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.

CHOSEN 1792x2688		97.12 107	96.80 101	98.08 121	99.30 71	94.56 209	98.05 213	99.71 1	93.57 195	97.09 131	98.91 96	88.17 202	99.89 35	96.87 98	99.56 76	99.81 8

HyFIR lowres test		96.90 115	96.49 119	98.14 116	99.33 61	95.56 162	97.38 262	99.65 2	92.34 239	97.61 118	98.20 168	89.29 172	99.10 181	96.97 85	97.60 166	99.77 20

MVS_111021_LR		98.34 46	98.23 39	98.67 78	99.27 79	96.90 102	97.95 222	99.58 3	97.14 41	98.44 68	99.01 81	95.03 69	99.62 126	97.91 38	99.75 38	99.50 88

MVS_111021_HR		98.47 36	98.34 26	98.88 70	99.22 90	97.32 83	97.91 225	99.58 3	97.20 37	98.33 74	99.00 82	95.99 35	99.64 121	98.05 35	99.76 32	99.69 48

PGM-MVS		98.49 34	98.23 39	99.27 38	99.72 12	98.08 58	98.99 60	99.49 5	95.43 104	99.03 30	99.32 30	95.56 46	99.94 3	96.80 102	99.77 26	99.78 13

ACMMP		98.23 52	97.95 52	99.09 57	99.74 7	97.62 74	99.03 52	99.41 6	95.98 81	97.60 120	99.36 26	94.45 85	99.93 15	97.14 79	98.85 118	99.70 45
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
CSCG		97.85 64	97.74 59	98.20 113	99.67 26	95.16 177	99.22 25	99.32 7	93.04 213	97.02 137	98.92 95	95.36 57	99.91 30	97.43 70	99.64 60	99.52 82

PVSNet_BlendedMVS		96.73 120	96.60 114	97.12 175	99.25 82	95.35 172	98.26 187	99.26 8	94.28 157	97.94 96	97.46 226	92.74 105	99.81 66	96.88 95	93.32 242	96.20 305

PVSNet_Blended		97.38 94	97.12 87	98.14 116	99.25 82	95.35 172	97.28 273	99.26 8	93.13 211	97.94 96	98.21 167	92.74 105	99.81 66	96.88 95	99.40 95	99.27 121

UniMVSNet_NR-MVSNet		95.71 158	95.15 166	97.40 164	96.84 261	96.97 98	98.74 109	99.24 10	95.16 120	93.88 233	97.72 207	91.68 127	98.31 270	95.81 133	87.25 314	96.92 230

WR-MVS_H		95.05 195	94.46 198	96.81 194	96.86 260	95.82 154	99.24 20	99.24 10	93.87 175	92.53 279	96.84 280	90.37 156	98.24 278	93.24 213	87.93 306	96.38 298

FC-MVSNet-test		96.42 131	96.05 131	97.53 158	96.95 253	97.27 86	99.36 8	99.23 12	95.83 86	93.93 230	98.37 149	92.00 121	98.32 268	96.02 127	92.72 250	97.00 225

VPA-MVSNet		95.75 156	95.11 169	97.69 146	97.24 233	97.27 86	98.94 70	99.23 12	95.13 122	95.51 180	97.32 235	85.73 248	98.91 203	97.33 75	89.55 287	96.89 238

FIs		96.51 128	96.12 130	97.67 148	97.13 244	97.54 77	99.36 8	99.22 14	95.89 83	94.03 228	98.35 151	91.98 122	98.44 249	96.40 116	92.76 249	97.01 224

tfpnnormal		93.66 262	92.70 270	96.55 219	96.94 254	95.94 146	98.97 64	99.19 15	91.04 282	91.38 297	97.34 233	84.94 260	98.61 231	85.45 319	89.02 296	95.11 321

UniMVSNet (Re)		95.78 155	95.19 165	97.58 154	96.99 252	97.47 79	98.79 104	99.18 16	95.60 96	93.92 231	97.04 261	91.68 127	98.48 243	95.80 135	87.66 309	96.79 248

PVSNet_Blended_VisFu		97.70 71	97.46 74	98.44 96	99.27 79	95.91 151	98.63 133	99.16 17	94.48 153	97.67 112	98.88 98	92.80 104	99.91 30	97.11 80	99.12 106	99.50 88

CHOSEN 280x420		97.18 104	97.18 86	97.20 169	98.81 120	93.27 250	95.78 324	99.15 18	95.25 116	96.79 150	98.11 174	92.29 111	99.07 184	98.56 8	99.85 3	99.25 123

D2MVS		95.18 188	95.08 170	95.48 267	97.10 246	92.07 266	98.30 181	99.13 19	94.02 166	92.90 267	96.73 283	89.48 167	98.73 223	94.48 177	93.60 236	95.65 317

PHI-MVS		98.34 46	98.06 46	99.18 47	99.15 97	98.12 57	99.04 50	99.09 20	93.32 204	98.83 45	99.10 66	96.54 16	99.83 55	97.70 54	99.76 32	99.59 77

UA-Net		97.96 56	97.62 61	98.98 63	98.86 116	97.47 79	98.89 78	99.08 21	96.67 58	98.72 53	99.54 1	93.15 101	99.81 66	94.87 162	98.83 119	99.65 64

PatchMatch-RL		96.59 125	96.03 133	98.27 107	99.31 66	96.51 119	97.91 225	99.06 22	93.72 183	96.92 142	98.06 177	88.50 196	99.65 119	91.77 254	99.00 110	98.66 175

3Dnovator	94.51 5	97.46 85	96.93 97	99.07 58	97.78 193	97.64 72	99.35 10	99.06 22	97.02 47	93.75 240	99.16 58	89.25 173	99.92 21	97.22 77	99.75 38	99.64 67

MSLP-MVS++		98.56 28	98.57 8	98.55 85	99.26 81	96.80 105	98.71 118	99.05 24	97.28 29	98.84 43	99.28 37	96.47 18	99.40 150	98.52 13	99.70 51	99.47 95

PS-CasMVS		94.67 217	93.99 226	96.71 198	96.68 270	95.26 175	99.13 39	99.03 25	93.68 189	92.33 285	97.95 185	85.35 254	98.10 286	93.59 204	88.16 305	96.79 248

TranMVSNet+NR-MVSNet		95.14 190	94.48 196	97.11 176	96.45 281	96.36 126	99.03 52	99.03 25	95.04 128	93.58 243	97.93 187	88.27 199	98.03 293	94.13 187	86.90 319	96.95 229

PEN-MVS		94.42 233	93.73 244	96.49 223	96.28 287	94.84 193	99.17 33	99.00 27	93.51 196	92.23 287	97.83 199	86.10 243	97.90 302	92.55 235	86.92 318	96.74 254

Vis-MVSNet		97.42 91	97.11 88	98.34 104	98.66 133	96.23 131	99.22 25	99.00 27	96.63 60	98.04 84	99.21 45	88.05 207	99.35 154	96.01 128	99.21 102	99.45 101
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DU-MVS		95.42 171	94.76 183	97.40 164	96.53 276	96.97 98	98.66 131	98.99 29	95.43 104	93.88 233	97.69 208	88.57 192	98.31 270	95.81 133	87.25 314	96.92 230

VPNet		94.99 198	94.19 211	97.40 164	97.16 242	96.57 116	98.71 118	98.97 30	95.67 93	94.84 191	98.24 166	80.36 301	98.67 228	96.46 112	87.32 313	96.96 227

OpenMVS	93.04 13	95.83 153	95.00 173	98.32 105	97.18 241	97.32 83	99.21 28	98.97 30	89.96 297	91.14 299	99.05 76	86.64 233	99.92 21	93.38 208	99.47 86	97.73 205

HFP-MVS		98.63 16	98.40 18	99.32 28	99.72 12	98.29 45	99.23 21	98.96 32	96.10 79	98.94 36	99.17 53	96.06 30	99.92 21	97.62 58	99.78 23	99.75 28

#test#		98.54 31	98.27 33	99.32 28	99.72 12	98.29 45	98.98 63	98.96 32	95.65 95	98.94 36	99.17 53	96.06 30	99.92 21	97.21 78	99.78 23	99.75 28

ACMMPR		98.59 20	98.36 22	99.29 31	99.74 7	98.15 55	99.23 21	98.95 34	96.10 79	98.93 40	99.19 52	95.70 44	99.94 3	97.62 58	99.79 19	99.78 13

CP-MVSNet		94.94 204	94.30 207	96.83 193	96.72 268	95.56 162	99.11 42	98.95 34	93.89 173	92.42 284	97.90 189	87.19 224	98.12 285	94.32 181	88.21 303	96.82 247

NR-MVSNet		94.98 200	94.16 214	97.44 160	96.53 276	97.22 91	98.74 109	98.95 34	94.96 132	89.25 313	97.69 208	89.32 171	98.18 280	94.59 173	87.40 312	96.92 230

region2R		98.61 17	98.38 20	99.29 31	99.74 7	98.16 54	99.23 21	98.93 37	96.15 74	98.94 36	99.17 53	95.91 39	99.94 3	97.55 66	99.79 19	99.78 13

APDe-MVS		99.02 3	98.84 2	99.55 6	99.57 33	98.96 12	99.39 5	98.93 37	97.38 24	99.41 11	99.54 1	96.66 13	99.84 52	98.86 1	99.85 3	99.87 1

VNet		97.79 67	97.40 78	98.96 65	98.88 114	97.55 76	98.63 133	98.93 37	96.74 55	99.02 31	98.84 102	90.33 158	99.83 55	98.53 9	96.66 182	99.50 88

UGNet		96.78 119	96.30 124	98.19 115	98.24 161	95.89 153	98.88 81	98.93 37	97.39 23	96.81 148	97.84 196	82.60 287	99.90 33	96.53 110	99.49 84	98.79 164
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
sss		97.39 93	96.98 96	98.61 81	98.60 139	96.61 113	98.22 189	98.93 37	93.97 170	98.01 90	98.48 137	91.98 122	99.85 49	96.45 113	98.15 147	99.39 105

QAPM		96.29 135	95.40 151	98.96 65	97.85 190	97.60 75	99.23 21	98.93 37	89.76 299	93.11 263	99.02 77	89.11 178	99.93 15	91.99 249	99.62 63	99.34 108

DPE-MVS		98.92 4	98.67 6	99.65 2	99.58 32	99.20 7	98.42 165	98.91 43	97.58 14	99.54 7	99.46 9	97.10 9	99.94 3	97.64 57	99.84 8	99.83 5

114514_t		96.93 113	96.27 125	98.92 67	99.50 40	97.63 73	98.85 86	98.90 44	84.80 328	97.77 104	99.11 64	92.84 103	99.66 118	94.85 163	99.77 26	99.47 95

LS3D		97.16 105	96.66 113	98.68 77	98.53 143	97.19 92	98.93 71	98.90 44	92.83 224	95.99 177	99.37 22	92.12 118	99.87 44	93.67 202	99.57 71	98.97 153

DELS-MVS		98.40 40	98.20 41	98.99 61	99.00 105	97.66 71	97.75 241	98.89 46	97.71 8	98.33 74	98.97 84	94.97 70	99.88 43	98.42 20	99.76 32	99.42 104
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
DP-MVS Recon		97.86 63	97.46 74	99.06 59	99.53 36	98.35 42	98.33 173	98.89 46	92.62 228	98.05 82	98.94 92	95.34 58	99.65 119	96.04 126	99.42 92	99.19 129

AdaColmap		97.15 106	96.70 109	98.48 93	99.16 95	96.69 110	98.01 217	98.89 46	94.44 155	96.83 145	98.68 117	90.69 152	99.76 98	94.36 179	99.29 101	98.98 152

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 64	98.88 49					99.94 3	98.47 15	99.81 10	99.84 4

test0726					99.72 12	99.25 2	99.06 48	98.88 49	97.62 11	99.56 5	99.50 4	97.42 6

DVP-MVS		98.74 8	98.55 10	99.29 31	99.75 3	98.23 48	99.26 18	98.88 49	97.52 15	99.41 11	98.78 108	96.00 34	99.79 87	97.79 47	99.59 68	99.85 2

Anonymous20231211		94.10 253	93.26 261	96.61 208	99.11 100	94.28 217	99.01 56	98.88 49	86.43 319	92.81 269	97.57 220	81.66 292	98.68 227	94.83 164	89.02 296	96.88 239

XVS		98.70 9	98.49 16	99.34 23	99.70 23	98.35 42	99.29 14	98.88 49	97.40 21	98.46 64	99.20 49	95.90 40	99.89 35	97.85 43	99.74 41	99.78 13

X-MVStestdata		94.06 257	92.30 276	99.34 23	99.70 23	98.35 42	99.29 14	98.88 49	97.40 21	98.46 64	43.50 347	95.90 40	99.89 35	97.85 43	99.74 41	99.78 13

SED-MVS		99.09 1	98.91 1	99.63 3	99.71 20	99.24 4	99.02 54	98.87 55	97.65 9	99.73 1	99.48 6	97.53 4	99.94 3	98.43 18	99.81 10	99.70 45

test_241102_TWO								98.87 55	97.65 9	99.53 8	99.48 6	97.34 8	99.94 3	98.43 18	99.80 17	99.83 5

test_241102_ONE					99.71 20	99.24 4		98.87 55	97.62 11	99.73 1	99.39 14	97.53 4	99.74 102

CP-MVS		98.57 26	98.36 22	99.19 43	99.66 27	97.86 66	99.34 11	98.87 55	95.96 82	98.60 60	99.13 61	96.05 32	99.94 3	97.77 48	99.86 1	99.77 20

SteuartSystems-ACMMP		98.90 5	98.75 4	99.36 21	99.22 90	98.43 32	99.10 43	98.87 55	97.38 24	99.35 14	99.40 13	97.78 3	99.87 44	97.77 48	99.85 3	99.78 13
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	96.37 2	97.93 61	98.48 17	96.30 238	99.00 105	89.54 304	97.43 259	98.87 55	98.16 2	99.26 18	99.38 21	96.12 28	99.64 121	98.30 26	99.77 26	99.72 39

ZNCC-MVS		98.49 34	98.20 41	99.35 22	99.73 11	98.39 33	99.19 31	98.86 61	95.77 88	98.31 76	99.10 66	95.46 50	99.93 15	97.57 65	99.81 10	99.74 33

testtj		98.33 48	97.95 52	99.47 11	99.49 44	98.70 19	98.83 90	98.86 61	95.48 101	98.91 42	99.17 53	95.48 49	99.93 15	95.80 135	99.53 81	99.76 26

DTE-MVSNet		93.98 259	93.26 261	96.14 244	96.06 296	94.39 214	99.20 29	98.86 61	93.06 212	91.78 293	97.81 201	85.87 247	97.58 314	90.53 271	86.17 323	96.46 295

SD-MVS		98.64 14	98.68 5	98.53 89	99.33 61	98.36 41	98.90 74	98.85 64	97.28 29	99.72 3	99.39 14	96.63 15	97.60 313	98.17 28	99.85 3	99.64 67
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
ETH3D-3000-0.1		98.35 44	98.00 50	99.38 17	99.47 45	98.68 20	98.67 128	98.84 65	94.66 146	99.11 26	99.25 40	95.46 50	99.81 66	96.80 102	99.73 43	99.63 70

test_part1				0.00 337		0.00 357	0.00 348	98.84 65				0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

test_prior3		98.22 53	97.90 55	99.19 43	99.31 66	98.22 49	97.80 237	98.84 65	96.12 77	97.89 101	98.69 115	95.96 36	99.70 110	96.89 92	99.60 65	99.65 64

test_prior				99.19 43	99.31 66	98.22 49		98.84 65					99.70 110			99.65 64

Anonymous20240529		95.10 192	94.22 209	97.75 140	99.01 104	94.26 219	98.87 83	98.83 69	85.79 325	96.64 153	98.97 84	78.73 309	99.85 49	96.27 118	94.89 212	99.12 139

9.14			98.06 46		99.47 45		98.71 118	98.82 70	94.36 156	99.16 24	99.29 36	96.05 32	99.81 66	97.00 83	99.71 50

SR-MVS		98.57 26	98.35 24	99.24 40	99.53 36	98.18 52	99.09 44	98.82 70	96.58 61	99.10 27	99.32 30	95.39 54	99.82 62	97.70 54	99.63 61	99.72 39

GST-MVS		98.43 38	98.12 44	99.34 23	99.72 12	98.38 34	99.09 44	98.82 70	95.71 91	98.73 52	99.06 75	95.27 60	99.93 15	97.07 82	99.63 61	99.72 39

abl_6		98.30 51	98.03 48	99.13 53	99.56 34	97.76 70	99.13 39	98.82 70	96.14 75	99.26 18	99.37 22	93.33 98	99.93 15	96.96 87	99.67 54	99.69 48

HPM-MVS_fast		98.38 41	98.13 43	99.12 55	99.75 3	97.86 66	99.44 4	98.82 70	94.46 154	98.94 36	99.20 49	95.16 65	99.74 102	97.58 62	99.85 3	99.77 20

APD-MVS		98.35 44	98.00 50	99.42 15	99.51 38	98.72 17	98.80 100	98.82 70	94.52 151	99.23 20	99.25 40	95.54 48	99.80 75	96.52 111	99.77 26	99.74 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SF-MVS		98.59 20	98.32 30	99.41 16	99.54 35	98.71 18	99.04 50	98.81 76	95.12 123	99.32 15	99.39 14	96.22 20	99.84 52	97.72 51	99.73 43	99.67 58

ETH3 D test6400		97.59 79	97.01 93	99.34 23	99.40 55	98.56 24	98.20 193	98.81 76	91.63 261	98.44 68	98.85 100	93.98 94	99.82 62	94.11 189	99.69 52	99.64 67

MVS_0304		92.81 278	92.01 279	95.23 274	97.46 218	91.33 280	98.17 202	98.81 76	91.13 281	93.80 238	95.68 317	66.08 340	98.06 291	90.79 267	96.13 204	96.32 302

ACMMP_NAP		98.61 17	98.30 31	99.55 6	99.62 30	98.95 13	98.82 93	98.81 76	95.80 87	99.16 24	99.47 8	95.37 56	99.92 21	97.89 41	99.75 38	99.79 10

Regformer-2		98.69 11	98.52 12	99.19 43	99.35 56	98.01 61	98.37 169	98.81 76	97.48 18	99.21 21	99.21 45	96.13 27	99.80 75	98.40 22	99.73 43	99.75 28

APD-MVS_3200maxsize		98.53 32	98.33 29	99.15 52	99.50 40	97.92 65	99.15 35	98.81 76	96.24 70	99.20 22	99.37 22	95.30 59	99.80 75	97.73 50	99.67 54	99.72 39

WR-MVS		95.15 189	94.46 198	97.22 168	96.67 271	96.45 121	98.21 190	98.81 76	94.15 160	93.16 259	97.69 208	87.51 218	98.30 272	95.29 154	88.62 300	96.90 237

mPP-MVS		98.51 33	98.26 34	99.25 39	99.75 3	98.04 59	99.28 16	98.81 76	96.24 70	98.35 73	99.23 42	95.46 50	99.94 3	97.42 71	99.81 10	99.77 20

CNVR-MVS		98.78 6	98.56 9	99.45 14	99.32 64	98.87 15	98.47 157	98.81 76	97.72 6	98.76 49	99.16 58	97.05 10	99.78 91	98.06 33	99.66 57	99.69 48

CPTT-MVS		97.72 70	97.32 81	98.92 67	99.64 28	97.10 95	99.12 41	98.81 76	92.34 239	98.09 80	99.08 73	93.01 102	99.92 21	96.06 125	99.77 26	99.75 28

SMA-MVS		98.58 23	98.25 35	99.56 5	99.51 38	99.04 11	98.95 68	98.80 86	93.67 191	99.37 13	99.52 3	96.52 17	99.89 35	98.06 33	99.81 10	99.76 26

HPM-MVS		98.36 43	98.10 45	99.13 53	99.74 7	97.82 68	99.53 1	98.80 86	94.63 147	98.61 59	98.97 84	95.13 66	99.77 96	97.65 56	99.83 9	99.79 10
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
Regformer-4		98.64 14	98.53 11	98.99 61	99.43 53	97.37 82	98.40 167	98.79 88	97.46 19	99.09 28	99.31 32	95.86 42	99.80 75	98.64 3	99.76 32	99.79 10

MP-MVS		98.33 48	98.01 49	99.28 35	99.75 3	98.18 52	99.22 25	98.79 88	96.13 76	97.92 99	99.23 42	94.54 80	99.94 3	96.74 106	99.78 23	99.73 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CANet		98.05 54	97.76 58	98.90 69	98.73 124	97.27 86	98.35 171	98.78 90	97.37 26	97.72 109	98.96 89	91.53 134	99.92 21	98.79 2	99.65 58	99.51 86

MP-MVS-pluss		98.31 50	97.92 54	99.49 9	99.72 12	98.88 14	98.43 163	98.78 90	94.10 162	97.69 111	99.42 12	95.25 62	99.92 21	98.09 32	99.80 17	99.67 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepC-MVS_fast	96.70 1	98.55 29	98.34 26	99.18 47	99.25 82	98.04 59	98.50 154	98.78 90	97.72 6	98.92 41	99.28 37	95.27 60	99.82 62	97.55 66	99.77 26	99.69 48
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		97.81 65	97.60 63	98.44 96	99.12 99	95.97 143	97.75 241	98.78 90	96.89 50	98.46 64	99.22 44	93.90 95	99.68 116	94.81 166	99.52 83	99.67 58

Regformer-1		98.66 12	98.51 13	99.12 55	99.35 56	97.81 69	98.37 169	98.76 94	97.49 17	99.20 22	99.21 45	96.08 29	99.79 87	98.42 20	99.73 43	99.75 28

NCCC		98.61 17	98.35 24	99.38 17	99.28 78	98.61 23	98.45 158	98.76 94	97.82 5	98.45 67	98.93 93	96.65 14	99.83 55	97.38 73	99.41 93	99.71 43

PLC	95.07 4	97.20 103	96.78 104	98.44 96	99.29 74	96.31 130	98.14 204	98.76 94	92.41 237	96.39 168	98.31 158	94.92 72	99.78 91	94.06 191	98.77 122	99.23 124
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
DeepC-MVS	95.98 3	97.88 62	97.58 64	98.77 73	99.25 82	96.93 100	98.83 90	98.75 97	96.96 49	96.89 144	99.50 4	90.46 155	99.87 44	97.84 45	99.76 32	99.52 82
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
zzz-MVS		98.55 29	98.25 35	99.46 12	99.76 1	98.64 21	98.55 147	98.74 98	97.27 33	98.02 86	99.39 14	94.81 73	99.96 1	97.91 38	99.79 19	99.77 20

MTGPA								98.74 98

MTAPA		98.58 23	98.29 32	99.46 12	99.76 1	98.64 21	98.90 74	98.74 98	97.27 33	98.02 86	99.39 14	94.81 73	99.96 1	97.91 38	99.79 19	99.77 20

ab-mvs		96.42 131	95.71 143	98.55 85	98.63 136	96.75 108	97.88 230	98.74 98	93.84 176	96.54 161	98.18 170	85.34 255	99.75 100	95.93 129	96.35 192	99.15 135

TEST9					99.31 66	98.50 28	97.92 223	98.73 102	92.63 227	97.74 107	98.68 117	96.20 23	99.80 75

train_agg		97.97 55	97.52 69	99.33 27	99.31 66	98.50 28	97.92 223	98.73 102	92.98 216	97.74 107	98.68 117	96.20 23	99.80 75	96.59 108	99.57 71	99.68 54

test_8					99.29 74	98.44 30	97.89 229	98.72 104	92.98 216	97.70 110	98.66 120	96.20 23	99.80 75

agg_prior1		97.95 59	97.51 71	99.28 35	99.30 71	98.38 34	97.81 236	98.72 104	93.16 210	97.57 121	98.66 120	96.14 26	99.81 66	96.63 107	99.56 76	99.66 62

agg_prior					99.30 71	98.38 34		98.72 104		97.57 121			99.81 66

无先验							97.58 253	98.72 104	91.38 267				99.87 44	93.36 210		99.60 75

save fliter					99.46 48	98.38 34	98.21 190	98.71 108	97.95 3

WTY-MVS		97.37 95	96.92 98	98.72 75	98.86 116	96.89 104	98.31 179	98.71 108	95.26 115	97.67 112	98.56 131	92.21 115	99.78 91	95.89 130	96.85 177	99.48 93

3Dnovator+	94.38 6	97.43 90	96.78 104	99.38 17	97.83 191	98.52 26	99.37 7	98.71 108	97.09 45	92.99 266	99.13 61	89.36 170	99.89 35	96.97 85	99.57 71	99.71 43

旧先验1					99.29 74	97.48 78		98.70 111			99.09 71	95.56 46			99.47 86	99.61 72

EI-MVSNet-Vis-set		98.47 36	98.39 19	98.69 76	99.46 48	96.49 120	98.30 181	98.69 112	97.21 36	98.84 43	99.36 26	95.41 53	99.78 91	98.62 5	99.65 58	99.80 9

新几何1				99.16 50	99.34 58	98.01 61		98.69 112	90.06 296	98.13 78	98.95 91	94.60 78	99.89 35	91.97 250	99.47 86	99.59 77

API-MVS		97.41 92	97.25 83	97.91 130	98.70 129	96.80 105	98.82 93	98.69 112	94.53 149	98.11 79	98.28 160	94.50 84	99.57 130	94.12 188	99.49 84	97.37 215

ETH3D cwj APD-0.16		97.96 56	97.52 69	99.29 31	99.05 101	98.52 26	98.33 173	98.68 115	93.18 208	98.68 54	99.13 61	94.62 77	99.83 55	96.45 113	99.55 79	99.52 82

EI-MVSNet-UG-set		98.41 39	98.34 26	98.61 81	99.45 51	96.32 128	98.28 184	98.68 115	97.17 39	98.74 50	99.37 22	95.25 62	99.79 87	98.57 7	99.54 80	99.73 36

Regformer-3		98.59 20	98.50 14	98.86 71	99.43 53	97.05 96	98.40 167	98.68 115	97.43 20	99.06 29	99.31 32	95.80 43	99.77 96	98.62 5	99.76 32	99.78 13

testdata				98.26 109	99.20 93	95.36 170		98.68 115	91.89 253	98.60 60	99.10 66	94.44 86	99.82 62	94.27 183	99.44 91	99.58 79

1121		97.37 95	96.77 108	99.16 50	99.34 58	97.99 64	98.19 197	98.68 115	90.14 295	98.01 90	98.97 84	94.80 75	99.87 44	93.36 210	99.46 89	99.61 72

MCST-MVS		98.65 13	98.37 21	99.48 10	99.60 31	98.87 15	98.41 166	98.68 115	97.04 46	98.52 63	98.80 106	96.78 12	99.83 55	97.93 37	99.61 64	99.74 33

PVSNet	91.96 18	96.35 133	96.15 129	96.96 185	99.17 94	92.05 267	96.08 317	98.68 115	93.69 187	97.75 106	97.80 202	88.86 187	99.69 115	94.26 184	99.01 109	99.15 135

MAR-MVS		96.91 114	96.40 121	98.45 95	98.69 131	96.90 102	98.66 131	98.68 115	92.40 238	97.07 134	97.96 184	91.54 133	99.75 100	93.68 200	98.92 112	98.69 171
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
原ACMM1				98.65 79	99.32 64	96.62 111		98.67 123	93.27 207	97.81 103	98.97 84	95.18 64	99.83 55	93.84 196	99.46 89	99.50 88

CDPH-MVS		97.94 60	97.49 72	99.28 35	99.47 45	98.44 30	97.91 225	98.67 123	92.57 231	98.77 48	98.85 100	95.93 38	99.72 104	95.56 145	99.69 52	99.68 54

UnsupCasMVSNet_eth		90.99 293	89.92 295	94.19 303	94.08 329	89.83 299	97.13 284	98.67 123	93.69 187	85.83 327	96.19 305	75.15 326	96.74 325	89.14 295	79.41 335	96.00 310

TSAR-MVS + MP.		98.78 6	98.62 7	99.24 40	99.69 25	98.28 47	99.14 36	98.66 126	96.84 51	99.56 5	99.31 32	96.34 19	99.70 110	98.32 25	99.73 43	99.73 36
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		98.58 23	98.25 35	99.55 6	99.50 40	99.08 9	98.72 117	98.66 126	97.51 16	98.15 77	98.83 103	95.70 44	99.92 21	97.53 68	99.67 54	99.66 62

test222					99.23 89	97.17 93	97.40 260	98.66 126	88.68 310	98.05 82	98.96 89	94.14 90			99.53 81	99.61 72

test11								98.66 126

XXY-MVS		95.20 187	94.45 200	97.46 159	96.75 266	96.56 117	98.86 85	98.65 130	93.30 206	93.27 256	98.27 163	84.85 262	98.87 210	94.82 165	91.26 266	96.96 227

IU-MVS					99.71 20	99.23 6		98.64 131	95.28 114	99.63 4				98.35 24	99.81 10	99.83 5

TAPA-MVS	93.98 7	95.35 178	94.56 192	97.74 141	99.13 98	94.83 195	98.33 173	98.64 131	86.62 317	96.29 170	98.61 123	94.00 93	99.29 158	80.00 331	99.41 93	99.09 141
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
F-COLMAP		97.09 109	96.80 101	97.97 127	99.45 51	94.95 190	98.55 147	98.62 133	93.02 214	96.17 173	98.58 128	94.01 92	99.81 66	93.95 193	98.90 113	99.14 137

EIA-MVS		97.75 68	97.58 64	98.27 107	98.38 149	96.44 122	99.01 56	98.60 134	95.88 84	97.26 126	97.53 223	94.97 70	99.33 156	97.38 73	99.20 103	99.05 146

PAPM_NR		97.46 85	97.11 88	98.50 91	99.50 40	96.41 124	98.63 133	98.60 134	95.18 119	97.06 135	98.06 177	94.26 89	99.57 130	93.80 198	98.87 117	99.52 82

cdsmvs_eth3d_5k		23.98 321	31.98 322	0.00 337	0.00 356	0.00 357	0.00 348	98.59 136	0.00 352	0.00 353	98.61 123	90.60 153	0.00 354	0.00 351	0.00 351	0.00 350

1314		96.25 139	95.73 139	97.79 136	97.13 244	95.55 164	98.19 197	98.59 136	93.47 198	92.03 291	97.82 200	91.33 138	99.49 141	94.62 170	98.44 137	98.32 191

CVMVSNet		95.43 170	96.04 132	93.57 307	97.93 185	83.62 334	98.12 207	98.59 136	95.68 92	96.56 157	99.02 77	87.51 218	97.51 317	93.56 206	97.44 168	99.60 75

OMC-MVS		97.55 83	97.34 80	98.20 113	99.33 61	95.92 150	98.28 184	98.59 136	95.52 100	97.97 93	99.10 66	93.28 100	99.49 141	95.09 159	98.88 115	99.19 129

LTVRE_ROB	92.95 15	94.60 220	93.90 231	96.68 202	97.41 226	94.42 212	98.52 149	98.59 136	91.69 259	91.21 298	98.35 151	84.87 261	99.04 188	91.06 263	93.44 240	96.60 272
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
MSP-MVS		99.03 2	98.83 3	99.63 3	99.72 12	99.25 2	98.97 64	98.58 141	97.62 11	99.45 9	99.46 9	97.42 6	99.94 3	98.47 15	99.81 10	99.69 48

UniMVSNet_ETH3D		94.24 243	93.33 258	96.97 184	97.19 240	93.38 247	98.74 109	98.57 142	91.21 279	93.81 237	98.58 128	72.85 334	98.77 221	95.05 160	93.93 229	98.77 166

PAPR		96.84 117	96.24 127	98.65 79	98.72 128	96.92 101	97.36 266	98.57 142	93.33 203	96.67 152	97.57 220	94.30 88	99.56 132	91.05 265	98.59 129	99.47 95

HQP_MVS		96.14 140	95.90 136	96.85 192	97.42 223	94.60 207	98.80 100	98.56 144	97.28 29	95.34 181	98.28 160	87.09 225	99.03 189	96.07 123	94.27 215	96.92 230

plane_prior5								98.56 144					99.03 189	96.07 123	94.27 215	96.92 230

ETV-MVS		97.96 56	97.81 56	98.40 101	98.42 147	97.27 86	98.73 113	98.55 146	96.84 51	98.38 71	97.44 229	95.39 54	99.35 154	97.62 58	98.89 114	98.58 181

CS-MVS		97.81 65	97.61 62	98.41 100	98.52 144	97.15 94	99.09 44	98.55 146	96.18 73	97.61 118	97.20 244	94.59 79	99.39 151	97.62 58	99.10 107	98.70 169

mvs_tets		95.41 173	95.00 173	96.65 203	95.58 310	94.42 212	99.00 58	98.55 146	95.73 90	93.21 258	98.38 148	83.45 285	98.63 230	97.09 81	94.00 226	96.91 235

LPG-MVS_test		95.62 163	95.34 157	96.47 225	97.46 218	93.54 240	98.99 60	98.54 149	94.67 144	94.36 210	98.77 110	85.39 252	99.11 178	95.71 140	94.15 221	96.76 252

LGP-MVS_train				96.47 225	97.46 218	93.54 240		98.54 149	94.67 144	94.36 210	98.77 110	85.39 252	99.11 178	95.71 140	94.15 221	96.76 252

test12				99.18 47	99.16 95	98.19 51		98.53 151		98.07 81		95.13 66	99.72 104		99.56 76	99.63 70

CNLPA		97.45 88	97.03 92	98.73 74	99.05 101	97.44 81	98.07 211	98.53 151	95.32 112	96.80 149	98.53 132	93.32 99	99.72 104	94.31 182	99.31 100	99.02 148

xxxxxxxxxxxxxcwj		98.70 9	98.50 14	99.30 30	99.46 48	98.38 34	98.21 190	98.52 153	97.95 3	99.32 15	99.39 14	96.22 20	99.84 52	97.72 51	99.73 43	99.67 58

jajsoiax		95.45 169	95.03 172	96.73 197	95.42 317	94.63 202	99.14 36	98.52 153	95.74 89	93.22 257	98.36 150	83.87 281	98.65 229	96.95 88	94.04 224	96.91 235

XVG-OURS		96.55 127	96.41 120	96.99 181	98.75 123	93.76 231	97.50 256	98.52 153	95.67 93	96.83 145	99.30 35	88.95 186	99.53 138	95.88 131	96.26 199	97.69 207

xiu_mvs_v1_base_debu		97.60 76	97.56 66	97.72 142	98.35 151	95.98 138	97.86 232	98.51 156	97.13 42	99.01 32	98.40 145	91.56 130	99.80 75	98.53 9	98.68 123	97.37 215

xiu_mvs_v1_base		97.60 76	97.56 66	97.72 142	98.35 151	95.98 138	97.86 232	98.51 156	97.13 42	99.01 32	98.40 145	91.56 130	99.80 75	98.53 9	98.68 123	97.37 215

xiu_mvs_v1_base_debi		97.60 76	97.56 66	97.72 142	98.35 151	95.98 138	97.86 232	98.51 156	97.13 42	99.01 32	98.40 145	91.56 130	99.80 75	98.53 9	98.68 123	97.37 215

PS-MVSNAJ		97.73 69	97.77 57	97.62 152	98.68 132	95.58 160	97.34 268	98.51 156	97.29 28	98.66 56	97.88 191	94.51 81	99.90 33	97.87 42	99.17 105	97.39 213

cascas		94.63 219	93.86 234	96.93 188	96.91 257	94.27 218	96.00 321	98.51 156	85.55 326	94.54 199	96.23 302	84.20 274	98.87 210	95.80 135	96.98 176	97.66 208

PS-MVSNAJss		96.43 130	96.26 126	96.92 190	95.84 304	95.08 182	99.16 34	98.50 161	95.87 85	93.84 236	98.34 155	94.51 81	98.61 231	96.88 95	93.45 239	97.06 222

MVS		94.67 217	93.54 252	98.08 121	96.88 259	96.56 117	98.19 197	98.50 161	78.05 337	92.69 274	98.02 179	91.07 145	99.63 124	90.09 276	98.36 142	98.04 196

XVG-OURS-SEG-HR		96.51 128	96.34 122	97.02 180	98.77 122	93.76 231	97.79 239	98.50 161	95.45 103	96.94 139	99.09 71	87.87 212	99.55 137	96.76 105	95.83 208	97.74 204

PVSNet_0	88.72 19	91.28 290	90.03 294	95.00 282	97.99 182	87.29 328	94.84 331	98.50 161	92.06 249	89.86 308	95.19 319	79.81 303	99.39 151	92.27 241	69.79 341	98.33 190

ACMH	92.88 16	94.55 225	93.95 228	96.34 236	97.63 203	93.26 251	98.81 99	98.49 165	93.43 200	89.74 309	98.53 132	81.91 290	99.08 183	93.69 199	93.30 243	96.70 261
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v2_base		97.66 73	97.70 60	97.56 156	98.61 138	95.46 167	97.44 257	98.46 166	97.15 40	98.65 57	98.15 171	94.33 87	99.80 75	97.84 45	98.66 127	97.41 211

HQP3-MVS								98.46 166							94.18 219

HQP-MVS		95.72 157	95.40 151	96.69 201	97.20 237	94.25 220	98.05 213	98.46 166	96.43 64	94.45 203	97.73 205	86.75 231	98.96 196	95.30 152	94.18 219	96.86 243

CLD-MVS		95.62 163	95.34 157	96.46 228	97.52 215	93.75 233	97.27 274	98.46 166	95.53 99	94.42 208	98.00 182	86.21 241	98.97 193	96.25 120	94.37 213	96.66 267
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-ACMP-BASELINE		94.54 226	94.14 216	95.75 261	96.55 275	91.65 276	98.11 209	98.44 170	94.96 132	94.22 218	97.90 189	79.18 307	99.11 178	94.05 192	93.85 230	96.48 293

ACMP	93.49 10	95.34 179	94.98 175	96.43 230	97.67 200	93.48 242	98.73 113	98.44 170	94.94 135	92.53 279	98.53 132	84.50 268	99.14 173	95.48 148	94.00 226	96.66 267
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	93.85 9	95.69 160	95.38 155	96.61 208	97.61 204	93.84 229	98.91 73	98.44 170	95.25 116	94.28 214	98.47 138	86.04 246	99.12 175	95.50 147	93.95 228	96.87 241
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+		97.12 107	96.69 110	98.39 102	98.19 167	96.72 109	97.37 264	98.43 173	93.71 184	97.65 115	98.02 179	92.20 116	99.25 160	96.87 98	97.79 158	99.19 129

RRT_test8_iter05		94.56 224	94.19 211	95.67 263	97.60 205	91.34 278	98.93 71	98.42 174	94.75 139	93.39 252	97.87 192	79.00 308	98.61 231	96.78 104	90.99 270	97.07 221

anonymousdsp		95.42 171	94.91 178	96.94 187	95.10 319	95.90 152	99.14 36	98.41 175	93.75 179	93.16 259	97.46 226	87.50 220	98.41 259	95.63 144	94.03 225	96.50 291

PMMVS		96.60 123	96.33 123	97.41 162	97.90 187	93.93 226	97.35 267	98.41 175	92.84 223	97.76 105	97.45 228	91.10 144	99.20 166	96.26 119	97.91 153	99.11 140

MVSFormer		97.57 81	97.49 72	97.84 133	98.07 176	95.76 156	99.47 2	98.40 177	94.98 130	98.79 46	98.83 103	92.34 109	98.41 259	96.91 89	99.59 68	99.34 108

test_djsdf		96.00 145	95.69 145	96.93 188	95.72 306	95.49 166	99.47 2	98.40 177	94.98 130	94.58 198	97.86 193	89.16 176	98.41 259	96.91 89	94.12 223	96.88 239

OPM-MVS		95.69 160	95.33 159	96.76 196	96.16 293	94.63 202	98.43 163	98.39 179	96.64 59	95.02 187	98.78 108	85.15 257	99.05 185	95.21 158	94.20 218	96.60 272

canonicalmvs		97.67 72	97.23 84	98.98 63	98.70 129	98.38 34	99.34 11	98.39 179	96.76 54	97.67 112	97.40 232	92.26 112	99.49 141	98.28 27	96.28 198	99.08 144

DP-MVS		96.59 125	95.93 135	98.57 83	99.34 58	96.19 134	98.70 122	98.39 179	89.45 304	94.52 200	99.35 28	91.85 124	99.85 49	92.89 226	98.88 115	99.68 54

diffmvs		97.58 80	97.40 78	98.13 118	98.32 158	95.81 155	98.06 212	98.37 182	96.20 72	98.74 50	98.89 97	91.31 139	99.25 160	98.16 29	98.52 132	99.34 108

ACMH+	92.99 14	94.30 239	93.77 240	95.88 256	97.81 192	92.04 268	98.71 118	98.37 182	93.99 169	90.60 305	98.47 138	80.86 298	99.05 185	92.75 228	92.40 252	96.55 280

MSDG		95.93 148	95.30 162	97.83 134	98.90 112	95.36 170	96.83 305	98.37 182	91.32 272	94.43 207	98.73 114	90.27 159	99.60 127	90.05 279	98.82 120	98.52 182

DPM-MVS		97.55 83	96.99 95	99.23 42	99.04 103	98.55 25	97.17 281	98.35 185	94.85 137	97.93 98	98.58 128	95.07 68	99.71 109	92.60 230	99.34 98	99.43 103

CMPMVS	66.06 21	89.70 301	89.67 297	89.78 320	93.19 332	76.56 341	97.00 289	98.35 185	80.97 334	81.57 334	97.75 204	74.75 328	98.61 231	89.85 282	93.63 234	94.17 329
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		94.19 246	93.43 256	96.47 225	95.90 301	94.38 215	99.26 18	98.34 187	91.99 250	92.76 271	97.13 247	88.31 198	98.52 241	89.48 291	87.70 308	96.52 286

CDS-MVSNet		96.99 111	96.69 110	97.90 131	98.05 179	95.98 138	98.20 193	98.33 188	93.67 191	96.95 138	98.49 136	93.54 96	98.42 252	95.24 157	97.74 161	99.31 114
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
casdiffmvs		97.63 75	97.41 77	98.28 106	98.33 156	96.14 135	98.82 93	98.32 189	96.38 67	97.95 94	99.21 45	91.23 141	99.23 163	98.12 30	98.37 140	99.48 93

baseline		97.64 74	97.44 76	98.25 110	98.35 151	96.20 132	99.00 58	98.32 189	96.33 69	98.03 85	99.17 53	91.35 137	99.16 169	98.10 31	98.29 145	99.39 105

cl-mvsnet2		94.68 214	94.19 211	96.13 245	98.11 174	93.60 238	96.94 292	98.31 191	92.43 236	93.32 255	96.87 278	86.51 234	98.28 276	94.10 190	91.16 267	96.51 289

test_yl		97.22 100	96.78 104	98.54 87	98.73 124	96.60 114	98.45 158	98.31 191	94.70 140	98.02 86	98.42 143	90.80 149	99.70 110	96.81 100	96.79 179	99.34 108

DCV-MVSNet		97.22 100	96.78 104	98.54 87	98.73 124	96.60 114	98.45 158	98.31 191	94.70 140	98.02 86	98.42 143	90.80 149	99.70 110	96.81 100	96.79 179	99.34 108

nrg030		96.28 137	95.72 140	97.96 129	96.90 258	98.15 55	99.39 5	98.31 191	95.47 102	94.42 208	98.35 151	92.09 119	98.69 224	97.50 69	89.05 294	97.04 223

TAMVS		97.02 110	96.79 103	97.70 145	98.06 178	95.31 174	98.52 149	98.31 191	93.95 171	97.05 136	98.61 123	93.49 97	98.52 241	95.33 151	97.81 157	99.29 119

EPP-MVSNet		97.46 85	97.28 82	97.99 126	98.64 135	95.38 169	99.33 13	98.31 191	93.61 194	97.19 128	99.07 74	94.05 91	99.23 163	96.89 92	98.43 139	99.37 107

UnsupCasMVSNet_bld		87.17 307	85.12 310	93.31 310	91.94 335	88.77 314	94.92 330	98.30 197	84.30 330	82.30 333	90.04 335	63.96 342	97.25 320	85.85 316	74.47 340	93.93 334

Vis-MVSNet (Re-imp)		96.87 116	96.55 116	97.83 134	98.73 124	95.46 167	99.20 29	98.30 197	94.96 132	96.60 156	98.87 99	90.05 161	98.59 235	93.67 202	98.60 128	99.46 99

TSAR-MVS + GP.		98.38 41	98.24 38	98.81 72	99.22 90	97.25 90	98.11 209	98.29 199	97.19 38	98.99 35	99.02 77	96.22 20	99.67 117	98.52 13	98.56 131	99.51 86

MS-PatchMatch		93.84 261	93.63 248	94.46 299	96.18 290	89.45 305	97.76 240	98.27 200	92.23 244	92.13 289	97.49 224	79.50 304	98.69 224	89.75 284	99.38 96	95.25 319

EI-MVSNet		95.96 146	95.83 138	96.36 234	97.93 185	93.70 237	98.12 207	98.27 200	93.70 186	95.07 185	99.02 77	92.23 114	98.54 239	94.68 167	93.46 237	96.84 244

MVSTER		96.06 142	95.72 140	97.08 178	98.23 162	95.93 149	98.73 113	98.27 200	94.86 136	95.07 185	98.09 175	88.21 200	98.54 239	96.59 108	93.46 237	96.79 248

FMVSNet2		94.47 231	93.61 249	97.04 179	98.21 164	96.43 123	98.79 104	98.27 200	92.46 232	93.50 249	97.09 252	81.16 293	98.00 296	91.09 261	91.93 257	96.70 261

FMVSNet3		94.97 201	94.26 208	97.11 176	98.18 169	96.62 111	98.56 145	98.26 204	93.67 191	94.09 224	97.10 248	84.25 271	98.01 294	92.08 244	92.14 253	96.70 261

Fast-Effi-MVS+		96.28 137	95.70 144	98.03 124	98.29 160	95.97 143	98.58 139	98.25 205	91.74 256	95.29 184	97.23 241	91.03 146	99.15 172	92.90 224	97.96 152	98.97 153

PAPM		94.95 202	94.00 224	97.78 137	97.04 249	95.65 158	96.03 320	98.25 205	91.23 277	94.19 220	97.80 202	91.27 140	98.86 212	82.61 326	97.61 165	98.84 162

CANet_DTU		96.96 112	96.55 116	98.21 112	98.17 171	96.07 137	97.98 220	98.21 207	97.24 35	97.13 130	98.93 93	86.88 230	99.91 30	95.00 161	99.37 97	98.66 175

HY-MVS	93.96 8	96.82 118	96.23 128	98.57 83	98.46 146	97.00 97	98.14 204	98.21 207	93.95 171	96.72 151	97.99 183	91.58 129	99.76 98	94.51 176	96.54 187	98.95 156

PCF-MVS	93.45 11	94.68 214	93.43 256	98.42 99	98.62 137	96.77 107	95.48 326	98.20 209	84.63 329	93.34 254	98.32 157	88.55 194	99.81 66	84.80 322	98.96 111	98.68 172
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v8		94.47 231	93.77 240	96.57 215	96.36 284	94.83 195	99.05 49	98.19 210	91.92 252	93.16 259	96.97 268	88.82 189	98.48 243	91.69 256	87.79 307	96.39 297

v10		94.29 240	93.55 251	96.51 222	96.39 283	94.80 197	98.99 60	98.19 210	91.35 270	93.02 265	96.99 266	88.09 205	98.41 259	90.50 272	88.41 302	96.33 301

mvs_anonymous		96.70 121	96.53 118	97.18 171	98.19 167	93.78 230	98.31 179	98.19 210	94.01 167	94.47 202	98.27 163	92.08 120	98.46 246	97.39 72	97.91 153	99.31 114

AllTest		95.24 184	94.65 188	96.99 181	99.25 82	93.21 253	98.59 137	98.18 213	91.36 268	93.52 246	98.77 110	84.67 264	99.72 104	89.70 286	97.87 155	98.02 197

TestCases				96.99 181	99.25 82	93.21 253		98.18 213	91.36 268	93.52 246	98.77 110	84.67 264	99.72 104	89.70 286	97.87 155	98.02 197

GBi-Net		94.49 229	93.80 237	96.56 216	98.21 164	95.00 184	98.82 93	98.18 213	92.46 232	94.09 224	97.07 255	81.16 293	97.95 298	92.08 244	92.14 253	96.72 257

test1		94.49 229	93.80 237	96.56 216	98.21 164	95.00 184	98.82 93	98.18 213	92.46 232	94.09 224	97.07 255	81.16 293	97.95 298	92.08 244	92.14 253	96.72 257

FMVSNet1		93.19 274	92.07 278	96.56 216	97.54 212	95.00 184	98.82 93	98.18 213	90.38 291	92.27 286	97.07 255	73.68 332	97.95 298	89.36 293	91.30 264	96.72 257

v1192		94.32 238	93.58 250	96.53 220	96.10 294	94.45 211	98.50 154	98.17 218	91.54 263	94.19 220	97.06 258	86.95 229	98.43 251	90.14 275	89.57 285	96.70 261

v1240		94.06 257	93.29 260	96.34 236	96.03 298	93.90 227	98.44 161	98.17 218	91.18 280	94.13 223	97.01 265	86.05 244	98.42 252	89.13 296	89.50 288	96.70 261

v144192		94.39 235	93.70 245	96.48 224	96.06 296	94.35 216	98.58 139	98.16 220	91.45 265	94.33 212	97.02 263	87.50 220	98.45 247	91.08 262	89.11 293	96.63 269

Fast-Effi-MVS+-dtu		95.87 150	95.85 137	95.91 253	97.74 197	91.74 274	98.69 124	98.15 221	95.56 98	94.92 189	97.68 211	88.98 184	98.79 219	93.19 215	97.78 159	97.20 219

v1921920		94.20 245	93.47 255	96.40 232	95.98 299	94.08 223	98.52 149	98.15 221	91.33 271	94.25 216	97.20 244	86.41 238	98.42 252	90.04 280	89.39 290	96.69 266

v1144		94.59 222	93.92 229	96.60 210	96.21 288	94.78 199	98.59 137	98.14 223	91.86 255	94.21 219	97.02 263	87.97 208	98.41 259	91.72 255	89.57 285	96.61 271

IterMVS-LS		95.46 167	95.21 164	96.22 241	98.12 173	93.72 236	98.32 178	98.13 224	93.71 184	94.26 215	97.31 236	92.24 113	98.10 286	94.63 168	90.12 278	96.84 244
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EU-MVSNet		93.66 262	94.14 216	92.25 316	95.96 300	83.38 335	98.52 149	98.12 225	94.69 142	92.61 276	98.13 173	87.36 223	96.39 333	91.82 252	90.00 280	96.98 226

IterMVS		94.09 254	93.85 235	94.80 290	97.99 182	90.35 296	97.18 279	98.12 225	93.68 189	92.46 283	97.34 233	84.05 276	97.41 318	92.51 237	91.33 263	96.62 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		94.11 252	93.87 233	94.85 287	97.98 184	90.56 294	97.18 279	98.11 227	93.75 179	92.58 277	97.48 225	83.97 278	97.41 318	92.48 239	91.30 264	96.58 274

COLMAP_ROB	93.27 12	95.33 180	94.87 180	96.71 198	99.29 74	93.24 252	98.58 139	98.11 227	89.92 298	93.57 244	99.10 66	86.37 239	99.79 87	90.78 268	98.10 149	97.09 220
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Effi-MVS+-dtu		96.29 135	96.56 115	95.51 266	97.89 188	90.22 297	98.80 100	98.10 229	96.57 62	96.45 167	96.66 286	90.81 147	98.91 203	95.72 138	97.99 151	97.40 212

mvs-test1		96.60 123	96.68 112	96.37 233	97.89 188	91.81 270	98.56 145	98.10 229	96.57 62	96.52 163	97.94 186	90.81 147	99.45 148	95.72 138	98.01 150	97.86 201

1112_ss		96.63 122	96.00 134	98.50 91	98.56 140	96.37 125	98.18 201	98.10 229	92.92 219	94.84 191	98.43 141	92.14 117	99.58 129	94.35 180	96.51 188	99.56 81

RRT_MVS		96.04 143	95.53 148	97.56 156	97.07 248	97.32 83	98.57 144	98.09 232	95.15 121	95.02 187	98.44 140	88.20 201	98.58 237	96.17 122	93.09 246	96.79 248

V42		94.78 210	94.14 216	96.70 200	96.33 286	95.22 176	98.97 64	98.09 232	92.32 241	94.31 213	97.06 258	88.39 197	98.55 238	92.90 224	88.87 298	96.34 299

miper_enhance_ethall		95.10 192	94.75 184	96.12 246	97.53 214	93.73 235	96.61 312	98.08 234	92.20 247	93.89 232	96.65 288	92.44 108	98.30 272	94.21 185	91.16 267	96.34 299

v2v482		94.69 212	94.03 220	96.65 203	96.17 291	94.79 198	98.67 128	98.08 234	92.72 225	94.00 229	97.16 246	87.69 217	98.45 247	92.91 223	88.87 298	96.72 257

miper_ehance_all_eth		95.01 196	94.69 187	95.97 250	97.70 199	93.31 249	97.02 288	98.07 236	92.23 244	93.51 248	96.96 270	91.85 124	98.15 282	93.68 200	91.16 267	96.44 296

eth_miper_zixun_eth		94.68 214	94.41 203	95.47 268	97.64 202	91.71 275	96.73 309	98.07 236	92.71 226	93.64 241	97.21 243	90.54 154	98.17 281	93.38 208	89.76 282	96.54 281

MVS_Test		97.28 98	97.00 94	98.13 118	98.33 156	95.97 143	98.74 109	98.07 236	94.27 158	98.44 68	98.07 176	92.48 107	99.26 159	96.43 115	98.19 146	99.16 134

Test_1112_low_res		96.34 134	95.66 147	98.36 103	98.56 140	95.94 146	97.71 243	98.07 236	92.10 248	94.79 195	97.29 237	91.75 126	99.56 132	94.17 186	96.50 189	99.58 79

alignmvs		97.56 82	97.07 91	99.01 60	98.66 133	98.37 40	98.83 90	98.06 240	96.74 55	98.00 92	97.65 212	90.80 149	99.48 145	98.37 23	96.56 186	99.19 129

testing_2		90.61 297	88.50 302	96.95 186	90.08 340	95.57 161	97.69 245	98.06 240	93.02 214	76.55 336	92.48 332	61.18 343	98.44 249	95.45 149	91.98 256	96.84 244

RPSCF		94.87 206	95.40 151	93.26 311	98.89 113	82.06 339	98.33 173	98.06 240	90.30 292	96.56 157	99.26 39	87.09 225	99.49 141	93.82 197	96.32 194	98.24 192

miper_lstm_enhance		94.33 237	94.07 219	95.11 279	97.75 194	90.97 286	97.22 276	98.03 243	91.67 260	92.76 271	96.97 268	90.03 162	97.78 309	92.51 237	89.64 284	96.56 278

cl_fuxian		94.79 209	94.43 202	95.89 255	97.75 194	93.12 256	97.16 282	98.03 243	92.23 244	93.46 251	97.05 260	91.39 135	98.01 294	93.58 205	89.21 292	96.53 283

pm-mvs1		93.94 260	93.06 263	96.59 211	96.49 279	95.16 177	98.95 68	98.03 243	92.32 241	91.08 300	97.84 196	84.54 267	98.41 259	92.16 242	86.13 325	96.19 306

v148		94.29 240	93.76 242	95.91 253	96.10 294	92.93 258	98.58 139	97.97 246	92.59 230	93.47 250	96.95 272	88.53 195	98.32 268	92.56 234	87.06 316	96.49 292

IS-MVSNet		97.22 100	96.88 99	98.25 110	98.85 118	96.36 126	99.19 31	97.97 246	95.39 106	97.23 127	98.99 83	91.11 143	98.93 201	94.60 171	98.59 129	99.47 95

cl-mvsnet_		94.51 228	94.01 223	96.02 247	97.58 207	93.40 246	97.05 286	97.96 248	91.73 258	92.76 271	97.08 254	89.06 180	98.13 284	92.61 229	90.29 277	96.52 286

cl-mvsnet1		94.52 227	94.03 220	95.99 248	97.57 211	93.38 247	97.05 286	97.94 249	91.74 256	92.81 269	97.10 248	89.12 177	98.07 290	92.60 230	90.30 276	96.53 283

pmmvs6		91.77 286	90.63 289	95.17 277	94.69 326	91.24 283	98.67 128	97.92 250	86.14 321	89.62 310	97.56 222	75.79 324	98.34 266	90.75 269	84.56 327	95.94 312

jason		97.32 97	97.08 90	98.06 123	97.45 222	95.59 159	97.87 231	97.91 251	94.79 138	98.55 62	98.83 103	91.12 142	99.23 163	97.58 62	99.60 65	99.34 108
jason: jason.
ppachtmachnet_test		93.22 272	92.63 271	94.97 283	95.45 315	90.84 287	96.88 301	97.88 252	90.60 286	92.08 290	97.26 238	88.08 206	97.86 308	85.12 321	90.33 275	96.22 304

tpm cat1		93.36 266	92.80 267	95.07 281	97.58 207	87.97 323	96.76 307	97.86 253	82.17 333	93.53 245	96.04 308	86.13 242	99.13 174	89.24 294	95.87 207	98.10 195

EG-PatchMatch MVS		91.13 291	90.12 293	94.17 304	94.73 325	89.00 313	98.13 206	97.81 254	89.22 307	85.32 329	96.46 294	67.71 337	98.42 252	87.89 305	93.82 231	95.08 322

BH-untuned		95.95 147	95.72 140	96.65 203	98.55 142	92.26 263	98.23 188	97.79 255	93.73 182	94.62 197	98.01 181	88.97 185	99.00 192	93.04 220	98.51 133	98.68 172

lupinMVS		97.44 89	97.22 85	98.12 120	98.07 176	95.76 156	97.68 246	97.76 256	94.50 152	98.79 46	98.61 123	92.34 109	99.30 157	97.58 62	99.59 68	99.31 114

VDDNet		95.36 177	94.53 193	97.86 132	98.10 175	95.13 180	98.85 86	97.75 257	90.46 288	98.36 72	99.39 14	73.27 333	99.64 121	97.98 36	96.58 185	98.81 163

ADS-MVSNet		95.00 197	94.45 200	96.63 206	98.00 180	91.91 269	96.04 318	97.74 258	90.15 293	96.47 165	96.64 289	87.89 210	98.96 196	90.08 277	97.06 173	99.02 148

tpmvs		94.60 220	94.36 205	95.33 273	97.46 218	88.60 317	96.88 301	97.68 259	91.29 274	93.80 238	96.42 297	88.58 191	99.24 162	91.06 263	96.04 206	98.17 193

pmmvs4		94.69 212	93.99 226	96.81 194	95.74 305	95.94 146	97.40 260	97.67 260	90.42 290	93.37 253	97.59 218	89.08 179	98.20 279	92.97 222	91.67 260	96.30 303

our_test_3		93.65 264	93.30 259	94.69 292	95.45 315	89.68 303	96.91 295	97.65 261	91.97 251	91.66 295	96.88 276	89.67 165	97.93 301	88.02 303	91.49 262	96.48 293

MVP-Stereo		94.28 242	93.92 229	95.35 272	94.95 321	92.60 261	97.97 221	97.65 261	91.61 262	90.68 304	97.09 252	86.32 240	98.42 252	89.70 286	99.34 98	95.02 324
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SCA		95.46 167	95.13 167	96.46 228	97.67 200	91.29 282	97.33 269	97.60 263	94.68 143	96.92 142	97.10 248	83.97 278	98.89 207	92.59 232	98.32 144	99.20 126

GA-MVS		94.81 208	94.03 220	97.14 173	97.15 243	93.86 228	96.76 307	97.58 264	94.00 168	94.76 196	97.04 261	80.91 296	98.48 243	91.79 253	96.25 200	99.09 141

test20.03		90.89 294	90.38 291	92.43 314	93.48 331	88.14 322	98.33 173	97.56 265	93.40 201	87.96 318	96.71 285	80.69 300	94.13 340	79.15 334	86.17 323	95.01 325

CR-MVSNet		94.76 211	94.15 215	96.59 211	97.00 250	93.43 243	94.96 328	97.56 265	92.46 232	96.93 140	96.24 300	88.15 203	97.88 306	87.38 306	96.65 183	98.46 184

Patchmtry		93.22 272	92.35 275	95.84 257	96.77 263	93.09 257	94.66 333	97.56 265	87.37 315	92.90 267	96.24 300	88.15 203	97.90 302	87.37 307	90.10 279	96.53 283

tpmrst		95.63 162	95.69 145	95.44 270	97.54 212	88.54 318	96.97 290	97.56 265	93.50 197	97.52 123	96.93 274	89.49 166	99.16 169	95.25 156	96.42 191	98.64 177

FMVSNet5		91.81 285	90.92 287	94.49 296	97.21 236	92.09 265	98.00 219	97.55 269	89.31 306	90.86 302	95.61 318	74.48 329	95.32 336	85.57 317	89.70 283	96.07 309

testgi		93.06 276	92.45 274	94.88 286	96.43 282	89.90 298	98.75 106	97.54 270	95.60 96	91.63 296	97.91 188	74.46 330	97.02 323	86.10 313	93.67 232	97.72 206

PatchmatchNet		95.71 158	95.52 149	96.29 239	97.58 207	90.72 291	96.84 304	97.52 271	94.06 163	97.08 132	96.96 270	89.24 174	98.90 206	92.03 248	98.37 140	99.26 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDA-MVSNet-bldmvs		89.97 300	88.35 304	94.83 289	95.21 318	91.34 278	97.64 249	97.51 272	88.36 311	71.17 342	96.13 306	79.22 306	96.63 330	83.65 323	86.27 322	96.52 286

USDC		93.33 269	92.71 269	95.21 275	96.83 262	90.83 288	96.91 295	97.50 273	93.84 176	90.72 303	98.14 172	77.69 315	98.82 216	89.51 290	93.21 245	95.97 311

ITE_SJBPF				95.44 270	97.42 223	91.32 281		97.50 273	95.09 127	93.59 242	98.35 151	81.70 291	98.88 209	89.71 285	93.39 241	96.12 307

Patchmatch-test		94.42 233	93.68 247	96.63 206	97.60 205	91.76 272	94.83 332	97.49 275	89.45 304	94.14 222	97.10 248	88.99 181	98.83 215	85.37 320	98.13 148	99.29 119

YYNet1		90.70 296	89.39 298	94.62 295	94.79 324	90.65 292	97.20 277	97.46 276	87.54 314	72.54 340	95.74 311	86.51 234	96.66 329	86.00 314	86.76 321	96.54 281

MDA-MVSNet_test_wron		90.71 295	89.38 299	94.68 293	94.83 323	90.78 290	97.19 278	97.46 276	87.60 313	72.41 341	95.72 314	86.51 234	96.71 328	85.92 315	86.80 320	96.56 278

BH-RMVSNet		95.92 149	95.32 160	97.69 146	98.32 158	94.64 201	98.19 197	97.45 278	94.56 148	96.03 175	98.61 123	85.02 258	99.12 175	90.68 270	99.06 108	99.30 117

MIMVSNet1		89.67 302	88.28 305	93.82 305	92.81 334	91.08 285	98.01 217	97.45 278	87.95 312	87.90 319	95.87 310	67.63 338	94.56 339	78.73 336	88.18 304	95.83 314

OurMVSNet-221017-0		94.21 244	94.00 224	94.85 287	95.60 309	89.22 309	98.89 78	97.43 280	95.29 113	92.18 288	98.52 135	82.86 286	98.59 235	93.46 207	91.76 259	96.74 254

BH-w/o		95.38 174	95.08 170	96.26 240	98.34 155	91.79 271	97.70 244	97.43 280	92.87 222	94.24 217	97.22 242	88.66 190	98.84 213	91.55 258	97.70 163	98.16 194

VDD-MVS		95.82 154	95.23 163	97.61 153	98.84 119	93.98 225	98.68 125	97.40 282	95.02 129	97.95 94	99.34 29	74.37 331	99.78 91	98.64 3	96.80 178	99.08 144

Gipuma		78.40 311	76.75 313	83.38 326	95.54 311	80.43 340	79.42 346	97.40 282	64.67 342	73.46 339	80.82 342	45.65 346	93.14 341	66.32 342	87.43 311	76.56 344
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
new-patchmatchnet		88.50 305	87.45 307	91.67 318	90.31 339	85.89 331	97.16 282	97.33 284	89.47 303	83.63 332	92.77 329	76.38 321	95.06 338	82.70 325	77.29 337	94.06 332

ADS-MVSNet2		94.58 223	94.40 204	95.11 279	98.00 180	88.74 315	96.04 318	97.30 285	90.15 293	96.47 165	96.64 289	87.89 210	97.56 315	90.08 277	97.06 173	99.02 148

MDTV_nov1_ep13			95.40 151		97.48 216	88.34 320	96.85 303	97.29 286	93.74 181	97.48 124	97.26 238	89.18 175	99.05 185	91.92 251	97.43 169

pmmvs5		93.65 264	92.97 265	95.68 262	95.49 313	92.37 262	98.20 193	97.28 287	89.66 301	92.58 277	97.26 238	82.14 288	98.09 288	93.18 216	90.95 271	96.58 274

EPNet_dtu		95.21 186	94.95 177	95.99 248	96.17 291	90.45 295	98.16 203	97.27 288	96.77 53	93.14 262	98.33 156	90.34 157	98.42 252	85.57 317	98.81 121	99.09 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		91.66 287	91.10 286	93.33 309	94.02 330	87.35 327	98.58 139	97.26 289	90.48 287	90.16 306	96.31 298	83.83 282	96.53 331	79.36 333	89.90 281	96.12 307

RPMNet		92.52 281	91.17 285	96.59 211	97.00 250	93.43 243	94.96 328	97.26 289	82.27 332	96.93 140	92.12 334	86.98 228	97.88 306	76.32 339	96.65 183	98.46 184

test_0402		91.32 289	90.27 292	94.48 297	96.60 273	91.12 284	98.50 154	97.22 291	86.10 322	88.30 317	96.98 267	77.65 317	97.99 297	78.13 337	92.94 248	94.34 327

dp		94.15 249	93.90 231	94.90 285	97.31 230	86.82 330	96.97 290	97.19 292	91.22 278	96.02 176	96.61 291	85.51 251	99.02 191	90.00 281	94.30 214	98.85 160

thres200		95.25 183	94.57 191	97.28 167	98.81 120	94.92 191	98.20 193	97.11 293	95.24 118	96.54 161	96.22 304	84.58 266	99.53 138	87.93 304	96.50 189	97.39 213

PatchT		93.06 276	91.97 280	96.35 235	96.69 269	92.67 260	94.48 334	97.08 294	86.62 317	97.08 132	92.23 333	87.94 209	97.90 302	78.89 335	96.69 181	98.49 183

TDRefinement		91.06 292	89.68 296	95.21 275	85.35 343	91.49 277	98.51 153	97.07 295	91.47 264	88.83 315	97.84 196	77.31 319	99.09 182	92.79 227	77.98 336	95.04 323

LF4IMVS		93.14 275	92.79 268	94.20 302	95.88 302	88.67 316	97.66 248	97.07 295	93.81 178	91.71 294	97.65 212	77.96 314	98.81 217	91.47 259	91.92 258	95.12 320

Anonymous202405211		95.28 182	94.49 195	97.67 148	99.00 105	93.75 233	98.70 122	97.04 297	90.66 285	96.49 164	98.80 106	78.13 312	99.83 55	96.21 121	95.36 211	99.44 102

baseline1		95.84 152	95.12 168	98.01 125	98.49 145	95.98 138	98.73 113	97.03 298	95.37 109	96.22 171	98.19 169	89.96 163	99.16 169	94.60 171	87.48 310	98.90 159

MIMVSNet		93.26 271	92.21 277	96.41 231	97.73 198	93.13 255	95.65 325	97.03 298	91.27 276	94.04 227	96.06 307	75.33 325	97.19 321	86.56 310	96.23 201	98.92 158

EPNet		97.28 98	96.87 100	98.51 90	94.98 320	96.14 135	98.90 74	97.02 300	98.28 1	95.99 177	99.11 64	91.36 136	99.89 35	96.98 84	99.19 104	99.50 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TR-MVS		94.94 204	94.20 210	97.17 172	97.75 194	94.14 222	97.59 252	97.02 300	92.28 243	95.75 179	97.64 214	83.88 280	98.96 196	89.77 283	96.15 203	98.40 186

JIA-IIPM		93.35 267	92.49 273	95.92 252	96.48 280	90.65 292	95.01 327	96.96 302	85.93 323	96.08 174	87.33 338	87.70 216	98.78 220	91.35 260	95.58 210	98.34 189

pmmvs-eth3d		90.36 298	89.05 300	94.32 301	91.10 337	92.12 264	97.63 251	96.95 303	88.86 309	84.91 330	93.13 328	78.32 311	96.74 325	88.70 298	81.81 332	94.09 331

tfpn200view9		95.32 181	94.62 189	97.43 161	98.94 110	94.98 187	98.68 125	96.93 304	95.33 110	96.55 159	96.53 292	84.23 272	99.56 132	88.11 300	96.29 195	97.76 202

thres400		95.38 174	94.62 189	97.65 151	98.94 110	94.98 187	98.68 125	96.93 304	95.33 110	96.55 159	96.53 292	84.23 272	99.56 132	88.11 300	96.29 195	98.40 186

thres100view900		95.38 174	94.70 186	97.41 162	98.98 108	94.92 191	98.87 83	96.90 306	95.38 107	96.61 155	96.88 276	84.29 269	99.56 132	88.11 300	96.29 195	97.76 202

thres600view7		95.49 166	94.77 182	97.67 148	98.98 108	95.02 183	98.85 86	96.90 306	95.38 107	96.63 154	96.90 275	84.29 269	99.59 128	88.65 299	96.33 193	98.40 186

CostFormer		94.95 202	94.73 185	95.60 265	97.28 231	89.06 311	97.53 255	96.89 308	89.66 301	96.82 147	96.72 284	86.05 244	98.95 200	95.53 146	96.13 204	98.79 164

new_pmnet		90.06 299	89.00 301	93.22 312	94.18 327	88.32 321	96.42 316	96.89 308	86.19 320	85.67 328	93.62 326	77.18 320	97.10 322	81.61 328	89.29 291	94.23 328

OpenMVS_ROB	86.42 20	89.00 304	87.43 308	93.69 306	93.08 333	89.42 306	97.91 225	96.89 308	78.58 336	85.86 326	94.69 323	69.48 336	98.29 275	77.13 338	93.29 244	93.36 336

tpm2		94.19 246	93.76 242	95.46 269	97.23 234	89.04 312	97.31 271	96.85 311	87.08 316	96.21 172	96.79 282	83.75 284	98.74 222	92.43 240	96.23 201	98.59 179

TransMVSNet (Re)		92.67 279	91.51 284	96.15 243	96.58 274	94.65 200	98.90 74	96.73 312	90.86 284	89.46 312	97.86 193	85.62 250	98.09 288	86.45 311	81.12 333	95.71 315

ambc				89.49 321	86.66 342	75.78 342	92.66 339	96.72 313		86.55 324	92.50 331	46.01 345	97.90 302	90.32 273	82.09 329	94.80 326

LCM-MVSNet		78.70 310	76.24 314	86.08 323	77.26 349	71.99 345	94.34 335	96.72 313	61.62 343	76.53 337	89.33 336	33.91 351	92.78 342	81.85 327	74.60 339	93.46 335

TinyColmap		92.31 283	91.53 283	94.65 294	96.92 255	89.75 300	96.92 293	96.68 315	90.45 289	89.62 310	97.85 195	76.06 323	98.81 217	86.74 309	92.51 251	95.41 318

Baseline_NR-MVSNet		94.35 236	93.81 236	95.96 251	96.20 289	94.05 224	98.61 136	96.67 316	91.44 266	93.85 235	97.60 217	88.57 192	98.14 283	94.39 178	86.93 317	95.68 316

SixPastTwentyTwo		93.34 268	92.86 266	94.75 291	95.67 307	89.41 307	98.75 106	96.67 316	93.89 173	90.15 307	98.25 165	80.87 297	98.27 277	90.90 266	90.64 273	96.57 276

DWT-MVSNet_test		94.82 207	94.36 205	96.20 242	97.35 228	90.79 289	98.34 172	96.57 318	92.91 220	95.33 183	96.44 296	82.00 289	99.12 175	94.52 175	95.78 209	98.70 169

LFMVS		95.86 151	94.98 175	98.47 94	98.87 115	96.32 128	98.84 89	96.02 319	93.40 201	98.62 58	99.20 49	74.99 327	99.63 124	97.72 51	97.20 172	99.46 99

IB-MVS	91.98 17	93.27 270	91.97 280	97.19 170	97.47 217	93.41 245	97.09 285	95.99 320	93.32 204	92.47 282	95.73 312	78.06 313	99.53 138	94.59 173	82.98 328	98.62 178
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
test0.0.03 1		94.08 255	93.51 253	95.80 258	95.53 312	92.89 259	97.38 262	95.97 321	95.11 124	92.51 281	96.66 286	87.71 214	96.94 324	87.03 308	93.67 232	97.57 209

FPMVS		77.62 313	77.14 312	79.05 328	79.25 347	60.97 349	95.79 323	95.94 322	65.96 341	67.93 343	94.40 324	37.73 349	88.88 345	68.83 341	88.46 301	87.29 339

Patchmatch-RL test		91.49 288	90.85 288	93.41 308	91.37 336	84.40 332	92.81 338	95.93 323	91.87 254	87.25 320	94.87 322	88.99 181	96.53 331	92.54 236	82.00 330	99.30 117

tpm		94.13 250	93.80 237	95.12 278	96.50 278	87.91 324	97.44 257	95.89 324	92.62 228	96.37 169	96.30 299	84.13 275	98.30 272	93.24 213	91.66 261	99.14 137

LCM-MVSNet-Re		95.22 185	95.32 160	94.91 284	98.18 169	87.85 325	98.75 106	95.66 325	95.11 124	88.96 314	96.85 279	90.26 160	97.65 311	95.65 143	98.44 137	99.22 125

ET-MVSNet_ETH3D		94.13 250	92.98 264	97.58 154	98.22 163	96.20 132	97.31 271	95.37 326	94.53 149	79.56 335	97.63 216	86.51 234	97.53 316	96.91 89	90.74 272	99.02 148

test-LLR		95.10 192	94.87 180	95.80 258	96.77 263	89.70 301	96.91 295	95.21 327	95.11 124	94.83 193	95.72 314	87.71 214	98.97 193	93.06 218	98.50 134	98.72 167

test-mter		94.08 255	93.51 253	95.80 258	96.77 263	89.70 301	96.91 295	95.21 327	92.89 221	94.83 193	95.72 314	77.69 315	98.97 193	93.06 218	98.50 134	98.72 167

PM-MVS		87.77 306	86.55 309	91.40 319	91.03 338	83.36 336	96.92 293	95.18 329	91.28 275	86.48 325	93.42 327	53.27 344	96.74 325	89.43 292	81.97 331	94.11 330

DeepMVS_CX				86.78 322	97.09 247	72.30 344		95.17 330	75.92 338	84.34 331	95.19 319	70.58 335	95.35 335	79.98 332	89.04 295	92.68 337

K. test v3		92.55 280	91.91 282	94.48 297	95.64 308	89.24 308	99.07 47	94.88 331	94.04 164	86.78 322	97.59 218	77.64 318	97.64 312	92.08 244	89.43 289	96.57 276

TESTMET0.1,1		94.18 248	93.69 246	95.63 264	96.92 255	89.12 310	96.91 295	94.78 332	93.17 209	94.88 190	96.45 295	78.52 310	98.92 202	93.09 217	98.50 134	98.85 160

pmmvs3		86.67 309	84.86 311	92.11 317	88.16 341	87.19 329	96.63 311	94.75 333	79.88 335	87.22 321	92.75 330	66.56 339	95.20 337	81.24 329	76.56 338	93.96 333

door								94.64 334

thisisatest0515		95.61 165	94.89 179	97.76 139	98.15 172	95.15 179	96.77 306	94.41 335	92.95 218	97.18 129	97.43 230	84.78 263	99.45 148	94.63 168	97.73 162	98.68 172

door-mid								94.37 336

tttt0517		96.07 141	95.51 150	97.78 137	98.41 148	94.84 193	99.28 16	94.33 337	94.26 159	97.64 116	98.64 122	84.05 276	99.47 146	95.34 150	97.60 166	99.03 147

DSMNet-mixed		92.52 281	92.58 272	92.33 315	94.15 328	82.65 337	98.30 181	94.26 338	89.08 308	92.65 275	95.73 312	85.01 259	95.76 334	86.24 312	97.76 160	98.59 179

thisisatest0530		96.01 144	95.36 156	97.97 127	98.38 149	95.52 165	98.88 81	94.19 339	94.04 164	97.64 116	98.31 158	83.82 283	99.46 147	95.29 154	97.70 163	98.93 157

MTMP							98.89 78	94.14 340

baseline2		95.11 191	94.52 194	96.87 191	96.65 272	93.56 239	98.27 186	94.10 341	93.45 199	92.02 292	97.43 230	87.45 222	99.19 167	93.88 195	97.41 170	97.87 200

PMVS	61.03 23	65.95 316	63.57 319	73.09 331	57.90 352	51.22 353	85.05 345	93.93 342	54.45 344	44.32 349	83.57 339	13.22 353	89.15 344	58.68 344	81.00 334	78.91 343
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		77.95 312	75.44 315	85.46 324	82.54 344	74.95 343	94.23 336	93.08 343	72.80 340	74.68 338	87.38 337	36.36 350	91.56 343	73.95 340	63.94 342	89.87 338

MVS-HIRNet		89.46 303	88.40 303	92.64 313	97.58 207	82.15 338	94.16 337	93.05 344	75.73 339	90.90 301	82.52 340	79.42 305	98.33 267	83.53 324	98.68 123	97.43 210

EPMVS		94.99 198	94.48 196	96.52 221	97.22 235	91.75 273	97.23 275	91.66 345	94.11 161	97.28 125	96.81 281	85.70 249	98.84 213	93.04 220	97.28 171	98.97 153

lessismore_v0				94.45 300	94.93 322	88.44 319		91.03 346		86.77 323	97.64 214	76.23 322	98.42 252	90.31 274	85.64 326	96.51 289

ANet_high		69.08 314	65.37 317	80.22 327	65.99 351	71.96 346	90.91 342	90.09 347	82.62 331	49.93 348	78.39 343	29.36 352	81.75 346	62.49 343	38.52 346	86.95 341

gg-mvs-nofinetune		92.21 284	90.58 290	97.13 174	96.75 266	95.09 181	95.85 322	89.40 348	85.43 327	94.50 201	81.98 341	80.80 299	98.40 265	92.16 242	98.33 143	97.88 199

GG-mvs-BLEND				96.59 211	96.34 285	94.98 187	96.51 315	88.58 349		93.10 264	94.34 325	80.34 302	98.05 292	89.53 289	96.99 175	96.74 254

E-PMN		64.94 317	64.25 318	67.02 332	82.28 345	59.36 351	91.83 341	85.63 350	52.69 345	60.22 345	77.28 344	41.06 348	80.12 348	46.15 346	41.14 344	61.57 346

EMVS		64.07 318	63.26 320	66.53 333	81.73 346	58.81 352	91.85 340	84.75 351	51.93 347	59.09 346	75.13 345	43.32 347	79.09 349	42.03 347	39.47 345	61.69 345

tmp_tt		68.90 315	66.97 316	74.68 330	50.78 353	59.95 350	87.13 343	83.47 352	38.80 348	62.21 344	96.23 302	64.70 341	76.91 350	88.91 297	30.49 347	87.19 340

MVE	62.14 22	63.28 319	59.38 321	74.99 329	74.33 350	65.47 347	85.55 344	80.50 353	52.02 346	51.10 347	75.00 346	10.91 356	80.50 347	51.60 345	53.40 343	78.99 342
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
N_pmnet		87.12 308	87.77 306	85.17 325	95.46 314	61.92 348	97.37 264	70.66 354	85.83 324	88.73 316	96.04 308	85.33 256	97.76 310	80.02 330	90.48 274	95.84 313

wuyk23d		30.17 320	30.18 323	30.16 334	78.61 348	43.29 354	66.79 347	14.21 355	17.31 349	14.82 352	11.93 352	11.55 355	41.43 351	37.08 348	19.30 348	5.76 349

testmvs		21.48 322	24.95 324	11.09 336	14.89 354	6.47 356	96.56 313	9.87 356	7.55 350	17.93 350	39.02 348	9.43 357	5.90 353	16.56 350	12.72 349	20.91 348

test123		20.95 323	23.72 325	12.64 335	13.54 355	8.19 355	96.55 314	6.13 357	7.48 351	16.74 351	37.98 349	12.97 354	6.05 352	16.69 349	5.43 350	23.68 347

uanet_test		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

pcd_1.5k_mvsjas		7.88 325	10.50 327	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	94.51 81	0.00 354	0.00 351	0.00 351	0.00 350

sosnet-low-res		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

sosnet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

uncertanet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

Regformer		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

n2								0.00 358

nn								0.00 358

ab-mvs-re		8.20 324	10.94 326	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	98.43 141	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

uanet		0.00 326	0.00 328	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

OPU-MVS				99.37 20	99.24 88	99.05 10	99.02 54				99.16 58	97.81 2	99.37 153	97.24 76	99.73 43	99.70 45

test_0728_THIRD									97.32 27	99.45 9	99.46 9	97.88 1	99.94 3	98.47 15	99.86 1	99.85 2

GSMVS																99.20 126

test_part2					99.63 29	99.18 8				99.27 17

sam_mvs1												89.45 168				99.20 126

sam_mvs												88.99 181

test_post1							96.68 310				30.43 351	87.85 213	98.69 224	92.59 232

test_post											31.83 350	88.83 188	98.91 203

patchmatchnet-post											95.10 321	89.42 169	98.89 207

gm-plane-assit					95.88 302	87.47 326			89.74 300		96.94 273		99.19 167	93.32 212

test9_res														96.39 117	99.57 71	99.69 48

agg_prior2														95.87 132	99.57 71	99.68 54

test_prior4						98.01 61	97.86 232

test_prior2							97.80 237		96.12 77	97.89 101	98.69 115	95.96 36		96.89 92	99.60 65

旧先验2							97.57 254		91.30 273	98.67 55			99.80 75	95.70 142

新几何2							97.64 249

原ACMM2							97.67 247

testdata2													99.89 35	91.65 257

segment_acmp												96.85 11

testdata1							97.32 270		96.34 68

plane_prior7					97.42 223	94.63 202

plane_prior6					97.35 228	94.61 205						87.09 225

plane_prior4											98.28 160

plane_prior3						94.61 205			97.02 47	95.34 181

plane_prior2							98.80 100		97.28 29

plane_prior1					97.37 227

plane_prior						94.60 207	98.44 161		96.74 55						94.22 217

HQP5-MVS						94.25 220

HQP-NCC					97.20 237		98.05 213		96.43 64	94.45 203

ACMP_Plane					97.20 237		98.05 213		96.43 64	94.45 203

BP-MVS														95.30 152

HQP4-MVS										94.45 203			98.96 196			96.87 241

HQP2-MVS												86.75 231

NP-MVS					97.28 231	94.51 210					97.73 205

MDTV_nov1_ep13_2view						84.26 333	96.89 300		90.97 283	97.90 100		89.89 164		93.91 194		99.18 133

ACMMP++_ref															92.97 247

ACMMP++															93.61 235

Test By Simon												94.64 76

High-resolution multi-view benchmark