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.

EI-MVSNet-UG-set		99.58 3	99.57 1	99.64 64	99.78 36	99.14 100	99.60 90	99.45 150	99.01 13	99.90 1	99.83 37	98.98 19	99.93 57	99.59 2	99.95 6	99.86 5

EI-MVSNet-Vis-set		99.58 3	99.56 3	99.64 64	99.78 36	99.15 99	99.61 88	99.45 150	99.01 13	99.89 2	99.82 44	99.01 12	99.92 65	99.56 5	99.95 6	99.85 8

Regformer-4		99.59 2	99.54 4	99.73 47	99.76 44	99.41 73	99.58 99	99.49 105	99.02 10	99.88 3	99.80 65	99.00 18	99.94 42	99.45 15	99.92 12	99.84 12

SD-MVS		99.41 33	99.52 6	99.05 146	99.74 67	99.68 33	99.46 154	99.52 76	99.11 7	99.88 3	99.91 5	99.43 1	97.70 330	98.72 80	99.93 11	99.77 52

APDe-MVS		99.66 1	99.57 1	99.92 1	99.77 41	99.89 1	99.75 34	99.56 48	99.02 10	99.88 3	99.85 26	99.18 6	99.96 19	99.22 31	99.92 12	99.90 1

Regformer-3		99.57 6	99.53 5	99.68 52	99.76 44	99.29 84	99.58 99	99.44 158	99.01 13	99.87 6	99.80 65	98.97 20	99.91 74	99.44 16	99.92 12	99.83 23

Vis-MVSNet		99.12 69	98.97 73	99.56 76	99.78 36	99.10 103	99.68 54	99.66 25	98.49 56	99.86 7	99.87 19	94.77 186	99.84 119	99.19 33	99.41 110	99.74 61
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SMA-MVS		99.47 20	99.34 24	99.86 13	99.73 72	99.85 6	99.56 112	99.50 99	97.61 144	99.84 8	99.82 44	99.28 3	99.91 74	98.79 72	99.91 17	99.81 36

xiu_mvs_v1_base_debu		99.29 48	99.27 41	99.34 107	99.63 109	98.97 126	99.12 252	99.51 85	98.86 31	99.84 8	99.47 200	98.18 77	99.99 1	99.50 8	99.31 116	99.08 169

xiu_mvs_v1_base		99.29 48	99.27 41	99.34 107	99.63 109	98.97 126	99.12 252	99.51 85	98.86 31	99.84 8	99.47 200	98.18 77	99.99 1	99.50 8	99.31 116	99.08 169

xiu_mvs_v1_base_debi		99.29 48	99.27 41	99.34 107	99.63 109	98.97 126	99.12 252	99.51 85	98.86 31	99.84 8	99.47 200	98.18 77	99.99 1	99.50 8	99.31 116	99.08 169

Regformer-1		99.53 9	99.47 8	99.72 49	99.71 82	99.44 70	99.49 142	99.46 139	98.95 24	99.83 12	99.76 88	99.01 12	99.93 57	99.17 36	99.87 39	99.80 42

Regformer-2		99.54 7	99.47 8	99.75 40	99.71 82	99.52 61	99.49 142	99.49 105	98.94 26	99.83 12	99.76 88	99.01 12	99.94 42	99.15 38	99.87 39	99.80 42

DeepPCF-MVS	98.18 3	98.81 111	99.37 17	97.12 301	99.60 119	91.75 329	98.61 320	99.44 158	99.35 1	99.83 12	99.85 26	98.70 51	99.81 139	99.02 48	99.91 17	99.81 36

TSAR-MVS + GP.		99.36 39	99.36 19	99.36 106	99.67 93	98.61 185	99.07 263	99.33 214	99.00 17	99.82 15	99.81 54	99.06 9	99.84 119	99.09 42	99.42 109	99.65 91

abl_6		99.44 26	99.31 32	99.83 24	99.85 23	99.75 24	99.66 65	99.59 38	98.13 82	99.82 15	99.81 54	98.60 57	99.96 19	98.46 112	99.88 35	99.79 46

MVSFormer		99.17 60	99.12 55	99.29 118	99.51 132	98.94 134	99.88 1	99.46 139	97.55 150	99.80 17	99.65 131	97.39 95	99.28 252	99.03 46	99.85 53	99.65 91

lupinMVS		99.13 64	99.01 69	99.46 95	99.51 132	98.94 134	99.05 269	99.16 251	97.86 117	99.80 17	99.56 164	97.39 95	99.86 107	98.94 54	99.85 53	99.58 111

APD-MVS_3200maxsize		99.48 17	99.35 22	99.85 19	99.76 44	99.83 8	99.63 79	99.54 62	98.36 65	99.79 19	99.82 44	98.86 32	99.95 33	98.62 91	99.81 69	99.78 50

jason		99.13 64	99.03 65	99.45 96	99.46 144	98.87 142	99.12 252	99.26 240	98.03 101	99.79 19	99.65 131	97.02 105	99.85 113	99.02 48	99.90 25	99.65 91
jason: jason.
SteuartSystems-ACMMP		99.54 7	99.42 11	99.87 6	99.82 29	99.81 14	99.59 92	99.51 85	98.62 49	99.79 19	99.83 37	99.28 3	99.97 11	98.48 109	99.90 25	99.84 12
Skip Steuart: Steuart Systems R&D Blog.
DeepC-MVS_fast	98.69 1	99.49 13	99.39 15	99.77 37	99.63 109	99.59 49	99.36 195	99.46 139	99.07 9	99.79 19	99.82 44	98.85 33	99.92 65	98.68 85	99.87 39	99.82 32
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + MP.		99.58 3	99.50 7	99.81 29	99.91 1	99.66 37	99.63 79	99.39 180	98.91 29	99.78 23	99.85 26	99.36 2	99.94 42	98.84 66	99.88 35	99.82 32

test_part2					99.81 32	99.83 8				99.77 24

ESAPD		99.31 45	99.13 53	99.87 6	99.81 32	99.83 8	99.37 189	99.48 114	97.97 108	99.77 24	99.78 78	98.96 21	99.95 33	97.15 213	99.84 58	99.83 23

HSP-MVS		99.41 33	99.26 44	99.85 19	99.89 8	99.80 15	99.67 56	99.37 193	98.70 45	99.77 24	99.49 190	98.21 76	99.95 33	98.46 112	99.77 77	99.81 36

UA-Net		99.42 30	99.29 37	99.80 31	99.62 113	99.55 54	99.50 134	99.70 15	98.79 40	99.77 24	99.96 1	97.45 94	99.96 19	98.92 55	99.90 25	99.89 2

APD-MVS		99.27 51	99.08 58	99.84 23	99.75 56	99.79 19	99.50 134	99.50 99	97.16 184	99.77 24	99.82 44	98.78 39	99.94 42	97.56 184	99.86 49	99.80 42
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMMP_Plus		99.47 20	99.34 24	99.88 4	99.87 15	99.86 3	99.47 151	99.48 114	98.05 98	99.76 29	99.86 22	98.82 35	99.93 57	98.82 71	99.91 17	99.84 12

HPM-MVS_fast		99.51 12	99.40 14	99.85 19	99.91 1	99.79 19	99.76 27	99.56 48	97.72 135	99.76 29	99.75 93	99.13 7	99.92 65	99.07 44	99.92 12	99.85 8

VNet		99.11 73	98.90 82	99.73 47	99.52 130	99.56 52	99.41 175	99.39 180	99.01 13	99.74 31	99.78 78	95.56 144	99.92 65	99.52 7	98.18 184	99.72 72

xiu_mvs_v2_base		99.26 53	99.25 45	99.29 118	99.53 129	98.91 139	99.02 278	99.45 150	98.80 39	99.71 32	99.26 255	98.94 27	99.98 5	99.34 22	99.23 120	98.98 182

PS-MVSNAJ		99.32 43	99.32 27	99.30 115	99.57 124	98.94 134	98.97 291	99.46 139	98.92 28	99.71 32	99.24 257	99.01 12	99.98 5	99.35 18	99.66 98	98.97 183

PGM-MVS		99.45 23	99.31 32	99.86 13	99.87 15	99.78 23	99.58 99	99.65 30	97.84 121	99.71 32	99.80 65	99.12 8	99.97 11	98.33 122	99.87 39	99.83 23

114514_t		98.93 96	98.67 109	99.72 49	99.85 23	99.53 58	99.62 82	99.59 38	92.65 320	99.71 32	99.78 78	98.06 81	99.90 87	98.84 66	99.91 17	99.74 61

PVSNet_Blended_VisFu		99.36 39	99.28 39	99.61 68	99.86 20	99.07 106	99.47 151	99.93 2	97.66 142	99.71 32	99.86 22	97.73 89	99.96 19	99.47 13	99.82 68	99.79 46

tfpn1000		98.33 140	98.02 154	99.25 125	99.78 36	98.73 170	99.70 42	97.55 342	97.48 156	99.69 37	99.53 177	92.37 265	99.85 113	97.82 157	98.26 179	99.16 160

zzz-MVS		99.49 13	99.36 19	99.89 2	99.90 3	99.86 3	99.36 195	99.47 130	98.79 40	99.68 38	99.81 54	98.43 64	99.97 11	98.88 57	99.90 25	99.83 23

MTAPA		99.52 11	99.39 15	99.89 2	99.90 3	99.86 3	99.66 65	99.47 130	98.79 40	99.68 38	99.81 54	98.43 64	99.97 11	98.88 57	99.90 25	99.83 23

HFP-MVS		99.49 13	99.37 17	99.86 13	99.87 15	99.80 15	99.66 65	99.67 22	98.15 80	99.68 38	99.69 115	99.06 9	99.96 19	98.69 83	99.87 39	99.84 12

#test#		99.43 28	99.29 37	99.86 13	99.87 15	99.80 15	99.55 118	99.67 22	97.83 122	99.68 38	99.69 115	99.06 9	99.96 19	98.39 115	99.87 39	99.84 12

VDDNet		97.55 243	97.02 258	99.16 134	99.49 139	98.12 211	99.38 187	99.30 223	95.35 282	99.68 38	99.90 7	82.62 340	99.93 57	99.31 25	98.13 192	99.42 144

HPM-MVS		99.42 30	99.28 39	99.83 24	99.90 3	99.72 28	99.81 15	99.54 62	97.59 145	99.68 38	99.63 142	98.91 29	99.94 42	98.58 96	99.91 17	99.84 12
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
VDD-MVS		97.73 227	97.35 239	98.88 184	99.47 143	97.12 244	99.34 202	98.85 287	98.19 76	99.67 44	99.85 26	82.98 338	99.92 65	99.49 12	98.32 174	99.60 105

ACMMPR		99.49 13	99.36 19	99.86 13	99.87 15	99.79 19	99.66 65	99.67 22	98.15 80	99.67 44	99.69 115	98.95 26	99.96 19	98.69 83	99.87 39	99.84 12

PVSNet_BlendedMVS		98.86 102	98.80 96	99.03 147	99.76 44	98.79 165	99.28 216	99.91 3	97.42 163	99.67 44	99.37 227	97.53 92	99.88 102	98.98 51	97.29 237	98.42 295

PVSNet_Blended		99.08 79	98.97 73	99.42 103	99.76 44	98.79 165	98.78 309	99.91 3	96.74 217	99.67 44	99.49 190	97.53 92	99.88 102	98.98 51	99.85 53	99.60 105

sss		99.17 60	99.05 60	99.53 81	99.62 113	98.97 126	99.36 195	99.62 31	97.83 122	99.67 44	99.65 131	97.37 98	99.95 33	99.19 33	99.19 123	99.68 84

region2R		99.48 17	99.35 22	99.87 6	99.88 11	99.80 15	99.65 75	99.66 25	98.13 82	99.66 49	99.68 120	98.96 21	99.96 19	98.62 91	99.87 39	99.84 12

RPSCF		98.22 150	98.62 117	96.99 302	99.82 29	91.58 330	99.72 39	99.44 158	96.61 226	99.66 49	99.89 10	95.92 135	99.82 135	97.46 195	99.10 129	99.57 112

OMC-MVS		99.08 79	99.04 63	99.20 132	99.67 93	98.22 206	99.28 216	99.52 76	98.07 93	99.66 49	99.81 54	97.79 87	99.78 154	97.79 160	99.81 69	99.60 105

LFMVS		97.90 199	97.35 239	99.54 77	99.52 130	99.01 119	99.39 182	98.24 323	97.10 192	99.65 52	99.79 73	84.79 334	99.91 74	99.28 27	98.38 172	99.69 80

MVS_111021_LR		99.41 33	99.33 26	99.65 59	99.77 41	99.51 63	98.94 299	99.85 6	98.82 35	99.65 52	99.74 98	98.51 59	99.80 143	98.83 68	99.89 33	99.64 97

CPTT-MVS		99.11 73	98.90 82	99.74 45	99.80 34	99.46 68	99.59 92	99.49 105	97.03 203	99.63 54	99.69 115	97.27 100	99.96 19	97.82 157	99.84 58	99.81 36

ACMMP		99.45 23	99.32 27	99.82 26	99.89 8	99.67 35	99.62 82	99.69 18	98.12 84	99.63 54	99.84 35	98.73 49	99.96 19	98.55 104	99.83 64	99.81 36
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
DeepC-MVS	98.35 2	99.30 46	99.19 48	99.64 64	99.82 29	99.23 91	99.62 82	99.55 55	98.94 26	99.63 54	99.95 2	95.82 139	99.94 42	99.37 17	99.97 3	99.73 66
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CHOSEN 280x420		99.12 69	99.13 53	99.08 142	99.66 103	97.89 219	98.43 327	99.71 13	98.88 30	99.62 57	99.76 88	96.63 117	99.70 185	99.46 14	99.99 1	99.66 88

PHI-MVS		99.30 46	99.17 50	99.70 51	99.56 127	99.52 61	99.58 99	99.80 8	97.12 188	99.62 57	99.73 101	98.58 58	99.90 87	98.61 93	99.91 17	99.68 84

tfpn_ndepth		98.17 157	97.84 175	99.15 136	99.75 56	98.76 169	99.61 88	97.39 344	96.92 210	99.61 59	99.38 223	92.19 267	99.86 107	97.57 182	98.13 192	98.82 200

MG-MVS		99.13 64	99.02 68	99.45 96	99.57 124	98.63 180	99.07 263	99.34 206	98.99 18	99.61 59	99.82 44	97.98 83	99.87 104	97.00 222	99.80 71	99.85 8

MP-MVS-pluss		99.37 38	99.20 47	99.88 4	99.90 3	99.87 2	99.30 209	99.52 76	97.18 182	99.60 61	99.79 73	98.79 38	99.95 33	98.83 68	99.91 17	99.83 23
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CDPH-MVS		99.13 64	98.91 81	99.80 31	99.75 56	99.71 29	99.15 248	99.41 170	96.60 228	99.60 61	99.55 167	98.83 34	99.90 87	97.48 192	99.83 64	99.78 50

EPP-MVSNet		99.13 64	98.99 70	99.53 81	99.65 105	99.06 107	99.81 15	99.33 214	97.43 161	99.60 61	99.88 14	97.14 102	99.84 119	99.13 39	98.94 142	99.69 80

HyFIR lowres test		99.11 73	98.92 79	99.65 59	99.90 3	99.37 76	99.02 278	99.91 3	97.67 141	99.59 64	99.75 93	95.90 136	99.73 169	99.53 6	99.02 135	99.86 5

MVS_0304		99.06 81	98.86 89	99.66 55	99.51 132	99.36 77	99.22 236	99.51 85	98.95 24	99.58 65	99.65 131	93.74 228	99.98 5	99.66 1	99.95 6	99.64 97

MVS_Test		99.10 76	98.97 73	99.48 90	99.49 139	99.14 100	99.67 56	99.34 206	97.31 171	99.58 65	99.76 88	97.65 91	99.82 135	98.87 61	99.07 132	99.46 138

MDTV_nov1_ep13_2view						95.18 303	99.35 199		96.84 214	99.58 65		95.19 158		97.82 157		99.46 138

DELS-MVS		99.48 17	99.42 11	99.65 59	99.72 76	99.40 75	99.05 269	99.66 25	99.14 6	99.57 68	99.80 65	98.46 62	99.94 42	99.57 4	99.84 58	99.60 105
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
CR-MVSNet		98.17 157	97.93 162	98.87 188	99.18 202	98.49 195	99.22 236	99.33 214	96.96 206	99.56 69	99.38 223	94.33 205	99.00 291	94.83 284	98.58 161	99.14 161

RPMNet		96.61 269	95.85 277	98.87 188	99.18 202	98.49 195	99.22 236	99.08 259	88.72 336	99.56 69	97.38 332	94.08 216	99.00 291	86.87 336	98.58 161	99.14 161

IS-MVSNet		99.05 83	98.87 86	99.57 74	99.73 72	99.32 80	99.75 34	99.20 247	98.02 102	99.56 69	99.86 22	96.54 119	99.67 190	98.09 135	99.13 126	99.73 66

conf0.01		98.21 153	97.89 167	99.15 136	99.76 44	99.04 109	99.67 56	97.71 334	97.10 192	99.55 72	99.54 170	92.70 247	99.79 146	96.90 232	98.12 194	98.61 275

conf0.002		98.21 153	97.89 167	99.15 136	99.76 44	99.04 109	99.67 56	97.71 334	97.10 192	99.55 72	99.54 170	92.70 247	99.79 146	96.90 232	98.12 194	98.61 275

thresconf0.02		98.24 146	97.89 167	99.27 121	99.76 44	99.04 109	99.67 56	97.71 334	97.10 192	99.55 72	99.54 170	92.70 247	99.79 146	96.90 232	98.12 194	98.97 183

tfpn_n400		98.24 146	97.89 167	99.27 121	99.76 44	99.04 109	99.67 56	97.71 334	97.10 192	99.55 72	99.54 170	92.70 247	99.79 146	96.90 232	98.12 194	98.97 183

tfpnconf		98.24 146	97.89 167	99.27 121	99.76 44	99.04 109	99.67 56	97.71 334	97.10 192	99.55 72	99.54 170	92.70 247	99.79 146	96.90 232	98.12 194	98.97 183

tfpnview11		98.24 146	97.89 167	99.27 121	99.76 44	99.04 109	99.67 56	97.71 334	97.10 192	99.55 72	99.54 170	92.70 247	99.79 146	96.90 232	98.12 194	98.97 183

MVS_111021_HR		99.41 33	99.32 27	99.66 55	99.72 76	99.47 67	98.95 297	99.85 6	98.82 35	99.54 78	99.73 101	98.51 59	99.74 161	98.91 56	99.88 35	99.77 52

CP-MVS		99.45 23	99.32 27	99.85 19	99.83 28	99.75 24	99.69 45	99.52 76	98.07 93	99.53 79	99.63 142	98.93 28	99.97 11	98.74 76	99.91 17	99.83 23

WTY-MVS		99.06 81	98.88 85	99.61 68	99.62 113	99.16 96	99.37 189	99.56 48	98.04 99	99.53 79	99.62 147	96.84 109	99.94 42	98.85 65	98.49 168	99.72 72

MCST-MVS		99.43 28	99.30 34	99.82 26	99.79 35	99.74 27	99.29 213	99.40 177	98.79 40	99.52 81	99.62 147	98.91 29	99.90 87	98.64 88	99.75 80	99.82 32

PatchT		97.03 266	96.44 267	98.79 202	98.99 236	98.34 202	99.16 245	99.07 262	92.13 321	99.52 81	97.31 334	94.54 198	98.98 293	88.54 329	98.73 157	99.03 176

CANet		99.25 54	99.14 52	99.59 70	99.41 153	99.16 96	99.35 199	99.57 44	98.82 35	99.51 83	99.61 150	96.46 120	99.95 33	99.59 2	99.98 2	99.65 91

mPP-MVS		99.44 26	99.30 34	99.86 13	99.88 11	99.79 19	99.69 45	99.48 114	98.12 84	99.50 84	99.75 93	98.78 39	99.97 11	98.57 98	99.89 33	99.83 23

PatchMatch-RL		98.84 110	98.62 117	99.52 85	99.71 82	99.28 85	99.06 267	99.77 9	97.74 133	99.50 84	99.53 177	95.41 148	99.84 119	97.17 212	99.64 101	99.44 141

PVSNet	96.02 17	98.85 108	98.84 92	98.89 177	99.73 72	97.28 237	98.32 331	99.60 35	97.86 117	99.50 84	99.57 162	96.75 114	99.86 107	98.56 101	99.70 92	99.54 115

LS3D		99.27 51	99.12 55	99.74 45	99.18 202	99.75 24	99.56 112	99.57 44	98.45 59	99.49 87	99.85 26	97.77 88	99.94 42	98.33 122	99.84 58	99.52 120

MP-MVS		99.33 42	99.15 51	99.87 6	99.88 11	99.82 13	99.66 65	99.46 139	98.09 89	99.48 88	99.74 98	98.29 73	99.96 19	97.93 149	99.87 39	99.82 32

旧先验2							98.96 293		96.70 220	99.47 89			99.94 42	98.19 128

MSDG		98.98 92	98.80 96	99.53 81	99.76 44	99.19 93	98.75 312	99.55 55	97.25 176	99.47 89	99.77 85	97.82 86	99.87 104	96.93 229	99.90 25	99.54 115

CDS-MVSNet		99.09 77	99.03 65	99.25 125	99.42 150	98.73 170	99.45 155	99.46 139	98.11 86	99.46 91	99.77 85	98.01 82	99.37 229	98.70 81	98.92 145	99.66 88
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MSLP-MVS++		99.46 22	99.47 8	99.44 99	99.60 119	99.16 96	99.41 175	99.71 13	98.98 19	99.45 92	99.78 78	99.19 5	99.54 210	99.28 27	99.84 58	99.63 101

XVG-OURS		98.73 119	98.68 108	98.88 184	99.70 87	97.73 232	98.92 300	99.55 55	98.52 55	99.45 92	99.84 35	95.27 152	99.91 74	98.08 139	98.84 151	99.00 179

tpmrst		98.33 140	98.48 127	97.90 279	99.16 209	94.78 307	99.31 207	99.11 256	97.27 174	99.45 92	99.59 155	95.33 149	99.84 119	98.48 109	98.61 158	99.09 168

TAMVS		99.12 69	99.08 58	99.24 128	99.46 144	98.55 187	99.51 129	99.46 139	98.09 89	99.45 92	99.82 44	98.34 71	99.51 211	98.70 81	98.93 143	99.67 87

CANet_DTU		98.97 94	98.87 86	99.25 125	99.33 170	98.42 201	99.08 262	99.30 223	99.16 5	99.43 96	99.75 93	95.27 152	99.97 11	98.56 101	99.95 6	99.36 149

Patchmatch-test1		98.16 159	98.14 143	98.22 259	99.30 179	95.55 292	99.07 263	98.97 272	97.57 148	99.43 96	99.60 153	92.72 244	99.60 204	97.38 200	99.20 122	99.50 128

testdata				99.54 77	99.75 56	98.95 131		99.51 85	97.07 199	99.43 96	99.70 109	98.87 31	99.94 42	97.76 164	99.64 101	99.72 72

XVG-OURS-SEG-HR		98.69 122	98.62 117	98.89 177	99.71 82	97.74 231	99.12 252	99.54 62	98.44 62	99.42 99	99.71 106	94.20 209	99.92 65	98.54 106	98.90 147	99.00 179

DP-MVS Recon		99.12 69	98.95 77	99.65 59	99.74 67	99.70 31	99.27 219	99.57 44	96.40 246	99.42 99	99.68 120	98.75 47	99.80 143	97.98 145	99.72 86	99.44 141

Effi-MVS+-dtu		98.78 115	98.89 84	98.47 231	99.33 170	96.91 262	99.57 105	99.30 223	98.47 57	99.41 101	98.99 277	96.78 111	99.74 161	98.73 78	99.38 111	98.74 213

MIMVSNet		97.73 227	97.45 222	98.57 220	99.45 148	97.50 235	99.02 278	98.98 271	96.11 269	99.41 101	99.14 264	90.28 294	98.74 305	95.74 266	98.93 143	99.47 135

CSCG		99.32 43	99.32 27	99.32 111	99.85 23	98.29 203	99.71 41	99.66 25	98.11 86	99.41 101	99.80 65	98.37 70	99.96 19	98.99 50	99.96 5	99.72 72

F-COLMAP		99.19 57	99.04 63	99.64 64	99.78 36	99.27 87	99.42 171	99.54 62	97.29 173	99.41 101	99.59 155	98.42 67	99.93 57	98.19 128	99.69 93	99.73 66

MDTV_nov1_ep13			98.32 135		99.11 217	94.44 311	99.27 219	98.74 299	97.51 154	99.40 105	99.62 147	94.78 182	99.76 159	97.59 179	98.81 154

CVMVSNet		98.57 129	98.67 109	98.30 246	99.35 166	95.59 291	99.50 134	99.55 55	98.60 51	99.39 106	99.83 37	94.48 200	99.45 215	98.75 75	98.56 164	99.85 8

CNVR-MVS		99.42 30	99.30 34	99.78 35	99.62 113	99.71 29	99.26 227	99.52 76	98.82 35	99.39 106	99.71 106	98.96 21	99.85 113	98.59 95	99.80 71	99.77 52

Effi-MVS+		98.81 111	98.59 122	99.48 90	99.46 144	99.12 102	98.08 337	99.50 99	97.50 155	99.38 108	99.41 214	96.37 123	99.81 139	99.11 41	98.54 165	99.51 125

mvs_anonymous		99.03 86	98.99 70	99.16 134	99.38 161	98.52 192	99.51 129	99.38 186	97.79 127	99.38 108	99.81 54	97.30 99	99.45 215	99.35 18	98.99 137	99.51 125

XVS		99.53 9	99.42 11	99.87 6	99.85 23	99.83 8	99.69 45	99.68 19	98.98 19	99.37 110	99.74 98	98.81 36	99.94 42	98.79 72	99.86 49	99.84 12

X-MVStestdata		96.55 270	95.45 291	99.87 6	99.85 23	99.83 8	99.69 45	99.68 19	98.98 19	99.37 110	64.01 356	98.81 36	99.94 42	98.79 72	99.86 49	99.84 12

diffmvs		98.72 120	98.49 126	99.43 102	99.48 142	99.19 93	99.62 82	99.42 167	95.58 280	99.37 110	99.67 124	96.14 129	99.74 161	98.14 132	98.96 140	99.37 148

PatchmatchNet		98.31 142	98.36 131	98.19 262	99.16 209	95.32 299	99.27 219	98.92 278	97.37 167	99.37 110	99.58 158	94.90 174	99.70 185	97.43 198	99.21 121	99.54 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
AllTest		98.87 99	98.72 103	99.31 112	99.86 20	98.48 197	99.56 112	99.61 32	97.85 119	99.36 114	99.85 26	95.95 132	99.85 113	96.66 248	99.83 64	99.59 109

TestCases				99.31 112	99.86 20	98.48 197		99.61 32	97.85 119	99.36 114	99.85 26	95.95 132	99.85 113	96.66 248	99.83 64	99.59 109

Vis-MVSNet (Re-imp)		98.87 99	98.72 103	99.31 112	99.71 82	98.88 141	99.80 19	99.44 158	97.91 115	99.36 114	99.78 78	95.49 147	99.43 224	97.91 150	99.11 127	99.62 103

alignmvs		98.81 111	98.56 124	99.58 73	99.43 149	99.42 72	99.51 129	98.96 274	98.61 50	99.35 117	98.92 283	94.78 182	99.77 156	99.35 18	98.11 200	99.54 115

VPA-MVSNet		98.29 143	97.95 160	99.30 115	99.16 209	99.54 55	99.50 134	99.58 43	98.27 71	99.35 117	99.37 227	92.53 258	99.65 194	99.35 18	94.46 292	98.72 215

AdaColmap		99.01 90	98.80 96	99.66 55	99.56 127	99.54 55	99.18 243	99.70 15	98.18 79	99.35 117	99.63 142	96.32 124	99.90 87	97.48 192	99.77 77	99.55 113

test222					99.75 56	99.49 64	98.91 302	99.49 105	96.42 243	99.34 120	99.65 131	98.28 74			99.69 93	99.72 72

API-MVS		99.04 84	99.03 65	99.06 144	99.40 158	99.31 83	99.55 118	99.56 48	98.54 53	99.33 121	99.39 222	98.76 44	99.78 154	96.98 224	99.78 75	98.07 307

v144192		97.92 197	97.60 206	98.87 188	98.83 274	98.65 178	99.55 118	99.34 206	96.20 260	99.32 122	99.40 218	94.36 204	99.26 260	96.37 257	95.03 278	98.70 221

canonicalmvs		99.02 87	98.86 89	99.51 87	99.42 150	99.32 80	99.80 19	99.48 114	98.63 48	99.31 123	98.81 292	97.09 103	99.75 160	99.27 29	97.90 206	99.47 135

v6		98.12 163	97.84 175	98.94 159	98.94 251	98.83 149	99.66 65	99.34 206	96.49 233	99.30 124	99.37 227	94.95 168	99.34 239	97.77 163	94.74 282	98.67 242

V42		98.06 169	97.79 180	98.86 192	98.98 240	98.84 146	99.69 45	99.34 206	96.53 232	99.30 124	99.37 227	94.67 192	99.32 243	97.57 182	94.66 288	98.42 295

ab-mvs		98.86 102	98.63 114	99.54 77	99.64 106	99.19 93	99.44 159	99.54 62	97.77 129	99.30 124	99.81 54	94.20 209	99.93 57	99.17 36	98.82 152	99.49 129

TAPA-MVS	97.07 15	97.74 226	97.34 242	98.94 159	99.70 87	97.53 234	99.25 229	99.51 85	91.90 324	99.30 124	99.63 142	98.78 39	99.64 196	88.09 331	99.87 39	99.65 91
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v1neww		98.12 163	97.84 175	98.93 162	98.97 243	98.81 158	99.66 65	99.35 198	96.49 233	99.29 128	99.37 227	95.02 164	99.32 243	97.73 168	94.73 283	98.67 242

v7new		98.12 163	97.84 175	98.93 162	98.97 243	98.81 158	99.66 65	99.35 198	96.49 233	99.29 128	99.37 227	95.02 164	99.32 243	97.73 168	94.73 283	98.67 242

新几何1				99.75 40	99.75 56	99.59 49		99.54 62	96.76 216	99.29 128	99.64 138	98.43 64	99.94 42	96.92 230	99.66 98	99.72 72

v7		98.05 175	97.78 182	98.87 188	98.99 236	98.67 175	99.64 77	99.34 206	96.31 251	99.29 128	99.51 185	94.78 182	99.27 255	97.03 220	95.15 275	98.66 253

VPNet		97.84 205	97.44 227	99.01 149	99.21 195	98.94 134	99.48 147	99.57 44	98.38 64	99.28 132	99.73 101	88.89 308	99.39 225	99.19 33	93.27 309	98.71 217

v1		98.05 175	97.76 189	98.93 162	98.92 258	98.80 163	99.57 105	99.35 198	96.39 247	99.28 132	99.36 234	94.86 177	99.32 243	97.38 200	94.72 285	98.68 231

HY-MVS	97.30 7	98.85 108	98.64 113	99.47 93	99.42 150	99.08 105	99.62 82	99.36 194	97.39 166	99.28 132	99.68 120	96.44 121	99.92 65	98.37 118	98.22 180	99.40 146

PAPM_NR		99.04 84	98.84 92	99.66 55	99.74 67	99.44 70	99.39 182	99.38 186	97.70 138	99.28 132	99.28 252	98.34 71	99.85 113	96.96 226	99.45 107	99.69 80

HPM-MVS++		99.39 37	99.23 46	99.87 6	99.75 56	99.84 7	99.43 164	99.51 85	98.68 47	99.27 136	99.53 177	98.64 55	99.96 19	98.44 114	99.80 71	99.79 46

v1240		97.69 233	97.32 245	98.79 202	98.85 272	98.43 199	99.48 147	99.36 194	96.11 269	99.27 136	99.36 234	93.76 226	99.24 263	94.46 290	95.23 272	98.70 221

thres600view7		97.86 202	97.51 212	98.92 167	99.72 76	97.95 218	99.59 92	98.74 299	97.94 111	99.27 136	98.62 299	91.75 275	99.86 107	93.73 305	98.19 183	98.96 189

PLC	97.94 4	99.02 87	98.85 91	99.53 81	99.66 103	99.01 119	99.24 231	99.52 76	96.85 213	99.27 136	99.48 196	98.25 75	99.91 74	97.76 164	99.62 104	99.65 91
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tfpn111		97.81 211	97.49 216	98.78 204	99.72 76	97.86 221	99.59 92	98.74 299	97.93 112	99.26 140	98.62 299	91.75 275	99.86 107	93.57 306	98.18 184	98.61 275

conf200view11		97.78 218	97.45 222	98.77 205	99.72 76	97.86 221	99.59 92	98.74 299	97.93 112	99.26 140	98.62 299	91.75 275	99.83 126	93.22 310	98.18 184	98.61 275

thres100view900		97.76 220	97.45 222	98.69 211	99.72 76	97.86 221	99.59 92	98.74 299	97.93 112	99.26 140	98.62 299	91.75 275	99.83 126	93.22 310	98.18 184	98.37 299

EPMVS		97.82 210	97.65 202	98.35 242	98.88 265	95.98 286	99.49 142	94.71 350	97.57 148	99.26 140	99.48 196	92.46 263	99.71 179	97.87 153	99.08 131	99.35 150

view600		97.97 188	97.66 197	98.89 177	99.75 56	97.81 225	99.69 45	98.80 291	98.02 102	99.25 144	98.88 284	91.95 269	99.89 95	94.36 293	98.29 175	98.96 189

view800		97.97 188	97.66 197	98.89 177	99.75 56	97.81 225	99.69 45	98.80 291	98.02 102	99.25 144	98.88 284	91.95 269	99.89 95	94.36 293	98.29 175	98.96 189

conf0.05thres1000		97.97 188	97.66 197	98.89 177	99.75 56	97.81 225	99.69 45	98.80 291	98.02 102	99.25 144	98.88 284	91.95 269	99.89 95	94.36 293	98.29 175	98.96 189

tfpn		97.97 188	97.66 197	98.89 177	99.75 56	97.81 225	99.69 45	98.80 291	98.02 102	99.25 144	98.88 284	91.95 269	99.89 95	94.36 293	98.29 175	98.96 189

1121		99.09 77	98.87 86	99.75 40	99.74 67	99.60 47	99.27 219	99.48 114	96.82 215	99.25 144	99.65 131	98.38 68	99.93 57	97.53 187	99.67 97	99.73 66

Fast-Effi-MVS+-dtu		98.77 117	98.83 95	98.60 217	99.41 153	96.99 256	99.52 125	99.49 105	98.11 86	99.24 149	99.34 241	96.96 107	99.79 146	97.95 148	99.45 107	99.02 178

v1921920		97.80 214	97.45 222	98.84 196	98.80 275	98.53 189	99.52 125	99.34 206	96.15 266	99.24 149	99.47 200	93.98 218	99.29 251	95.40 275	95.13 276	98.69 226

divwei89l23v2f112		98.06 169	97.78 182	98.91 171	98.90 261	98.77 168	99.57 105	99.35 198	96.45 240	99.24 149	99.37 227	94.92 172	99.27 255	97.50 190	94.71 287	98.68 231

LPG-MVS_test		98.22 150	98.13 144	98.49 227	99.33 170	97.05 251	99.58 99	99.55 55	97.46 157	99.24 149	99.83 37	92.58 256	99.72 173	98.09 135	97.51 221	98.68 231

LGP-MVS_train				98.49 227	99.33 170	97.05 251		99.55 55	97.46 157	99.24 149	99.83 37	92.58 256	99.72 173	98.09 135	97.51 221	98.68 231

v1144		97.98 185	97.69 196	98.85 195	98.87 268	98.66 177	99.54 121	99.35 198	96.27 254	99.23 154	99.35 238	94.67 192	99.23 264	96.73 243	95.16 274	98.68 231

v1141		98.05 175	97.76 189	98.91 171	98.91 260	98.78 167	99.57 105	99.35 198	96.41 245	99.23 154	99.36 234	94.93 171	99.27 255	97.38 200	94.72 285	98.68 231

OPM-MVS		98.19 156	98.10 146	98.45 233	98.88 265	97.07 249	99.28 216	99.38 186	98.57 52	99.22 156	99.81 54	92.12 268	99.66 192	98.08 139	97.54 220	98.61 275

test_djsdf		98.67 124	98.57 123	98.98 153	98.70 292	98.91 139	99.88 1	99.46 139	97.55 150	99.22 156	99.88 14	95.73 142	99.28 252	99.03 46	97.62 213	98.75 210

test12				99.75 40	99.64 106	99.61 45		99.29 227		99.21 158		98.38 68	99.89 95		99.74 82	99.74 61

NCCC		99.34 41	99.19 48	99.79 34	99.61 117	99.65 40	99.30 209	99.48 114	98.86 31	99.21 158	99.63 142	98.72 50	99.90 87	98.25 126	99.63 103	99.80 42

PMMVS		98.80 114	98.62 117	99.34 107	99.27 187	98.70 173	98.76 311	99.31 221	97.34 168	99.21 158	99.07 270	97.20 101	99.82 135	98.56 101	98.87 149	99.52 120

v1192		97.81 211	97.44 227	98.91 171	98.88 265	98.68 174	99.51 129	99.34 206	96.18 262	99.20 161	99.34 241	94.03 217	99.36 233	95.32 277	95.18 273	98.69 226

EI-MVSNet		98.67 124	98.67 109	98.68 212	99.35 166	97.97 215	99.50 134	99.38 186	96.93 209	99.20 161	99.83 37	97.87 84	99.36 233	98.38 117	97.56 218	98.71 217

MVSTER		98.49 130	98.32 135	99.00 151	99.35 166	99.02 117	99.54 121	99.38 186	97.41 164	99.20 161	99.73 101	93.86 223	99.36 233	98.87 61	97.56 218	98.62 266

v2v482		98.06 169	97.77 186	98.92 167	98.90 261	98.82 156	99.57 105	99.36 194	96.65 223	99.19 164	99.35 238	94.20 209	99.25 261	97.72 172	94.97 279	98.69 226

CNLPA		99.14 63	98.99 70	99.59 70	99.58 122	99.41 73	99.16 245	99.44 158	98.45 59	99.19 164	99.49 190	98.08 80	99.89 95	97.73 168	99.75 80	99.48 131

UGNet		98.87 99	98.69 107	99.40 104	99.22 194	98.72 172	99.44 159	99.68 19	99.24 3	99.18 166	99.42 211	92.74 243	99.96 19	99.34 22	99.94 10	99.53 119
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
tfpn200view9		97.72 229	97.38 235	98.72 209	99.69 89	97.96 216	99.50 134	98.73 308	97.83 122	99.17 167	98.45 308	91.67 281	99.83 126	93.22 310	98.18 184	98.37 299

thres400		97.77 219	97.38 235	98.92 167	99.69 89	97.96 216	99.50 134	98.73 308	97.83 122	99.17 167	98.45 308	91.67 281	99.83 126	93.22 310	98.18 184	98.96 189

Test_1112_low_res		98.89 98	98.66 112	99.57 74	99.69 89	98.95 131	99.03 275	99.47 130	96.98 205	99.15 169	99.23 258	96.77 113	99.89 95	98.83 68	98.78 155	99.86 5

1112_ss		98.98 92	98.77 99	99.59 70	99.68 92	99.02 117	99.25 229	99.48 114	97.23 179	99.13 170	99.58 158	96.93 108	99.90 87	98.87 61	98.78 155	99.84 12

CLD-MVS		98.16 159	98.10 146	98.33 243	99.29 182	96.82 265	98.75 312	99.44 158	97.83 122	99.13 170	99.55 167	92.92 237	99.67 190	98.32 124	97.69 210	98.48 291
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
原ACMM1				99.65 59	99.73 72	99.33 79		99.47 130	97.46 157	99.12 172	99.66 130	98.67 54	99.91 74	97.70 173	99.69 93	99.71 79

tpm		97.67 238	97.55 208	98.03 268	99.02 233	95.01 305	99.43 164	98.54 318	96.44 241	99.12 172	99.34 241	91.83 274	99.60 204	97.75 166	96.46 251	99.48 131

HQP_MVS		98.27 145	98.22 141	98.44 236	99.29 182	96.97 258	99.39 182	99.47 130	98.97 22	99.11 174	99.61 150	92.71 245	99.69 188	97.78 161	97.63 211	98.67 242

plane_prior3						97.00 255			98.69 46	99.11 174

CHOSEN 1792x2688		99.19 57	99.10 57	99.45 96	99.89 8	98.52 192	99.39 182	99.94 1	98.73 44	99.11 174	99.89 10	95.50 146	99.94 42	99.50 8	99.97 3	99.89 2

mvs-test1		98.86 102	98.84 92	98.89 177	99.33 170	97.77 230	99.44 159	99.30 223	98.47 57	99.10 177	99.43 209	96.78 111	99.95 33	98.73 78	99.02 135	98.96 189

v8		97.95 193	97.63 204	98.93 162	98.95 248	98.81 158	99.80 19	99.41 170	96.03 273	99.10 177	99.42 211	94.92 172	99.30 249	96.94 228	94.08 300	98.66 253

ADS-MVSNet2		98.02 180	98.07 151	97.87 280	99.33 170	95.19 302	99.23 232	99.08 259	96.24 257	99.10 177	99.67 124	94.11 214	98.93 301	96.81 239	99.05 133	99.48 131

ADS-MVSNet		98.20 155	98.08 149	98.56 222	99.33 170	96.48 275	99.23 232	99.15 252	96.24 257	99.10 177	99.67 124	94.11 214	99.71 179	96.81 239	99.05 133	99.48 131

thres200		97.61 241	97.28 249	98.62 216	99.64 106	98.03 212	99.26 227	98.74 299	97.68 140	99.09 181	98.32 310	91.66 283	99.81 139	92.88 316	98.22 180	98.03 311

dp		97.75 224	97.80 179	97.59 293	99.10 220	93.71 319	99.32 204	98.88 285	96.48 239	99.08 182	99.55 167	92.67 254	99.82 135	96.52 252	98.58 161	99.24 157

GBi-Net		97.68 235	97.48 217	98.29 247	99.51 132	97.26 239	99.43 164	99.48 114	96.49 233	99.07 183	99.32 246	90.26 295	98.98 293	97.10 216	96.65 246	98.62 266

test1		97.68 235	97.48 217	98.29 247	99.51 132	97.26 239	99.43 164	99.48 114	96.49 233	99.07 183	99.32 246	90.26 295	98.98 293	97.10 216	96.65 246	98.62 266

FMVSNet3		98.03 178	97.76 189	98.84 196	99.39 160	98.98 123	99.40 181	99.38 186	96.67 222	99.07 183	99.28 252	92.93 236	98.98 293	97.10 216	96.65 246	98.56 287

IterMVS-LS		98.46 132	98.42 129	98.58 219	99.59 121	98.00 213	99.37 189	99.43 166	96.94 208	99.07 183	99.59 155	97.87 84	99.03 288	98.32 124	95.62 266	98.71 217
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
pmmvs4		98.13 161	97.90 163	98.81 199	98.61 300	98.87 142	98.99 284	99.21 246	96.44 241	99.06 187	99.58 158	95.90 136	99.11 280	97.18 211	96.11 258	98.46 294

XVG-ACMP-BASELINE		97.83 207	97.71 195	98.20 261	99.11 217	96.33 280	99.41 175	99.52 76	98.06 97	99.05 188	99.50 187	89.64 302	99.73 169	97.73 168	97.38 234	98.53 288

CostFormer		97.72 229	97.73 193	97.71 291	99.15 212	94.02 315	99.54 121	99.02 268	94.67 290	99.04 189	99.35 238	92.35 266	99.77 156	98.50 108	97.94 205	99.34 151

DP-MVS		99.16 62	98.95 77	99.78 35	99.77 41	99.53 58	99.41 175	99.50 99	97.03 203	99.04 189	99.88 14	97.39 95	99.92 65	98.66 86	99.90 25	99.87 4

ACMM	97.58 5	98.37 139	98.34 133	98.48 229	99.41 153	97.10 245	99.56 112	99.45 150	98.53 54	99.04 189	99.85 26	93.00 235	99.71 179	98.74 76	97.45 228	98.64 258
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Fast-Effi-MVS+		98.70 121	98.43 128	99.51 87	99.51 132	99.28 85	99.52 125	99.47 130	96.11 269	99.01 192	99.34 241	96.20 128	99.84 119	97.88 152	98.82 152	99.39 147

nrg030		98.64 127	98.42 129	99.28 120	99.05 229	99.69 32	99.81 15	99.46 139	98.04 99	99.01 192	99.82 44	96.69 116	99.38 226	99.34 22	94.59 291	98.78 204

test_prior3		99.21 56	99.05 60	99.68 52	99.67 93	99.48 65	98.96 293	99.56 48	98.34 66	99.01 192	99.52 182	98.68 52	99.83 126	97.96 146	99.74 82	99.74 61

test_prior2							98.96 293		98.34 66	99.01 192	99.52 182	98.68 52		97.96 146	99.74 82

v52		97.79 216	97.50 214	98.66 215	98.80 275	98.62 182	99.87 4	99.44 158	95.87 275	99.01 192	99.46 204	94.44 203	99.33 240	96.65 250	93.96 303	98.05 308

V4		97.80 214	97.51 212	98.67 214	98.79 277	98.63 180	99.87 4	99.44 158	95.87 275	99.01 192	99.46 204	94.52 199	99.33 240	96.64 251	93.97 302	98.05 308

MAR-MVS		98.86 102	98.63 114	99.54 77	99.37 163	99.66 37	99.45 155	99.54 62	96.61 226	99.01 192	99.40 218	97.09 103	99.86 107	97.68 176	99.53 106	99.10 164
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
PS-MVSNAJss		98.92 97	98.92 79	98.90 175	98.78 281	98.53 189	99.78 22	99.54 62	98.07 93	99.00 199	99.76 88	99.01 12	99.37 229	99.13 39	97.23 238	98.81 201

PAPR		98.63 128	98.34 133	99.51 87	99.40 158	99.03 116	98.80 308	99.36 194	96.33 248	99.00 199	99.12 268	98.46 62	99.84 119	95.23 278	99.37 115	99.66 88

v10		97.85 203	97.52 210	98.86 192	98.99 236	98.67 175	99.75 34	99.41 170	95.70 278	98.98 201	99.41 214	94.75 188	99.23 264	96.01 262	94.63 290	98.67 242

UniMVSNet (Re)		98.29 143	98.00 156	99.13 140	99.00 235	99.36 77	99.49 142	99.51 85	97.95 110	98.97 202	99.13 265	96.30 125	99.38 226	98.36 120	93.34 308	98.66 253

TEST9					99.67 93	99.65 40	99.05 269	99.41 170	96.22 259	98.95 203	99.49 190	98.77 42	99.91 74

train_agg		99.02 87	98.77 99	99.77 37	99.67 93	99.65 40	99.05 269	99.41 170	96.28 252	98.95 203	99.49 190	98.76 44	99.91 74	97.63 177	99.72 86	99.75 56

BH-RMVSNet		98.41 136	98.08 149	99.40 104	99.41 153	98.83 149	99.30 209	98.77 295	97.70 138	98.94 205	99.65 131	92.91 239	99.74 161	96.52 252	99.55 105	99.64 97

test_8					99.67 93	99.61 45	99.03 275	99.41 170	96.28 252	98.93 206	99.48 196	98.76 44	99.91 74

3Dnovator	97.25 9	99.24 55	99.05 60	99.81 29	99.12 215	99.66 37	99.84 9	99.74 10	99.09 8	98.92 207	99.90 7	95.94 134	99.98 5	98.95 53	99.92 12	99.79 46

v7n		97.87 201	97.52 210	98.92 167	98.76 285	98.58 186	99.84 9	99.46 139	96.20 260	98.91 208	99.70 109	94.89 175	99.44 220	96.03 261	93.89 304	98.75 210

JIA-IIPM		97.50 250	97.02 258	98.93 162	98.73 287	97.80 229	99.30 209	98.97 272	91.73 325	98.91 208	94.86 341	95.10 161	99.71 179	97.58 180	97.98 204	99.28 155

v148		97.79 216	97.55 208	98.50 226	98.74 286	97.72 233	99.54 121	99.33 214	96.26 255	98.90 210	99.51 185	94.68 191	99.14 274	97.83 156	93.15 311	98.63 264

GA-MVS		97.85 203	97.47 219	99.00 151	99.38 161	97.99 214	98.57 322	99.15 252	97.04 202	98.90 210	99.30 249	89.83 300	99.38 226	96.70 245	98.33 173	99.62 103

tpm2		97.44 254	97.34 242	97.74 290	99.15 212	94.36 312	99.45 155	98.94 275	93.45 315	98.90 210	99.44 208	91.35 286	99.59 206	97.31 203	98.07 201	99.29 154

agg_prior3		98.97 94	98.71 105	99.75 40	99.67 93	99.60 47	99.04 274	99.41 170	95.93 274	98.87 213	99.48 196	98.61 56	99.91 74	97.63 177	99.72 86	99.75 56

agg_prior1		99.01 90	98.76 101	99.76 39	99.67 93	99.62 43	98.99 284	99.40 177	96.26 255	98.87 213	99.49 190	98.77 42	99.91 74	97.69 174	99.72 86	99.75 56

agg_prior					99.67 93	99.62 43		99.40 177		98.87 213			99.91 74

anonymousdsp		98.44 133	98.28 138	98.94 159	98.50 306	98.96 130	99.77 24	99.50 99	97.07 199	98.87 213	99.77 85	94.76 187	99.28 252	98.66 86	97.60 214	98.57 286

DSMNet-mixed		97.25 260	97.35 239	96.95 304	97.84 316	93.61 321	99.57 105	96.63 346	96.13 268	98.87 213	98.61 303	94.59 195	97.70 330	95.08 280	98.86 150	99.55 113

FMVSNet2		97.72 229	97.36 237	98.80 201	99.51 132	98.84 146	99.45 155	99.42 167	96.49 233	98.86 218	99.29 251	90.26 295	98.98 293	96.44 254	96.56 249	98.58 285

PatchFormer-LS_test		98.01 183	98.05 152	97.87 280	99.15 212	94.76 308	99.42 171	98.93 276	97.12 188	98.84 219	98.59 304	93.74 228	99.80 143	98.55 104	98.17 190	99.06 174

ITE_SJBPF				98.08 266	99.29 182	96.37 278		98.92 278	98.34 66	98.83 220	99.75 93	91.09 288	99.62 202	95.82 264	97.40 232	98.25 304

Patchmtry		97.75 224	97.40 233	98.81 199	99.10 220	98.87 142	99.11 258	99.33 214	94.83 287	98.81 221	99.38 223	94.33 205	99.02 289	96.10 259	95.57 267	98.53 288

BH-untuned		98.42 135	98.36 131	98.59 218	99.49 139	96.70 268	99.27 219	99.13 255	97.24 178	98.80 222	99.38 223	95.75 141	99.74 161	97.07 219	99.16 124	99.33 152

FIs		98.78 115	98.63 114	99.23 130	99.18 202	99.54 55	99.83 12	99.59 38	98.28 70	98.79 223	99.81 54	96.75 114	99.37 229	99.08 43	96.38 253	98.78 204

OurMVSNet-221017-0		97.88 200	97.77 186	98.19 262	98.71 291	96.53 273	99.88 1	99.00 269	97.79 127	98.78 224	99.94 3	91.68 280	99.35 236	97.21 207	96.99 244	98.69 226

MVS-HIRNet		95.75 291	95.16 295	97.51 295	99.30 179	93.69 320	98.88 304	95.78 347	85.09 339	98.78 224	92.65 343	91.29 287	99.37 229	94.85 283	99.85 53	99.46 138

tpmvs		97.98 185	98.02 154	97.84 283	99.04 230	94.73 309	99.31 207	99.20 247	96.10 272	98.76 226	99.42 211	94.94 169	99.81 139	96.97 225	98.45 169	98.97 183

Patchmatch-test		97.93 194	97.65 202	98.77 205	99.18 202	97.07 249	99.03 275	99.14 254	96.16 264	98.74 227	99.57 162	94.56 196	99.72 173	93.36 309	99.11 127	99.52 120

QAPM		98.67 124	98.30 137	99.80 31	99.20 197	99.67 35	99.77 24	99.72 11	94.74 289	98.73 228	99.90 7	95.78 140	99.98 5	96.96 226	99.88 35	99.76 55

3Dnovator+	97.12 13	99.18 59	98.97 73	99.82 26	99.17 207	99.68 33	99.81 15	99.51 85	99.20 4	98.72 229	99.89 10	95.68 143	99.97 11	98.86 64	99.86 49	99.81 36

semantic-postprocess				98.06 267	99.57 124	96.36 279		99.49 105	97.18 182	98.71 230	99.72 105	92.70 247	99.14 274	97.44 197	95.86 262	98.67 242

UniMVSNet_NR-MVSNet		98.22 150	97.97 158	98.96 156	98.92 258	98.98 123	99.48 147	99.53 72	97.76 130	98.71 230	99.46 204	96.43 122	99.22 267	98.57 98	92.87 314	98.69 226

DU-MVS		98.08 168	97.79 180	98.96 156	98.87 268	98.98 123	99.41 175	99.45 150	97.87 116	98.71 230	99.50 187	94.82 179	99.22 267	98.57 98	92.87 314	98.68 231

tpm cat1		97.39 256	97.36 237	97.50 296	99.17 207	93.73 317	99.43 164	99.31 221	91.27 326	98.71 230	99.08 269	94.31 207	99.77 156	96.41 256	98.50 167	99.00 179

XXY-MVS		98.38 138	98.09 148	99.24 128	99.26 189	99.32 80	99.56 112	99.55 55	97.45 160	98.71 230	99.83 37	93.23 232	99.63 201	98.88 57	96.32 255	98.76 209

IterMVS		97.83 207	97.77 186	98.02 270	99.58 122	96.27 282	99.02 278	99.48 114	97.22 180	98.71 230	99.70 109	92.75 241	99.13 277	97.46 195	96.00 260	98.67 242
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		98.75 118	98.62 117	99.15 136	99.08 223	99.45 69	99.86 8	99.60 35	98.23 75	98.70 236	99.82 44	96.80 110	99.22 267	99.07 44	96.38 253	98.79 203

COLMAP_ROB	97.56 6	98.86 102	98.75 102	99.17 133	99.88 11	98.53 189	99.34 202	99.59 38	97.55 150	98.70 236	99.89 10	95.83 138	99.90 87	98.10 134	99.90 25	99.08 169
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TR-MVS		97.76 220	97.41 232	98.82 198	99.06 226	97.87 220	98.87 305	98.56 317	96.63 225	98.68 238	99.22 259	92.49 259	99.65 194	95.40 275	97.79 208	98.95 196

WR-MVS		98.06 169	97.73 193	99.06 144	98.86 271	99.25 89	99.19 242	99.35 198	97.30 172	98.66 239	99.43 209	93.94 219	99.21 271	98.58 96	94.28 295	98.71 217

HQP-NCC					99.19 199		98.98 288		98.24 72	98.66 239

ACMP_Plane					99.19 199		98.98 288		98.24 72	98.66 239

HQP4-MVS										98.66 239			99.64 196			98.64 258

HQP-MVS		98.02 180	97.90 163	98.37 241	99.19 199	96.83 263	98.98 288	99.39 180	98.24 72	98.66 239	99.40 218	92.47 260	99.64 196	97.19 209	97.58 216	98.64 258

LF4IMVS		97.52 246	97.46 221	97.70 292	98.98 240	95.55 292	99.29 213	98.82 290	98.07 93	98.66 239	99.64 138	89.97 299	99.61 203	97.01 221	96.68 245	97.94 315

mvs_tets		98.40 137	98.23 140	98.91 171	98.67 296	98.51 194	99.66 65	99.53 72	98.19 76	98.65 245	99.81 54	92.75 241	99.44 220	99.31 25	97.48 227	98.77 207

TESTMET0.1,1		97.55 243	97.27 251	98.40 239	98.93 256	96.53 273	98.67 316	97.61 341	96.96 206	98.64 246	99.28 252	88.63 314	99.45 215	97.30 204	99.38 111	99.21 158

jajsoiax		98.43 134	98.28 138	98.88 184	98.60 301	98.43 199	99.82 13	99.53 72	98.19 76	98.63 247	99.80 65	93.22 233	99.44 220	99.22 31	97.50 223	98.77 207

Baseline_NR-MVSNet		97.76 220	97.45 222	98.68 212	99.09 222	98.29 203	99.41 175	98.85 287	95.65 279	98.63 247	99.67 124	94.82 179	99.10 282	98.07 141	92.89 313	98.64 258

EPNet		98.86 102	98.71 105	99.30 115	97.20 327	98.18 207	99.62 82	98.91 281	99.28 2	98.63 247	99.81 54	95.96 131	99.99 1	99.24 30	99.72 86	99.73 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test-LLR		98.06 169	97.90 163	98.55 224	98.79 277	97.10 245	98.67 316	97.75 331	97.34 168	98.61 250	98.85 288	94.45 201	99.45 215	97.25 205	99.38 111	99.10 164

test-mter		97.49 252	97.13 255	98.55 224	98.79 277	97.10 245	98.67 316	97.75 331	96.65 223	98.61 250	98.85 288	88.23 319	99.45 215	97.25 205	99.38 111	99.10 164

FMVSNet1		96.84 267	96.36 268	98.29 247	99.32 177	97.26 239	99.43 164	99.48 114	95.11 284	98.55 252	99.32 246	83.95 337	98.98 293	95.81 265	96.26 256	98.62 266

v748		97.52 246	97.23 252	98.41 238	98.69 293	97.23 242	99.87 4	99.45 150	95.72 277	98.51 253	99.53 177	94.13 213	99.30 249	96.78 241	92.39 318	98.70 221

PCF-MVS	97.08 14	97.66 239	97.06 257	99.47 93	99.61 117	99.09 104	98.04 338	99.25 242	91.24 327	98.51 253	99.70 109	94.55 197	99.91 74	92.76 317	99.85 53	99.42 144
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		97.93 194	97.66 197	98.76 207	98.78 281	98.62 182	99.65 75	99.49 105	97.76 130	98.49 255	99.60 153	94.23 208	98.97 300	98.00 144	92.90 312	98.70 221

CP-MVSNet		98.09 167	97.78 182	99.01 149	98.97 243	99.24 90	99.67 56	99.46 139	97.25 176	98.48 256	99.64 138	93.79 224	99.06 284	98.63 89	94.10 299	98.74 213

ACMP	97.20 11	98.06 169	97.94 161	98.45 233	99.37 163	97.01 254	99.44 159	99.49 105	97.54 153	98.45 257	99.79 73	91.95 269	99.72 173	97.91 150	97.49 226	98.62 266
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
cascas		97.69 233	97.43 230	98.48 229	98.60 301	97.30 236	98.18 336	99.39 180	92.96 317	98.41 258	98.78 295	93.77 225	99.27 255	98.16 131	98.61 158	98.86 198

WR-MVS_H		98.13 161	97.87 174	98.90 175	99.02 233	98.84 146	99.70 42	99.59 38	97.27 174	98.40 259	99.19 261	95.53 145	99.23 264	98.34 121	93.78 305	98.61 275

BH-w/o		98.00 184	97.89 167	98.32 244	99.35 166	96.20 284	99.01 282	98.90 283	96.42 243	98.38 260	99.00 276	95.26 154	99.72 173	96.06 260	98.61 158	99.03 176

pmmvs5		97.52 246	97.30 247	98.16 264	98.57 303	96.73 267	99.27 219	98.90 283	96.14 267	98.37 261	99.53 177	91.54 285	99.14 274	97.51 189	95.87 261	98.63 264

DWT-MVSNet_test		97.53 245	97.40 233	97.93 276	99.03 232	94.86 306	99.57 105	98.63 313	96.59 230	98.36 262	98.79 293	89.32 304	99.74 161	98.14 132	98.16 191	99.20 159

EU-MVSNet		97.98 185	98.03 153	97.81 286	98.72 289	96.65 271	99.66 65	99.66 25	98.09 89	98.35 263	99.82 44	95.25 155	98.01 322	97.41 199	95.30 271	98.78 204

FMVSNet5		96.43 273	96.19 270	97.15 299	99.11 217	95.89 288	99.32 204	99.52 76	94.47 299	98.34 264	99.07 270	87.54 323	97.07 333	92.61 318	95.72 264	98.47 292

PS-CasMVS		97.93 194	97.59 207	98.95 158	98.99 236	99.06 107	99.68 54	99.52 76	97.13 186	98.31 265	99.68 120	92.44 264	99.05 285	98.51 107	94.08 300	98.75 210

USDC		97.34 257	97.20 253	97.75 289	99.07 224	95.20 301	98.51 325	99.04 266	97.99 107	98.31 265	99.86 22	89.02 306	99.55 209	95.67 270	97.36 235	98.49 290

PEN-MVS		97.76 220	97.44 227	98.72 209	98.77 284	98.54 188	99.78 22	99.51 85	97.06 201	98.29 267	99.64 138	92.63 255	98.89 302	98.09 135	93.16 310	98.72 215

tfpnnormal		97.84 205	97.47 219	98.98 153	99.20 197	99.22 92	99.64 77	99.61 32	96.32 249	98.27 268	99.70 109	93.35 231	99.44 220	95.69 268	95.40 269	98.27 302

tpmp4_e23		97.34 257	97.29 248	97.52 294	99.25 191	93.73 317	99.58 99	99.19 250	94.00 306	98.20 269	99.41 214	90.74 292	99.74 161	97.13 215	98.07 201	99.07 173

LTVRE_ROB	97.16 12	98.02 180	97.90 163	98.40 239	99.23 192	96.80 266	99.70 42	99.60 35	97.12 188	98.18 270	99.70 109	91.73 279	99.72 173	98.39 115	97.45 228	98.68 231
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
ACMH	97.28 8	98.10 166	97.99 157	98.44 236	99.41 153	96.96 260	99.60 90	99.56 48	98.09 89	98.15 271	99.91 5	90.87 291	99.70 185	98.88 57	97.45 228	98.67 242
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		97.24 261	97.32 245	96.99 302	98.45 308	93.51 322	98.82 307	99.32 220	97.41 164	98.13 272	99.30 249	88.99 307	99.56 207	95.68 269	99.80 71	97.90 318

LP		97.04 265	96.80 261	97.77 288	98.90 261	95.23 300	98.97 291	99.06 264	94.02 305	98.09 273	99.41 214	93.88 221	98.82 303	90.46 323	98.42 171	99.26 156

MVS		97.28 259	96.55 266	99.48 90	98.78 281	98.95 131	99.27 219	99.39 180	83.53 340	98.08 274	99.54 170	96.97 106	99.87 104	94.23 301	99.16 124	99.63 101

PAPM		97.59 242	97.09 256	99.07 143	99.06 226	98.26 205	98.30 332	99.10 257	94.88 286	98.08 274	99.34 241	96.27 126	99.64 196	89.87 325	98.92 145	99.31 153

OpenMVS	96.50 16	98.47 131	98.12 145	99.52 85	99.04 230	99.53 58	99.82 13	99.72 11	94.56 295	98.08 274	99.88 14	94.73 189	99.98 5	97.47 194	99.76 79	99.06 174

gg-mvs-nofinetune		96.17 286	95.32 293	98.73 208	98.79 277	98.14 209	99.38 187	94.09 351	91.07 329	98.07 277	91.04 347	89.62 303	99.35 236	96.75 242	99.09 130	98.68 231

test0.0.03 1		97.71 232	97.42 231	98.56 222	98.41 309	97.82 224	98.78 309	98.63 313	97.34 168	98.05 278	98.98 280	94.45 201	98.98 293	95.04 281	97.15 242	98.89 197

1314		98.68 123	98.54 125	99.11 141	98.89 264	98.65 178	99.27 219	99.49 105	96.89 211	97.99 279	99.56 164	97.72 90	99.83 126	97.74 167	99.27 119	98.84 199

DTE-MVSNet		97.51 249	97.19 254	98.46 232	98.63 299	98.13 210	99.84 9	99.48 114	96.68 221	97.97 280	99.67 124	92.92 237	98.56 308	96.88 238	92.60 317	98.70 221

SixPastTwentyTwo		97.50 250	97.33 244	98.03 268	98.65 297	96.23 283	99.77 24	98.68 311	97.14 185	97.90 281	99.93 4	90.45 293	99.18 273	97.00 222	96.43 252	98.67 242

pm-mvs1		97.68 235	97.28 249	98.88 184	99.06 226	98.62 182	99.50 134	99.45 150	96.32 249	97.87 282	99.79 73	92.47 260	99.35 236	97.54 186	93.54 307	98.67 242

testgi		97.65 240	97.50 214	98.13 265	99.36 165	96.45 276	99.42 171	99.48 114	97.76 130	97.87 282	99.45 207	91.09 288	98.81 304	94.53 288	98.52 166	99.13 163

EPNet_dtu		98.03 178	97.96 159	98.23 257	98.27 311	95.54 294	99.23 232	98.75 296	99.02 10	97.82 284	99.71 106	96.11 130	99.48 212	93.04 314	99.65 100	99.69 80
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		97.12 263	96.89 260	97.83 284	99.07 224	95.52 295	98.57 322	98.74 299	97.58 147	97.81 285	99.79 73	88.16 320	99.56 207	95.10 279	97.21 239	98.39 298

ACMH+	97.24 10	97.92 197	97.78 182	98.32 244	99.46 144	96.68 270	99.56 112	99.54 62	98.41 63	97.79 286	99.87 19	90.18 298	99.66 192	98.05 143	97.18 241	98.62 266

N_pmnet		94.95 300	95.83 278	92.31 324	98.47 307	79.33 347	99.12 252	92.81 356	93.87 308	97.68 287	99.13 265	93.87 222	99.01 290	91.38 321	96.19 257	98.59 282

PVSNet_0	94.43 19	96.09 288	95.47 290	97.94 275	99.31 178	94.34 313	97.81 339	99.70 15	97.12 188	97.46 288	98.75 296	89.71 301	99.79 146	97.69 174	81.69 343	99.68 84

pmmvs6		96.53 271	96.09 272	97.82 285	98.69 293	95.47 296	99.37 189	99.47 130	93.46 314	97.41 289	99.78 78	87.06 326	99.33 240	96.92 230	92.70 316	98.65 256

new_pmnet		96.38 277	96.03 273	97.41 297	98.13 314	95.16 304	99.05 269	99.20 247	93.94 307	97.39 290	98.79 293	91.61 284	99.04 286	90.43 324	95.77 263	98.05 308

IB-MVS	95.67 18	96.22 284	95.44 292	98.57 220	99.21 195	96.70 268	98.65 319	97.74 333	96.71 219	97.27 291	98.54 306	86.03 328	99.92 65	98.47 111	86.30 339	99.10 164
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
GG-mvs-BLEND				98.45 233	98.55 304	98.16 208	99.43 164	93.68 352		97.23 292	98.46 307	89.30 305	99.22 267	95.43 274	98.22 180	97.98 313

MVP-Stereo		97.81 211	97.75 192	97.99 273	97.53 320	96.60 272	98.96 293	98.85 287	97.22 180	97.23 292	99.36 234	95.28 151	99.46 214	95.51 272	99.78 75	97.92 317
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
TransMVSNet (Re)		97.15 262	96.58 265	98.86 192	99.12 215	98.85 145	99.49 142	98.91 281	95.48 281	97.16 294	99.80 65	93.38 230	99.11 280	94.16 303	91.73 319	98.62 266

NR-MVSNet		97.97 188	97.61 205	99.02 148	98.87 268	99.26 88	99.47 151	99.42 167	97.63 143	97.08 295	99.50 187	95.07 162	99.13 277	97.86 154	93.59 306	98.68 231

Anonymous20231206		96.22 284	96.03 273	96.79 308	97.31 325	94.14 314	99.63 79	99.08 259	96.17 263	97.04 296	99.06 272	93.94 219	97.76 329	86.96 335	95.06 277	98.47 292

testpf		95.66 292	96.02 275	94.58 316	98.35 310	92.32 327	97.25 344	97.91 330	92.83 318	97.03 297	98.99 277	88.69 311	98.61 307	95.72 267	97.40 232	92.80 343

test_0402		96.64 268	96.24 269	97.85 282	98.85 272	96.43 277	99.44 159	99.26 240	93.52 312	96.98 298	99.52 182	88.52 315	99.20 272	92.58 319	97.50 223	97.93 316

MIMVSNet1		95.51 293	95.04 296	96.92 305	97.38 322	95.60 290	99.52 125	99.50 99	93.65 310	96.97 299	99.17 262	85.28 332	96.56 337	88.36 330	95.55 268	98.60 281

TDRefinement		95.42 295	94.57 300	97.97 274	89.83 346	96.11 285	99.48 147	98.75 296	96.74 217	96.68 300	99.88 14	88.65 313	99.71 179	98.37 118	82.74 342	98.09 306

testus		94.61 301	95.30 294	92.54 323	96.44 328	84.18 339	98.36 328	99.03 267	94.18 304	96.49 301	98.57 305	88.74 309	95.09 342	87.41 333	98.45 169	98.36 301

pmmvs3		94.09 306	93.25 308	96.60 310	94.76 335	94.49 310	98.92 300	98.18 326	89.66 331	96.48 302	98.06 313	86.28 327	97.33 332	89.68 326	87.20 333	97.97 314

DeepMVS_CX				93.34 319	99.29 182	82.27 344		99.22 245	85.15 338	96.33 303	99.05 273	90.97 290	99.73 169	93.57 306	97.77 209	98.01 312

LCM-MVSNet-Re		97.83 207	98.15 142	96.87 306	99.30 179	92.25 328	99.59 92	98.26 322	97.43 161	96.20 304	99.13 265	96.27 126	98.73 306	98.17 130	98.99 137	99.64 97

test20.03		96.12 287	95.96 276	96.63 309	97.44 321	95.45 297	99.51 129	99.38 186	96.55 231	96.16 305	99.25 256	93.76 226	96.17 338	87.35 334	94.22 297	98.27 302

K. test v3		97.10 264	96.79 262	98.01 271	98.72 289	96.33 280	99.87 4	97.05 345	97.59 145	96.16 305	99.80 65	88.71 310	99.04 286	96.69 246	96.55 250	98.65 256

test2356		94.07 307	94.46 302	92.89 321	95.18 333	86.13 337	97.60 342	99.06 264	93.61 311	96.15 307	98.28 311	85.60 331	93.95 344	86.68 337	98.00 203	98.59 282

UnsupCasMVSNet_eth		96.44 272	96.12 271	97.40 298	98.65 297	95.65 289	99.36 195	99.51 85	97.13 186	96.04 308	98.99 277	88.40 317	98.17 311	96.71 244	90.27 322	98.40 297

lessismore_v0				97.79 287	98.69 293	95.44 298		94.75 349		95.71 309	99.87 19	88.69 311	99.32 243	95.89 263	94.93 281	98.62 266

Patchmatch-RL test		95.84 290	95.81 279	95.95 313	95.61 330	90.57 331	98.24 333	98.39 319	95.10 285	95.20 310	98.67 298	94.78 182	97.77 328	96.28 258	90.02 323	99.51 125

ambc				93.06 320	92.68 341	82.36 343	98.47 326	98.73 308		95.09 311	97.41 331	55.55 351	99.10 282	96.42 255	91.32 320	97.71 329

PM-MVS		92.96 309	92.23 311	95.14 315	95.61 330	89.98 333	99.37 189	98.21 324	94.80 288	95.04 312	97.69 321	65.06 347	97.90 325	94.30 298	89.98 324	97.54 333

OpenMVS_ROB	92.34 20	94.38 304	93.70 305	96.41 312	97.38 322	93.17 323	99.06 267	98.75 296	86.58 337	94.84 313	98.26 312	81.53 341	99.32 243	89.01 328	97.87 207	96.76 334

v17		96.42 274	95.81 279	98.25 254	98.94 251	98.80 163	99.76 27	99.28 234	94.57 293	94.18 314	97.71 318	95.23 156	98.16 312	94.86 282	87.73 331	97.80 321

v18		96.42 274	95.80 281	98.26 250	98.95 248	98.82 156	99.76 27	99.28 234	94.58 292	94.12 315	97.70 319	95.22 157	98.16 312	94.83 284	87.80 329	97.79 326

v16		96.39 276	95.76 282	98.26 250	98.96 246	98.81 158	99.76 27	99.28 234	94.57 293	94.10 316	97.70 319	95.04 163	98.16 312	94.70 286	87.77 330	97.80 321

EG-PatchMatch MVS		95.97 289	95.69 283	96.81 307	97.78 317	92.79 325	99.16 245	98.93 276	96.16 264	94.08 317	99.22 259	82.72 339	99.47 213	95.67 270	97.50 223	98.17 305

v11		96.23 283	95.57 289	98.21 260	98.93 256	98.83 149	99.72 39	99.29 227	94.29 303	94.05 318	97.64 324	94.88 176	98.04 320	92.89 315	88.43 327	97.77 327

v15		96.28 278	95.62 284	98.25 254	98.94 251	98.83 149	99.76 27	99.29 227	94.52 297	94.02 319	97.61 326	95.02 164	98.13 316	94.53 288	86.92 334	97.80 321

DI_MVS_plusplus_test		97.45 253	96.79 262	99.44 99	97.76 318	99.04 109	99.21 239	98.61 315	97.74 133	94.01 320	98.83 290	87.38 325	99.83 126	98.63 89	98.90 147	99.44 141

V14		96.26 279	95.60 285	98.26 250	98.94 251	98.83 149	99.76 27	99.29 227	94.49 298	93.96 321	97.66 322	94.99 167	98.13 316	94.41 291	86.90 335	97.80 321

V9		96.25 280	95.58 286	98.26 250	98.94 251	98.83 149	99.75 34	99.29 227	94.45 300	93.96 321	97.62 325	94.94 169	98.14 315	94.40 292	86.87 336	97.81 319

test_normal		97.44 254	96.77 264	99.44 99	97.75 319	99.00 121	99.10 260	98.64 312	97.71 136	93.93 323	98.82 291	87.39 324	99.83 126	98.61 93	98.97 139	99.49 129

v13		96.24 281	95.58 286	98.25 254	98.98 240	98.83 149	99.75 34	99.29 227	94.35 302	93.89 324	97.60 327	95.17 159	98.11 318	94.27 300	86.86 337	97.81 319

v12		96.24 281	95.58 286	98.23 257	98.96 246	98.81 158	99.76 27	99.29 227	94.42 301	93.85 325	97.60 327	95.12 160	98.09 319	94.32 297	86.85 338	97.80 321

pmmvs-eth3d		95.34 297	94.73 298	97.15 299	95.53 332	95.94 287	99.35 199	99.10 257	95.13 283	93.55 326	97.54 330	88.15 321	97.91 324	94.58 287	89.69 325	97.61 330

new-patchmatchnet		94.48 302	94.08 303	95.67 314	95.08 334	92.41 326	99.18 243	99.28 234	94.55 296	93.49 327	97.37 333	87.86 322	97.01 334	91.57 320	88.36 328	97.61 330

UnsupCasMVSNet_bld		93.53 308	92.51 310	96.58 311	97.38 322	93.82 316	98.24 333	99.48 114	91.10 328	93.10 328	96.66 336	74.89 342	98.37 309	94.03 304	87.71 332	97.56 332

Anonymous20231211		90.69 314	89.39 315	94.58 316	94.25 336	88.18 334	99.29 213	99.07 262	82.45 342	92.95 329	97.65 323	63.96 349	97.79 327	89.27 327	85.63 340	97.77 327

test1235678		92.91 310	93.30 307	91.71 327	93.14 340	83.01 341	98.75 312	98.58 316	92.80 319	92.45 330	97.91 315	88.51 316	93.54 345	82.26 341	95.35 270	98.59 282

Gipuma		90.99 313	90.15 314	93.51 318	98.73 287	90.12 332	93.98 348	99.45 150	79.32 343	92.28 331	94.91 340	69.61 344	97.98 323	87.42 332	95.67 265	92.45 345
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CMPMVS	69.68 23	94.13 305	94.90 297	91.84 325	97.24 326	80.01 346	98.52 324	99.48 114	89.01 334	91.99 332	99.67 124	85.67 330	99.13 277	95.44 273	97.03 243	96.39 336
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test12356		91.74 312	92.19 313	90.37 330	91.22 342	82.41 342	98.61 320	98.28 321	90.66 330	91.82 333	97.92 314	84.90 333	92.61 346	81.64 342	94.66 288	96.09 338

PMMVS2		86.87 316	85.37 319	91.35 329	90.21 345	83.80 340	98.89 303	97.45 343	83.13 341	91.67 334	95.03 339	48.49 353	94.70 343	85.86 338	77.62 344	95.54 339

1111		92.30 311	92.21 312	92.55 322	93.30 338	86.27 335	99.15 248	98.74 299	91.94 322	90.85 335	97.82 316	84.18 335	95.21 340	79.65 343	94.27 296	96.19 337

.test1245		83.42 319	86.17 317	75.15 341	93.30 338	86.27 335	99.15 248	98.74 299	91.94 322	90.85 335	97.82 316	84.18 335	95.21 340	79.65 343	39.90 353	43.98 354

LCM-MVSNet		86.80 317	85.22 320	91.53 328	87.81 348	80.96 345	98.23 335	98.99 270	71.05 346	90.13 337	96.51 337	48.45 354	96.88 335	90.51 322	85.30 341	96.76 334

Test4		95.05 298	93.67 306	99.22 131	96.07 329	98.94 134	99.20 241	99.27 239	97.71 136	89.96 338	97.59 329	66.18 346	99.25 261	98.06 142	98.96 140	99.47 135

testmv		87.91 315	87.80 316	88.24 331	87.68 349	77.50 349	99.07 263	97.66 340	89.27 332	86.47 339	96.22 338	68.35 345	92.49 348	76.63 347	88.82 326	94.72 341

testing_2		94.44 303	92.93 309	98.98 153	94.16 337	99.00 121	99.42 171	99.28 234	96.60 228	84.86 340	96.84 335	70.91 343	99.27 255	98.23 127	96.08 259	98.68 231

E-PMN		80.61 322	79.88 323	82.81 337	90.75 344	76.38 351	97.69 340	95.76 348	66.44 350	83.52 341	92.25 344	62.54 350	87.16 353	68.53 351	61.40 347	84.89 352

FPMVS		84.93 318	85.65 318	82.75 338	86.77 350	63.39 356	98.35 330	98.92 278	74.11 345	83.39 342	98.98 280	50.85 352	92.40 349	84.54 339	94.97 279	92.46 344

EMVS		80.02 323	79.22 324	82.43 339	91.19 343	76.40 350	97.55 343	92.49 358	66.36 351	83.01 343	91.27 345	64.63 348	85.79 354	65.82 352	60.65 348	85.08 351

YYNet1		95.36 296	94.51 301	97.92 277	97.89 315	97.10 245	99.10 260	99.23 244	93.26 316	80.77 344	99.04 274	92.81 240	98.02 321	94.30 298	94.18 298	98.64 258

MDA-MVSNet_test_wron		95.45 294	94.60 299	98.01 271	98.16 313	97.21 243	99.11 258	99.24 243	93.49 313	80.73 345	98.98 280	93.02 234	98.18 310	94.22 302	94.45 293	98.64 258

MDA-MVSNet-bldmvs		94.96 299	93.98 304	97.92 277	98.24 312	97.27 238	99.15 248	99.33 214	93.80 309	80.09 346	99.03 275	88.31 318	97.86 326	93.49 308	94.36 294	98.62 266

tmp_tt		82.80 321	81.52 321	86.66 332	66.61 357	68.44 355	92.79 350	97.92 328	68.96 348	80.04 347	99.85 26	85.77 329	96.15 339	97.86 154	43.89 352	95.39 340

no-one		83.04 320	80.12 322	91.79 326	89.44 347	85.65 338	99.32 204	98.32 320	89.06 333	79.79 348	89.16 349	44.86 355	96.67 336	84.33 340	46.78 351	93.05 342

PNet_i23d		79.43 324	77.68 325	84.67 334	86.18 351	71.69 354	96.50 346	93.68 352	75.17 344	71.33 349	91.18 346	32.18 358	90.62 350	78.57 346	74.34 345	91.71 347

MVE	76.82 21	76.91 326	74.31 328	84.70 333	85.38 353	76.05 352	96.88 345	93.17 354	67.39 349	71.28 350	89.01 350	21.66 363	87.69 352	71.74 350	72.29 346	90.35 348
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		77.30 325	74.86 327	84.62 335	75.88 355	77.61 348	97.63 341	93.15 355	88.81 335	64.27 351	89.29 348	36.51 356	83.93 355	75.89 348	52.31 350	92.33 346

wuykxyi23d		74.42 328	71.19 329	84.14 336	76.16 354	74.29 353	96.00 347	92.57 357	69.57 347	63.84 352	87.49 351	21.98 360	88.86 351	75.56 349	57.50 349	89.26 350

PMVS	70.75 22	75.98 327	74.97 326	79.01 340	70.98 356	55.18 357	93.37 349	98.21 324	65.08 352	61.78 353	93.83 342	21.74 362	92.53 347	78.59 345	91.12 321	89.34 349
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		39.01 332	42.50 332	28.53 344	39.17 358	20.91 359	98.75 312	19.17 361	19.83 355	38.57 354	66.67 353	33.16 357	15.42 357	37.50 355	29.66 355	49.26 353

testmvs		39.17 331	43.78 330	25.37 345	36.04 359	16.84 360	98.36 328	26.56 359	20.06 354	38.51 355	67.32 352	29.64 359	15.30 358	37.59 354	39.90 353	43.98 354

wuyk23d		40.18 330	41.29 333	36.84 342	86.18 351	49.12 358	79.73 351	22.81 360	27.64 353	25.46 356	28.45 357	21.98 360	48.89 356	55.80 353	23.56 356	12.51 356

cdsmvs_eth3d_5k		24.64 333	32.85 334	0.00 346	0.00 360	0.00 361	0.00 352	99.51 85	0.00 356	0.00 357	99.56 164	96.58 118	0.00 359	0.00 356	0.00 357	0.00 357

pcd_1.5k_mvsjas		8.27 335	11.03 336	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.27 358	99.01 12	0.00 359	0.00 356	0.00 357	0.00 357

pcd1.5k->3k		40.85 329	43.49 331	32.93 343	98.95 248	0.00 361	0.00 352	99.53 72	0.00 356	0.00 357	0.27 358	95.32 150	0.00 359	0.00 356	97.30 236	98.80 202

sosnet-low-res		0.02 336	0.03 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.27 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

sosnet		0.02 336	0.03 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.27 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

uncertanet		0.02 336	0.03 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.27 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

Regformer		0.02 336	0.03 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.27 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

ab-mvs-re		8.30 334	11.06 335	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	99.58 158	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

uanet		0.02 336	0.03 337	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.27 358	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

GSMVS																99.52 120

test_part3							99.37 189		97.97 108		99.78 78		99.95 33	97.15 213

test_part1								99.48 114				98.96 21			99.84 58	99.83 23

sam_mvs1												94.86 177				99.52 120

sam_mvs												94.72 190

MTGPA								99.47 130

test_post1							99.23 232				65.14 355	94.18 212	99.71 179	97.58 180

test_post											65.99 354	94.65 194	99.73 169

patchmatchnet-post											98.70 297	94.79 181	99.74 161

MTMP								98.88 285

gm-plane-assit					98.54 305	92.96 324			94.65 291		99.15 263		99.64 196	97.56 184

test9_res														97.49 191	99.72 86	99.75 56

agg_prior2														97.21 207	99.73 85	99.75 56

test_prior4						99.56 52	98.99 284

test_prior				99.68 52	99.67 93	99.48 65		99.56 48					99.83 126			99.74 61

新几何2							99.01 282

旧先验1					99.74 67	99.59 49		99.54 62			99.69 115	98.47 61			99.68 96	99.73 66

无先验							98.99 284	99.51 85	96.89 211				99.93 57	97.53 187		99.72 72

原ACMM2							98.95 297

testdata2													99.95 33	96.67 247

segment_acmp												98.96 21

testdata1							98.85 306		98.32 69

plane_prior7					99.29 182	97.03 253

plane_prior6					99.27 187	96.98 257						92.71 245

plane_prior5								99.47 130					99.69 188	97.78 161	97.63 211	98.67 242

plane_prior4											99.61 150

plane_prior2							99.39 182		98.97 22

plane_prior1					99.26 189

plane_prior						96.97 258	99.21 239		98.45 59						97.60 214

n2								0.00 362

nn								0.00 362

door-mid								98.05 327

test11								99.35 198

door								97.92 328

HQP5-MVS						96.83 263

BP-MVS														97.19 209

HQP3-MVS								99.39 180							97.58 216

HQP2-MVS												92.47 260

NP-MVS					99.23 192	96.92 261					99.40 218

ACMMP++_ref															97.19 240

ACMMP++															97.43 231

Test By Simon												98.75 47

High-resolution multi-view benchmark