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.

APDe-MVS		97.82 1	97.73 1	98.08 9	99.15 25	94.82 13	98.81 2	98.30 22	94.76 24	98.30 5	98.90 2	93.77 8	99.68 38	97.93 1	99.69 1	99.75 1

SMA-MVS		97.36 8	97.06 9	98.25 4	99.06 29	95.30 7	97.94 41	98.19 33	90.66 137	99.06 1	98.94 1	93.33 11	99.83 15	96.72 13	99.68 2	99.63 5

CP-MVS		97.02 21	96.81 22	97.64 33	99.33 14	93.54 45	98.80 3	98.28 23	92.99 69	96.45 45	98.30 36	91.90 34	99.85 11	95.61 42	99.68 2	99.54 20

SD-MVS		97.41 7	97.53 2	97.06 57	98.57 52	94.46 17	97.92 43	98.14 41	94.82 21	99.01 2	98.55 10	94.18 5	97.41 278	96.94 5	99.64 4	99.32 44

test_part1								98.26 25				95.31 1			99.63 5	99.63 5

ESAPD		97.57 4	97.29 7	98.41 2	99.28 17	95.74 3	97.50 91	98.26 25	93.81 45	98.10 7	98.53 12	95.31 1	99.87 5	95.19 48	99.63 5	99.63 5

HPM-MVS_fast		96.51 39	96.27 40	97.22 52	99.32 15	92.74 64	98.74 4	98.06 58	90.57 145	96.77 31	98.35 25	90.21 57	99.53 71	94.80 64	99.63 5	99.38 40

SteuartSystems-ACMMP		97.62 3	97.53 2	97.87 14	98.39 60	94.25 23	98.43 16	98.27 24	95.34 9	98.11 6	98.56 8	94.53 3	99.71 30	96.57 17	99.62 8	99.65 3
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS		96.69 34	96.45 36	97.40 41	99.36 12	93.11 56	98.87 1	98.06 58	91.17 124	96.40 46	97.99 51	90.99 47	99.58 56	95.61 42	99.61 9	99.49 27
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
HFP-MVS		97.14 15	96.92 16	97.83 16	99.42 3	94.12 28	98.52 10	98.32 19	93.21 60	97.18 21	98.29 37	92.08 29	99.83 15	95.63 40	99.59 10	99.54 20

region2R		97.07 18	96.84 19	97.77 23	99.46 1	93.79 38	98.52 10	98.24 28	93.19 63	97.14 24	98.34 28	91.59 40	99.87 5	95.46 45	99.59 10	99.64 4

#test#		97.02 21	96.75 26	97.83 16	99.42 3	94.12 28	98.15 29	98.32 19	92.57 83	97.18 21	98.29 37	92.08 29	99.83 15	95.12 52	99.59 10	99.54 20

ACMMPR		97.07 18	96.84 19	97.79 20	99.44 2	93.88 34	98.52 10	98.31 21	93.21 60	97.15 23	98.33 31	91.35 42	99.86 8	95.63 40	99.59 10	99.62 8

mPP-MVS		96.86 27	96.60 29	97.64 33	99.40 5	93.44 48	98.50 13	98.09 50	93.27 59	95.95 61	98.33 31	91.04 46	99.88 3	95.20 47	99.57 14	99.60 11

MP-MVS-pluss		96.70 33	96.27 40	97.98 11	99.23 23	94.71 14	96.96 139	98.06 58	90.67 135	95.55 75	98.78 3	91.07 45	99.86 8	96.58 16	99.55 15	99.38 40
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 31	96.45 36	97.72 26	99.39 7	93.80 37	98.41 17	98.06 58	93.37 55	95.54 76	98.34 28	90.59 53	99.88 3	94.83 62	99.54 16	99.49 27

PHI-MVS		96.77 31	96.46 35	97.71 28	98.40 58	94.07 30	98.21 28	98.45 15	89.86 154	97.11 27	98.01 49	92.52 22	99.69 36	96.03 32	99.53 17	99.36 42

ACMMP_Plus		97.20 11	96.86 18	98.23 5	99.09 26	95.16 9	97.60 83	98.19 33	92.82 78	97.93 11	98.74 4	91.60 39	99.86 8	96.26 21	99.52 18	99.67 2

DeepC-MVS_fast	93.89 2	96.93 26	96.64 28	97.78 21	98.64 47	94.30 21	97.41 99	98.04 65	94.81 22	96.59 38	98.37 24	91.24 43	99.64 47	95.16 50	99.52 18	99.42 35
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS++		97.34 9	96.97 13	98.47 1	99.08 27	96.16 1	97.55 88	97.97 79	95.59 4	96.61 36	97.89 53	92.57 20	99.84 14	95.95 33	99.51 20	99.40 36

APD-MVS		96.95 24	96.60 29	98.01 10	99.03 30	94.93 12	97.72 61	98.10 48	91.50 113	98.01 9	98.32 33	92.33 24	99.58 56	94.85 61	99.51 20	99.53 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
zzz-MVS		97.07 18	96.77 25	97.97 12	99.37 10	94.42 19	97.15 127	98.08 51	95.07 14	96.11 52	98.59 6	90.88 50	99.90 1	96.18 28	99.50 22	99.58 12

MTAPA		97.08 17	96.78 24	97.97 12	99.37 10	94.42 19	97.24 115	98.08 51	95.07 14	96.11 52	98.59 6	90.88 50	99.90 1	96.18 28	99.50 22	99.58 12

CNVR-MVS		97.68 2	97.44 5	98.37 3	98.90 33	95.86 2	97.27 113	98.08 51	95.81 3	97.87 12	98.31 34	94.26 4	99.68 38	97.02 4	99.49 24	99.57 14

DeepPCF-MVS	93.97 1	96.61 37	97.09 8	95.15 136	98.09 81	86.63 255	96.00 228	98.15 39	95.43 7	97.95 10	98.56 8	93.40 10	99.36 92	96.77 12	99.48 25	99.45 31

TSAR-MVS + MP.		97.42 6	97.33 6	97.69 29	99.25 20	94.24 24	98.07 34	97.85 89	93.72 47	98.57 3	98.35 25	93.69 9	99.40 88	97.06 3	99.46 26	99.44 33

MSLP-MVS++		96.94 25	97.06 9	96.59 69	98.72 38	91.86 89	97.67 67	98.49 12	94.66 27	97.24 19	98.41 22	92.31 27	98.94 128	96.61 15	99.46 26	98.96 72

PGM-MVS		96.81 29	96.53 32	97.65 31	99.35 13	93.53 46	97.65 70	98.98 1	92.22 88	97.14 24	98.44 17	91.17 44	99.85 11	94.35 69	99.46 26	99.57 14

CDPH-MVS		95.97 54	95.38 56	97.77 23	98.93 32	94.44 18	96.35 202	97.88 84	86.98 246	96.65 35	97.89 53	91.99 33	99.47 79	92.26 98	99.46 26	99.39 37

DELS-MVS		96.61 37	96.38 38	97.30 45	97.79 100	93.19 54	95.96 229	98.18 36	95.23 11	95.87 62	97.65 73	91.45 41	99.70 35	95.87 34	99.44 30	99.00 70
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
CPTT-MVS		95.57 60	95.19 61	96.70 63	99.27 19	91.48 98	98.33 20	98.11 46	87.79 225	95.17 80	98.03 47	87.09 93	99.61 48	93.51 84	99.42 31	99.02 65

MVS_111021_HR		96.68 36	96.58 31	96.99 59	98.46 54	92.31 74	96.20 217	98.90 2	94.30 35	95.86 63	97.74 67	92.33 24	99.38 91	96.04 31	99.42 31	99.28 49

XVS		97.18 12	96.96 14	97.81 18	99.38 8	94.03 32	98.59 7	98.20 31	94.85 17	96.59 38	98.29 37	91.70 37	99.80 21	95.66 38	99.40 33	99.62 8

X-MVStestdata		91.71 177	89.67 234	97.81 18	99.38 8	94.03 32	98.59 7	98.20 31	94.85 17	96.59 38	32.69 352	91.70 37	99.80 21	95.66 38	99.40 33	99.62 8

MCST-MVS		97.18 12	96.84 19	98.20 6	99.30 16	95.35 5	97.12 129	98.07 56	93.54 53	96.08 54	97.69 69	93.86 7	99.71 30	96.50 18	99.39 35	99.55 18

test9_res														94.81 63	99.38 36	99.45 31

agg_prior2														93.94 75	99.38 36	99.50 25

test_prior3		96.46 41	96.20 43	97.23 50	98.67 41	92.99 58	96.35 202	98.00 72	92.80 79	96.03 55	97.59 80	92.01 31	99.41 86	95.01 56	99.38 36	99.29 46

test_prior2							96.35 202		92.80 79	96.03 55	97.59 80	92.01 31		95.01 56	99.38 36

train_agg		96.30 45	95.83 48	97.72 26	98.70 39	94.19 25	96.41 194	98.02 68	88.58 197	96.03 55	97.56 84	92.73 16	99.59 53	95.04 54	99.37 40	99.39 37

agg_prior3		96.16 49	95.67 50	97.62 36	98.67 41	93.88 34	96.41 194	98.00 72	87.93 222	95.81 65	97.47 88	92.33 24	99.59 53	95.04 54	99.37 40	99.39 37

agg_prior1		96.22 48	95.77 49	97.56 37	98.67 41	93.79 38	96.28 210	98.00 72	88.76 194	95.68 69	97.55 86	92.70 18	99.57 64	95.01 56	99.32 42	99.32 44

3Dnovator	91.36 5	95.19 69	94.44 80	97.44 40	96.56 150	93.36 52	98.65 6	98.36 16	94.12 37	89.25 225	98.06 46	82.20 174	99.77 23	93.41 89	99.32 42	99.18 53

Regformer-1		97.10 16	96.96 14	97.54 38	98.32 66	93.48 47	96.83 152	97.99 77	95.20 12	97.46 15	98.25 40	92.48 23	99.58 56	96.79 11	99.29 44	99.55 18

Regformer-2		97.16 14	96.99 12	97.67 30	98.32 66	93.84 36	96.83 152	98.10 48	95.24 10	97.49 14	98.25 40	92.57 20	99.61 48	96.80 9	99.29 44	99.56 16

CSCG		96.05 51	95.91 47	96.46 79	99.24 21	90.47 131	98.30 21	98.57 11	89.01 179	93.97 98	97.57 82	92.62 19	99.76 24	94.66 67	99.27 46	99.15 56

MVS_0304		96.05 51	95.45 53	97.85 15	97.75 103	94.50 16	96.87 149	97.95 82	95.46 6	95.60 73	98.01 49	80.96 192	99.83 15	97.23 2	99.25 47	99.23 50

APD-MVS_3200maxsize		96.81 29	96.71 27	97.12 56	99.01 31	92.31 74	97.98 40	98.06 58	93.11 66	97.44 16	98.55 10	90.93 48	99.55 66	96.06 30	99.25 47	99.51 24

test12				97.65 31	98.46 54	94.26 22		97.66 104		95.52 77		90.89 49	99.46 80		99.25 47	99.22 51

DeepC-MVS	93.07 3	96.06 50	95.66 51	97.29 46	97.96 88	93.17 55	97.30 112	98.06 58	93.92 40	93.38 106	98.66 5	86.83 95	99.73 26	95.60 44	99.22 50	98.96 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HSP-MVS		97.53 5	97.49 4	97.63 35	99.40 5	93.77 41	98.53 9	97.85 89	95.55 5	98.56 4	97.81 62	93.90 6	99.65 42	96.62 14	99.21 51	99.48 29

CANet		96.39 43	96.02 45	97.50 39	97.62 109	93.38 50	97.02 134	97.96 80	95.42 8	94.86 83	97.81 62	87.38 90	99.82 19	96.88 7	99.20 52	99.29 46

MVS_111021_LR		96.24 47	96.19 44	96.39 81	98.23 75	91.35 103	96.24 215	98.79 4	93.99 39	95.80 66	97.65 73	89.92 61	99.24 98	95.87 34	99.20 52	98.58 95

NCCC		97.30 10	97.03 11	98.11 8	98.77 36	95.06 11	97.34 107	98.04 65	95.96 2	97.09 28	97.88 55	93.18 12	99.71 30	95.84 36	99.17 54	99.56 16

test222					98.24 72	92.21 77	95.33 256	97.60 109	79.22 319	95.25 78	97.84 61	88.80 69			99.15 55	98.72 89

114514_t		93.95 99	93.06 108	96.63 66	99.07 28	91.61 94	97.46 98	97.96 80	77.99 324	93.00 121	97.57 82	86.14 104	99.33 93	89.22 151	99.15 55	98.94 75

Regformer-3		96.85 28	96.80 23	97.01 58	98.34 63	92.02 85	96.96 139	97.76 92	95.01 16	97.08 29	98.42 19	91.71 36	99.54 68	96.80 9	99.13 57	99.48 29

Regformer-4		96.97 23	96.87 17	97.25 49	98.34 63	92.66 67	96.96 139	98.01 70	95.12 13	97.14 24	98.42 19	91.82 35	99.61 48	96.90 6	99.13 57	99.50 25

新几何1				97.32 44	98.60 48	93.59 44		97.75 93	81.58 306	95.75 68	97.85 59	90.04 59	99.67 40	86.50 205	99.13 57	98.69 92

原ACMM1				96.38 82	98.59 49	91.09 114		97.89 83	87.41 234	95.22 79	97.68 70	90.25 55	99.54 68	87.95 175	99.12 60	98.49 105

1121		94.71 82	93.83 85	97.34 43	98.57 52	93.64 43	96.04 224	97.73 95	81.56 308	95.68 69	97.85 59	90.23 56	99.65 42	87.68 182	99.12 60	98.73 88

abl_6		96.40 42	96.21 42	96.98 60	98.89 34	92.20 79	97.89 45	98.03 67	93.34 58	97.22 20	98.42 19	87.93 80	99.72 29	95.10 53	99.07 62	99.02 65

MVSFormer		95.37 62	95.16 62	95.99 100	96.34 162	91.21 106	98.22 26	97.57 112	91.42 117	96.22 49	97.32 90	86.20 102	97.92 239	94.07 71	99.05 63	98.85 83

lupinMVS		94.99 75	94.56 73	96.29 89	96.34 162	91.21 106	95.83 235	96.27 216	88.93 185	96.22 49	96.88 106	86.20 102	98.85 136	95.27 46	99.05 63	98.82 86

旧先验1					98.38 61	93.38 50		97.75 93			98.09 44	92.30 28			99.01 65	99.16 54

testdata				95.46 125	98.18 79	88.90 191		97.66 104	82.73 297	97.03 30	98.07 45	90.06 58	98.85 136	89.67 141	98.98 66	98.64 94

3Dnovator+	91.43 4	95.40 61	94.48 78	98.16 7	96.90 136	95.34 6	98.48 14	97.87 86	94.65 28	88.53 235	98.02 48	83.69 128	99.71 30	93.18 92	98.96 67	99.44 33

CHOSEN 280x420		93.12 124	92.72 119	94.34 179	96.71 144	87.27 238	90.29 326	97.72 98	86.61 256	91.34 154	95.29 187	84.29 124	98.41 174	93.25 91	98.94 68	97.35 156

jason		94.84 80	94.39 81	96.18 94	95.52 191	90.93 119	96.09 221	96.52 209	89.28 166	96.01 59	97.32 90	84.70 119	98.77 143	95.15 51	98.91 69	98.85 83
jason: jason.
QAPM		93.45 115	92.27 133	96.98 60	96.77 142	92.62 68	98.39 18	98.12 43	84.50 281	88.27 241	97.77 65	82.39 170	99.81 20	85.40 224	98.81 70	98.51 101

MG-MVS		95.61 59	95.38 56	96.31 86	98.42 57	90.53 129	96.04 224	97.48 120	93.47 54	95.67 72	98.10 43	89.17 64	99.25 97	91.27 127	98.77 71	99.13 58

API-MVS		94.84 80	94.49 77	95.90 102	97.90 96	92.00 86	97.80 52	97.48 120	89.19 169	94.81 84	96.71 111	88.84 68	99.17 103	88.91 160	98.76 72	96.53 180

CHOSEN 1792x2688		94.15 90	93.51 96	96.06 96	98.27 69	89.38 174	95.18 264	98.48 14	85.60 266	93.76 100	97.11 100	83.15 135	99.61 48	91.33 125	98.72 73	99.19 52

OpenMVS	89.19 12	92.86 135	91.68 148	96.40 80	95.34 199	92.73 65	98.27 23	98.12 43	84.86 276	85.78 274	97.75 66	78.89 239	99.74 25	87.50 189	98.65 74	96.73 173

EPNet		95.20 68	94.56 73	97.14 55	92.80 306	92.68 66	97.85 49	94.87 283	96.64 1	92.46 129	97.80 64	86.23 100	99.65 42	93.72 81	98.62 75	99.10 62
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DP-MVS Recon		95.68 58	95.12 63	97.37 42	99.19 24	94.19 25	97.03 132	98.08 51	88.35 211	95.09 81	97.65 73	89.97 60	99.48 78	92.08 107	98.59 76	98.44 112

Vis-MVSNet		95.23 66	94.81 66	96.51 74	97.18 126	91.58 97	98.26 24	98.12 43	94.38 33	94.90 82	98.15 42	82.28 171	98.92 129	91.45 124	98.58 77	99.01 69
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UGNet		94.04 97	93.28 105	96.31 86	96.85 137	91.19 109	97.88 46	97.68 103	94.40 31	93.00 121	96.18 141	73.39 289	99.61 48	91.72 115	98.46 78	98.13 124
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
CANet_DTU		94.37 85	93.65 91	96.55 70	96.46 158	92.13 81	96.21 216	96.67 204	94.38 33	93.53 103	97.03 103	79.34 221	99.71 30	90.76 130	98.45 79	97.82 139

TAPA-MVS	90.10 7	92.30 158	91.22 172	95.56 116	98.33 65	89.60 159	96.79 159	97.65 106	81.83 303	91.52 149	97.23 95	87.94 79	98.91 130	71.31 324	98.37 80	98.17 123
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
EI-MVSNet-Vis-set		96.51 39	96.47 34	96.63 66	98.24 72	91.20 108	96.89 148	97.73 95	94.74 25	96.49 42	98.49 14	90.88 50	99.58 56	96.44 19	98.32 81	99.13 58

PS-MVSNAJ		95.37 62	95.33 58	95.49 121	97.35 122	90.66 127	95.31 258	97.48 120	93.85 42	96.51 41	95.70 168	88.65 71	99.65 42	94.80 64	98.27 82	96.17 190

LS3D		93.57 112	92.61 123	96.47 77	97.59 112	91.61 94	97.67 67	97.72 98	85.17 271	90.29 180	98.34 28	84.60 120	99.73 26	83.85 250	98.27 82	98.06 129

PVSNet_Blended		94.87 79	94.56 73	95.81 105	98.27 69	89.46 168	95.47 252	98.36 16	88.84 188	94.36 90	96.09 147	88.02 77	99.58 56	93.44 87	98.18 84	98.40 115

MAR-MVS		94.22 88	93.46 98	96.51 74	98.00 83	92.19 80	97.67 67	97.47 123	88.13 220	93.00 121	95.84 155	84.86 118	99.51 75	87.99 174	98.17 85	97.83 138
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
MS-PatchMatch		90.27 236	89.77 230	91.78 279	94.33 247	84.72 276	95.55 247	96.73 196	86.17 261	86.36 270	95.28 189	71.28 296	97.80 250	84.09 243	98.14 86	92.81 307

AdaColmap		94.34 86	93.68 90	96.31 86	98.59 49	91.68 93	96.59 185	97.81 91	89.87 153	92.15 138	97.06 102	83.62 129	99.54 68	89.34 147	98.07 87	97.70 143

MVP-Stereo		90.74 225	90.08 217	92.71 251	93.19 300	88.20 208	95.86 233	96.27 216	86.07 262	84.86 280	94.76 209	77.84 259	97.75 255	83.88 249	98.01 88	92.17 325
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Vis-MVSNet (Re-imp)		94.15 90	93.88 84	94.95 149	97.61 110	87.92 227	98.10 31	95.80 241	92.22 88	93.02 120	97.45 89	84.53 122	97.91 242	88.24 169	97.97 89	99.02 65

EI-MVSNet-UG-set		96.34 44	96.30 39	96.47 77	98.20 76	90.93 119	96.86 150	97.72 98	94.67 26	96.16 51	98.46 15	90.43 54	99.58 56	96.23 22	97.96 90	98.90 79

IS-MVSNet		94.90 77	94.52 76	96.05 97	97.67 106	90.56 128	98.44 15	96.22 220	93.21 60	93.99 96	97.74 67	85.55 109	98.45 167	89.98 135	97.86 91	99.14 57

CNLPA		94.28 87	93.53 95	96.52 71	98.38 61	92.55 70	96.59 185	96.88 191	90.13 150	91.91 142	97.24 94	85.21 112	99.09 118	87.64 185	97.83 92	97.92 132

xiu_mvs_v2_base		95.32 64	95.29 59	95.40 127	97.22 124	90.50 130	95.44 253	97.44 132	93.70 49	96.46 44	96.18 141	88.59 74	99.53 71	94.79 66	97.81 93	96.17 190

PAPM_NR		95.01 71	94.59 72	96.26 91	98.89 34	90.68 126	97.24 115	97.73 95	91.80 107	92.93 126	96.62 125	89.13 65	99.14 107	89.21 152	97.78 94	98.97 71

PVSNet_Blended_VisFu		95.27 65	94.91 65	96.38 82	98.20 76	90.86 121	97.27 113	98.25 27	90.21 148	94.18 94	97.27 92	87.48 88	99.73 26	93.53 83	97.77 95	98.55 96

TSAR-MVS + GP.		96.69 34	96.49 33	97.27 48	98.31 68	93.39 49	96.79 159	96.72 197	94.17 36	97.44 16	97.66 72	92.76 14	99.33 93	96.86 8	97.76 96	99.08 63

ACMMP		96.27 46	95.93 46	97.28 47	99.24 21	92.62 68	98.25 25	98.81 3	92.99 69	94.56 87	98.39 23	88.96 66	99.85 11	94.57 68	97.63 97	99.36 42
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
BH-RMVSNet		92.72 140	91.97 140	94.97 147	97.16 127	87.99 222	96.15 218	95.60 246	90.62 140	91.87 143	97.15 99	78.41 244	98.57 157	83.16 255	97.60 98	98.36 119

PatchMatch-RL		92.90 133	92.02 138	95.56 116	98.19 78	90.80 123	95.27 261	97.18 151	87.96 221	91.86 144	95.68 169	80.44 205	98.99 126	84.01 246	97.54 99	96.89 169

xiu_mvs_v1_base_debu		95.01 71	94.76 67	95.75 108	96.58 147	91.71 90	96.25 212	97.35 143	92.99 69	96.70 32	96.63 122	82.67 160	99.44 83	96.22 23	97.46 100	96.11 195

xiu_mvs_v1_base		95.01 71	94.76 67	95.75 108	96.58 147	91.71 90	96.25 212	97.35 143	92.99 69	96.70 32	96.63 122	82.67 160	99.44 83	96.22 23	97.46 100	96.11 195

xiu_mvs_v1_base_debi		95.01 71	94.76 67	95.75 108	96.58 147	91.71 90	96.25 212	97.35 143	92.99 69	96.70 32	96.63 122	82.67 160	99.44 83	96.22 23	97.46 100	96.11 195

MVS		91.71 177	90.44 204	95.51 119	95.20 211	91.59 96	96.04 224	97.45 129	73.44 336	87.36 257	95.60 172	85.42 110	99.10 115	85.97 215	97.46 100	95.83 209

PVSNet	86.66 18	92.24 161	91.74 147	93.73 210	97.77 102	83.69 286	92.88 305	96.72 197	87.91 223	93.00 121	94.86 203	78.51 242	99.05 124	86.53 203	97.45 104	98.47 108

PAPR		94.18 89	93.42 102	96.48 76	97.64 108	91.42 102	95.55 247	97.71 101	88.99 180	92.34 134	95.82 157	89.19 63	99.11 109	86.14 210	97.38 105	98.90 79

LCM-MVSNet-Re		92.50 146	92.52 128	92.44 256	96.82 141	81.89 297	96.92 146	93.71 311	92.41 86	84.30 284	94.60 216	85.08 114	97.03 291	91.51 121	97.36 106	98.40 115

UA-Net		95.95 55	95.53 52	97.20 54	97.67 106	92.98 60	97.65 70	98.13 42	94.81 22	96.61 36	98.35 25	88.87 67	99.51 75	90.36 134	97.35 107	99.11 61

PCF-MVS	89.48 11	91.56 193	89.95 223	96.36 84	96.60 146	92.52 71	92.51 310	97.26 148	79.41 317	88.90 227	96.56 127	84.04 125	99.55 66	77.01 309	97.30 108	97.01 159
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
BH-untuned		92.94 131	92.62 122	93.92 199	97.22 124	86.16 259	96.40 198	96.25 218	90.06 151	89.79 202	96.17 143	83.19 133	98.35 179	87.19 196	97.27 109	97.24 157

gg-mvs-nofinetune		87.82 277	85.61 284	94.44 174	94.46 242	89.27 184	91.21 321	84.61 349	80.88 311	89.89 197	74.98 341	71.50 294	97.53 269	85.75 219	97.21 110	96.51 181

MVS_Test		94.89 78	94.62 71	95.68 112	96.83 140	89.55 162	96.70 172	97.17 153	91.17 124	95.60 73	96.11 146	87.87 81	98.76 144	93.01 95	97.17 111	98.72 89

PLC	91.00 6	94.11 93	93.43 100	96.13 95	98.58 51	91.15 113	96.69 174	97.39 137	87.29 237	91.37 152	96.71 111	88.39 75	99.52 74	87.33 193	97.13 112	97.73 141
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
1314		92.81 138	92.03 137	95.14 137	95.33 202	89.52 165	96.04 224	97.44 132	87.72 228	86.25 271	95.33 186	83.84 126	98.79 140	89.26 149	97.05 113	97.11 158

test_normal		92.01 167	90.75 190	95.80 106	93.24 295	89.97 141	95.93 231	96.24 219	90.62 140	81.63 300	93.45 271	74.98 276	98.89 133	93.61 82	97.04 114	98.55 96

DI_MVS_plusplus_test		92.01 167	90.77 188	95.73 111	93.34 291	89.78 148	96.14 219	96.18 222	90.58 144	81.80 299	93.50 268	74.95 277	98.90 131	93.51 84	96.94 115	98.51 101

EPNet_dtu		91.71 177	91.28 168	92.99 243	93.76 279	83.71 284	96.69 174	95.28 260	93.15 64	87.02 265	95.95 150	83.37 132	97.38 281	79.46 298	96.84 116	97.88 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Test4		89.48 251	87.50 261	95.44 126	90.76 320	89.72 149	95.78 239	97.09 163	90.28 147	77.67 325	91.74 299	55.42 338	98.08 201	91.92 109	96.83 117	98.52 99

Effi-MVS+		94.93 76	94.45 79	96.36 84	96.61 145	91.47 99	96.41 194	97.41 136	91.02 129	94.50 88	95.92 151	87.53 87	98.78 141	93.89 77	96.81 118	98.84 85

OMC-MVS		95.09 70	94.70 70	96.25 92	98.46 54	91.28 104	96.43 192	97.57 112	92.04 102	94.77 85	97.96 52	87.01 94	99.09 118	91.31 126	96.77 119	98.36 119

test-LLR		91.42 200	91.19 173	92.12 268	94.59 238	80.66 304	94.29 278	92.98 324	91.11 126	90.76 172	92.37 287	79.02 227	98.07 205	88.81 164	96.74 120	97.63 144

test-mter		90.19 240	89.54 237	92.12 268	94.59 238	80.66 304	94.29 278	92.98 324	87.68 229	90.76 172	92.37 287	67.67 312	98.07 205	88.81 164	96.74 120	97.63 144

F-COLMAP		93.58 111	92.98 109	95.37 128	98.40 58	88.98 189	97.18 124	97.29 147	87.75 227	90.49 175	97.10 101	85.21 112	99.50 77	86.70 202	96.72 122	97.63 144

mvs_anonymous		93.82 103	93.74 87	94.06 187	96.44 159	85.41 267	95.81 236	97.05 169	89.85 156	90.09 191	96.36 136	87.44 89	97.75 255	93.97 73	96.69 123	99.02 65

DP-MVS		92.76 139	91.51 162	96.52 71	98.77 36	90.99 115	97.38 105	96.08 225	82.38 299	89.29 222	97.87 56	83.77 127	99.69 36	81.37 281	96.69 123	98.89 81

TESTMET0.1,1		90.06 242	89.42 239	91.97 272	94.41 245	80.62 306	94.29 278	91.97 333	87.28 238	90.44 177	92.47 286	68.79 307	97.67 260	88.50 168	96.60 125	97.61 148

mvs-test1		93.63 109	93.69 89	93.46 227	96.02 177	84.61 277	97.24 115	96.72 197	93.85 42	92.30 135	95.76 163	83.08 141	98.89 133	91.69 118	96.54 126	96.87 170

EPP-MVSNet		95.22 67	95.04 64	95.76 107	97.49 121	89.56 161	98.67 5	97.00 176	90.69 134	94.24 93	97.62 78	89.79 62	98.81 139	93.39 90	96.49 127	98.92 77

PMMVS		92.86 135	92.34 132	94.42 176	94.92 225	86.73 251	94.53 273	96.38 212	84.78 278	94.27 92	95.12 195	83.13 137	98.40 175	91.47 123	96.49 127	98.12 125

Fast-Effi-MVS+		93.46 114	92.75 116	95.59 115	96.77 142	90.03 135	96.81 156	97.13 159	88.19 216	91.30 157	94.27 244	86.21 101	98.63 151	87.66 184	96.46 129	98.12 125

BH-w/o		92.14 166	91.75 145	93.31 233	96.99 135	85.73 262	95.67 241	95.69 243	88.73 195	89.26 224	94.82 207	82.97 151	98.07 205	85.26 226	96.32 130	96.13 194

diffmvs		93.43 116	92.75 116	95.48 123	96.47 157	89.61 158	96.09 221	97.14 157	85.97 263	93.09 119	95.35 185	84.87 117	98.55 159	89.51 145	96.26 131	98.28 121

sss		94.51 84	93.80 86	96.64 64	97.07 130	91.97 87	96.32 206	98.06 58	88.94 184	94.50 88	96.78 108	84.60 120	99.27 96	91.90 110	96.02 132	98.68 93

Patchmatch-test1		91.54 195	90.85 185	93.59 219	95.59 189	84.95 273	94.72 269	95.58 248	90.82 130	92.25 136	93.58 265	75.80 269	97.41 278	83.35 252	95.98 133	98.40 115

CDS-MVSNet		94.14 92	93.54 94	95.93 101	96.18 169	91.46 100	96.33 205	97.04 172	88.97 183	93.56 101	96.51 129	87.55 86	97.89 243	89.80 138	95.95 134	98.44 112
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		91.52 196	90.30 208	95.20 130	95.30 203	89.83 146	93.38 296	96.85 193	86.26 259	88.59 234	95.80 158	84.88 116	98.15 193	75.67 312	95.93 135	97.63 144

LFMVS		93.60 110	92.63 121	96.52 71	98.13 80	91.27 105	97.94 41	93.39 316	90.57 145	96.29 47	98.31 34	69.00 306	99.16 104	94.18 70	95.87 136	99.12 60

CVMVSNet		91.23 208	91.75 145	89.67 307	95.77 185	74.69 327	96.44 190	94.88 280	85.81 264	92.18 137	97.64 76	79.07 224	95.58 319	88.06 172	95.86 137	98.74 87

TAMVS		94.01 98	93.46 98	95.64 113	96.16 171	90.45 132	96.71 169	96.89 190	89.27 167	93.46 105	96.92 105	87.29 91	97.94 235	88.70 166	95.74 138	98.53 98

Effi-MVS+-dtu		93.08 125	93.21 106	92.68 253	96.02 177	83.25 289	97.14 128	96.72 197	93.85 42	91.20 169	93.44 272	83.08 141	98.30 184	91.69 118	95.73 139	96.50 182

HyFIR lowres test		93.66 108	92.92 111	95.87 103	98.24 72	89.88 145	94.58 271	98.49 12	85.06 273	93.78 99	95.78 162	82.86 156	98.67 149	91.77 114	95.71 140	99.07 64

MVS-HIRNet		82.47 305	81.21 306	86.26 318	95.38 197	69.21 338	88.96 334	89.49 342	66.28 340	80.79 305	74.08 343	68.48 309	97.39 280	71.93 322	95.47 141	92.18 324

GG-mvs-BLEND				93.62 217	93.69 281	89.20 185	92.39 313	83.33 350		87.98 246	89.84 306	71.00 298	96.87 295	82.08 269	95.40 142	94.80 271

PatchmatchNet		91.91 171	91.35 164	93.59 219	95.38 197	84.11 281	93.15 301	95.39 253	89.54 160	92.10 139	93.68 261	82.82 158	98.13 194	84.81 230	95.32 143	98.52 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VNet		95.89 56	95.45 53	97.21 53	98.07 82	92.94 61	97.50 91	98.15 39	93.87 41	97.52 13	97.61 79	85.29 111	99.53 71	95.81 37	95.27 144	99.16 54

DSMNet-mixed		86.34 288	86.12 282	87.00 315	89.88 324	70.43 333	94.93 267	90.08 340	77.97 325	85.42 279	92.78 280	74.44 280	93.96 328	74.43 314	95.14 145	96.62 179

alignmvs		95.87 57	95.23 60	97.78 21	97.56 114	95.19 8	97.86 47	97.17 153	94.39 32	96.47 43	96.40 134	85.89 105	99.20 99	96.21 26	95.11 146	98.95 74

MSDG		91.42 200	90.24 212	94.96 148	97.15 128	88.91 190	93.69 290	96.32 214	85.72 265	86.93 266	96.47 131	80.24 209	98.98 127	80.57 291	95.05 147	96.98 160

VDD-MVS		93.82 103	93.08 107	96.02 98	97.88 97	89.96 143	97.72 61	95.85 238	92.43 85	95.86 63	98.44 17	68.42 310	99.39 89	96.31 20	94.85 148	98.71 91

VDDNet		93.05 127	92.07 135	96.02 98	96.84 138	90.39 133	98.08 33	95.85 238	86.22 260	95.79 67	98.46 15	67.59 313	99.19 100	94.92 60	94.85 148	98.47 108

canonicalmvs		96.02 53	95.45 53	97.75 25	97.59 112	95.15 10	98.28 22	97.60 109	94.52 29	96.27 48	96.12 144	87.65 84	99.18 102	96.20 27	94.82 150	98.91 78

Patchmatch-test		89.42 253	87.99 257	93.70 213	95.27 204	85.11 269	88.98 333	94.37 298	81.11 309	87.10 263	93.69 260	82.28 171	97.50 271	74.37 315	94.76 151	98.48 107

cascas		91.20 209	90.08 217	94.58 171	94.97 221	89.16 187	93.65 292	97.59 111	79.90 316	89.40 217	92.92 278	75.36 273	98.36 178	92.14 103	94.75 152	96.23 187

Fast-Effi-MVS+-dtu		92.29 159	91.99 139	93.21 238	95.27 204	85.52 266	97.03 132	96.63 207	92.09 96	89.11 226	95.14 193	80.33 208	98.08 201	87.54 188	94.74 153	96.03 202

WTY-MVS		94.71 82	94.02 82	96.79 62	97.71 105	92.05 83	96.59 185	97.35 143	90.61 142	94.64 86	96.93 104	86.41 99	99.39 89	91.20 129	94.71 154	98.94 75

HY-MVS	89.66 9	93.87 101	92.95 110	96.63 66	97.10 129	92.49 72	95.64 244	96.64 205	89.05 178	93.00 121	95.79 161	85.77 108	99.45 82	89.16 154	94.35 155	97.96 130

MDTV_nov1_ep13			90.76 189		95.22 209	80.33 309	93.03 304	95.28 260	88.14 219	92.84 127	93.83 256	81.34 187	98.08 201	82.86 259	94.34 156

thres200		92.23 162	91.39 163	94.75 161	97.61 110	89.03 188	96.60 184	95.09 270	92.08 101	93.28 111	94.00 251	78.39 245	99.04 125	81.26 289	94.18 157	96.19 189

conf200view11		92.45 149	91.58 155	95.05 141	97.92 92	89.37 175	97.71 63	94.66 285	92.20 90	93.31 108	94.90 199	78.06 254	99.08 120	81.40 277	94.08 158	96.70 175

thres100view900		92.43 151	91.58 155	94.98 146	97.92 92	89.37 175	97.71 63	94.66 285	92.20 90	93.31 108	94.90 199	78.06 254	99.08 120	81.40 277	94.08 158	96.48 183

tfpn200view9		92.38 154	91.52 160	94.95 149	97.85 98	89.29 181	97.41 99	94.88 280	92.19 93	93.27 112	94.46 222	78.17 247	99.08 120	81.40 277	94.08 158	96.48 183

thres400		92.42 152	91.52 160	95.12 139	97.85 98	89.29 181	97.41 99	94.88 280	92.19 93	93.27 112	94.46 222	78.17 247	99.08 120	81.40 277	94.08 158	96.98 160

tfpn111		92.45 149	91.58 155	95.06 140	97.92 92	89.37 175	97.71 63	94.66 285	92.20 90	93.31 108	94.90 199	78.06 254	99.11 109	81.37 281	94.06 162	96.70 175

thres600view7		92.49 148	91.60 154	95.18 131	97.91 95	89.47 166	97.65 70	94.66 285	92.18 95	93.33 107	94.91 198	78.06 254	99.10 115	81.61 270	94.06 162	96.98 160

view600		92.55 142	91.68 148	95.18 131	97.98 84	89.44 170	98.00 36	94.57 290	92.09 96	93.17 115	95.52 177	78.14 250	99.11 109	81.61 270	94.04 164	96.98 160

view800		92.55 142	91.68 148	95.18 131	97.98 84	89.44 170	98.00 36	94.57 290	92.09 96	93.17 115	95.52 177	78.14 250	99.11 109	81.61 270	94.04 164	96.98 160

conf0.05thres1000		92.55 142	91.68 148	95.18 131	97.98 84	89.44 170	98.00 36	94.57 290	92.09 96	93.17 115	95.52 177	78.14 250	99.11 109	81.61 270	94.04 164	96.98 160

tfpn		92.55 142	91.68 148	95.18 131	97.98 84	89.44 170	98.00 36	94.57 290	92.09 96	93.17 115	95.52 177	78.14 250	99.11 109	81.61 270	94.04 164	96.98 160

CR-MVSNet		90.82 221	89.77 230	93.95 195	94.45 243	87.19 242	90.23 327	95.68 244	86.89 251	92.40 130	92.36 290	80.91 196	97.05 289	81.09 290	93.95 168	97.60 149

RPMNet		88.52 266	86.72 278	93.95 195	94.45 243	87.19 242	90.23 327	94.99 275	77.87 326	92.40 130	87.55 331	80.17 211	97.05 289	68.84 328	93.95 168	97.60 149

tfpn1000		91.99 170	91.05 175	94.80 157	97.78 101	89.66 156	97.91 44	92.90 327	88.99 180	91.73 145	94.84 204	78.99 231	98.33 182	82.41 266	93.91 170	96.40 185

tfpn_ndepth		91.88 173	90.96 179	94.62 166	97.73 104	89.93 144	97.75 55	92.92 326	88.93 185	91.73 145	93.80 258	78.91 232	98.49 166	83.02 258	93.86 171	95.45 226

1112_ss		93.37 117	92.42 131	96.21 93	97.05 133	90.99 115	96.31 207	96.72 197	86.87 252	89.83 200	96.69 115	86.51 98	99.14 107	88.12 171	93.67 172	98.50 103

PatchT		88.87 259	87.42 264	93.22 237	94.08 265	85.10 270	89.51 331	94.64 289	81.92 302	92.36 133	88.15 326	80.05 212	97.01 293	72.43 320	93.65 173	97.54 152

COLMAP_ROB	87.81 15	90.40 234	89.28 241	93.79 203	97.95 89	87.13 244	96.92 146	95.89 237	82.83 296	86.88 268	97.18 96	73.77 286	99.29 95	78.44 303	93.62 174	94.95 257
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GA-MVS		91.38 202	90.31 207	94.59 167	94.65 236	87.62 234	94.34 276	96.19 221	90.73 133	90.35 179	93.83 256	71.84 292	97.96 233	87.22 195	93.61 175	98.21 122

TR-MVS		91.48 197	90.59 202	94.16 184	96.40 160	87.33 236	95.67 241	95.34 259	87.68 229	91.46 150	95.52 177	76.77 264	98.35 179	82.85 260	93.61 175	96.79 172

Test_1112_low_res		92.84 137	91.84 143	95.85 104	97.04 134	89.97 141	95.53 249	96.64 205	85.38 267	89.65 210	95.18 191	85.86 106	99.10 115	87.70 180	93.58 177	98.49 105

conf0.01		91.74 175	90.67 194	94.94 152	97.55 115	89.68 150	97.64 74	93.14 318	88.43 202	91.24 162	94.30 234	78.91 232	98.45 167	81.28 283	93.57 178	96.70 175

conf0.002		91.74 175	90.67 194	94.94 152	97.55 115	89.68 150	97.64 74	93.14 318	88.43 202	91.24 162	94.30 234	78.91 232	98.45 167	81.28 283	93.57 178	96.70 175

thresconf0.02		91.69 182	90.67 194	94.75 161	97.55 115	89.68 150	97.64 74	93.14 318	88.43 202	91.24 162	94.30 234	78.91 232	98.45 167	81.28 283	93.57 178	96.11 195

tfpn_n400		91.69 182	90.67 194	94.75 161	97.55 115	89.68 150	97.64 74	93.14 318	88.43 202	91.24 162	94.30 234	78.91 232	98.45 167	81.28 283	93.57 178	96.11 195

tfpnconf		91.69 182	90.67 194	94.75 161	97.55 115	89.68 150	97.64 74	93.14 318	88.43 202	91.24 162	94.30 234	78.91 232	98.45 167	81.28 283	93.57 178	96.11 195

tfpnview11		91.69 182	90.67 194	94.75 161	97.55 115	89.68 150	97.64 74	93.14 318	88.43 202	91.24 162	94.30 234	78.91 232	98.45 167	81.28 283	93.57 178	96.11 195

ab-mvs		93.57 112	92.55 125	96.64 64	97.28 123	91.96 88	95.40 254	97.45 129	89.81 158	93.22 114	96.28 138	79.62 218	99.46 80	90.74 131	93.11 184	98.50 103

AllTest		90.23 238	88.98 245	93.98 191	97.94 90	86.64 252	96.51 189	95.54 249	85.38 267	85.49 277	96.77 109	70.28 302	99.15 105	80.02 294	92.87 185	96.15 192

TestCases				93.98 191	97.94 90	86.64 252		95.54 249	85.38 267	85.49 277	96.77 109	70.28 302	99.15 105	80.02 294	92.87 185	96.15 192

MIMVSNet		88.50 268	86.76 276	93.72 212	94.84 229	87.77 231	91.39 317	94.05 306	86.41 257	87.99 245	92.59 283	63.27 324	95.82 315	77.44 305	92.84 187	97.57 151

EPMVS		90.70 228	89.81 229	93.37 231	94.73 234	84.21 279	93.67 291	88.02 343	89.50 162	92.38 132	93.49 269	77.82 260	97.78 252	86.03 214	92.68 188	98.11 128

XVG-OURS		93.72 107	93.35 103	94.80 157	97.07 130	88.61 194	94.79 268	97.46 125	91.97 105	93.99 96	97.86 58	81.74 183	98.88 135	92.64 97	92.67 189	96.92 168

XVG-OURS-SEG-HR		93.86 102	93.55 93	94.81 156	97.06 132	88.53 196	95.28 259	97.45 129	91.68 110	94.08 95	97.68 70	82.41 169	98.90 131	93.84 79	92.47 190	96.98 160

CLD-MVS		92.98 129	92.53 127	94.32 180	96.12 175	89.20 185	95.28 259	97.47 123	92.66 81	89.90 195	95.62 171	80.58 202	98.40 175	92.73 96	92.40 191	95.38 234
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OPM-MVS		93.28 120	92.76 114	94.82 154	94.63 237	90.77 125	96.65 177	97.18 151	93.72 47	91.68 147	97.26 93	79.33 222	98.63 151	92.13 104	92.28 192	95.07 251

HQP_MVS		93.78 105	93.43 100	94.82 154	96.21 166	89.99 138	97.74 57	97.51 118	94.85 17	91.34 154	96.64 118	81.32 188	98.60 154	93.02 93	92.23 193	95.86 205

plane_prior5								97.51 118					98.60 154	93.02 93	92.23 193	95.86 205

RPSCF		90.75 224	90.86 184	90.42 301	96.84 138	76.29 325	95.61 246	96.34 213	83.89 286	91.38 151	97.87 56	76.45 265	98.78 141	87.16 198	92.23 193	96.20 188

CostFormer		91.18 212	90.70 192	92.62 254	94.84 229	81.76 298	94.09 284	94.43 295	84.15 283	92.72 128	93.77 259	79.43 220	98.20 188	90.70 132	92.18 196	97.90 133

plane_prior						89.99 138	97.24 115		94.06 38						92.16 197

HQP3-MVS								97.39 137							92.10 198

HQP-MVS		93.19 123	92.74 118	94.54 172	95.86 180	89.33 178	96.65 177	97.39 137	93.55 50	90.14 182	95.87 153	80.95 193	98.50 163	92.13 104	92.10 198	95.78 212

tpm2		89.96 243	89.21 242	92.23 262	94.91 227	81.25 301	93.78 288	94.42 296	80.62 314	91.56 148	93.44 272	76.44 266	97.94 235	85.60 221	92.08 200	97.49 153

LPG-MVS_test		92.94 131	92.56 124	94.10 185	96.16 171	88.26 202	97.65 70	97.46 125	91.29 120	90.12 188	97.16 97	79.05 225	98.73 146	92.25 100	91.89 201	95.31 238

LGP-MVS_train				94.10 185	96.16 171	88.26 202		97.46 125	91.29 120	90.12 188	97.16 97	79.05 225	98.73 146	92.25 100	91.89 201	95.31 238

tpmp4_e23		89.58 250	88.59 250	92.54 255	95.16 212	81.53 299	94.11 283	95.09 270	81.66 304	88.60 233	93.44 272	75.11 274	98.33 182	82.45 265	91.72 203	97.75 140

ACMM	89.79 8	92.96 130	92.50 129	94.35 178	96.30 164	88.71 192	97.58 86	97.36 142	91.40 119	90.53 174	96.65 117	79.77 215	98.75 145	91.24 128	91.64 204	95.59 221
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
JIA-IIPM		88.26 274	87.04 275	91.91 273	93.52 285	81.42 300	89.38 332	94.38 297	80.84 312	90.93 171	80.74 338	79.22 223	97.92 239	82.76 261	91.62 205	96.38 186

test_djsdf		93.07 126	92.76 114	94.00 190	93.49 287	88.70 193	98.22 26	97.57 112	91.42 117	90.08 192	95.55 175	82.85 157	97.92 239	94.07 71	91.58 206	95.40 232

jajsoiax		92.42 152	91.89 142	94.03 189	93.33 293	88.50 197	97.73 59	97.53 116	92.00 104	88.85 229	96.50 130	75.62 272	98.11 197	93.88 78	91.56 207	95.48 222

mvs_tets		92.31 157	91.76 144	93.94 198	93.41 289	88.29 200	97.63 81	97.53 116	92.04 102	88.76 230	96.45 132	74.62 279	98.09 200	93.91 76	91.48 208	95.45 226

ACMP	89.59 10	92.62 141	92.14 134	94.05 188	96.40 160	88.20 208	97.36 106	97.25 150	91.52 112	88.30 239	96.64 118	78.46 243	98.72 148	91.86 113	91.48 208	95.23 245
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ADS-MVSNet2		89.45 252	88.59 250	92.03 271	95.86 180	82.26 295	90.93 322	94.32 300	83.23 294	91.28 160	91.81 297	79.01 229	95.99 311	79.52 296	91.39 210	97.84 136

ADS-MVSNet		89.89 245	88.68 249	93.53 223	95.86 180	84.89 274	90.93 322	95.07 272	83.23 294	91.28 160	91.81 297	79.01 229	97.85 245	79.52 296	91.39 210	97.84 136

anonymousdsp		92.16 164	91.55 158	93.97 193	92.58 310	89.55 162	97.51 90	97.42 135	89.42 164	88.40 236	94.84 204	80.66 201	97.88 244	91.87 112	91.28 212	94.48 282

CMPMVS	62.92 21	85.62 294	84.92 289	87.74 312	89.14 327	73.12 331	94.17 281	96.80 195	73.98 334	73.65 330	94.93 197	66.36 317	97.61 265	83.95 248	91.28 212	92.48 314
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pcd1.5k->3k		38.37 329	40.51 330	31.96 342	94.29 249	0.00 361	0.00 352	97.69 102	0.00 356	0.00 357	0.00 358	81.45 186	0.00 359	0.00 356	91.11 214	95.89 204

XVG-ACMP-BASELINE		90.93 218	90.21 215	93.09 240	94.31 248	85.89 260	95.33 256	97.26 148	91.06 128	89.38 218	95.44 183	68.61 308	98.60 154	89.46 146	91.05 215	94.79 273

ACMMP++															91.02 216

PS-MVSNAJss		93.74 106	93.51 96	94.44 174	93.91 274	89.28 183	97.75 55	97.56 115	92.50 84	89.94 194	96.54 128	88.65 71	98.18 191	93.83 80	90.90 217	95.86 205

EG-PatchMatch MVS		87.02 284	85.44 285	91.76 281	92.67 308	85.00 271	96.08 223	96.45 210	83.41 293	79.52 321	93.49 269	57.10 334	97.72 257	79.34 300	90.87 218	92.56 310

test2356		82.77 303	82.14 301	84.65 319	85.77 336	70.36 334	91.22 320	93.69 314	81.58 306	81.82 298	89.00 319	60.63 330	90.77 339	64.74 332	90.80 219	92.82 305

PVSNet_BlendedMVS		94.06 95	93.92 83	94.47 173	98.27 69	89.46 168	96.73 164	98.36 16	90.17 149	94.36 90	95.24 190	88.02 77	99.58 56	93.44 87	90.72 220	94.36 286

DWT-MVSNet_test		90.76 222	89.89 225	93.38 230	95.04 219	83.70 285	95.85 234	94.30 301	88.19 216	90.46 176	92.80 279	73.61 287	98.50 163	88.16 170	90.58 221	97.95 131

EI-MVSNet		93.03 128	92.88 112	93.48 225	95.77 185	86.98 247	96.44 190	97.12 160	90.66 137	91.30 157	97.64 76	86.56 97	98.05 213	89.91 136	90.55 222	95.41 228

MVSTER		93.20 122	92.81 113	94.37 177	96.56 150	89.59 160	97.06 131	97.12 160	91.24 123	91.30 157	95.96 149	82.02 177	98.05 213	93.48 86	90.55 222	95.47 224

FIs		94.09 94	93.70 88	95.27 129	95.70 187	92.03 84	98.10 31	98.68 7	93.36 57	90.39 178	96.70 113	87.63 85	97.94 235	92.25 100	90.50 224	95.84 208

FC-MVSNet-test		93.94 100	93.57 92	95.04 142	95.48 193	91.45 101	98.12 30	98.71 5	93.37 55	90.23 181	96.70 113	87.66 83	97.85 245	91.49 122	90.39 225	95.83 209

ACMMP++_ref															90.30 226

PatchFormer-LS_test		91.68 187	91.18 174	93.19 239	95.24 208	83.63 287	95.53 249	95.44 252	89.82 157	91.37 152	92.58 284	80.85 200	98.52 161	89.65 143	90.16 227	97.42 155

LTVRE_ROB	88.41 13	90.99 216	89.92 224	94.19 182	96.18 169	89.55 162	96.31 207	97.09 163	87.88 224	85.67 275	95.91 152	78.79 240	98.57 157	81.50 275	89.98 228	94.44 284
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
testus		82.63 304	82.15 300	84.07 320	87.31 333	67.67 339	93.18 297	94.29 302	82.47 298	82.14 296	90.69 302	53.01 340	91.94 336	66.30 331	89.96 229	92.62 309

tpmvs		89.83 248	89.15 244	91.89 274	94.92 225	80.30 310	93.11 302	95.46 251	86.28 258	88.08 243	92.65 281	80.44 205	98.52 161	81.47 276	89.92 230	96.84 171

ITE_SJBPF				92.43 257	95.34 199	85.37 268		95.92 230	91.47 114	87.75 248	96.39 135	71.00 298	97.96 233	82.36 267	89.86 231	93.97 293

USDC		88.94 256	87.83 258	92.27 258	94.66 235	84.96 272	93.86 287	95.90 232	87.34 236	83.40 292	95.56 174	67.43 314	98.19 190	82.64 264	89.67 232	93.66 296

ACMH	87.59 16	90.53 232	89.42 239	93.87 200	96.21 166	87.92 227	97.24 115	96.94 185	88.45 201	83.91 290	96.27 139	71.92 291	98.62 153	84.43 238	89.43 233	95.05 256
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		91.44 199	91.32 166	91.79 278	95.15 213	79.20 319	93.42 295	95.37 255	88.55 199	93.49 104	93.67 262	82.49 166	98.27 185	90.41 133	89.34 234	97.90 133

test0.0.03 1		89.37 254	88.70 248	91.41 287	92.47 311	85.63 264	95.22 263	92.70 329	91.11 126	86.91 267	93.65 263	79.02 227	93.19 332	78.00 304	89.18 235	95.41 228

OpenMVS_ROB	81.14 20	84.42 298	82.28 299	90.83 293	90.06 322	84.05 282	95.73 240	94.04 307	73.89 335	80.17 320	91.53 301	59.15 331	97.64 263	66.92 330	89.05 236	90.80 332

GBi-Net		91.35 204	90.27 210	94.59 167	96.51 153	91.18 110	97.50 91	96.93 186	88.82 190	89.35 219	94.51 218	73.87 283	97.29 285	86.12 211	88.82 237	95.31 238

test1		91.35 204	90.27 210	94.59 167	96.51 153	91.18 110	97.50 91	96.93 186	88.82 190	89.35 219	94.51 218	73.87 283	97.29 285	86.12 211	88.82 237	95.31 238

FMVSNet3		91.78 174	90.69 193	95.03 143	96.53 152	92.27 76	97.02 134	96.93 186	89.79 159	89.35 219	94.65 214	77.01 263	97.47 273	86.12 211	88.82 237	95.35 236

tpm cat1		88.36 273	87.21 272	91.81 277	95.13 215	80.55 307	92.58 309	95.70 242	74.97 332	87.45 253	91.96 295	78.01 258	98.17 192	80.39 293	88.74 240	96.72 174

testing_2		87.33 281	85.03 288	94.22 181	87.77 332	89.32 180	94.97 266	97.11 162	89.22 168	71.64 334	88.73 320	55.16 339	97.94 235	91.95 108	88.73 241	95.41 228

test_0402		86.46 287	84.79 290	91.45 285	95.02 220	85.55 265	96.29 209	94.89 279	80.90 310	82.21 294	93.97 252	68.21 311	97.29 285	62.98 334	88.68 242	91.51 329

FMVSNet2		91.31 206	90.08 217	94.99 144	96.51 153	92.21 77	97.41 99	96.95 184	88.82 190	88.62 232	94.75 210	73.87 283	97.42 277	85.20 227	88.55 243	95.35 236

testgi		87.97 275	87.21 272	90.24 303	92.86 304	80.76 303	96.67 176	94.97 276	91.74 108	85.52 276	95.83 156	62.66 326	94.47 326	76.25 310	88.36 244	95.48 222

ACMH+	87.92 14	90.20 239	89.18 243	93.25 235	96.48 156	86.45 256	96.99 137	96.68 202	88.83 189	84.79 281	96.22 140	70.16 304	98.53 160	84.42 239	88.04 245	94.77 275

tpm		90.25 237	89.74 233	91.76 281	93.92 273	79.73 315	93.98 285	93.54 315	88.28 212	91.99 141	93.25 275	77.51 262	97.44 275	87.30 194	87.94 246	98.12 125

pmmvs4		90.93 218	89.85 227	94.17 183	93.34 291	90.79 124	94.60 270	96.02 226	84.62 279	87.45 253	95.15 192	81.88 181	97.45 274	87.70 180	87.87 247	94.27 290

XXY-MVS		92.16 164	91.23 171	94.95 149	94.75 233	90.94 118	97.47 97	97.43 134	89.14 176	88.90 227	96.43 133	79.71 216	98.24 186	89.56 144	87.68 248	95.67 220

pmmvs5		89.86 247	88.87 247	92.82 245	92.86 304	86.23 258	96.26 211	95.39 253	84.24 282	87.12 261	94.51 218	74.27 281	97.36 282	87.61 187	87.57 249	94.86 264

LF4IMVS		87.94 276	87.25 268	89.98 305	92.38 312	80.05 314	94.38 275	95.25 263	87.59 231	84.34 283	94.74 211	64.31 323	97.66 262	84.83 229	87.45 250	92.23 323

FMVSNet1		89.88 246	88.31 254	94.59 167	95.41 195	91.18 110	97.50 91	96.93 186	86.62 255	87.41 255	94.51 218	65.94 320	97.29 285	83.04 257	87.43 251	95.31 238

dp		88.90 258	88.26 256	90.81 294	94.58 240	76.62 324	92.85 306	94.93 278	85.12 272	90.07 193	93.07 276	75.81 268	98.12 196	80.53 292	87.42 252	97.71 142

OurMVSNet-221017-0		90.51 233	90.19 216	91.44 286	93.41 289	81.25 301	96.98 138	96.28 215	91.68 110	86.55 269	96.30 137	74.20 282	97.98 226	88.96 159	87.40 253	95.09 248

TinyColmap		86.82 285	85.35 287	91.21 288	94.91 227	82.99 290	93.94 286	94.02 308	83.58 290	81.56 301	94.68 212	62.34 327	98.13 194	75.78 311	87.35 254	92.52 311

IterMVS		90.15 241	89.67 234	91.61 283	95.48 193	83.72 283	94.33 277	96.12 224	89.99 152	87.31 259	94.15 248	75.78 270	96.27 301	86.97 200	86.89 255	94.83 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
semantic-postprocess				91.82 276	95.52 191	84.20 280		96.15 223	90.61 142	87.39 256	94.27 244	75.63 271	96.44 298	87.34 192	86.88 256	94.82 269

EU-MVSNet		88.72 260	88.90 246	88.20 310	93.15 301	74.21 328	96.63 181	94.22 304	85.18 270	87.32 258	95.97 148	76.16 267	94.98 324	85.27 225	86.17 257	95.41 228

Anonymous20231206		87.09 283	86.14 281	89.93 306	91.22 318	80.35 308	96.11 220	95.35 256	83.57 291	84.16 286	93.02 277	73.54 288	95.61 317	72.16 321	86.14 258	93.84 295

IterMVS-LS		92.29 159	91.94 141	93.34 232	96.25 165	86.97 248	96.57 188	97.05 169	90.67 135	89.50 216	94.80 208	86.59 96	97.64 263	89.91 136	86.11 259	95.40 232
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VPA-MVSNet		93.24 121	92.48 130	95.51 119	95.70 187	92.39 73	97.86 47	98.66 9	92.30 87	92.09 140	95.37 184	80.49 204	98.40 175	93.95 74	85.86 260	95.75 216

nrg030		94.05 96	93.31 104	96.27 90	95.22 209	94.59 15	98.34 19	97.46 125	92.93 76	91.21 168	96.64 118	87.23 92	98.22 187	94.99 59	85.80 261	95.98 203

v1192		91.07 213	90.23 213	93.58 221	93.70 280	87.82 230	96.73 164	97.07 166	87.77 226	89.58 211	94.32 232	80.90 199	97.97 229	86.52 204	85.48 262	94.95 257

v1240		90.70 228	89.85 227	93.23 236	93.51 286	86.80 250	96.61 182	97.02 175	87.16 240	89.58 211	94.31 233	79.55 219	97.98 226	85.52 222	85.44 263	94.90 262

v7		91.47 198	90.73 191	93.68 215	94.13 257	88.16 211	97.09 130	97.05 169	88.38 209	89.80 201	94.52 217	82.21 173	98.01 222	88.00 173	85.42 264	94.87 263

v1144		91.37 203	90.60 201	93.68 215	93.89 275	88.23 205	96.84 151	97.03 174	88.37 210	89.69 208	94.39 227	82.04 176	97.98 226	87.80 178	85.37 265	94.84 265

FMVSNet5		87.29 282	85.79 283	91.78 279	94.80 231	87.28 237	95.49 251	95.28 260	84.09 284	83.85 291	91.82 296	62.95 325	94.17 327	78.48 302	85.34 266	93.91 294

WR-MVS		92.34 155	91.53 159	94.77 160	95.13 215	90.83 122	96.40 198	97.98 78	91.88 106	89.29 222	95.54 176	82.50 165	97.80 250	89.79 139	85.27 267	95.69 219

v1921920		90.85 220	90.03 220	93.29 234	93.55 283	86.96 249	96.74 163	97.04 172	87.36 235	89.52 215	94.34 230	80.23 210	97.97 229	86.27 207	85.21 268	94.94 259

Patchmtry		88.64 264	87.25 268	92.78 249	94.09 263	86.64 252	89.82 330	95.68 244	80.81 313	87.63 252	92.36 290	80.91 196	97.03 291	78.86 301	85.12 269	94.67 277

v6		91.69 182	91.00 178	93.75 207	94.14 256	88.12 215	97.20 121	96.98 177	89.19 169	89.90 195	94.42 226	83.04 145	98.07 205	89.07 155	85.10 270	95.07 251

v1neww		91.70 180	91.01 176	93.75 207	94.19 251	88.14 213	97.20 121	96.98 177	89.18 171	89.87 198	94.44 224	83.10 139	98.06 210	89.06 156	85.09 271	95.06 254

v7new		91.70 180	91.01 176	93.75 207	94.19 251	88.14 213	97.20 121	96.98 177	89.18 171	89.87 198	94.44 224	83.10 139	98.06 210	89.06 156	85.09 271	95.06 254

V42		91.58 192	90.87 183	93.73 210	94.05 268	88.50 197	97.32 110	96.97 180	88.80 193	89.71 206	94.33 231	82.54 164	98.05 213	89.01 158	85.07 273	94.64 279

SixPastTwentyTwo		89.15 255	88.54 252	90.98 290	93.49 287	80.28 311	96.70 172	94.70 284	90.78 131	84.15 287	95.57 173	71.78 293	97.71 258	84.63 234	85.07 273	94.94 259

v2v482		91.59 191	90.85 185	93.80 202	93.87 276	88.17 210	96.94 145	96.88 191	89.54 160	89.53 214	94.90 199	81.70 184	98.02 221	89.25 150	85.04 275	95.20 246

v1141		91.61 188	90.89 180	93.78 204	94.01 269	88.24 204	96.96 139	96.96 181	89.17 173	89.75 204	94.29 240	82.99 149	98.03 218	88.85 162	85.00 276	95.07 251

v1		91.61 188	90.89 180	93.78 204	94.01 269	88.21 207	96.96 139	96.96 181	89.17 173	89.78 203	94.29 240	82.97 151	98.05 213	88.85 162	84.99 277	95.08 249

divwei89l23v2f112		91.61 188	90.89 180	93.78 204	94.01 269	88.22 206	96.96 139	96.96 181	89.17 173	89.75 204	94.28 242	83.02 147	98.03 218	88.86 161	84.98 278	95.08 249

v144192		91.06 214	90.28 209	93.39 229	93.66 282	87.23 241	96.83 152	97.07 166	87.43 233	89.69 208	94.28 242	81.48 185	98.00 225	87.18 197	84.92 279	94.93 261

testpf		80.97 307	81.40 305	79.65 326	91.53 316	72.43 332	73.47 348	89.55 341	78.63 321	80.81 304	89.06 318	61.36 328	91.36 338	83.34 253	84.89 280	75.15 345

CP-MVSNet		91.89 172	91.24 170	93.82 201	95.05 218	88.57 195	97.82 51	98.19 33	91.70 109	88.21 242	95.76 163	81.96 178	97.52 270	87.86 176	84.65 281	95.37 235

tfpnnormal		89.70 249	88.40 253	93.60 218	95.15 213	90.10 134	97.56 87	98.16 38	87.28 238	86.16 272	94.63 215	77.57 261	98.05 213	74.48 313	84.59 282	92.65 308

PS-CasMVS		91.55 194	90.84 187	93.69 214	94.96 222	88.28 201	97.84 50	98.24 28	91.46 115	88.04 244	95.80 158	79.67 217	97.48 272	87.02 199	84.54 283	95.31 238

N_pmnet		78.73 310	78.71 309	78.79 328	92.80 306	46.50 355	94.14 282	43.71 358	78.61 322	80.83 303	91.66 300	74.94 278	96.36 299	67.24 329	84.45 284	93.50 297

WR-MVS_H		92.00 169	91.35 164	93.95 195	95.09 217	89.47 166	98.04 35	98.68 7	91.46 115	88.34 237	94.68 212	85.86 106	97.56 267	85.77 218	84.24 285	94.82 269

v10		91.04 215	90.23 213	93.49 224	94.12 259	88.16 211	97.32 110	97.08 165	88.26 213	88.29 240	94.22 247	82.17 175	97.97 229	86.45 206	84.12 286	94.33 287

UniMVSNet (Re)		93.31 119	92.55 125	95.61 114	95.39 196	93.34 53	97.39 103	98.71 5	93.14 65	90.10 190	94.83 206	87.71 82	98.03 218	91.67 120	83.99 287	95.46 225

UniMVSNet_NR-MVSNet		93.37 117	92.67 120	95.47 124	95.34 199	92.83 62	97.17 125	98.58 10	92.98 74	90.13 186	95.80 158	88.37 76	97.85 245	91.71 116	83.93 288	95.73 218

DU-MVS		92.90 133	92.04 136	95.49 121	94.95 223	92.83 62	97.16 126	98.24 28	93.02 68	90.13 186	95.71 166	83.47 130	97.85 245	91.71 116	83.93 288	95.78 212

v8		91.29 207	90.53 203	93.57 222	94.15 255	88.12 215	97.34 107	97.06 168	88.99 180	88.32 238	94.26 246	83.08 141	98.01 222	87.62 186	83.92 290	94.57 280

V4		90.71 227	90.00 221	92.82 245	93.21 298	87.03 245	97.59 85	97.16 156	88.21 214	87.69 249	93.92 255	80.93 195	98.06 210	87.39 190	83.90 291	93.39 300

v52		90.70 228	90.00 221	92.82 245	93.24 295	87.03 245	97.60 83	97.14 157	88.21 214	87.69 249	93.94 253	80.91 196	98.07 205	87.39 190	83.87 292	93.36 302

v7n		90.76 222	89.86 226	93.45 228	93.54 284	87.60 235	97.70 66	97.37 140	88.85 187	87.65 251	94.08 250	81.08 190	98.10 198	84.68 233	83.79 293	94.66 278

VPNet		92.23 162	91.31 167	94.99 144	95.56 190	90.96 117	97.22 120	97.86 88	92.96 75	90.96 170	96.62 125	75.06 275	98.20 188	91.90 110	83.65 294	95.80 211

NR-MVSNet		92.34 155	91.27 169	95.53 118	94.95 223	93.05 57	97.39 103	98.07 56	92.65 82	84.46 282	95.71 166	85.00 115	97.77 254	89.71 140	83.52 295	95.78 212

v148		90.99 216	90.38 206	92.81 248	93.83 277	85.80 261	96.78 161	96.68 202	89.45 163	88.75 231	93.93 254	82.96 153	97.82 249	87.83 177	83.25 296	94.80 271

Baseline_NR-MVSNet		91.20 209	90.62 200	92.95 244	93.83 277	88.03 221	97.01 136	95.12 269	88.42 208	89.70 207	95.13 194	83.47 130	97.44 275	89.66 142	83.24 297	93.37 301

TranMVSNet+NR-MVSNet		92.50 146	91.63 153	95.14 137	94.76 232	92.07 82	97.53 89	98.11 46	92.90 77	89.56 213	96.12 144	83.16 134	97.60 266	89.30 148	83.20 298	95.75 216

PEN-MVS		91.20 209	90.44 204	93.48 225	94.49 241	87.91 229	97.76 54	98.18 36	91.29 120	87.78 247	95.74 165	80.35 207	97.33 283	85.46 223	82.96 299	95.19 247

new_pmnet		82.89 302	81.12 307	88.18 311	89.63 325	80.18 312	91.77 316	92.57 330	76.79 328	75.56 328	88.23 325	61.22 329	94.48 325	71.43 323	82.92 300	89.87 334

FPMVS		71.27 316	69.85 316	75.50 331	74.64 345	59.03 349	91.30 318	91.50 335	58.80 343	57.92 343	88.28 324	29.98 352	85.53 347	53.43 345	82.84 301	81.95 341

MIMVSNet1		84.93 297	83.05 297	90.56 299	89.56 326	84.84 275	95.40 254	95.35 256	83.91 285	80.38 315	92.21 294	57.23 333	93.34 331	70.69 327	82.75 302	93.50 297

v748		90.34 235	89.54 237	92.75 250	93.25 294	85.71 263	97.61 82	97.17 153	88.54 200	87.20 260	93.54 266	81.02 191	98.01 222	85.73 220	81.80 303	94.52 281

LP		84.13 299	81.85 304	90.97 291	93.20 299	82.12 296	87.68 337	94.27 303	76.80 327	81.93 297	88.52 321	72.97 290	95.95 312	59.53 339	81.73 304	94.84 265

pm-mvs1		90.72 226	89.65 236	93.96 194	94.29 249	89.63 157	97.79 53	96.82 194	89.07 177	86.12 273	95.48 182	78.61 241	97.78 252	86.97 200	81.67 305	94.46 283

DTE-MVSNet		90.56 231	89.75 232	93.01 242	93.95 272	87.25 239	97.64 74	97.65 106	90.74 132	87.12 261	95.68 169	79.97 213	97.00 294	83.33 254	81.66 306	94.78 274

IB-MVS	87.33 17	89.91 244	88.28 255	94.79 159	95.26 207	87.70 233	95.12 265	93.95 309	89.35 165	87.03 264	92.49 285	70.74 300	99.19 100	89.18 153	81.37 307	97.49 153
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
test20.03		86.14 290	85.40 286	88.35 308	90.12 321	80.06 313	95.90 232	95.20 265	88.59 196	81.29 302	93.62 264	71.43 295	92.65 333	71.26 325	81.17 308	92.34 322

test1235678		79.82 309	78.53 310	83.69 321	82.55 341	67.55 340	92.50 311	94.13 305	79.28 318	72.10 333	86.45 334	57.27 332	90.68 340	61.60 337	80.90 309	92.82 305

K. test v3		87.64 279	86.75 277	90.32 302	93.02 303	79.48 317	96.61 182	92.08 332	90.66 137	80.25 319	94.09 249	67.21 316	96.65 297	85.96 216	80.83 310	94.83 267

MDA-MVSNet_test_wron		85.87 292	84.23 294	90.80 296	92.38 312	82.57 291	93.17 299	95.15 267	82.15 300	67.65 336	92.33 293	78.20 246	95.51 320	77.33 306	79.74 311	94.31 289

YYNet1		85.87 292	84.23 294	90.78 297	92.38 312	82.46 293	93.17 299	95.14 268	82.12 301	67.69 335	92.36 290	78.16 249	95.50 321	77.31 307	79.73 312	94.39 285

pmmvs6		87.81 278	86.19 280	92.69 252	91.32 317	86.30 257	97.34 107	96.41 211	80.59 315	84.05 289	94.37 229	67.37 315	97.67 260	84.75 231	79.51 313	94.09 292

Gipuma		67.86 319	65.41 320	75.18 332	92.66 309	73.45 330	66.50 350	94.52 294	53.33 345	57.80 344	66.07 347	30.81 349	89.20 343	48.15 348	78.88 314	62.90 349
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
1111		78.29 311	77.55 311	80.50 324	83.89 337	59.98 347	91.89 314	93.71 311	75.06 330	73.60 331	87.67 329	55.66 336	92.60 334	58.54 341	77.92 315	88.93 336

MDA-MVSNet-bldmvs		85.00 296	82.95 298	91.17 289	93.13 302	83.33 288	94.56 272	95.00 274	84.57 280	65.13 340	92.65 281	70.45 301	95.85 313	73.57 318	77.49 316	94.33 287

Patchmatch-RL test		87.38 280	86.24 279	90.81 294	88.74 328	78.40 322	88.12 336	93.17 317	87.11 241	82.17 295	89.29 317	81.95 179	95.60 318	88.64 167	77.02 317	98.41 114

lessismore_v0				90.45 300	91.96 315	79.09 320		87.19 346		80.32 317	94.39 227	66.31 318	97.55 268	84.00 247	76.84 318	94.70 276

pmmvs-eth3d		86.22 289	84.45 292	91.53 284	88.34 329	87.25 239	94.47 274	95.01 273	83.47 292	79.51 322	89.61 311	69.75 305	95.71 316	83.13 256	76.73 319	91.64 327

PM-MVS		83.48 300	81.86 303	88.31 309	87.83 331	77.59 323	93.43 294	91.75 334	86.91 249	80.63 309	89.91 305	44.42 345	95.84 314	85.17 228	76.73 319	91.50 330

test12356		74.97 313	74.13 314	77.49 329	78.81 343	56.23 351	88.53 335	92.75 328	75.14 329	67.50 337	85.07 335	44.88 344	89.96 341	58.71 340	75.75 321	86.26 337

ambc				86.56 317	83.60 339	70.00 337	85.69 340	94.97 276		80.60 310	88.45 322	37.42 347	96.84 296	82.69 263	75.44 322	92.86 304

v16		88.69 262	87.50 261	92.26 260	94.19 251	88.11 217	96.81 156	95.95 228	87.01 244	80.71 308	89.80 308	83.08 141	96.20 303	84.61 235	75.34 323	92.48 314

v18		88.71 261	87.52 260	92.27 258	94.16 254	88.11 217	96.82 155	95.96 227	87.03 242	80.76 306	89.81 307	83.15 135	96.22 302	84.69 232	75.31 324	92.49 312

v11		88.41 272	87.19 274	92.08 270	94.08 265	87.77 231	96.75 162	95.85 238	86.74 254	80.50 312	89.50 316	82.49 166	96.08 310	83.55 251	75.20 325	92.38 321

v17		88.67 263	87.47 263	92.26 260	94.13 257	88.09 219	96.81 156	95.95 228	87.02 243	80.72 307	89.75 309	83.11 138	96.20 303	84.61 235	75.15 326	92.49 312

v15		88.53 265	87.31 265	92.20 263	94.09 263	88.05 220	96.72 167	95.90 232	87.01 244	80.53 311	89.60 313	83.02 147	96.13 305	84.29 240	74.64 327	92.41 318

v13		88.45 271	87.22 271	92.16 267	94.08 265	87.95 226	96.71 169	95.90 232	86.86 253	80.27 318	89.55 315	82.92 154	96.12 307	84.02 245	74.63 328	92.40 319

V14		88.52 266	87.30 266	92.17 265	94.12 259	87.99 222	96.72 167	95.91 231	86.98 246	80.50 312	89.63 310	83.03 146	96.12 307	84.23 241	74.60 329	92.40 319

V9		88.49 269	87.26 267	92.18 264	94.12 259	87.97 225	96.73 164	95.90 232	86.95 248	80.40 314	89.61 311	82.98 150	96.13 305	84.14 242	74.55 330	92.44 316

TDRefinement		86.53 286	84.76 291	91.85 275	82.23 342	84.25 278	96.38 200	95.35 256	84.97 275	84.09 288	94.94 196	65.76 321	98.34 181	84.60 237	74.52 331	92.97 303

v12		88.46 270	87.23 270	92.17 265	94.10 262	87.99 222	96.71 169	95.90 232	86.91 249	80.34 316	89.58 314	82.92 154	96.11 309	84.09 243	74.50 332	92.42 317

TransMVSNet (Re)		88.94 256	87.56 259	93.08 241	94.35 246	88.45 199	97.73 59	95.23 264	87.47 232	84.26 285	95.29 187	79.86 214	97.33 283	79.44 299	74.44 333	93.45 299

PMVS	53.92 22	58.58 323	55.40 324	68.12 336	51.00 356	48.64 353	78.86 346	87.10 347	46.77 348	35.84 352	74.28 342	8.76 358	86.34 346	42.07 349	73.91 334	69.38 347
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepMVS_CX				74.68 333	90.84 319	64.34 344		81.61 353	65.34 341	67.47 338	88.01 327	48.60 343	80.13 350	62.33 336	73.68 335	79.58 343

UnsupCasMVSNet_eth		85.99 291	84.45 292	90.62 298	89.97 323	82.40 294	93.62 293	97.37 140	89.86 154	78.59 324	92.37 287	65.25 322	95.35 322	82.27 268	70.75 336	94.10 291

new-patchmatchnet		83.18 301	81.87 302	87.11 314	86.88 334	75.99 326	93.70 289	95.18 266	85.02 274	77.30 326	88.40 323	65.99 319	93.88 329	74.19 317	70.18 337	91.47 331

pmmvs3		79.97 308	77.50 312	87.39 313	82.80 340	79.38 318	92.70 308	90.75 338	70.69 338	78.66 323	87.47 332	51.34 342	93.40 330	73.39 319	69.65 338	89.38 335

Anonymous20231211		78.22 312	75.30 313	86.99 316	86.14 335	74.16 329	95.62 245	93.88 310	66.43 339	74.44 329	87.86 328	41.39 346	95.11 323	62.49 335	69.46 339	91.71 326

LCM-MVSNet		72.55 314	69.39 317	82.03 322	70.81 352	65.42 343	90.12 329	94.36 299	55.02 344	65.88 339	81.72 337	24.16 356	89.96 341	74.32 316	68.10 340	90.71 333

testmv		72.22 315	70.02 315	78.82 327	73.06 350	61.75 345	91.24 319	92.31 331	74.45 333	61.06 342	80.51 339	34.21 348	88.63 344	55.31 344	68.07 341	86.06 338

UnsupCasMVSNet_bld		82.13 306	79.46 308	90.14 304	88.00 330	82.47 292	90.89 324	96.62 208	78.94 320	75.61 327	84.40 336	56.63 335	96.31 300	77.30 308	66.77 342	91.63 328

PVSNet_0	82.17 19	85.46 295	83.64 296	90.92 292	95.27 204	79.49 316	90.55 325	95.60 246	83.76 289	83.00 293	89.95 304	71.09 297	97.97 229	82.75 262	60.79 343	95.31 238

PMMVS2		70.19 317	66.92 319	80.01 325	76.35 344	65.67 342	86.22 339	87.58 345	64.83 342	62.38 341	80.29 340	26.78 354	88.49 345	63.79 333	54.07 344	85.88 339

MVE	50.73 23	53.25 326	48.81 329	66.58 337	65.34 353	57.50 350	72.49 349	70.94 356	40.15 351	39.28 351	63.51 348	6.89 361	73.48 354	38.29 350	42.38 345	68.76 348
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PNet_i23d		59.01 322	55.87 323	68.44 335	73.98 348	51.37 352	81.36 344	82.41 351	52.37 346	42.49 349	70.39 346	11.39 357	79.99 351	49.77 347	38.71 346	73.97 346

wuykxyi23d		56.92 324	51.11 328	74.38 334	62.30 354	61.47 346	80.09 345	84.87 348	49.62 347	30.80 353	57.20 351	7.03 359	82.94 348	55.69 343	32.36 347	78.72 344

no-one		68.12 318	63.78 321	81.13 323	74.01 347	70.22 336	87.61 338	90.71 339	72.63 337	53.13 345	71.89 344	30.29 350	91.45 337	61.53 338	32.21 348	81.72 342

E-PMN		53.28 325	52.56 326	55.43 338	74.43 346	47.13 354	83.63 343	76.30 354	42.23 349	42.59 348	62.22 349	28.57 353	74.40 352	31.53 351	31.51 349	44.78 350

ANet_high		63.94 321	59.58 322	77.02 330	61.24 355	66.06 341	85.66 341	87.93 344	78.53 323	42.94 347	71.04 345	25.42 355	80.71 349	52.60 346	30.83 350	84.28 340

EMVS		52.08 327	51.31 327	54.39 339	72.62 351	45.39 356	83.84 342	75.51 355	41.13 350	40.77 350	59.65 350	30.08 351	73.60 353	28.31 352	29.90 351	44.18 351

tmp_tt		51.94 328	53.82 325	46.29 341	33.73 357	45.30 357	78.32 347	67.24 357	18.02 352	50.93 346	87.05 333	52.99 341	53.11 355	70.76 326	25.29 352	40.46 352

wuyk23d		25.11 330	24.57 332	26.74 343	73.98 348	39.89 358	57.88 351	9.80 359	12.27 353	10.39 354	6.97 357	7.03 359	36.44 356	25.43 353	17.39 353	3.89 356

.test1245		65.38 320	69.22 318	53.86 340	83.89 337	59.98 347	91.89 314	93.71 311	75.06 330	73.60 331	87.67 329	55.66 336	92.60 334	58.54 341	2.96 354	9.00 354

testmvs		13.36 332	16.33 333	4.48 345	5.04 358	2.26 360	93.18 297	3.28 360	2.70 354	8.24 355	21.66 353	2.29 363	2.19 357	7.58 354	2.96 354	9.00 354

test123		13.04 333	15.66 334	5.18 344	4.51 359	3.45 359	92.50 311	1.81 361	2.50 355	7.58 356	20.15 354	3.67 362	2.18 358	7.13 355	1.07 356	9.90 353

cdsmvs_eth3d_5k		23.24 331	30.99 331	0.00 346	0.00 360	0.00 361	0.00 352	97.63 108	0.00 356	0.00 357	96.88 106	84.38 123	0.00 359	0.00 356	0.00 357	0.00 357

pcd_1.5k_mvsjas		7.39 335	9.85 336	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	0.00 358	88.65 71	0.00 359	0.00 356	0.00 357	0.00 357

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

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

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

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

ab-mvs-re		8.06 334	10.74 335	0.00 346	0.00 360	0.00 361	0.00 352	0.00 362	0.00 356	0.00 357	96.69 115	0.00 364	0.00 359	0.00 356	0.00 357	0.00 357

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

GSMVS																98.45 110

test_part3							97.50 91		93.81 45		98.53 12		99.87 5	95.19 48

test_part2					99.28 17	95.74 3				98.10 7

sam_mvs1												82.76 159				98.45 110

sam_mvs												81.94 180

MTGPA								98.08 51

test_post1							92.81 307				16.58 356	80.53 203	97.68 259	86.20 209

test_post											17.58 355	81.76 182	98.08 201

patchmatchnet-post											90.45 303	82.65 163	98.10 198

MTMP								82.03 352

gm-plane-assit					93.22 297	78.89 321			84.82 277		93.52 267		98.64 150	87.72 179

TEST9					98.70 39	94.19 25	96.41 194	98.02 68	88.17 218	96.03 55	97.56 84	92.74 15	99.59 53

test_8					98.67 41	94.06 31	96.37 201	98.01 70	88.58 197	95.98 60	97.55 86	92.73 16	99.58 56

agg_prior					98.67 41	93.79 38		98.00 72		95.68 69			99.57 64

test_prior4						93.66 42	96.42 193

test_prior				97.23 50	98.67 41	92.99 58		98.00 72					99.41 86			99.29 46

旧先验2							95.94 230		81.66 304	97.34 18			98.82 138	92.26 98

新几何2							95.79 237

无先验							95.79 237	97.87 86	83.87 288				99.65 42	87.68 182		98.89 81

原ACMM2							95.67 241

testdata2													99.67 40	85.96 216

segment_acmp												92.89 13

testdata1							95.26 262		93.10 67

plane_prior7					96.21 166	89.98 140

plane_prior6					96.10 176	90.00 136						81.32 188

plane_prior4											96.64 118

plane_prior3						90.00 136			94.46 30	91.34 154

plane_prior2							97.74 57		94.85 17

plane_prior1					96.14 174

n2								0.00 362

nn								0.00 362

door-mid								91.06 337

test11								97.88 84

door								91.13 336

HQP5-MVS						89.33 178

HQP-NCC					95.86 180		96.65 177		93.55 50	90.14 182

ACMP_Plane					95.86 180		96.65 177		93.55 50	90.14 182

BP-MVS														92.13 104

HQP4-MVS										90.14 182			98.50 163			95.78 212

HQP2-MVS												80.95 193

NP-MVS					95.99 179	89.81 147					95.87 153

MDTV_nov1_ep13_2view						70.35 335	93.10 303		83.88 287	93.55 102		82.47 168		86.25 208		98.38 118

Test By Simon												88.73 70

High-resolution multi-view benchmark