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.

SED-MVS		99.28 5	99.11 6	99.77 6	99.93 26	99.30 8	99.96 25	98.43 116	97.27 20	99.80 16	99.94 4	96.71 20	100.00 1	100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 25				99.80 58	97.44 11	100.00 1	100.00 1	99.98 33	100.00 1

test_241102_TWO								98.43 116	97.27 20	99.80 16	99.94 4	97.18 17	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 26	99.30 8		98.43 116	97.26 22	99.80 16	99.88 22	96.71 20	100.00 1

testtj		98.89 18	98.69 18	99.52 26	99.94 14	98.56 53	99.90 76	98.55 83	95.14 78	99.72 31	99.84 46	95.46 43	100.00 1	99.65 32	99.99 20	99.99 20

DVP-MVS		99.30 4	99.16 3	99.73 8	99.93 26	99.29 10	99.95 43	98.32 151	97.28 18	99.83 10	99.91 13	97.22 15	100.00 1	99.99 5	100.00 1	99.89 90
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									96.48 40	99.83 10	99.91 13	97.87 4	100.00 1	99.92 9	100.00 1	100.00 1

test_0728_SECOND				99.82 5	99.94 14	99.47 5	99.95 43	98.43 116					100.00 1	99.99 5	100.00 1	100.00 1

DPM-MVS		98.83 21	98.46 30	99.97 1	99.33 106	99.92 1	99.96 25	98.44 108	97.96 7	99.55 45	99.94 4	97.18 17	100.00 1	93.81 191	99.94 57	99.98 51

GST-MVS		98.27 59	97.97 64	99.17 57	99.92 35	97.57 88	99.93 64	98.39 135	94.04 123	98.80 91	99.74 81	92.98 118	100.00 1	98.16 97	99.76 89	99.93 81

SMA-MVS		98.76 26	98.48 29	99.62 15	99.87 52	98.87 27	99.86 101	98.38 139	93.19 151	99.77 23	99.94 4	95.54 40	100.00 1	99.74 24	99.99 20	100.00 1
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ACMMP_NAP		98.49 43	98.14 54	99.54 23	99.66 87	98.62 50	99.85 104	98.37 142	94.68 92	99.53 47	99.83 49	92.87 120	100.00 1	98.66 82	99.84 80	99.99 20

zzz-MVS		98.33 55	98.00 62	99.30 47	99.85 55	97.93 78	99.80 122	98.28 158	95.76 62	97.18 141	99.88 22	92.74 124	100.00 1	98.67 79	99.88 76	99.99 20

MTAPA		98.29 58	97.96 67	99.30 47	99.85 55	97.93 78	99.39 200	98.28 158	95.76 62	97.18 141	99.88 22	92.74 124	100.00 1	98.67 79	99.88 76	99.99 20

HFP-MVS		98.56 37	98.37 40	99.14 63	99.96 8	97.43 99	99.95 43	98.61 69	94.77 88	99.31 66	99.85 33	94.22 83	100.00 1	98.70 77	99.98 33	99.98 51

region2R		98.54 39	98.37 40	99.05 73	99.96 8	97.18 107	99.96 25	98.55 83	94.87 86	99.45 53	99.85 33	94.07 89	100.00 1	98.67 79	100.00 1	99.98 51

#test#		98.59 35	98.41 33	99.14 63	99.96 8	97.43 99	99.95 43	98.61 69	95.00 81	99.31 66	99.85 33	94.22 83	100.00 1	98.78 73	99.98 33	99.98 51

HPM-MVS++		99.07 9	98.88 13	99.63 12	99.90 42	99.02 19	99.95 43	98.56 77	97.56 13	99.44 54	99.85 33	95.38 45	100.00 1	99.31 43	99.99 20	99.87 93

新几何1				99.42 38	99.75 76	98.27 65		98.63 66	92.69 168	99.55 45	99.82 53	94.40 71	100.00 1	91.21 225	99.94 57	99.99 20

无先验							99.49 186	98.71 53	93.46 144				100.00 1	94.36 178		99.99 20

1121		98.03 69	97.57 80	99.40 41	99.74 77	98.21 66	98.31 291	98.62 67	92.78 163	99.53 47	99.83 49	95.08 50	100.00 1	94.36 178	99.92 67	99.99 20

MSLP-MVS++		99.13 7	99.01 9	99.49 31	99.94 14	98.46 59	99.98 10	98.86 45	97.10 25	99.80 16	99.94 4	95.92 33	100.00 1	99.51 34	100.00 1	100.00 1

ACMMPR		98.50 42	98.32 44	99.05 73	99.96 8	97.18 107	99.95 43	98.60 71	94.77 88	99.31 66	99.84 46	93.73 98	100.00 1	98.70 77	99.98 33	99.98 51

MP-MVS		98.23 63	97.97 64	99.03 75	99.94 14	97.17 110	99.95 43	98.39 135	94.70 91	98.26 119	99.81 57	91.84 145	100.00 1	98.85 67	99.97 44	99.93 81
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		98.34 54	98.13 55	98.99 79	99.92 35	97.00 113	99.75 137	99.50 16	93.90 130	99.37 63	99.76 72	93.24 113	100.00 1	97.75 120	99.96 48	99.98 51

MCST-MVS		99.32 3	99.14 4	99.86 3	99.97 3	99.59 3	99.97 18	98.64 63	98.47 2	99.13 78	99.92 11	96.38 26	100.00 1	99.74 24	100.00 1	100.00 1

mPP-MVS		98.39 52	98.20 50	98.97 81	99.97 3	96.92 117	99.95 43	98.38 139	95.04 80	98.61 103	99.80 58	93.39 104	100.00 1	98.64 83	100.00 1	99.98 51

CNVR-MVS		99.40 1	99.26 1	99.84 4	99.98 2	99.51 4	99.98 10	98.69 55	98.20 3	99.93 1	99.98 2	96.82 19	100.00 1	99.75 22	100.00 1	99.99 20

NCCC		99.37 2	99.25 2	99.71 10	99.96 8	99.15 16	99.97 18	98.62 67	98.02 6	99.90 2	99.95 3	97.33 13	100.00 1	99.54 33	100.00 1	100.00 1

CP-MVS		98.45 46	98.32 44	98.87 86	99.96 8	96.62 126	99.97 18	98.39 135	94.43 102	98.90 88	99.87 26	94.30 81	100.00 1	99.04 54	99.99 20	99.99 20

DP-MVS Recon		98.41 49	98.02 61	99.56 21	99.97 3	98.70 43	99.92 68	98.44 108	92.06 195	98.40 112	99.84 46	95.68 38	100.00 1	98.19 95	99.71 93	99.97 63

PHI-MVS		98.41 49	98.21 49	99.03 75	99.86 54	97.10 111	99.98 10	98.80 50	90.78 229	99.62 40	99.78 66	95.30 46	100.00 1	99.80 18	99.93 63	99.99 20

DeepPCF-MVS	95.94 2	97.71 85	98.98 10	93.92 267	99.63 88	81.76 342	99.96 25	98.56 77	99.47 1	99.19 76	99.99 1	94.16 87	100.00 1	99.92 9	99.93 63	100.00 1

DeepC-MVS_fast	96.59 1	98.81 22	98.54 26	99.62 15	99.90 42	98.85 29	99.24 219	98.47 103	98.14 4	99.08 79	99.91 13	93.09 116	100.00 1	99.04 54	99.99 20	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		97.23 101	96.80 105	98.51 112	99.99 1	95.60 166	99.09 228	98.84 47	93.32 147	96.74 151	99.72 84	86.04 211	100.00 1	98.01 105	99.43 112	99.94 80

ZNCC-MVS		98.31 56	98.03 60	99.17 57	99.88 49	97.59 87	99.94 58	98.44 108	94.31 110	98.50 107	99.82 53	93.06 117	99.99 36	98.30 94	99.99 20	99.93 81

DPE-MVS		99.26 6	99.10 7	99.74 7	99.89 45	99.24 14	99.87 90	98.44 108	97.48 15	99.64 36	99.94 4	96.68 22	99.99 36	99.99 5	100.00 1	99.99 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
testdata2													99.99 36	90.54 241

CPTT-MVS		97.64 87	97.32 89	98.58 105	99.97 3	95.77 159	99.96 25	98.35 146	89.90 242	98.36 113	99.79 62	91.18 155	99.99 36	98.37 91	99.99 20	99.99 20

API-MVS		97.86 74	97.66 74	98.47 114	99.52 96	95.41 170	99.47 189	98.87 44	91.68 205	98.84 89	99.85 33	92.34 134	99.99 36	98.44 89	99.96 48	100.00 1

ACMMP		97.74 83	97.44 83	98.66 97	99.92 35	96.13 147	99.18 223	99.45 17	94.84 87	96.41 161	99.71 86	91.40 149	99.99 36	97.99 107	98.03 146	99.87 93
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
CANet_DTU		96.76 117	96.15 121	98.60 102	98.78 136	97.53 90	99.84 108	97.63 217	97.25 23	99.20 73	99.64 99	81.36 248	99.98 42	92.77 211	98.89 124	98.28 206

SD-MVS		98.92 16	98.70 17	99.56 21	99.70 85	98.73 41	99.94 58	98.34 148	96.38 44	99.81 12	99.76 72	94.59 67	99.98 42	99.84 13	99.96 48	99.97 63
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
abl_6		97.67 86	97.34 87	98.66 97	99.68 86	96.11 150	99.68 153	98.14 180	93.80 134	99.27 71	99.70 88	88.65 190	99.98 42	97.46 124	99.72 92	99.89 90

PAPM_NR		98.12 66	97.93 68	98.70 94	99.94 14	96.13 147	99.82 115	98.43 116	94.56 97	97.52 134	99.70 88	94.40 71	99.98 42	97.00 135	99.98 33	99.99 20

PAPR		98.52 41	98.16 53	99.58 20	99.97 3	98.77 36	99.95 43	98.43 116	95.35 73	98.03 124	99.75 77	94.03 90	99.98 42	98.11 100	99.83 81	99.99 20

CSCG		97.10 104	97.04 98	97.27 166	99.89 45	91.92 248	99.90 76	99.07 31	88.67 262	95.26 181	99.82 53	93.17 115	99.98 42	98.15 98	99.47 109	99.90 89

CNLPA		97.76 82	97.38 84	98.92 85	99.53 95	96.84 118	99.87 90	98.14 180	93.78 135	96.55 156	99.69 91	92.28 135	99.98 42	97.13 131	99.44 111	99.93 81

MG-MVS		98.91 17	98.65 20	99.68 11	99.94 14	99.07 18	99.64 163	99.44 18	97.33 17	99.00 85	99.72 84	94.03 90	99.98 42	98.73 76	100.00 1	100.00 1

MAR-MVS		97.43 91	97.19 92	98.15 132	99.47 100	94.79 189	99.05 239	98.76 51	92.65 171	98.66 100	99.82 53	88.52 191	99.98 42	98.12 99	99.63 97	99.67 117
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
MP-MVS-pluss		98.07 68	97.64 75	99.38 44	99.74 77	98.41 60	99.74 140	98.18 173	93.35 146	96.45 158	99.85 33	92.64 127	99.97 51	98.91 63	99.89 74	99.77 104
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PLC	95.54 3	97.93 72	97.89 69	98.05 136	99.82 65	94.77 190	99.92 68	98.46 105	93.93 128	97.20 140	99.27 129	95.44 44	99.97 51	97.41 125	99.51 108	99.41 161
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
XVS		98.70 28	98.55 25	99.15 61	99.94 14	97.50 94	99.94 58	98.42 127	96.22 49	99.41 57	99.78 66	94.34 76	99.96 53	98.92 61	99.95 51	99.99 20

X-MVStestdata		93.83 191	92.06 220	99.15 61	99.94 14	97.50 94	99.94 58	98.42 127	96.22 49	99.41 57	41.37 368	94.34 76	99.96 53	98.92 61	99.95 51	99.99 20

原ACMM1				98.96 82	99.73 81	96.99 114		98.51 97	94.06 121	99.62 40	99.85 33	94.97 59	99.96 53	95.11 157	99.95 51	99.92 87

1314		96.84 113	95.96 132	99.48 33	96.74 240	98.52 55	98.31 291	98.86 45	95.82 58	89.91 235	98.98 151	87.49 197	99.96 53	97.80 113	99.73 91	99.96 70

MVS		96.60 125	95.56 144	99.72 9	96.85 233	99.22 15	98.31 291	98.94 36	91.57 208	90.90 223	99.61 101	86.66 206	99.96 53	97.36 126	99.88 76	99.99 20

UGNet		95.33 157	94.57 165	97.62 153	98.55 142	94.85 185	98.67 275	99.32 24	95.75 65	96.80 150	96.27 252	72.18 311	99.96 53	94.58 174	99.05 123	98.04 210
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
QAPM		95.40 156	94.17 172	99.10 69	96.92 227	97.71 83	99.40 196	98.68 56	89.31 247	88.94 261	98.89 161	82.48 237	99.96 53	93.12 208	99.83 81	99.62 126

CANet		98.27 59	97.82 70	99.63 12	99.72 83	99.10 17	99.98 10	98.51 97	97.00 28	98.52 105	99.71 86	87.80 194	99.95 60	99.75 22	99.38 113	99.83 96

旧先验2							99.46 191		94.21 114	99.85 6			99.95 60	96.96 137

PVSNet_BlendedMVS		96.05 141	95.82 139	96.72 180	99.59 90	96.99 114	99.95 43	99.10 28	94.06 121	98.27 117	95.80 261	89.00 185	99.95 60	99.12 47	87.53 252	93.24 315

PVSNet_Blended		97.94 71	97.64 75	98.83 88	99.59 90	96.99 114	100.00 1	99.10 28	95.38 72	98.27 117	99.08 141	89.00 185	99.95 60	99.12 47	99.25 117	99.57 138

DP-MVS		94.54 177	93.42 192	97.91 141	99.46 102	94.04 200	98.93 251	97.48 239	81.15 332	90.04 232	99.55 105	87.02 203	99.95 60	88.97 257	98.11 141	99.73 109

PVSNet	91.05 13	97.13 103	96.69 108	98.45 116	99.52 96	95.81 157	99.95 43	99.65 10	94.73 90	99.04 81	99.21 136	84.48 225	99.95 60	94.92 160	98.74 128	99.58 137

3Dnovator	91.47 12	96.28 138	95.34 149	99.08 71	96.82 235	97.47 97	99.45 192	98.81 48	95.52 70	89.39 249	99.00 148	81.97 240	99.95 60	97.27 128	99.83 81	99.84 95

LS3D		95.84 146	95.11 156	98.02 137	99.85 55	95.10 180	98.74 268	98.50 101	87.22 282	93.66 199	99.86 29	87.45 198	99.95 60	90.94 234	99.81 87	99.02 190

testdata				98.42 119	99.47 100	95.33 172		98.56 77	93.78 135	99.79 21	99.85 33	93.64 101	99.94 68	94.97 159	99.94 57	100.00 1

TSAR-MVS + GP.		98.60 33	98.51 28	98.86 87	99.73 81	96.63 125	99.97 18	97.92 199	98.07 5	98.76 95	99.55 105	95.00 57	99.94 68	99.91 11	97.68 150	99.99 20

DELS-MVS		98.54 39	98.22 48	99.50 29	99.15 111	98.65 48	100.00 1	98.58 73	97.70 9	98.21 121	99.24 134	92.58 128	99.94 68	98.63 84	99.94 57	99.92 87
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
F-COLMAP		96.93 110	96.95 101	96.87 175	99.71 84	91.74 253	99.85 104	97.95 195	93.11 154	95.72 174	99.16 138	92.35 133	99.94 68	95.32 155	99.35 114	98.92 192

3Dnovator+	91.53 11	96.31 135	95.24 151	99.52 26	96.88 232	98.64 49	99.72 148	98.24 164	95.27 76	88.42 272	98.98 151	82.76 236	99.94 68	97.10 133	99.83 81	99.96 70

OpenMVS	90.15 15	94.77 169	93.59 186	98.33 123	96.07 249	97.48 96	99.56 174	98.57 75	90.46 232	86.51 296	98.95 157	78.57 274	99.94 68	93.86 187	99.74 90	97.57 219

EPNet		98.49 43	98.40 35	98.77 90	99.62 89	96.80 120	99.90 76	99.51 15	97.60 12	99.20 73	99.36 124	93.71 99	99.91 74	97.99 107	98.71 129	99.61 128
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20240529		92.10 232	90.65 243	96.47 186	98.82 133	90.61 274	98.72 270	98.67 59	75.54 347	93.90 197	98.58 182	66.23 333	99.90 75	94.70 171	90.67 221	98.90 195

CHOSEN 1792x2688		96.81 114	96.53 113	97.64 151	98.91 127	93.07 220	99.65 159	99.80 3	95.64 67	95.39 178	98.86 167	84.35 227	99.90 75	96.98 136	99.16 121	99.95 78

MVS_111021_LR		98.42 48	98.38 38	98.53 111	99.39 103	95.79 158	99.87 90	99.86 2	96.70 36	98.78 92	99.79 62	92.03 141	99.90 75	99.17 46	99.86 79	99.88 92

DeepC-MVS	94.51 4	96.92 111	96.40 117	98.45 116	99.16 110	95.90 154	99.66 156	98.06 186	96.37 47	94.37 190	99.49 110	83.29 234	99.90 75	97.63 121	99.61 101	99.55 140
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PS-MVSNAJ		98.44 47	98.20 50	99.16 59	98.80 135	98.92 23	99.54 178	98.17 174	97.34 16	99.85 6	99.85 33	91.20 152	99.89 79	99.41 40	99.67 95	98.69 203

VNet		97.21 102	96.57 112	99.13 68	98.97 119	97.82 81	99.03 241	99.21 27	94.31 110	99.18 77	98.88 163	86.26 210	99.89 79	98.93 60	94.32 205	99.69 114

sss		97.57 88	97.03 99	99.18 54	98.37 149	98.04 72	99.73 145	99.38 21	93.46 144	98.76 95	99.06 142	91.21 151	99.89 79	96.33 144	97.01 166	99.62 126

MVS_111021_HR		98.72 27	98.62 22	99.01 78	99.36 105	97.18 107	99.93 64	99.90 1	96.81 33	98.67 99	99.77 68	93.92 92	99.89 79	99.27 45	99.94 57	99.96 70

PVSNet_0	88.03 19	91.80 239	90.27 251	96.38 193	98.27 156	90.46 278	99.94 58	99.61 11	93.99 124	86.26 303	97.39 215	71.13 317	99.89 79	98.77 74	67.05 349	98.79 200

PCF-MVS	94.20 5	95.18 159	94.10 174	98.43 118	98.55 142	95.99 152	97.91 307	97.31 257	90.35 235	89.48 248	99.22 135	85.19 220	99.89 79	90.40 245	98.47 133	99.41 161
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Anonymous202405211		93.10 209	91.99 221	96.40 191	99.10 112	89.65 292	98.88 256	97.93 197	83.71 321	94.00 195	98.75 172	68.79 322	99.88 85	95.08 158	91.71 220	99.68 115

AllTest		92.48 223	91.64 226	95.00 224	99.01 115	88.43 305	98.94 250	96.82 305	86.50 291	88.71 263	98.47 190	74.73 301	99.88 85	85.39 292	96.18 178	96.71 223

TestCases				95.00 224	99.01 115	88.43 305		96.82 305	86.50 291	88.71 263	98.47 190	74.73 301	99.88 85	85.39 292	96.18 178	96.71 223

PVSNet_Blended_VisFu		97.27 99	96.81 104	98.66 97	98.81 134	96.67 124	99.92 68	98.64 63	94.51 99	96.38 162	98.49 186	89.05 184	99.88 85	97.10 133	98.34 135	99.43 159

MSDG		94.37 183	93.36 196	97.40 160	98.88 130	93.95 204	99.37 203	97.38 250	85.75 303	90.80 224	99.17 137	84.11 229	99.88 85	86.35 286	98.43 134	98.36 205

xxxxxxxxxxxxxcwj		98.98 14	98.79 15	99.54 23	99.82 65	98.79 33	99.96 25	97.52 234	97.66 10	99.81 12	99.89 19	94.70 65	99.86 90	99.84 13	99.93 63	99.96 70

SF-MVS		98.67 30	98.40 35	99.50 29	99.77 73	98.67 44	99.90 76	98.21 168	93.53 142	99.81 12	99.89 19	94.70 65	99.86 90	99.84 13	99.93 63	99.96 70

ETH3 D test6400		98.81 22	98.54 26	99.59 18	99.93 26	98.93 22	99.93 64	98.46 105	94.56 97	99.84 8	99.92 11	94.32 80	99.86 90	99.96 8	99.98 33	100.00 1

ETH3D-3000-0.1		98.68 29	98.42 31	99.47 34	99.83 63	98.57 51	99.90 76	98.37 142	93.81 133	99.81 12	99.90 17	94.34 76	99.86 90	99.84 13	99.98 33	99.97 63

ETH3D cwj APD-0.16		98.40 51	98.07 59	99.40 41	99.59 90	98.41 60	99.86 101	98.24 164	92.18 190	99.73 27	99.87 26	93.47 103	99.85 94	99.74 24	99.95 51	99.93 81

9.14			98.38 38		99.87 52		99.91 72	98.33 149	93.22 150	99.78 22	99.89 19	94.57 68	99.85 94	99.84 13	99.97 44

TEST9					99.92 35	98.92 23	99.96 25	98.43 116	93.90 130	99.71 32	99.86 29	95.88 34	99.85 94

train_agg		98.88 19	98.65 20	99.59 18	99.92 35	98.92 23	99.96 25	98.43 116	94.35 107	99.71 32	99.86 29	95.94 31	99.85 94	99.69 31	99.98 33	99.99 20

test_8					99.92 35	98.88 26	99.96 25	98.43 116	94.35 107	99.69 34	99.85 33	95.94 31	99.85 94

agg_prior1		98.88 19	98.66 19	99.54 23	99.93 26	98.77 36	99.96 25	98.43 116	94.63 96	99.63 38	99.85 33	95.79 37	99.85 94	99.72 28	99.99 20	99.99 20

agg_prior					99.93 26	98.77 36		98.43 116		99.63 38			99.85 94

SteuartSystems-ACMMP		99.02 11	98.97 11	99.18 54	98.72 138	97.71 83	99.98 10	98.44 108	96.85 29	99.80 16	99.91 13	97.57 6	99.85 94	99.44 38	99.99 20	99.99 20
Skip Steuart: Steuart Systems R&D Blog.
COLMAP_ROB	90.47 14	92.18 230	91.49 232	94.25 254	99.00 117	88.04 311	98.42 289	96.70 312	82.30 329	88.43 270	99.01 146	76.97 281	99.85 94	86.11 289	96.50 174	94.86 230
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_yl		97.83 77	97.37 85	99.21 51	99.18 108	97.98 75	99.64 163	99.27 25	91.43 214	97.88 128	98.99 149	95.84 35	99.84 103	98.82 69	95.32 197	99.79 100

DCV-MVSNet		97.83 77	97.37 85	99.21 51	99.18 108	97.98 75	99.64 163	99.27 25	91.43 214	97.88 128	98.99 149	95.84 35	99.84 103	98.82 69	95.32 197	99.79 100

PatchMatch-RL		96.04 142	95.40 146	97.95 138	99.59 90	95.22 178	99.52 180	99.07 31	93.96 126	96.49 157	98.35 193	82.28 238	99.82 105	90.15 248	99.22 120	98.81 199

ZD-MVS					99.92 35	98.57 51		98.52 90	92.34 186	99.31 66	99.83 49	95.06 52	99.80 106	99.70 30	99.97 44

test_prior3		98.99 13	98.84 14	99.43 35	99.94 14	98.49 57	99.95 43	98.65 60	95.78 60	99.73 27	99.76 72	96.00 29	99.80 106	99.78 20	100.00 1	99.99 20

test_prior				99.43 35	99.94 14	98.49 57		98.65 60					99.80 106			99.99 20

APDe-MVS		99.06 10	98.91 12	99.51 28	99.94 14	98.76 40	99.91 72	98.39 135	97.20 24	99.46 52	99.85 33	95.53 42	99.79 109	99.86 12	100.00 1	99.99 20

XVG-OURS-SEG-HR		94.79 167	94.70 164	95.08 221	98.05 168	89.19 295	99.08 230	97.54 230	93.66 139	94.87 184	99.58 103	78.78 272	99.79 109	97.31 127	93.40 214	96.25 225

test1172		98.38 53	98.25 47	98.77 90	99.88 49	96.56 129	99.80 122	98.36 144	94.68 92	99.20 73	99.80 58	93.28 110	99.78 111	99.34 42	99.92 67	99.98 51

SR-MVS-dyc-post		98.31 56	98.17 52	98.71 93	99.79 70	96.37 136	99.76 134	98.31 153	94.43 102	99.40 61	99.75 77	93.28 110	99.78 111	98.90 64	99.92 67	99.97 63

SR-MVS		98.46 45	98.30 46	98.93 84	99.88 49	97.04 112	99.84 108	98.35 146	94.92 83	99.32 65	99.80 58	93.35 105	99.78 111	99.30 44	99.95 51	99.96 70

RPMNet		89.76 280	87.28 295	97.19 167	96.29 245	92.66 231	92.01 350	98.31 153	70.19 354	96.94 145	85.87 353	87.25 200	99.78 111	62.69 356	95.96 183	99.13 186

hse-mvs3		94.92 165	94.36 168	96.59 185	98.85 132	91.29 264	98.93 251	98.94 36	95.90 56	98.77 93	98.42 192	90.89 161	99.77 115	97.80 113	70.76 339	98.72 202

VDD-MVS		93.77 195	92.94 201	96.27 195	98.55 142	90.22 282	98.77 267	97.79 210	90.85 227	96.82 149	99.42 116	61.18 348	99.77 115	98.95 58	94.13 207	98.82 198

HY-MVS	92.50 7	97.79 81	97.17 94	99.63 12	98.98 118	99.32 6	97.49 312	99.52 13	95.69 66	98.32 115	97.41 213	93.32 107	99.77 115	98.08 103	95.75 190	99.81 98

Regformer-1		98.79 24	98.60 23	99.36 45	99.85 55	98.34 62	99.87 90	98.52 90	96.05 53	99.41 57	99.79 62	94.93 60	99.76 118	99.07 49	99.90 72	99.99 20

Regformer-2		98.78 25	98.59 24	99.36 45	99.85 55	98.32 63	99.87 90	98.52 90	96.04 54	99.41 57	99.79 62	94.92 61	99.76 118	99.05 50	99.90 72	99.98 51

APD-MVS_3200maxsize		98.25 62	98.08 58	98.78 89	99.81 68	96.60 127	99.82 115	98.30 156	93.95 127	99.37 63	99.77 68	92.84 121	99.76 118	98.95 58	99.92 67	99.97 63

Regformer-3		98.58 36	98.41 33	99.10 69	99.84 60	97.57 88	99.66 156	98.52 90	95.79 59	99.01 83	99.77 68	94.40 71	99.75 121	98.82 69	99.83 81	99.98 51

Regformer-4		98.56 37	98.39 37	99.08 71	99.84 60	97.52 91	99.66 156	98.52 90	95.76 62	99.01 83	99.77 68	94.33 79	99.75 121	98.80 72	99.83 81	99.98 51

CDPH-MVS		98.65 31	98.36 42	99.49 31	99.94 14	98.73 41	99.87 90	98.33 149	93.97 125	99.76 24	99.87 26	94.99 58	99.75 121	98.55 86	100.00 1	99.98 51

test12				99.43 35	99.74 77	98.56 53		98.40 132		99.65 35		94.76 63	99.75 121		99.98 33	99.99 20

XVG-OURS		94.82 166	94.74 163	95.06 222	98.00 170	89.19 295	99.08 230	97.55 228	94.10 117	94.71 185	99.62 100	80.51 259	99.74 125	96.04 148	93.06 218	96.25 225

APD-MVS		98.62 32	98.35 43	99.41 39	99.90 42	98.51 56	99.87 90	98.36 144	94.08 118	99.74 26	99.73 83	94.08 88	99.74 125	99.42 39	99.99 20	99.99 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
WTY-MVS		98.10 67	97.60 78	99.60 17	98.92 125	99.28 12	99.89 84	99.52 13	95.58 69	98.24 120	99.39 121	93.33 106	99.74 125	97.98 109	95.58 193	99.78 103

EI-MVSNet-UG-set		98.14 65	97.99 63	98.60 102	99.80 69	96.27 138	99.36 205	98.50 101	95.21 77	98.30 116	99.75 77	93.29 109	99.73 128	98.37 91	99.30 115	99.81 98

MSP-MVS		99.09 8	99.12 5	98.98 80	99.93 26	97.24 104	99.95 43	98.42 127	97.50 14	99.52 50	99.88 22	97.43 12	99.71 129	99.50 35	99.98 33	100.00 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
xiu_mvs_v2_base		98.23 63	97.97 64	99.02 77	98.69 139	98.66 46	99.52 180	98.08 185	97.05 26	99.86 4	99.86 29	90.65 163	99.71 129	99.39 41	98.63 130	98.69 203

EI-MVSNet-Vis-set		98.27 59	98.11 57	98.75 92	99.83 63	96.59 128	99.40 196	98.51 97	95.29 75	98.51 106	99.76 72	93.60 102	99.71 129	98.53 87	99.52 106	99.95 78

ab-mvs		94.69 171	93.42 192	98.51 112	98.07 167	96.26 139	96.49 327	98.68 56	90.31 236	94.54 186	97.00 228	76.30 289	99.71 129	95.98 149	93.38 215	99.56 139

xiu_mvs_v1_base_debu		97.43 91	97.06 95	98.55 106	97.74 188	98.14 67	99.31 210	97.86 205	96.43 41	99.62 40	99.69 91	85.56 215	99.68 133	99.05 50	98.31 137	97.83 212

xiu_mvs_v1_base		97.43 91	97.06 95	98.55 106	97.74 188	98.14 67	99.31 210	97.86 205	96.43 41	99.62 40	99.69 91	85.56 215	99.68 133	99.05 50	98.31 137	97.83 212

xiu_mvs_v1_base_debi		97.43 91	97.06 95	98.55 106	97.74 188	98.14 67	99.31 210	97.86 205	96.43 41	99.62 40	99.69 91	85.56 215	99.68 133	99.05 50	98.31 137	97.83 212

HPM-MVS		97.96 70	97.72 72	98.68 95	99.84 60	96.39 135	99.90 76	98.17 174	92.61 173	98.62 102	99.57 104	91.87 144	99.67 136	98.87 66	99.99 20	99.99 20
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		96.54 126	95.96 132	98.27 126	98.23 159	95.71 163	98.00 305	98.45 107	93.72 138	98.41 110	99.27 129	88.71 189	99.66 137	91.19 226	97.69 149	99.44 158

HPM-MVS_fast		97.80 80	97.50 81	98.68 95	99.79 70	96.42 132	99.88 87	98.16 177	91.75 204	98.94 87	99.54 107	91.82 146	99.65 138	97.62 122	99.99 20	99.99 20

114514_t		97.41 95	96.83 103	99.14 63	99.51 98	97.83 80	99.89 84	98.27 161	88.48 266	99.06 80	99.66 97	90.30 167	99.64 139	96.32 145	99.97 44	99.96 70

TSAR-MVS + MP.		98.93 15	98.77 16	99.41 39	99.74 77	98.67 44	99.77 129	98.38 139	96.73 35	99.88 3	99.74 81	94.89 62	99.59 140	99.80 18	99.98 33	99.97 63
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
LFMVS		94.75 170	93.56 188	98.30 124	99.03 114	95.70 164	98.74 268	97.98 192	87.81 275	98.47 108	99.39 121	67.43 330	99.53 141	98.01 105	95.20 199	99.67 117

canonicalmvs		97.09 106	96.32 118	99.39 43	98.93 123	98.95 21	99.72 148	97.35 252	94.45 100	97.88 128	99.42 116	86.71 205	99.52 142	98.48 88	93.97 210	99.72 111

thres200		96.96 108	96.21 120	99.22 50	98.97 119	98.84 30	99.85 104	99.71 5	93.17 152	96.26 164	98.88 163	89.87 172	99.51 143	94.26 182	94.91 200	99.31 172

OMC-MVS		97.28 98	97.23 91	97.41 159	99.76 74	93.36 218	99.65 159	97.95 195	96.03 55	97.41 137	99.70 88	89.61 174	99.51 143	96.73 142	98.25 140	99.38 163

thres100view900		96.74 119	95.92 135	99.18 54	98.90 128	98.77 36	99.74 140	99.71 5	92.59 175	95.84 170	98.86 167	89.25 181	99.50 145	93.84 188	94.57 201	99.27 175

tfpn200view9		96.79 115	95.99 125	99.19 53	98.94 121	98.82 31	99.78 126	99.71 5	92.86 157	96.02 167	98.87 165	89.33 179	99.50 145	93.84 188	94.57 201	99.27 175

thres600view7		96.69 122	95.87 138	99.14 63	98.90 128	98.78 35	99.74 140	99.71 5	92.59 175	95.84 170	98.86 167	89.25 181	99.50 145	93.44 201	94.50 204	99.16 182

thres400		96.78 116	95.99 125	99.16 59	98.94 121	98.82 31	99.78 126	99.71 5	92.86 157	96.02 167	98.87 165	89.33 179	99.50 145	93.84 188	94.57 201	99.16 182

VDDNet		93.12 208	91.91 223	96.76 178	96.67 243	92.65 233	98.69 273	98.21 168	82.81 326	97.75 131	99.28 126	61.57 346	99.48 149	98.09 102	94.09 208	98.15 208

RPSCF		91.80 239	92.79 204	88.83 324	98.15 164	69.87 355	98.11 301	96.60 315	83.93 319	94.33 191	99.27 129	79.60 266	99.46 150	91.99 216	93.16 217	97.18 221

alignmvs		97.81 79	97.33 88	99.25 49	98.77 137	98.66 46	99.99 5	98.44 108	94.40 106	98.41 110	99.47 111	93.65 100	99.42 151	98.57 85	94.26 206	99.67 117

Test_1112_low_res		95.72 148	94.83 160	98.42 119	97.79 184	96.41 133	99.65 159	96.65 314	92.70 167	92.86 210	96.13 256	92.15 138	99.30 152	91.88 219	93.64 212	99.55 140

1112_ss		96.01 143	95.20 153	98.42 119	97.80 183	96.41 133	99.65 159	96.66 313	92.71 166	92.88 209	99.40 119	92.16 137	99.30 152	91.92 218	93.66 211	99.55 140

cascas		94.64 174	93.61 183	97.74 149	97.82 182	96.26 139	99.96 25	97.78 211	85.76 301	94.00 195	97.54 210	76.95 282	99.21 154	97.23 129	95.43 195	97.76 216

TAPA-MVS	92.12 8	94.42 181	93.60 185	96.90 174	99.33 106	91.78 252	99.78 126	98.00 189	89.89 243	94.52 187	99.47 111	91.97 142	99.18 155	69.90 346	99.52 106	99.73 109
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IB-MVS	92.85 6	94.99 164	93.94 178	98.16 129	97.72 192	95.69 165	99.99 5	98.81 48	94.28 112	92.70 211	96.90 230	95.08 50	99.17 156	96.07 147	73.88 337	99.60 130
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
thisisatest0515		97.41 95	97.02 100	98.59 104	97.71 194	97.52 91	99.97 18	98.54 87	91.83 200	97.45 136	99.04 143	97.50 8	99.10 157	94.75 168	96.37 177	99.16 182

thisisatest0530		97.10 104	96.72 107	98.22 128	97.60 197	96.70 122	99.92 68	98.54 87	91.11 221	97.07 144	98.97 153	97.47 9	99.03 158	93.73 196	96.09 180	98.92 192

tttt0517		96.85 112	96.49 114	97.92 140	97.48 205	95.89 156	99.85 104	98.54 87	90.72 230	96.63 153	98.93 160	97.47 9	99.02 159	93.03 209	95.76 189	98.85 196

mvs-test1		95.53 153	95.97 130	94.20 255	97.77 185	85.44 324	99.95 43	97.06 281	94.92 83	96.58 154	98.72 173	85.81 212	98.98 160	94.80 165	98.11 141	98.18 207

MVS_Test		96.46 129	95.74 140	98.61 101	98.18 162	97.23 105	99.31 210	97.15 270	91.07 222	98.84 89	97.05 226	88.17 193	98.97 161	94.39 177	97.50 153	99.61 128

tpmvs		94.28 187	93.57 187	96.40 191	98.55 142	91.50 262	95.70 338	98.55 83	87.47 277	92.15 213	94.26 318	91.42 148	98.95 162	88.15 266	95.85 186	98.76 201

EIA-MVS		97.53 89	97.46 82	97.76 147	98.04 169	94.84 186	99.98 10	97.61 222	94.41 105	97.90 127	99.59 102	92.40 132	98.87 163	98.04 104	99.13 122	99.59 131

tpm cat1		93.51 201	92.52 212	96.47 186	97.77 185	91.47 263	96.13 331	98.06 186	80.98 333	92.91 208	93.78 322	89.66 173	98.87 163	87.03 281	96.39 176	99.09 188

ETV-MVS		97.92 73	97.80 71	98.25 127	98.14 165	96.48 130	99.98 10	97.63 217	95.61 68	99.29 70	99.46 113	92.55 129	98.82 165	99.02 56	98.54 131	99.46 154

BH-RMVSNet		95.18 159	94.31 170	97.80 143	98.17 163	95.23 177	99.76 134	97.53 232	92.52 180	94.27 192	99.25 133	76.84 283	98.80 166	90.89 236	99.54 105	99.35 168

gm-plane-assit					96.97 226	93.76 208			91.47 212		98.96 155		98.79 167	94.92 160

casdiffmvs		96.42 131	95.97 130	97.77 146	97.30 214	94.98 182	99.84 108	97.09 277	93.75 137	96.58 154	99.26 132	85.07 221	98.78 168	97.77 118	97.04 165	99.54 144

DWT-MVSNet_test		97.31 97	97.19 92	97.66 150	98.24 158	94.67 191	98.86 260	98.20 172	93.60 141	98.09 122	98.89 161	97.51 7	98.78 168	94.04 185	97.28 159	99.55 140

TR-MVS		94.54 177	93.56 188	97.49 156	97.96 172	94.34 196	98.71 271	97.51 236	90.30 237	94.51 188	98.69 174	75.56 294	98.77 170	92.82 210	95.99 182	99.35 168

diffmvs		97.00 107	96.64 109	98.09 134	97.64 195	96.17 146	99.81 117	97.19 264	94.67 94	98.95 86	99.28 126	86.43 208	98.76 171	98.37 91	97.42 156	99.33 170

Vis-MVSNet		95.72 148	95.15 155	97.45 157	97.62 196	94.28 197	99.28 216	98.24 164	94.27 113	96.84 148	98.94 158	79.39 267	98.76 171	93.25 202	98.49 132	99.30 173
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
tpmrst		96.27 139	95.98 127	97.13 168	97.96 172	93.15 219	96.34 329	98.17 174	92.07 193	98.71 98	95.12 294	93.91 93	98.73 173	94.91 162	96.62 171	99.50 151

PMMVS		96.76 117	96.76 106	96.76 178	98.28 154	92.10 243	99.91 72	97.98 192	94.12 116	99.53 47	99.39 121	86.93 204	98.73 173	96.95 138	97.73 148	99.45 156

lupinMVS		97.85 75	97.60 78	98.62 100	97.28 216	97.70 85	99.99 5	97.55 228	95.50 71	99.43 55	99.67 95	90.92 159	98.71 175	98.40 90	99.62 98	99.45 156

Effi-MVS+		96.30 136	95.69 141	98.16 129	97.85 180	96.26 139	97.41 313	97.21 263	90.37 234	98.65 101	98.58 182	86.61 207	98.70 176	97.11 132	97.37 158	99.52 147

baseline1		95.78 147	94.86 159	98.54 109	98.47 147	98.07 70	99.06 235	97.99 190	92.68 169	94.13 194	98.62 179	93.28 110	98.69 177	93.79 193	85.76 261	98.84 197

BH-w/o		95.71 150	95.38 148	96.68 181	98.49 146	92.28 239	99.84 108	97.50 237	92.12 192	92.06 214	98.79 171	84.69 223	98.67 178	95.29 156	99.66 96	99.09 188

baseline		96.43 130	95.98 127	97.76 147	97.34 210	95.17 179	99.51 182	97.17 267	93.92 129	96.90 147	99.28 126	85.37 218	98.64 179	97.50 123	96.86 170	99.46 154

baseline2		96.71 121	96.49 114	97.37 162	95.63 269	95.96 153	99.74 140	98.88 43	92.94 156	91.61 216	98.97 153	97.72 5	98.62 180	94.83 164	98.08 145	97.53 220

MDTV_nov1_ep13			95.69 141		97.90 175	94.15 198	95.98 334	98.44 108	93.12 153	97.98 125	95.74 263	95.10 49	98.58 181	90.02 249	96.92 168

jason		97.24 100	96.86 102	98.38 122	95.73 262	97.32 103	99.97 18	97.40 249	95.34 74	98.60 104	99.54 107	87.70 195	98.56 182	97.94 110	99.47 109	99.25 177
jason: jason.
EPP-MVSNet		96.69 122	96.60 110	96.96 172	97.74 188	93.05 222	99.37 203	98.56 77	88.75 260	95.83 172	99.01 146	96.01 28	98.56 182	96.92 139	97.20 162	99.25 177

BH-untuned		95.18 159	94.83 160	96.22 196	98.36 150	91.22 265	99.80 122	97.32 256	90.91 225	91.08 221	98.67 175	83.51 231	98.54 184	94.23 183	99.61 101	98.92 192

PAPM		98.60 33	98.42 31	99.14 63	96.05 250	98.96 20	99.90 76	99.35 23	96.68 37	98.35 114	99.66 97	96.45 25	98.51 185	99.45 37	99.89 74	99.96 70

OPM-MVS		93.21 206	92.80 203	94.44 248	93.12 308	90.85 270	99.77 129	97.61 222	96.19 51	91.56 217	98.65 176	75.16 299	98.47 186	93.78 194	89.39 228	93.99 283

ACMP	92.05 9	92.74 217	92.42 214	93.73 271	95.91 255	88.72 300	99.81 117	97.53 232	94.13 115	87.00 290	98.23 195	74.07 305	98.47 186	96.22 146	88.86 234	93.99 283
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CLD-MVS		94.06 189	93.90 179	94.55 241	96.02 251	90.69 271	99.98 10	97.72 212	96.62 39	91.05 222	98.85 170	77.21 279	98.47 186	98.11 100	89.51 227	94.48 235
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMM	91.95 10	92.88 214	92.52 212	93.98 266	95.75 261	89.08 298	99.77 129	97.52 234	93.00 155	89.95 234	97.99 203	76.17 291	98.46 189	93.63 199	88.87 233	94.39 244
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dp		95.05 162	94.43 167	96.91 173	97.99 171	92.73 229	96.29 330	97.98 192	89.70 245	95.93 169	94.67 309	93.83 97	98.45 190	86.91 285	96.53 173	99.54 144

CS-MVS-test		97.85 75	97.70 73	98.30 124	97.57 198	96.72 121	100.00 1	97.11 274	95.06 79	99.76 24	99.45 114	92.12 140	98.44 191	98.97 57	99.28 116	99.75 106

ACMH+	89.98 16	90.35 267	89.54 264	92.78 293	95.99 252	86.12 319	98.81 264	97.18 266	89.38 246	83.14 319	97.76 207	68.42 326	98.43 192	89.11 256	86.05 260	93.78 299

ITE_SJBPF				92.38 295	95.69 267	85.14 325		95.71 332	92.81 160	89.33 252	98.11 197	70.23 319	98.42 193	85.91 290	88.16 245	93.59 307

Fast-Effi-MVS+		95.02 163	94.19 171	97.52 155	97.88 176	94.55 192	99.97 18	97.08 278	88.85 259	94.47 189	97.96 204	84.59 224	98.41 194	89.84 251	97.10 163	99.59 131

ACMH	89.72 17	90.64 260	89.63 261	93.66 277	95.64 268	88.64 303	98.55 279	97.45 240	89.03 251	81.62 326	97.61 209	69.75 320	98.41 194	89.37 253	87.62 251	93.92 289
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		92.96 212	92.71 205	93.71 273	95.43 271	88.67 301	99.75 137	97.62 219	92.81 160	90.05 230	98.49 186	75.24 297	98.40 196	95.84 152	89.12 229	94.07 275

LGP-MVS_train				93.71 273	95.43 271	88.67 301		97.62 219	92.81 160	90.05 230	98.49 186	75.24 297	98.40 196	95.84 152	89.12 229	94.07 275

XVG-ACMP-BASELINE		91.22 249	90.75 240	92.63 294	93.73 297	85.61 321	98.52 283	97.44 242	92.77 164	89.90 236	96.85 234	66.64 332	98.39 198	92.29 214	88.61 238	93.89 291

HQP4-MVS										93.37 201			98.39 198			94.53 231

HQP-MVS		94.61 175	94.50 166	94.92 227	95.78 256	91.85 249	99.87 90	97.89 201	96.82 30	93.37 201	98.65 176	80.65 257	98.39 198	97.92 111	89.60 222	94.53 231

TDRefinement		84.76 309	82.56 316	91.38 306	74.58 360	84.80 328	97.36 314	94.56 350	84.73 315	80.21 333	96.12 257	63.56 342	98.39 198	87.92 269	63.97 350	90.95 341

EPMVS		96.53 127	96.01 124	98.09 134	98.43 148	96.12 149	96.36 328	99.43 19	93.53 142	97.64 132	95.04 296	94.41 70	98.38 202	91.13 227	98.11 141	99.75 106

HQP_MVS		94.49 180	94.36 168	94.87 228	95.71 265	91.74 253	99.84 108	97.87 203	96.38 44	93.01 205	98.59 180	80.47 261	98.37 203	97.79 116	89.55 225	94.52 233

plane_prior5								97.87 203					98.37 203	97.79 116	89.55 225	94.52 233

TinyColmap		87.87 297	86.51 298	91.94 301	95.05 277	85.57 322	97.65 311	94.08 352	84.40 317	81.82 325	96.85 234	62.14 345	98.33 205	80.25 321	86.37 259	91.91 334

CMPMVS	61.59 21	84.75 310	85.14 304	83.57 335	90.32 340	62.54 359	96.98 322	97.59 226	74.33 350	69.95 353	96.66 240	64.17 340	98.32 206	87.88 270	88.41 243	89.84 348
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
USDC		90.00 277	88.96 276	93.10 288	94.81 280	88.16 309	98.71 271	95.54 337	93.66 139	83.75 317	97.20 219	65.58 335	98.31 207	83.96 302	87.49 253	92.85 322

TESTMET0.1,1		96.74 119	96.26 119	98.16 129	97.36 209	96.48 130	99.96 25	98.29 157	91.93 197	95.77 173	98.07 199	95.54 40	98.29 208	90.55 240	98.89 124	99.70 112

CostFormer		96.10 140	95.88 137	96.78 177	97.03 223	92.55 235	97.08 320	97.83 208	90.04 241	98.72 97	94.89 303	95.01 56	98.29 208	96.54 143	95.77 188	99.50 151

AUN-MVS		93.28 205	92.60 207	95.34 213	98.29 152	90.09 285	99.31 210	98.56 77	91.80 203	96.35 163	98.00 201	89.38 178	98.28 210	92.46 212	69.22 344	97.64 217

LTVRE_ROB	88.28 18	90.29 270	89.05 275	94.02 262	95.08 276	90.15 284	97.19 317	97.43 243	84.91 314	83.99 315	97.06 225	74.00 306	98.28 210	84.08 299	87.71 249	93.62 306
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
test-LLR		96.47 128	96.04 123	97.78 144	97.02 224	95.44 168	99.96 25	98.21 168	94.07 119	95.55 175	96.38 247	93.90 94	98.27 212	90.42 243	98.83 126	99.64 124

test-mter		96.39 132	95.93 134	97.78 144	97.02 224	95.44 168	99.96 25	98.21 168	91.81 202	95.55 175	96.38 247	95.17 47	98.27 212	90.42 243	98.83 126	99.64 124

hse-mvs2		94.38 182	94.08 175	95.31 215	98.27 156	90.02 286	99.29 215	98.56 77	95.90 56	98.77 93	98.00 201	90.89 161	98.26 214	97.80 113	69.20 345	97.64 217

CS-MVS		97.74 83	97.61 77	98.15 132	97.52 204	96.69 123	100.00 1	97.11 274	94.93 82	99.73 27	99.41 118	91.68 147	98.25 215	98.84 68	99.24 119	99.52 147

HyFIR lowres test		96.66 124	96.43 116	97.36 163	99.05 113	93.91 205	99.70 150	99.80 3	90.54 231	96.26 164	98.08 198	92.15 138	98.23 216	96.84 141	95.46 194	99.93 81

CHOSEN 280x420		99.01 12	99.03 8	98.95 83	99.38 104	98.87 27	98.46 284	99.42 20	97.03 27	99.02 82	99.09 140	99.35 1	98.21 217	99.73 27	99.78 88	99.77 104

ADS-MVSNet		94.79 167	94.02 176	97.11 170	97.87 178	93.79 206	94.24 339	98.16 177	90.07 239	96.43 159	94.48 314	90.29 168	98.19 218	87.44 273	97.23 160	99.36 166

DROMVSNet		97.45 90	97.30 90	97.90 142	97.43 206	95.90 154	99.99 5	97.08 278	94.64 95	99.64 36	99.33 125	89.56 175	98.15 219	98.76 75	99.25 117	99.65 123

test_post											63.35 364	94.43 69	98.13 220

LF4IMVS		89.25 288	88.85 277	90.45 314	92.81 317	81.19 344	98.12 300	94.79 347	91.44 213	86.29 302	97.11 221	65.30 338	98.11 221	88.53 262	85.25 266	92.07 330

IS-MVSNet		96.29 137	95.90 136	97.45 157	98.13 166	94.80 188	99.08 230	97.61 222	92.02 196	95.54 177	98.96 155	90.64 164	98.08 222	93.73 196	97.41 157	99.47 153

DeepMVS_CX				82.92 337	95.98 254	58.66 361		96.01 327	92.72 165	78.34 339	95.51 275	58.29 351	98.08 222	82.57 309	85.29 265	92.03 332

PatchmatchNet		95.94 144	95.45 145	97.39 161	97.83 181	94.41 195	96.05 333	98.40 132	92.86 157	97.09 143	95.28 291	94.21 86	98.07 224	89.26 255	98.11 141	99.70 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
GeoE		94.36 185	93.48 190	96.99 171	97.29 215	93.54 212	99.96 25	96.72 311	88.35 269	93.43 200	98.94 158	82.05 239	98.05 225	88.12 268	96.48 175	99.37 165

MS-PatchMatch		90.65 259	90.30 250	91.71 304	94.22 289	85.50 323	98.24 295	97.70 213	88.67 262	86.42 299	96.37 249	67.82 328	98.03 226	83.62 304	99.62 98	91.60 335

Patchmatch-test		92.65 221	91.50 231	96.10 199	96.85 233	90.49 277	91.50 352	97.19 264	82.76 327	90.23 229	95.59 270	95.02 54	98.00 227	77.41 332	96.98 167	99.82 97

tpm2		95.47 155	95.18 154	96.35 194	96.91 228	91.70 257	96.96 323	97.93 197	88.04 272	98.44 109	95.40 280	93.32 107	97.97 228	94.00 186	95.61 192	99.38 163

JIA-IIPM		91.76 242	90.70 242	94.94 226	96.11 248	87.51 313	93.16 346	98.13 182	75.79 346	97.58 133	77.68 357	92.84 121	97.97 228	88.47 263	96.54 172	99.33 170

VPA-MVSNet		92.70 218	91.55 230	96.16 197	95.09 275	96.20 144	98.88 256	99.00 33	91.02 224	91.82 215	95.29 290	76.05 293	97.96 230	95.62 154	81.19 294	94.30 251

patchmatchnet-post											91.70 338	95.12 48	97.95 231

SCA		94.69 171	93.81 182	97.33 165	97.10 219	94.44 193	98.86 260	98.32 151	93.30 148	96.17 166	95.59 270	76.48 287	97.95 231	91.06 229	97.43 154	99.59 131

GG-mvs-BLEND				98.54 109	98.21 160	98.01 73	93.87 343	98.52 90		97.92 126	97.92 205	99.02 2	97.94 233	98.17 96	99.58 103	99.67 117

Effi-MVS+-dtu		94.53 179	95.30 150	92.22 297	97.77 185	82.54 335	99.59 169	97.06 281	94.92 83	95.29 180	95.37 284	85.81 212	97.89 234	94.80 165	97.07 164	96.23 227

XXY-MVS		91.82 235	90.46 245	95.88 203	93.91 294	95.40 171	98.87 259	97.69 214	88.63 264	87.87 278	97.08 223	74.38 304	97.89 234	91.66 221	84.07 277	94.35 249

D2MVS		92.76 216	92.59 210	93.27 283	95.13 274	89.54 294	99.69 151	99.38 21	92.26 188	87.59 281	94.61 311	85.05 222	97.79 236	91.59 222	88.01 246	92.47 327

gg-mvs-nofinetune		93.51 201	91.86 225	98.47 114	97.72 192	97.96 77	92.62 347	98.51 97	74.70 349	97.33 138	69.59 360	98.91 3	97.79 236	97.77 118	99.56 104	99.67 117

test_post1							95.78 337				59.23 367	93.20 114	97.74 238	91.06 229

nrg030		93.51 201	92.53 211	96.45 188	94.36 286	97.20 106	99.81 117	97.16 269	91.60 207	89.86 237	97.46 211	86.37 209	97.68 239	95.88 151	80.31 306	94.46 236

Fast-Effi-MVS+-dtu		93.72 198	93.86 181	93.29 282	97.06 221	86.16 318	99.80 122	96.83 303	92.66 170	92.58 212	97.83 206	81.39 247	97.67 240	89.75 252	96.87 169	96.05 229

GA-MVS		93.83 191	92.84 202	96.80 176	95.73 262	93.57 210	99.88 87	97.24 262	92.57 178	92.92 207	96.66 240	78.73 273	97.67 240	87.75 271	94.06 209	99.17 181

UniMVSNet_ETH3D		90.06 276	88.58 282	94.49 245	94.67 283	88.09 310	97.81 309	97.57 227	83.91 320	88.44 268	97.41 213	57.44 352	97.62 242	91.41 223	88.59 240	97.77 215

Anonymous20231211		89.86 278	88.44 284	94.13 258	98.93 123	90.68 272	98.54 281	98.26 162	76.28 343	86.73 292	95.54 272	70.60 318	97.56 243	90.82 237	80.27 307	94.15 268

VPNet		91.81 236	90.46 245	95.85 205	94.74 281	95.54 167	98.98 245	98.59 72	92.14 191	90.77 225	97.44 212	68.73 324	97.54 244	94.89 163	77.89 320	94.46 236

MVS-HIRNet		86.22 301	83.19 313	95.31 215	96.71 242	90.29 281	92.12 349	97.33 255	62.85 355	86.82 291	70.37 359	69.37 321	97.49 245	75.12 339	97.99 147	98.15 208

test_part1		92.15 231	90.72 241	96.44 190	98.87 131	97.46 98	98.99 244	98.26 162	85.89 298	86.34 301	96.34 250	81.71 242	97.48 246	91.06 229	78.99 312	94.37 245

Vis-MVSNet (Re-imp)		96.32 134	95.98 127	97.35 164	97.93 174	94.82 187	99.47 189	98.15 179	91.83 200	95.09 182	99.11 139	91.37 150	97.47 247	93.47 200	97.43 154	99.74 108

RRT_test8_iter05		94.58 176	94.11 173	95.98 201	97.88 176	96.11 150	99.89 84	97.45 240	91.66 206	88.28 273	96.71 238	96.53 24	97.40 248	94.73 170	83.85 280	94.45 241

tfpnnormal		89.29 286	87.61 293	94.34 252	94.35 287	94.13 199	98.95 249	98.94 36	83.94 318	84.47 313	95.51 275	74.84 300	97.39 249	77.05 335	80.41 304	91.48 337

jajsoiax		91.92 234	91.18 236	94.15 256	91.35 332	90.95 268	99.00 243	97.42 245	92.61 173	87.38 286	97.08 223	72.46 310	97.36 250	94.53 175	88.77 235	94.13 272

EPNet_dtu		95.71 150	95.39 147	96.66 182	98.92 125	93.41 216	99.57 172	98.90 41	96.19 51	97.52 134	98.56 184	92.65 126	97.36 250	77.89 330	98.33 136	99.20 180
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
cl-mvsnet2		93.77 195	93.25 199	95.33 214	99.49 99	94.43 194	99.61 167	98.09 183	90.38 233	89.16 258	95.61 268	90.56 165	97.34 252	91.93 217	84.45 272	94.21 259

V42		91.28 247	90.12 256	94.74 232	93.42 303	93.46 214	99.68 153	97.02 284	87.36 279	89.85 239	95.05 295	81.31 249	97.34 252	87.34 276	80.07 308	93.40 310

mvs_tets		91.81 236	91.08 237	94.00 264	91.63 330	90.58 275	98.67 275	97.43 243	92.43 184	87.37 287	97.05 226	71.76 312	97.32 254	94.75 168	88.68 237	94.11 273

EI-MVSNet		93.73 197	93.40 195	94.74 232	96.80 236	92.69 230	99.06 235	97.67 215	88.96 255	91.39 218	99.02 144	88.75 188	97.30 255	91.07 228	87.85 247	94.22 257

MVSTER		95.53 153	95.22 152	96.45 188	98.56 141	97.72 82	99.91 72	97.67 215	92.38 185	91.39 218	97.14 220	97.24 14	97.30 255	94.80 165	87.85 247	94.34 250

TAMVS		95.85 145	95.58 143	96.65 183	97.07 220	93.50 213	99.17 224	97.82 209	91.39 217	95.02 183	98.01 200	92.20 136	97.30 255	93.75 195	95.83 187	99.14 185

PS-MVSNAJss		93.64 200	93.31 197	94.61 237	92.11 323	92.19 241	99.12 226	97.38 250	92.51 181	88.45 267	96.99 229	91.20 152	97.29 258	94.36 178	87.71 249	94.36 246

OurMVSNet-221017-0		89.81 279	89.48 268	90.83 310	91.64 329	81.21 343	98.17 299	95.38 340	91.48 211	85.65 308	97.31 216	72.66 309	97.29 258	88.15 266	84.83 269	93.97 285

MVP-Stereo		90.93 252	90.45 247	92.37 296	91.25 334	88.76 299	98.05 304	96.17 324	87.27 281	84.04 314	95.30 287	78.46 276	97.27 260	83.78 303	99.70 94	91.09 338
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
RRT_MVS		95.23 158	94.77 162	96.61 184	98.28 154	98.32 63	99.81 117	97.41 247	92.59 175	91.28 220	97.76 207	95.02 54	97.23 261	93.65 198	87.14 254	94.28 253

v8		90.54 263	89.17 271	94.66 235	93.43 302	93.40 217	99.20 221	96.94 295	85.76 301	87.56 282	94.51 312	81.96 241	97.19 262	84.94 296	78.25 317	93.38 312

mvs_anonymous		95.65 152	95.03 157	97.53 154	98.19 161	95.74 161	99.33 207	97.49 238	90.87 226	90.47 228	97.10 222	88.23 192	97.16 263	95.92 150	97.66 151	99.68 115

v2v482		91.30 245	90.07 257	95.01 223	93.13 306	93.79 206	99.77 129	97.02 284	88.05 271	89.25 253	95.37 284	80.73 255	97.15 264	87.28 277	80.04 309	94.09 274

UniMVSNet (Re)		93.07 210	92.13 217	95.88 203	94.84 279	96.24 143	99.88 87	98.98 34	92.49 183	89.25 253	95.40 280	87.09 202	97.14 265	93.13 207	78.16 318	94.26 254

v7n		89.65 282	88.29 287	93.72 272	92.22 322	90.56 276	99.07 234	97.10 276	85.42 309	86.73 292	94.72 305	80.06 263	97.13 266	81.14 317	78.12 319	93.49 308

CDS-MVSNet		96.34 133	96.07 122	97.13 168	97.37 208	94.96 183	99.53 179	97.91 200	91.55 209	95.37 179	98.32 194	95.05 53	97.13 266	93.80 192	95.75 190	99.30 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EG-PatchMatch MVS		85.35 307	83.81 309	89.99 318	90.39 339	81.89 340	98.21 298	96.09 326	81.78 331	74.73 348	93.72 323	51.56 357	97.12 268	79.16 326	88.61 238	90.96 340

v144192		90.79 257	89.52 265	94.59 238	93.11 309	92.77 225	99.56 174	96.99 287	86.38 293	89.82 240	94.95 302	80.50 260	97.10 269	83.98 301	80.41 304	93.90 290

FIs		94.10 188	93.43 191	96.11 198	94.70 282	96.82 119	99.58 170	98.93 40	92.54 179	89.34 251	97.31 216	87.62 196	97.10 269	94.22 184	86.58 257	94.40 243

v1192		90.62 262	89.25 270	94.72 234	93.13 306	93.07 220	99.50 184	97.02 284	86.33 294	89.56 247	95.01 297	79.22 268	97.09 271	82.34 311	81.16 295	94.01 280

miper_enhance_ethall		94.36 185	93.98 177	95.49 208	98.68 140	95.24 176	99.73 145	97.29 258	93.28 149	89.86 237	95.97 259	94.37 75	97.05 272	92.20 215	84.45 272	94.19 260

v1144		91.09 250	89.83 258	94.87 228	93.25 305	93.69 209	99.62 166	96.98 289	86.83 289	89.64 245	94.99 300	80.94 252	97.05 272	85.08 295	81.16 295	93.87 293

v148		90.70 258	89.63 261	93.92 267	92.97 312	90.97 267	99.75 137	96.89 299	87.51 276	88.27 274	95.01 297	81.67 243	97.04 274	87.40 275	77.17 328	93.75 300

pm-mvs1		89.36 285	87.81 292	94.01 263	93.40 304	91.93 247	98.62 278	96.48 319	86.25 295	83.86 316	96.14 255	73.68 307	97.04 274	86.16 288	75.73 335	93.04 319

v1921920		90.46 264	89.12 272	94.50 244	92.96 313	92.46 236	99.49 186	96.98 289	86.10 296	89.61 246	95.30 287	78.55 275	97.03 276	82.17 312	80.89 302	94.01 280

v1240		90.20 272	88.79 279	94.44 248	93.05 311	92.27 240	99.38 201	96.92 297	85.89 298	89.36 250	94.87 304	77.89 278	97.03 276	80.66 319	81.08 298	94.01 280

v10		90.25 271	88.82 278	94.57 240	93.53 300	93.43 215	99.08 230	96.87 301	85.00 311	87.34 288	94.51 312	80.93 253	97.02 278	82.85 308	79.23 311	93.26 314

lessismore_v0				90.53 311	90.58 338	80.90 346		95.80 330		77.01 341	95.84 260	66.15 334	96.95 279	83.03 307	75.05 336	93.74 303

OpenMVS_ROB	79.82 20	83.77 316	81.68 319	90.03 317	88.30 348	82.82 332	98.46 284	95.22 343	73.92 351	76.00 345	91.29 339	55.00 354	96.94 280	68.40 349	88.51 242	90.34 344

anonymousdsp		91.79 241	90.92 239	94.41 251	90.76 337	92.93 224	98.93 251	97.17 267	89.08 249	87.46 285	95.30 287	78.43 277	96.92 281	92.38 213	88.73 236	93.39 311

MVSFormer		96.94 109	96.60 110	97.95 138	97.28 216	97.70 85	99.55 176	97.27 260	91.17 218	99.43 55	99.54 107	90.92 159	96.89 282	94.67 172	99.62 98	99.25 177

test_djsdf		92.83 215	92.29 216	94.47 246	91.90 326	92.46 236	99.55 176	97.27 260	91.17 218	89.96 233	96.07 258	81.10 250	96.89 282	94.67 172	88.91 231	94.05 277

pmmvs6		85.69 302	83.84 308	91.26 307	90.00 343	84.41 329	97.82 308	96.15 325	75.86 345	81.29 328	95.39 282	61.21 347	96.87 284	83.52 306	73.29 338	92.50 326

tpm		93.70 199	93.41 194	94.58 239	95.36 273	87.41 314	97.01 321	96.90 298	90.85 227	96.72 152	94.14 319	90.40 166	96.84 285	90.75 239	88.54 241	99.51 149

FC-MVSNet-test		93.81 193	93.15 200	95.80 206	94.30 288	96.20 144	99.42 195	98.89 42	92.33 187	89.03 260	97.27 218	87.39 199	96.83 286	93.20 203	86.48 258	94.36 246

pmmvs4		92.10 232	91.07 238	95.18 219	92.82 316	94.96 183	99.48 188	96.83 303	87.45 278	88.66 266	96.56 245	83.78 230	96.83 286	89.29 254	84.77 270	93.75 300

WR-MVS		92.31 227	91.25 235	95.48 211	94.45 285	95.29 173	99.60 168	98.68 56	90.10 238	88.07 276	96.89 231	80.68 256	96.80 288	93.14 206	79.67 310	94.36 246

miper_ehance_all_eth		93.16 207	92.60 207	94.82 231	97.57 198	93.56 211	99.50 184	97.07 280	88.75 260	88.85 262	95.52 274	90.97 158	96.74 289	90.77 238	84.45 272	94.17 261

UniMVSNet_NR-MVSNet		92.95 213	92.11 218	95.49 208	94.61 284	95.28 174	99.83 114	99.08 30	91.49 210	89.21 255	96.86 233	87.14 201	96.73 290	93.20 203	77.52 323	94.46 236

DU-MVS		92.46 224	91.45 233	95.49 208	94.05 291	95.28 174	99.81 117	98.74 52	92.25 189	89.21 255	96.64 242	81.66 244	96.73 290	93.20 203	77.52 323	94.46 236

bset_n11_16_dypcd		93.05 211	92.30 215	95.31 215	90.23 341	95.05 181	99.44 194	97.28 259	92.51 181	90.65 226	96.68 239	85.30 219	96.71 292	94.49 176	84.14 275	94.16 266

eth_miper_zixun_eth		92.41 225	91.93 222	93.84 270	97.28 216	90.68 272	98.83 262	96.97 291	88.57 265	89.19 257	95.73 265	89.24 183	96.69 293	89.97 250	81.55 291	94.15 268

SixPastTwentyTwo		88.73 290	88.01 291	90.88 308	91.85 327	82.24 337	98.22 297	95.18 345	88.97 254	82.26 322	96.89 231	71.75 313	96.67 294	84.00 300	82.98 282	93.72 304

cl-mvsnet____		92.31 227	91.58 228	94.52 242	97.33 212	92.77 225	99.57 172	96.78 308	86.97 287	87.56 282	95.51 275	89.43 177	96.62 295	88.60 259	82.44 285	94.16 266

WR-MVS_H		91.30 245	90.35 248	94.15 256	94.17 290	92.62 234	99.17 224	98.94 36	88.87 258	86.48 298	94.46 316	84.36 226	96.61 296	88.19 265	78.51 316	93.21 316

NR-MVSNet		91.56 244	90.22 252	95.60 207	94.05 291	95.76 160	98.25 294	98.70 54	91.16 220	80.78 331	96.64 242	83.23 235	96.57 297	91.41 223	77.73 322	94.46 236

Baseline_NR-MVSNet		90.33 268	89.51 266	92.81 292	92.84 314	89.95 288	99.77 129	93.94 354	84.69 316	89.04 259	95.66 267	81.66 244	96.52 298	90.99 232	76.98 329	91.97 333

cl-mvsnet1		92.32 226	91.60 227	94.47 246	97.31 213	92.74 227	99.58 170	96.75 309	86.99 286	87.64 280	95.54 272	89.55 176	96.50 299	88.58 260	82.44 285	94.17 261

pmmvs5		90.17 274	89.09 273	93.40 280	92.10 324	89.77 291	99.74 140	95.58 336	85.88 300	87.24 289	95.74 263	73.41 308	96.48 300	88.54 261	83.56 281	93.95 286

cl_fuxian		92.53 222	91.87 224	94.52 242	97.40 207	92.99 223	99.40 196	96.93 296	87.86 273	88.69 265	95.44 278	89.95 171	96.44 301	90.45 242	80.69 303	94.14 271

TransMVSNet (Re)		87.25 298	85.28 303	93.16 285	93.56 299	91.03 266	98.54 281	94.05 353	83.69 322	81.09 329	96.16 254	75.32 296	96.40 302	76.69 336	68.41 346	92.06 331

CP-MVSNet		91.23 248	90.22 252	94.26 253	93.96 293	92.39 238	99.09 228	98.57 75	88.95 256	86.42 299	96.57 244	79.19 269	96.37 303	90.29 246	78.95 313	94.02 278

ambc				83.23 336	77.17 359	62.61 358	87.38 357	94.55 351		76.72 343	86.65 351	30.16 362	96.36 304	84.85 297	69.86 340	90.73 342

IterMVS-LS		92.69 219	92.11 218	94.43 250	96.80 236	92.74 227	99.45 192	96.89 299	88.98 253	89.65 244	95.38 283	88.77 187	96.34 305	90.98 233	82.04 288	94.22 257
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PS-CasMVS		90.63 261	89.51 266	93.99 265	93.83 295	91.70 257	98.98 245	98.52 90	88.48 266	86.15 304	96.53 246	75.46 295	96.31 306	88.83 258	78.86 315	93.95 286

MVS_0304		89.28 287	88.31 286	92.21 298	97.05 222	86.53 317	97.76 310	99.57 12	85.58 306	93.86 198	92.71 331	51.04 358	96.30 307	84.49 298	92.72 219	93.79 298

FMVSNet3		92.69 219	91.58 228	95.99 200	98.29 152	97.42 101	99.26 218	97.62 219	89.80 244	89.68 241	95.32 286	81.62 246	96.27 308	87.01 282	85.65 262	94.29 252

test_0402		85.58 303	83.94 307	90.50 312	93.81 296	85.04 326	98.55 279	95.20 344	76.01 344	79.72 335	95.13 293	64.15 341	96.26 309	66.04 354	86.88 256	90.21 346

FMVSNet2		91.02 251	89.56 263	95.41 212	97.53 200	95.74 161	98.98 245	97.41 247	87.05 283	88.43 270	95.00 299	71.34 314	96.24 310	85.12 294	85.21 267	94.25 256

TranMVSNet+NR-MVSNet		91.68 243	90.61 244	94.87 228	93.69 298	93.98 203	99.69 151	98.65 60	91.03 223	88.44 268	96.83 237	80.05 264	96.18 311	90.26 247	76.89 331	94.45 241

GBi-Net		90.88 254	89.82 259	94.08 259	97.53 200	91.97 244	98.43 286	96.95 292	87.05 283	89.68 241	94.72 305	71.34 314	96.11 312	87.01 282	85.65 262	94.17 261

test1		90.88 254	89.82 259	94.08 259	97.53 200	91.97 244	98.43 286	96.95 292	87.05 283	89.68 241	94.72 305	71.34 314	96.11 312	87.01 282	85.65 262	94.17 261

FMVSNet1		88.50 291	86.64 297	94.08 259	95.62 270	91.97 244	98.43 286	96.95 292	83.00 324	86.08 305	94.72 305	59.09 350	96.11 312	81.82 315	84.07 277	94.17 261

our_test_3		90.39 265	89.48 268	93.12 286	92.40 320	89.57 293	99.33 207	96.35 321	87.84 274	85.30 309	94.99 300	84.14 228	96.09 315	80.38 320	84.56 271	93.71 305

PatchT		90.38 266	88.75 280	95.25 218	95.99 252	90.16 283	91.22 354	97.54 230	76.80 342	97.26 139	86.01 352	91.88 143	96.07 316	66.16 353	95.91 185	99.51 149

CR-MVSNet		93.45 204	92.62 206	95.94 202	96.29 245	92.66 231	92.01 350	96.23 322	92.62 172	96.94 145	93.31 327	91.04 156	96.03 317	79.23 323	95.96 183	99.13 186

Patchmtry		89.70 281	88.49 283	93.33 281	96.24 247	89.94 290	91.37 353	96.23 322	78.22 340	87.69 279	93.31 327	91.04 156	96.03 317	80.18 322	82.10 287	94.02 278

ppachtmachnet_test		89.58 283	88.35 285	93.25 284	92.40 320	90.44 279	99.33 207	96.73 310	85.49 307	85.90 307	95.77 262	81.09 251	96.00 319	76.00 338	82.49 284	93.30 313

PEN-MVS		90.19 273	89.06 274	93.57 278	93.06 310	90.90 269	99.06 235	98.47 103	88.11 270	85.91 306	96.30 251	76.67 284	95.94 320	87.07 279	76.91 330	93.89 291

miper_lstm_enhance		91.81 236	91.39 234	93.06 289	97.34 210	89.18 297	99.38 201	96.79 307	86.70 290	87.47 284	95.22 292	90.00 170	95.86 321	88.26 264	81.37 293	94.15 268

N_pmnet		80.06 323	80.78 321	77.89 338	91.94 325	45.28 367	98.80 265	56.82 370	78.10 341	80.08 334	93.33 325	77.03 280	95.76 322	68.14 350	82.81 283	92.64 323

LCM-MVSNet-Re		92.31 227	92.60 207	91.43 305	97.53 200	79.27 351	99.02 242	91.83 358	92.07 193	80.31 332	94.38 317	83.50 232	95.48 323	97.22 130	97.58 152	99.54 144

K. test v3		88.05 294	87.24 296	90.47 313	91.82 328	82.23 338	98.96 248	97.42 245	89.05 250	76.93 342	95.60 269	68.49 325	95.42 324	85.87 291	81.01 300	93.75 300

ADS-MVSNet2		93.80 194	93.88 180	93.55 279	97.87 178	85.94 320	94.24 339	96.84 302	90.07 239	96.43 159	94.48 314	90.29 168	95.37 325	87.44 273	97.23 160	99.36 166

ET-MVSNet_ETH3D		94.37 183	93.28 198	97.64 151	98.30 151	97.99 74	99.99 5	97.61 222	94.35 107	71.57 351	99.45 114	96.23 27	95.34 326	96.91 140	85.14 268	99.59 131

CVMVSNet		94.68 173	94.94 158	93.89 269	96.80 236	86.92 316	99.06 235	98.98 34	94.45 100	94.23 193	99.02 144	85.60 214	95.31 327	90.91 235	95.39 196	99.43 159

DTE-MVSNet		89.40 284	88.24 288	92.88 291	92.66 318	89.95 288	99.10 227	98.22 167	87.29 280	85.12 311	96.22 253	76.27 290	95.30 328	83.56 305	75.74 334	93.41 309

IterMVS		90.91 253	90.17 254	93.12 286	96.78 239	90.42 280	98.89 254	97.05 283	89.03 251	86.49 297	95.42 279	76.59 286	95.02 329	87.22 278	84.09 276	93.93 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		90.85 256	90.16 255	92.93 290	96.72 241	89.96 287	98.89 254	96.99 287	88.95 256	86.63 294	95.67 266	76.48 287	95.00 330	87.04 280	84.04 279	93.84 295

test0.0.03 1		93.86 190	93.61 183	94.64 236	95.02 278	92.18 242	99.93 64	98.58 73	94.07 119	87.96 277	98.50 185	93.90 94	94.96 331	81.33 316	93.17 216	96.78 222

UnsupCasMVSNet_bld		79.97 324	77.03 327	88.78 325	85.62 353	81.98 339	93.66 344	97.35 252	75.51 348	70.79 352	83.05 354	48.70 359	94.91 332	78.31 329	60.29 355	89.46 351

MIMVSNet		90.30 269	88.67 281	95.17 220	96.45 244	91.64 259	92.39 348	97.15 270	85.99 297	90.50 227	93.19 329	66.95 331	94.86 333	82.01 313	93.43 213	99.01 191

new_pmnet		84.49 313	82.92 315	89.21 321	90.03 342	82.60 334	96.89 324	95.62 335	80.59 334	75.77 347	89.17 344	65.04 339	94.79 334	72.12 343	81.02 299	90.23 345

testgi		89.01 289	88.04 290	91.90 302	93.49 301	84.89 327	99.73 145	95.66 334	93.89 132	85.14 310	98.17 196	59.68 349	94.66 335	77.73 331	88.88 232	96.16 228

KD-MVS_2432*1600		88.00 295	86.10 299	93.70 275	96.91 228	94.04 200	97.17 318	97.12 272	84.93 312	81.96 323	92.41 334	92.48 130	94.51 336	79.23 323	52.68 357	92.56 324

miper_refine_blended		88.00 295	86.10 299	93.70 275	96.91 228	94.04 200	97.17 318	97.12 272	84.93 312	81.96 323	92.41 334	92.48 130	94.51 336	79.23 323	52.68 357	92.56 324

Anonymous20240521		85.15 308	83.81 309	89.16 322	88.32 347	82.69 333	98.80 265	95.74 331	79.72 336	81.53 327	90.99 340	65.38 337	94.16 338	72.69 342	81.11 297	90.63 343

pmmvs-eth3d		84.03 315	81.97 318	90.20 315	84.15 355	87.09 315	98.10 302	94.73 349	83.05 323	74.10 349	87.77 348	65.56 336	94.01 339	81.08 318	69.24 343	89.49 350

UnsupCasMVSNet_eth		85.52 304	83.99 305	90.10 316	89.36 345	83.51 331	96.65 325	97.99 190	89.14 248	75.89 346	93.83 321	63.25 343	93.92 340	81.92 314	67.90 348	92.88 321

PM-MVS		80.47 321	78.88 325	85.26 333	83.79 356	72.22 354	95.89 336	91.08 359	85.71 304	76.56 344	88.30 346	36.64 361	93.90 341	82.39 310	69.57 342	89.66 349

MDA-MVSNet_test_wron		85.51 305	83.32 312	92.10 299	90.96 335	88.58 304	99.20 221	96.52 317	79.70 337	57.12 359	92.69 332	79.11 270	93.86 342	77.10 334	77.46 325	93.86 294

YYNet1		85.50 306	83.33 311	92.00 300	90.89 336	88.38 308	99.22 220	96.55 316	79.60 338	57.26 358	92.72 330	79.09 271	93.78 343	77.25 333	77.37 326	93.84 295

Patchmatch-RL test		86.90 299	85.98 301	89.67 319	84.45 354	75.59 352	89.71 355	92.43 356	86.89 288	77.83 340	90.94 341	94.22 83	93.63 344	87.75 271	69.61 341	99.79 100

MDA-MVSNet-bldmvs		84.09 314	81.52 320	91.81 303	91.32 333	88.00 312	98.67 275	95.92 329	80.22 335	55.60 360	93.32 326	68.29 327	93.60 345	73.76 340	76.61 332	93.82 297

Anonymous20231206		86.32 300	85.42 302	89.02 323	89.11 346	80.53 349	99.05 239	95.28 341	85.43 308	82.82 320	93.92 320	74.40 303	93.44 346	66.99 351	81.83 290	93.08 318

EU-MVSNet		90.14 275	90.34 249	89.54 320	92.55 319	81.06 345	98.69 273	98.04 188	91.41 216	86.59 295	96.84 236	80.83 254	93.31 347	86.20 287	81.91 289	94.26 254

DIV-MVS_2432*1600		83.59 317	82.06 317	88.20 329	86.93 350	80.70 347	97.21 316	96.38 320	82.87 325	82.49 321	88.97 345	67.63 329	92.32 348	73.75 341	62.30 353	91.58 336

test_method		80.79 320	79.70 323	84.08 334	92.83 315	67.06 357	99.51 182	95.42 338	54.34 357	81.07 330	93.53 324	44.48 360	92.22 349	78.90 327	77.23 327	92.94 320

DSMNet-mixed		88.28 293	88.24 288	88.42 328	89.64 344	75.38 353	98.06 303	89.86 361	85.59 305	88.20 275	92.14 337	76.15 292	91.95 350	78.46 328	96.05 181	97.92 211

CL-MVSNet_2432*1600		84.50 312	83.15 314	88.53 327	86.00 352	81.79 341	98.82 263	97.35 252	85.12 310	83.62 318	90.91 342	76.66 285	91.40 351	69.53 347	60.36 354	92.40 328

FMVSNet5		88.32 292	87.47 294	90.88 308	96.90 231	88.39 307	97.28 315	95.68 333	82.60 328	84.67 312	92.40 336	79.83 265	91.16 352	76.39 337	81.51 292	93.09 317

pmmvs3		80.27 322	77.77 326	87.76 330	80.32 358	82.43 336	98.23 296	91.97 357	72.74 352	78.75 337	87.97 347	57.30 353	90.99 353	70.31 345	62.37 352	89.87 347

new-patchmatchnet		81.19 319	79.34 324	86.76 332	82.86 357	80.36 350	97.92 306	95.27 342	82.09 330	72.02 350	86.87 350	62.81 344	90.74 354	71.10 344	63.08 351	89.19 352

MIMVSNet1		82.58 318	80.51 322	88.78 325	86.68 351	84.20 330	96.65 325	95.41 339	78.75 339	78.59 338	92.44 333	51.88 356	89.76 355	65.26 355	78.95 313	92.38 329

test20.03		84.72 311	83.99 305	86.91 331	88.19 349	80.62 348	98.88 256	95.94 328	88.36 268	78.87 336	94.62 310	68.75 323	89.11 356	66.52 352	75.82 333	91.00 339

Gipuma		66.95 328	65.00 329	72.79 341	91.52 331	67.96 356	66.16 362	95.15 346	47.89 359	58.54 357	67.99 361	29.74 363	87.54 357	50.20 360	77.83 321	62.87 360
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		67.77 326	64.73 330	76.87 339	62.95 366	56.25 363	89.37 356	93.74 355	44.53 360	61.99 355	80.74 355	20.42 368	86.53 358	69.37 348	59.50 356	87.84 353

PMMVS2		67.15 327	64.15 331	76.14 340	70.56 363	62.07 360	93.89 342	87.52 365	58.09 356	60.02 356	78.32 356	22.38 367	84.54 359	59.56 358	47.03 359	81.80 355

FPMVS		68.72 325	68.72 328	68.71 343	65.95 364	44.27 369	95.97 335	94.74 348	51.13 358	53.26 361	90.50 343	25.11 366	83.00 360	60.80 357	80.97 301	78.87 356

PMVS	49.05 23	53.75 331	51.34 335	60.97 346	40.80 370	34.68 370	74.82 361	89.62 363	37.55 362	28.67 368	72.12 358	7.09 372	81.63 361	43.17 363	68.21 347	66.59 359
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		65.23 329	62.94 332	72.13 342	44.90 369	50.03 365	81.05 359	89.42 364	38.45 361	48.51 363	99.90 17	54.09 355	78.70 362	91.84 220	18.26 364	87.64 354

MVE	53.74 22	51.54 333	47.86 337	62.60 345	59.56 367	50.93 364	79.41 360	77.69 367	35.69 364	36.27 366	61.76 365	5.79 374	69.63 363	37.97 364	36.61 360	67.24 358
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 330	52.24 333	67.66 344	49.27 368	56.82 362	83.94 358	82.02 366	70.47 353	33.28 367	64.54 362	17.23 370	69.16 364	45.59 362	23.85 363	77.02 357

E-PMN		52.30 332	52.18 334	52.67 347	71.51 361	45.40 366	93.62 345	76.60 368	36.01 363	43.50 364	64.13 363	27.11 365	67.31 365	31.06 365	26.06 361	45.30 364

EMVS		51.44 334	51.22 336	52.11 348	70.71 362	44.97 368	94.04 341	75.66 369	35.34 365	42.40 365	61.56 366	28.93 364	65.87 366	27.64 366	24.73 362	45.49 363

wuyk23d		20.37 338	20.84 341	18.99 351	65.34 365	27.73 371	50.43 363	7.67 373	9.50 368	8.01 369	6.34 369	6.13 373	26.24 367	23.40 367	10.69 366	2.99 365

test123		37.68 336	39.14 339	33.31 349	19.94 371	24.83 372	98.36 290	9.75 372	15.53 367	51.31 362	87.14 349	19.62 369	17.74 368	47.10 361	3.47 367	57.36 361

testmvs		40.60 335	44.45 338	29.05 350	19.49 372	14.11 373	99.68 153	18.47 371	20.74 366	64.59 354	98.48 189	10.95 371	17.09 369	56.66 359	11.01 365	55.94 362

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

cdsmvs_eth3d_5k		23.43 337	31.24 340	0.00 352	0.00 373	0.00 374	0.00 364	98.09 183	0.00 369	0.00 370	99.67 95	83.37 233	0.00 370	0.00 368	0.00 368	0.00 366

pcd_1.5k_mvsjas		7.60 340	10.13 343	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	0.00 370	91.20 152	0.00 370	0.00 368	0.00 368	0.00 366

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

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

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

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

ab-mvs-re		8.28 339	11.04 342	0.00 352	0.00 373	0.00 374	0.00 364	0.00 374	0.00 369	0.00 370	99.40 119	0.00 375	0.00 370	0.00 368	0.00 368	0.00 366

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

eth-test2					0.00 373

eth-test					0.00 373

RE-MVS-def			98.13 55		99.79 70	96.37 136	99.76 134	98.31 153	94.43 102	99.40 61	99.75 77	92.95 119		98.90 64	99.92 67	99.97 63

IU-MVS					99.93 26	99.31 7		98.41 131	97.71 8	99.84 8				100.00 1	100.00 1	100.00 1

save fliter					99.82 65	98.79 33	99.96 25	98.40 132	97.66 10

test0726					99.93 26	99.29 10	99.96 25	98.42 127	97.28 18	99.86 4	99.94 4	97.22 15

GSMVS																99.59 131

test_part2					99.89 45	99.25 13				99.49 51

sam_mvs1												94.72 64				99.59 131

sam_mvs												94.25 82

MTGPA								98.28 158

MTMP							99.87 90	96.49 318

test9_res														99.71 29	99.99 20	100.00 1

agg_prior2														99.48 36	100.00 1	100.00 1

test_prior4						98.05 71	99.94 58

test_prior2							99.95 43		95.78 60	99.73 27	99.76 72	96.00 29		99.78 20	100.00 1

新几何2							99.40 196

旧先验1					99.76 74	97.52 91		98.64 63			99.85 33	95.63 39			99.94 57	99.99 20

原ACMM2							99.90 76

test222					99.55 94	97.41 102	99.34 206	98.55 83	91.86 199	99.27 71	99.83 49	93.84 96			99.95 51	99.99 20

segment_acmp												96.68 22

testdata1							99.28 216		96.35 48

plane_prior7					95.71 265	91.59 261

plane_prior6					95.76 260	91.72 256						80.47 261

plane_prior4											98.59 180

plane_prior3						91.64 259			96.63 38	93.01 205

plane_prior2							99.84 108		96.38 44

plane_prior1					95.73 262

plane_prior						91.74 253	99.86 101		96.76 34						89.59 224

n2								0.00 374

nn								0.00 374

door-mid								89.69 362

test11								98.44 108

door								90.31 360

HQP5-MVS						91.85 249

HQP-NCC					95.78 256		99.87 90		96.82 30	93.37 201

ACMP_Plane					95.78 256		99.87 90		96.82 30	93.37 201

BP-MVS														97.92 111

HQP3-MVS								97.89 201							89.60 222

HQP2-MVS												80.65 257

NP-MVS					95.77 259	91.79 251					98.65 176

MDTV_nov1_ep13_2view						96.26 139	96.11 332		91.89 198	98.06 123		94.40 71		94.30 181		99.67 117

ACMMP++_ref															87.04 255

ACMMP++															88.23 244

Test By Simon												92.82 123

High-resolution multi-view benchmark