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.

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 2	99.98 1	99.99 1	99.96 1	99.77 1	100.00 1	99.81 1	100.00 1	99.85 7

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 14	99.34 14	99.69 4	99.58 28	99.90 2	99.86 7	99.78 5	99.58 3	99.95 15	99.00 33	99.95 16	99.78 14

UA-Net		99.47 11	99.40 14	99.70 2	99.49 84	99.29 17	99.80 3	99.72 9	99.82 3	99.04 111	99.81 3	98.05 67	99.96 8	98.85 41	99.99 5	99.86 6

ANet_high		99.57 7	99.67 5	99.28 79	99.89 6	98.09 127	99.14 40	99.93 1	99.82 3	99.93 2	99.81 3	99.17 12	99.94 23	99.31 16	100.00 1	99.82 9

test_part1		97.91 168	97.46 199	99.27 82	98.80 233	98.18 120	99.07 46	99.36 108	99.75 5	99.63 25	99.49 39	82.20 342	99.89 58	98.87 40	99.95 16	99.74 24

gg-mvs-nofinetune		92.37 328	91.20 333	95.85 314	95.80 362	92.38 319	99.31 18	81.84 369	99.75 5	91.83 359	99.74 8	68.29 365	99.02 349	87.15 349	97.12 335	96.16 352

LFMVS		97.20 228	96.72 241	98.64 171	98.72 242	96.95 213	98.93 59	94.14 350	99.74 7	98.78 158	99.01 122	84.45 326	99.73 223	97.44 118	99.27 234	99.25 198

Anonymous20231211		99.27 25	99.27 24	99.26 85	99.29 122	98.18 120	99.49 8	99.51 57	99.70 8	99.80 9	99.68 14	96.84 151	99.83 136	99.21 23	99.91 40	99.77 16

nrg030		99.40 18	99.35 17	99.54 29	99.58 51	99.13 51	98.98 56	99.48 69	99.68 9	99.46 43	99.26 69	98.62 29	99.73 223	99.17 26	99.92 34	99.76 20

VDDNet		98.21 147	97.95 161	99.01 127	99.58 51	97.74 170	99.01 50	97.29 318	99.67 10	98.97 124	99.50 36	90.45 287	99.80 168	97.88 97	99.20 244	99.48 112

v7n		99.53 8	99.57 8	99.41 60	99.88 7	98.54 96	99.45 9	99.61 24	99.66 11	99.68 19	99.66 17	98.44 40	99.95 15	99.73 2	99.96 14	99.75 22

pmmvs6		99.67 3	99.70 3	99.60 13	99.90 4	99.27 20	99.53 7	99.76 7	99.64 12	99.84 8	99.83 2	99.50 5	99.87 84	99.36 14	99.92 34	99.64 39

DTE-MVSNet		99.43 15	99.35 17	99.66 4	99.71 30	99.30 16	99.31 18	99.51 57	99.64 12	99.56 28	99.46 43	98.23 52	99.97 3	98.78 45	99.93 25	99.72 25

VPA-MVSNet		99.30 24	99.30 23	99.28 79	99.49 84	98.36 107	99.00 52	99.45 80	99.63 14	99.52 35	99.44 48	98.25 50	99.88 67	99.09 28	99.84 56	99.62 44

DP-MVS		98.93 49	98.81 51	99.28 79	99.21 136	98.45 102	98.46 99	99.33 125	99.63 14	99.48 40	99.15 90	97.23 132	99.75 215	97.17 130	99.66 145	99.63 43

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 24	99.85 13	99.11 55	99.90 1	99.78 5	99.63 14	99.78 10	99.67 16	99.48 6	99.81 159	99.30 17	99.97 11	99.77 16
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
PEN-MVS		99.41 17	99.34 19	99.62 6	99.73 24	99.14 48	99.29 23	99.54 50	99.62 17	99.56 28	99.42 49	98.16 60	99.96 8	98.78 45	99.93 25	99.77 16

K. test v3		98.00 163	97.66 183	99.03 123	99.79 19	97.56 180	99.19 36	92.47 356	99.62 17	99.52 35	99.66 17	89.61 292	99.96 8	99.25 20	99.81 69	99.56 71

FC-MVSNet-test		99.27 25	99.25 25	99.34 72	99.77 20	98.37 106	99.30 22	99.57 35	99.61 19	99.40 52	99.50 36	97.12 135	99.85 105	99.02 32	99.94 21	99.80 12

VDD-MVS		98.56 104	98.39 112	99.07 113	99.13 161	98.07 133	98.59 81	97.01 322	99.59 20	99.11 95	99.27 67	94.82 231	99.79 183	98.34 72	99.63 151	99.34 172

MIMVSNet1		99.38 20	99.32 21	99.55 26	99.86 11	99.19 34	99.41 10	99.59 26	99.59 20	99.71 14	99.57 27	97.12 135	99.90 49	99.21 23	99.87 52	99.54 83

Gipuma		99.03 36	99.16 30	98.64 171	99.94 2	98.51 98	99.32 15	99.75 8	99.58 22	98.60 179	99.62 21	98.22 55	99.51 306	97.70 108	99.73 106	97.89 315
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PS-CasMVS		99.40 18	99.33 20	99.62 6	99.71 30	99.10 56	99.29 23	99.53 53	99.53 23	99.46 43	99.41 51	98.23 52	99.95 15	98.89 39	99.95 16	99.81 11

FIs		99.14 32	99.09 34	99.29 77	99.70 36	98.28 110	99.13 41	99.52 56	99.48 24	99.24 80	99.41 51	96.79 157	99.82 146	98.69 53	99.88 49	99.76 20

PS-MVSNAJss		99.46 12	99.49 10	99.35 69	99.90 4	98.15 123	99.20 32	99.65 19	99.48 24	99.92 3	99.71 12	98.07 64	99.96 8	99.53 9	100.00 1	99.93 1

VPNet		98.87 55	98.83 48	99.01 127	99.70 36	97.62 179	98.43 102	99.35 114	99.47 26	99.28 71	99.05 108	96.72 163	99.82 146	98.09 84	99.36 218	99.59 55

WR-MVS_H		99.33 23	99.22 27	99.65 5	99.71 30	99.24 23	99.32 15	99.55 46	99.46 27	99.50 39	99.34 60	97.30 124	99.93 28	98.90 37	99.93 25	99.77 16

tfpnnormal		98.90 53	98.90 43	98.91 139	99.67 40	97.82 162	99.00 52	99.44 83	99.45 28	99.51 38	99.24 72	98.20 57	99.86 91	95.92 222	99.69 129	99.04 233

OurMVSNet-221017-0		99.37 21	99.31 22	99.53 36	99.91 3	98.98 61	99.63 6	99.58 28	99.44 29	99.78 10	99.76 6	96.39 178	99.92 35	99.44 13	99.92 34	99.68 31

CP-MVSNet		99.21 29	99.09 34	99.56 24	99.65 43	98.96 65	99.13 41	99.34 120	99.42 30	99.33 62	99.26 69	97.01 142	99.94 23	98.74 50	99.93 25	99.79 13

TranMVSNet+NR-MVSNet		99.17 30	99.07 36	99.46 55	99.37 110	98.87 67	98.39 105	99.42 92	99.42 30	99.36 58	99.06 101	98.38 43	99.95 15	98.34 72	99.90 44	99.57 66

TransMVSNet (Re)		99.44 13	99.47 12	99.36 64	99.80 17	98.58 91	99.27 29	99.57 35	99.39 32	99.75 12	99.62 21	99.17 12	99.83 136	99.06 30	99.62 154	99.66 34

TDRefinement		99.42 16	99.38 15	99.55 26	99.76 22	99.33 15	99.68 5	99.71 10	99.38 33	99.53 33	99.61 23	98.64 28	99.80 168	98.24 75	99.84 56	99.52 93

Baseline_NR-MVSNet		98.98 43	98.86 46	99.36 64	99.82 16	98.55 93	97.47 203	99.57 35	99.37 34	99.21 84	99.61 23	96.76 160	99.83 136	98.06 86	99.83 62	99.71 26

SixPastTwentyTwo		98.75 72	98.62 74	99.16 97	99.83 15	97.96 148	99.28 27	98.20 292	99.37 34	99.70 15	99.65 19	92.65 274	99.93 28	99.04 31	99.84 56	99.60 49

RPMNet		97.02 242	96.93 227	97.30 275	97.71 323	94.22 279	98.11 128	99.30 141	99.37 34	96.91 289	99.34 60	86.72 307	99.87 84	97.53 115	97.36 331	97.81 321

Anonymous20240521		98.69 82	98.87 44	98.16 224	99.77 20	95.11 263	99.08 44	99.44 83	99.34 37	99.33 62	99.55 29	94.10 252	99.94 23	99.25 20	99.96 14	99.42 138

PatchT		96.65 259	96.35 259	97.54 264	97.40 336	95.32 254	97.98 149	96.64 330	99.33 38	96.89 293	99.42 49	84.32 328	99.81 159	97.69 110	97.49 324	97.48 335

DIV-MVS_2432*1600		99.25 27	99.18 28	99.44 56	99.63 48	99.06 60	98.69 73	99.54 50	99.31 39	99.62 27	99.53 33	97.36 122	99.86 91	99.24 22	99.71 118	99.39 150

VNet		98.42 124	98.30 124	98.79 156	98.79 235	97.29 192	98.23 116	98.66 271	99.31 39	98.85 148	98.80 174	94.80 234	99.78 195	98.13 80	99.13 258	99.31 184

pm-mvs1		99.44 13	99.48 11	99.33 74	99.80 17	98.63 84	99.29 23	99.63 21	99.30 41	99.65 22	99.60 25	99.16 14	99.82 146	99.07 29	99.83 62	99.56 71

test_0402		98.76 70	98.71 62	98.93 136	99.56 62	98.14 125	98.45 101	99.34 120	99.28 42	98.95 127	98.91 143	98.34 48	99.79 183	95.63 239	99.91 40	98.86 261

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 7	98.61 87	99.34 13	99.71 10	99.27 43	99.90 4	99.74 8	99.68 2	99.97 3	99.55 8	99.99 5	99.88 3

Anonymous20240529		98.93 49	98.87 44	99.12 102	99.19 143	98.22 118	99.01 50	98.99 225	99.25 44	99.54 30	99.37 54	97.04 138	99.80 168	97.89 94	99.52 190	99.35 170

Regformer-4		98.73 75	98.68 67	98.89 142	99.02 186	97.22 198	97.17 227	99.06 205	99.21 45	99.17 91	98.85 162	97.45 116	99.86 91	98.48 63	99.70 123	99.60 49

FMVSNet1		99.17 30	99.17 29	99.17 94	99.55 65	98.24 113	99.20 32	99.44 83	99.21 45	99.43 47	99.55 29	97.82 83	99.86 91	98.42 67	99.89 48	99.41 141

LS3D		98.63 94	98.38 114	99.36 64	97.25 341	99.38 5	99.12 43	99.32 127	99.21 45	98.44 197	98.88 155	97.31 123	99.80 168	96.58 180	99.34 222	98.92 253

alignmvs		97.35 215	96.88 232	98.78 159	98.54 276	98.09 127	97.71 176	97.69 308	99.20 48	97.59 253	95.90 338	88.12 304	99.55 293	98.18 79	98.96 279	98.70 282

EI-MVSNet-UG-set		98.69 82	98.71 62	98.62 176	99.10 166	96.37 227	97.23 219	98.87 241	99.20 48	99.19 86	98.99 125	97.30 124	99.85 105	98.77 48	99.79 82	99.65 38

EI-MVSNet-Vis-set		98.68 86	98.70 65	98.63 174	99.09 169	96.40 226	97.23 219	98.86 246	99.20 48	99.18 90	98.97 131	97.29 126	99.85 105	98.72 51	99.78 86	99.64 39

JIA-IIPM		95.52 288	95.03 295	97.00 285	96.85 347	94.03 286	96.93 240	95.82 338	99.20 48	94.63 344	99.71 12	83.09 335	99.60 277	94.42 268	94.64 355	97.36 337

canonicalmvs		98.34 133	98.26 128	98.58 181	98.46 283	97.82 162	98.96 57	99.46 77	99.19 52	97.46 265	95.46 346	98.59 31	99.46 315	98.08 85	98.71 291	98.46 292

casdiffmvs		98.95 47	99.00 39	98.81 152	99.38 108	97.33 190	97.82 165	99.57 35	99.17 53	99.35 59	99.17 84	98.35 47	99.69 238	98.46 64	99.73 106	99.41 141

UniMVSNet_NR-MVSNet		98.86 57	98.68 67	99.40 62	99.17 152	98.74 76	97.68 179	99.40 96	99.14 54	99.06 104	98.59 214	96.71 164	99.93 28	98.57 58	99.77 90	99.53 89

Regformer-3		98.61 97	98.61 77	98.63 174	99.02 186	96.53 224	97.17 227	98.84 248	99.13 55	99.10 98	98.85 162	97.24 131	99.79 183	98.41 68	99.70 123	99.57 66

hse-mvs3		97.77 186	97.33 208	99.10 106	99.21 136	97.84 158	98.35 109	98.57 276	99.11 56	98.58 183	99.02 115	88.65 301	99.96 8	98.11 81	96.34 344	99.49 104

hse-mvs2		97.46 207	97.07 220	98.64 171	98.73 240	97.33 190	97.45 205	97.64 311	99.11 56	98.58 183	97.98 270	88.65 301	99.79 183	98.11 81	97.39 328	98.81 267

MVSFormer		98.26 142	98.43 105	97.77 246	98.88 216	93.89 295	99.39 11	99.56 42	99.11 56	98.16 214	98.13 256	93.81 255	99.97 3	99.26 18	99.57 175	99.43 135

test_djsdf		99.52 9	99.51 9	99.53 36	99.86 11	98.74 76	99.39 11	99.56 42	99.11 56	99.70 15	99.73 10	99.00 15	99.97 3	99.26 18	99.98 9	99.89 2

Vis-MVSNet		99.34 22	99.36 16	99.27 82	99.73 24	98.26 111	99.17 37	99.78 5	99.11 56	99.27 73	99.48 41	98.82 21	99.95 15	98.94 35	99.93 25	99.59 55
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH+	96.62 9	99.08 34	99.00 39	99.33 74	99.71 30	98.83 70	98.60 79	99.58 28	99.11 56	99.53 33	99.18 80	98.81 22	99.67 250	96.71 173	99.77 90	99.50 100

IterMVS-SCA-FT		97.85 180	98.18 138	96.87 293	99.27 124	91.16 337	95.53 308	99.25 159	99.10 62	99.41 49	99.35 58	93.10 265	99.96 8	98.65 54	99.94 21	99.49 104

NR-MVSNet		98.95 47	98.82 49	99.36 64	99.16 154	98.72 81	99.22 31	99.20 170	99.10 62	99.72 13	98.76 181	96.38 180	99.86 91	98.00 91	99.82 65	99.50 100

UGNet		98.53 113	98.45 101	98.79 156	97.94 313	96.96 212	99.08 44	98.54 277	99.10 62	96.82 297	99.47 42	96.55 170	99.84 122	98.56 61	99.94 21	99.55 79
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
jajsoiax		99.58 6	99.61 7	99.48 50	99.87 10	98.61 87	99.28 27	99.66 18	99.09 65	99.89 6	99.68 14	99.53 4	99.97 3	99.50 10	99.99 5	99.87 4

COLMAP_ROB	96.50 10	98.99 39	98.85 47	99.41 60	99.58 51	99.10 56	98.74 68	99.56 42	99.09 65	99.33 62	99.19 78	98.40 42	99.72 231	95.98 220	99.76 99	99.42 138
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test20.03		98.78 67	98.77 56	98.78 159	99.46 95	97.20 201	97.78 167	99.24 164	99.04 67	99.41 49	98.90 146	97.65 94	99.76 208	97.70 108	99.79 82	99.39 150

v8		99.01 37	99.16 30	98.57 184	99.47 94	96.31 230	98.90 60	99.47 75	99.03 68	99.52 35	99.57 27	96.93 147	99.81 159	99.60 4	99.98 9	99.60 49

EPP-MVSNet		98.30 136	98.04 155	99.07 113	99.56 62	97.83 159	99.29 23	98.07 298	99.03 68	98.59 181	99.13 93	92.16 278	99.90 49	96.87 157	99.68 134	99.49 104

IS-MVSNet		98.19 149	97.90 166	99.08 110	99.57 55	97.97 144	99.31 18	98.32 287	99.01 70	98.98 121	99.03 114	91.59 282	99.79 183	95.49 244	99.80 77	99.48 112

3Dnovator+	97.89 3	98.69 82	98.51 88	99.24 89	98.81 231	98.40 103	99.02 49	99.19 175	98.99 71	98.07 222	99.28 65	97.11 137	99.84 122	96.84 160	99.32 224	99.47 120

PMVS	91.26 20	97.86 175	97.94 163	97.65 253	99.71 30	97.94 151	98.52 88	98.68 270	98.99 71	97.52 260	99.35 58	97.41 118	98.18 360	91.59 327	99.67 140	96.82 344
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Regformer-2		98.60 99	98.46 99	99.02 126	98.85 221	97.71 172	96.91 243	99.09 201	98.98 73	99.01 115	98.64 203	97.37 121	99.84 122	97.75 107	99.57 175	99.52 93

Regformer-1		98.55 108	98.44 103	98.87 144	98.85 221	97.29 192	96.91 243	98.99 225	98.97 74	98.99 119	98.64 203	97.26 130	99.81 159	97.79 100	99.57 175	99.51 96

EI-MVSNet		98.40 127	98.51 88	98.04 233	99.10 166	94.73 269	97.20 223	98.87 241	98.97 74	99.06 104	99.02 115	96.00 192	99.80 168	98.58 56	99.82 65	99.60 49

EPNet		96.14 274	95.44 283	98.25 218	90.76 368	95.50 249	97.92 154	94.65 343	98.97 74	92.98 355	98.85 162	89.12 296	99.87 84	95.99 219	99.68 134	99.39 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IterMVS-LS		98.55 108	98.70 65	98.09 226	99.48 92	94.73 269	97.22 222	99.39 98	98.97 74	99.38 54	99.31 64	96.00 192	99.93 28	98.58 56	99.97 11	99.60 49
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmtry		97.35 215	96.97 226	98.50 197	97.31 340	96.47 225	98.18 121	98.92 233	98.95 78	98.78 158	99.37 54	85.44 320	99.85 105	95.96 221	99.83 62	99.17 218

anonymousdsp		99.51 10	99.47 12	99.62 6	99.88 7	99.08 59	99.34 13	99.69 14	98.93 79	99.65 22	99.72 11	98.93 19	99.95 15	99.11 27	100.00 1	99.82 9

UniMVSNet (Re)		98.87 55	98.71 62	99.35 69	99.24 129	98.73 79	97.73 175	99.38 100	98.93 79	99.12 93	98.73 184	96.77 158	99.86 91	98.63 55	99.80 77	99.46 122

Anonymous202405211		97.90 169	97.50 193	99.08 110	98.90 210	98.25 112	98.53 87	96.16 334	98.87 81	99.11 95	98.86 159	90.40 288	99.78 195	97.36 122	99.31 226	99.19 212

baseline		98.96 46	99.02 37	98.76 162	99.38 108	97.26 195	98.49 94	99.50 59	98.86 82	99.19 86	99.06 101	98.23 52	99.69 238	98.71 52	99.76 99	99.33 178

IterMVS		97.73 188	98.11 148	96.57 300	99.24 129	90.28 338	95.52 310	99.21 168	98.86 82	99.33 62	99.33 62	93.11 264	99.94 23	98.49 62	99.94 21	99.48 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DU-MVS		98.82 60	98.63 73	99.39 63	99.16 154	98.74 76	97.54 195	99.25 159	98.84 84	99.06 104	98.76 181	96.76 160	99.93 28	98.57 58	99.77 90	99.50 100

zzz-MVS		98.79 64	98.52 86	99.61 9	99.67 40	99.36 9	97.33 212	99.20 170	98.83 85	98.89 140	98.90 146	96.98 145	99.92 35	97.16 131	99.70 123	99.56 71

MTAPA		98.88 54	98.64 72	99.61 9	99.67 40	99.36 9	98.43 102	99.20 170	98.83 85	98.89 140	98.90 146	96.98 145	99.92 35	97.16 131	99.70 123	99.56 71

bset_n11_16_dypcd		96.99 246	96.56 253	98.27 217	99.00 189	95.25 255	92.18 359	94.05 351	98.75 87	99.01 115	98.38 237	88.98 297	99.93 28	98.77 48	99.92 34	99.64 39

v10		98.97 44	99.11 33	98.55 189	99.44 100	96.21 232	98.90 60	99.55 46	98.73 88	99.48 40	99.60 25	96.63 167	99.83 136	99.70 3	99.99 5	99.61 48

UnsupCasMVSNet_eth		97.89 171	97.60 189	98.75 164	99.31 118	97.17 204	97.62 185	99.35 114	98.72 89	98.76 162	98.68 193	92.57 275	99.74 219	97.76 106	95.60 351	99.34 172

SR-MVS-dyc-post		98.81 62	98.55 83	99.57 18	99.20 140	99.38 5	98.48 97	99.30 141	98.64 90	98.95 127	98.96 134	97.49 113	99.86 91	96.56 185	99.39 213	99.45 126

RE-MVS-def			98.58 81		99.20 140	99.38 5	98.48 97	99.30 141	98.64 90	98.95 127	98.96 134	97.75 87		96.56 185	99.39 213	99.45 126

Fast-Effi-MVS+-dtu		98.27 140	98.09 149	98.81 152	98.43 286	98.11 126	97.61 187	99.50 59	98.64 90	97.39 270	97.52 298	98.12 63	99.95 15	96.90 154	98.71 291	98.38 299

APD-MVS_3200maxsize		98.84 59	98.61 77	99.53 36	99.19 143	99.27 20	98.49 94	99.33 125	98.64 90	99.03 114	98.98 129	97.89 77	99.85 105	96.54 189	99.42 209	99.46 122

XVS		98.72 76	98.45 101	99.53 36	99.46 95	99.21 26	98.65 74	99.34 120	98.62 94	97.54 258	98.63 207	97.50 110	99.83 136	96.79 162	99.53 187	99.56 71

X-MVStestdata		94.32 305	92.59 323	99.53 36	99.46 95	99.21 26	98.65 74	99.34 120	98.62 94	97.54 258	45.85 365	97.50 110	99.83 136	96.79 162	99.53 187	99.56 71

abl_6		98.99 39	98.78 54	99.61 9	99.45 98	99.46 3	98.60 79	99.50 59	98.59 96	99.24 80	99.04 111	98.54 34	99.89 58	96.45 195	99.62 154	99.50 100

GBi-Net		98.65 90	98.47 97	99.17 94	98.90 210	98.24 113	99.20 32	99.44 83	98.59 96	98.95 127	99.55 29	94.14 248	99.86 91	97.77 102	99.69 129	99.41 141

test1		98.65 90	98.47 97	99.17 94	98.90 210	98.24 113	99.20 32	99.44 83	98.59 96	98.95 127	99.55 29	94.14 248	99.86 91	97.77 102	99.69 129	99.41 141

FMVSNet2		98.49 117	98.40 109	98.75 164	98.90 210	97.14 207	98.61 78	99.13 195	98.59 96	99.19 86	99.28 65	94.14 248	99.82 146	97.97 92	99.80 77	99.29 191

WR-MVS		98.40 127	98.19 137	99.03 123	99.00 189	97.65 176	96.85 246	98.94 228	98.57 100	98.89 140	98.50 224	95.60 209	99.85 105	97.54 114	99.85 54	99.59 55

3Dnovator	98.27 2	98.81 62	98.73 58	99.05 120	98.76 236	97.81 164	99.25 30	99.30 141	98.57 100	98.55 189	99.33 62	97.95 76	99.90 49	97.16 131	99.67 140	99.44 131

DROMVSNet		98.85 58	98.81 51	98.97 130	99.08 173	98.61 87	98.99 55	99.81 4	98.54 102	97.73 243	98.07 265	98.50 36	99.88 67	98.81 44	99.72 113	98.42 297

XXY-MVS		99.14 32	99.15 32	99.10 106	99.76 22	97.74 170	98.85 65	99.62 22	98.48 103	99.37 56	99.49 39	98.75 24	99.86 91	98.20 78	99.80 77	99.71 26

test1172		98.76 70	98.49 93	99.57 18	99.18 150	99.37 8	98.39 105	99.31 132	98.43 104	98.90 137	98.88 155	97.49 113	99.86 91	96.43 197	99.37 217	99.48 112

GeoE		99.05 35	98.99 41	99.25 87	99.44 100	98.35 108	98.73 70	99.56 42	98.42 105	98.91 136	98.81 173	98.94 18	99.91 45	98.35 71	99.73 106	99.49 104

LCM-MVSNet-Re		98.64 92	98.48 95	99.11 104	98.85 221	98.51 98	98.49 94	99.83 3	98.37 106	99.69 17	99.46 43	98.21 56	99.92 35	94.13 279	99.30 229	98.91 256

MDA-MVSNet-bldmvs		97.94 167	97.91 165	98.06 231	99.44 100	94.96 265	96.63 259	99.15 194	98.35 107	98.83 151	99.11 96	94.31 245	99.85 105	96.60 179	98.72 289	99.37 160

thres600view7		94.45 303	93.83 309	96.29 305	99.06 178	91.53 327	97.99 147	94.24 348	98.34 108	97.44 267	95.01 350	79.84 347	99.67 250	84.33 354	98.23 305	97.66 329

thres100view900		94.19 308	93.67 312	95.75 316	99.06 178	91.35 331	98.03 141	94.24 348	98.33 109	97.40 269	94.98 352	79.84 347	99.62 270	83.05 356	98.08 315	96.29 348

Vis-MVSNet (Re-imp)		97.46 207	97.16 216	98.34 210	99.55 65	96.10 233	98.94 58	98.44 282	98.32 110	98.16 214	98.62 209	88.76 298	99.73 223	93.88 287	99.79 82	99.18 214

new-patchmatchnet		98.35 132	98.74 57	97.18 279	99.24 129	92.23 322	96.42 270	99.48 69	98.30 111	99.69 17	99.53 33	97.44 117	99.82 146	98.84 42	99.77 90	99.49 104

v148		98.45 121	98.60 79	98.00 235	99.44 100	94.98 264	97.44 206	99.06 205	98.30 111	99.32 68	98.97 131	96.65 166	99.62 270	98.37 69	99.85 54	99.39 150

ACMH	96.65 7	99.25 27	99.24 26	99.26 85	99.72 29	98.38 105	99.07 46	99.55 46	98.30 111	99.65 22	99.45 47	99.22 9	99.76 208	98.44 65	99.77 90	99.64 39
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS		98.71 77	98.43 105	99.57 18	99.18 150	99.35 11	98.36 108	99.29 148	98.29 114	98.88 144	98.85 162	97.53 106	99.87 84	96.14 215	99.31 226	99.48 112

Effi-MVS+-dtu		98.26 142	97.90 166	99.35 69	98.02 309	99.49 2	98.02 143	99.16 188	98.29 114	97.64 249	97.99 269	96.44 176	99.95 15	96.66 176	98.93 281	98.60 287

mvs-test1		97.83 183	97.48 197	98.89 142	98.02 309	99.20 32	97.20 223	99.16 188	98.29 114	96.46 312	97.17 314	96.44 176	99.92 35	96.66 176	97.90 320	97.54 334

xxxxxxxxxxxxxcwj		98.44 122	98.24 130	99.06 118	99.11 162	97.97 144	96.53 262	99.54 50	98.24 117	98.83 151	98.90 146	97.80 84	99.82 146	95.68 236	99.52 190	99.38 157

save fliter					99.11 162	97.97 144	96.53 262	99.02 218	98.24 117

EU-MVSNet		97.66 193	98.50 90	95.13 327	99.63 48	85.84 354	98.35 109	98.21 291	98.23 119	99.54 30	99.46 43	95.02 225	99.68 247	98.24 75	99.87 52	99.87 4

test_yl		96.69 256	96.29 262	97.90 238	98.28 294	95.24 256	97.29 215	97.36 314	98.21 120	98.17 212	97.86 277	86.27 310	99.55 293	94.87 254	98.32 303	98.89 257

DCV-MVSNet		96.69 256	96.29 262	97.90 238	98.28 294	95.24 256	97.29 215	97.36 314	98.21 120	98.17 212	97.86 277	86.27 310	99.55 293	94.87 254	98.32 303	98.89 257

baseline1		95.96 278	95.44 283	97.52 266	98.51 279	93.99 289	98.39 105	96.09 336	98.21 120	98.40 205	97.76 284	86.88 306	99.63 268	95.42 245	89.27 363	98.95 247

SD-MVS		98.40 127	98.68 67	97.54 264	98.96 197	97.99 139	97.88 158	99.36 108	98.20 123	99.63 25	99.04 111	98.76 23	95.33 365	96.56 185	99.74 103	99.31 184
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
HQP_MVS		97.99 166	97.67 180	98.93 136	99.19 143	97.65 176	97.77 170	99.27 153	98.20 123	97.79 239	97.98 270	94.90 227	99.70 234	94.42 268	99.51 193	99.45 126

plane_prior2							97.77 170		98.20 123

test_0728_THIRD									98.17 126	99.08 101	99.02 115	97.89 77	99.88 67	97.07 138	99.71 118	99.70 29

E-PMN		94.17 309	94.37 304	93.58 340	96.86 346	85.71 356	90.11 361	97.07 321	98.17 126	97.82 238	97.19 312	84.62 325	98.94 352	89.77 342	97.68 323	96.09 355

EG-PatchMatch MVS		98.99 39	99.01 38	98.94 135	99.50 77	97.47 184	98.04 140	99.59 26	98.15 128	99.40 52	99.36 57	98.58 32	99.76 208	98.78 45	99.68 134	99.59 55

ETV-MVS		98.03 159	97.86 169	98.56 188	98.69 253	98.07 133	97.51 199	99.50 59	98.10 129	97.50 262	95.51 344	98.41 41	99.88 67	96.27 207	99.24 239	97.71 328

tttt0517		95.64 285	94.98 296	97.64 255	99.36 111	93.81 297	98.72 71	90.47 362	98.08 130	98.67 169	98.34 242	73.88 361	99.92 35	97.77 102	99.51 193	99.20 207

RRT_test8_iter05		95.24 293	95.13 293	95.57 320	97.32 339	87.02 351	97.99 147	99.41 93	98.06 131	99.12 93	99.05 108	66.85 369	99.85 105	98.93 36	99.47 204	99.84 8

SED-MVS		98.91 51	98.72 60	99.49 48	99.49 84	99.17 36	98.10 130	99.31 132	98.03 132	99.66 20	99.02 115	98.36 44	99.88 67	96.91 149	99.62 154	99.41 141

test_241102_TWO								99.30 141	98.03 132	99.26 77	99.02 115	97.51 109	99.88 67	96.91 149	99.60 163	99.66 34

test_241102_ONE					99.49 84	99.17 36		99.31 132	97.98 134	99.66 20	98.90 146	98.36 44	99.48 311

DVP-MVS		98.77 69	98.52 86	99.52 41	99.50 77	99.21 26	98.02 143	98.84 248	97.97 135	99.08 101	99.02 115	97.61 99	99.88 67	96.99 143	99.63 151	99.48 112
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
test0726					99.50 77	99.21 26	98.17 124	99.35 114	97.97 135	99.26 77	99.06 101	97.61 99

tfpn200view9		94.03 312	93.44 314	95.78 315	98.93 202	91.44 329	97.60 188	94.29 346	97.94 137	97.10 278	94.31 358	79.67 349	99.62 270	83.05 356	98.08 315	96.29 348

thres400		94.14 310	93.44 314	96.24 307	98.93 202	91.44 329	97.60 188	94.29 346	97.94 137	97.10 278	94.31 358	79.67 349	99.62 270	83.05 356	98.08 315	97.66 329

EMVS		93.83 315	94.02 307	93.23 344	96.83 348	84.96 357	89.77 362	96.32 333	97.92 139	97.43 268	96.36 332	86.17 312	98.93 353	87.68 348	97.73 322	95.81 356

SteuartSystems-ACMMP		98.79 64	98.54 84	99.54 29	99.73 24	99.16 40	98.23 116	99.31 132	97.92 139	98.90 137	98.90 146	98.00 70	99.88 67	96.15 214	99.72 113	99.58 61
Skip Steuart: Steuart Systems R&D Blog.
v2v482		98.56 104	98.62 74	98.37 208	99.42 105	95.81 242	97.58 191	99.16 188	97.90 141	99.28 71	99.01 122	95.98 196	99.79 183	99.33 15	99.90 44	99.51 96

FMVSNet3		97.50 202	97.24 212	98.29 215	98.08 307	95.83 241	97.86 161	98.91 235	97.89 142	98.95 127	98.95 138	87.06 305	99.81 159	97.77 102	99.69 129	99.23 202

V42		98.78 67	98.78 54	98.76 162	99.44 100	97.04 208	98.27 113	99.19 175	97.87 143	99.25 79	99.16 86	96.84 151	99.78 195	99.21 23	99.84 56	99.46 122

CSCG		98.68 86	98.50 90	99.20 92	99.45 98	98.63 84	98.56 84	99.57 35	97.87 143	98.85 148	98.04 267	97.66 93	99.84 122	96.72 171	99.81 69	99.13 222

xiu_mvs_v1_base_debu		97.86 175	98.17 139	96.92 290	98.98 194	93.91 292	96.45 267	99.17 185	97.85 145	98.41 201	97.14 317	98.47 37	99.92 35	98.02 88	99.05 265	96.92 341

xiu_mvs_v1_base		97.86 175	98.17 139	96.92 290	98.98 194	93.91 292	96.45 267	99.17 185	97.85 145	98.41 201	97.14 317	98.47 37	99.92 35	98.02 88	99.05 265	96.92 341

xiu_mvs_v1_base_debi		97.86 175	98.17 139	96.92 290	98.98 194	93.91 292	96.45 267	99.17 185	97.85 145	98.41 201	97.14 317	98.47 37	99.92 35	98.02 88	99.05 265	96.92 341

RRT_MVS		97.07 237	96.57 252	98.58 181	95.89 361	96.33 228	97.36 210	98.77 260	97.85 145	99.08 101	99.12 94	82.30 339	99.96 8	98.82 43	99.90 44	99.45 126

diffmvs		98.22 146	98.24 130	98.17 223	99.00 189	95.44 251	96.38 272	99.58 28	97.79 149	98.53 192	98.50 224	96.76 160	99.74 219	97.95 93	99.64 148	99.34 172

CANet		97.87 174	97.76 173	98.19 222	97.75 321	95.51 248	96.76 252	99.05 209	97.74 150	96.93 286	98.21 252	95.59 210	99.89 58	97.86 99	99.93 25	99.19 212

DELS-MVS		98.27 140	98.20 135	98.48 198	98.86 219	96.70 221	95.60 306	99.20 170	97.73 151	98.45 196	98.71 187	97.50 110	99.82 146	98.21 77	99.59 165	98.93 252
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
RPSCF		98.62 96	98.36 116	99.42 57	99.65 43	99.42 4	98.55 85	99.57 35	97.72 152	98.90 137	99.26 69	96.12 187	99.52 302	95.72 233	99.71 118	99.32 180

MVS_Test		98.18 150	98.36 116	97.67 251	98.48 281	94.73 269	98.18 121	99.02 218	97.69 153	98.04 226	99.11 96	97.22 133	99.56 290	98.57 58	98.90 282	98.71 280

DPE-MVS		98.59 102	98.26 128	99.57 18	99.27 124	99.15 45	97.01 234	99.39 98	97.67 154	99.44 46	98.99 125	97.53 106	99.89 58	95.40 246	99.68 134	99.66 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ab-mvs		98.41 125	98.36 116	98.59 180	99.19 143	97.23 196	99.32 15	98.81 254	97.66 155	98.62 175	99.40 53	96.82 154	99.80 168	95.88 223	99.51 193	98.75 277

MSDG		97.71 189	97.52 192	98.28 216	98.91 209	96.82 216	94.42 339	99.37 104	97.65 156	98.37 206	98.29 247	97.40 119	99.33 330	94.09 280	99.22 241	98.68 286

NCCC		97.86 175	97.47 198	99.05 120	98.61 265	98.07 133	96.98 236	98.90 236	97.63 157	97.04 283	97.93 275	95.99 195	99.66 258	95.31 247	98.82 285	99.43 135

PM-MVS		98.82 60	98.72 60	99.12 102	99.64 46	98.54 96	97.98 149	99.68 15	97.62 158	99.34 61	99.18 80	97.54 104	99.77 201	97.79 100	99.74 103	99.04 233

ACMM	96.08 12	98.91 51	98.73 58	99.48 50	99.55 65	99.14 48	98.07 134	99.37 104	97.62 158	99.04 111	98.96 134	98.84 20	99.79 183	97.43 119	99.65 146	99.49 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MP-MVS		98.46 120	98.09 149	99.54 29	99.57 55	99.22 25	98.50 93	99.19 175	97.61 160	97.58 254	98.66 198	97.40 119	99.88 67	94.72 259	99.60 163	99.54 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVS_111021_HR		98.25 144	98.08 152	98.75 164	99.09 169	97.46 185	95.97 287	99.27 153	97.60 161	97.99 228	98.25 248	98.15 62	99.38 325	96.87 157	99.57 175	99.42 138

MVS_111021_LR		98.30 136	98.12 147	98.83 149	99.16 154	98.03 137	96.09 284	99.30 141	97.58 162	98.10 220	98.24 249	98.25 50	99.34 328	96.69 174	99.65 146	99.12 223

APDe-MVS		98.99 39	98.79 53	99.60 13	99.21 136	99.15 45	98.87 62	99.48 69	97.57 163	99.35 59	99.24 72	97.83 80	99.89 58	97.88 97	99.70 123	99.75 22

API-MVS		97.04 241	96.91 231	97.42 271	97.88 316	98.23 117	98.18 121	98.50 280	97.57 163	97.39 270	96.75 322	96.77 158	99.15 346	90.16 341	99.02 272	94.88 359

DeepC-MVS	97.60 4	98.97 44	98.93 42	99.10 106	99.35 115	97.98 143	98.01 146	99.46 77	97.56 165	99.54 30	99.50 36	98.97 16	99.84 122	98.06 86	99.92 34	99.49 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSP-MVS		98.40 127	98.00 158	99.61 9	99.57 55	99.25 22	98.57 83	99.35 114	97.55 166	99.31 70	97.71 286	94.61 238	99.88 67	96.14 215	99.19 248	99.70 29
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
CP-MVS		98.70 80	98.42 107	99.52 41	99.36 111	99.12 53	98.72 71	99.36 108	97.54 167	98.30 207	98.40 233	97.86 79	99.89 58	96.53 190	99.72 113	99.56 71

v1144		98.60 99	98.66 70	98.41 204	99.36 111	95.90 238	97.58 191	99.34 120	97.51 168	99.27 73	99.15 90	96.34 183	99.80 168	99.47 12	99.93 25	99.51 96

PMMVS2		98.07 158	98.08 152	98.04 233	99.41 106	94.59 275	94.59 336	99.40 96	97.50 169	98.82 155	98.83 168	96.83 153	99.84 122	97.50 117	99.81 69	99.71 26

ITE_SJBPF				98.87 144	99.22 134	98.48 100		99.35 114	97.50 169	98.28 209	98.60 213	97.64 97	99.35 327	93.86 288	99.27 234	98.79 273

MVSTER		96.86 250	96.55 254	97.79 245	97.91 315	94.21 281	97.56 193	98.87 241	97.49 171	99.06 104	99.05 108	80.72 344	99.80 168	98.44 65	99.82 65	99.37 160

Patchmatch-RL test		97.26 222	97.02 223	97.99 236	99.52 72	95.53 247	96.13 283	99.71 10	97.47 172	99.27 73	99.16 86	84.30 329	99.62 270	97.89 94	99.77 90	98.81 267

HFP-MVS		98.71 77	98.44 103	99.51 45	99.49 84	99.16 40	98.52 88	99.31 132	97.47 172	98.58 183	98.50 224	97.97 74	99.85 105	96.57 182	99.59 165	99.53 89

MSLP-MVS++		98.02 161	98.14 146	97.64 255	98.58 270	95.19 259	97.48 201	99.23 166	97.47 172	97.90 231	98.62 209	97.04 138	98.81 356	97.55 112	99.41 210	98.94 251

ACMMPR		98.70 80	98.42 107	99.54 29	99.52 72	99.14 48	98.52 88	99.31 132	97.47 172	98.56 187	98.54 218	97.75 87	99.88 67	96.57 182	99.59 165	99.58 61

mPP-MVS		98.64 92	98.34 119	99.54 29	99.54 68	99.17 36	98.63 76	99.24 164	97.47 172	98.09 221	98.68 193	97.62 98	99.89 58	96.22 209	99.62 154	99.57 66

region2R		98.69 82	98.40 109	99.54 29	99.53 70	99.17 36	98.52 88	99.31 132	97.46 177	98.44 197	98.51 221	97.83 80	99.88 67	96.46 194	99.58 171	99.58 61

HPM-MVS++		98.10 155	97.64 185	99.48 50	99.09 169	99.13 51	97.52 197	98.75 264	97.46 177	96.90 292	97.83 280	96.01 191	99.84 122	95.82 230	99.35 220	99.46 122

CS-MVS		98.16 154	98.22 133	97.97 237	98.56 273	97.01 211	98.10 130	99.70 13	97.45 179	97.29 273	97.19 312	97.72 89	99.80 168	98.37 69	99.62 154	97.11 340

TinyColmap		97.89 171	97.98 159	97.60 257	98.86 219	94.35 278	96.21 280	99.44 83	97.45 179	99.06 104	98.88 155	97.99 73	99.28 337	94.38 272	99.58 171	99.18 214

GST-MVS		98.61 97	98.30 124	99.52 41	99.51 74	99.20 32	98.26 114	99.25 159	97.44 181	98.67 169	98.39 235	97.68 91	99.85 105	96.00 218	99.51 193	99.52 93

MVS_0304		97.64 194	97.35 205	98.52 193	97.87 317	96.69 222	98.59 81	98.05 300	97.44 181	93.74 354	98.85 162	93.69 259	99.88 67	98.11 81	99.81 69	98.98 242

v1192		98.60 99	98.66 70	98.41 204	99.27 124	95.88 239	97.52 197	99.36 108	97.41 183	99.33 62	99.20 77	96.37 181	99.82 146	99.57 6	99.92 34	99.55 79

plane_prior3						97.78 166			97.41 183	97.79 239

EIA-MVS		98.00 163	97.74 175	98.80 154	98.72 242	98.09 127	98.05 138	99.60 25	97.39 185	96.63 302	95.55 343	97.68 91	99.80 168	96.73 170	99.27 234	98.52 290

thres200		93.72 317	93.14 319	95.46 324	98.66 263	91.29 333	96.61 260	94.63 344	97.39 185	96.83 296	93.71 361	79.88 346	99.56 290	82.40 359	98.13 312	95.54 358

testgi		98.32 134	98.39 112	98.13 225	99.57 55	95.54 246	97.78 167	99.49 67	97.37 187	99.19 86	97.65 290	98.96 17	99.49 308	96.50 192	98.99 276	99.34 172

mvs_anonymous		97.83 183	98.16 142	96.87 293	98.18 301	91.89 324	97.31 214	98.90 236	97.37 187	98.83 151	99.46 43	96.28 184	99.79 183	98.90 37	98.16 310	98.95 247

EPNet_dtu		94.93 299	94.78 300	95.38 325	93.58 365	87.68 348	96.78 250	95.69 340	97.35 189	89.14 363	98.09 263	88.15 303	99.49 308	94.95 253	99.30 229	98.98 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmatch-test		96.55 262	96.34 260	97.17 280	98.35 289	93.06 306	98.40 104	97.79 304	97.33 190	98.41 201	98.67 195	83.68 333	99.69 238	95.16 248	99.31 226	98.77 275

HPM-MVS_fast		99.01 37	98.82 49	99.57 18	99.71 30	99.35 11	99.00 52	99.50 59	97.33 190	98.94 133	98.86 159	98.75 24	99.82 146	97.53 115	99.71 118	99.56 71

XVG-OURS-SEG-HR		98.49 117	98.28 126	99.14 100	99.49 84	98.83 70	96.54 261	99.48 69	97.32 192	99.11 95	98.61 212	99.33 8	99.30 334	96.23 208	98.38 302	99.28 192

DeepC-MVS_fast	96.85 6	98.30 136	98.15 144	98.75 164	98.61 265	97.23 196	97.76 172	99.09 201	97.31 193	98.75 163	98.66 198	97.56 103	99.64 265	96.10 217	99.55 182	99.39 150
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Effi-MVS+		98.02 161	97.82 171	98.62 176	98.53 278	97.19 202	97.33 212	99.68 15	97.30 194	96.68 300	97.46 303	98.56 33	99.80 168	96.63 178	98.20 307	98.86 261

XVG-OURS		98.53 113	98.34 119	99.11 104	99.50 77	98.82 72	95.97 287	99.50 59	97.30 194	99.05 109	98.98 129	99.35 7	99.32 331	95.72 233	99.68 134	99.18 214

ZNCC-MVS		98.68 86	98.40 109	99.54 29	99.57 55	99.21 26	98.46 99	99.29 148	97.28 196	98.11 219	98.39 235	98.00 70	99.87 84	96.86 159	99.64 148	99.55 79

eth_miper_zixun_eth		97.23 226	97.25 210	97.17 280	98.00 311	92.77 313	94.71 329	99.18 179	97.27 197	98.56 187	98.74 183	91.89 281	99.69 238	97.06 139	99.81 69	99.05 229

MDA-MVSNet_test_wron		97.60 197	97.66 183	97.41 272	99.04 181	93.09 305	95.27 315	98.42 283	97.26 198	98.88 144	98.95 138	95.43 217	99.73 223	97.02 140	98.72 289	99.41 141

miper_lstm_enhance		97.18 230	97.16 216	97.25 278	98.16 302	92.85 311	95.15 320	99.31 132	97.25 199	98.74 165	98.78 177	90.07 289	99.78 195	97.19 129	99.80 77	99.11 225

xiu_mvs_v2_base		97.16 232	97.49 194	96.17 309	98.54 276	92.46 317	95.45 312	98.84 248	97.25 199	97.48 264	96.49 326	98.31 49	99.90 49	96.34 203	98.68 293	96.15 353

PS-MVSNAJ		97.08 236	97.39 201	96.16 311	98.56 273	92.46 317	95.24 317	98.85 247	97.25 199	97.49 263	95.99 336	98.07 64	99.90 49	96.37 200	98.67 294	96.12 354

YYNet1		97.60 197	97.67 180	97.39 273	99.04 181	93.04 309	95.27 315	98.38 286	97.25 199	98.92 135	98.95 138	95.48 216	99.73 223	96.99 143	98.74 287	99.41 141

XVG-ACMP-BASELINE		98.56 104	98.34 119	99.22 91	99.54 68	98.59 90	97.71 176	99.46 77	97.25 199	98.98 121	98.99 125	97.54 104	99.84 122	95.88 223	99.74 103	99.23 202

CNVR-MVS		98.17 152	97.87 168	99.07 113	98.67 258	98.24 113	97.01 234	98.93 230	97.25 199	97.62 250	98.34 242	97.27 127	99.57 287	96.42 198	99.33 223	99.39 150

CANet_DTU		97.26 222	97.06 221	97.84 242	97.57 328	94.65 273	96.19 282	98.79 257	97.23 205	95.14 340	98.24 249	93.22 262	99.84 122	97.34 123	99.84 56	99.04 233

v1921920		98.54 111	98.60 79	98.38 207	99.20 140	95.76 244	97.56 193	99.36 108	97.23 205	99.38 54	99.17 84	96.02 190	99.84 122	99.57 6	99.90 44	99.54 83

MIMVSNet		96.62 261	96.25 265	97.71 250	99.04 181	94.66 272	99.16 38	96.92 326	97.23 205	97.87 233	99.10 98	86.11 314	99.65 263	91.65 325	99.21 243	98.82 264

FMVSNet5		96.01 276	95.20 291	98.41 204	97.53 331	96.10 233	98.74 68	99.50 59	97.22 208	98.03 227	99.04 111	69.80 364	99.88 67	97.27 126	99.71 118	99.25 198

thisisatest0530		95.27 292	94.45 302	97.74 249	99.19 143	94.37 277	97.86 161	90.20 363	97.17 209	98.22 211	97.65 290	73.53 362	99.90 49	96.90 154	99.35 220	98.95 247

v1240		98.55 108	98.62 74	98.32 211	99.22 134	95.58 245	97.51 199	99.45 80	97.16 210	99.45 45	99.24 72	96.12 187	99.85 105	99.60 4	99.88 49	99.55 79

ACMMP		98.75 72	98.50 90	99.52 41	99.56 62	99.16 40	98.87 62	99.37 104	97.16 210	98.82 155	99.01 122	97.71 90	99.87 84	96.29 206	99.69 129	99.54 83
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
v144192		98.54 111	98.57 82	98.45 201	99.21 136	95.98 236	97.63 184	99.36 108	97.15 212	99.32 68	99.18 80	95.84 203	99.84 122	99.50 10	99.91 40	99.54 83

OPM-MVS		98.56 104	98.32 123	99.25 87	99.41 106	98.73 79	97.13 231	99.18 179	97.10 213	98.75 163	98.92 142	98.18 58	99.65 263	96.68 175	99.56 180	99.37 160

cl_fuxian		97.36 214	97.37 203	97.31 274	98.09 306	93.25 304	95.01 323	99.16 188	97.05 214	98.77 161	98.72 186	92.88 270	99.64 265	96.93 148	99.76 99	99.05 229

cl-mvsnet____		97.02 242	96.83 236	97.58 259	97.82 319	94.04 285	94.66 332	99.16 188	97.04 215	98.63 173	98.71 187	88.68 300	99.69 238	97.00 141	99.81 69	99.00 240

cl-mvsnet1		97.02 242	96.84 235	97.58 259	97.82 319	94.03 286	94.66 332	99.16 188	97.04 215	98.63 173	98.71 187	88.69 299	99.69 238	97.00 141	99.81 69	99.01 237

PGM-MVS		98.66 89	98.37 115	99.55 26	99.53 70	99.18 35	98.23 116	99.49 67	97.01 217	98.69 167	98.88 155	98.00 70	99.89 58	95.87 226	99.59 165	99.58 61

TSAR-MVS + MP.		98.63 94	98.49 93	99.06 118	99.64 46	97.90 153	98.51 92	98.94 228	96.96 218	99.24 80	98.89 154	97.83 80	99.81 159	96.88 156	99.49 201	99.48 112
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
ACMMP_NAP		98.75 72	98.48 95	99.57 18	99.58 51	99.29 17	97.82 165	99.25 159	96.94 219	98.78 158	99.12 94	98.02 68	99.84 122	97.13 135	99.67 140	99.59 55

CVMVSNet		96.25 272	97.21 214	93.38 343	99.10 166	80.56 367	97.20 223	98.19 294	96.94 219	99.00 118	99.02 115	89.50 294	99.80 168	96.36 202	99.59 165	99.78 14

CS-MVS-test		97.75 187	97.70 178	97.90 238	98.30 293	97.66 174	97.93 152	99.65 19	96.91 221	96.27 316	96.28 333	97.00 143	99.80 168	97.64 111	99.28 232	96.24 350

CNLPA		97.17 231	96.71 242	98.55 189	98.56 273	98.05 136	96.33 274	98.93 230	96.91 221	97.06 282	97.39 306	94.38 244	99.45 317	91.66 324	99.18 250	98.14 307

DeepPCF-MVS	96.93 5	98.32 134	98.01 157	99.23 90	98.39 288	98.97 62	95.03 322	99.18 179	96.88 223	99.33 62	98.78 177	98.16 60	99.28 337	96.74 168	99.62 154	99.44 131

wuyk23d		96.06 275	97.62 187	91.38 346	98.65 264	98.57 92	98.85 65	96.95 324	96.86 224	99.90 4	99.16 86	99.18 11	98.40 359	89.23 344	99.77 90	77.18 363

AllTest		98.44 122	98.20 135	99.16 97	99.50 77	98.55 93	98.25 115	99.58 28	96.80 225	98.88 144	99.06 101	97.65 94	99.57 287	94.45 266	99.61 161	99.37 160

TestCases				99.16 97	99.50 77	98.55 93		99.58 28	96.80 225	98.88 144	99.06 101	97.65 94	99.57 287	94.45 266	99.61 161	99.37 160

SF-MVS		98.53 113	98.27 127	99.32 76	99.31 118	98.75 75	98.19 120	99.41 93	96.77 227	98.83 151	98.90 146	97.80 84	99.82 146	95.68 236	99.52 190	99.38 157

HPM-MVS		98.79 64	98.53 85	99.59 17	99.65 43	99.29 17	99.16 38	99.43 89	96.74 228	98.61 177	98.38 237	98.62 29	99.87 84	96.47 193	99.67 140	99.59 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
plane_prior						97.65 176	97.07 232		96.72 229						99.36 218

BH-untuned		96.83 251	96.75 240	97.08 283	98.74 239	93.33 303	96.71 255	98.26 289	96.72 229	98.44 197	97.37 308	95.20 221	99.47 313	91.89 322	97.43 327	98.44 295

BH-RMVSNet		96.83 251	96.58 251	97.58 259	98.47 282	94.05 284	96.67 257	97.36 314	96.70 231	97.87 233	97.98 270	95.14 223	99.44 318	90.47 340	98.58 299	99.25 198

TAMVS		98.24 145	98.05 154	98.80 154	99.07 174	97.18 203	97.88 158	98.81 254	96.66 232	99.17 91	99.21 75	94.81 233	99.77 201	96.96 147	99.88 49	99.44 131

LPG-MVS_test		98.71 77	98.46 99	99.47 53	99.57 55	98.97 62	98.23 116	99.48 69	96.60 233	99.10 98	99.06 101	98.71 26	99.83 136	95.58 242	99.78 86	99.62 44

LGP-MVS_train				99.47 53	99.57 55	98.97 62		99.48 69	96.60 233	99.10 98	99.06 101	98.71 26	99.83 136	95.58 242	99.78 86	99.62 44

CL-MVSNet_2432*1600		97.44 210	97.22 213	98.08 229	98.57 272	95.78 243	94.30 342	98.79 257	96.58 235	98.60 179	98.19 254	94.74 237	99.64 265	96.41 199	98.84 283	98.82 264

our_test_3		97.39 213	97.73 177	96.34 304	98.70 249	89.78 340	94.61 335	98.97 227	96.50 236	99.04 111	98.85 162	95.98 196	99.84 122	97.26 127	99.67 140	99.41 141

test_prior3		97.48 206	97.00 224	98.95 133	98.69 253	97.95 149	95.74 301	99.03 214	96.48 237	96.11 318	97.63 292	95.92 200	99.59 281	94.16 274	99.20 244	99.30 187

test_prior2							95.74 301		96.48 237	96.11 318	97.63 292	95.92 200		94.16 274	99.20 244

MG-MVS		96.77 254	96.61 249	97.26 277	98.31 292	93.06 306	95.93 292	98.12 297	96.45 239	97.92 229	98.73 184	93.77 257	99.39 323	91.19 334	99.04 268	99.33 178

MVP-Stereo		98.08 157	97.92 164	98.57 184	98.96 197	96.79 217	97.90 157	99.18 179	96.41 240	98.46 195	98.95 138	95.93 199	99.60 277	96.51 191	98.98 278	99.31 184
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ppachtmachnet_test		97.50 202	97.74 175	96.78 298	98.70 249	91.23 336	94.55 337	99.05 209	96.36 241	99.21 84	98.79 176	96.39 178	99.78 195	96.74 168	99.82 65	99.34 172

TSAR-MVS + GP.		98.18 150	97.98 159	98.77 161	98.71 245	97.88 154	96.32 275	98.66 271	96.33 242	99.23 83	98.51 221	97.48 115	99.40 321	97.16 131	99.46 205	99.02 236

testdata1							95.44 313		96.32 243

LF4IMVS		97.90 169	97.69 179	98.52 193	99.17 152	97.66 174	97.19 226	99.47 75	96.31 244	97.85 235	98.20 253	96.71 164	99.52 302	94.62 260	99.72 113	98.38 299

#test#		98.50 116	98.16 142	99.51 45	99.49 84	99.16 40	98.03 141	99.31 132	96.30 245	98.58 183	98.50 224	97.97 74	99.85 105	95.68 236	99.59 165	99.53 89

test-LLR		93.90 314	93.85 308	94.04 335	96.53 351	84.62 359	94.05 346	92.39 357	96.17 246	94.12 348	95.07 348	82.30 339	99.67 250	95.87 226	98.18 308	97.82 319

test0.0.03 1		94.51 302	93.69 311	96.99 286	96.05 358	93.61 302	94.97 324	93.49 352	96.17 246	97.57 256	94.88 354	82.30 339	99.01 351	93.60 294	94.17 359	98.37 301

Anonymous20231206		98.21 147	98.21 134	98.20 221	99.51 74	95.43 252	98.13 125	99.32 127	96.16 248	98.93 134	98.82 171	96.00 192	99.83 136	97.32 124	99.73 106	99.36 166

SCA		96.41 268	96.66 247	95.67 317	98.24 297	88.35 345	95.85 297	96.88 327	96.11 249	97.67 247	98.67 195	93.10 265	99.85 105	94.16 274	99.22 241	98.81 267

MS-PatchMatch		97.68 191	97.75 174	97.45 269	98.23 299	93.78 298	97.29 215	98.84 248	96.10 250	98.64 172	98.65 200	96.04 189	99.36 326	96.84 160	99.14 255	99.20 207

HQP-NCC					98.67 258		96.29 276		96.05 251	95.55 331

ACMP_Plane					98.67 258		96.29 276		96.05 251	95.55 331

HQP-MVS		97.00 245	96.49 256	98.55 189	98.67 258	96.79 217	96.29 276	99.04 212	96.05 251	95.55 331	96.84 320	93.84 253	99.54 296	92.82 309	99.26 237	99.32 180

PHI-MVS		98.29 139	97.95 161	99.34 72	98.44 285	99.16 40	98.12 127	99.38 100	96.01 254	98.06 223	98.43 231	97.80 84	99.67 250	95.69 235	99.58 171	99.20 207

miper_ehance_all_eth		97.06 238	97.03 222	97.16 282	97.83 318	93.06 306	94.66 332	99.09 201	95.99 255	98.69 167	98.45 230	92.73 273	99.61 276	96.79 162	99.03 269	98.82 264

AUN-MVS		96.24 273	95.45 282	98.60 179	98.70 249	97.22 198	97.38 208	97.65 309	95.95 256	95.53 335	97.96 274	82.11 343	99.79 183	96.31 204	97.44 326	98.80 272

MVE	83.40 22	92.50 327	91.92 330	94.25 334	98.83 226	91.64 326	92.71 355	83.52 368	95.92 257	86.46 366	95.46 346	95.20 221	95.40 364	80.51 361	98.64 295	95.73 357
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CDS-MVSNet		97.69 190	97.35 205	98.69 168	98.73 240	97.02 210	96.92 242	98.75 264	95.89 258	98.59 181	98.67 195	92.08 280	99.74 219	96.72 171	99.81 69	99.32 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
D2MVS		97.84 181	97.84 170	97.83 243	99.14 159	94.74 268	96.94 238	98.88 239	95.84 259	98.89 140	98.96 134	94.40 243	99.69 238	97.55 112	99.95 16	99.05 229

testtj		97.79 185	97.25 210	99.42 57	99.03 184	98.85 68	97.78 167	99.18 179	95.83 260	98.12 218	98.50 224	95.50 214	99.86 91	92.23 320	99.07 264	99.54 83

PAPM_NR		96.82 253	96.32 261	98.30 214	99.07 174	96.69 222	97.48 201	98.76 261	95.81 261	96.61 304	96.47 328	94.12 251	99.17 344	90.82 339	97.78 321	99.06 228

ACMP	95.32 15	98.41 125	98.09 149	99.36 64	99.51 74	98.79 74	97.68 179	99.38 100	95.76 262	98.81 157	98.82 171	98.36 44	99.82 146	94.75 256	99.77 90	99.48 112
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MCST-MVS		98.00 163	97.63 186	99.10 106	99.24 129	98.17 122	96.89 245	98.73 267	95.66 263	97.92 229	97.70 288	97.17 134	99.66 258	96.18 213	99.23 240	99.47 120

AdaColmap		97.14 233	96.71 242	98.46 200	98.34 290	97.80 165	96.95 237	98.93 230	95.58 264	96.92 287	97.66 289	95.87 202	99.53 298	90.97 335	99.14 255	98.04 310

ETH3D-3000-0.1		98.03 159	97.62 187	99.29 77	99.11 162	98.80 73	97.47 203	99.32 127	95.54 265	98.43 200	98.62 209	96.61 168	99.77 201	93.95 284	99.49 201	99.30 187

pmmvs-eth3d		98.47 119	98.34 119	98.86 146	99.30 121	97.76 167	97.16 229	99.28 150	95.54 265	99.42 48	99.19 78	97.27 127	99.63 268	97.89 94	99.97 11	99.20 207

9.14			97.78 172		99.07 174		97.53 196	99.32 127	95.53 267	98.54 191	98.70 190	97.58 101	99.76 208	94.32 273	99.46 205

GA-MVS		95.86 280	95.32 288	97.49 267	98.60 267	94.15 283	93.83 349	97.93 302	95.49 268	96.68 300	97.42 305	83.21 334	99.30 334	96.22 209	98.55 300	99.01 237

tpmvs		95.02 298	95.25 289	94.33 333	96.39 356	85.87 353	98.08 133	96.83 328	95.46 269	95.51 336	98.69 191	85.91 315	99.53 298	94.16 274	96.23 346	97.58 332

KD-MVS_2432*1600		92.87 324	91.99 328	95.51 322	91.37 366	89.27 341	94.07 344	98.14 295	95.42 270	97.25 275	96.44 329	67.86 366	99.24 339	91.28 331	96.08 348	98.02 311

miper_refine_blended		92.87 324	91.99 328	95.51 322	91.37 366	89.27 341	94.07 344	98.14 295	95.42 270	97.25 275	96.44 329	67.86 366	99.24 339	91.28 331	96.08 348	98.02 311

UnsupCasMVSNet_bld		97.30 219	96.92 229	98.45 201	99.28 123	96.78 220	96.20 281	99.27 153	95.42 270	98.28 209	98.30 246	93.16 263	99.71 232	94.99 251	97.37 329	98.87 260

PatchmatchNet		95.58 286	95.67 275	95.30 326	97.34 338	87.32 349	97.65 183	96.65 329	95.30 273	97.07 281	98.69 191	84.77 323	99.75 215	94.97 252	98.64 295	98.83 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
N_pmnet		97.63 196	97.17 215	98.99 129	99.27 124	97.86 156	95.98 286	93.41 353	95.25 274	99.47 42	98.90 146	95.63 208	99.85 105	96.91 149	99.73 106	99.27 194

MVS-HIRNet		94.32 305	95.62 276	90.42 347	98.46 283	75.36 368	96.29 276	89.13 365	95.25 274	95.38 337	99.75 7	92.88 270	99.19 343	94.07 281	99.39 213	96.72 346

OMC-MVS		97.88 173	97.49 194	99.04 122	98.89 215	98.63 84	96.94 238	99.25 159	95.02 276	98.53 192	98.51 221	97.27 127	99.47 313	93.50 298	99.51 193	99.01 237

tpmrst		95.07 296	95.46 281	93.91 337	97.11 343	84.36 361	97.62 185	96.96 323	94.98 277	96.35 314	98.80 174	85.46 319	99.59 281	95.60 240	96.23 346	97.79 324

APD-MVS		98.10 155	97.67 180	99.42 57	99.11 162	98.93 66	97.76 172	99.28 150	94.97 278	98.72 166	98.77 179	97.04 138	99.85 105	93.79 290	99.54 183	99.49 104
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WTY-MVS		96.67 258	96.27 264	97.87 241	98.81 231	94.61 274	96.77 251	97.92 303	94.94 279	97.12 277	97.74 285	91.11 284	99.82 146	93.89 286	98.15 311	99.18 214

CPTT-MVS		97.84 181	97.36 204	99.27 82	99.31 118	98.46 101	98.29 111	99.27 153	94.90 280	97.83 236	98.37 239	94.90 227	99.84 122	93.85 289	99.54 183	99.51 96

MP-MVS-pluss		98.57 103	98.23 132	99.60 13	99.69 38	99.35 11	97.16 229	99.38 100	94.87 281	98.97 124	98.99 125	98.01 69	99.88 67	97.29 125	99.70 123	99.58 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
Fast-Effi-MVS+		97.67 192	97.38 202	98.57 184	98.71 245	97.43 187	97.23 219	99.45 80	94.82 282	96.13 317	96.51 325	98.52 35	99.91 45	96.19 211	98.83 284	98.37 301

ET-MVSNet_ETH3D		94.30 307	93.21 317	97.58 259	98.14 303	94.47 276	94.78 328	93.24 355	94.72 283	89.56 362	95.87 339	78.57 355	99.81 159	96.91 149	97.11 336	98.46 292

EPMVS		93.72 317	93.27 316	95.09 328	96.04 359	87.76 347	98.13 125	85.01 367	94.69 284	96.92 287	98.64 203	78.47 357	99.31 332	95.04 249	96.46 343	98.20 304

cl-mvsnet2		95.79 282	95.39 286	96.98 287	96.77 349	92.79 312	94.40 340	98.53 278	94.59 285	97.89 232	98.17 255	82.82 338	99.24 339	96.37 200	99.03 269	98.92 253

PVSNet_BlendedMVS		97.55 200	97.53 191	97.60 257	98.92 206	93.77 299	96.64 258	99.43 89	94.49 286	97.62 250	99.18 80	96.82 154	99.67 250	94.73 257	99.93 25	99.36 166

sss		97.21 227	96.93 227	98.06 231	98.83 226	95.22 258	96.75 253	98.48 281	94.49 286	97.27 274	97.90 276	92.77 272	99.80 168	96.57 182	99.32 224	99.16 221

tpm		94.67 301	94.34 305	95.66 318	97.68 327	88.42 344	97.88 158	94.90 342	94.46 288	96.03 323	98.56 217	78.66 353	99.79 183	95.88 223	95.01 354	98.78 274

CLD-MVS		97.49 204	97.16 216	98.48 198	99.07 174	97.03 209	94.71 329	99.21 168	94.46 288	98.06 223	97.16 315	97.57 102	99.48 311	94.46 265	99.78 86	98.95 247
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TESTMET0.1,1		92.19 331	91.77 331	93.46 341	96.48 353	82.80 364	94.05 346	91.52 360	94.45 290	94.00 351	94.88 354	66.65 370	99.56 290	95.78 231	98.11 313	98.02 311

PVSNet_Blended_VisFu		98.17 152	98.15 144	98.22 220	99.73 24	95.15 260	97.36 210	99.68 15	94.45 290	98.99 119	99.27 67	96.87 150	99.94 23	97.13 135	99.91 40	99.57 66

MDTV_nov1_ep13			95.22 290		97.06 344	83.20 363	97.74 174	96.16 334	94.37 292	96.99 285	98.83 168	83.95 331	99.53 298	93.90 285	97.95 319

TR-MVS		95.55 287	95.12 294	96.86 296	97.54 330	93.94 290	96.49 266	96.53 331	94.36 293	97.03 284	96.61 324	94.26 247	99.16 345	86.91 350	96.31 345	97.47 336

jason		97.45 209	97.35 205	97.76 247	99.24 129	93.93 291	95.86 295	98.42 283	94.24 294	98.50 194	98.13 256	94.82 231	99.91 45	97.22 128	99.73 106	99.43 135
jason: jason.
HyFIR lowres test		97.19 229	96.60 250	98.96 132	99.62 50	97.28 194	95.17 318	99.50 59	94.21 295	99.01 115	98.32 245	86.61 308	99.99 2	97.10 137	99.84 56	99.60 49

ETH3D cwj APD-0.16		97.55 200	97.00 224	99.19 93	98.51 279	98.64 83	96.85 246	99.13 195	94.19 296	97.65 248	98.40 233	95.78 204	99.81 159	93.37 301	99.16 251	99.12 223

SMA-MVS		98.40 127	98.03 156	99.51 45	99.16 154	99.21 26	98.05 138	99.22 167	94.16 297	98.98 121	99.10 98	97.52 108	99.79 183	96.45 195	99.64 148	99.53 89
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
ZD-MVS					99.01 188	98.84 69		99.07 204	94.10 298	98.05 225	98.12 259	96.36 182	99.86 91	92.70 314	99.19 248

thisisatest0515		94.12 311	93.16 318	96.97 288	98.60 267	92.90 310	93.77 350	90.61 361	94.10 298	96.91 289	95.87 339	74.99 360	99.80 168	94.52 263	99.12 261	98.20 304

USDC		97.41 212	97.40 200	97.44 270	98.94 200	93.67 301	95.17 318	99.53 53	94.03 300	98.97 124	99.10 98	95.29 219	99.34 328	95.84 229	99.73 106	99.30 187

test-mter		92.33 329	91.76 332	94.04 335	96.53 351	84.62 359	94.05 346	92.39 357	94.00 301	94.12 348	95.07 348	65.63 372	99.67 250	95.87 226	98.18 308	97.82 319

baseline2		93.73 316	92.83 322	96.42 303	97.70 325	91.28 334	96.84 248	89.77 364	93.96 302	92.44 357	95.93 337	79.14 352	99.77 201	92.94 305	96.76 341	98.21 303

pmmvs5		97.64 194	97.49 194	98.08 229	99.14 159	95.12 262	96.70 256	99.05 209	93.77 303	98.62 175	98.83 168	93.23 261	99.75 215	98.33 74	99.76 99	99.36 166

BH-w/o		95.13 295	94.89 299	95.86 313	98.20 300	91.31 332	95.65 304	97.37 313	93.64 304	96.52 307	95.70 341	93.04 268	99.02 349	88.10 347	95.82 350	97.24 338

pmmvs4		97.58 199	97.28 209	98.51 195	98.84 224	96.93 214	95.40 314	98.52 279	93.60 305	98.61 177	98.65 200	95.10 224	99.60 277	96.97 146	99.79 82	98.99 241

CHOSEN 280x420		95.51 289	95.47 280	95.65 319	98.25 296	88.27 346	93.25 353	98.88 239	93.53 306	94.65 343	97.15 316	86.17 312	99.93 28	97.41 120	99.93 25	98.73 279

lupinMVS		97.06 238	96.86 233	97.65 253	98.88 216	93.89 295	95.48 311	97.97 301	93.53 306	98.16 214	97.58 294	93.81 255	99.91 45	96.77 165	99.57 175	99.17 218

PatchMatch-RL		97.24 225	96.78 238	98.61 178	99.03 184	97.83 159	96.36 273	99.06 205	93.49 308	97.36 272	97.78 282	95.75 205	99.49 308	93.44 299	98.77 286	98.52 290

DP-MVS Recon		97.33 217	96.92 229	98.57 184	99.09 169	97.99 139	96.79 249	99.35 114	93.18 309	97.71 244	98.07 265	95.00 226	99.31 332	93.97 282	99.13 258	98.42 297

1112_ss		97.29 221	96.86 233	98.58 181	99.34 117	96.32 229	96.75 253	99.58 28	93.14 310	96.89 293	97.48 301	92.11 279	99.86 91	96.91 149	99.54 183	99.57 66

IU-MVS					99.49 84	99.15 45		98.87 241	92.97 311	99.41 49				96.76 166	99.62 154	99.66 34

F-COLMAP		97.30 219	96.68 244	99.14 100	99.19 143	98.39 104	97.27 218	99.30 141	92.93 312	96.62 303	98.00 268	95.73 206	99.68 247	92.62 315	98.46 301	99.35 170

FPMVS		93.44 320	92.23 325	97.08 283	99.25 128	97.86 156	95.61 305	97.16 320	92.90 313	93.76 353	98.65 200	75.94 359	95.66 363	79.30 363	97.49 324	97.73 326

DSMNet-mixed		97.42 211	97.60 189	96.87 293	99.15 158	91.46 328	98.54 86	99.12 197	92.87 314	97.58 254	99.63 20	96.21 185	99.90 49	95.74 232	99.54 183	99.27 194

dp		93.47 319	93.59 313	93.13 345	96.64 350	81.62 366	97.66 181	96.42 332	92.80 315	96.11 318	98.64 203	78.55 356	99.59 281	93.31 302	92.18 362	98.16 306

PVSNet	93.40 17	95.67 284	95.70 273	95.57 320	98.83 226	88.57 343	92.50 356	97.72 306	92.69 316	96.49 311	96.44 329	93.72 258	99.43 319	93.61 293	99.28 232	98.71 280

new_pmnet		96.99 246	96.76 239	97.67 251	98.72 242	94.89 266	95.95 291	98.20 292	92.62 317	98.55 189	98.54 218	94.88 230	99.52 302	93.96 283	99.44 208	98.59 289

原ACMM1				98.35 209	98.90 210	96.25 231		98.83 253	92.48 318	96.07 321	98.10 261	95.39 218	99.71 232	92.61 316	98.99 276	99.08 226

IB-MVS	91.63 19	92.24 330	90.90 334	96.27 306	97.22 342	91.24 335	94.36 341	93.33 354	92.37 319	92.24 358	94.58 357	66.20 371	99.89 58	93.16 304	94.63 356	97.66 329
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
CR-MVSNet		96.28 271	95.95 268	97.28 276	97.71 323	94.22 279	98.11 128	98.92 233	92.31 320	96.91 289	99.37 54	85.44 320	99.81 159	97.39 121	97.36 331	97.81 321

HY-MVS	95.94 13	95.90 279	95.35 287	97.55 263	97.95 312	94.79 267	98.81 67	96.94 325	92.28 321	95.17 339	98.57 216	89.90 291	99.75 215	91.20 333	97.33 333	98.10 308

DWT-MVSNet_test		92.75 326	92.05 327	94.85 329	96.48 353	87.21 350	97.83 164	94.99 341	92.22 322	92.72 356	94.11 360	70.75 363	99.46 315	95.01 250	94.33 358	97.87 317

MAR-MVS		96.47 266	95.70 273	98.79 156	97.92 314	99.12 53	98.28 112	98.60 275	92.16 323	95.54 334	96.17 334	94.77 236	99.52 302	89.62 343	98.23 305	97.72 327
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
DPM-MVS		96.32 269	95.59 278	98.51 195	98.76 236	97.21 200	94.54 338	98.26 289	91.94 324	96.37 313	97.25 311	93.06 267	99.43 319	91.42 330	98.74 287	98.89 257

agg_prior1		97.06 238	96.40 258	99.03 123	98.68 256	97.99 139	95.76 299	99.01 221	91.73 325	95.59 327	97.50 299	96.49 173	99.77 201	93.71 291	99.14 255	99.34 172

train_agg		97.10 234	96.45 257	99.07 113	98.71 245	98.08 131	95.96 289	99.03 214	91.64 326	95.85 324	97.53 296	96.47 174	99.76 208	93.67 292	99.16 251	99.36 166

test_8					98.67 258	98.01 138	95.91 294	99.02 218	91.64 326	95.79 326	97.50 299	96.47 174	99.76 208

CHOSEN 1792x2688		97.49 204	97.14 219	98.54 192	99.68 39	96.09 235	96.50 265	99.62 22	91.58 328	98.84 150	98.97 131	92.36 276	99.88 67	96.76 166	99.95 16	99.67 33

PMMVS		96.51 263	95.98 267	98.09 226	97.53 331	95.84 240	94.92 325	98.84 248	91.58 328	96.05 322	95.58 342	95.68 207	99.66 258	95.59 241	98.09 314	98.76 276

Test_1112_low_res		96.99 246	96.55 254	98.31 213	99.35 115	95.47 250	95.84 298	99.53 53	91.51 330	96.80 298	98.48 229	91.36 283	99.83 136	96.58 180	99.53 187	99.62 44

TEST9					98.71 245	98.08 131	95.96 289	99.03 214	91.40 331	95.85 324	97.53 296	96.52 171	99.76 208

PAPR		95.29 291	94.47 301	97.75 248	97.50 335	95.14 261	94.89 326	98.71 269	91.39 332	95.35 338	95.48 345	94.57 239	99.14 347	84.95 353	97.37 329	98.97 246

1314		95.74 283	95.60 277	96.17 309	97.53 331	92.75 314	98.07 134	98.31 288	91.22 333	94.25 346	96.68 323	95.53 211	99.03 348	91.64 326	97.18 334	96.74 345

CDPH-MVS		97.26 222	96.66 247	99.07 113	99.00 189	98.15 123	96.03 285	99.01 221	91.21 334	97.79 239	97.85 279	96.89 149	99.69 238	92.75 312	99.38 216	99.39 150

miper_enhance_ethall		96.01 276	95.74 271	96.81 297	96.41 355	92.27 321	93.69 351	98.89 238	91.14 335	98.30 207	97.35 310	90.58 286	99.58 286	96.31 204	99.03 269	98.60 287

PVSNet_Blended		96.88 249	96.68 244	97.47 268	98.92 206	93.77 299	94.71 329	99.43 89	90.98 336	97.62 250	97.36 309	96.82 154	99.67 250	94.73 257	99.56 180	98.98 242

PLC	94.65 16	96.51 263	95.73 272	98.85 147	98.75 238	97.91 152	96.42 270	99.06 205	90.94 337	95.59 327	97.38 307	94.41 242	99.59 281	90.93 336	98.04 318	99.05 229
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ADS-MVSNet2		95.43 290	94.98 296	96.76 299	98.14 303	91.74 325	97.92 154	97.76 305	90.23 338	96.51 308	98.91 143	85.61 317	99.85 105	92.88 307	96.90 337	98.69 283

ADS-MVSNet		95.24 293	94.93 298	96.18 308	98.14 303	90.10 339	97.92 154	97.32 317	90.23 338	96.51 308	98.91 143	85.61 317	99.74 219	92.88 307	96.90 337	98.69 283

QAPM		97.31 218	96.81 237	98.82 150	98.80 233	97.49 183	99.06 48	99.19 175	90.22 340	97.69 246	99.16 86	96.91 148	99.90 49	90.89 338	99.41 210	99.07 227

PVSNet_0	89.98 21	91.15 333	90.30 336	93.70 339	97.72 322	84.34 362	90.24 360	97.42 312	90.20 341	93.79 352	93.09 362	90.90 285	98.89 355	86.57 351	72.76 365	97.87 317

testdata				98.09 226	98.93 202	95.40 253		98.80 256	90.08 342	97.45 266	98.37 239	95.26 220	99.70 234	93.58 295	98.95 280	99.17 218

MDTV_nov1_ep13_2view						74.92 369	97.69 178		90.06 343	97.75 242		85.78 316		93.52 296		98.69 283

OpenMVS	96.65 7	97.09 235	96.68 244	98.32 211	98.32 291	97.16 205	98.86 64	99.37 104	89.48 344	96.29 315	99.15 90	96.56 169	99.90 49	92.90 306	99.20 244	97.89 315

无先验							95.74 301	98.74 266	89.38 345				99.73 223	92.38 318		99.22 206

CostFormer		93.97 313	93.78 310	94.51 332	97.53 331	85.83 355	97.98 149	95.96 337	89.29 346	94.99 342	98.63 207	78.63 354	99.62 270	94.54 262	96.50 342	98.09 309

CMPMVS	75.91 23	96.29 270	95.44 283	98.84 148	96.25 357	98.69 82	97.02 233	99.12 197	88.90 347	97.83 236	98.86 159	89.51 293	98.90 354	91.92 321	99.51 193	98.92 253
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ETH3 D test6400		96.46 267	95.59 278	99.08 110	98.88 216	98.21 119	96.53 262	99.18 179	88.87 348	97.08 280	97.79 281	93.64 260	99.77 201	88.92 345	99.40 212	99.28 192

pmmvs3		95.03 297	94.40 303	96.93 289	97.70 325	92.53 316	95.08 321	97.71 307	88.57 349	97.71 244	98.08 264	79.39 351	99.82 146	96.19 211	99.11 262	98.43 296

旧先验2							95.76 299		88.56 350	97.52 260			99.66 258	94.48 264

gm-plane-assit					94.83 363	81.97 365			88.07 351		94.99 351		99.60 277	91.76 323

1121		96.73 255	96.00 266	98.91 139	98.95 199	97.76 167	98.07 134	98.73 267	87.65 352	96.54 305	98.13 256	94.52 240	99.73 223	92.38 318	99.02 272	99.24 201

新几何1				98.91 139	98.94 200	97.76 167		98.76 261	87.58 353	96.75 299	98.10 261	94.80 234	99.78 195	92.73 313	99.00 275	99.20 207

PAPM		91.88 332	90.34 335	96.51 301	98.06 308	92.56 315	92.44 357	97.17 319	86.35 354	90.38 361	96.01 335	86.61 308	99.21 342	70.65 365	95.43 352	97.75 325

tpm2		93.09 323	92.58 324	94.62 331	97.56 329	86.53 352	97.66 181	95.79 339	86.15 355	94.07 350	98.23 251	75.95 358	99.53 298	90.91 337	96.86 340	97.81 321

test222					98.92 206	96.93 214	95.54 307	98.78 259	85.72 356	96.86 295	98.11 260	94.43 241			99.10 263	99.23 202

cascas		94.79 300	94.33 306	96.15 312	96.02 360	92.36 320	92.34 358	99.26 158	85.34 357	95.08 341	94.96 353	92.96 269	98.53 358	94.41 271	98.59 298	97.56 333

OpenMVS_ROB	95.38 14	95.84 281	95.18 292	97.81 244	98.41 287	97.15 206	97.37 209	98.62 274	83.86 358	98.65 171	98.37 239	94.29 246	99.68 247	88.41 346	98.62 297	96.60 347

TAPA-MVS	96.21 11	96.63 260	95.95 268	98.65 170	98.93 202	98.09 127	96.93 240	99.28 150	83.58 359	98.13 217	97.78 282	96.13 186	99.40 321	93.52 296	99.29 231	98.45 294
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
tpm cat1		93.29 321	93.13 320	93.75 338	97.39 337	84.74 358	97.39 207	97.65 309	83.39 360	94.16 347	98.41 232	82.86 337	99.39 323	91.56 328	95.35 353	97.14 339

114514_t		96.50 265	95.77 270	98.69 168	99.48 92	97.43 187	97.84 163	99.55 46	81.42 361	96.51 308	98.58 215	95.53 211	99.67 250	93.41 300	99.58 171	98.98 242

PCF-MVS	92.86 18	94.36 304	93.00 321	98.42 203	98.70 249	97.56 180	93.16 354	99.11 199	79.59 362	97.55 257	97.43 304	92.19 277	99.73 223	79.85 362	99.45 207	97.97 314
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS		93.19 322	92.09 326	96.50 302	96.91 345	94.03 286	98.07 134	98.06 299	68.01 363	94.56 345	96.48 327	95.96 198	99.30 334	83.84 355	96.89 339	96.17 351

DeepMVS_CX				93.44 342	98.24 297	94.21 281		94.34 345	64.28 364	91.34 360	94.87 356	89.45 295	92.77 366	77.54 364	93.14 360	93.35 361

tmp_tt		78.77 335	78.73 338	78.90 349	58.45 370	74.76 370	94.20 343	78.26 371	39.16 365	86.71 365	92.82 363	80.50 345	75.19 367	86.16 352	92.29 361	86.74 362

test_method		79.78 334	79.50 337	80.62 348	80.21 369	45.76 371	70.82 363	98.41 285	31.08 366	80.89 367	97.71 286	84.85 322	97.37 362	91.51 329	80.03 364	98.75 277

test123		17.04 338	20.11 341	7.82 350	10.25 372	4.91 372	94.80 327	4.47 373	4.93 367	10.00 369	24.28 367	9.69 373	3.64 368	10.14 366	12.43 367	14.92 364

testmvs		17.12 337	20.53 340	6.87 351	12.05 371	4.20 373	93.62 352	6.73 372	4.62 368	10.41 368	24.33 366	8.28 374	3.56 369	9.69 367	15.07 366	12.86 365

uanet_test		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

cdsmvs_eth3d_5k		24.66 336	32.88 339	0.00 352	0.00 373	0.00 374	0.00 364	99.10 200	0.00 369	0.00 370	97.58 294	99.21 10	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		8.17 339	10.90 342	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	98.07 64	0.00 370	0.00 368	0.00 368	0.00 366

sosnet-low-res		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

sosnet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uncertanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

Regformer		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

ab-mvs-re		8.12 340	10.83 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	97.48 301	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

uanet		0.00 341	0.00 344	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

eth-test2					0.00 373

eth-test					0.00 373

OPU-MVS				98.82 150	98.59 269	98.30 109	98.10 130				98.52 220	98.18 58	98.75 357	94.62 260	99.48 203	99.41 141

test_0728_SECOND				99.60 13	99.50 77	99.23 24	98.02 143	99.32 127					99.88 67	96.99 143	99.63 151	99.68 31

GSMVS																98.81 267

test_part2					99.36 111	99.10 56				99.05 109

sam_mvs1												84.74 324				98.81 267

sam_mvs												84.29 330

ambc				98.24 219	98.82 229	95.97 237	98.62 77	99.00 224		99.27 73	99.21 75	96.99 144	99.50 307	96.55 188	99.50 200	99.26 197

MTGPA								99.20 170

test_post1							97.59 190				20.48 369	83.07 336	99.66 258	94.16 274

test_post											21.25 368	83.86 332	99.70 234

patchmatchnet-post											98.77 179	84.37 327	99.85 105

GG-mvs-BLEND				94.76 330	94.54 364	92.13 323	99.31 18	80.47 370		88.73 364	91.01 364	67.59 368	98.16 361	82.30 360	94.53 357	93.98 360

MTMP							97.93 152	91.91 359

test9_res														93.28 303	99.15 254	99.38 157

agg_prior2														92.50 317	99.16 251	99.37 160

agg_prior					98.68 256	97.99 139		99.01 221		95.59 327			99.77 201

test_prior4						97.97 144	95.86 295

test_prior				98.95 133	98.69 253	97.95 149		99.03 214					99.59 281			99.30 187

新几何2							95.93 292

旧先验1					98.82 229	97.45 186		98.76 261			98.34 242	95.50 214			99.01 274	99.23 202

原ACMM2							95.53 308

testdata2													99.79 183	92.80 311

segment_acmp												97.02 141

test12				98.93 136	98.58 270	97.83 159		98.66 271		96.53 306		95.51 213	99.69 238		99.13 258	99.27 194

plane_prior7					99.19 143	97.87 155

plane_prior6					98.99 193	97.70 173						94.90 227

plane_prior5								99.27 153					99.70 234	94.42 268	99.51 193	99.45 126

plane_prior4											97.98 270

plane_prior1					99.05 180

n2								0.00 374

nn								0.00 374

door-mid								99.57 35

lessismore_v0				98.97 130	99.73 24	97.53 182		86.71 366		99.37 56	99.52 35	89.93 290	99.92 35	98.99 34	99.72 113	99.44 131

test11								98.87 241

door								99.41 93

HQP5-MVS						96.79 217

BP-MVS														92.82 309

HQP4-MVS										95.56 330			99.54 296			99.32 180

HQP3-MVS								99.04 212							99.26 237

HQP2-MVS												93.84 253

NP-MVS					98.84 224	97.39 189					96.84 320

ACMMP++_ref															99.77 90

ACMMP++															99.68 134

Test By Simon												96.52 171

High-resolution multi-view benchmark