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.

test_part1								97.45 6				91.93 1			99.02 2	98.67 4

ESAPD		95.32 3	95.38 3	95.17 6	98.55 5	87.22 10	95.99 35	97.45 6	88.25 66	96.40 2	97.60 4	91.93 1	99.62 1	93.18 18	99.02 2	98.67 4

HSP-MVS		95.30 4	95.48 2	94.76 24	98.49 10	86.52 28	96.91 15	96.73 54	91.73 9	96.10 5	96.69 38	89.90 3	99.30 29	94.70 3	98.04 49	98.45 18

DeepPCF-MVS	89.96 1	94.20 25	94.77 9	92.49 88	96.52 66	80.00 172	94.00 167	97.08 29	90.05 26	95.65 7	97.29 12	89.66 4	98.97 61	93.95 8	98.71 19	98.50 11

SD-MVS		94.96 7	95.33 5	93.88 49	97.25 52	86.69 21	96.19 29	97.11 28	90.42 24	96.95 1	97.27 13	89.53 5	96.91 216	94.38 5	98.85 8	98.03 49

CNVR-MVS		95.40 2	95.37 4	95.50 3	98.11 25	88.51 3	95.29 63	96.96 37	92.09 3	95.32 9	97.08 25	89.49 6	99.33 26	95.10 2	98.85 8	98.66 6

APDe-MVS		95.46 1	95.64 1	94.91 12	98.26 20	86.29 38	97.46 2	97.40 9	89.03 47	96.20 4	98.10 1	89.39 7	99.34 23	95.88 1	99.03 1	99.10 1

MCST-MVS		94.45 13	94.20 20	95.19 5	98.46 12	87.50 8	95.00 86	97.12 26	87.13 90	92.51 50	96.30 54	89.24 8	99.34 23	93.46 12	98.62 32	98.73 3

TSAR-MVS + MP.		94.85 8	94.94 7	94.58 31	98.25 21	86.33 34	96.11 31	96.62 65	88.14 70	96.10 5	96.96 28	89.09 9	98.94 65	94.48 4	98.68 24	98.48 13

SteuartSystems-ACMMP		95.20 5	95.32 6	94.85 16	96.99 55	86.33 34	97.33 3	97.30 17	91.38 12	95.39 8	97.46 9	88.98 10	99.40 21	94.12 7	98.89 7	98.82 2
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		95.14 6	94.91 8	95.83 1	98.25 21	89.65 1	95.92 40	96.96 37	91.75 8	94.02 19	96.83 32	88.12 11	99.55 7	93.41 15	98.94 5	98.28 28

agg_prior1		93.29 43	92.97 45	94.26 42	97.38 43	85.92 44	93.92 170	96.72 56	81.96 208	92.16 56	96.23 57	87.85 12	98.97 61	91.95 41	98.55 37	97.90 58

CSCG		93.23 48	93.05 42	93.76 55	98.04 29	84.07 77	96.22 28	97.37 10	84.15 152	90.05 84	95.66 79	87.77 13	99.15 38	89.91 65	98.27 42	98.07 45

NCCC		94.81 9	94.69 10	95.17 6	97.83 32	87.46 9	95.66 51	96.93 40	92.34 2	93.94 20	96.58 45	87.74 14	99.44 20	92.83 22	98.40 39	98.62 7

TEST9					97.53 36	86.49 29	94.07 159	96.78 50	81.61 226	92.77 40	96.20 59	87.71 15	99.12 41

train_agg		93.44 39	93.08 41	94.52 33	97.53 36	86.49 29	94.07 159	96.78 50	81.86 221	92.77 40	96.20 59	87.63 16	99.12 41	92.14 35	98.69 21	97.94 53

test_8					97.49 39	86.30 37	94.02 165	96.76 53	81.86 221	92.70 44	96.20 59	87.63 16	99.02 53

TSAR-MVS + GP.		93.66 35	93.41 36	94.41 38	96.59 63	86.78 18	94.40 127	93.93 217	89.77 32	94.21 15	95.59 81	87.35 18	98.61 85	92.72 23	96.15 80	97.83 61

APD-MVS		94.24 22	94.07 24	94.75 25	98.06 28	86.90 15	95.88 41	96.94 39	85.68 121	95.05 11	97.18 21	87.31 19	99.07 44	91.90 45	98.61 33	98.28 28
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Regformer-2		94.33 19	94.22 17	94.68 27	95.54 101	86.75 20	94.57 116	96.70 58	91.84 6	94.41 12	96.56 47	87.19 20	99.13 40	93.50 11	97.65 57	98.16 38

segment_acmp												87.16 21

Regformer-1		94.22 23	94.13 22	94.51 34	95.54 101	86.36 33	94.57 116	96.44 72	91.69 10	94.32 14	96.56 47	87.05 22	99.03 50	93.35 16	97.65 57	98.15 39

agg_prior3		93.27 44	92.89 47	94.40 39	97.49 39	86.12 41	94.07 159	96.73 54	81.46 229	92.46 52	96.05 67	86.90 23	99.15 38	92.14 35	98.69 21	97.94 53

旧先验1					96.79 59	81.81 127		95.67 123			96.81 33	86.69 24			97.66 56	96.97 88

test_prior3		93.60 36	93.53 35	93.82 51	97.29 48	84.49 64	94.12 151	96.88 43	87.67 81	92.63 45	96.39 52	86.62 25	98.87 67	91.50 49	98.67 26	98.11 43

test_prior2							94.12 151		87.67 81	92.63 45	96.39 52	86.62 25		91.50 49	98.67 26

CDPH-MVS		92.83 52	92.30 54	94.44 35	97.79 33	86.11 42	94.06 162	96.66 62	80.09 240	92.77 40	96.63 42	86.62 25	99.04 49	87.40 90	98.66 28	98.17 37

DELS-MVS		93.43 40	93.25 38	93.97 46	95.42 106	85.04 55	93.06 214	97.13 25	90.74 20	91.84 62	95.09 92	86.32 28	99.21 32	91.22 52	98.45 38	97.65 65
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
HFP-MVS		94.52 11	94.40 12	94.86 14	98.61 3	86.81 16	96.94 10	97.34 11	88.63 56	93.65 23	97.21 18	86.10 29	99.49 16	92.35 29	98.77 14	98.30 26

#test#		94.32 20	94.14 21	94.86 14	98.61 3	86.81 16	96.43 23	97.34 11	87.51 84	93.65 23	97.21 18	86.10 29	99.49 16	91.68 47	98.77 14	98.30 26

MVS_111021_HR		93.45 38	93.31 37	93.84 50	96.99 55	84.84 56	93.24 207	97.24 19	88.76 53	91.60 68	95.85 73	86.07 31	98.66 80	91.91 42	98.16 45	98.03 49

Regformer-4		93.91 30	93.81 28	94.19 44	95.36 107	85.47 51	94.68 108	96.41 75	91.60 11	93.75 22	96.71 36	85.95 32	99.10 43	93.21 17	96.65 72	98.01 51

ACMMP_Plus		94.74 10	94.56 11	95.28 4	98.02 30	87.70 4	95.68 49	97.34 11	88.28 65	95.30 10	97.67 3	85.90 33	99.54 10	93.91 9	98.95 4	98.60 8

Regformer-3		93.68 34	93.64 34	93.81 53	95.36 107	84.61 60	94.68 108	95.83 113	91.27 13	93.60 26	96.71 36	85.75 34	98.86 70	92.87 21	96.65 72	97.96 52

PHI-MVS		93.89 31	93.65 33	94.62 30	96.84 58	86.43 31	96.69 21	97.49 4	85.15 132	93.56 29	96.28 55	85.60 35	99.31 28	92.45 25	98.79 11	98.12 42

MP-MVS-pluss		94.21 24	94.00 26	94.85 16	98.17 24	86.65 24	94.82 97	97.17 24	86.26 111	92.83 38	97.87 2	85.57 36	99.56 3	94.37 6	98.92 6	98.34 23
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		94.25 21	94.07 24	94.77 23	98.47 11	86.31 36	96.71 20	96.98 33	89.04 46	91.98 60	97.19 20	85.43 37	99.56 3	92.06 37	98.79 11	98.44 19

DeepC-MVS_fast	89.43 2	94.04 26	93.79 29	94.80 22	97.48 41	86.78 18	95.65 53	96.89 42	89.40 38	92.81 39	96.97 27	85.37 38	99.24 31	90.87 58	98.69 21	98.38 22
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
region2R		94.43 15	94.27 16	94.92 11	98.65 1	86.67 23	96.92 14	97.23 21	88.60 58	93.58 27	97.27 13	85.22 39	99.54 10	92.21 31	98.74 18	98.56 10

CP-MVS		94.34 18	94.21 19	94.74 26	98.39 16	86.64 25	97.60 1	97.24 19	88.53 60	92.73 43	97.23 16	85.20 40	99.32 27	92.15 34	98.83 10	98.25 34

test12				94.34 40	97.13 53	86.15 40		96.29 81		91.04 75		85.08 41	99.01 55		98.13 46	97.86 59

ACMMPR		94.43 15	94.28 15	94.91 12	98.63 2	86.69 21	96.94 10	97.32 16	88.63 56	93.53 30	97.26 15	85.04 42	99.54 10	92.35 29	98.78 13	98.50 11

XVS		94.45 13	94.32 13	94.85 16	98.54 7	86.60 26	96.93 12	97.19 22	90.66 22	92.85 36	97.16 23	85.02 43	99.49 16	91.99 38	98.56 35	98.47 14

X-MVStestdata		88.31 136	86.13 183	94.85 16	98.54 7	86.60 26	96.93 12	97.19 22	90.66 22	92.85 36	23.41 351	85.02 43	99.49 16	91.99 38	98.56 35	98.47 14

MSLP-MVS++		93.72 33	94.08 23	92.65 82	97.31 46	83.43 91	95.79 44	97.33 14	90.03 27	93.58 27	96.96 28	84.87 45	97.76 139	92.19 33	98.66 28	96.76 94

HPM-MVS		94.02 27	93.88 27	94.43 37	98.39 16	85.78 49	97.25 5	97.07 30	86.90 101	92.62 47	96.80 35	84.85 46	99.17 35	92.43 26	98.65 30	98.33 24

PGM-MVS		93.96 29	93.72 32	94.68 27	98.43 13	86.22 39	95.30 61	97.78 1	87.45 85	93.26 31	97.33 11	84.62 47	99.51 14	90.75 60	98.57 34	98.32 25

EI-MVSNet-Vis-set		93.01 51	92.92 46	93.29 59	95.01 123	83.51 90	94.48 119	95.77 117	90.87 16	92.52 49	96.67 40	84.50 48	99.00 58	91.99 38	94.44 107	97.36 74

MPTG		94.47 12	94.30 14	95.00 9	98.42 14	86.95 12	95.06 82	96.97 34	91.07 14	93.14 34	97.56 6	84.30 49	99.56 3	93.43 13	98.75 16	98.47 14

MTAPA		94.42 17	94.22 17	95.00 9	98.42 14	86.95 12	94.36 137	96.97 34	91.07 14	93.14 34	97.56 6	84.30 49	99.56 3	93.43 13	98.75 16	98.47 14

EI-MVSNet-UG-set		92.74 54	92.62 50	93.12 65	94.86 131	83.20 96	94.40 127	95.74 120	90.71 21	92.05 59	96.60 44	84.00 51	98.99 59	91.55 48	93.63 116	97.17 81

mPP-MVS		93.99 28	93.78 30	94.63 29	98.50 9	85.90 47	96.87 16	96.91 41	88.70 54	91.83 64	97.17 22	83.96 52	99.55 7	91.44 51	98.64 31	98.43 20

APD-MVS_3200maxsize		93.78 32	93.77 31	93.80 54	97.92 31	84.19 75	96.30 26	96.87 45	86.96 97	93.92 21	97.47 8	83.88 53	98.96 64	92.71 24	97.87 52	98.26 33

EPP-MVSNet		91.70 64	91.56 59	92.13 103	95.88 91	80.50 162	97.33 3	95.25 160	86.15 113	89.76 86	95.60 80	83.42 54	98.32 100	87.37 92	93.25 126	97.56 70

UA-Net		92.83 52	92.54 52	93.68 56	96.10 83	84.71 59	95.66 51	96.39 77	91.92 4	93.22 32	96.49 49	83.16 55	98.87 67	84.47 121	95.47 88	97.45 73

UniMVSNet_NR-MVSNet		89.92 96	89.29 95	91.81 118	93.39 181	83.72 83	94.43 125	97.12 26	89.80 31	86.46 136	93.32 142	83.16 55	97.23 193	84.92 114	81.02 274	94.49 183

1121		90.42 85	89.49 89	93.20 62	97.27 50	84.46 67	92.63 226	95.51 138	71.01 317	91.20 73	96.21 58	82.92 57	99.05 46	80.56 177	98.07 48	96.10 112

新几何1				93.10 66	97.30 47	84.35 73		95.56 131	71.09 316	91.26 72	96.24 56	82.87 58	98.86 70	79.19 205	98.10 47	96.07 114

原ACMM1				92.01 104	97.34 45	81.05 146		96.81 48	78.89 250	90.45 79	95.92 70	82.65 59	98.84 75	80.68 175	98.26 43	96.14 108

DeepC-MVS	88.79 3	93.31 42	92.99 44	94.26 42	96.07 85	85.83 48	94.89 92	96.99 32	89.02 48	89.56 87	97.37 10	82.51 60	99.38 22	92.20 32	98.30 41	97.57 69
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS_fast		93.40 41	93.22 39	93.94 48	98.36 18	84.83 57	97.15 7	96.80 49	85.77 118	92.47 51	97.13 24	82.38 61	99.07 44	90.51 62	98.40 39	97.92 57

canonicalmvs		93.27 44	92.75 49	94.85 16	95.70 97	87.66 5	96.33 25	96.41 75	90.00 28	94.09 17	94.60 106	82.33 62	98.62 84	92.40 28	92.86 134	98.27 31

DP-MVS Recon		91.95 59	91.28 62	93.96 47	98.33 19	85.92 44	94.66 111	96.66 62	82.69 197	90.03 85	95.82 74	82.30 63	99.03 50	84.57 120	96.48 77	96.91 90

PAPR		90.02 91	89.27 97	92.29 97	95.78 94	80.95 150	92.68 225	96.22 86	81.91 211	86.66 134	93.75 137	82.23 64	98.44 94	79.40 204	94.79 96	97.48 72

MVS_Test		91.31 69	91.11 64	91.93 110	94.37 149	80.14 166	93.46 196	95.80 115	86.46 107	91.35 71	93.77 135	82.21 65	98.09 122	87.57 88	94.95 95	97.55 71

nrg030		91.08 74	90.39 74	93.17 64	93.07 190	86.91 14	96.41 24	96.26 82	88.30 64	88.37 100	94.85 99	82.19 66	97.64 146	91.09 53	82.95 246	94.96 150

UniMVSNet (Re)		89.80 98	89.07 100	92.01 104	93.60 177	84.52 63	94.78 100	97.47 5	89.26 41	86.44 139	92.32 179	82.10 67	97.39 179	84.81 117	80.84 278	94.12 195

testdata				90.49 161	96.40 67	77.89 242		95.37 153	72.51 306	93.63 25	96.69 38	82.08 68	97.65 144	83.08 137	97.39 60	95.94 118

PAPM_NR		91.22 71	90.78 72	92.52 87	97.60 35	81.46 134	94.37 133	96.24 85	86.39 109	87.41 120	94.80 101	82.06 69	98.48 91	82.80 143	95.37 90	97.61 67

MG-MVS		91.77 61	91.70 58	92.00 106	97.08 54	80.03 171	93.60 191	95.18 167	87.85 76	90.89 76	96.47 50	82.06 69	98.36 95	85.07 112	97.04 65	97.62 66

CANet		93.54 37	93.20 40	94.55 32	95.65 98	85.73 50	94.94 89	96.69 60	91.89 5	90.69 77	95.88 72	81.99 71	99.54 10	93.14 20	97.95 51	98.39 21

FC-MVSNet-test		90.27 87	90.18 79	90.53 153	93.71 174	79.85 176	95.77 45	97.59 2	89.31 40	86.27 142	94.67 103	81.93 72	97.01 208	84.26 126	88.09 203	94.71 165

FIs		90.51 84	90.35 75	90.99 144	93.99 164	80.98 148	95.73 46	97.54 3	89.15 44	86.72 133	94.68 102	81.83 73	97.24 191	85.18 111	88.31 200	94.76 164

ACMMP		93.24 47	92.88 48	94.30 41	98.09 27	85.33 53	96.86 17	97.45 6	88.33 63	90.15 83	97.03 26	81.44 74	99.51 14	90.85 59	95.74 83	98.04 48
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
Effi-MVS+		91.59 66	91.11 64	93.01 71	94.35 152	83.39 93	94.60 113	95.10 169	87.10 91	90.57 78	93.10 153	81.43 75	98.07 124	89.29 69	94.48 104	97.59 68

MVS_111021_LR		92.47 55	92.29 55	92.98 72	95.99 88	84.43 71	93.08 212	96.09 94	88.20 69	91.12 74	95.72 78	81.33 76	97.76 139	91.74 46	97.37 61	96.75 95

mvs_anonymous		89.37 113	89.32 94	89.51 213	93.47 179	74.22 277	91.65 254	94.83 185	82.91 191	85.45 169	93.79 134	81.23 77	96.36 247	86.47 106	94.09 110	97.94 53

PVSNet_BlendedMVS		89.98 92	89.70 86	90.82 147	96.12 78	81.25 139	93.92 170	96.83 46	83.49 168	89.10 92	92.26 184	81.04 78	98.85 73	86.72 103	87.86 205	92.35 274

PVSNet_Blended		90.73 78	90.32 76	91.98 107	96.12 78	81.25 139	92.55 230	96.83 46	82.04 207	89.10 92	92.56 172	81.04 78	98.85 73	86.72 103	95.91 81	95.84 123

alignmvs		93.08 50	92.50 53	94.81 21	95.62 100	87.61 6	95.99 35	96.07 96	89.77 32	94.12 16	94.87 96	80.56 80	98.66 80	92.42 27	93.10 129	98.15 39

abl_6		93.18 49	93.05 42	93.57 58	97.52 38	84.27 74	95.53 56	96.67 61	87.85 76	93.20 33	97.22 17	80.35 81	99.18 34	91.91 42	97.21 62	97.26 75

API-MVS		90.66 79	90.07 81	92.45 90	96.36 69	84.57 62	96.06 33	95.22 166	82.39 199	89.13 91	94.27 116	80.32 82	98.46 92	80.16 186	96.71 70	94.33 188

PVSNet_Blended_VisFu		91.38 68	90.91 69	92.80 78	96.39 68	83.17 97	94.87 95	96.66 62	83.29 174	89.27 90	94.46 108	80.29 83	99.17 35	87.57 88	95.37 90	96.05 116

test222					96.55 65	81.70 128	92.22 240	95.01 172	68.36 323	90.20 82	96.14 64	80.26 84			97.80 54	96.05 116

Test By Simon												80.02 85

IterMVS-LS		88.36 135	87.91 130	89.70 206	93.80 171	78.29 232	93.73 182	95.08 171	85.73 119	84.75 194	91.90 199	79.88 86	96.92 215	83.83 132	82.51 250	93.89 206
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 117	88.86 107	89.80 201	91.84 214	78.30 231	93.70 186	95.01 172	85.73 119	87.15 124	95.28 85	79.87 87	97.21 195	83.81 133	87.36 209	93.88 208

TAPA-MVS	84.62 6	88.16 140	87.01 151	91.62 122	96.64 61	80.65 156	94.39 129	96.21 89	76.38 273	86.19 144	95.44 82	79.75 88	98.08 123	62.75 316	95.29 92	96.13 109
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 110	88.64 109	91.71 120	94.74 133	80.81 154	93.54 192	95.10 169	83.11 177	86.82 132	90.67 243	79.74 89	97.75 142	80.51 179	93.55 117	96.57 99

pcd_1.5k_mvsjas		6.64 334	8.86 335	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	79.70 90	0.00 358	0.00 355	0.00 356	0.00 356

PS-MVSNAJss		89.97 93	89.62 87	91.02 142	91.90 212	80.85 153	95.26 70	95.98 101	86.26 111	86.21 143	94.29 113	79.70 90	97.65 144	88.87 73	88.10 201	94.57 176

PS-MVSNAJ		91.18 72	90.92 68	91.96 108	95.26 113	82.60 118	92.09 245	95.70 122	86.27 110	91.84 62	92.46 173	79.70 90	98.99 59	89.08 70	95.86 82	94.29 189

xiu_mvs_v2_base		91.13 73	90.89 70	91.86 113	94.97 126	82.42 119	92.24 239	95.64 128	86.11 115	91.74 67	93.14 151	79.67 93	98.89 66	89.06 71	95.46 89	94.28 190

WR-MVS_H		87.80 155	87.37 137	89.10 230	93.23 186	78.12 236	95.61 54	97.30 17	87.90 74	83.72 218	92.01 195	79.65 94	96.01 259	76.36 229	80.54 282	93.16 249

EPNet		91.79 60	91.02 67	94.10 45	90.10 289	85.25 54	96.03 34	92.05 250	92.83 1	87.39 122	95.78 75	79.39 95	99.01 55	88.13 81	97.48 59	98.05 47
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
NR-MVSNet		88.58 131	87.47 135	91.93 110	93.04 192	84.16 76	94.77 101	96.25 84	89.05 45	80.04 268	93.29 145	79.02 96	97.05 206	81.71 162	80.05 288	94.59 174

TAMVS		89.21 115	88.29 121	91.96 108	93.71 174	82.62 117	93.30 202	94.19 202	82.22 202	87.78 116	93.94 126	78.83 97	96.95 213	77.70 218	92.98 131	96.32 103

1112_ss		88.42 132	87.33 138	91.72 119	94.92 128	80.98 148	92.97 218	94.54 192	78.16 263	83.82 216	93.88 131	78.78 98	97.91 134	79.45 200	89.41 174	96.26 105

CDS-MVSNet		89.45 107	88.51 111	92.29 97	93.62 176	83.61 88	93.01 215	94.68 189	81.95 209	87.82 115	93.24 147	78.69 99	96.99 209	80.34 182	93.23 127	96.28 104
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 101	88.92 104	91.67 121	95.47 105	81.15 144	92.38 235	94.78 187	83.11 177	89.06 94	94.32 111	78.67 100	96.61 234	81.57 163	90.89 156	97.24 76

CPTT-MVS		91.99 58	91.80 57	92.55 85	98.24 23	81.98 126	96.76 19	96.49 71	81.89 213	90.24 81	96.44 51	78.59 101	98.61 85	89.68 66	97.85 53	97.06 86

IS-MVSNet		91.43 67	91.09 66	92.46 89	95.87 93	81.38 137	96.95 9	93.69 222	89.72 34	89.50 89	95.98 68	78.57 102	97.77 138	83.02 139	96.50 76	98.22 35

OMC-MVS		91.23 70	90.62 73	93.08 67	96.27 71	84.07 77	93.52 193	95.93 104	86.95 98	89.51 88	96.13 65	78.50 103	98.35 97	85.84 107	92.90 133	96.83 93

PCF-MVS	84.11 10	87.74 157	86.08 186	92.70 81	94.02 159	84.43 71	89.27 283	95.87 111	73.62 296	84.43 202	94.33 110	78.48 104	98.86 70	70.27 267	94.45 106	94.81 162
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 137	88.32 119	88.27 254	94.71 136	72.41 297	93.15 208	90.98 283	87.77 78	79.25 274	91.96 196	78.35 105	95.75 270	83.04 138	95.62 84	96.65 97

HY-MVS	83.01 12	89.03 121	87.94 129	92.29 97	94.86 131	82.77 108	92.08 246	94.49 193	81.52 228	86.93 128	92.79 168	78.32 106	98.23 102	79.93 190	90.55 157	95.88 121

diffmvs		89.07 118	88.32 119	91.34 129	93.24 185	79.79 177	92.29 238	94.98 175	80.24 237	87.38 123	92.45 174	78.02 107	97.33 181	83.29 136	92.93 132	96.91 90

MVS		87.44 176	86.10 185	91.44 127	92.61 202	83.62 87	92.63 226	95.66 125	67.26 327	81.47 248	92.15 186	77.95 108	98.22 103	79.71 196	95.48 87	92.47 269

MVSFormer		91.68 65	91.30 61	92.80 78	93.86 168	83.88 80	95.96 38	95.90 108	84.66 141	91.76 65	94.91 94	77.92 109	97.30 183	89.64 67	97.11 63	97.24 76

lupinMVS		90.92 75	90.21 77	93.03 70	93.86 168	83.88 80	92.81 221	93.86 218	79.84 242	91.76 65	94.29 113	77.92 109	98.04 126	90.48 63	97.11 63	97.17 81

Test_1112_low_res		87.65 159	86.51 175	91.08 138	94.94 127	79.28 202	91.77 248	94.30 200	76.04 278	83.51 224	92.37 177	77.86 111	97.73 143	78.69 209	89.13 187	96.22 106

VNet		92.24 57	91.91 56	93.24 61	96.59 63	83.43 91	94.84 96	96.44 72	89.19 43	94.08 18	95.90 71	77.85 112	98.17 105	88.90 72	93.38 123	98.13 41

DU-MVS		89.34 114	88.50 112	91.85 114	93.04 192	83.72 83	94.47 122	96.59 67	89.50 36	86.46 136	93.29 145	77.25 113	97.23 193	84.92 114	81.02 274	94.59 174

Baseline_NR-MVSNet		87.07 188	86.63 173	88.40 251	91.44 226	77.87 243	94.23 142	92.57 240	84.12 153	85.74 154	92.08 191	77.25 113	96.04 256	82.29 152	79.94 291	91.30 292

jason		90.80 76	90.10 80	92.90 75	93.04 192	83.53 89	93.08 212	94.15 204	80.22 238	91.41 70	94.91 94	76.87 115	97.93 133	90.28 64	96.90 66	97.24 76
jason: jason.
PAPM		86.68 196	85.39 201	90.53 153	93.05 191	79.33 201	89.79 276	94.77 188	78.82 252	81.95 244	93.24 147	76.81 116	97.30 183	66.94 294	93.16 128	94.95 157

Vis-MVSNet (Re-imp)		89.59 102	89.44 91	90.03 191	95.74 95	75.85 271	95.61 54	90.80 288	87.66 83	87.83 114	95.40 84	76.79 117	96.46 242	78.37 210	96.73 69	97.80 62

114514_t		89.51 104	88.50 112	92.54 86	98.11 25	81.99 125	95.16 76	96.36 79	70.19 319	85.81 148	95.25 87	76.70 118	98.63 83	82.07 154	96.86 68	97.00 87

PLC	84.53 7	89.06 120	88.03 126	92.15 101	97.27 50	82.69 115	94.29 138	95.44 147	79.71 244	84.01 213	94.18 118	76.68 119	98.75 78	77.28 222	93.41 122	95.02 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 125	87.95 128	91.49 125	92.68 201	83.01 103	94.92 91	96.31 80	89.88 30	85.53 163	93.85 133	76.63 120	96.96 212	81.91 158	79.87 293	94.50 181

MAR-MVS		90.30 86	89.37 93	93.07 69	96.61 62	84.48 66	95.68 49	95.67 123	82.36 201	87.85 109	92.85 162	76.63 120	98.80 76	80.01 187	96.68 71	95.91 119
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
v18		84.97 235	83.76 233	88.60 241	91.36 236	79.41 190	93.82 175	94.04 207	83.00 187	76.61 288	86.60 297	76.19 122	95.43 282	80.39 180	71.79 315	90.96 297

v6		87.98 145	87.25 142	90.16 176	91.36 236	79.39 195	94.37 133	95.27 159	84.48 144	85.78 149	91.51 215	76.15 123	97.46 156	84.46 122	81.88 261	93.62 232

v1neww		87.98 145	87.25 142	90.16 176	91.38 233	79.41 190	94.37 133	95.28 156	84.48 144	85.77 150	91.53 213	76.12 124	97.45 158	84.45 123	81.89 259	93.61 233

v7new		87.98 145	87.25 142	90.16 176	91.38 233	79.41 190	94.37 133	95.28 156	84.48 144	85.77 150	91.53 213	76.12 124	97.45 158	84.45 123	81.89 259	93.61 233

WR-MVS		88.38 133	87.67 132	90.52 159	93.30 184	80.18 164	93.26 205	95.96 103	88.57 59	85.47 168	92.81 166	76.12 124	96.91 216	81.24 165	82.29 252	94.47 186

v16		84.96 236	83.74 235	88.62 239	91.40 231	79.48 184	93.83 173	94.04 207	83.03 184	76.54 289	86.59 298	76.11 127	95.42 283	80.33 183	71.80 314	90.95 299

v17		84.93 238	83.70 237	88.62 239	91.36 236	79.48 184	93.83 173	94.03 209	83.04 183	76.51 290	86.57 299	76.05 128	95.42 283	80.31 185	71.65 316	90.96 297

v8		87.50 175	86.71 162	89.89 196	91.37 235	79.40 194	94.50 118	95.38 151	84.81 138	83.60 222	91.33 223	76.05 128	97.42 169	82.84 142	80.51 285	92.84 259

v148		87.04 189	86.32 179	89.21 226	90.94 264	77.26 259	93.71 185	94.43 195	84.84 137	84.36 206	90.80 241	76.04 130	97.05 206	82.12 153	79.60 294	93.31 244

v15		84.79 241	83.53 242	88.57 245	91.30 247	79.41 190	93.70 186	94.01 210	83.06 180	76.27 291	86.42 303	76.03 131	95.38 285	80.01 187	71.00 319	90.92 300

V14		84.79 241	83.52 243	88.57 245	91.32 243	79.43 189	93.72 184	94.01 210	83.06 180	76.22 292	86.43 300	76.01 132	95.37 286	79.96 189	70.99 320	90.91 301

V9		84.77 243	83.50 244	88.58 242	91.33 241	79.46 186	93.75 180	94.00 213	83.07 179	76.07 297	86.43 300	75.97 133	95.37 286	79.91 192	70.93 322	90.91 301

v1		87.85 150	87.10 145	90.11 187	91.21 250	79.24 206	94.09 155	95.24 161	84.44 148	85.70 155	91.31 226	75.96 134	97.45 158	84.18 127	81.73 266	93.64 229

3Dnovator+	87.14 4	92.42 56	91.37 60	95.55 2	95.63 99	88.73 2	97.07 8	96.77 52	90.84 17	84.02 212	96.62 43	75.95 135	99.34 23	87.77 85	97.68 55	98.59 9

v1141		87.84 151	87.09 146	90.11 187	91.23 248	79.25 204	94.08 157	95.24 161	84.44 148	85.69 157	91.31 226	75.91 136	97.44 165	84.17 128	81.74 265	93.63 231

divwei89l23v2f112		87.84 151	87.09 146	90.10 189	91.23 248	79.24 206	94.09 155	95.24 161	84.44 148	85.70 155	91.31 226	75.91 136	97.44 165	84.17 128	81.73 266	93.64 229

v13		84.72 246	83.44 247	88.58 242	91.31 246	79.52 180	93.77 178	94.00 213	83.03 184	75.85 300	86.38 305	75.84 138	95.35 289	79.83 194	70.95 321	90.87 304

v12		84.74 244	83.46 245	88.58 242	91.32 243	79.50 181	93.75 180	94.01 210	83.06 180	75.98 299	86.41 304	75.82 139	95.36 288	79.87 193	70.89 323	90.89 303

BH-untuned		88.60 130	88.13 125	90.01 193	95.24 120	78.50 226	93.29 203	94.15 204	84.75 139	84.46 200	93.40 139	75.76 140	97.40 176	77.59 219	94.52 103	94.12 195

BH-w/o		87.57 173	87.05 150	89.12 228	94.90 130	77.90 241	92.41 233	93.51 224	82.89 192	83.70 219	91.34 222	75.75 141	97.07 204	75.49 236	93.49 119	92.39 272

cdsmvs_eth3d_5k		22.14 329	29.52 330	0.00 345	0.00 359	0.00 360	0.00 351	95.76 118	0.00 355	0.00 356	94.29 113	75.66 142	0.00 358	0.00 355	0.00 356	0.00 356

CNLPA		89.07 118	87.98 127	92.34 95	96.87 57	84.78 58	94.08 157	93.24 227	81.41 230	84.46 200	95.13 91	75.57 143	96.62 232	77.21 223	93.84 114	95.61 132

v11		84.67 249	83.41 248	88.44 250	91.32 243	79.13 209	93.69 189	93.99 215	82.81 193	76.20 293	86.24 307	75.48 144	95.35 289	79.53 198	71.48 318	90.85 305

CHOSEN 1792x2688		88.84 125	87.69 131	92.30 96	96.14 77	81.42 136	90.01 272	95.86 112	74.52 291	87.41 120	93.94 126	75.46 145	98.36 95	80.36 181	95.53 85	97.12 84

MVS_0304		93.25 46	92.62 50	95.14 8	95.72 96	87.58 7	94.71 107	96.59 67	91.78 7	91.46 69	96.18 63	75.45 146	99.55 7	93.53 10	98.19 44	98.28 28

CP-MVSNet		87.63 163	87.26 141	88.74 235	93.12 189	76.59 265	95.29 63	96.58 69	88.43 61	83.49 225	92.98 160	75.28 147	95.83 266	78.97 206	81.15 271	93.79 214

v7		87.75 156	86.96 152	90.12 182	91.20 251	79.50 181	94.28 139	95.46 141	83.45 169	85.75 152	91.56 212	75.13 148	97.43 167	83.60 134	82.18 254	93.42 242

v10		87.25 182	86.38 176	89.85 197	91.19 253	79.50 181	94.48 119	95.45 145	83.79 159	83.62 221	91.19 231	75.13 148	97.42 169	81.94 157	80.60 280	92.63 265

Vis-MVSNet		91.75 62	91.23 63	93.29 59	95.32 110	83.78 82	96.14 30	95.98 101	89.89 29	90.45 79	96.58 45	75.09 150	98.31 101	84.75 118	96.90 66	97.78 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 124	88.26 123	90.94 146	94.05 158	80.78 155	91.71 251	95.38 151	81.55 227	88.63 96	93.91 130	75.04 151	95.47 281	82.47 148	91.61 141	96.57 99

v1144		87.61 171	86.79 159	90.06 190	91.01 259	79.34 198	93.95 169	95.42 150	83.36 173	85.66 159	91.31 226	74.98 152	97.42 169	83.37 135	82.06 255	93.42 242

V42		87.68 158	86.86 154	90.15 180	90.58 278	80.14 166	94.24 141	95.28 156	83.66 161	85.67 158	91.33 223	74.73 153	97.41 174	84.43 125	81.83 262	92.89 257

XVG-OURS-SEG-HR		89.95 94	89.45 90	91.47 126	94.00 163	81.21 142	91.87 247	96.06 98	85.78 117	88.55 97	95.73 77	74.67 154	97.27 187	88.71 74	89.64 172	95.91 119

v2v482		87.84 151	87.06 149	90.17 175	90.99 260	79.23 208	94.00 167	95.13 168	84.87 136	85.53 163	92.07 193	74.45 155	97.45 158	84.71 119	81.75 264	93.85 212

CLD-MVS		89.47 106	88.90 105	91.18 134	94.22 153	82.07 124	92.13 243	96.09 94	87.90 74	85.37 179	92.45 174	74.38 156	97.56 149	87.15 95	90.43 158	93.93 204
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 159	86.85 155	90.03 191	92.14 208	80.60 159	93.76 179	95.23 164	82.94 189	84.60 196	94.02 122	74.27 157	95.49 280	81.04 167	83.68 239	94.01 203

HQP_MVS		90.60 83	90.19 78	91.82 116	94.70 137	82.73 112	95.85 42	96.22 86	90.81 18	86.91 129	94.86 97	74.23 158	98.12 109	88.15 79	89.99 165	94.63 170

plane_prior6					94.52 143	82.75 109						74.23 158

v144192		87.19 186	86.35 177	89.74 202	90.64 277	78.24 234	93.92 170	95.43 148	81.93 210	85.51 165	91.05 238	74.21 160	97.45 158	82.86 141	81.56 268	93.53 237

VPA-MVSNet		89.62 100	88.96 102	91.60 123	93.86 168	82.89 107	95.46 57	97.33 14	87.91 73	88.43 99	93.31 143	74.17 161	97.40 176	87.32 93	82.86 248	94.52 179

ab-mvs		89.41 110	88.35 116	92.60 83	95.15 121	82.65 116	92.20 241	95.60 129	83.97 154	88.55 97	93.70 138	74.16 162	98.21 104	82.46 149	89.37 175	96.94 89

1314		87.51 174	86.57 174	90.34 172	92.42 204	79.74 179	92.63 226	95.35 155	78.35 259	80.14 266	91.62 208	74.05 163	97.15 197	81.05 166	93.53 118	94.12 195

test_djsdf		89.03 121	88.64 109	90.21 174	90.74 273	79.28 202	95.96 38	95.90 108	84.66 141	85.33 181	92.94 161	74.02 164	97.30 183	89.64 67	88.53 193	94.05 200

AdaColmap		89.89 97	89.07 100	92.37 94	97.41 42	83.03 101	94.42 126	95.92 105	82.81 193	86.34 141	94.65 104	73.89 165	99.02 53	80.69 174	95.51 86	95.05 144

HyFIR lowres test		88.09 143	86.81 157	91.93 110	96.00 87	80.63 157	90.01 272	95.79 116	73.42 297	87.68 118	92.10 190	73.86 166	97.96 130	80.75 173	91.70 140	97.19 80

HQP2-MVS												73.83 167

HQP-MVS		89.80 98	89.28 96	91.34 129	94.17 154	81.56 129	94.39 129	96.04 99	88.81 50	85.43 172	93.97 125	73.83 167	97.96 130	87.11 97	89.77 170	94.50 181

3Dnovator	86.66 5	91.73 63	90.82 71	94.44 35	94.59 141	86.37 32	97.18 6	97.02 31	89.20 42	84.31 208	96.66 41	73.74 169	99.17 35	86.74 100	97.96 50	97.79 63

EPNet_dtu		86.49 201	85.94 190	88.14 259	90.24 287	72.82 289	94.11 153	92.20 246	86.66 105	79.42 273	92.36 178	73.52 170	95.81 268	71.26 262	93.66 115	95.80 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 251	83.06 252	88.54 247	91.72 218	78.44 227	95.18 74	92.82 234	82.73 195	79.67 270	92.12 187	73.49 171	95.96 261	71.10 266	68.73 330	91.21 293

Effi-MVS+-dtu		88.65 129	88.35 116	89.54 210	93.33 182	76.39 266	94.47 122	94.36 197	87.70 79	85.43 172	89.56 265	73.45 172	97.26 189	85.57 109	91.28 143	94.97 147

mvs-test1		89.45 107	89.14 98	90.38 169	93.33 182	77.63 251	94.95 88	94.36 197	87.70 79	87.10 126	92.81 166	73.45 172	98.03 127	85.57 109	93.04 130	95.48 134

PEN-MVS		86.80 192	86.27 181	88.40 251	92.32 206	75.71 272	95.18 74	96.38 78	87.97 71	82.82 232	93.15 150	73.39 174	95.92 262	76.15 233	79.03 296	93.59 235

v1192		87.25 182	86.33 178	90.00 194	90.76 272	79.04 210	93.80 176	95.48 140	82.57 198	85.48 167	91.18 232	73.38 175	97.42 169	82.30 151	82.06 255	93.53 237

QAPM		89.51 104	88.15 124	93.59 57	94.92 128	84.58 61	96.82 18	96.70 58	78.43 258	83.41 226	96.19 62	73.18 176	99.30 29	77.11 225	96.54 75	96.89 92

tpmrst		85.35 227	84.99 206	86.43 289	90.88 269	67.88 320	88.71 290	91.43 271	80.13 239	86.08 146	88.80 272	73.05 177	96.02 258	82.48 147	83.40 245	95.40 137

PS-CasMVS		87.32 179	86.88 153	88.63 238	92.99 195	76.33 268	95.33 58	96.61 66	88.22 68	83.30 228	93.07 154	73.03 178	95.79 269	78.36 211	81.00 276	93.75 220

DTE-MVSNet		86.11 205	85.48 199	87.98 261	91.65 222	74.92 275	94.93 90	95.75 119	87.36 86	82.26 237	93.04 155	72.85 179	95.82 267	74.04 249	77.46 301	93.20 247

MVSTER		88.84 125	88.29 121	90.51 160	92.95 196	80.44 163	93.73 182	95.01 172	84.66 141	87.15 124	93.12 152	72.79 180	97.21 195	87.86 84	87.36 209	93.87 209

pcd1.5k->3k		37.02 327	38.84 328	31.53 340	92.33 205	0.00 360	0.00 351	96.13 92	0.00 355	0.00 356	0.00 357	72.70 181	0.00 358	0.00 355	88.43 197	94.60 173

v1921920		86.97 190	86.06 187	89.69 207	90.53 282	78.11 237	93.80 176	95.43 148	81.90 212	85.33 181	91.05 238	72.66 182	97.41 174	82.05 155	81.80 263	93.53 237

DP-MVS		87.25 182	85.36 202	92.90 75	97.65 34	83.24 95	94.81 98	92.00 252	74.99 286	81.92 245	95.00 93	72.66 182	99.05 46	66.92 296	92.33 138	96.40 101

v7n		86.81 191	85.76 193	89.95 195	90.72 274	79.25 204	95.07 80	95.92 105	84.45 147	82.29 236	90.86 240	72.60 184	97.53 151	79.42 203	80.52 284	93.08 254

v748		86.27 203	85.28 203	89.25 225	90.26 286	77.58 258	94.89 92	95.50 139	84.28 151	81.41 250	90.46 251	72.57 185	97.32 182	79.81 195	78.36 297	92.84 259

OPM-MVS		90.12 89	89.56 88	91.82 116	93.14 188	83.90 79	94.16 150	95.74 120	88.96 49	87.86 108	95.43 83	72.48 186	97.91 134	88.10 82	90.18 164	93.65 228

LS3D		87.89 149	86.32 179	92.59 84	96.07 85	82.92 106	95.23 71	94.92 180	75.66 280	82.89 231	95.98 68	72.48 186	99.21 32	68.43 287	95.23 94	95.64 131

pm-mvs1		86.61 197	85.54 195	89.82 198	91.44 226	80.18 164	95.28 69	94.85 183	83.84 156	81.66 247	92.62 171	72.45 188	96.48 240	79.67 197	78.06 298	92.82 261

PMMVS		85.71 223	84.96 209	87.95 262	88.90 304	77.09 260	88.68 291	90.06 300	72.32 307	86.47 135	90.76 242	72.15 189	94.40 301	81.78 161	93.49 119	92.36 273

PatchmatchNet		85.85 212	84.70 217	89.29 224	91.76 217	75.54 273	88.49 293	91.30 273	81.63 225	85.05 184	88.70 274	71.71 190	96.24 251	74.61 246	89.05 188	96.08 113
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 191				96.12 110

V4		86.50 199	85.54 195	89.39 217	89.13 300	78.99 211	94.73 102	95.54 134	83.59 162	82.10 240	90.61 245	71.60 192	97.45 158	82.52 145	80.01 289	91.74 283

v52		86.50 199	85.53 198	89.39 217	89.17 299	78.99 211	94.72 105	95.54 134	83.59 162	82.10 240	90.60 246	71.59 193	97.45 158	82.52 145	79.99 290	91.73 284

patchmatchnet-post											83.76 316	71.53 194	96.48 240

v1240		86.78 193	85.85 191	89.56 209	90.45 283	77.79 245	93.61 190	95.37 153	81.65 223	85.43 172	91.15 234	71.50 195	97.43 167	81.47 164	82.05 257	93.47 241

anonymousdsp		87.84 151	87.09 146	90.12 182	89.13 300	80.54 160	94.67 110	95.55 132	82.05 205	83.82 216	92.12 187	71.47 196	97.15 197	87.15 95	87.80 206	92.67 263

Patchmatch-test		81.37 278	79.30 282	87.58 268	90.92 266	74.16 279	80.99 333	87.68 329	70.52 318	76.63 287	88.81 271	71.21 197	92.76 318	60.01 324	86.93 215	95.83 124

F-COLMAP		87.95 148	86.80 158	91.40 128	96.35 70	80.88 152	94.73 102	95.45 145	79.65 245	82.04 243	94.61 105	71.13 198	98.50 90	76.24 232	91.05 150	94.80 163

pmmvs4		85.43 225	83.86 232	90.16 176	90.02 292	82.97 105	90.27 267	92.67 238	75.93 279	80.73 257	91.74 203	71.05 199	95.73 271	78.85 207	83.46 243	91.78 282

CR-MVSNet		85.35 227	83.76 233	90.12 182	90.58 278	79.34 198	85.24 316	91.96 256	78.27 260	85.55 161	87.87 288	71.03 200	95.61 272	73.96 251	89.36 176	95.40 137

Patchmtry		82.71 265	80.93 268	88.06 260	90.05 291	76.37 267	84.74 318	91.96 256	72.28 308	81.32 252	87.87 288	71.03 200	95.50 279	68.97 283	80.15 287	92.32 275

PatchFormer-LS_test		86.02 208	85.13 205	88.70 236	91.52 223	74.12 280	91.19 262	92.09 248	82.71 196	84.30 209	87.24 294	70.87 202	96.98 210	81.04 167	85.17 226	95.00 146

RPMNet		83.18 263	80.87 269	90.12 182	90.58 278	79.34 198	85.24 316	90.78 289	71.44 312	85.55 161	82.97 321	70.87 202	95.61 272	61.01 320	89.36 176	95.40 137

Patchmatch-RL test		81.67 272	79.96 276	86.81 287	85.42 321	71.23 303	82.17 331	87.50 331	78.47 257	77.19 286	82.50 322	70.81 204	93.48 310	82.66 144	72.89 311	95.71 129

CostFormer		85.77 217	84.94 210	88.26 255	91.16 256	72.58 296	89.47 281	91.04 282	76.26 276	86.45 138	89.97 258	70.74 205	96.86 219	82.35 150	87.07 214	95.34 140

sam_mvs												70.60 206

xiu_mvs_v1_base_debu		90.64 80	90.05 82	92.40 91	93.97 165	84.46 67	93.32 198	95.46 141	85.17 129	92.25 53	94.03 119	70.59 207	98.57 87	90.97 54	94.67 97	94.18 191

xiu_mvs_v1_base		90.64 80	90.05 82	92.40 91	93.97 165	84.46 67	93.32 198	95.46 141	85.17 129	92.25 53	94.03 119	70.59 207	98.57 87	90.97 54	94.67 97	94.18 191

xiu_mvs_v1_base_debi		90.64 80	90.05 82	92.40 91	93.97 165	84.46 67	93.32 198	95.46 141	85.17 129	92.25 53	94.03 119	70.59 207	98.57 87	90.97 54	94.67 97	94.18 191

test_post											10.29 352	70.57 210	95.91 264

CANet_DTU		90.26 88	89.41 92	92.81 77	93.46 180	83.01 103	93.48 194	94.47 194	89.43 37	87.76 117	94.23 117	70.54 211	99.03 50	84.97 113	96.39 78	96.38 102

BH-RMVSNet		88.37 134	87.48 134	91.02 142	95.28 111	79.45 188	92.89 220	93.07 230	85.45 125	86.91 129	94.84 100	70.35 212	97.76 139	73.97 250	94.59 101	95.85 122

Fast-Effi-MVS+-dtu		87.44 176	86.72 161	89.63 208	92.04 211	77.68 250	94.03 164	93.94 216	85.81 116	82.42 235	91.32 225	70.33 213	97.06 205	80.33 183	90.23 163	94.14 194

MDTV_nov1_ep13_2view						55.91 342	87.62 302		73.32 298	84.59 197		70.33 213		74.65 245		95.50 133

ACMM	84.12 9	89.14 116	88.48 115	91.12 135	94.65 140	81.22 141	95.31 59	96.12 93	85.31 128	85.92 147	94.34 109	70.19 215	98.06 125	85.65 108	88.86 190	94.08 199
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		89.45 107	88.90 105	91.12 135	94.47 145	81.49 132	95.30 61	96.14 90	86.73 103	85.45 169	95.16 89	69.89 216	98.10 115	87.70 86	89.23 179	93.77 218

LGP-MVS_train				91.12 135	94.47 145	81.49 132		96.14 90	86.73 103	85.45 169	95.16 89	69.89 216	98.10 115	87.70 86	89.23 179	93.77 218

CHOSEN 280x420		85.15 231	83.99 230	88.65 237	92.47 203	78.40 229	79.68 336	92.76 235	74.90 288	81.41 250	89.59 263	69.85 218	95.51 277	79.92 191	95.29 92	92.03 279

LTVRE_ROB	82.13 13	86.26 204	84.90 212	90.34 172	94.44 148	81.50 131	92.31 237	94.89 181	83.03 184	79.63 271	92.67 169	69.69 219	97.79 137	71.20 263	86.26 217	91.72 285
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
OpenMVS	83.78 11	88.74 128	87.29 139	93.08 67	92.70 200	85.39 52	96.57 22	96.43 74	78.74 255	80.85 256	96.07 66	69.64 220	99.01 55	78.01 216	96.65 72	94.83 161

MDTV_nov1_ep13			83.56 241		91.69 221	69.93 314	87.75 300	91.54 268	78.60 256	84.86 193	88.90 270	69.54 221	96.03 257	70.25 268	88.93 189

PatchT		82.68 266	81.27 264	86.89 285	90.09 290	70.94 308	84.06 323	90.15 297	74.91 287	85.63 160	83.57 317	69.37 222	94.87 299	65.19 307	88.50 195	94.84 160

VPNet		88.20 139	87.47 135	90.39 167	93.56 178	79.46 186	94.04 163	95.54 134	88.67 55	86.96 127	94.58 107	69.33 223	97.15 197	84.05 130	80.53 283	94.56 177

ACMP	84.23 8	89.01 123	88.35 116	90.99 144	94.73 134	81.27 138	95.07 80	95.89 110	86.48 106	83.67 220	94.30 112	69.33 223	97.99 129	87.10 99	88.55 192	93.72 222
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 297				9.81 353	69.31 225	95.53 275	76.65 228

tpmvs		83.35 262	82.07 259	87.20 280	91.07 258	71.00 307	88.31 295	91.70 260	78.91 249	80.49 262	87.18 295	69.30 226	97.08 203	68.12 291	83.56 241	93.51 240

thres200		87.21 185	86.24 182	90.12 182	95.36 107	78.53 220	93.26 205	92.10 247	86.42 108	88.00 107	91.11 236	69.24 227	98.00 128	69.58 277	91.04 151	93.83 213

tfpn200view9		87.58 172	86.64 171	90.41 166	95.99 88	78.64 215	94.58 114	91.98 254	86.94 99	88.09 101	91.77 201	69.18 228	98.10 115	70.13 271	91.10 144	94.48 184

thres400		87.62 166	86.64 171	90.57 151	95.99 88	78.64 215	94.58 114	91.98 254	86.94 99	88.09 101	91.77 201	69.18 228	98.10 115	70.13 271	91.10 144	94.96 150

tfpnnormal		84.72 246	83.23 250	89.20 227	92.79 199	80.05 169	94.48 119	95.81 114	82.38 200	81.08 254	91.21 230	69.01 230	96.95 213	61.69 318	80.59 281	90.58 310

tfpn111		87.63 163	86.68 165	90.47 163	96.12 78	78.55 217	95.03 83	91.58 263	87.15 87	88.06 104	92.29 181	68.91 231	98.15 108	69.88 276	91.10 144	94.71 165

conf200view11		87.65 159	86.71 162	90.46 165	96.12 78	78.55 217	95.03 83	91.58 263	87.15 87	88.06 104	92.29 181	68.91 231	98.10 115	70.13 271	91.10 144	94.71 165

thres100view900		87.63 163	86.71 162	90.38 169	96.12 78	78.55 217	95.03 83	91.58 263	87.15 87	88.06 104	92.29 181	68.91 231	98.10 115	70.13 271	91.10 144	94.48 184

thres600view7		87.65 159	86.67 166	90.59 150	96.08 84	78.72 213	94.88 94	91.58 263	87.06 96	88.08 103	92.30 180	68.91 231	98.10 115	70.05 275	91.10 144	94.96 150

view600		87.62 166	86.65 167	90.53 153	96.19 73	78.52 221	95.29 63	91.09 275	87.08 92	87.84 110	93.03 156	68.86 235	98.11 111	69.44 278	91.02 152	94.96 150

view800		87.62 166	86.65 167	90.53 153	96.19 73	78.52 221	95.29 63	91.09 275	87.08 92	87.84 110	93.03 156	68.86 235	98.11 111	69.44 278	91.02 152	94.96 150

conf0.05thres1000		87.62 166	86.65 167	90.53 153	96.19 73	78.52 221	95.29 63	91.09 275	87.08 92	87.84 110	93.03 156	68.86 235	98.11 111	69.44 278	91.02 152	94.96 150

tfpn		87.62 166	86.65 167	90.53 153	96.19 73	78.52 221	95.29 63	91.09 275	87.08 92	87.84 110	93.03 156	68.86 235	98.11 111	69.44 278	91.02 152	94.96 150

PatchMatch-RL		86.77 195	85.54 195	90.47 163	95.88 91	82.71 114	90.54 265	92.31 243	79.82 243	84.32 207	91.57 211	68.77 239	96.39 245	73.16 255	93.48 121	92.32 275

XVG-OURS		89.40 112	88.70 108	91.52 124	94.06 157	81.46 134	91.27 260	96.07 96	86.14 114	88.89 95	95.77 76	68.73 240	97.26 189	87.39 91	89.96 167	95.83 124

TR-MVS		86.78 193	85.76 193	89.82 198	94.37 149	78.41 228	92.47 232	92.83 233	81.11 233	86.36 140	92.40 176	68.73 240	97.48 154	73.75 253	89.85 169	93.57 236

tpm		84.73 245	84.02 229	86.87 286	90.33 284	68.90 317	89.06 287	89.94 303	80.85 235	85.75 152	89.86 260	68.54 242	95.97 260	77.76 217	84.05 235	95.75 128

DI_MVS_plusplus_test		88.15 141	86.82 156	92.14 102	90.67 276	81.07 145	93.01 215	94.59 191	83.83 158	77.78 281	90.63 244	68.51 243	98.16 106	88.02 83	94.37 108	97.17 81

test_normal		88.13 142	86.78 160	92.18 100	90.55 281	81.19 143	92.74 223	94.64 190	83.84 156	77.49 284	90.51 250	68.49 244	98.16 106	88.22 78	94.55 102	97.21 79

tfpn_ndepth		86.10 206	84.98 207	89.43 216	95.52 104	78.29 232	94.62 112	89.60 310	81.88 220	85.43 172	90.54 247	68.47 245	96.85 220	68.46 286	90.34 161	93.15 251

FMVSNet3		87.40 178	86.11 184	91.30 131	93.79 173	83.64 86	94.20 149	94.81 186	83.89 155	84.37 203	91.87 200	68.45 246	96.56 235	78.23 213	85.36 223	93.70 223

conf0.01		85.83 214	84.54 220	89.71 204	95.26 113	77.63 251	94.21 143	89.33 312	81.89 213	84.94 187	91.51 215	68.43 247	96.80 221	66.05 299	89.23 179	94.71 165

conf0.002		85.83 214	84.54 220	89.71 204	95.26 113	77.63 251	94.21 143	89.33 312	81.89 213	84.94 187	91.51 215	68.43 247	96.80 221	66.05 299	89.23 179	94.71 165

thresconf0.02		85.75 218	84.54 220	89.38 219	95.26 113	77.63 251	94.21 143	89.33 312	81.89 213	84.94 187	91.51 215	68.43 247	96.80 221	66.05 299	89.23 179	93.70 223

tfpn_n400		85.75 218	84.54 220	89.38 219	95.26 113	77.63 251	94.21 143	89.33 312	81.89 213	84.94 187	91.51 215	68.43 247	96.80 221	66.05 299	89.23 179	93.70 223

tfpnconf		85.75 218	84.54 220	89.38 219	95.26 113	77.63 251	94.21 143	89.33 312	81.89 213	84.94 187	91.51 215	68.43 247	96.80 221	66.05 299	89.23 179	93.70 223

tfpnview11		85.75 218	84.54 220	89.38 219	95.26 113	77.63 251	94.21 143	89.33 312	81.89 213	84.94 187	91.51 215	68.43 247	96.80 221	66.05 299	89.23 179	93.70 223

MVP-Stereo		85.97 210	84.86 213	89.32 223	90.92 266	82.19 122	92.11 244	94.19 202	78.76 254	78.77 276	91.63 207	68.38 253	96.56 235	75.01 243	93.95 111	89.20 317
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tfpn1000		86.06 207	84.92 211	89.49 214	95.54 101	77.79 245	94.72 105	89.07 319	82.05 205	85.36 180	91.94 197	68.32 254	96.65 230	67.04 293	90.24 162	94.02 202

tpm cat1		81.96 270	80.27 272	87.01 281	91.09 257	71.02 306	87.38 303	91.53 269	66.25 328	80.17 264	86.35 306	68.22 255	96.15 254	69.16 282	82.29 252	93.86 211

tpm2		84.08 253	82.94 253	87.48 272	91.39 232	71.27 302	89.23 285	90.37 293	71.95 310	84.64 195	89.33 266	67.30 256	96.55 237	75.17 240	87.09 213	94.63 170

test-LLR		85.87 211	85.41 200	87.25 276	90.95 262	71.67 300	89.55 277	89.88 305	83.41 170	84.54 198	87.95 285	67.25 257	95.11 294	81.82 159	93.37 124	94.97 147

test0.0.03 1		82.41 268	81.69 261	84.59 302	88.23 309	72.89 288	90.24 268	87.83 327	83.41 170	79.86 269	89.78 261	67.25 257	88.99 330	65.18 308	83.42 244	91.90 281

CVMVSNet		84.69 248	84.79 215	84.37 304	91.84 214	64.92 328	93.70 186	91.47 270	66.19 329	86.16 145	95.28 85	67.18 259	93.33 312	80.89 172	90.42 159	94.88 159

Patchmatch-test1		85.81 216	84.71 216	89.12 228	92.15 207	76.60 264	91.12 263	91.69 261	83.53 167	85.50 166	88.56 277	66.79 260	95.00 297	72.69 257	90.35 160	95.76 127

IterMVS		84.88 239	83.98 231	87.60 267	91.44 226	76.03 270	90.18 270	92.41 242	83.24 176	81.06 255	90.42 252	66.60 261	94.28 302	79.46 199	80.98 277	92.48 268
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 180	85.98 188	91.08 138	94.01 160	83.10 98	95.14 77	94.94 176	83.57 164	84.37 203	91.64 204	66.59 262	96.34 248	78.23 213	85.36 223	93.79 214

test1		87.26 180	85.98 188	91.08 138	94.01 160	83.10 98	95.14 77	94.94 176	83.57 164	84.37 203	91.64 204	66.59 262	96.34 248	78.23 213	85.36 223	93.79 214

FMVSNet2		87.19 186	85.82 192	91.30 131	94.01 160	83.67 85	94.79 99	94.94 176	83.57 164	83.88 214	92.05 194	66.59 262	96.51 238	77.56 220	85.01 227	93.73 221

EPMVS		83.90 256	82.70 257	87.51 269	90.23 288	72.67 292	88.62 292	81.96 342	81.37 231	85.01 185	88.34 280	66.31 265	94.45 300	75.30 239	87.12 212	95.43 136

semantic-postprocess				88.18 258	91.71 219	76.87 263		92.65 239	85.40 126	81.44 249	90.54 247	66.21 266	95.00 297	81.04 167	81.05 272	92.66 264

tpmp4_e23		83.87 257	82.33 258	88.48 248	91.46 225	72.82 289	89.82 275	91.57 267	73.02 302	81.86 246	89.05 268	66.20 267	96.97 211	71.57 261	86.39 216	95.66 130

MDA-MVSNet_test_wron		79.21 294	77.19 294	85.29 297	88.22 310	72.77 291	85.87 311	90.06 300	74.34 292	62.62 335	87.56 291	66.14 268	91.99 322	66.90 297	73.01 309	91.10 296

YYNet1		79.22 293	77.20 293	85.28 298	88.20 311	72.66 293	85.87 311	90.05 302	74.33 293	62.70 334	87.61 290	66.09 269	92.03 321	66.94 294	72.97 310	91.15 294

JIA-IIPM		81.04 281	78.98 287	87.25 276	88.64 305	73.48 285	81.75 332	89.61 309	73.19 299	82.05 242	73.71 336	66.07 270	95.87 265	71.18 265	84.60 230	92.41 271

MSDG		84.86 240	83.09 251	90.14 181	93.80 171	80.05 169	89.18 286	93.09 229	78.89 250	78.19 277	91.91 198	65.86 271	97.27 187	68.47 285	88.45 196	93.11 252

jajsoiax		88.24 138	87.50 133	90.48 162	90.89 268	80.14 166	95.31 59	95.65 127	84.97 135	84.24 210	94.02 122	65.31 272	97.42 169	88.56 75	88.52 194	93.89 206

cascas		86.43 202	84.98 207	90.80 148	92.10 210	80.92 151	90.24 268	95.91 107	73.10 300	83.57 223	88.39 279	65.15 273	97.46 156	84.90 116	91.43 142	94.03 201

ADS-MVSNet2		81.66 273	79.71 279	87.50 270	91.35 239	74.19 278	83.33 327	88.48 323	72.90 303	82.24 238	85.77 309	64.98 274	93.20 314	64.57 310	83.74 237	95.12 142

ADS-MVSNet		81.56 275	79.78 277	86.90 284	91.35 239	71.82 299	83.33 327	89.16 318	72.90 303	82.24 238	85.77 309	64.98 274	93.76 306	64.57 310	83.74 237	95.12 142

pmmvs5		84.21 252	82.84 256	88.34 253	88.95 303	76.94 262	92.41 233	91.91 258	75.63 281	80.28 263	91.18 232	64.59 276	95.57 274	77.09 226	83.47 242	92.53 267

PVSNet	78.82 18	85.55 224	84.65 218	88.23 257	94.72 135	71.93 298	87.12 304	92.75 236	78.80 253	84.95 186	90.53 249	64.43 277	96.71 229	74.74 244	93.86 113	96.06 115

UGNet		89.95 94	88.95 103	92.95 73	94.51 144	83.31 94	95.70 48	95.23 164	89.37 39	87.58 119	93.94 126	64.00 278	98.78 77	83.92 131	96.31 79	96.74 96
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
RPSCF		85.07 232	84.27 226	87.48 272	92.91 197	70.62 310	91.69 253	92.46 241	76.20 277	82.67 234	95.22 88	63.94 279	97.29 186	77.51 221	85.80 220	94.53 178

mvs_tets		88.06 144	87.28 140	90.38 169	90.94 264	79.88 174	95.22 72	95.66 125	85.10 133	84.21 211	93.94 126	63.53 280	97.40 176	88.50 76	88.40 199	93.87 209

dp		81.47 277	80.23 273	85.17 299	89.92 294	65.49 327	86.74 305	90.10 299	76.30 275	81.10 253	87.12 296	62.81 281	95.92 262	68.13 290	79.88 292	94.09 198

LFMVS		90.08 90	89.13 99	92.95 73	96.71 60	82.32 121	96.08 32	89.91 304	86.79 102	92.15 58	96.81 33	62.60 282	98.34 98	87.18 94	93.90 112	98.19 36

DWT-MVSNet_test		84.95 237	83.68 238	88.77 233	91.43 229	73.75 283	91.74 250	90.98 283	80.66 236	83.84 215	87.36 292	62.44 283	97.11 201	78.84 208	85.81 219	95.46 135

Anonymous20231206		81.03 282	79.77 278	84.82 301	87.85 316	70.26 312	91.42 257	92.08 249	73.67 295	77.75 282	89.25 267	62.43 284	93.08 316	61.50 319	82.00 258	91.12 295

VDD-MVS		90.74 77	89.92 85	93.20 62	96.27 71	83.02 102	95.73 46	93.86 218	88.42 62	92.53 48	96.84 31	62.09 285	98.64 82	90.95 57	92.62 136	97.93 56

MS-PatchMatch		85.05 233	84.16 227	87.73 265	91.42 230	78.51 225	91.25 261	93.53 223	77.50 265	80.15 265	91.58 209	61.99 286	95.51 277	75.69 235	94.35 109	89.16 318

OurMVSNet-221017-0		85.35 227	84.64 219	87.49 271	90.77 271	72.59 295	94.01 166	94.40 196	84.72 140	79.62 272	93.17 149	61.91 287	96.72 227	81.99 156	81.16 269	93.16 249

test20.03		79.95 288	79.08 285	82.55 311	85.79 320	67.74 321	91.09 264	91.08 279	81.23 232	74.48 307	89.96 259	61.63 288	90.15 328	60.08 322	76.38 303	89.76 312

DSMNet-mixed		76.94 298	76.29 297	78.89 315	83.10 329	56.11 341	87.78 299	79.77 345	60.65 337	75.64 301	88.71 273	61.56 289	88.34 332	60.07 323	89.29 178	92.21 278

IB-MVS	80.51 15	85.24 230	83.26 249	91.19 133	92.13 209	79.86 175	91.75 249	91.29 274	83.28 175	80.66 259	88.49 278	61.28 290	98.46 92	80.99 170	79.46 295	95.25 141
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
GA-MVS		86.61 197	85.27 204	90.66 149	91.33 241	78.71 214	90.40 266	93.81 221	85.34 127	85.12 183	89.57 264	61.25 291	97.11 201	80.99 170	89.59 173	96.15 107

N_pmnet		68.89 311	68.44 312	70.23 327	89.07 302	28.79 356	88.06 296	19.50 357	69.47 321	71.86 319	84.93 312	61.24 292	91.75 324	54.70 328	77.15 302	90.15 311

EU-MVSNet		81.32 279	80.95 267	82.42 312	88.50 307	63.67 329	93.32 198	91.33 272	64.02 333	80.57 261	92.83 164	61.21 293	92.27 320	76.34 230	80.38 286	91.32 291

VDDNet		89.56 103	88.49 114	92.76 80	95.07 122	82.09 123	96.30 26	93.19 228	81.05 234	91.88 61	96.86 30	61.16 294	98.33 99	88.43 77	92.49 137	97.84 60

PVSNet_0	73.20 20	77.22 297	74.83 300	84.37 304	90.70 275	71.10 305	83.09 329	89.67 308	72.81 305	73.93 309	83.13 320	60.79 295	93.70 307	68.54 284	50.84 342	88.30 329

SixPastTwentyTwo		83.91 255	82.90 254	86.92 283	90.99 260	70.67 309	93.48 194	91.99 253	85.54 123	77.62 283	92.11 189	60.59 296	96.87 218	76.05 234	77.75 299	93.20 247

gg-mvs-nofinetune		81.77 271	79.37 281	88.99 231	90.85 270	77.73 249	86.29 308	79.63 346	74.88 289	83.19 229	69.05 339	60.34 297	96.11 255	75.46 237	94.64 100	93.11 252

MDA-MVSNet-bldmvs		78.85 295	76.31 296	86.46 288	89.76 296	73.88 282	88.79 289	90.42 292	79.16 248	59.18 336	88.33 281	60.20 298	94.04 304	62.00 317	68.96 328	91.48 289

pmmvs6		83.42 259	81.60 262	88.87 232	88.01 313	77.87 243	94.96 87	94.24 201	74.67 290	78.80 275	91.09 237	60.17 299	96.49 239	77.06 227	75.40 306	92.23 277

ACMH	80.38 17	85.36 226	83.68 238	90.39 167	94.45 147	80.63 157	94.73 102	94.85 183	82.09 204	77.24 285	92.65 170	60.01 300	97.58 147	72.25 259	84.87 228	92.96 255
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 263	89.73 297	77.91 240	87.80 298	78.23 348		80.58 260	83.86 315	59.88 301	95.33 291	71.20 263	92.22 139	90.60 309

pmmvs-eth3d		80.97 283	78.72 288	87.74 264	84.99 324	79.97 173	90.11 271	91.65 262	75.36 282	73.51 310	86.03 308	59.45 302	93.96 305	75.17 240	72.21 312	89.29 316

test_0402		81.30 280	79.17 284	87.67 266	93.19 187	78.17 235	92.98 217	91.71 259	75.25 283	76.02 298	90.31 253	59.23 303	96.37 246	50.22 334	83.63 240	88.47 328

FMVSNet1		85.85 212	84.11 228	91.08 138	92.81 198	83.10 98	95.14 77	94.94 176	81.64 224	82.68 233	91.64 204	59.01 304	96.34 248	75.37 238	83.78 236	93.79 214

COLMAP_ROB	80.39 16	83.96 254	82.04 260	89.74 202	95.28 111	79.75 178	94.25 140	92.28 244	75.17 284	78.02 280	93.77 135	58.60 305	97.84 136	65.06 309	85.92 218	91.63 286
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	81.04 14	85.05 233	83.46 245	89.82 198	94.66 139	79.37 196	94.44 124	94.12 206	82.19 203	78.04 279	92.82 165	58.23 306	97.54 150	73.77 252	82.90 247	92.54 266

LP		75.51 301	72.15 305	85.61 295	87.86 315	73.93 281	80.20 335	88.43 324	67.39 324	70.05 321	80.56 329	58.18 307	93.18 315	46.28 340	70.36 325	89.71 314

CMPMVS	59.16 21	80.52 285	79.20 283	84.48 303	83.98 326	67.63 322	89.95 274	93.84 220	64.79 332	66.81 329	91.14 235	57.93 308	95.17 292	76.25 231	88.10 201	90.65 306
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ITE_SJBPF				88.24 256	91.88 213	77.05 261		92.92 231	85.54 123	80.13 267	93.30 144	57.29 309	96.20 252	72.46 258	84.71 229	91.49 288

TESTMET0.1,1		83.74 258	82.85 255	86.42 290	89.96 293	71.21 304	89.55 277	87.88 326	77.41 266	83.37 227	87.31 293	56.71 310	93.65 308	80.62 176	92.85 135	94.40 187

UnsupCasMVSNet_eth		80.07 287	78.27 289	85.46 296	85.24 322	72.63 294	88.45 294	94.87 182	82.99 188	71.64 320	88.07 284	56.34 311	91.75 324	73.48 254	63.36 337	92.01 280

K. test v3		81.59 274	80.15 275	85.91 293	89.89 295	69.42 316	92.57 229	87.71 328	85.56 122	73.44 311	89.71 262	55.58 312	95.52 276	77.17 224	69.76 326	92.78 262

test-mter		84.54 250	83.64 240	87.25 276	90.95 262	71.67 300	89.55 277	89.88 305	79.17 247	84.54 198	87.95 285	55.56 313	95.11 294	81.82 159	93.37 124	94.97 147

lessismore_v0				86.04 291	88.46 308	68.78 318		80.59 344		73.01 314	90.11 256	55.39 314	96.43 244	75.06 242	65.06 332	92.90 256

MVS-HIRNet		73.70 304	72.20 304	78.18 318	91.81 216	56.42 340	82.94 330	82.58 340	55.24 339	68.88 323	66.48 340	55.32 315	95.13 293	58.12 325	88.42 198	83.01 335

new-patchmatchnet		76.41 299	75.17 299	80.13 314	82.65 332	59.61 334	87.66 301	91.08 279	78.23 262	69.85 322	83.22 319	54.76 316	91.63 326	64.14 312	64.89 333	89.16 318

XVG-ACMP-BASELINE		86.00 209	84.84 214	89.45 215	91.20 251	78.00 238	91.70 252	95.55 132	85.05 134	82.97 230	92.25 185	54.49 317	97.48 154	82.93 140	87.45 208	92.89 257

USDC		82.76 264	81.26 265	87.26 275	91.17 254	74.55 276	89.27 283	93.39 226	78.26 261	75.30 302	92.08 191	54.43 318	96.63 231	71.64 260	85.79 221	90.61 307

AllTest		83.42 259	81.39 263	89.52 211	95.01 123	77.79 245	93.12 209	90.89 286	77.41 266	76.12 295	93.34 140	54.08 319	97.51 152	68.31 288	84.27 233	93.26 245

TestCases				89.52 211	95.01 123	77.79 245		90.89 286	77.41 266	76.12 295	93.34 140	54.08 319	97.51 152	68.31 288	84.27 233	93.26 245

MIMVSNet		82.59 267	80.53 270	88.76 234	91.51 224	78.32 230	86.57 307	90.13 298	79.32 246	80.70 258	88.69 275	52.98 321	93.07 317	66.03 305	88.86 190	94.90 158

FMVSNet5		81.52 276	79.60 280	87.27 274	91.17 254	77.95 239	91.49 256	92.26 245	76.87 271	76.16 294	87.91 287	51.67 322	92.34 319	67.74 292	81.16 269	91.52 287

testgi		80.94 284	80.20 274	83.18 308	87.96 314	66.29 324	91.28 259	90.70 291	83.70 160	78.12 278	92.84 163	51.37 323	90.82 327	63.34 313	82.46 251	92.43 270

Test4		85.75 218	83.72 236	91.83 115	88.08 312	81.03 147	92.48 231	95.54 134	83.38 172	73.40 312	88.57 276	50.99 324	97.37 180	86.61 105	94.47 105	97.09 85

UnsupCasMVSNet_bld		76.23 300	73.27 302	85.09 300	83.79 327	72.92 287	85.65 315	93.47 225	71.52 311	68.84 324	79.08 332	49.77 325	93.21 313	66.81 298	60.52 339	89.13 320

OpenMVS_ROB	74.94 19	79.51 291	77.03 295	86.93 282	87.00 317	76.23 269	92.33 236	90.74 290	68.93 322	74.52 306	88.23 282	49.58 326	96.62 232	57.64 326	84.29 232	87.94 330

testing_2		83.40 261	81.02 266	90.56 152	85.06 323	80.51 161	91.37 258	95.57 130	82.92 190	67.06 328	85.54 311	49.47 327	97.24 191	86.74 100	85.44 222	93.93 204

TDRefinement		79.81 289	77.34 291	87.22 279	79.24 338	75.48 274	93.12 209	92.03 251	76.45 272	75.01 303	91.58 209	49.19 328	96.44 243	70.22 270	69.18 327	89.75 313

MIMVSNet1		79.38 292	77.28 292	85.69 294	86.35 319	73.67 284	91.61 255	92.75 236	78.11 264	72.64 316	88.12 283	48.16 329	91.97 323	60.32 321	77.49 300	91.43 290

LF4IMVS		80.37 286	79.07 286	84.27 306	86.64 318	69.87 315	89.39 282	91.05 281	76.38 273	74.97 304	90.00 257	47.85 330	94.25 303	74.55 247	80.82 279	88.69 323

EG-PatchMatch MVS		82.37 269	80.34 271	88.46 249	90.27 285	79.35 197	92.80 222	94.33 199	77.14 270	73.26 313	90.18 255	47.47 331	96.72 227	70.25 268	87.32 211	89.30 315

testpf		71.41 309	72.11 306	69.30 329	84.53 325	59.79 333	62.74 346	83.14 339	71.11 315	68.83 325	81.57 327	46.70 332	84.83 343	74.51 248	75.86 305	63.30 343

TinyColmap		79.76 290	77.69 290	85.97 292	91.71 219	73.12 286	89.55 277	90.36 294	75.03 285	72.03 318	90.19 254	46.22 333	96.19 253	63.11 314	81.03 273	88.59 324

test2356		74.50 302	73.27 302	78.20 316	80.81 334	59.84 332	83.76 326	88.33 325	71.43 313	72.37 317	81.84 325	45.60 334	86.26 338	50.97 332	84.32 231	88.50 325

tmp_tt		35.64 328	39.24 327	24.84 341	14.87 356	23.90 357	62.71 347	51.51 356	6.58 352	36.66 346	62.08 344	44.37 335	30.34 355	52.40 329	22.00 351	20.27 351

new_pmnet		72.15 307	70.13 308	78.20 316	82.95 331	65.68 325	83.91 324	82.40 341	62.94 335	64.47 332	79.82 331	42.85 336	86.26 338	57.41 327	74.44 308	82.65 336

test1235678		72.22 306	70.31 307	77.93 319	78.04 339	58.04 336	85.76 313	89.80 307	70.15 320	63.43 333	80.20 330	42.24 337	87.24 335	48.68 336	74.50 307	88.50 325

1111		70.54 310	69.71 309	73.04 324	79.30 336	44.83 349	84.23 321	88.96 320	67.33 325	65.42 330	82.28 323	41.11 338	88.11 333	47.12 338	71.60 317	86.19 332

.test1245		57.63 320	61.79 317	45.14 338	79.30 336	44.83 349	84.23 321	88.96 320	67.33 325	65.42 330	82.28 323	41.11 338	88.11 333	47.12 338	0.39 353	2.46 354

testus		74.41 303	73.35 301	77.59 320	82.49 333	57.08 337	86.02 309	90.21 296	72.28 308	72.89 315	84.32 314	37.08 340	86.96 336	52.24 330	82.65 249	88.73 321

pmmvs3		71.81 308	68.71 311	81.11 313	75.86 340	70.42 311	86.74 305	83.66 338	58.95 338	68.64 326	80.89 328	36.93 341	89.52 329	63.10 315	63.59 336	83.39 334

PM-MVS		78.11 296	76.12 298	84.09 307	83.54 328	70.08 313	88.97 288	85.27 336	79.93 241	74.73 305	86.43 300	34.70 342	93.48 310	79.43 202	72.06 313	88.72 322

Anonymous20231211		72.97 305	69.63 310	83.00 310	83.05 330	66.91 323	92.69 224	89.45 311	61.06 336	67.50 327	83.46 318	34.34 343	93.61 309	51.11 331	63.97 335	88.48 327

ambc				83.06 309	79.99 335	63.51 330	77.47 339	92.86 232		74.34 308	84.45 313	28.74 344	95.06 296	73.06 256	68.89 329	90.61 307

test12356		64.99 314	63.78 313	68.61 331	72.69 342	39.14 352	78.46 337	87.61 330	64.91 331	55.77 337	77.48 333	28.10 345	85.59 340	44.69 341	64.35 334	81.12 338

DeepMVS_CX				56.31 336	74.23 341	51.81 345		56.67 355	44.85 343	48.54 342	75.16 334	27.87 346	58.74 353	40.92 344	52.22 341	58.39 347

no-one		61.56 316	56.58 318	76.49 322	67.80 348	62.76 331	78.13 338	86.11 332	63.16 334	43.24 343	64.70 342	26.12 347	88.95 331	50.84 333	29.15 345	77.77 340

testmv		65.49 313	62.66 314	73.96 323	68.78 345	53.14 344	84.70 319	88.56 322	65.94 330	52.35 339	74.65 335	25.02 348	85.14 341	43.54 342	60.40 340	83.60 333

FPMVS		64.63 315	62.55 315	70.88 326	70.80 343	56.71 338	84.42 320	84.42 337	51.78 341	49.57 340	81.61 326	23.49 349	81.48 345	40.61 345	76.25 304	74.46 342

ANet_high		58.88 318	54.22 321	72.86 325	56.50 354	56.67 339	80.75 334	86.00 333	73.09 301	37.39 345	64.63 343	22.17 350	79.49 348	43.51 343	23.96 349	82.43 337

EMVS		42.07 326	41.12 326	44.92 339	63.45 351	35.56 355	73.65 340	63.48 352	33.05 349	26.88 351	45.45 350	21.27 351	67.14 351	19.80 351	23.02 350	32.06 350

Gipuma		57.99 319	54.91 320	67.24 332	88.51 306	65.59 326	52.21 349	90.33 295	43.58 345	42.84 344	51.18 347	20.29 352	85.07 342	34.77 347	70.45 324	51.05 348
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 325	42.29 325	46.03 337	65.58 349	37.41 353	73.51 341	64.62 351	33.99 348	28.47 350	47.87 348	19.90 353	67.91 350	22.23 350	24.45 348	32.77 349

PMMVS2		59.60 317	56.40 319	69.21 330	68.83 344	46.58 347	73.02 344	77.48 349	55.07 340	49.21 341	72.95 338	17.43 354	80.04 346	49.32 335	44.33 343	80.99 339

LCM-MVSNet		66.00 312	62.16 316	77.51 321	64.51 350	58.29 335	83.87 325	90.90 285	48.17 342	54.69 338	73.31 337	16.83 355	86.75 337	65.47 306	61.67 338	87.48 331

PNet_i23d		50.48 323	47.18 323	60.36 334	68.59 346	44.56 351	72.75 345	72.61 350	43.92 344	33.91 347	60.19 345	6.16 356	73.52 349	38.50 346	28.04 346	63.01 344

PMVS	47.18 22	52.22 321	48.46 322	63.48 333	45.72 355	46.20 348	73.41 342	78.31 347	41.03 346	30.06 348	65.68 341	6.05 357	83.43 344	30.04 348	65.86 331	60.80 345
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 324	38.59 329	57.77 335	56.52 353	48.77 346	55.38 348	58.64 354	29.33 350	28.96 349	52.65 346	4.68 358	64.62 352	28.11 349	33.07 344	59.93 346
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 330	20.48 331	23.63 342	68.59 346	36.41 354	49.57 350	6.85 358	9.37 351	7.89 353	4.46 356	4.03 359	31.37 354	17.47 352	16.07 352	3.12 352

wuykxyi23d		50.55 322	44.13 324	69.81 328	56.77 352	54.58 343	73.22 343	80.78 343	39.79 347	22.08 352	46.69 349	4.03 359	79.71 347	47.65 337	26.13 347	75.14 341

test123		8.76 332	11.22 333	1.39 343	0.85 358	0.97 358	85.76 313	0.35 360	0.54 354	2.45 355	8.14 355	0.60 361	0.48 356	2.16 354	0.17 355	2.71 353

testmvs		8.92 331	11.52 332	1.12 344	1.06 357	0.46 359	86.02 309	0.65 359	0.62 353	2.74 354	9.52 354	0.31 362	0.45 357	2.38 353	0.39 353	2.46 354

sosnet-low-res		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

sosnet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

uncertanet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

Regformer		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

ab-mvs-re		7.82 333	10.43 334	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	93.88 131	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

uanet		0.00 335	0.00 336	0.00 345	0.00 359	0.00 360	0.00 351	0.00 361	0.00 355	0.00 356	0.00 357	0.00 363	0.00 358	0.00 355	0.00 356	0.00 356

GSMVS																96.12 110

test_part3							95.99 35		88.25 66		97.60 4		99.62 1	93.18 18

test_part2					98.55 5	87.22 10				96.40 2

MTGPA								96.97 34

MTMP								60.64 353

gm-plane-assit					89.60 298	68.00 319			77.28 269		88.99 269		97.57 148	79.44 201

test9_res														91.91 42	98.71 19	98.07 45

agg_prior2														90.54 61	98.68 24	98.27 31

agg_prior					97.38 43	85.92 44		96.72 56		92.16 56			98.97 61

test_prior4						85.96 43	94.11 153

test_prior				93.82 51	97.29 48	84.49 64		96.88 43					98.87 67			98.11 43

旧先验2							93.36 197		71.25 314	94.37 13			97.13 200	86.74 100

新几何2							93.11 211

无先验							93.28 204	96.26 82	73.95 294				99.05 46	80.56 177		96.59 98

原ACMM2							92.94 219

testdata2													98.75 78	78.30 212

testdata1							92.15 242		87.94 72

plane_prior7					94.70 137	82.74 111

plane_prior5								96.22 86					98.12 109	88.15 79	89.99 165	94.63 170

plane_prior4											94.86 97

plane_prior3						82.75 109			90.26 25	86.91 129

plane_prior2							95.85 42		90.81 18

plane_prior1					94.59 141

plane_prior						82.73 112	95.21 73		89.66 35						89.88 168

n2								0.00 361

nn								0.00 361

door-mid								85.49 334

test11								96.57 70

door								85.33 335

HQP5-MVS						81.56 129

HQP-NCC					94.17 154		94.39 129		88.81 50	85.43 172

ACMP_Plane					94.17 154		94.39 129		88.81 50	85.43 172

BP-MVS														87.11 97

HQP4-MVS										85.43 172			97.96 130			94.51 180

HQP3-MVS								96.04 99							89.77 170

NP-MVS					94.37 149	82.42 119					93.98 124

ACMMP++_ref															87.47 207

ACMMP++															88.01 204

High-resolution multi-view benchmark