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.

PGM-MVS		96.81 38	96.53 41	97.65 44	99.35 21	93.53 62	97.65 80	98.98 1	92.22 105	97.14 38	98.44 25	91.17 61	99.85 14	94.35 87	99.46 38	99.57 19

MVS_111021_HR		96.68 45	96.58 39	96.99 71	98.46 70	92.31 92	96.20 215	98.90 2	94.30 44	95.86 82	97.74 83	92.33 34	99.38 107	96.04 41	99.42 43	99.28 62

ACMMP		96.27 56	95.93 57	97.28 59	99.24 28	92.62 85	98.25 28	98.81 3	92.99 81	94.56 110	98.39 32	88.96 85	99.85 14	94.57 86	97.63 115	99.36 55
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
MVS_111021_LR		96.24 57	96.19 54	96.39 96	98.23 93	91.35 123	96.24 213	98.79 4	93.99 49	95.80 84	97.65 90	89.92 80	99.24 116	95.87 44	99.20 66	98.58 115

FC-MVSNet-test		93.94 118	93.57 111	95.04 159	95.48 215	91.45 120	98.12 38	98.71 5	93.37 67	90.23 196	96.70 137	87.66 102	97.85 251	91.49 144	90.39 236	95.83 221

UniMVSNet (Re)		93.31 136	92.55 143	95.61 136	95.39 218	93.34 69	97.39 105	98.71 5	93.14 77	90.10 205	94.83 229	87.71 101	98.03 227	91.67 142	83.99 302	95.46 238

FIs		94.09 112	93.70 107	95.27 151	95.70 207	92.03 102	98.10 39	98.68 7	93.36 69	90.39 193	96.70 137	87.63 104	97.94 241	92.25 123	90.50 235	95.84 220

WR-MVS_H		92.00 184	91.35 180	93.95 207	95.09 242	89.47 180	98.04 45	98.68 7	91.46 128	88.34 251	94.68 236	85.86 130	97.56 276	85.77 249	84.24 300	94.82 279

VPA-MVSNet		93.24 138	92.48 148	95.51 142	95.70 207	92.39 91	97.86 55	98.66 9	92.30 104	92.09 163	95.37 209	80.49 215	98.40 187	93.95 94	85.86 276	95.75 228

UniMVSNet_NR-MVSNet		93.37 134	92.67 138	95.47 147	95.34 224	92.83 79	97.17 129	98.58 10	92.98 86	90.13 201	95.80 185	88.37 95	97.85 251	91.71 138	83.93 303	95.73 230

CSCG		96.05 61	95.91 58	96.46 91	99.24 28	90.47 154	98.30 23	98.57 11	89.01 194	93.97 122	97.57 99	92.62 28	99.76 30	94.66 84	99.27 59	99.15 69

MSLP-MVS++		96.94 32	97.06 13	96.59 81	98.72 55	91.86 107	97.67 77	98.49 12	94.66 35	97.24 33	98.41 31	92.31 36	98.94 146	96.61 21	99.46 38	98.96 88

HyFIR lowres test		93.66 126	92.92 130	95.87 122	98.24 89	89.88 168	94.58 269	98.49 12	85.06 280	93.78 125	95.78 189	82.86 173	98.67 169	91.77 136	95.71 158	99.07 79

CHOSEN 1792x2688		94.15 108	93.51 115	96.06 114	98.27 85	89.38 185	95.18 261	98.48 14	85.60 273	93.76 126	97.11 119	83.15 164	99.61 61	91.33 147	98.72 88	99.19 65

PHI-MVS		96.77 40	96.46 45	97.71 41	98.40 74	94.07 47	98.21 34	98.45 15	89.86 174	97.11 41	98.01 64	92.52 32	99.69 44	96.03 42	99.53 24	99.36 55

PVSNet_BlendedMVS		94.06 113	93.92 102	94.47 184	98.27 85	89.46 182	96.73 167	98.36 16	90.17 168	94.36 113	95.24 214	88.02 96	99.58 69	93.44 106	90.72 231	94.36 298

PVSNet_Blended		94.87 95	94.56 90	95.81 124	98.27 85	89.46 182	95.47 247	98.36 16	88.84 202	94.36 113	96.09 174	88.02 96	99.58 69	93.44 106	98.18 102	98.40 135

3Dnovator	91.36 5	95.19 85	94.44 97	97.44 52	96.56 167	93.36 68	98.65 6	98.36 16	94.12 46	89.25 234	98.06 60	82.20 189	99.77 29	93.41 108	99.32 53	99.18 66

DPE-MVS		97.86 3	97.65 4	98.47 3	99.17 32	95.78 5	97.21 126	98.35 19	95.16 14	98.71 10	98.80 9	95.05 7	99.89 3	96.70 19	99.73 1	99.73 7

HFP-MVS		97.14 19	96.92 20	97.83 26	99.42 6	94.12 44	98.52 10	98.32 20	93.21 72	97.18 35	98.29 47	92.08 38	99.83 22	95.63 54	99.59 15	99.54 28

#test#		97.02 26	96.75 31	97.83 26	99.42 6	94.12 44	98.15 37	98.32 20	92.57 99	97.18 35	98.29 47	92.08 38	99.83 22	95.12 68	99.59 15	99.54 28

ACMMPR		97.07 22	96.84 24	97.79 32	99.44 5	93.88 51	98.52 10	98.31 22	93.21 72	97.15 37	98.33 41	91.35 56	99.86 8	95.63 54	99.59 15	99.62 13

APDe-MVS		97.82 4	97.73 3	98.08 15	99.15 33	94.82 25	98.81 2	98.30 23	94.76 32	98.30 13	98.90 3	93.77 14	99.68 47	97.93 1	99.69 3	99.75 3

test0726					99.45 2	95.36 10	98.31 22	98.29 24	94.92 22	98.99 4	98.92 2	95.08 5

DVP-MVS		97.59 7	97.54 5	97.73 38	99.40 11	93.77 57	98.53 9	98.29 24	95.55 5	98.56 12	97.81 78	93.90 12	99.65 53	96.62 20	99.21 65	99.77 1

test_0728_SECOND				98.51 2	99.45 2	95.93 3	98.21 34	98.28 26					99.86 8	97.52 2	99.67 6	99.75 3

CP-MVS		97.02 26	96.81 27	97.64 46	99.33 22	93.54 61	98.80 3	98.28 26	92.99 81	96.45 62	98.30 46	91.90 44	99.85 14	95.61 56	99.68 4	99.54 28

SED-MVS		98.05 1	97.99 1	98.24 7	99.42 6	95.30 15	98.25 28	98.27 28	95.13 15	99.19 1	98.89 4	95.54 3	99.85 14	97.52 2	99.66 8	99.56 22

test_241102_TWO								98.27 28	95.13 15	98.93 6	98.89 4	94.99 8	99.85 14	97.52 2	99.65 10	99.74 5

test_241102_ONE					99.42 6	95.30 15		98.27 28	95.09 18	99.19 1	98.81 8	95.54 3	99.65 53

SF-MVS		97.39 10	97.13 11	98.17 11	99.02 41	95.28 17	98.23 31	98.27 28	92.37 103	98.27 14	98.65 13	93.33 17	99.72 35	96.49 25	99.52 25	99.51 33

SteuartSystems-ACMMP		97.62 6	97.53 6	97.87 24	98.39 76	94.25 37	98.43 17	98.27 28	95.34 10	98.11 16	98.56 17	94.53 9	99.71 38	96.57 23	99.62 13	99.65 9
Skip Steuart: Steuart Systems R&D Blog.
test_part1				0.00 337		0.00 357	0.00 348	98.26 33				0.00 358	0.00 354	0.00 351	0.00 351	0.00 350

PVSNet_Blended_VisFu		95.27 80	94.91 82	96.38 97	98.20 94	90.86 143	97.27 117	98.25 34	90.21 167	94.18 117	97.27 111	87.48 108	99.73 32	93.53 103	97.77 113	98.55 116

ETH3D-3000-0.1		97.07 22	96.71 33	98.14 13	98.90 47	95.33 14	97.68 76	98.24 35	91.57 124	97.90 21	98.37 33	92.61 29	99.66 52	95.59 59	99.51 29	99.43 48

region2R		97.07 22	96.84 24	97.77 35	99.46 1	93.79 54	98.52 10	98.24 35	93.19 75	97.14 38	98.34 38	91.59 53	99.87 7	95.46 62	99.59 15	99.64 10

PS-CasMVS		91.55 198	90.84 200	93.69 222	94.96 247	88.28 215	97.84 59	98.24 35	91.46 128	88.04 261	95.80 185	79.67 231	97.48 284	87.02 229	84.54 297	95.31 251

DU-MVS		92.90 153	92.04 157	95.49 144	94.95 248	92.83 79	97.16 130	98.24 35	93.02 80	90.13 201	95.71 193	83.47 158	97.85 251	91.71 138	83.93 303	95.78 224

9.14			96.75 31		98.93 43		97.73 69	98.23 39	91.28 138	97.88 22	98.44 25	93.00 21	99.65 53	95.76 48	99.47 36

testtj		96.93 33	96.56 40	98.05 17	99.10 34	94.66 27	97.78 64	98.22 40	92.74 94	97.59 24	98.20 54	91.96 43	99.86 8	94.21 89	99.25 61	99.63 11

ETH3 D test6400		96.16 59	95.52 65	98.07 16	98.90 47	95.06 22	97.03 136	98.21 41	88.16 225	96.64 51	97.70 85	91.18 60	99.67 49	92.44 120	99.47 36	99.48 40

D2MVS		91.30 213	90.95 194	92.35 267	94.71 262	85.52 271	96.18 216	98.21 41	88.89 200	86.60 286	93.82 277	79.92 227	97.95 240	89.29 181	90.95 228	93.56 312

XVS		97.18 16	96.96 18	97.81 30	99.38 14	94.03 49	98.59 7	98.20 43	94.85 24	96.59 54	98.29 47	91.70 49	99.80 27	95.66 49	99.40 45	99.62 13

X-MVStestdata		91.71 190	89.67 247	97.81 30	99.38 14	94.03 49	98.59 7	98.20 43	94.85 24	96.59 54	32.69 347	91.70 49	99.80 27	95.66 49	99.40 45	99.62 13

ACMMP_NAP		97.20 15	96.86 22	98.23 8	99.09 35	95.16 20	97.60 86	98.19 45	92.82 91	97.93 20	98.74 11	91.60 52	99.86 8	96.26 29	99.52 25	99.67 8

CP-MVSNet		91.89 187	91.24 187	93.82 215	95.05 243	88.57 209	97.82 60	98.19 45	91.70 121	88.21 257	95.76 190	81.96 193	97.52 282	87.86 205	84.65 293	95.37 248

ZNCC-MVS		96.96 30	96.67 35	97.85 25	99.37 16	94.12 44	98.49 14	98.18 47	92.64 98	96.39 64	98.18 55	91.61 51	99.88 4	95.59 59	99.55 21	99.57 19

SMA-MVS		97.35 12	97.03 14	98.30 6	99.06 39	95.42 8	97.94 50	98.18 47	90.57 162	98.85 7	98.94 1	93.33 17	99.83 22	96.72 18	99.68 4	99.63 11

PEN-MVS		91.20 217	90.44 213	93.48 231	94.49 270	87.91 228	97.76 65	98.18 47	91.29 135	87.78 266	95.74 192	80.35 218	97.33 295	85.46 253	82.96 313	95.19 260

DELS-MVS		96.61 46	96.38 48	97.30 57	97.79 115	93.19 71	95.96 227	98.18 47	95.23 12	95.87 81	97.65 90	91.45 54	99.70 43	95.87 44	99.44 42	99.00 86
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
tfpnnormal		89.70 261	88.40 265	93.60 225	95.15 238	90.10 159	97.56 89	98.16 51	87.28 251	86.16 290	94.63 239	77.57 263	98.05 223	74.48 320	84.59 296	92.65 320

VNet		95.89 66	95.45 68	97.21 65	98.07 103	92.94 78	97.50 93	98.15 52	93.87 51	97.52 25	97.61 96	85.29 136	99.53 85	95.81 47	95.27 164	99.16 67

DeepPCF-MVS	93.97 1	96.61 46	97.09 12	95.15 155	98.09 101	86.63 255	96.00 225	98.15 52	95.43 6	97.95 19	98.56 17	93.40 16	99.36 108	96.77 17	99.48 35	99.45 44

SD-MVS		97.41 9	97.53 6	97.06 69	98.57 68	94.46 29	97.92 52	98.14 54	94.82 28	99.01 3	98.55 19	94.18 11	97.41 291	96.94 10	99.64 11	99.32 57
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
GST-MVS		96.85 36	96.52 42	97.82 29	99.36 19	94.14 43	98.29 24	98.13 55	92.72 95	96.70 46	98.06 60	91.35 56	99.86 8	94.83 78	99.28 57	99.47 43

UA-Net		95.95 65	95.53 64	97.20 66	97.67 120	92.98 77	97.65 80	98.13 55	94.81 29	96.61 52	98.35 35	88.87 86	99.51 90	90.36 159	97.35 125	99.11 75

QAPM		93.45 133	92.27 153	96.98 72	96.77 157	92.62 85	98.39 19	98.12 57	84.50 288	88.27 255	97.77 81	82.39 186	99.81 26	85.40 254	98.81 85	98.51 121

Vis-MVSNet		95.23 82	94.81 83	96.51 86	97.18 136	91.58 115	98.26 27	98.12 57	94.38 42	94.90 105	98.15 56	82.28 187	98.92 147	91.45 146	98.58 94	99.01 84
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 155	91.68 170	96.40 94	95.34 224	92.73 82	98.27 26	98.12 57	84.86 283	85.78 292	97.75 82	78.89 247	99.74 31	87.50 220	98.65 91	96.73 194

TranMVSNet+NR-MVSNet		92.50 163	91.63 171	95.14 156	94.76 259	92.07 100	97.53 91	98.11 60	92.90 89	89.56 222	96.12 171	83.16 163	97.60 274	89.30 180	83.20 312	95.75 228

CPTT-MVS		95.57 74	95.19 76	96.70 75	99.27 26	91.48 117	98.33 21	98.11 60	87.79 236	95.17 102	98.03 62	87.09 114	99.61 61	93.51 104	99.42 43	99.02 80

Regformer-2		97.16 18	96.99 16	97.67 43	98.32 82	93.84 52	96.83 159	98.10 62	95.24 11	97.49 26	98.25 51	92.57 30	99.61 61	96.80 14	99.29 55	99.56 22

APD-MVS		96.95 31	96.60 37	98.01 19	99.03 40	94.93 24	97.72 72	98.10 62	91.50 126	98.01 18	98.32 43	92.33 34	99.58 69	94.85 76	99.51 29	99.53 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 35	96.60 37	97.64 46	99.40 11	93.44 64	98.50 13	98.09 64	93.27 71	95.95 80	98.33 41	91.04 63	99.88 4	95.20 65	99.57 20	99.60 16

zzz-MVS		97.07 22	96.77 30	97.97 22	99.37 16	94.42 31	97.15 132	98.08 65	95.07 19	96.11 71	98.59 15	90.88 67	99.90 1	96.18 38	99.50 32	99.58 17

MTGPA								98.08 65

MTAPA		97.08 21	96.78 29	97.97 22	99.37 16	94.42 31	97.24 119	98.08 65	95.07 19	96.11 71	98.59 15	90.88 67	99.90 1	96.18 38	99.50 32	99.58 17

CNVR-MVS		97.68 5	97.44 8	98.37 5	98.90 47	95.86 4	97.27 117	98.08 65	95.81 3	97.87 23	98.31 44	94.26 10	99.68 47	97.02 9	99.49 34	99.57 19

DP-MVS Recon		95.68 70	95.12 79	97.37 54	99.19 31	94.19 39	97.03 136	98.08 65	88.35 218	95.09 104	97.65 90	89.97 79	99.48 94	92.08 130	98.59 93	98.44 132

SR-MVS		97.01 28	96.86 22	97.47 51	99.09 35	93.27 70	97.98 47	98.07 70	93.75 55	97.45 28	98.48 22	91.43 55	99.59 66	96.22 32	99.27 59	99.54 28

MCST-MVS		97.18 16	96.84 24	98.20 10	99.30 24	95.35 12	97.12 134	98.07 70	93.54 64	96.08 73	97.69 86	93.86 13	99.71 38	96.50 24	99.39 47	99.55 26

NR-MVSNet		92.34 170	91.27 186	95.53 141	94.95 248	93.05 74	97.39 105	98.07 70	92.65 97	84.46 302	95.71 193	85.00 140	97.77 260	89.71 169	83.52 309	95.78 224

MP-MVS-pluss		96.70 42	96.27 50	97.98 21	99.23 30	94.71 26	96.96 147	98.06 73	90.67 153	95.55 95	98.78 10	91.07 62	99.86 8	96.58 22	99.55 21	99.38 53
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 38	96.71 33	97.12 68	99.01 42	92.31 92	97.98 47	98.06 73	93.11 78	97.44 29	98.55 19	90.93 65	99.55 80	96.06 40	99.25 61	99.51 33

MP-MVS		96.77 40	96.45 46	97.72 39	99.39 13	93.80 53	98.41 18	98.06 73	93.37 67	95.54 97	98.34 38	90.59 71	99.88 4	94.83 78	99.54 23	99.49 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 49	96.27 50	97.22 64	99.32 23	92.74 81	98.74 4	98.06 73	90.57 162	96.77 45	98.35 35	90.21 75	99.53 85	94.80 81	99.63 12	99.38 53

HPM-MVS		96.69 43	96.45 46	97.40 53	99.36 19	93.11 73	98.87 1	98.06 73	91.17 142	96.40 63	97.99 65	90.99 64	99.58 69	95.61 56	99.61 14	99.49 38
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 102	93.80 105	96.64 76	97.07 142	91.97 105	96.32 204	98.06 73	88.94 198	94.50 111	96.78 132	84.60 144	99.27 114	91.90 132	96.02 149	98.68 113

DeepC-MVS	93.07 3	96.06 60	95.66 62	97.29 58	97.96 105	93.17 72	97.30 115	98.06 73	93.92 50	93.38 135	98.66 12	86.83 116	99.73 32	95.60 58	99.22 64	98.96 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ETH3D cwj APD-0.16		96.56 48	96.06 55	98.05 17	98.26 88	95.19 18	96.99 144	98.05 80	89.85 176	97.26 32	98.22 53	91.80 46	99.69 44	94.84 77	99.28 57	99.27 63

NCCC		97.30 14	97.03 14	98.11 14	98.77 53	95.06 22	97.34 109	98.04 81	95.96 2	97.09 42	97.88 70	93.18 20	99.71 38	95.84 46	99.17 68	99.56 22

DeepC-MVS_fast	93.89 2	96.93 33	96.64 36	97.78 33	98.64 63	94.30 33	97.41 101	98.04 81	94.81 29	96.59 54	98.37 33	91.24 58	99.64 60	95.16 66	99.52 25	99.42 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
abl_6		96.40 52	96.21 52	96.98 72	98.89 50	92.20 97	97.89 53	98.03 83	93.34 70	97.22 34	98.42 28	87.93 99	99.72 35	95.10 69	99.07 76	99.02 80

save fliter					98.91 45	94.28 34	97.02 139	98.02 84	95.35 8

TEST9					98.70 56	94.19 39	96.41 192	98.02 84	88.17 223	96.03 74	97.56 101	92.74 24	99.59 66

train_agg		96.30 55	95.83 60	97.72 39	98.70 56	94.19 39	96.41 192	98.02 84	88.58 211	96.03 74	97.56 101	92.73 25	99.59 66	95.04 70	99.37 52	99.39 51

test_8					98.67 58	94.06 48	96.37 199	98.01 87	88.58 211	95.98 79	97.55 103	92.73 25	99.58 69

Regformer-4		96.97 29	96.87 21	97.25 61	98.34 79	92.66 84	96.96 147	98.01 87	95.12 17	97.14 38	98.42 28	91.82 45	99.61 61	96.90 11	99.13 71	99.50 36

agg_prior1		96.22 58	95.77 61	97.56 48	98.67 58	93.79 54	96.28 208	98.00 89	88.76 208	95.68 89	97.55 103	92.70 27	99.57 77	95.01 71	99.32 53	99.32 57

agg_prior					98.67 58	93.79 54		98.00 89		95.68 89			99.57 77

test_prior3		96.46 51	96.20 53	97.23 62	98.67 58	92.99 75	96.35 200	98.00 89	92.80 92	96.03 74	97.59 97	92.01 40	99.41 102	95.01 71	99.38 48	99.29 59

test_prior				97.23 62	98.67 58	92.99 75		98.00 89					99.41 102			99.29 59

Regformer-1		97.10 20	96.96 18	97.54 49	98.32 82	93.48 63	96.83 159	97.99 93	95.20 13	97.46 27	98.25 51	92.48 33	99.58 69	96.79 16	99.29 55	99.55 26

WR-MVS		92.34 170	91.53 175	94.77 175	95.13 240	90.83 144	96.40 195	97.98 94	91.88 118	89.29 231	95.54 204	82.50 182	97.80 256	89.79 168	85.27 284	95.69 231

HPM-MVS++		97.34 13	96.97 17	98.47 3	99.08 37	96.16 2	97.55 90	97.97 95	95.59 4	96.61 52	97.89 68	92.57 30	99.84 19	95.95 43	99.51 29	99.40 50

CANet		96.39 53	96.02 56	97.50 50	97.62 123	93.38 66	97.02 139	97.96 96	95.42 7	94.86 106	97.81 78	87.38 110	99.82 25	96.88 12	99.20 66	99.29 59

114514_t		93.95 117	93.06 127	96.63 78	99.07 38	91.61 112	97.46 100	97.96 96	77.99 329	93.00 143	97.57 99	86.14 128	99.33 109	89.22 184	99.15 69	98.94 91

IU-MVS					99.42 6	95.39 9		97.94 98	90.40 166	98.94 5				97.41 7	99.66 8	99.74 5

CS-MVS		95.80 68	95.65 63	96.24 108	97.32 131	91.43 121	98.10 39	97.91 99	93.38 66	95.16 103	94.57 241	90.21 75	98.98 143	95.53 61	98.67 90	98.30 142

Anonymous20231211		90.63 241	89.42 251	94.27 192	98.24 89	89.19 197	98.05 44	97.89 100	79.95 321	88.25 256	94.96 221	72.56 292	98.13 207	89.70 170	85.14 286	95.49 234

原ACMM1				96.38 97	98.59 65	91.09 136		97.89 100	87.41 247	95.22 101	97.68 87	90.25 73	99.54 82	87.95 204	99.12 74	98.49 124

CDPH-MVS		95.97 64	95.38 71	97.77 35	98.93 43	94.44 30	96.35 200	97.88 102	86.98 255	96.65 50	97.89 68	91.99 42	99.47 95	92.26 121	99.46 38	99.39 51

test11								97.88 102

EIA-MVS		95.53 75	95.47 67	95.71 131	97.06 145	89.63 171	97.82 60	97.87 104	93.57 60	93.92 123	95.04 220	90.61 70	98.95 145	94.62 85	98.68 89	98.54 117

无先验							95.79 235	97.87 104	83.87 296				99.65 53	87.68 213		98.89 97

3Dnovator+	91.43 4	95.40 76	94.48 95	98.16 12	96.90 150	95.34 13	98.48 15	97.87 104	94.65 36	88.53 249	98.02 63	83.69 156	99.71 38	93.18 112	98.96 81	99.44 46

VPNet		92.23 178	91.31 183	94.99 161	95.56 211	90.96 139	97.22 125	97.86 107	92.96 87	90.96 185	96.62 149	75.06 279	98.20 201	91.90 132	83.65 308	95.80 223

MSP-MVS		97.91 2	97.81 2	98.22 9	99.45 2	95.36 10	98.21 34	97.85 108	94.92 22	98.73 8	98.87 6	95.08 5	99.84 19	97.52 2	99.67 6	99.48 40

TSAR-MVS + MP.		97.42 8	97.33 9	97.69 42	99.25 27	94.24 38	98.07 43	97.85 108	93.72 56	98.57 11	98.35 35	93.69 15	99.40 104	97.06 8	99.46 38	99.44 46
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
AdaColmap		94.34 104	93.68 109	96.31 101	98.59 65	91.68 111	96.59 183	97.81 110	89.87 173	92.15 161	97.06 122	83.62 157	99.54 82	89.34 179	98.07 105	97.70 167

ETV-MVS		96.02 62	95.89 59	96.40 94	97.16 137	92.44 90	97.47 98	97.77 111	94.55 37	96.48 59	94.51 243	91.23 59	98.92 147	95.65 52	98.19 101	97.82 163

Regformer-3		96.85 36	96.80 28	97.01 70	98.34 79	92.02 103	96.96 147	97.76 112	95.01 21	97.08 43	98.42 28	91.71 48	99.54 82	96.80 14	99.13 71	99.48 40

新几何1				97.32 56	98.60 64	93.59 60		97.75 113	81.58 312	95.75 86	97.85 74	90.04 78	99.67 49	86.50 235	99.13 71	98.69 112

旧先验1					98.38 77	93.38 66		97.75 113			98.09 58	92.30 37			99.01 79	99.16 67

EI-MVSNet-Vis-set		96.51 49	96.47 44	96.63 78	98.24 89	91.20 130	96.89 154	97.73 115	94.74 33	96.49 58	98.49 21	90.88 67	99.58 69	96.44 27	98.32 98	99.13 71

1121		94.71 100	93.83 104	97.34 55	98.57 68	93.64 59	96.04 221	97.73 115	81.56 313	95.68 89	97.85 74	90.23 74	99.65 53	87.68 213	99.12 74	98.73 108

PAPM_NR		95.01 87	94.59 89	96.26 106	98.89 50	90.68 149	97.24 119	97.73 115	91.80 119	92.93 148	96.62 149	89.13 84	99.14 126	89.21 185	97.78 112	98.97 87

Anonymous20240529		91.98 185	90.73 204	95.73 130	98.14 99	89.40 184	97.99 46	97.72 118	79.63 323	93.54 130	97.41 107	69.94 308	99.56 79	91.04 152	91.11 224	98.22 143

CHOSEN 280x420		93.12 142	92.72 137	94.34 190	96.71 160	87.27 237	90.29 328	97.72 118	86.61 261	91.34 174	95.29 211	84.29 150	98.41 186	93.25 111	98.94 82	97.35 180

EI-MVSNet-UG-set		96.34 54	96.30 49	96.47 89	98.20 94	90.93 141	96.86 155	97.72 118	94.67 34	96.16 70	98.46 23	90.43 72	99.58 69	96.23 31	97.96 108	98.90 95

LS3D		93.57 130	92.61 141	96.47 89	97.59 126	91.61 112	97.67 77	97.72 118	85.17 278	90.29 195	98.34 38	84.60 144	99.73 32	83.85 273	98.27 99	98.06 151

PAPR		94.18 107	93.42 121	96.48 88	97.64 122	91.42 122	95.55 243	97.71 122	88.99 195	92.34 157	95.82 184	89.19 82	99.11 128	86.14 241	97.38 123	98.90 95

UGNet		94.04 115	93.28 124	96.31 101	96.85 151	91.19 131	97.88 54	97.68 123	94.40 40	93.00 143	96.18 168	73.39 291	99.61 61	91.72 137	98.46 95	98.13 146
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
testdata				95.46 148	98.18 98	88.90 203		97.66 124	82.73 305	97.03 44	98.07 59	90.06 77	98.85 153	89.67 171	98.98 80	98.64 114

test12				97.65 44	98.46 70	94.26 36		97.66 124		95.52 98		90.89 66	99.46 96		99.25 61	99.22 64

DTE-MVSNet		90.56 242	89.75 245	93.01 249	93.95 285	87.25 238	97.64 84	97.65 126	90.74 150	87.12 277	95.68 196	79.97 226	97.00 307	83.33 274	81.66 318	94.78 286

TAPA-MVS	90.10 7	92.30 173	91.22 189	95.56 138	98.33 81	89.60 173	96.79 163	97.65 126	81.83 310	91.52 170	97.23 114	87.94 98	98.91 149	71.31 331	98.37 97	98.17 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
cdsmvs_eth3d_5k		23.24 321	30.99 322	0.00 337	0.00 356	0.00 357	0.00 348	97.63 128	0.00 352	0.00 353	96.88 130	84.38 147	0.00 354	0.00 351	0.00 351	0.00 350

DPM-MVS		95.69 69	94.92 81	98.01 19	98.08 102	95.71 7	95.27 257	97.62 129	90.43 165	95.55 95	97.07 121	91.72 47	99.50 92	89.62 173	98.94 82	98.82 103

canonicalmvs		96.02 62	95.45 68	97.75 37	97.59 126	95.15 21	98.28 25	97.60 130	94.52 38	96.27 67	96.12 171	87.65 103	99.18 121	96.20 37	94.82 172	98.91 94

test222					98.24 89	92.21 95	95.33 252	97.60 130	79.22 325	95.25 100	97.84 77	88.80 88			99.15 69	98.72 109

cascas		91.20 217	90.08 230	94.58 182	94.97 246	89.16 198	93.65 299	97.59 132	79.90 322	89.40 226	92.92 296	75.36 278	98.36 190	92.14 126	94.75 174	96.23 203

MVSFormer		95.37 77	95.16 77	95.99 118	96.34 180	91.21 128	98.22 32	97.57 133	91.42 130	96.22 68	97.32 109	86.20 126	97.92 245	94.07 91	99.05 77	98.85 100

test_djsdf		93.07 144	92.76 133	94.00 202	93.49 300	88.70 207	98.22 32	97.57 133	91.42 130	90.08 207	95.55 203	82.85 174	97.92 245	94.07 91	91.58 216	95.40 245

OMC-MVS		95.09 86	94.70 87	96.25 107	98.46 70	91.28 124	96.43 190	97.57 133	92.04 114	94.77 108	97.96 67	87.01 115	99.09 132	91.31 148	96.77 137	98.36 139

PS-MVSNAJss		93.74 124	93.51 115	94.44 185	93.91 287	89.28 193	97.75 66	97.56 136	92.50 100	89.94 209	96.54 152	88.65 90	98.18 204	93.83 100	90.90 229	95.86 217

jajsoiax		92.42 167	91.89 164	94.03 201	93.33 305	88.50 211	97.73 69	97.53 137	92.00 116	88.85 241	96.50 154	75.62 277	98.11 211	93.88 98	91.56 217	95.48 235

mvs_tets		92.31 172	91.76 166	93.94 210	93.41 302	88.29 214	97.63 85	97.53 137	92.04 114	88.76 244	96.45 156	74.62 281	98.09 216	93.91 96	91.48 218	95.45 240

HQP_MVS		93.78 123	93.43 119	94.82 170	96.21 184	89.99 163	97.74 67	97.51 139	94.85 24	91.34 174	96.64 142	81.32 203	98.60 175	93.02 115	92.23 204	95.86 217

plane_prior5								97.51 139					98.60 175	93.02 115	92.23 204	95.86 217

PS-MVSNAJ		95.37 77	95.33 73	95.49 144	97.35 130	90.66 150	95.31 254	97.48 141	93.85 52	96.51 57	95.70 195	88.65 90	99.65 53	94.80 81	98.27 99	96.17 206

API-MVS		94.84 96	94.49 94	95.90 121	97.90 111	92.00 104	97.80 62	97.48 141	89.19 190	94.81 107	96.71 135	88.84 87	99.17 122	88.91 191	98.76 87	96.53 197

MG-MVS		95.61 72	95.38 71	96.31 101	98.42 73	90.53 152	96.04 221	97.48 141	93.47 65	95.67 92	98.10 57	89.17 83	99.25 115	91.27 149	98.77 86	99.13 71

MAR-MVS		94.22 106	93.46 117	96.51 86	98.00 104	92.19 98	97.67 77	97.47 144	88.13 227	93.00 143	95.84 182	84.86 142	99.51 90	87.99 203	98.17 103	97.83 162
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
CLD-MVS		92.98 148	92.53 145	94.32 191	96.12 193	89.20 195	95.28 255	97.47 144	92.66 96	89.90 210	95.62 198	80.58 213	98.40 187	92.73 118	92.40 202	95.38 247
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 211	90.22 226	94.68 177	94.86 255	87.86 229	97.23 124	97.46 146	87.99 228	89.90 210	96.92 128	66.35 322	98.23 197	90.30 160	90.99 227	97.96 152

nrg030		94.05 114	93.31 123	96.27 105	95.22 235	94.59 28	98.34 20	97.46 146	92.93 88	91.21 183	96.64 142	87.23 113	98.22 198	94.99 74	85.80 277	95.98 215

RRT_test8_iter05		91.19 220	90.78 202	92.41 266	95.76 206	83.14 298	97.32 112	97.46 146	91.37 134	89.07 237	95.57 200	70.33 304	98.21 199	93.56 102	86.62 271	95.89 216

XVG-OURS		93.72 125	93.35 122	94.80 173	97.07 142	88.61 208	94.79 265	97.46 146	91.97 117	93.99 120	97.86 73	81.74 198	98.88 152	92.64 119	92.67 199	96.92 188

LPG-MVS_test		92.94 151	92.56 142	94.10 197	96.16 189	88.26 216	97.65 80	97.46 146	91.29 135	90.12 203	97.16 116	79.05 240	98.73 163	92.25 123	91.89 212	95.31 251

LGP-MVS_train				94.10 197	96.16 189	88.26 216		97.46 146	91.29 135	90.12 203	97.16 116	79.05 240	98.73 163	92.25 123	91.89 212	95.31 251

MVS		91.71 190	90.44 213	95.51 142	95.20 237	91.59 114	96.04 221	97.45 152	73.44 336	87.36 274	95.60 199	85.42 135	99.10 129	85.97 246	97.46 118	95.83 221

XVG-OURS-SEG-HR		93.86 120	93.55 112	94.81 172	97.06 145	88.53 210	95.28 255	97.45 152	91.68 122	94.08 119	97.68 87	82.41 185	98.90 150	93.84 99	92.47 201	96.98 184

baseline		95.58 73	95.42 70	96.08 112	96.78 156	90.41 157	97.16 130	97.45 152	93.69 59	95.65 93	97.85 74	87.29 111	98.68 168	95.66 49	97.25 129	99.13 71

ab-mvs		93.57 130	92.55 143	96.64 76	97.28 132	91.96 106	95.40 249	97.45 152	89.81 178	93.22 141	96.28 165	79.62 233	99.46 96	90.74 154	93.11 193	98.50 122

xiu_mvs_v2_base		95.32 79	95.29 74	95.40 149	97.22 133	90.50 153	95.44 248	97.44 156	93.70 58	96.46 61	96.18 168	88.59 93	99.53 85	94.79 83	97.81 111	96.17 206

1314		92.81 159	92.03 158	95.14 156	95.33 227	89.52 179	96.04 221	97.44 156	87.72 240	86.25 289	95.33 210	83.84 154	98.79 157	89.26 182	97.05 134	97.11 182

casdiffmvs		95.64 71	95.49 66	96.08 112	96.76 159	90.45 155	97.29 116	97.44 156	94.00 48	95.46 99	97.98 66	87.52 107	98.73 163	95.64 53	97.33 126	99.08 77

XXY-MVS		92.16 180	91.23 188	94.95 166	94.75 260	90.94 140	97.47 98	97.43 159	89.14 191	88.90 238	96.43 157	79.71 230	98.24 196	89.56 174	87.68 259	95.67 232

anonymousdsp		92.16 180	91.55 174	93.97 205	92.58 317	89.55 176	97.51 92	97.42 160	89.42 184	88.40 250	94.84 228	80.66 212	97.88 250	91.87 134	91.28 222	94.48 294

Effi-MVS+		94.93 92	94.45 96	96.36 99	96.61 161	91.47 118	96.41 192	97.41 161	91.02 147	94.50 111	95.92 178	87.53 106	98.78 158	93.89 97	96.81 136	98.84 102

HQP3-MVS								97.39 162							92.10 209

HQP-MVS		93.19 141	92.74 136	94.54 183	95.86 199	89.33 188	96.65 175	97.39 162	93.55 61	90.14 197	95.87 180	80.95 206	98.50 182	92.13 127	92.10 209	95.78 224

PLC	91.00 6	94.11 111	93.43 119	96.13 111	98.58 67	91.15 135	96.69 172	97.39 162	87.29 250	91.37 173	96.71 135	88.39 94	99.52 89	87.33 223	97.13 133	97.73 165
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 234	89.86 238	93.45 234	93.54 297	87.60 234	97.70 75	97.37 165	88.85 201	87.65 268	94.08 269	81.08 205	98.10 212	84.68 262	83.79 307	94.66 291

UnsupCasMVSNet_eth		85.99 295	84.45 297	90.62 302	89.97 330	82.40 304	93.62 300	97.37 165	89.86 174	78.59 329	92.37 304	65.25 328	95.35 329	82.27 285	70.75 336	94.10 305

ACMM	89.79 8	92.96 149	92.50 147	94.35 189	96.30 182	88.71 206	97.58 87	97.36 167	91.40 133	90.53 189	96.65 141	79.77 229	98.75 162	91.24 150	91.64 214	95.59 233
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 87	94.76 84	95.75 127	96.58 164	91.71 108	96.25 210	97.35 168	92.99 81	96.70 46	96.63 146	82.67 177	99.44 99	96.22 32	97.46 118	96.11 211

xiu_mvs_v1_base		95.01 87	94.76 84	95.75 127	96.58 164	91.71 108	96.25 210	97.35 168	92.99 81	96.70 46	96.63 146	82.67 177	99.44 99	96.22 32	97.46 118	96.11 211

xiu_mvs_v1_base_debi		95.01 87	94.76 84	95.75 127	96.58 164	91.71 108	96.25 210	97.35 168	92.99 81	96.70 46	96.63 146	82.67 177	99.44 99	96.22 32	97.46 118	96.11 211

diffmvs		95.25 81	95.13 78	95.63 134	96.43 176	89.34 187	95.99 226	97.35 168	92.83 90	96.31 65	97.37 108	86.44 121	98.67 169	96.26 29	97.19 131	98.87 99

WTY-MVS		94.71 100	94.02 101	96.79 74	97.71 119	92.05 101	96.59 183	97.35 168	90.61 159	94.64 109	96.93 125	86.41 122	99.39 105	91.20 151	94.71 176	98.94 91

F-COLMAP		93.58 129	92.98 128	95.37 150	98.40 74	88.98 201	97.18 128	97.29 173	87.75 239	90.49 190	97.10 120	85.21 137	99.50 92	86.70 232	96.72 140	97.63 169

XVG-ACMP-BASELINE		90.93 230	90.21 227	93.09 247	94.31 278	85.89 266	95.33 252	97.26 174	91.06 146	89.38 227	95.44 208	68.61 312	98.60 175	89.46 176	91.05 225	94.79 284

PCF-MVS	89.48 11	91.56 197	89.95 235	96.36 99	96.60 162	92.52 88	92.51 317	97.26 174	79.41 324	88.90 238	96.56 151	84.04 153	99.55 80	77.01 315	97.30 127	97.01 183
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 162	92.14 155	94.05 200	96.40 177	88.20 219	97.36 108	97.25 176	91.52 125	88.30 253	96.64 142	78.46 251	98.72 166	91.86 135	91.48 218	95.23 258
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
xxxxxxxxxxxxxcwj		97.36 11	97.20 10	97.83 26	98.91 45	94.28 34	97.02 139	97.22 177	95.35 8	98.27 14	98.65 13	93.33 17	99.72 35	96.49 25	99.52 25	99.51 33

OPM-MVS		93.28 137	92.76 133	94.82 170	94.63 266	90.77 147	96.65 175	97.18 178	93.72 56	91.68 168	97.26 112	79.33 237	98.63 172	92.13 127	92.28 203	95.07 262

PatchMatch-RL		92.90 153	92.02 159	95.56 138	98.19 96	90.80 145	95.27 257	97.18 178	87.96 229	91.86 167	95.68 196	80.44 216	98.99 142	84.01 269	97.54 117	96.89 189

MVS_0304		88.79 270	87.57 272	92.46 263	94.65 264	86.15 265	96.40 195	97.17 180	86.44 262	88.02 262	91.71 316	56.68 338	97.03 303	84.47 265	92.58 200	94.19 304

alignmvs		95.87 67	95.23 75	97.78 33	97.56 128	95.19 18	97.86 55	97.17 180	94.39 41	96.47 60	96.40 160	85.89 129	99.20 118	96.21 36	95.11 168	98.95 90

MVS_Test		94.89 94	94.62 88	95.68 132	96.83 154	89.55 176	96.70 170	97.17 180	91.17 142	95.60 94	96.11 173	87.87 100	98.76 161	93.01 117	97.17 132	98.72 109

Fast-Effi-MVS+		93.46 132	92.75 135	95.59 137	96.77 157	90.03 160	96.81 162	97.13 183	88.19 221	91.30 177	94.27 259	86.21 125	98.63 172	87.66 215	96.46 147	98.12 147

EI-MVSNet		93.03 146	92.88 131	93.48 231	95.77 204	86.98 246	96.44 188	97.12 184	90.66 155	91.30 177	97.64 93	86.56 118	98.05 223	89.91 164	90.55 233	95.41 241

MVSTER		93.20 140	92.81 132	94.37 188	96.56 167	89.59 174	97.06 135	97.12 184	91.24 139	91.30 177	95.96 176	82.02 192	98.05 223	93.48 105	90.55 233	95.47 237

testing_2		87.33 285	85.03 293	94.22 193	87.77 339	89.32 190	94.97 263	97.11 186	89.22 189	71.64 335	88.73 325	55.16 340	97.94 241	91.95 131	88.73 252	95.41 241

test_yl		94.78 98	94.23 99	96.43 92	97.74 117	91.22 126	96.85 156	97.10 187	91.23 140	95.71 87	96.93 125	84.30 148	99.31 111	93.10 113	95.12 166	98.75 105

DCV-MVSNet		94.78 98	94.23 99	96.43 92	97.74 117	91.22 126	96.85 156	97.10 187	91.23 140	95.71 87	96.93 125	84.30 148	99.31 111	93.10 113	95.12 166	98.75 105

LTVRE_ROB	88.41 13	90.99 226	89.92 236	94.19 194	96.18 187	89.55 176	96.31 205	97.09 189	87.88 232	85.67 293	95.91 179	78.79 248	98.57 178	81.50 288	89.98 239	94.44 296
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
v10		91.04 224	90.23 224	93.49 230	94.12 281	88.16 222	97.32 112	97.08 190	88.26 220	88.29 254	94.22 264	82.17 190	97.97 234	86.45 236	84.12 301	94.33 299

v144192		91.06 223	90.28 220	93.39 235	93.66 295	87.23 240	96.83 159	97.07 191	87.43 246	89.69 217	94.28 258	81.48 201	98.00 230	87.18 227	84.92 292	94.93 270

v1192		91.07 222	90.23 224	93.58 227	93.70 293	87.82 230	96.73 167	97.07 191	87.77 237	89.58 220	94.32 256	80.90 210	97.97 234	86.52 234	85.48 280	94.95 266

v8		91.29 214	90.53 212	93.57 228	94.15 280	88.12 223	97.34 109	97.06 193	88.99 195	88.32 252	94.26 261	83.08 166	98.01 229	87.62 217	83.92 305	94.57 293

mvs_anonymous		93.82 121	93.74 106	94.06 199	96.44 175	85.41 273	95.81 234	97.05 194	89.85 176	90.09 206	96.36 162	87.44 109	97.75 261	93.97 93	96.69 141	99.02 80

IterMVS-LS		92.29 174	91.94 162	93.34 238	96.25 183	86.97 247	96.57 186	97.05 194	90.67 153	89.50 225	94.80 231	86.59 117	97.64 269	89.91 164	86.11 275	95.40 245
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 232	90.03 234	93.29 240	93.55 296	86.96 248	96.74 166	97.04 196	87.36 248	89.52 224	94.34 253	80.23 221	97.97 234	86.27 237	85.21 285	94.94 268

CDS-MVSNet		94.14 110	93.54 113	95.93 119	96.18 187	91.46 119	96.33 203	97.04 196	88.97 197	93.56 128	96.51 153	87.55 105	97.89 249	89.80 167	95.95 151	98.44 132
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 208	90.60 208	93.68 223	93.89 288	88.23 218	96.84 158	97.03 198	88.37 217	89.69 217	94.39 250	82.04 191	97.98 231	87.80 207	85.37 282	94.84 276

v1240		90.70 239	89.85 239	93.23 242	93.51 299	86.80 249	96.61 180	97.02 199	87.16 253	89.58 220	94.31 257	79.55 234	97.98 231	85.52 252	85.44 281	94.90 273

EPP-MVSNet		95.22 83	95.04 80	95.76 125	97.49 129	89.56 175	98.67 5	97.00 200	90.69 152	94.24 116	97.62 95	89.79 81	98.81 156	93.39 109	96.49 145	98.92 93

V42		91.58 196	90.87 196	93.73 218	94.05 284	88.50 211	97.32 112	96.97 201	88.80 207	89.71 215	94.33 254	82.54 181	98.05 223	89.01 189	85.07 288	94.64 292

FMVSNet2		91.31 212	90.08 230	94.99 161	96.51 170	92.21 95	97.41 101	96.95 202	88.82 204	88.62 246	94.75 233	73.87 285	97.42 290	85.20 257	88.55 254	95.35 249

ACMH	87.59 16	90.53 243	89.42 251	93.87 213	96.21 184	87.92 226	97.24 119	96.94 203	88.45 215	83.91 310	96.27 166	71.92 293	98.62 174	84.43 266	89.43 244	95.05 264
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 209	90.27 221	94.59 178	96.51 170	91.18 132	97.50 93	96.93 204	88.82 204	89.35 228	94.51 243	73.87 285	97.29 297	86.12 242	88.82 248	95.31 251

test1		91.35 209	90.27 221	94.59 178	96.51 170	91.18 132	97.50 93	96.93 204	88.82 204	89.35 228	94.51 243	73.87 285	97.29 297	86.12 242	88.82 248	95.31 251

FMVSNet3		91.78 189	90.69 206	95.03 160	96.53 169	92.27 94	97.02 139	96.93 204	89.79 179	89.35 228	94.65 238	77.01 266	97.47 285	86.12 242	88.82 248	95.35 249

FMVSNet1		89.88 258	88.31 266	94.59 178	95.41 217	91.18 132	97.50 93	96.93 204	86.62 260	87.41 272	94.51 243	65.94 326	97.29 297	83.04 277	87.43 262	95.31 251

miper_enhance_ethall		91.54 199	91.01 193	93.15 245	95.35 223	87.07 245	93.97 290	96.90 208	86.79 259	89.17 235	93.43 292	86.55 119	97.64 269	89.97 163	86.93 266	94.74 288

eth_miper_zixun_eth		91.02 225	90.59 209	92.34 268	95.33 227	84.35 284	94.10 287	96.90 208	88.56 213	88.84 242	94.33 254	84.08 152	97.60 274	88.77 194	84.37 299	95.06 263

TAMVS		94.01 116	93.46 117	95.64 133	96.16 189	90.45 155	96.71 169	96.89 210	89.27 188	93.46 133	96.92 128	87.29 111	97.94 241	88.70 195	95.74 156	98.53 118

miper_ehance_all_eth		91.59 194	91.13 192	92.97 251	95.55 212	86.57 256	94.47 272	96.88 211	87.77 237	88.88 240	94.01 270	86.22 124	97.54 278	89.49 175	86.93 266	94.79 284

v2v482		91.59 194	90.85 199	93.80 216	93.87 289	88.17 221	96.94 150	96.88 211	89.54 180	89.53 223	94.90 225	81.70 199	98.02 228	89.25 183	85.04 290	95.20 259

CNLPA		94.28 105	93.53 114	96.52 83	98.38 77	92.55 87	96.59 183	96.88 211	90.13 170	91.91 165	97.24 113	85.21 137	99.09 132	87.64 216	97.83 110	97.92 155

RRT_MVS		93.21 139	92.32 152	95.91 120	94.92 250	94.15 42	96.92 151	96.86 214	91.42 130	91.28 180	96.43 157	79.66 232	98.10 212	93.29 110	90.06 238	95.46 238

PAPM		91.52 200	90.30 219	95.20 153	95.30 230	89.83 169	93.38 304	96.85 215	86.26 265	88.59 247	95.80 185	84.88 141	98.15 206	75.67 319	95.93 152	97.63 169

cl_fuxian		91.38 206	90.89 195	92.88 254	95.58 210	86.30 259	94.68 267	96.84 216	88.17 223	88.83 243	94.23 262	85.65 133	97.47 285	89.36 178	84.63 294	94.89 274

pm-mvs1		90.72 238	89.65 249	93.96 206	94.29 279	89.63 171	97.79 63	96.82 217	89.07 192	86.12 291	95.48 207	78.61 249	97.78 258	86.97 230	81.67 317	94.46 295

CMPMVS	62.92 21	85.62 298	84.92 294	87.74 316	89.14 334	73.12 338	94.17 285	96.80 218	73.98 334	73.65 334	94.93 223	66.36 321	97.61 273	83.95 271	91.28 222	92.48 323
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 248	89.77 243	91.78 282	94.33 276	84.72 282	95.55 243	96.73 219	86.17 267	86.36 288	95.28 213	71.28 298	97.80 256	84.09 268	98.14 104	92.81 319

Effi-MVS+-dtu		93.08 143	93.21 125	92.68 261	96.02 196	83.25 297	97.14 133	96.72 220	93.85 52	91.20 184	93.44 290	83.08 166	98.30 194	91.69 140	95.73 157	96.50 199

mvs-test1		93.63 127	93.69 108	93.46 233	96.02 196	84.61 283	97.24 119	96.72 220	93.85 52	92.30 158	95.76 190	83.08 166	98.89 151	91.69 140	96.54 144	96.87 190

TSAR-MVS + GP.		96.69 43	96.49 43	97.27 60	98.31 84	93.39 65	96.79 163	96.72 220	94.17 45	97.44 29	97.66 89	92.76 23	99.33 109	96.86 13	97.76 114	99.08 77

1112_ss		93.37 134	92.42 149	96.21 109	97.05 147	90.99 137	96.31 205	96.72 220	86.87 258	89.83 213	96.69 139	86.51 120	99.14 126	88.12 201	93.67 187	98.50 122

PVSNet	86.66 18	92.24 177	91.74 169	93.73 218	97.77 116	83.69 294	92.88 312	96.72 220	87.91 231	93.00 143	94.86 227	78.51 250	99.05 138	86.53 233	97.45 122	98.47 127

miper_lstm_enhance		90.50 245	90.06 233	91.83 278	95.33 227	83.74 290	93.86 292	96.70 225	87.56 244	87.79 265	93.81 278	83.45 160	96.92 309	87.39 221	84.62 295	94.82 279

v148		90.99 226	90.38 215	92.81 257	93.83 290	85.80 267	96.78 165	96.68 226	89.45 183	88.75 245	93.93 274	82.96 172	97.82 255	87.83 206	83.25 310	94.80 282

ACMH+	87.92 14	90.20 251	89.18 256	93.25 241	96.48 173	86.45 257	96.99 144	96.68 226	88.83 203	84.79 301	96.22 167	70.16 307	98.53 180	84.42 267	88.04 256	94.77 287

CANet_DTU		94.37 103	93.65 110	96.55 82	96.46 174	92.13 99	96.21 214	96.67 228	94.38 42	93.53 131	97.03 123	79.34 236	99.71 38	90.76 153	98.45 96	97.82 163

cl-mvsnet_		90.96 229	90.32 217	92.89 253	95.37 221	86.21 262	94.46 274	96.64 229	87.82 233	88.15 259	94.18 265	82.98 170	97.54 278	87.70 210	85.59 278	94.92 272

HY-MVS	89.66 9	93.87 119	92.95 129	96.63 78	97.10 141	92.49 89	95.64 241	96.64 229	89.05 193	93.00 143	95.79 188	85.77 132	99.45 98	89.16 188	94.35 178	97.96 152

Test_1112_low_res		92.84 157	91.84 165	95.85 123	97.04 148	89.97 166	95.53 245	96.64 229	85.38 274	89.65 219	95.18 215	85.86 130	99.10 129	87.70 210	93.58 192	98.49 124

cl-mvsnet1		90.97 228	90.33 216	92.88 254	95.36 222	86.19 263	94.46 274	96.63 232	87.82 233	88.18 258	94.23 262	82.99 169	97.53 280	87.72 208	85.57 279	94.93 270

Fast-Effi-MVS+-dtu		92.29 174	91.99 160	93.21 244	95.27 231	85.52 271	97.03 136	96.63 232	92.09 112	89.11 236	95.14 217	80.33 219	98.08 217	87.54 219	94.74 175	96.03 214

UnsupCasMVSNet_bld		82.13 307	79.46 309	90.14 308	88.00 337	82.47 302	90.89 326	96.62 234	78.94 326	75.61 331	84.40 335	56.63 339	96.31 317	77.30 314	66.77 340	91.63 329

cl-mvsnet2		91.21 216	90.56 211	93.14 246	96.09 195	86.80 249	94.41 276	96.58 235	87.80 235	88.58 248	93.99 272	80.85 211	97.62 272	89.87 166	86.93 266	94.99 265

jason		94.84 96	94.39 98	96.18 110	95.52 213	90.93 141	96.09 219	96.52 236	89.28 187	96.01 78	97.32 109	84.70 143	98.77 160	95.15 67	98.91 84	98.85 100
jason: jason.
EG-PatchMatch MVS		87.02 288	85.44 290	91.76 284	92.67 315	85.00 277	96.08 220	96.45 237	83.41 301	79.52 326	93.49 288	57.10 337	97.72 263	79.34 306	90.87 230	92.56 321

pmmvs6		87.81 282	86.19 285	92.69 260	91.32 325	86.30 259	97.34 109	96.41 238	80.59 320	84.05 309	94.37 252	67.37 319	97.67 266	84.75 261	79.51 324	94.09 307

PMMVS		92.86 155	92.34 150	94.42 187	94.92 250	86.73 251	94.53 271	96.38 239	84.78 285	94.27 115	95.12 219	83.13 165	98.40 187	91.47 145	96.49 145	98.12 147

RPSCF		90.75 236	90.86 197	90.42 305	96.84 152	76.29 333	95.61 242	96.34 240	83.89 294	91.38 172	97.87 71	76.45 269	98.78 158	87.16 228	92.23 204	96.20 204

MSDG		91.42 204	90.24 223	94.96 165	97.15 139	88.91 202	93.69 297	96.32 241	85.72 272	86.93 283	96.47 155	80.24 220	98.98 143	80.57 296	95.05 169	96.98 184

OurMVSNet-221017-0		90.51 244	90.19 228	91.44 290	93.41 302	81.25 309	96.98 146	96.28 242	91.68 122	86.55 287	96.30 164	74.20 284	97.98 231	88.96 190	87.40 264	95.09 261

MVP-Stereo		90.74 237	90.08 230	92.71 259	93.19 307	88.20 219	95.86 231	96.27 243	86.07 268	84.86 300	94.76 232	77.84 261	97.75 261	83.88 272	98.01 106	92.17 327
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 91	94.56 90	96.29 104	96.34 180	91.21 128	95.83 233	96.27 243	88.93 199	96.22 68	96.88 130	86.20 126	98.85 153	95.27 64	99.05 77	98.82 103

BH-untuned		92.94 151	92.62 140	93.92 212	97.22 133	86.16 264	96.40 195	96.25 245	90.06 171	89.79 214	96.17 170	83.19 162	98.35 191	87.19 226	97.27 128	97.24 181

IS-MVSNet		94.90 93	94.52 93	96.05 115	97.67 120	90.56 151	98.44 16	96.22 246	93.21 72	93.99 120	97.74 83	85.55 134	98.45 185	89.98 162	97.86 109	99.14 70

GA-MVS		91.38 206	90.31 218	94.59 178	94.65 264	87.62 233	94.34 279	96.19 247	90.73 151	90.35 194	93.83 275	71.84 294	97.96 238	87.22 225	93.61 190	98.21 144

IterMVS-SCA-FT		90.31 247	89.81 241	91.82 279	95.52 213	84.20 287	94.30 281	96.15 248	90.61 159	87.39 273	94.27 259	75.80 274	96.44 315	87.34 222	86.88 270	94.82 279

IterMVS		90.15 253	89.67 247	91.61 286	95.48 215	83.72 291	94.33 280	96.12 249	89.99 172	87.31 276	94.15 267	75.78 276	96.27 318	86.97 230	86.89 269	94.83 277
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 160	91.51 178	96.52 83	98.77 53	90.99 137	97.38 107	96.08 250	82.38 306	89.29 231	97.87 71	83.77 155	99.69 44	81.37 293	96.69 141	98.89 97

pmmvs4		90.93 230	89.85 239	94.17 195	93.34 304	90.79 146	94.60 268	96.02 251	84.62 286	87.45 270	95.15 216	81.88 196	97.45 287	87.70 210	87.87 258	94.27 303

ppachtmachnet_test		88.35 277	87.29 275	91.53 287	92.45 319	83.57 295	93.75 295	95.97 252	84.28 289	85.32 298	94.18 265	79.00 246	96.93 308	75.71 318	84.99 291	94.10 305

ITE_SJBPF				92.43 265	95.34 224	85.37 274		95.92 253	91.47 127	87.75 267	96.39 161	71.00 300	97.96 238	82.36 284	89.86 241	93.97 308

USDC		88.94 266	87.83 271	92.27 269	94.66 263	84.96 278	93.86 292	95.90 254	87.34 249	83.40 312	95.56 202	67.43 318	98.19 203	82.64 283	89.67 243	93.66 311

COLMAP_ROB	87.81 15	90.40 246	89.28 254	93.79 217	97.95 106	87.13 244	96.92 151	95.89 255	82.83 304	86.88 285	97.18 115	73.77 288	99.29 113	78.44 309	93.62 189	94.95 266
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 121	93.08 126	96.02 116	97.88 112	89.96 167	97.72 72	95.85 256	92.43 101	95.86 82	98.44 25	68.42 314	99.39 105	96.31 28	94.85 170	98.71 111

VDDNet		93.05 145	92.07 156	96.02 116	96.84 152	90.39 158	98.08 42	95.85 256	86.22 266	95.79 85	98.46 23	67.59 317	99.19 119	94.92 75	94.85 170	98.47 127

Vis-MVSNet (Re-imp)		94.15 108	93.88 103	94.95 166	97.61 124	87.92 226	98.10 39	95.80 258	92.22 105	93.02 142	97.45 105	84.53 146	97.91 248	88.24 199	97.97 107	99.02 80

tpm cat1		88.36 276	87.21 278	91.81 280	95.13 240	80.55 315	92.58 316	95.70 259	74.97 333	87.45 270	91.96 312	78.01 260	98.17 205	80.39 298	88.74 251	96.72 195

our_test_3		88.78 271	87.98 270	91.20 293	92.45 319	82.53 301	93.61 301	95.69 260	85.77 271	84.88 299	93.71 280	79.99 225	96.78 313	79.47 303	86.24 272	94.28 302

BH-w/o		92.14 182	91.75 167	93.31 239	96.99 149	85.73 268	95.67 238	95.69 260	88.73 209	89.26 233	94.82 230	82.97 171	98.07 220	85.26 256	96.32 148	96.13 210

CR-MVSNet		90.82 233	89.77 243	93.95 207	94.45 272	87.19 241	90.23 329	95.68 262	86.89 257	92.40 152	92.36 307	80.91 208	97.05 301	81.09 295	93.95 185	97.60 174

Patchmtry		88.64 273	87.25 276	92.78 258	94.09 282	86.64 252	89.82 332	95.68 262	80.81 318	87.63 269	92.36 307	80.91 208	97.03 303	78.86 307	85.12 287	94.67 290

BH-RMVSNet		92.72 161	91.97 161	94.97 164	97.16 137	87.99 225	96.15 217	95.60 264	90.62 158	91.87 166	97.15 118	78.41 252	98.57 178	83.16 275	97.60 116	98.36 139

PVSNet_0	82.17 19	85.46 299	83.64 301	90.92 296	95.27 231	79.49 324	90.55 327	95.60 264	83.76 297	83.00 313	89.95 320	71.09 299	97.97 234	82.75 281	60.79 341	95.31 251

SCA		91.84 188	91.18 191	93.83 214	95.59 209	84.95 279	94.72 266	95.58 266	90.82 148	92.25 159	93.69 281	75.80 274	98.10 212	86.20 239	95.98 150	98.45 129

AllTest		90.23 250	88.98 258	93.98 203	97.94 107	86.64 252	96.51 187	95.54 267	85.38 274	85.49 295	96.77 133	70.28 305	99.15 124	80.02 299	92.87 194	96.15 208

TestCases				93.98 203	97.94 107	86.64 252		95.54 267	85.38 274	85.49 295	96.77 133	70.28 305	99.15 124	80.02 299	92.87 194	96.15 208

tpmvs		89.83 260	89.15 257	91.89 276	94.92 250	80.30 318	93.11 309	95.46 269	86.28 264	88.08 260	92.65 299	80.44 216	98.52 181	81.47 289	89.92 240	96.84 191

pmmvs5		89.86 259	88.87 260	92.82 256	92.86 311	86.23 261	96.26 209	95.39 270	84.24 290	87.12 277	94.51 243	74.27 283	97.36 294	87.61 218	87.57 260	94.86 275

PatchmatchNet		91.91 186	91.35 180	93.59 226	95.38 219	84.11 288	93.15 308	95.39 270	89.54 180	92.10 162	93.68 283	82.82 175	98.13 207	84.81 260	95.32 163	98.52 119
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 203	91.32 182	91.79 281	95.15 238	79.20 327	93.42 303	95.37 272	88.55 214	93.49 132	93.67 284	82.49 183	98.27 195	90.41 157	89.34 245	97.90 156

Anonymous20231206		87.09 287	86.14 286	89.93 310	91.22 326	80.35 316	96.11 218	95.35 273	83.57 299	84.16 306	93.02 295	73.54 290	95.61 324	72.16 328	86.14 274	93.84 310

MIMVSNet1		84.93 301	83.05 302	90.56 303	89.56 333	84.84 281	95.40 249	95.35 273	83.91 293	80.38 322	92.21 311	57.23 336	93.34 337	70.69 334	82.75 316	93.50 313

TDRefinement		86.53 290	84.76 296	91.85 277	82.23 343	84.25 285	96.38 198	95.35 273	84.97 282	84.09 308	94.94 222	65.76 327	98.34 193	84.60 264	74.52 332	92.97 317

TR-MVS		91.48 202	90.59 209	94.16 196	96.40 177	87.33 235	95.67 238	95.34 276	87.68 241	91.46 171	95.52 205	76.77 267	98.35 191	82.85 279	93.61 190	96.79 193

EPNet_dtu		91.71 190	91.28 185	92.99 250	93.76 292	83.71 292	96.69 172	95.28 277	93.15 76	87.02 281	95.95 177	83.37 161	97.38 293	79.46 304	96.84 135	97.88 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 286	85.79 288	91.78 282	94.80 258	87.28 236	95.49 246	95.28 277	84.09 292	83.85 311	91.82 313	62.95 331	94.17 333	78.48 308	85.34 283	93.91 309

MDTV_nov1_ep13			90.76 203		95.22 235	80.33 317	93.03 311	95.28 277	88.14 226	92.84 149	93.83 275	81.34 202	98.08 217	82.86 278	94.34 179

LF4IMVS		87.94 280	87.25 276	89.98 309	92.38 321	80.05 322	94.38 277	95.25 280	87.59 243	84.34 303	94.74 234	64.31 329	97.66 268	84.83 259	87.45 261	92.23 325

TransMVSNet (Re)		88.94 266	87.56 273	93.08 248	94.35 275	88.45 213	97.73 69	95.23 281	87.47 245	84.26 305	95.29 211	79.86 228	97.33 295	79.44 305	74.44 333	93.45 315

test20.03		86.14 294	85.40 291	88.35 312	90.12 328	80.06 321	95.90 230	95.20 282	88.59 210	81.29 317	93.62 286	71.43 297	92.65 339	71.26 332	81.17 320	92.34 324

new-patchmatchnet		83.18 304	81.87 305	87.11 318	86.88 340	75.99 334	93.70 296	95.18 283	85.02 281	77.30 330	88.40 327	65.99 325	93.88 335	74.19 324	70.18 337	91.47 332

MDA-MVSNet_test_wron		85.87 296	84.23 299	90.80 300	92.38 321	82.57 300	93.17 306	95.15 284	82.15 307	67.65 337	92.33 310	78.20 254	95.51 327	77.33 312	79.74 322	94.31 301

YYNet1		85.87 296	84.23 299	90.78 301	92.38 321	82.46 303	93.17 306	95.14 285	82.12 308	67.69 336	92.36 307	78.16 257	95.50 328	77.31 313	79.73 323	94.39 297

Baseline_NR-MVSNet		91.20 217	90.62 207	92.95 252	93.83 290	88.03 224	97.01 143	95.12 286	88.42 216	89.70 216	95.13 218	83.47 158	97.44 288	89.66 172	83.24 311	93.37 316

thres200		92.23 178	91.39 179	94.75 176	97.61 124	89.03 200	96.60 182	95.09 287	92.08 113	93.28 138	94.00 271	78.39 253	99.04 140	81.26 294	94.18 180	96.19 205

ADS-MVSNet		89.89 257	88.68 262	93.53 229	95.86 199	84.89 280	90.93 324	95.07 288	83.23 302	91.28 180	91.81 314	79.01 244	97.85 251	79.52 301	91.39 220	97.84 160

pmmvs-eth3d		86.22 293	84.45 297	91.53 287	88.34 336	87.25 238	94.47 272	95.01 289	83.47 300	79.51 327	89.61 323	69.75 309	95.71 323	83.13 276	76.73 329	91.64 328

Anonymous202405211		92.07 183	90.83 201	95.76 125	98.19 96	88.75 205	97.58 87	95.00 290	86.00 269	93.64 127	97.45 105	66.24 324	99.53 85	90.68 156	92.71 197	99.01 84

MDA-MVSNet-bldmvs		85.00 300	82.95 303	91.17 294	93.13 309	83.33 296	94.56 270	95.00 290	84.57 287	65.13 340	92.65 299	70.45 303	95.85 320	73.57 325	77.49 326	94.33 299

RPMNet		88.52 274	86.72 283	93.95 207	94.45 272	87.19 241	90.23 329	94.99 292	77.87 331	92.40 152	87.55 332	80.17 222	97.05 301	68.84 335	93.95 185	97.60 174

ambc				86.56 320	83.60 341	70.00 341	85.69 339	94.97 293		80.60 321	88.45 326	37.42 345	96.84 311	82.69 282	75.44 331	92.86 318

testgi		87.97 279	87.21 278	90.24 307	92.86 311	80.76 311	96.67 174	94.97 293	91.74 120	85.52 294	95.83 183	62.66 332	94.47 332	76.25 316	88.36 255	95.48 235

dp		88.90 268	88.26 268	90.81 298	94.58 269	76.62 332	92.85 313	94.93 295	85.12 279	90.07 208	93.07 294	75.81 273	98.12 210	80.53 297	87.42 263	97.71 166

test_0402		86.46 291	84.79 295	91.45 289	95.02 245	85.55 270	96.29 207	94.89 296	80.90 315	82.21 314	93.97 273	68.21 315	97.29 297	62.98 339	88.68 253	91.51 330

tfpn200view9		92.38 169	91.52 176	94.95 166	97.85 113	89.29 191	97.41 101	94.88 297	92.19 109	93.27 139	94.46 248	78.17 255	99.08 134	81.40 290	94.08 181	96.48 200

CVMVSNet		91.23 215	91.75 167	89.67 311	95.77 204	74.69 335	96.44 188	94.88 297	85.81 270	92.18 160	97.64 93	79.07 239	95.58 326	88.06 202	95.86 154	98.74 107

thres400		92.42 167	91.52 176	95.12 158	97.85 113	89.29 191	97.41 101	94.88 297	92.19 109	93.27 139	94.46 248	78.17 255	99.08 134	81.40 290	94.08 181	96.98 184

EPNet		95.20 84	94.56 90	97.14 67	92.80 313	92.68 83	97.85 58	94.87 300	96.64 1	92.46 151	97.80 80	86.23 123	99.65 53	93.72 101	98.62 92	99.10 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SixPastTwentyTwo		89.15 265	88.54 264	90.98 295	93.49 300	80.28 319	96.70 170	94.70 301	90.78 149	84.15 307	95.57 200	71.78 295	97.71 264	84.63 263	85.07 288	94.94 268

thres100view900		92.43 166	91.58 173	94.98 163	97.92 109	89.37 186	97.71 74	94.66 302	92.20 107	93.31 137	94.90 225	78.06 258	99.08 134	81.40 290	94.08 181	96.48 200

thres600view7		92.49 165	91.60 172	95.18 154	97.91 110	89.47 180	97.65 80	94.66 302	92.18 111	93.33 136	94.91 224	78.06 258	99.10 129	81.61 287	94.06 184	96.98 184

PatchT		88.87 269	87.42 274	93.22 243	94.08 283	85.10 276	89.51 333	94.64 304	81.92 309	92.36 155	88.15 330	80.05 224	97.01 306	72.43 327	93.65 188	97.54 177

baseline1		92.82 158	91.90 163	95.55 140	97.20 135	90.77 147	97.19 127	94.58 305	92.20 107	92.36 155	96.34 163	84.16 151	98.21 199	89.20 186	83.90 306	97.68 168

Gipuma		67.86 313	65.41 315	75.18 327	92.66 316	73.45 337	66.50 346	94.52 306	53.33 343	57.80 343	66.07 343	30.81 346	89.20 341	48.15 343	78.88 325	62.90 343
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CostFormer		91.18 221	90.70 205	92.62 262	94.84 256	81.76 307	94.09 288	94.43 307	84.15 291	92.72 150	93.77 279	79.43 235	98.20 201	90.70 155	92.18 207	97.90 156

tpm2		89.96 255	89.21 255	92.23 270	94.91 253	81.25 309	93.78 294	94.42 308	80.62 319	91.56 169	93.44 290	76.44 270	97.94 241	85.60 251	92.08 211	97.49 178

JIA-IIPM		88.26 278	87.04 280	91.91 275	93.52 298	81.42 308	89.38 334	94.38 309	80.84 317	90.93 186	80.74 337	79.22 238	97.92 245	82.76 280	91.62 215	96.38 202

Patchmatch-test		89.42 263	87.99 269	93.70 221	95.27 231	85.11 275	88.98 335	94.37 310	81.11 314	87.10 279	93.69 281	82.28 187	97.50 283	74.37 322	94.76 173	98.48 126

LCM-MVSNet		72.55 310	69.39 313	82.03 322	70.81 349	65.42 345	90.12 331	94.36 311	55.02 342	65.88 339	81.72 336	24.16 352	89.96 340	74.32 323	68.10 339	90.71 334

ADS-MVSNet2		89.45 262	88.59 263	92.03 273	95.86 199	82.26 305	90.93 324	94.32 312	83.23 302	91.28 180	91.81 314	79.01 244	95.99 319	79.52 301	91.39 220	97.84 160

DWT-MVSNet_test		90.76 234	89.89 237	93.38 236	95.04 244	83.70 293	95.85 232	94.30 313	88.19 221	90.46 191	92.80 297	73.61 289	98.50 182	88.16 200	90.58 232	97.95 154

EU-MVSNet		88.72 272	88.90 259	88.20 314	93.15 308	74.21 336	96.63 179	94.22 314	85.18 277	87.32 275	95.97 175	76.16 272	94.98 330	85.27 255	86.17 273	95.41 241

MIMVSNet		88.50 275	86.76 281	93.72 220	94.84 256	87.77 231	91.39 321	94.05 315	86.41 263	87.99 263	92.59 301	63.27 330	95.82 322	77.44 311	92.84 196	97.57 176

OpenMVS_ROB	81.14 20	84.42 302	82.28 304	90.83 297	90.06 329	84.05 289	95.73 237	94.04 316	73.89 335	80.17 325	91.53 318	59.15 335	97.64 269	66.92 337	89.05 247	90.80 333

TinyColmap		86.82 289	85.35 292	91.21 292	94.91 253	82.99 299	93.94 291	94.02 317	83.58 298	81.56 316	94.68 236	62.34 333	98.13 207	75.78 317	87.35 265	92.52 322

IB-MVS	87.33 17	89.91 256	88.28 267	94.79 174	95.26 234	87.70 232	95.12 262	93.95 318	89.35 186	87.03 280	92.49 302	70.74 302	99.19 119	89.18 187	81.37 319	97.49 178
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
LCM-MVSNet-Re		92.50 163	92.52 146	92.44 264	96.82 155	81.89 306	96.92 151	93.71 319	92.41 102	84.30 304	94.60 240	85.08 139	97.03 303	91.51 143	97.36 124	98.40 135

tpm		90.25 249	89.74 246	91.76 284	93.92 286	79.73 323	93.98 289	93.54 320	88.28 219	91.99 164	93.25 293	77.51 264	97.44 288	87.30 224	87.94 257	98.12 147

ET-MVSNet_ETH3D		91.49 201	90.11 229	95.63 134	96.40 177	91.57 116	95.34 251	93.48 321	90.60 161	75.58 332	95.49 206	80.08 223	96.79 312	94.25 88	89.76 242	98.52 119

LFMVS		93.60 128	92.63 139	96.52 83	98.13 100	91.27 125	97.94 50	93.39 322	90.57 162	96.29 66	98.31 44	69.00 310	99.16 123	94.18 90	95.87 153	99.12 74

Patchmatch-RL test		87.38 284	86.24 284	90.81 298	88.74 335	78.40 330	88.12 337	93.17 323	87.11 254	82.17 315	89.29 324	81.95 194	95.60 325	88.64 196	77.02 327	98.41 134

test-LLR		91.42 204	91.19 190	92.12 271	94.59 267	80.66 312	94.29 282	92.98 324	91.11 144	90.76 187	92.37 304	79.02 242	98.07 220	88.81 192	96.74 138	97.63 169

test-mter		90.19 252	89.54 250	92.12 271	94.59 267	80.66 312	94.29 282	92.98 324	87.68 241	90.76 187	92.37 304	67.67 316	98.07 220	88.81 192	96.74 138	97.63 169

test0.0.03 1		89.37 264	88.70 261	91.41 291	92.47 318	85.63 269	95.22 260	92.70 326	91.11 144	86.91 284	93.65 285	79.02 242	93.19 338	78.00 310	89.18 246	95.41 241

new_pmnet		82.89 305	81.12 308	88.18 315	89.63 332	80.18 320	91.77 320	92.57 327	76.79 332	75.56 333	88.23 329	61.22 334	94.48 331	71.43 330	82.92 314	89.87 335

thisisatest0515		92.29 174	91.30 184	95.25 152	96.60 162	88.90 203	94.36 278	92.32 328	87.92 230	93.43 134	94.57 241	77.28 265	99.00 141	89.42 177	95.86 154	97.86 159

thisisatest0530		93.03 146	92.21 154	95.49 144	97.07 142	89.11 199	97.49 97	92.19 329	90.16 169	94.09 118	96.41 159	76.43 271	99.05 138	90.38 158	95.68 159	98.31 141

tttt0517		92.96 149	92.33 151	94.87 169	97.11 140	87.16 243	97.97 49	92.09 330	90.63 157	93.88 124	97.01 124	76.50 268	99.06 137	90.29 161	95.45 161	98.38 137

K. test v3		87.64 283	86.75 282	90.32 306	93.02 310	79.48 325	96.61 180	92.08 331	90.66 155	80.25 324	94.09 268	67.21 320	96.65 314	85.96 247	80.83 321	94.83 277

TESTMET0.1,1		90.06 254	89.42 251	91.97 274	94.41 274	80.62 314	94.29 282	91.97 332	87.28 251	90.44 192	92.47 303	68.79 311	97.67 266	88.50 198	96.60 143	97.61 173

PM-MVS		83.48 303	81.86 306	88.31 313	87.83 338	77.59 331	93.43 302	91.75 333	86.91 256	80.63 320	89.91 321	44.42 344	95.84 321	85.17 258	76.73 329	91.50 331

baseline2		91.63 193	90.86 197	93.94 210	94.33 276	86.32 258	95.92 229	91.64 334	89.37 185	86.94 282	94.69 235	81.62 200	98.69 167	88.64 196	94.57 177	96.81 192

FPMVS		71.27 311	69.85 312	75.50 326	74.64 345	59.03 347	91.30 322	91.50 335	58.80 341	57.92 342	88.28 328	29.98 348	85.53 344	53.43 341	82.84 315	81.95 339

door								91.13 336

door-mid								91.06 337

pmmvs3		79.97 308	77.50 311	87.39 317	82.80 342	79.38 326	92.70 315	90.75 338	70.69 337	78.66 328	87.47 333	51.34 342	93.40 336	73.39 326	69.65 338	89.38 336

DSMNet-mixed		86.34 292	86.12 287	87.00 319	89.88 331	70.43 339	94.93 264	90.08 339	77.97 330	85.42 297	92.78 298	74.44 282	93.96 334	74.43 321	95.14 165	96.62 196

MVS-HIRNet		82.47 306	81.21 307	86.26 321	95.38 219	69.21 342	88.96 336	89.49 340	66.28 338	80.79 319	74.08 341	68.48 313	97.39 292	71.93 329	95.47 160	92.18 326

EPMVS		90.70 239	89.81 241	93.37 237	94.73 261	84.21 286	93.67 298	88.02 341	89.50 182	92.38 154	93.49 288	77.82 262	97.78 258	86.03 245	92.68 198	98.11 150

ANet_high		63.94 314	59.58 316	77.02 325	61.24 351	66.06 343	85.66 340	87.93 342	78.53 328	42.94 345	71.04 342	25.42 351	80.71 345	52.60 342	30.83 345	84.28 338

PMMVS2		70.19 312	66.92 314	80.01 323	76.35 344	65.67 344	86.22 338	87.58 343	64.83 340	62.38 341	80.29 338	26.78 350	88.49 342	63.79 338	54.07 342	85.88 337

lessismore_v0				90.45 304	91.96 324	79.09 328		87.19 344		80.32 323	94.39 250	66.31 323	97.55 277	84.00 270	76.84 328	94.70 289

PMVS	53.92 22	58.58 315	55.40 317	68.12 329	51.00 352	48.64 349	78.86 343	87.10 345	46.77 344	35.84 349	74.28 340	8.76 353	86.34 343	42.07 344	73.91 334	69.38 341
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
gg-mvs-nofinetune		87.82 281	85.61 289	94.44 185	94.46 271	89.27 194	91.21 323	84.61 346	80.88 316	89.89 212	74.98 339	71.50 296	97.53 280	85.75 250	97.21 130	96.51 198

GG-mvs-BLEND				93.62 224	93.69 294	89.20 195	92.39 319	83.33 347		87.98 264	89.84 322	71.00 300	96.87 310	82.08 286	95.40 162	94.80 282

MTMP							97.86 55	82.03 348

DeepMVS_CX				74.68 328	90.84 327	64.34 346		81.61 349	65.34 339	67.47 338	88.01 331	48.60 343	80.13 346	62.33 340	73.68 335	79.58 340

E-PMN		53.28 316	52.56 319	55.43 331	74.43 346	47.13 350	83.63 342	76.30 350	42.23 345	42.59 346	62.22 345	28.57 349	74.40 347	31.53 346	31.51 344	44.78 344

EMVS		52.08 318	51.31 320	54.39 332	72.62 348	45.39 352	83.84 341	75.51 351	41.13 346	40.77 347	59.65 346	30.08 347	73.60 348	28.31 347	29.90 346	44.18 345

MVE	50.73 23	53.25 317	48.81 321	66.58 330	65.34 350	57.50 348	72.49 345	70.94 352	40.15 347	39.28 348	63.51 344	6.89 355	73.48 349	38.29 345	42.38 343	68.76 342
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 319	53.82 318	46.29 333	33.73 353	45.30 353	78.32 344	67.24 353	18.02 348	50.93 344	87.05 334	52.99 341	53.11 350	70.76 333	25.29 347	40.46 346

N_pmnet		78.73 309	78.71 310	78.79 324	92.80 313	46.50 351	94.14 286	43.71 354	78.61 327	80.83 318	91.66 317	74.94 280	96.36 316	67.24 336	84.45 298	93.50 313

wuyk23d		25.11 320	24.57 323	26.74 334	73.98 347	39.89 354	57.88 347	9.80 355	12.27 349	10.39 350	6.97 352	7.03 354	36.44 351	25.43 348	17.39 348	3.89 349

testmvs		13.36 322	16.33 324	4.48 336	5.04 354	2.26 356	93.18 305	3.28 356	2.70 350	8.24 351	21.66 348	2.29 357	2.19 352	7.58 349	2.96 349	9.00 348

test123		13.04 323	15.66 325	5.18 335	4.51 355	3.45 355	92.50 318	1.81 357	2.50 351	7.58 352	20.15 349	3.67 356	2.18 353	7.13 350	1.07 350	9.90 347

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		7.39 325	9.85 327	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	0.00 353	88.65 90	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		8.06 324	10.74 326	0.00 337	0.00 356	0.00 357	0.00 348	0.00 358	0.00 352	0.00 353	96.69 139	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				98.55 1	98.82 52	96.86 1	98.25 28				98.26 50	96.04 1	99.24 116	95.36 63	99.59 15	99.56 22

test_0728_THIRD									94.78 31	98.73 8	98.87 6	95.87 2	99.84 19	97.45 6	99.72 2	99.77 1

GSMVS																98.45 129

test_part2					99.28 25	95.74 6				98.10 17

sam_mvs1												82.76 176				98.45 129

sam_mvs												81.94 195

test_post1							92.81 314				16.58 351	80.53 214	97.68 265	86.20 239

test_post											17.58 350	81.76 197	98.08 217

patchmatchnet-post											90.45 319	82.65 180	98.10 212

gm-plane-assit					93.22 306	78.89 329			84.82 284		93.52 287		98.64 171	87.72 208

test9_res														94.81 80	99.38 48	99.45 44

agg_prior2														93.94 95	99.38 48	99.50 36

test_prior4						93.66 58	96.42 191

test_prior2							96.35 200		92.80 92	96.03 74	97.59 97	92.01 40		95.01 71	99.38 48

旧先验2							95.94 228		81.66 311	97.34 31			98.82 155	92.26 121

新几何2							95.79 235

原ACMM2							95.67 238

testdata2													99.67 49	85.96 247

segment_acmp												92.89 22

testdata1							95.26 259		93.10 79

plane_prior7					96.21 184	89.98 165

plane_prior6					96.10 194	90.00 161						81.32 203

plane_prior4											96.64 142

plane_prior3						90.00 161			94.46 39	91.34 174

plane_prior2							97.74 67		94.85 24

plane_prior1					96.14 192

plane_prior						89.99 163	97.24 119		94.06 47						92.16 208

HQP5-MVS						89.33 188

HQP-NCC					95.86 199		96.65 175		93.55 61	90.14 197

ACMP_Plane					95.86 199		96.65 175		93.55 61	90.14 197

BP-MVS														92.13 127

HQP4-MVS										90.14 197			98.50 182			95.78 224

HQP2-MVS												80.95 206

NP-MVS					95.99 198	89.81 170					95.87 180

MDTV_nov1_ep13_2view						70.35 340	93.10 310		83.88 295	93.55 129		82.47 184		86.25 238		98.38 137

ACMMP++_ref															90.30 237

ACMMP++															91.02 226

Test By Simon												88.73 89

High-resolution multi-view benchmark