91 240	97.33 111	89.55 329	96.89 279

MM		98.51 33	98.24 46	99.33 26	99.12 102	98.14 56	98.93 95	97.02 340	98.96 1	99.17 41	99.47 20	91.97 136	99.94 8	99.85 4	99.69 60	99.91 2

LS3D		97.16 118	96.66 128	98.68 75	98.53 162	97.19 95	98.93 95	98.90 57	92.83 271	95.99 208	99.37 38	92.12 129	99.87 58	93.67 239	99.57 84	98.97 175

casdiffmvs_mvg		97.72 79	97.48 86	98.44 99	98.42 168	96.59 121	98.92 97	98.44 184	96.20 101	97.76 131	99.20 67	91.66 142	99.23 191	98.27 55	98.41 162	99.49 96
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMM	93.85 9	95.69 184	95.38 179	96.61 237	97.61 245	93.84 253	98.91 98	98.44 184	95.25 150	94.28 255	98.47 167	86.04 267	99.12 206	95.50 180	93.95 267	96.87 282
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MTAPA		98.58 23	98.29 42	99.46 14	99.76 2	98.64 25	98.90 99	98.74 108	97.27 49	98.02 115	99.39 32	94.81 77	99.96 4	97.91 72	99.79 29	99.77 27

SD-MVS		98.64 16	98.68 11	98.53 89	99.33 59	98.36 41	98.90 99	98.85 78	97.28 45	99.72 12	99.39 32	96.63 20	97.60 353	98.17 58	99.85 6	99.64 71
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TransMVSNet (Re)		92.67 317	91.51 323	96.15 274	96.58 318	94.65 219	98.90 99	96.73 354	90.86 331	89.46 358	97.86 224	85.62 272	98.09 327	86.45 357	81.12 383	95.71 357

EPNet		97.28 111	96.87 115	98.51 90	94.98 368	96.14 146	98.90 99	97.02 340	98.28 10	95.99 208	99.11 84	91.36 150	99.89 47	96.98 119	99.19 123	99.50 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 47	99.41 56	97.54 76	98.89 103	99.31 12	98.49 8	99.86 2	99.42 29	96.45 24	99.96 4	99.86 1	99.74 49	99.90 3

fmvsm_s_conf0.1_n_a		98.08 60	98.04 60	98.21 119	97.66 242	95.39 181	98.89 103	99.17 26	97.24 50	99.76 8	99.67 1	91.13 157	99.88 56	99.39 13	99.41 110	99.35 115

MTMP							98.89 103	94.14 391

UA-Net		97.96 67	97.62 75	98.98 59	98.86 129	97.47 80	98.89 103	99.08 32	96.67 82	98.72 76	99.54 8	93.15 104	99.81 81	94.87 196	98.83 140	99.65 69

OurMVSNet-221017-0		94.21 277	94.00 254	94.85 323	95.60 354	89.22 350	98.89 103	97.43 314	95.29 147	92.18 331	98.52 164	82.86 317	98.59 273	93.46 244	91.76 300	96.74 294

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 51	99.43 54	97.48 78	98.88 108	99.30 13	98.47 9	99.85 4	99.43 28	96.71 17	99.96 4	99.86 1	99.80 23	99.89 5

thisisatest0530		96.01 164	95.36 180	97.97 139	98.38 171	95.52 176	98.88 108	94.19 390	94.04 202	97.64 145	98.31 186	83.82 314	99.46 168	95.29 186	97.70 188	98.93 180

MVS_0304		98.47 38	98.22 50	99.21 39	99.00 114	97.80 69	98.88 108	95.32 377	98.86 2	98.53 88	99.44 27	94.38 87	99.94 8	99.86 1	99.70 58	99.90 3

UGNet		96.78 133	96.30 142	98.19 123	98.24 189	95.89 164	98.88 108	98.93 50	97.39 38	96.81 177	97.84 227	82.60 319	99.90 45	96.53 143	99.49 100	98.79 190
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
fmvsm_s_conf0.1_n		98.18 59	98.21 51	98.11 131	98.54 161	95.24 191	98.87 112	99.24 17	97.50 31	99.70 13	99.67 1	91.33 152	99.89 47	99.47 12	99.54 93	99.21 138

Anonymous20240529		95.10 218	94.22 237	97.75 155	99.01 113	94.26 240	98.87 112	98.83 80	85.79 379	96.64 182	98.97 105	78.73 343	99.85 63	96.27 150	94.89 250	99.12 155

thres100view900		95.38 200	94.70 213	97.41 181	98.98 119	94.92 208	98.87 112	96.90 347	95.38 141	96.61 185	96.88 313	84.29 299	99.56 145	88.11 346	96.29 227	97.76 240

fmvsm_s_conf0.5_n_a		98.38 47	98.42 25	98.27 112	99.09 106	95.41 180	98.86 115	99.37 8	97.69 21	99.78 6	99.61 4	92.38 118	99.91 39	99.58 10	99.43 108	99.49 96

XXY-MVS		95.20 213	94.45 227	97.46 175	96.75 308	96.56 123	98.86 115	98.65 135	93.30 250	93.27 299	98.27 191	84.85 287	98.87 247	94.82 199	91.26 308	96.96 268

fmvsm_s_conf0.5_n		98.42 44	98.51 18	98.13 127	99.30 68	95.25 190	98.85 117	99.39 7	97.94 14	99.74 9	99.62 3	92.59 115	99.91 39	99.65 7	99.52 96	99.25 133

VDDNet		95.36 203	94.53 220	97.86 144	98.10 206	95.13 197	98.85 117	97.75 283	90.46 336	98.36 98	99.39 32	73.27 379	99.64 131	97.98 66	96.58 215	98.81 189

thres600view7		95.49 191	94.77 209	97.67 164	98.98 119	95.02 200	98.85 117	96.90 347	95.38 141	96.63 183	96.90 312	84.29 299	99.59 140	88.65 343	96.33 223	98.40 220

114514_t		96.93 126	96.27 143	98.92 64	99.50 41	97.63 72	98.85 117	98.90 57	84.80 383	97.77 130	99.11 84	92.84 111	99.66 128	94.85 197	99.77 35	99.47 100

test_fmvsmconf0.1_n		98.58 23	98.44 24	98.99 57	97.73 236	97.15 97	98.84 121	98.97 42	98.75 3	99.43 27	99.54 8	93.29 102	99.93 25	99.64 9	99.79 29	99.89 5

LFMVS		95.86 174	94.98 201	98.47 95	98.87 128	96.32 138	98.84 121	96.02 367	93.40 245	98.62 83	99.20 67	74.99 371	99.63 134	97.72 84	97.20 198	99.46 104

alignmvs		97.56 95	97.07 107	99.01 56	98.66 149	98.37 40	98.83 123	98.06 263	96.74 78	98.00 119	97.65 245	90.80 165	99.48 164	98.37 47	96.56 216	99.19 143

DeepC-MVS	95.98 3	97.88 71	97.58 77	98.77 71	99.25 81	96.93 103	98.83 123	98.75 106	96.96 67	96.89 173	99.50 15	90.46 171	99.87 58	97.84 78	99.76 41	99.52 86
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf_n		98.92 7	98.87 6	99.04 55	98.88 126	97.25 92	98.82 125	99.34 10	98.75 3	99.80 5	99.61 4	95.16 68	99.95 7	99.70 6	99.80 23	99.93 1

sd_testset		96.17 159	95.76 161	97.42 180	99.30 68	94.34 237	98.82 125	99.08 32	95.92 111	95.96 210	98.76 137	82.83 318	99.32 183	95.56 177	95.59 245	98.60 209

ACMMP_NAP		98.61 18	98.30 41	99.55 9	99.62 30	98.95 17	98.82 125	98.81 86	95.80 119	99.16 44	99.47 20	95.37 56	99.92 31	97.89 74	99.75 45	99.79 19

casdiffmvs		97.63 87	97.41 90	98.28 111	98.33 181	96.14 146	98.82 125	98.32 207	96.38 96	97.95 121	99.21 65	91.23 156	99.23 191	98.12 60	98.37 163	99.48 98
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		94.49 259	93.80 270	96.56 244	98.21 193	95.00 201	98.82 125	98.18 233	92.46 280	94.09 265	97.07 290	81.16 326	97.95 337	92.08 281	92.14 295	96.72 297

test1		94.49 259	93.80 270	96.56 244	98.21 193	95.00 201	98.82 125	98.18 233	92.46 280	94.09 265	97.07 290	81.16 326	97.95 337	92.08 281	92.14 295	96.72 297

FMVSNet1		93.19 310	92.07 317	96.56 244	97.54 252	95.00 201	98.82 125	98.18 233	90.38 339	92.27 329	97.07 290	73.68 378	97.95 337	89.36 335	91.30 306	96.72 297

API-MVS		97.41 105	97.25 97	97.91 142	98.70 143	96.80 109	98.82 125	98.69 120	94.53 186	98.11 106	98.28 188	94.50 84	99.57 142	94.12 224	99.49 100	97.37 256

ACMH	92.88 16	94.55 252	93.95 258	96.34 267	97.63 244	93.26 279	98.81 133	98.49 178	93.43 244	89.74 354	98.53 161	81.91 321	99.08 214	93.69 236	93.30 284	96.70 301
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvs1		96.42 148	96.67 127	95.66 295	98.82 133	88.53 363	98.80 134	98.20 228	96.39 95	99.64 17	99.20 67	80.35 335	99.67 126	99.04 17	99.57 84	98.78 193

Effi-MVS+-dtu		96.29 154	96.56 130	95.51 300	97.89 225	90.22 334	98.80 134	98.10 251	96.57 87	96.45 196	96.66 324	90.81 164	98.91 240	95.72 171	97.99 175	97.40 253

HQP_MVS		96.14 161	95.90 157	96.85 218	97.42 263	94.60 226	98.80 134	98.56 155	97.28 45	95.34 219	98.28 188	87.09 246	99.03 220	96.07 155	94.27 253	96.92 271

plane_prior2							98.80 134		97.28 45

APD-MVS		98.35 52	98.00 62	99.42 16	99.51 39	98.72 21	98.80 134	98.82 81	94.52 188	99.23 37	99.25 61	95.54 50	99.80 88	96.52 144	99.77 35	99.74 37
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
UniMVSNet (Re)		95.78 178	95.19 190	97.58 171	96.99 292	97.47 80	98.79 139	99.18 25	95.60 130	93.92 273	97.04 297	91.68 140	98.48 282	95.80 168	87.66 352	96.79 288

FMVSNet2		94.47 262	93.61 283	97.04 204	98.21 193	96.43 129	98.79 139	98.27 218	92.46 280	93.50 291	97.09 287	81.16 326	98.00 334	91.09 303	91.93 298	96.70 301

tt0805		94.54 253	93.85 267	96.63 234	97.98 217	93.06 288	98.77 141	97.84 279	93.67 233	93.80 280	98.04 208	76.88 363	98.96 231	94.79 201	92.86 289	97.86 239

testgi		93.06 313	92.45 313	94.88 322	96.43 326	89.90 337	98.75 142	97.54 301	95.60 130	91.63 339	97.91 219	74.46 375	97.02 365	86.10 359	93.67 272	97.72 244

LCM-MVSNet-Re		95.22 211	95.32 184	94.91 319	98.18 199	87.85 373	98.75 142	95.66 374	95.11 157	88.96 360	96.85 316	90.26 176	97.65 351	95.65 175	98.44 159	99.22 137

SixPastTwentyTwo		93.34 304	92.86 303	94.75 327	95.67 352	89.41 348	98.75 142	96.67 358	93.89 212	90.15 352	98.25 194	80.87 330	98.27 316	90.90 309	90.64 314	96.57 316

UniMVSNet_ETH3D		94.24 276	93.33 294	96.97 209	97.19 281	93.38 274	98.74 145	98.57 151	91.21 326	93.81 279	98.58 157	72.85 380	98.77 259	95.05 193	93.93 268	98.77 195

MVS_Test		97.28 111	97.00 109	98.13 127	98.33 181	95.97 154	98.74 145	98.07 258	94.27 196	98.44 95	98.07 205	92.48 116	99.26 187	96.43 147	98.19 170	99.16 150

UniMVSNet_NR-MVSNet		95.71 181	95.15 191	97.40 183	96.84 302	96.97 101	98.74 145	99.24 17	95.16 154	93.88 275	97.72 238	91.68 140	98.31 309	95.81 166	87.25 358	96.92 271

NR-MVSNet		94.98 227	94.16 242	97.44 178	96.53 320	97.22 94	98.74 145	98.95 46	94.96 167	89.25 359	97.69 241	89.32 191	98.18 319	94.59 209	87.40 355	96.92 271

MVSMamba_pp		98.02 64	97.82 66	98.61 80	98.25 188	97.32 84	98.73 149	98.56 155	96.18 103	98.84 63	98.72 140	92.90 110	99.45 170	98.37 47	99.85 6	99.07 166

ETV-MVS		97.96 67	97.81 67	98.40 104	98.42 168	97.27 87	98.73 149	98.55 158	96.84 71	98.38 97	97.44 262	95.39 54	99.35 180	97.62 93	98.89 135	98.58 213

baseline1		95.84 175	95.12 194	98.01 137	98.49 165	95.98 149	98.73 149	97.03 338	95.37 143	96.22 201	98.19 198	89.96 179	99.16 198	94.60 207	87.48 353	98.90 182

MVSTER		96.06 163	95.72 163	97.08 202	98.23 191	95.93 160	98.73 149	98.27 218	94.86 172	95.07 226	98.09 204	88.21 221	98.54 278	96.59 141	93.46 278	96.79 288

ACMP	93.49 10	95.34 205	94.98 201	96.43 260	97.67 240	93.48 268	98.73 149	98.44 184	94.94 170	92.53 322	98.53 161	84.50 298	99.14 203	95.48 181	94.00 265	96.66 307
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
mamv4		97.97 65	97.75 70	98.63 79	98.28 187	97.36 83	98.72 154	98.57 151	95.76 121	98.76 71	98.70 142	92.91 109	99.45 170	98.24 57	99.84 13	99.07 166

HPM-MVS++		98.58 23	98.25 44	99.55 9	99.50 41	99.08 11	98.72 154	98.66 131	97.51 30	98.15 104	98.83 125	95.70 45	99.92 31	97.53 102	99.67 63	99.66 68

9.14			98.06 58		99.47 47		98.71 156	98.82 81	94.36 194	99.16 44	99.29 53	96.05 33	99.81 81	97.00 118	99.71 57

VPNet		94.99 225	94.19 239	97.40 183	97.16 283	96.57 122	98.71 156	98.97 42	95.67 128	94.84 231	98.24 195	80.36 334	98.67 267	96.46 145	87.32 357	96.96 268

MSLP-MVS++		98.56 29	98.57 15	98.55 85	99.26 80	96.80 109	98.71 156	99.05 36	97.28 45	98.84 63	99.28 54	96.47 23	99.40 175	98.52 37	99.70 58	99.47 100

ACMH+	92.99 14	94.30 271	93.77 273	95.88 288	97.81 229	92.04 301	98.71 156	98.37 200	93.99 207	90.60 348	98.47 167	80.86 331	99.05 216	92.75 265	92.40 294	96.55 320

Anonymous202405211		95.28 208	94.49 222	97.67 164	99.00 114	93.75 257	98.70 160	97.04 337	90.66 332	96.49 193	98.80 128	78.13 350	99.83 69	96.21 154	95.36 249	99.44 107

iter_conf05		96.47 146	96.48 135	96.43 260	96.72 310	93.98 248	98.70 160	97.88 276	95.76 121	95.84 213	98.67 148	93.01 105	98.55 275	97.71 88	94.02 264	96.76 291

DP-MVS		96.59 139	95.93 156	98.57 83	99.34 57	96.19 144	98.70 160	98.39 194	89.45 355	94.52 240	99.35 44	91.85 137	99.85 63	92.89 263	98.88 136	99.68 61

Fast-Effi-MVS+-dtu		95.87 173	95.85 158	95.91 285	97.74 235	91.74 306	98.69 163	98.15 241	95.56 132	94.92 229	97.68 244	88.98 204	98.79 257	93.19 251	97.78 184	97.20 260

tfpn200view9		95.32 207	94.62 216	97.43 179	98.94 122	94.98 204	98.68 164	96.93 345	95.33 144	96.55 189	96.53 330	84.23 303	99.56 145	88.11 346	96.29 227	97.76 240

VDD-MVS		95.82 177	95.23 188	97.61 170	98.84 132	93.98 248	98.68 164	97.40 316	95.02 163	97.95 121	99.34 48	74.37 376	99.78 101	98.64 25	96.80 208	99.08 162

thres400		95.38 200	94.62 216	97.65 168	98.94 122	94.98 204	98.68 164	96.93 345	95.33 144	96.55 189	96.53 330	84.23 303	99.56 145	88.11 346	96.29 227	98.40 220

pmmvs6		91.77 324	90.63 329	95.17 312	94.69 375	91.24 315	98.67 167	97.92 274	86.14 375	89.62 355	97.56 255	75.79 368	98.34 305	90.75 311	84.56 371	95.94 353

v2v482		94.69 240	94.03 250	96.65 230	96.17 335	94.79 216	98.67 167	98.08 256	92.72 273	94.00 270	97.16 281	87.69 238	98.45 287	92.91 260	88.87 341	96.72 297

DU-MVS		95.42 197	94.76 210	97.40 183	96.53 320	96.97 101	98.66 169	98.99 41	95.43 138	93.88 275	97.69 241	88.57 212	98.31 309	95.81 166	87.25 358	96.92 271

MAR-MVS		96.91 127	96.40 138	98.45 97	98.69 146	96.90 105	98.66 169	98.68 123	92.40 286	97.07 163	97.96 216	91.54 147	99.75 109	93.68 237	98.92 133	98.69 200
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
testing3		93.19 310	92.48 312	95.30 309	98.07 207	92.27 294	98.64 171	97.17 328	93.94 211	93.98 271	97.04 297	67.97 387	96.01 382	88.40 344	97.14 199	97.63 247

patch_mono-2		98.36 50	98.87 6	96.82 220	99.53 36	90.68 326	98.64 171	99.29 14	97.88 15	99.19 40	99.52 11	96.80 15	99.97 1	99.11 16	99.86 1	99.82 16

h-mvs33		96.17 159	95.62 172	97.81 149	99.03 110	94.45 230	98.64 171	98.75 106	97.48 32	98.67 77	98.72 140	89.76 181	99.86 62	97.95 68	81.59 381	99.11 156

VNet		97.79 76	97.40 91	98.96 62	98.88 126	97.55 75	98.63 174	98.93 50	96.74 78	99.02 48	98.84 123	90.33 174	99.83 69	98.53 31	96.66 212	99.50 91

PVSNet_Blended_VisFu		97.70 81	97.46 87	98.44 99	99.27 78	95.91 162	98.63 174	99.16 27	94.48 190	97.67 140	98.88 119	92.80 112	99.91 39	97.11 115	99.12 125	99.50 91

PAPM_NR		97.46 98	97.11 104	98.50 91	99.50 41	96.41 132	98.63 174	98.60 141	95.18 153	97.06 164	98.06 206	94.26 91	99.57 142	93.80 235	98.87 138	99.52 86

Baseline_NR-MVSNet		94.35 268	93.81 269	95.96 283	96.20 333	94.05 246	98.61 177	96.67 358	91.44 313	93.85 277	97.60 250	88.57 212	98.14 322	94.39 213	86.93 361	95.68 358

v1144		94.59 250	93.92 259	96.60 239	96.21 332	94.78 217	98.59 178	98.14 243	91.86 303	94.21 260	97.02 300	87.97 229	98.41 298	91.72 293	89.57 327	96.61 311

AllTest		95.24 210	94.65 215	96.99 206	99.25 81	93.21 282	98.59 178	98.18 233	91.36 315	93.52 288	98.77 133	84.67 293	99.72 113	89.70 328	97.87 180	98.02 235

Fast-Effi-MVS+		96.28 156	95.70 168	98.03 136	98.29 186	95.97 154	98.58 180	98.25 223	91.74 304	95.29 223	97.23 277	91.03 162	99.15 201	92.90 261	97.96 177	98.97 175

Anonymous20231206		91.66 325	91.10 325	93.33 350	94.02 381	87.35 375	98.58 180	97.26 324	90.48 335	90.16 351	96.31 335	83.83 313	96.53 376	79.36 387	89.90 323	96.12 348

v144192		94.39 267	93.70 279	96.48 254	96.06 340	94.35 236	98.58 180	98.16 240	91.45 312	94.33 253	97.02 300	87.50 241	98.45 287	91.08 304	89.11 336	96.63 309

v148		94.29 273	93.76 275	95.91 285	96.10 338	92.93 289	98.58 180	97.97 269	92.59 278	93.47 292	96.95 309	88.53 216	98.32 307	92.56 271	87.06 360	96.49 332

COLMAP_ROB	93.27 12	95.33 206	94.87 207	96.71 225	99.29 73	93.24 281	98.58 180	98.11 248	89.92 346	93.57 286	99.10 86	86.37 260	99.79 98	90.78 310	98.10 173	97.09 261
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_vis1_rt		91.29 328	90.65 328	93.19 354	97.45 261	86.25 379	98.57 185	90.90 404	93.30 250	86.94 373	93.59 382	62.07 396	99.11 208	97.48 105	95.58 247	94.22 377

FMVSNet3		94.97 229	94.26 235	97.11 200	98.18 199	96.62 116	98.56 186	98.26 222	93.67 233	94.09 265	97.10 283	84.25 301	98.01 332	92.08 281	92.14 295	96.70 301

F-COLMAP		97.09 122	96.80 117	97.97 139	99.45 52	94.95 207	98.55 187	98.62 140	93.02 263	96.17 203	98.58 157	94.01 95	99.81 81	93.95 229	98.90 134	99.14 153

dmvs_re		94.48 261	94.18 241	95.37 306	97.68 239	90.11 336	98.54 188	97.08 332	94.56 184	94.42 248	97.24 276	84.25 301	97.76 349	91.02 308	92.83 290	98.24 227

v1921920		94.20 278	93.47 290	96.40 264	95.98 343	94.08 245	98.52 189	98.15 241	91.33 318	94.25 257	97.20 280	86.41 259	98.42 291	90.04 322	89.39 333	96.69 306

EU-MVSNet		93.66 297	94.14 244	92.25 362	95.96 345	83.38 386	98.52 189	98.12 245	94.69 178	92.61 319	98.13 202	87.36 244	96.39 378	91.82 290	90.00 322	96.98 266

TAMVS		97.02 123	96.79 119	97.70 160	98.06 210	95.31 188	98.52 189	98.31 209	93.95 209	97.05 165	98.61 152	93.49 100	98.52 280	95.33 183	97.81 182	99.29 127

LTVRE_ROB	92.95 15	94.60 248	93.90 262	96.68 229	97.41 266	94.42 232	98.52 189	98.59 144	91.69 307	91.21 341	98.35 179	84.87 286	99.04 219	91.06 305	93.44 281	96.60 312
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
TDRefinement		91.06 332	89.68 337	95.21 310	85.35 406	91.49 311	98.51 193	97.07 334	91.47 311	88.83 364	97.84 227	77.31 357	99.09 213	92.79 264	77.98 394	95.04 369

v1192		94.32 270	93.58 284	96.53 249	96.10 338	94.45 230	98.50 194	98.17 238	91.54 310	94.19 261	97.06 294	86.95 250	98.43 290	90.14 317	89.57 327	96.70 301

test_0402		91.32 327	90.27 333	94.48 336	96.60 316	91.12 316	98.50 194	97.22 326	86.10 376	88.30 366	96.98 304	77.65 355	97.99 335	78.13 391	92.94 288	94.34 374

DeepC-MVS_fast	96.70 1	98.55 30	98.34 35	99.18 42	99.25 81	98.04 59	98.50 194	98.78 100	97.72 17	98.92 60	99.28 54	95.27 62	99.82 76	97.55 100	99.77 35	99.69 56
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CNVR-MVS		98.78 11	98.56 16	99.45 15	99.32 62	98.87 19	98.47 197	98.81 86	97.72 17	98.76 71	99.16 77	97.05 13	99.78 101	98.06 63	99.66 65	99.69 56

test_yl		97.22 113	96.78 120	98.54 87	98.73 138	96.60 119	98.45 198	98.31 209	94.70 176	98.02 115	98.42 171	90.80 165	99.70 119	96.81 135	96.79 209	99.34 116

DCV-MVSNet		97.22 113	96.78 120	98.54 87	98.73 138	96.60 119	98.45 198	98.31 209	94.70 176	98.02 115	98.42 171	90.80 165	99.70 119	96.81 135	96.79 209	99.34 116

NCCC		98.61 18	98.35 32	99.38 18	99.28 77	98.61 26	98.45 198	98.76 104	97.82 16	98.45 93	98.93 114	96.65 19	99.83 69	97.38 109	99.41 110	99.71 49

v1240		94.06 292	93.29 296	96.34 267	96.03 342	93.90 251	98.44 201	98.17 238	91.18 327	94.13 264	97.01 302	86.05 265	98.42 291	89.13 338	89.50 331	96.70 301

plane_prior						94.60 226	98.44 201		96.74 78						94.22 255

MP-MVS-pluss		98.31 56	97.92 65	99.49 12	99.72 12	98.88 18	98.43 203	98.78 100	94.10 200	97.69 139	99.42 29	95.25 64	99.92 31	98.09 62	99.80 23	99.67 65
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
OPM-MVS		95.69 184	95.33 183	96.76 223	96.16 337	94.63 221	98.43 203	98.39 194	96.64 83	95.02 228	98.78 131	85.15 282	99.05 216	95.21 190	94.20 256	96.60 312
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DPE-MVS		98.92 7	98.67 12	99.65 2	99.58 32	99.20 9	98.42 205	98.91 56	97.58 27	99.54 22	99.46 24	97.10 12	99.94 8	97.64 92	99.84 13	99.83 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MCST-MVS		98.65 15	98.37 29	99.48 13	99.60 31	98.87 19	98.41 206	98.68 123	97.04 63	98.52 89	98.80 128	96.78 16	99.83 69	97.93 70	99.61 76	99.74 37

hse-mvs2		95.71 181	95.30 186	96.93 212	98.50 163	93.53 266	98.36 207	98.10 251	97.48 32	98.67 77	97.99 213	89.76 181	99.02 223	97.95 68	80.91 386	98.22 229

CANet		98.05 62	97.76 69	98.90 67	98.73 138	97.27 87	98.35 208	98.78 100	97.37 41	97.72 137	98.96 110	91.53 148	99.92 31	98.79 23	99.65 68	99.51 89

AUN-MVS		94.53 255	93.73 277	96.92 215	98.50 163	93.52 267	98.34 209	98.10 251	93.83 217	95.94 212	97.98 215	85.59 273	99.03 220	94.35 215	80.94 385	98.22 229

test20.03		90.89 334	90.38 332	92.43 358	93.48 383	88.14 370	98.33 210	97.56 295	93.40 245	87.96 367	96.71 323	80.69 333	94.13 393	79.15 388	86.17 367	95.01 371

DP-MVS Recon		97.86 72	97.46 87	99.06 54	99.53 36	98.35 42	98.33 210	98.89 59	92.62 276	98.05 110	98.94 113	95.34 58	99.65 129	96.04 159	99.42 109	99.19 143

RPSCF		94.87 234	95.40 175	93.26 352	98.89 125	82.06 390	98.33 210	98.06 263	90.30 341	96.56 187	99.26 57	87.09 246	99.49 159	93.82 234	96.32 224	98.24 227

TAPA-MVS	93.98 7	95.35 204	94.56 219	97.74 156	99.13 101	94.83 213	98.33 210	98.64 136	86.62 371	96.29 200	98.61 152	94.00 96	99.29 185	80.00 385	99.41 110	99.09 158
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IterMVS-LS		95.46 193	95.21 189	96.22 273	98.12 204	93.72 260	98.32 214	98.13 244	93.71 226	94.26 256	97.31 271	92.24 124	98.10 325	94.63 204	90.12 320	96.84 285
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_anonymous		96.70 136	96.53 133	97.18 194	98.19 197	93.78 254	98.31 215	98.19 230	94.01 205	94.47 242	98.27 191	92.08 132	98.46 286	97.39 108	97.91 178	99.31 122

WTY-MVS		97.37 109	96.92 113	98.72 73	98.86 129	96.89 107	98.31 215	98.71 116	95.26 149	97.67 140	98.56 160	92.21 126	99.78 101	95.89 163	96.85 207	99.48 98

D2MVS		95.18 214	95.08 196	95.48 301	97.10 287	92.07 299	98.30 217	99.13 30	94.02 204	92.90 310	96.73 321	89.48 186	98.73 261	94.48 212	93.60 277	95.65 359

EI-MVSNet-Vis-set		98.47 38	98.39 27	98.69 74	99.46 49	96.49 126	98.30 217	98.69 120	97.21 52	98.84 63	99.36 42	95.41 53	99.78 101	98.62 26	99.65 68	99.80 18

DSMNet-mixed		92.52 320	92.58 310	92.33 360	94.15 377	82.65 388	98.30 217	94.26 389	89.08 360	92.65 318	95.73 356	85.01 284	95.76 384	86.24 358	97.76 185	98.59 211

EI-MVSNet-UG-set		98.41 45	98.34 35	98.61 80	99.45 52	96.32 138	98.28 220	98.68 123	97.17 55	98.74 73	99.37 38	95.25 64	99.79 98	98.57 28	99.54 93	99.73 42

OMC-MVS		97.55 96	97.34 94	98.20 121	99.33 59	95.92 161	98.28 220	98.59 144	95.52 134	97.97 120	99.10 86	93.28 103	99.49 159	95.09 191	98.88 136	99.19 143

baseline2		95.11 217	94.52 221	96.87 217	96.65 315	93.56 263	98.27 222	94.10 392	93.45 243	92.02 335	97.43 263	87.45 243	99.19 196	93.88 232	97.41 196	97.87 238

PVSNet_BlendedMVS		96.73 134	96.60 129	97.12 199	99.25 81	95.35 185	98.26 223	99.26 15	94.28 195	97.94 123	97.46 259	92.74 113	99.81 81	96.88 129	93.32 283	96.20 346

BH-untuned		95.95 167	95.72 163	96.65 230	98.55 160	92.26 295	98.23 224	97.79 281	93.73 223	94.62 237	98.01 211	88.97 205	99.00 226	93.04 256	98.51 155	98.68 201

sss		97.39 106	96.98 111	98.61 80	98.60 156	96.61 118	98.22 225	98.93 50	93.97 208	98.01 118	98.48 166	91.98 134	99.85 63	96.45 146	98.15 171	99.39 112

save fliter					99.46 49	98.38 35	98.21 226	98.71 116	97.95 13

WR-MVS		95.15 215	94.46 225	97.22 190	96.67 314	96.45 127	98.21 226	98.81 86	94.15 198	93.16 302	97.69 241	87.51 239	98.30 311	95.29 186	88.62 343	96.90 278

pmmvs5		93.65 299	92.97 302	95.68 294	95.49 358	92.37 293	98.20 228	97.28 322	89.66 351	92.58 320	97.26 273	82.14 320	98.09 327	93.18 252	90.95 312	96.58 314

thres200		95.25 209	94.57 218	97.28 188	98.81 134	94.92 208	98.20 228	97.11 330	95.24 152	96.54 191	96.22 341	84.58 296	99.53 153	87.93 350	96.50 219	97.39 254

CDS-MVSNet		96.99 124	96.69 125	97.90 143	98.05 211	95.98 149	98.20 228	98.33 206	93.67 233	96.95 167	98.49 165	93.54 99	98.42 291	95.24 189	97.74 186	99.31 122
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ETVMVS		94.50 258	93.44 291	97.68 163	98.18 199	95.35 185	98.19 231	97.11 330	93.73 223	96.40 197	95.39 363	74.53 373	98.84 250	91.10 302	96.31 225	98.84 187

WB-MVS		84.86 358	85.33 359	83.46 379	89.48 397	69.56 405	98.19 231	96.42 364	89.55 353	81.79 389	94.67 372	84.80 288	90.12 401	52.44 405	80.64 387	90.69 392

1314		96.25 158	95.73 162	97.79 150	97.13 285	95.55 175	98.19 231	98.59 144	93.47 242	92.03 334	97.82 231	91.33 152	99.49 159	94.62 206	98.44 159	98.32 226

MVS		94.67 245	93.54 287	98.08 133	96.88 300	96.56 123	98.19 231	98.50 173	78.05 394	92.69 317	98.02 209	91.07 161	99.63 134	90.09 318	98.36 165	98.04 234

BH-RMVSNet		95.92 171	95.32 184	97.69 161	98.32 184	94.64 220	98.19 231	97.45 312	94.56 184	96.03 206	98.61 152	85.02 283	99.12 206	90.68 312	99.06 126	99.30 125

1112_ss		96.63 137	96.00 153	98.50 91	98.56 158	96.37 135	98.18 236	98.10 251	92.92 267	94.84 231	98.43 169	92.14 128	99.58 141	94.35 215	96.51 218	99.56 85

EPNet_dtu		95.21 212	94.95 203	95.99 280	96.17 335	90.45 330	98.16 237	97.27 323	96.77 75	93.14 305	98.33 184	90.34 173	98.42 291	85.57 363	98.81 142	99.09 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HY-MVS	93.96 8	96.82 132	96.23 146	98.57 83	98.46 166	97.00 100	98.14 238	98.21 226	93.95 209	96.72 180	97.99 213	91.58 143	99.76 107	94.51 211	96.54 217	98.95 178

PLC	95.07 4	97.20 116	96.78 120	98.44 99	99.29 73	96.31 140	98.14 238	98.76 104	92.41 285	96.39 198	98.31 186	94.92 76	99.78 101	94.06 227	98.77 143	99.23 135
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EG-PatchMatch MVS		91.13 331	90.12 334	94.17 343	94.73 374	89.00 354	98.13 240	97.81 280	89.22 359	85.32 384	96.46 332	67.71 388	98.42 291	87.89 351	93.82 270	95.08 368

EI-MVSNet		95.96 166	95.83 159	96.36 265	97.93 222	93.70 261	98.12 241	98.27 218	93.70 228	95.07 226	99.02 98	92.23 125	98.54 278	94.68 202	93.46 278	96.84 285

CVMVSNet		95.43 196	96.04 151	93.57 346	97.93 222	83.62 384	98.12 241	98.59 144	95.68 127	96.56 187	99.02 98	87.51 239	97.51 358	93.56 243	97.44 194	99.60 77

TSAR-MVS + GP.		98.38 47	98.24 46	98.81 70	99.22 89	97.25 92	98.11 243	98.29 217	97.19 54	98.99 52	99.02 98	96.22 26	99.67 126	98.52 37	98.56 153	99.51 89

XVG-ACMP-BASELINE		94.54 253	94.14 244	95.75 293	96.55 319	91.65 308	98.11 243	98.44 184	94.96 167	94.22 259	97.90 220	79.18 342	99.11 208	94.05 228	93.85 269	96.48 334

testing99		94.83 235	94.08 247	97.07 203	97.94 220	93.13 284	98.10 245	97.17 328	94.86 172	95.34 219	96.00 350	76.31 365	99.40 175	95.08 192	95.90 241	98.68 201

testing11		95.00 223	94.28 234	97.16 196	97.96 219	93.36 276	98.09 246	97.06 336	94.94 170	95.33 222	96.15 343	76.89 362	99.40 175	95.77 170	96.30 226	98.72 196

SSC-MVS		84.27 359	84.71 362	82.96 383	89.19 399	68.83 406	98.08 247	96.30 366	89.04 361	81.37 391	94.47 373	84.60 295	89.89 402	49.80 407	79.52 389	90.15 393

CNLPA		97.45 101	97.03 108	98.73 72	99.05 108	97.44 82	98.07 248	98.53 162	95.32 146	96.80 178	98.53 161	93.32 101	99.72 113	94.31 218	99.31 119	99.02 170

diffmvs		97.58 93	97.40 91	98.13 127	98.32 184	95.81 167	98.06 249	98.37 200	96.20 101	98.74 73	98.89 118	91.31 154	99.25 188	98.16 59	98.52 154	99.34 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CHOSEN 1792x2688		97.12 120	96.80 117	98.08 133	99.30 68	94.56 228	98.05 250	99.71 1	93.57 238	97.09 160	98.91 117	88.17 222	99.89 47	96.87 132	99.56 90	99.81 17

HQP-NCC					97.20 278		98.05 250		96.43 91	94.45 243

ACMP_Plane					97.20 278		98.05 250		96.43 91	94.45 243

HQP-MVS		95.72 180	95.40 175	96.69 228	97.20 278	94.25 241	98.05 250	98.46 180	96.43 91	94.45 243	97.73 236	86.75 252	98.96 231	95.30 184	94.18 257	96.86 284

MIMVSNet1		89.67 343	88.28 348	93.82 344	92.81 387	91.08 317	98.01 254	97.45 312	87.95 366	87.90 368	95.87 352	67.63 389	94.56 392	78.73 390	88.18 347	95.83 355

AdaColmap		97.15 119	96.70 124	98.48 94	99.16 98	96.69 115	98.01 254	98.89 59	94.44 192	96.83 174	98.68 145	90.69 168	99.76 107	94.36 214	99.29 120	98.98 174

testing91		94.98 227	94.25 236	97.20 191	97.94 220	93.41 271	98.00 256	97.58 292	94.99 164	95.45 218	96.04 347	77.20 359	99.42 174	94.97 195	96.02 240	98.78 193

FMVSNet5		91.81 323	90.92 326	94.49 335	97.21 277	92.09 298	98.00 256	97.55 300	89.31 358	90.86 345	95.61 361	74.48 374	95.32 388	85.57 363	89.70 325	96.07 350

CANet_DTU		96.96 125	96.55 131	98.21 119	98.17 202	96.07 148	97.98 258	98.21 226	97.24 50	97.13 159	98.93 114	86.88 251	99.91 39	95.00 194	99.37 116	98.66 205

MVP-Stereo		94.28 275	93.92 259	95.35 307	94.95 369	92.60 292	97.97 259	97.65 287	91.61 309	90.68 347	97.09 287	86.32 261	98.42 291	89.70 328	99.34 117	95.02 370
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
KD-MVS_self_test		90.38 337	89.38 340	93.40 349	92.85 386	88.94 357	97.95 260	97.94 272	90.35 340	90.25 350	93.96 379	79.82 337	95.94 383	84.62 373	76.69 396	95.33 362

MVS_111021_LR		98.34 53	98.23 48	98.67 76	99.27 78	96.90 105	97.95 260	99.58 3	97.14 58	98.44 95	99.01 102	95.03 73	99.62 137	97.91 72	99.75 45	99.50 91

testing222		94.12 286	93.03 300	97.37 186	98.02 212	94.66 218	97.94 262	96.65 360	94.63 182	95.78 214	95.76 353	71.49 381	98.92 238	91.17 301	95.88 242	98.52 215

TEST9					99.31 64	98.50 29	97.92 263	98.73 111	92.63 275	97.74 134	98.68 145	96.20 28	99.80 88

train_agg		97.97 65	97.52 83	99.33 26	99.31 64	98.50 29	97.92 263	98.73 111	92.98 264	97.74 134	98.68 145	96.20 28	99.80 88	96.59 141	99.57 84	99.68 61

Syy-MVS		92.55 318	92.61 309	92.38 359	97.39 267	83.41 385	97.91 265	97.46 308	93.16 256	93.42 294	95.37 364	84.75 290	96.12 380	77.00 393	96.99 202	97.60 248

myMVS_eth3d		92.73 316	92.01 318	94.89 321	97.39 267	90.94 319	97.91 265	97.46 308	93.16 256	93.42 294	95.37 364	68.09 386	96.12 380	88.34 345	96.99 202	97.60 248

CDPH-MVS		97.94 69	97.49 84	99.28 32	99.47 47	98.44 31	97.91 265	98.67 128	92.57 279	98.77 70	98.85 122	95.93 38	99.72 113	95.56 177	99.69 60	99.68 61

MVS_111021_HR		98.47 38	98.34 35	98.88 68	99.22 89	97.32 84	97.91 265	99.58 3	97.20 53	98.33 101	99.00 103	95.99 36	99.64 131	98.05 65	99.76 41	99.69 56

PatchMatch-RL		96.59 139	96.03 152	98.27 112	99.31 64	96.51 125	97.91 265	99.06 34	93.72 225	96.92 171	98.06 206	88.50 217	99.65 129	91.77 292	99.00 131	98.66 205

OpenMVS_ROB	86.42 20	89.00 347	87.43 355	93.69 345	93.08 385	89.42 347	97.91 265	96.89 349	78.58 393	85.86 379	94.69 371	69.48 384	98.29 314	77.13 392	93.29 285	93.36 387

test_8					99.29 73	98.44 31	97.89 271	98.72 113	92.98 264	97.70 138	98.66 149	96.20 28	99.80 88

ab-mvs		96.42 148	95.71 166	98.55 85	98.63 153	96.75 112	97.88 272	98.74 108	93.84 215	96.54 191	98.18 199	85.34 278	99.75 109	95.93 162	96.35 222	99.15 151

jason		97.32 110	97.08 106	98.06 135	97.45 261	95.59 171	97.87 273	97.91 275	94.79 175	98.55 87	98.83 125	91.12 158	99.23 191	97.58 96	99.60 78	99.34 116
jason: jason.
WB-MVSnew		94.19 279	94.04 249	94.66 330	96.82 304	92.14 296	97.86 274	95.96 370	93.50 240	95.64 216	96.77 320	88.06 227	97.99 335	84.87 368	96.86 206	93.85 385

xiu_mvs_v1_base_debu		97.60 90	97.56 79	97.72 157	98.35 174	95.98 149	97.86 274	98.51 168	97.13 59	99.01 49	98.40 173	91.56 144	99.80 88	98.53 31	98.68 144	97.37 256

xiu_mvs_v1_base		97.60 90	97.56 79	97.72 157	98.35 174	95.98 149	97.86 274	98.51 168	97.13 59	99.01 49	98.40 173	91.56 144	99.80 88	98.53 31	98.68 144	97.37 256

xiu_mvs_v1_base_debi		97.60 90	97.56 79	97.72 157	98.35 174	95.98 149	97.86 274	98.51 168	97.13 59	99.01 49	98.40 173	91.56 144	99.80 88	98.53 31	98.68 144	97.37 256

test_prior4						98.01 61	97.86 274

mvsany_test3		88.80 348	88.04 349	91.09 366	89.78 396	81.57 391	97.83 279	95.49 375	93.81 218	87.53 369	93.95 380	56.14 399	97.43 359	94.68 202	83.13 375	94.26 375

FA-MVS(test-final)		96.41 151	95.94 155	97.82 148	98.21 193	95.20 193	97.80 280	97.58 292	93.21 253	97.36 153	97.70 239	89.47 187	99.56 145	94.12 224	97.99 175	98.71 199

test_prior2							97.80 280		96.12 106	97.89 128	98.69 144	95.96 37		96.89 127	99.60 78

XVG-OURS-SEG-HR		96.51 144	96.34 139	97.02 205	98.77 136	93.76 255	97.79 282	98.50 173	95.45 137	96.94 168	99.09 92	87.87 233	99.55 152	96.76 139	95.83 244	97.74 242

MS-PatchMatch		93.84 296	93.63 282	94.46 338	96.18 334	89.45 346	97.76 283	98.27 218	92.23 292	92.13 332	97.49 257	79.50 339	98.69 263	89.75 326	99.38 115	95.25 363

DELS-MVS		98.40 46	98.20 52	98.99 57	99.00 114	97.66 70	97.75 284	98.89 59	97.71 19	98.33 101	98.97 105	94.97 74	99.88 56	98.42 45	99.76 41	99.42 111
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
MG-MVS		97.81 75	97.60 76	98.44 99	99.12 102	95.97 154	97.75 284	98.78 100	96.89 70	98.46 90	99.22 64	93.90 97	99.68 125	94.81 200	99.52 96	99.67 65

test_f		86.07 357	85.39 358	88.10 370	89.28 398	75.57 397	97.73 286	96.33 365	89.41 357	85.35 383	91.56 394	43.31 405	95.53 385	91.32 299	84.23 373	93.21 389

bld_raw_dy_0_64		97.62 88	97.67 74	97.46 175	98.43 167	94.02 247	97.71 287	98.53 162	95.87 116	98.78 69	98.70 142	92.93 108	99.46 168	98.25 56	99.86 1	98.90 182

Test_1112_low_res		96.34 153	95.66 171	98.36 106	98.56 158	95.94 157	97.71 287	98.07 258	92.10 296	94.79 235	97.29 272	91.75 139	99.56 145	94.17 222	96.50 219	99.58 83

BH-w/o		95.38 200	95.08 196	96.26 272	98.34 179	91.79 303	97.70 289	97.43 314	92.87 269	94.24 258	97.22 278	88.66 210	98.84 250	91.55 296	97.70 188	98.16 232

lupinMVS		97.44 102	97.22 100	98.12 130	98.07 207	95.76 168	97.68 290	97.76 282	94.50 189	98.79 67	98.61 152	92.34 119	99.30 184	97.58 96	99.59 80	99.31 122

原ACMM2							97.67 291

test_vis3_rt		79.22 361	77.40 368	84.67 376	86.44 404	74.85 400	97.66 292	81.43 411	84.98 382	67.12 404	81.91 402	28.09 413	97.60 353	88.96 339	80.04 388	81.55 402

LF4IMVS		93.14 312	92.79 305	94.20 341	95.88 347	88.67 360	97.66 292	97.07 334	93.81 218	91.71 337	97.65 245	77.96 352	98.81 255	91.47 297	91.92 299	95.12 366

EGC-MVSNET		75.22 370	69.54 373	92.28 361	94.81 372	89.58 344	97.64 294	96.50 362	1.82 413	5.57 414	95.74 354	68.21 385	96.26 379	73.80 396	91.71 301	90.99 391

新几何2							97.64 294

MDA-MVSNet-bldmvs		89.97 341	88.35 347	94.83 325	95.21 365	91.34 312	97.64 294	97.51 304	88.36 365	71.17 402	96.13 344	79.22 341	96.63 375	83.65 375	86.27 366	96.52 326

pmmvs-eth3d		90.36 338	89.05 343	94.32 340	91.10 393	92.12 297	97.63 297	96.95 344	88.86 362	84.91 385	93.13 387	78.32 347	96.74 370	88.70 341	81.81 380	94.09 380

TR-MVS		94.94 232	94.20 238	97.17 195	97.75 232	94.14 244	97.59 298	97.02 340	92.28 291	95.75 215	97.64 247	83.88 311	98.96 231	89.77 325	96.15 237	98.40 220

无先验							97.58 299	98.72 113	91.38 314				99.87 58	93.36 247		99.60 77

旧先验2							97.57 300		91.30 320	98.67 77			99.80 88	95.70 174

mvsany_test1		97.69 82	97.70 72	97.66 167	98.24 189	94.18 243	97.53 301	97.53 302	95.52 134	99.66 15	99.51 13	94.30 89	99.56 145	98.38 46	98.62 149	99.23 135

CostFormer		94.95 230	94.73 212	95.60 298	97.28 272	89.06 352	97.53 301	96.89 349	89.66 351	96.82 176	96.72 322	86.05 265	98.95 236	95.53 179	96.13 238	98.79 190

UWE-MVS		94.30 271	93.89 264	95.53 299	97.83 227	88.95 356	97.52 303	93.25 394	94.44 192	96.63 183	97.07 290	78.70 344	99.28 186	91.99 286	97.56 193	98.36 223

XVG-OURS		96.55 143	96.41 137	96.99 206	98.75 137	93.76 255	97.50 304	98.52 166	95.67 128	96.83 174	99.30 52	88.95 206	99.53 153	95.88 164	96.26 232	97.69 245

xiu_mvs_v2_base		97.66 85	97.70 72	97.56 173	98.61 155	95.46 178	97.44 305	98.46 180	97.15 57	98.65 82	98.15 200	94.33 88	99.80 88	97.84 78	98.66 148	97.41 252

tpm		94.13 284	93.80 270	95.12 313	96.50 322	87.91 372	97.44 305	95.89 373	92.62 276	96.37 199	96.30 336	84.13 306	98.30 311	93.24 249	91.66 303	99.14 153

DeepPCF-MVS	96.37 2	97.93 70	98.48 23	96.30 270	99.00 114	89.54 345	97.43 307	98.87 69	98.16 11	99.26 36	99.38 37	96.12 31	99.64 131	98.30 51	99.77 35	99.72 45

test222					99.23 88	97.17 96	97.40 308	98.66 131	88.68 363	98.05 110	98.96 110	94.14 93			99.53 95	99.61 75

pmmvs4		94.69 240	93.99 256	96.81 221	95.74 350	95.94 157	97.40 308	97.67 286	90.42 338	93.37 296	97.59 251	89.08 199	98.20 318	92.97 258	91.67 302	96.30 343

test0.0.03 1		94.08 290	93.51 288	95.80 290	95.53 357	92.89 290	97.38 310	95.97 369	95.11 157	92.51 324	96.66 324	87.71 235	96.94 367	87.03 354	93.67 272	97.57 250

HyFIR lowres test		96.90 128	96.49 134	98.14 124	99.33 59	95.56 173	97.38 310	99.65 2	92.34 287	97.61 147	98.20 197	89.29 192	99.10 212	96.97 120	97.60 191	99.77 27

Effi-MVS+		97.12 120	96.69 125	98.39 105	98.19 197	96.72 114	97.37 312	98.43 188	93.71 226	97.65 144	98.02 209	92.20 127	99.25 188	96.87 132	97.79 183	99.19 143

N_pmnet		87.12 355	87.77 353	85.17 375	95.46 360	61.92 411	97.37 312	70.66 416	85.83 378	88.73 365	96.04 347	85.33 279	97.76 349	80.02 384	90.48 315	95.84 354

PAPR		96.84 131	96.24 145	98.65 77	98.72 142	96.92 104	97.36 314	98.57 151	93.33 247	96.67 181	97.57 253	94.30 89	99.56 145	91.05 307	98.59 151	99.47 100

PMMVS		96.60 138	96.33 140	97.41 181	97.90 224	93.93 250	97.35 315	98.41 190	92.84 270	97.76 131	97.45 261	91.10 160	99.20 195	96.26 151	97.91 178	99.11 156

PS-MVSNAJ		97.73 78	97.77 68	97.62 169	98.68 147	95.58 172	97.34 316	98.51 168	97.29 44	98.66 81	97.88 223	94.51 81	99.90 45	97.87 75	99.17 124	97.39 254

SCA		95.46 193	95.13 192	96.46 258	97.67 240	91.29 314	97.33 317	97.60 291	94.68 179	96.92 171	97.10 283	83.97 309	98.89 244	92.59 269	98.32 168	99.20 139

testdata1							97.32 318		96.34 97

ET-MVSNet_ETH3D		94.13 284	92.98 301	97.58 171	98.22 192	96.20 142	97.31 319	95.37 376	94.53 186	79.56 394	97.63 249	86.51 255	97.53 357	96.91 123	90.74 313	99.02 170

tpm2		94.19 279	93.76 275	95.46 303	97.23 275	89.04 353	97.31 319	96.85 353	87.08 370	96.21 202	96.79 319	83.75 315	98.74 260	92.43 277	96.23 235	98.59 211

PVSNet_Blended		97.38 107	97.12 103	98.14 124	99.25 81	95.35 185	97.28 321	99.26 15	93.13 258	97.94 123	98.21 196	92.74 113	99.81 81	96.88 129	99.40 113	99.27 129

CLD-MVS		95.62 187	95.34 181	96.46 258	97.52 255	93.75 257	97.27 322	98.46 180	95.53 133	94.42 248	98.00 212	86.21 262	98.97 227	96.25 153	94.37 251	96.66 307
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPMVS		94.99 225	94.48 223	96.52 250	97.22 276	91.75 305	97.23 323	91.66 401	94.11 199	97.28 154	96.81 318	85.70 271	98.84 250	93.04 256	97.28 197	98.97 175

miper_lstm_enhance		94.33 269	94.07 248	95.11 314	97.75 232	90.97 318	97.22 324	98.03 265	91.67 308	92.76 314	96.97 305	90.03 178	97.78 348	92.51 274	89.64 326	96.56 318

APD_test1		88.22 350	88.01 350	88.86 369	95.98 343	74.66 401	97.21 325	96.44 363	83.96 386	86.66 376	97.90 220	60.95 397	97.84 347	82.73 377	90.23 319	94.09 380

dmvs_testset		87.64 352	88.93 345	83.79 378	95.25 364	63.36 410	97.20 326	91.17 402	93.07 260	85.64 382	95.98 351	85.30 281	91.52 400	69.42 399	87.33 356	96.49 332

YYNet1		90.70 336	89.39 339	94.62 332	94.79 373	90.65 327	97.20 326	97.46 308	87.54 368	72.54 400	95.74 354	86.51 255	96.66 374	86.00 360	86.76 365	96.54 321

MDA-MVSNet_test_wron		90.71 335	89.38 340	94.68 329	94.83 371	90.78 324	97.19 328	97.46 308	87.60 367	72.41 401	95.72 358	86.51 255	96.71 373	85.92 361	86.80 364	96.56 318

IterMVS-SCA-FT		94.11 287	93.87 265	94.85 323	97.98 217	90.56 329	97.18 329	98.11 248	93.75 220	92.58 320	97.48 258	83.97 309	97.41 360	92.48 276	91.30 306	96.58 314

IterMVS		94.09 289	93.85 267	94.80 326	97.99 215	90.35 332	97.18 329	98.12 245	93.68 231	92.46 326	97.34 268	84.05 307	97.41 360	92.51 274	91.33 305	96.62 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FE-MVS		95.62 187	94.90 205	97.78 151	98.37 173	94.92 208	97.17 331	97.38 318	90.95 330	97.73 136	97.70 239	85.32 280	99.63 134	91.18 300	98.33 166	98.79 190

DPM-MVS		97.55 96	96.99 110	99.23 38	99.04 109	98.55 27	97.17 331	98.35 203	94.85 174	97.93 125	98.58 157	95.07 72	99.71 118	92.60 267	99.34 117	99.43 109

c3_l		94.79 237	94.43 229	95.89 287	97.75 232	93.12 286	97.16 333	98.03 265	92.23 292	93.46 293	97.05 296	91.39 149	98.01 332	93.58 242	89.21 335	96.53 323

new-patchmatchnet		88.50 349	87.45 354	91.67 364	90.31 395	85.89 380	97.16 333	97.33 319	89.47 354	83.63 387	92.77 389	76.38 364	95.06 390	82.70 378	77.29 395	94.06 382

UnsupCasMVSNet_eth		90.99 333	89.92 336	94.19 342	94.08 378	89.83 338	97.13 335	98.67 128	93.69 229	85.83 380	96.19 342	75.15 370	96.74 370	89.14 337	79.41 390	96.00 351

IB-MVS	91.98 17	93.27 306	91.97 319	97.19 193	97.47 257	93.41 271	97.09 336	95.99 368	93.32 248	92.47 325	95.73 356	78.06 351	99.53 153	94.59 209	82.98 376	98.62 208
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
cl____		94.51 257	94.01 253	96.02 279	97.58 247	93.40 273	97.05 337	97.96 271	91.73 306	92.76 314	97.08 289	89.06 200	98.13 323	92.61 266	90.29 318	96.52 326

DIV-MVS_self_test		94.52 256	94.03 250	95.99 280	97.57 251	93.38 274	97.05 337	97.94 272	91.74 304	92.81 312	97.10 283	89.12 197	98.07 329	92.60 267	90.30 317	96.53 323

miper_ehance_all_eth		95.01 222	94.69 214	95.97 282	97.70 238	93.31 277	97.02 339	98.07 258	92.23 292	93.51 290	96.96 307	91.85 137	98.15 321	93.68 237	91.16 309	96.44 337

CMPMVS	66.06 21	89.70 342	89.67 338	89.78 367	93.19 384	76.56 393	97.00 340	98.35 203	80.97 391	81.57 390	97.75 235	74.75 372	98.61 270	89.85 324	93.63 275	94.17 378
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
tpmrst		95.63 186	95.69 169	95.44 304	97.54 252	88.54 362	96.97 341	97.56 295	93.50 240	97.52 151	96.93 311	89.49 185	99.16 198	95.25 188	96.42 221	98.64 207

dp		94.15 283	93.90 262	94.90 320	97.31 271	86.82 378	96.97 341	97.19 327	91.22 325	96.02 207	96.61 329	85.51 274	99.02 223	90.00 323	94.30 252	98.85 185

cl22		94.68 242	94.19 239	96.13 276	98.11 205	93.60 262	96.94 343	98.31 209	92.43 284	93.32 298	96.87 315	86.51 255	98.28 315	94.10 226	91.16 309	96.51 329

PM-MVS		87.77 351	86.55 357	91.40 365	91.03 394	83.36 387	96.92 344	95.18 380	91.28 322	86.48 378	93.42 383	53.27 400	96.74 370	89.43 334	81.97 379	94.11 379

TinyColmap		92.31 321	91.53 322	94.65 331	96.92 296	89.75 339	96.92 344	96.68 357	90.45 337	89.62 355	97.85 226	76.06 367	98.81 255	86.74 355	92.51 293	95.41 361

our_test_3		93.65 299	93.30 295	94.69 328	95.45 361	89.68 343	96.91 346	97.65 287	91.97 299	91.66 338	96.88 313	89.67 184	97.93 340	88.02 349	91.49 304	96.48 334

test-LLR		95.10 218	94.87 207	95.80 290	96.77 305	89.70 341	96.91 346	95.21 378	95.11 157	94.83 233	95.72 358	87.71 235	98.97 227	93.06 254	98.50 156	98.72 196

TESTMET0.1,1		94.18 282	93.69 280	95.63 296	96.92 296	89.12 351	96.91 346	94.78 383	93.17 255	94.88 230	96.45 333	78.52 345	98.92 238	93.09 253	98.50 156	98.85 185

test-mter		94.08 290	93.51 288	95.80 290	96.77 305	89.70 341	96.91 346	95.21 378	92.89 268	94.83 233	95.72 358	77.69 353	98.97 227	93.06 254	98.50 156	98.72 196

USDC		93.33 305	92.71 306	95.21 310	96.83 303	90.83 323	96.91 346	97.50 305	93.84 215	90.72 346	98.14 201	77.69 353	98.82 254	89.51 332	93.21 286	95.97 352

MDTV_nov1_ep13_2view						84.26 382	96.89 351		90.97 329	97.90 127		89.89 180		93.91 231		99.18 148

ppachtmachnet_test		93.22 308	92.63 308	94.97 318	95.45 361	90.84 322	96.88 352	97.88 276	90.60 333	92.08 333	97.26 273	88.08 226	97.86 346	85.12 367	90.33 316	96.22 345

tpmvs		94.60 248	94.36 232	95.33 308	97.46 258	88.60 361	96.88 352	97.68 285	91.29 321	93.80 280	96.42 334	88.58 211	99.24 190	91.06 305	96.04 239	98.17 231

MDTV_nov1_ep13			95.40 175		97.48 256	88.34 366	96.85 354	97.29 321	93.74 222	97.48 152	97.26 273	89.18 195	99.05 216	91.92 289	97.43 195

PatchmatchNet		95.71 181	95.52 173	96.29 271	97.58 247	90.72 325	96.84 355	97.52 303	94.06 201	97.08 161	96.96 307	89.24 194	98.90 243	92.03 285	98.37 163	99.26 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MSDG		95.93 170	95.30 186	97.83 146	98.90 124	95.36 183	96.83 356	98.37 200	91.32 319	94.43 247	98.73 139	90.27 175	99.60 139	90.05 321	98.82 141	98.52 215

thisisatest0515		95.61 190	94.89 206	97.76 154	98.15 203	95.15 196	96.77 357	94.41 386	92.95 266	97.18 158	97.43 263	84.78 289	99.45 170	94.63 204	97.73 187	98.68 201

GA-MVS		94.81 236	94.03 250	97.14 197	97.15 284	93.86 252	96.76 358	97.58 292	94.00 206	94.76 236	97.04 297	80.91 329	98.48 282	91.79 291	96.25 233	99.09 158

tpm cat1		93.36 302	92.80 304	95.07 316	97.58 247	87.97 371	96.76 358	97.86 278	82.17 390	93.53 287	96.04 347	86.13 263	99.13 204	89.24 336	95.87 243	98.10 233

eth_miper_zixun_eth		94.68 242	94.41 230	95.47 302	97.64 243	91.71 307	96.73 360	98.07 258	92.71 274	93.64 283	97.21 279	90.54 170	98.17 320	93.38 245	89.76 324	96.54 321

test_post1							96.68 361				30.43 412	87.85 234	98.69 263	92.59 269

pmmvs3		86.67 356	84.86 361	92.11 363	88.16 400	87.19 377	96.63 362	94.75 384	79.88 392	87.22 371	92.75 390	66.56 391	95.20 389	81.24 382	76.56 397	93.96 383

miper_enhance_ethall		95.10 218	94.75 211	96.12 277	97.53 254	93.73 259	96.61 363	98.08 256	92.20 295	93.89 274	96.65 326	92.44 117	98.30 311	94.21 221	91.16 309	96.34 340

testmvs		21.48 379	24.95 382	11.09 395	14.89 417	6.47 420	96.56 364	9.87 418	7.55 411	17.93 411	39.02 409	9.43 418	5.90 414	16.56 413	12.72 411	20.91 409

test123		20.95 380	23.72 383	12.64 394	13.54 418	8.19 419	96.55 365	6.13 419	7.48 412	16.74 412	37.98 410	12.97 415	6.05 413	16.69 412	5.43 412	23.68 408

CL-MVSNet_self_test		90.11 339	89.14 342	93.02 355	91.86 390	88.23 369	96.51 366	98.07 258	90.49 334	90.49 349	94.41 374	84.75 290	95.34 387	80.79 383	74.95 398	95.50 360

GG-mvs-BLEND				96.59 240	96.34 329	94.98 204	96.51 366	88.58 407		93.10 307	94.34 378	80.34 336	98.05 330	89.53 331	96.99 202	96.74 294

new_pmnet		90.06 340	89.00 344	93.22 353	94.18 376	88.32 367	96.42 368	96.89 349	86.19 374	85.67 381	93.62 381	77.18 360	97.10 364	81.61 381	89.29 334	94.23 376

PVSNet	91.96 18	96.35 152	96.15 147	96.96 210	99.17 94	92.05 300	96.08 369	98.68 123	93.69 229	97.75 133	97.80 233	88.86 207	99.69 124	94.26 220	99.01 130	99.15 151

ADS-MVSNet2		94.58 251	94.40 231	95.11 314	98.00 213	88.74 359	96.04 370	97.30 320	90.15 342	96.47 194	96.64 327	87.89 231	97.56 356	90.08 319	97.06 200	99.02 170

ADS-MVSNet		95.00 223	94.45 227	96.63 234	98.00 213	91.91 302	96.04 370	97.74 284	90.15 342	96.47 194	96.64 327	87.89 231	98.96 231	90.08 319	97.06 200	99.02 170

PAPM		94.95 230	94.00 254	97.78 151	97.04 289	95.65 170	96.03 372	98.25 223	91.23 324	94.19 261	97.80 233	91.27 155	98.86 249	82.61 379	97.61 190	98.84 187

cascas		94.63 247	93.86 266	96.93 212	96.91 298	94.27 239	96.00 373	98.51 168	85.55 380	94.54 239	96.23 339	84.20 305	98.87 247	95.80 168	96.98 205	97.66 246

gg-mvs-nofinetune		92.21 322	90.58 330	97.13 198	96.75 308	95.09 198	95.85 374	89.40 406	85.43 381	94.50 241	81.98 401	80.80 332	98.40 304	92.16 279	98.33 166	97.88 237

FPMVS		77.62 369	77.14 369	79.05 387	79.25 410	60.97 412	95.79 375	95.94 371	65.96 401	67.93 403	94.40 375	37.73 407	88.88 404	68.83 400	88.46 344	87.29 398

CHOSEN 280x420		97.18 117	97.18 102	97.20 191	98.81 134	93.27 278	95.78 376	99.15 28	95.25 150	96.79 179	98.11 203	92.29 121	99.07 215	98.56 30	99.85 6	99.25 133

MIMVSNet		93.26 307	92.21 316	96.41 262	97.73 236	93.13 284	95.65 377	97.03 338	91.27 323	94.04 268	96.06 346	75.33 369	97.19 363	86.56 356	96.23 235	98.92 181

KD-MVS_2432*1600		89.61 344	87.96 351	94.54 333	94.06 379	91.59 309	95.59 378	97.63 289	89.87 347	88.95 361	94.38 376	78.28 348	96.82 368	84.83 369	68.05 402	95.21 364

miper_refine_blended		89.61 344	87.96 351	94.54 333	94.06 379	91.59 309	95.59 378	97.63 289	89.87 347	88.95 361	94.38 376	78.28 348	96.82 368	84.83 369	68.05 402	95.21 364

PCF-MVS	93.45 11	94.68 242	93.43 292	98.42 103	98.62 154	96.77 111	95.48 380	98.20 228	84.63 384	93.34 297	98.32 185	88.55 215	99.81 81	84.80 371	98.96 132	98.68 201
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
JIA-IIPM		93.35 303	92.49 311	95.92 284	96.48 324	90.65 327	95.01 381	96.96 343	85.93 377	96.08 205	87.33 398	87.70 237	98.78 258	91.35 298	95.58 247	98.34 224

CR-MVSNet		94.76 239	94.15 243	96.59 240	97.00 290	93.43 269	94.96 382	97.56 295	92.46 280	96.93 169	96.24 337	88.15 223	97.88 345	87.38 352	96.65 213	98.46 218

RPMNet		92.81 315	91.34 324	97.24 189	97.00 290	93.43 269	94.96 382	98.80 93	82.27 389	96.93 169	92.12 393	86.98 249	99.82 76	76.32 394	96.65 213	98.46 218

UnsupCasMVSNet_bld		87.17 353	85.12 360	93.31 351	91.94 389	88.77 358	94.92 384	98.30 215	84.30 385	82.30 388	90.04 395	63.96 394	97.25 362	85.85 362	74.47 400	93.93 384

PVSNet_0	88.72 19	91.28 329	90.03 335	95.00 317	97.99 215	87.29 376	94.84 385	98.50 173	92.06 297	89.86 353	95.19 366	79.81 338	99.39 178	92.27 278	69.79 401	98.33 225

Patchmatch-test		94.42 265	93.68 281	96.63 234	97.60 246	91.76 304	94.83 386	97.49 307	89.45 355	94.14 263	97.10 283	88.99 201	98.83 253	85.37 366	98.13 172	99.29 127

testf1		79.02 363	77.70 365	82.99 381	88.10 401	66.90 407	94.67 387	93.11 395	71.08 399	74.02 397	93.41 384	34.15 409	93.25 395	72.25 397	78.50 392	88.82 395

APD_test2		79.02 363	77.70 365	82.99 381	88.10 401	66.90 407	94.67 387	93.11 395	71.08 399	74.02 397	93.41 384	34.15 409	93.25 395	72.25 397	78.50 392	88.82 395

Patchmtry		93.22 308	92.35 314	95.84 289	96.77 305	93.09 287	94.66 389	97.56 295	87.37 369	92.90 310	96.24 337	88.15 223	97.90 341	87.37 353	90.10 321	96.53 323

kuosan		78.45 366	77.69 367	80.72 385	92.73 388	75.32 398	94.63 390	74.51 414	75.96 395	80.87 393	93.19 386	63.23 395	79.99 409	42.56 409	81.56 382	86.85 401

dongtai		82.47 360	81.88 363	84.22 377	95.19 366	76.03 394	94.59 391	74.14 415	82.63 387	87.19 372	96.09 345	64.10 393	87.85 405	58.91 403	84.11 374	88.78 397

PatchT		93.06 313	91.97 319	96.35 266	96.69 312	92.67 291	94.48 392	97.08 332	86.62 371	97.08 161	92.23 392	87.94 230	97.90 341	78.89 389	96.69 211	98.49 217

LCM-MVSNet		78.70 365	76.24 371	86.08 373	77.26 412	71.99 403	94.34 393	96.72 355	61.62 403	76.53 395	89.33 396	33.91 411	92.78 398	81.85 380	74.60 399	93.46 386

PMMVS2		77.95 368	75.44 372	85.46 374	82.54 407	74.95 399	94.23 394	93.08 397	72.80 398	74.68 396	87.38 397	36.36 408	91.56 399	73.95 395	63.94 404	89.87 394

MVS-HIRNet		89.46 346	88.40 346	92.64 357	97.58 247	82.15 389	94.16 395	93.05 398	75.73 397	90.90 344	82.52 400	79.42 340	98.33 306	83.53 376	98.68 144	97.43 251

Patchmatch-RL test		91.49 326	90.85 327	93.41 348	91.37 391	84.40 381	92.81 396	95.93 372	91.87 302	87.25 370	94.87 370	88.99 201	96.53 376	92.54 273	82.00 378	99.30 125

ambc				89.49 368	86.66 403	75.78 395	92.66 397	96.72 355		86.55 377	92.50 391	46.01 401	97.90 341	90.32 315	82.09 377	94.80 373

EMVS		64.07 375	63.26 378	66.53 392	81.73 409	58.81 415	91.85 398	84.75 409	51.93 407	59.09 407	75.13 406	43.32 404	79.09 410	42.03 410	39.47 407	61.69 406

E-PMN		64.94 374	64.25 376	67.02 391	82.28 408	59.36 414	91.83 399	85.63 408	52.69 405	60.22 406	77.28 405	41.06 406	80.12 408	46.15 408	41.14 406	61.57 407

ANet_high		69.08 371	65.37 375	80.22 386	65.99 414	71.96 404	90.91 400	90.09 405	82.62 388	49.93 409	78.39 404	29.36 412	81.75 406	62.49 402	38.52 408	86.95 400

tmp_tt		68.90 372	66.97 374	74.68 389	50.78 416	59.95 413	87.13 401	83.47 410	38.80 409	62.21 405	96.23 339	64.70 392	76.91 411	88.91 340	30.49 409	87.19 399

MVE	62.14 22	63.28 376	59.38 379	74.99 388	74.33 413	65.47 409	85.55 402	80.50 412	52.02 406	51.10 408	75.00 407	10.91 417	80.50 407	51.60 406	53.40 405	78.99 403
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	61.03 23	65.95 373	63.57 377	73.09 390	57.90 415	51.22 417	85.05 403	93.93 393	54.45 404	44.32 410	83.57 399	13.22 414	89.15 403	58.68 404	81.00 384	78.91 404
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		79.03 362	78.17 364	81.63 384	86.06 405	54.40 416	82.75 404	96.89 349	39.54 408	80.98 392	95.57 362	58.37 398	94.73 391	84.74 372	78.61 391	95.75 356

Gipuma		78.40 367	76.75 370	83.38 380	95.54 356	80.43 392	79.42 405	97.40 316	64.67 402	73.46 399	80.82 403	45.65 402	93.14 397	66.32 401	87.43 354	76.56 405
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
wuyk23d		30.17 377	30.18 381	30.16 393	78.61 411	43.29 418	66.79 406	14.21 417	17.31 410	14.82 413	11.93 413	11.55 416	41.43 412	37.08 411	19.30 410	5.76 410

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		23.98 378	31.98 380	0.00 396	0.00 419	0.00 421	0.00 407	98.59 144	0.00 414	0.00 415	98.61 152	90.60 169	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		7.88 382	10.50 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	94.51 81	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.20 381	10.94 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	98.43 169	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						90.94 319								88.66 342

MSC_two_6792asdad				99.62 6	99.17 94	99.08 11		98.63 138					99.94 8	98.53 31	99.80 23	99.86 8

PC_three_1452									95.08 161	99.60 19	99.16 77	97.86 2	98.47 285	97.52 103	99.72 55	99.74 37

No_MVS				99.62 6	99.17 94	99.08 11		98.63 138					99.94 8	98.53 31	99.80 23	99.86 8

test_one_0601					99.66 26	99.25 2		98.86 75	97.55 28	99.20 38	99.47 20	97.57 6

eth-test2					0.00 419

eth-test					0.00 419

ZD-MVS					99.46 49	98.70 23		98.79 98	93.21 253	98.67 77	98.97 105	95.70 45	99.83 69	96.07 155	99.58 83

IU-MVS					99.71 19	99.23 7		98.64 136	95.28 148	99.63 18				98.35 49	99.81 16	99.83 13

test_241102_TWO								98.87 69	97.65 22	99.53 23	99.48 18	97.34 11	99.94 8	98.43 43	99.80 23	99.83 13

test_241102_ONE					99.71 19	99.24 5		98.87 69	97.62 24	99.73 10	99.39 32	97.53 7	99.74 111

test_0728_THIRD									97.32 42	99.45 25	99.46 24	97.88 1	99.94 8	98.47 39	99.86 1	99.85 10

GSMVS																99.20 139

test_part2					99.63 29	99.18 10				99.27 35

sam_mvs1												89.45 188				99.20 139

sam_mvs												88.99 201

MTGPA								98.74 108

test_post											31.83 411	88.83 208	98.91 240

patchmatchnet-post											95.10 368	89.42 189	98.89 244

gm-plane-assit					95.88 347	87.47 374			89.74 350		96.94 310		99.19 196	93.32 248

test9_res														96.39 149	99.57 84	99.69 56

agg_prior2														95.87 165	99.57 84	99.68 61

agg_prior					99.30 68	98.38 35		98.72 113		97.57 150			99.81 81

TestCases				96.99 206	99.25 81	93.21 282		98.18 233	91.36 315	93.52 288	98.77 133	84.67 293	99.72 113	89.70 328	97.87 180	98.02 235

test_prior				99.19 40	99.31 64	98.22 48		98.84 79					99.70 119			99.65 69

新几何1				99.16 45	99.34 57	98.01 61		98.69 120	90.06 344	98.13 105	98.95 112	94.60 79	99.89 47	91.97 288	99.47 103	99.59 79

旧先验1					99.29 73	97.48 78		98.70 119			99.09 92	95.56 48			99.47 103	99.61 75

原ACMM1				98.65 77	99.32 62	96.62 116		98.67 128	93.27 252	97.81 129	98.97 105	95.18 67	99.83 69	93.84 233	99.46 106	99.50 91

testdata2													99.89 47	91.65 295

segment_acmp												96.85 14

testdata				98.26 115	99.20 92	95.36 183		98.68 123	91.89 301	98.60 85	99.10 86	94.44 86	99.82 76	94.27 219	99.44 107	99.58 83

test12				99.18 42	99.16 98	98.19 50		98.53 162		98.07 109		95.13 70	99.72 113		99.56 90	99.63 73

plane_prior7					97.42 263	94.63 221

plane_prior6					97.35 270	94.61 224						87.09 246

plane_prior5								98.56 155					99.03 220	96.07 155	94.27 253	96.92 271

plane_prior4											98.28 188

plane_prior3						94.61 224			97.02 64	95.34 219

plane_prior1					97.37 269

n2								0.00 420

nn								0.00 420

door-mid								94.37 387

lessismore_v0				94.45 339	94.93 370	88.44 365		91.03 403		86.77 375	97.64 247	76.23 366	98.42 291	90.31 316	85.64 370	96.51 329

LGP-MVS_train				96.47 255	97.46 258	93.54 264		98.54 160	94.67 180	94.36 251	98.77 133	85.39 275	99.11 208	95.71 172	94.15 259	96.76 291

test11								98.66 131

door								94.64 385

HQP5-MVS						94.25 241

BP-MVS														95.30 184

HQP4-MVS										94.45 243			98.96 231			96.87 282

HQP3-MVS								98.46 180							94.18 257

HQP2-MVS												86.75 252

NP-MVS					97.28 272	94.51 229					97.73 236

ACMMP++_ref															92.97 287

ACMMP++															93.61 276

Test By Simon												94.64 78

ITE_SJBPF				95.44 304	97.42 263	91.32 313		97.50 305	95.09 160	93.59 284	98.35 179	81.70 322	98.88 246	89.71 327	93.39 282	96.12 348

DeepMVS_CX				86.78 372	97.09 288	72.30 402		95.17 381	75.92 396	84.34 386	95.19 366	70.58 382	95.35 386	79.98 386	89.04 338	92.68 390

High-resolution multi-view benchmark