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	94.00 166	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	96.91 215	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 85	97.12 26	87.13 89	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	93.92 169	96.72 56	81.96 207	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	84.15 151	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	94.07 158	96.78 50	81.61 225	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	94.07 158	96.78 50	81.86 220	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	94.02 164	96.76 53	81.86 220	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	94.40 126	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	85.68 120	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	95.54 100	86.75 20	94.57 115	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	95.54 100	86.36 33	94.57 115	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	94.07 158	96.73 54	81.46 228	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	94.12 150	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							94.12 150		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	94.06 161	96.66 62	80.09 239	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	95.42 105	85.04 55	93.06 213	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	93.24 206	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	95.36 106	85.47 51	94.68 107	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	95.36 106	84.61 60	94.68 107	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	85.15 131	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 96	97.17 24	86.26 110	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	86.13 182	94.85 16	98.54 7	86.60 26	96.93 12	97.19 22	90.66 22	92.85 36	23.41 350	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	97.76 138	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	86.90 100	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	95.01 122	83.51 90	94.48 118	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	94.36 136	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	94.86 130	83.20 96	94.40 126	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 96	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 90	80.50 162	97.33 3	95.25 160	86.15 112	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 82	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	93.39 180	83.72 83	94.43 124	97.12 26	89.80 31	86.46 135	93.32 142	83.16 55	97.23 192	84.92 114	81.02 273	94.49 182

1121		90.42 85	89.49 89	93.20 62	97.27 50	84.46 67	92.63 225	95.51 138	71.01 316	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	71.09 315	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	78.89 249	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 84	85.83 48	94.89 91	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	85.77 117	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 96	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	94.66 110	96.66 62	82.69 196	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 93	80.95 150	92.68 224	96.22 86	81.91 210	86.66 133	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	94.37 148	80.14 166	93.46 195	95.80 115	86.46 106	91.35 71	93.77 135	82.21 65	98.09 121	87.57 88	94.95 95	97.55 71

nrg030		91.08 74	90.39 74	93.17 64	93.07 189	86.91 14	96.41 24	96.26 82	88.30 64	88.37 100	94.85 99	82.19 66	97.64 145	91.09 53	82.95 245	94.96 150

UniMVSNet (Re)		89.80 98	89.07 100	92.01 104	93.60 176	84.52 63	94.78 99	97.47 5	89.26 41	86.44 138	92.32 179	82.10 67	97.39 178	84.81 117	80.84 277	94.12 194

testdata				90.49 161	96.40 67	77.89 241		95.37 153	72.51 305	93.63 25	96.69 38	82.08 68	97.65 143	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	94.37 132	96.24 85	86.39 108	87.41 119	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	93.60 190	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 97	85.73 50	94.94 88	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	93.71 173	79.85 176	95.77 45	97.59 2	89.31 40	86.27 141	94.67 103	81.93 72	97.01 207	84.26 126	88.09 202	94.71 165

FIs		90.51 84	90.35 75	90.99 144	93.99 163	80.98 148	95.73 46	97.54 3	89.15 44	86.72 132	94.68 102	81.83 73	97.24 190	85.18 111	88.31 199	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	94.35 151	83.39 93	94.60 112	95.10 169	87.10 90	90.57 78	93.10 153	81.43 75	98.07 123	89.29 69	94.48 104	97.59 68

MVS_111021_LR		92.47 55	92.29 55	92.98 72	95.99 87	84.43 71	93.08 211	96.09 94	88.20 69	91.12 74	95.72 78	81.33 76	97.76 138	91.74 46	97.37 61	96.75 95

mvs_anonymous		89.37 113	89.32 94	89.51 212	93.47 178	74.22 276	91.65 253	94.83 185	82.91 190	85.45 168	93.79 134	81.23 77	96.36 246	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	93.92 169	96.83 46	83.49 167	89.10 92	92.26 183	81.04 78	98.85 73	86.72 103	87.86 204	92.35 273

PVSNet_Blended		90.73 78	90.32 76	91.98 107	96.12 78	81.25 139	92.55 229	96.83 46	82.04 206	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 99	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	82.39 198	89.13 91	94.27 116	80.32 82	98.46 92	80.16 186	96.71 70	94.33 187

PVSNet_Blended_VisFu		91.38 68	90.91 69	92.80 78	96.39 68	83.17 97	94.87 94	96.66 62	83.29 173	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	92.22 239	95.01 172	68.36 322	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	89.70 205	93.80 170	78.29 231	93.73 181	95.08 171	85.73 118	84.75 193	91.90 198	79.88 86	96.92 214	83.83 132	82.51 249	93.89 205
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	89.80 200	91.84 213	78.30 230	93.70 185	95.01 172	85.73 118	87.15 123	95.28 85	79.87 87	97.21 194	83.81 133	87.36 208	93.88 207

TAPA-MVS	84.62 6	88.16 140	87.01 151	91.62 122	96.64 61	80.65 156	94.39 128	96.21 89	76.38 272	86.19 143	95.44 82	79.75 88	98.08 122	62.75 315	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	94.74 132	80.81 154	93.54 191	95.10 169	83.11 176	86.82 131	90.67 242	79.74 89	97.75 141	80.51 179	93.55 117	96.57 99

pcd_1.5k_mvsjas		6.64 333	8.86 334	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	79.70 90	0.00 357	0.00 354	0.00 355	0.00 355

PS-MVSNAJss		89.97 93	89.62 87	91.02 142	91.90 211	80.85 153	95.26 70	95.98 101	86.26 110	86.21 142	94.29 113	79.70 90	97.65 143	88.87 73	88.10 200	94.57 175

PS-MVSNAJ		91.18 72	90.92 68	91.96 108	95.26 112	82.60 118	92.09 244	95.70 122	86.27 109	91.84 62	92.46 173	79.70 90	98.99 59	89.08 70	95.86 82	94.29 188

xiu_mvs_v2_base		91.13 73	90.89 70	91.86 113	94.97 125	82.42 119	92.24 238	95.64 128	86.11 114	91.74 67	93.14 151	79.67 93	98.89 66	89.06 71	95.46 89	94.28 189

WR-MVS_H		87.80 155	87.37 137	89.10 229	93.23 185	78.12 235	95.61 54	97.30 17	87.90 74	83.72 217	92.01 194	79.65 94	96.01 258	76.36 229	80.54 281	93.16 248

EPNet		91.79 60	91.02 67	94.10 45	90.10 288	85.25 54	96.03 34	92.05 250	92.83 1	87.39 121	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	93.04 191	84.16 76	94.77 100	96.25 84	89.05 45	80.04 267	93.29 145	79.02 96	97.05 205	81.71 162	80.05 287	94.59 173

TAMVS		89.21 115	88.29 121	91.96 108	93.71 173	82.62 117	93.30 201	94.19 202	82.22 201	87.78 115	93.94 126	78.83 97	96.95 212	77.70 218	92.98 131	96.32 103

1112_ss		88.42 132	87.33 138	91.72 119	94.92 127	80.98 148	92.97 217	94.54 192	78.16 262	83.82 215	93.88 131	78.78 98	97.91 133	79.45 200	89.41 173	96.26 105

CDS-MVSNet		89.45 107	88.51 111	92.29 97	93.62 175	83.61 88	93.01 214	94.68 189	81.95 208	87.82 114	93.24 147	78.69 99	96.99 208	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	95.47 104	81.15 144	92.38 234	94.78 187	83.11 176	89.06 94	94.32 111	78.67 100	96.61 233	81.57 163	90.89 155	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	81.89 212	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 92	81.38 137	96.95 9	93.69 222	89.72 34	89.50 89	95.98 68	78.57 102	97.77 137	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	93.52 192	95.93 104	86.95 97	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	86.08 185	92.70 81	94.02 158	84.43 71	89.27 282	95.87 111	73.62 295	84.43 201	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	88.27 253	94.71 135	72.41 296	93.15 207	90.98 282	87.77 78	79.25 273	91.96 195	78.35 105	95.75 269	83.04 138	95.62 84	96.65 97

HY-MVS	83.01 12	89.03 121	87.94 129	92.29 97	94.86 130	82.77 108	92.08 245	94.49 193	81.52 227	86.93 127	92.79 168	78.32 106	98.23 102	79.93 190	90.55 156	95.88 121

diffmvs		89.07 118	88.32 119	91.34 129	93.24 184	79.79 177	92.29 237	94.98 175	80.24 236	87.38 122	92.45 174	78.02 107	97.33 180	83.29 136	92.93 132	96.91 90

MVS		87.44 175	86.10 184	91.44 127	92.61 201	83.62 87	92.63 225	95.66 125	67.26 326	81.47 247	92.15 185	77.95 108	98.22 103	79.71 196	95.48 87	92.47 268

MVSFormer		91.68 65	91.30 61	92.80 78	93.86 167	83.88 80	95.96 38	95.90 108	84.66 140	91.76 65	94.91 94	77.92 109	97.30 182	89.64 67	97.11 63	97.24 76

lupinMVS		90.92 75	90.21 77	93.03 70	93.86 167	83.88 80	92.81 220	93.86 218	79.84 241	91.76 65	94.29 113	77.92 109	98.04 125	90.48 63	97.11 63	97.17 81

Test_1112_low_res		87.65 159	86.51 174	91.08 138	94.94 126	79.28 202	91.77 247	94.30 200	76.04 277	83.51 223	92.37 177	77.86 111	97.73 142	78.69 209	89.13 186	96.22 106

VNet		92.24 57	91.91 56	93.24 61	96.59 63	83.43 91	94.84 95	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	93.04 191	83.72 83	94.47 121	96.59 67	89.50 36	86.46 135	93.29 145	77.25 113	97.23 192	84.92 114	81.02 273	94.59 173

Baseline_NR-MVSNet		87.07 187	86.63 172	88.40 250	91.44 225	77.87 242	94.23 141	92.57 240	84.12 152	85.74 153	92.08 190	77.25 113	96.04 255	82.29 152	79.94 290	91.30 291

jason		90.80 76	90.10 80	92.90 75	93.04 191	83.53 89	93.08 211	94.15 204	80.22 237	91.41 70	94.91 94	76.87 115	97.93 132	90.28 64	96.90 66	97.24 76
jason: jason.
PAPM		86.68 195	85.39 200	90.53 153	93.05 190	79.33 201	89.79 275	94.77 188	78.82 251	81.95 243	93.24 147	76.81 116	97.30 182	66.94 293	93.16 128	94.95 157

Vis-MVSNet (Re-imp)		89.59 102	89.44 91	90.03 190	95.74 94	75.85 270	95.61 54	90.80 287	87.66 83	87.83 113	95.40 84	76.79 117	96.46 241	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	70.19 318	85.81 147	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	94.29 137	95.44 147	79.71 243	84.01 212	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	92.68 200	83.01 103	94.92 90	96.31 80	89.88 30	85.53 162	93.85 133	76.63 120	96.96 211	81.91 158	79.87 292	94.50 180

MAR-MVS		90.30 86	89.37 93	93.07 69	96.61 62	84.48 66	95.68 49	95.67 123	82.36 200	87.85 108	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		84.97 234	83.76 232	88.60 240	91.36 235	79.41 190	93.82 174	94.04 207	83.00 186	76.61 287	86.60 296	76.19 122	95.43 281	80.39 180	71.79 314	90.96 296

v6		87.98 145	87.25 142	90.16 175	91.36 235	79.39 195	94.37 132	95.27 159	84.48 143	85.78 148	91.51 214	76.15 123	97.46 155	84.46 122	81.88 260	93.62 231

v1neww		87.98 145	87.25 142	90.16 175	91.38 232	79.41 190	94.37 132	95.28 156	84.48 143	85.77 149	91.53 212	76.12 124	97.45 157	84.45 123	81.89 258	93.61 232

v7new		87.98 145	87.25 142	90.16 175	91.38 232	79.41 190	94.37 132	95.28 156	84.48 143	85.77 149	91.53 212	76.12 124	97.45 157	84.45 123	81.89 258	93.61 232

WR-MVS		88.38 133	87.67 132	90.52 159	93.30 183	80.18 164	93.26 204	95.96 103	88.57 59	85.47 167	92.81 166	76.12 124	96.91 215	81.24 165	82.29 251	94.47 185

v16		84.96 235	83.74 234	88.62 238	91.40 230	79.48 184	93.83 172	94.04 207	83.03 183	76.54 288	86.59 297	76.11 127	95.42 282	80.33 183	71.80 313	90.95 298

v17		84.93 237	83.70 236	88.62 238	91.36 235	79.48 184	93.83 172	94.03 209	83.04 182	76.51 289	86.57 298	76.05 128	95.42 282	80.31 185	71.65 315	90.96 296

v8		87.50 174	86.71 162	89.89 195	91.37 234	79.40 194	94.50 117	95.38 151	84.81 137	83.60 221	91.33 222	76.05 128	97.42 168	82.84 142	80.51 284	92.84 258

v148		87.04 188	86.32 178	89.21 225	90.94 263	77.26 258	93.71 184	94.43 195	84.84 136	84.36 205	90.80 240	76.04 130	97.05 205	82.12 153	79.60 293	93.31 243

v15		84.79 240	83.53 241	88.57 244	91.30 246	79.41 190	93.70 185	94.01 210	83.06 179	76.27 290	86.42 302	76.03 131	95.38 284	80.01 187	71.00 318	90.92 299

V14		84.79 240	83.52 242	88.57 244	91.32 242	79.43 189	93.72 183	94.01 210	83.06 179	76.22 291	86.43 299	76.01 132	95.37 285	79.96 189	70.99 319	90.91 300

V9		84.77 242	83.50 243	88.58 241	91.33 240	79.46 186	93.75 179	94.00 213	83.07 178	76.07 296	86.43 299	75.97 133	95.37 285	79.91 192	70.93 321	90.91 300

v1		87.85 150	87.10 145	90.11 186	91.21 249	79.24 206	94.09 154	95.24 161	84.44 147	85.70 154	91.31 225	75.96 134	97.45 157	84.18 127	81.73 265	93.64 228

3Dnovator+	87.14 4	92.42 56	91.37 60	95.55 2	95.63 98	88.73 2	97.07 8	96.77 52	90.84 17	84.02 211	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	90.11 186	91.23 247	79.25 204	94.08 156	95.24 161	84.44 147	85.69 156	91.31 225	75.91 136	97.44 164	84.17 128	81.74 264	93.63 230

divwei89l23v2f112		87.84 151	87.09 146	90.10 188	91.23 247	79.24 206	94.09 154	95.24 161	84.44 147	85.70 154	91.31 225	75.91 136	97.44 164	84.17 128	81.73 265	93.64 228

v13		84.72 245	83.44 246	88.58 241	91.31 245	79.52 180	93.77 177	94.00 213	83.03 183	75.85 299	86.38 304	75.84 138	95.35 288	79.83 194	70.95 320	90.87 303

v12		84.74 243	83.46 244	88.58 241	91.32 242	79.50 181	93.75 179	94.01 210	83.06 179	75.98 298	86.41 303	75.82 139	95.36 287	79.87 193	70.89 322	90.89 302

BH-untuned		88.60 130	88.13 125	90.01 192	95.24 119	78.50 225	93.29 202	94.15 204	84.75 138	84.46 199	93.40 139	75.76 140	97.40 175	77.59 219	94.52 103	94.12 194

BH-w/o		87.57 172	87.05 150	89.12 227	94.90 129	77.90 240	92.41 232	93.51 224	82.89 191	83.70 218	91.34 221	75.75 141	97.07 203	75.49 236	93.49 119	92.39 271

cdsmvs_eth3d_5k		22.14 328	29.52 329	0.00 344	0.00 358	0.00 359	0.00 350	95.76 118	0.00 354	0.00 355	94.29 113	75.66 142	0.00 357	0.00 354	0.00 355	0.00 355

CNLPA		89.07 118	87.98 127	92.34 95	96.87 57	84.78 58	94.08 156	93.24 227	81.41 229	84.46 199	95.13 91	75.57 143	96.62 231	77.21 223	93.84 114	95.61 132

v11		84.67 248	83.41 247	88.44 249	91.32 242	79.13 209	93.69 188	93.99 215	82.81 192	76.20 292	86.24 306	75.48 144	95.35 288	79.53 198	71.48 317	90.85 304

CHOSEN 1792x2688		88.84 125	87.69 131	92.30 96	96.14 77	81.42 136	90.01 271	95.86 112	74.52 290	87.41 119	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 95	87.58 7	94.71 106	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	88.74 234	93.12 188	76.59 264	95.29 63	96.58 69	88.43 61	83.49 224	92.98 160	75.28 147	95.83 265	78.97 206	81.15 270	93.79 213

v7		87.75 156	86.96 152	90.12 181	91.20 250	79.50 181	94.28 138	95.46 141	83.45 168	85.75 151	91.56 211	75.13 148	97.43 166	83.60 134	82.18 253	93.42 241

v10		87.25 181	86.38 175	89.85 196	91.19 252	79.50 181	94.48 118	95.45 145	83.79 158	83.62 220	91.19 230	75.13 148	97.42 168	81.94 157	80.60 279	92.63 264

Vis-MVSNet		91.75 62	91.23 63	93.29 59	95.32 109	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	94.05 157	80.78 155	91.71 250	95.38 151	81.55 226	88.63 96	93.91 130	75.04 151	95.47 280	82.47 148	91.61 141	96.57 99

v1144		87.61 170	86.79 159	90.06 189	91.01 258	79.34 198	93.95 168	95.42 150	83.36 172	85.66 158	91.31 225	74.98 152	97.42 168	83.37 135	82.06 254	93.42 241

V42		87.68 158	86.86 154	90.15 179	90.58 277	80.14 166	94.24 140	95.28 156	83.66 160	85.67 157	91.33 222	74.73 153	97.41 173	84.43 125	81.83 261	92.89 256

XVG-OURS-SEG-HR		89.95 94	89.45 90	91.47 126	94.00 162	81.21 142	91.87 246	96.06 98	85.78 116	88.55 97	95.73 77	74.67 154	97.27 186	88.71 74	89.64 171	95.91 119

v2v482		87.84 151	87.06 149	90.17 174	90.99 259	79.23 208	94.00 166	95.13 168	84.87 135	85.53 162	92.07 192	74.45 155	97.45 157	84.71 119	81.75 263	93.85 211

CLD-MVS		89.47 106	88.90 105	91.18 134	94.22 152	82.07 124	92.13 242	96.09 94	87.90 74	85.37 178	92.45 174	74.38 156	97.56 148	87.15 95	90.43 157	93.93 203
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	90.03 190	92.14 207	80.60 159	93.76 178	95.23 164	82.94 188	84.60 195	94.02 122	74.27 157	95.49 279	81.04 167	83.68 238	94.01 202

HQP_MVS		90.60 83	90.19 78	91.82 116	94.70 136	82.73 112	95.85 42	96.22 86	90.81 18	86.91 128	94.86 97	74.23 158	98.12 108	88.15 79	89.99 164	94.63 169

plane_prior6					94.52 142	82.75 109						74.23 158

v144192		87.19 185	86.35 176	89.74 201	90.64 276	78.24 233	93.92 169	95.43 148	81.93 209	85.51 164	91.05 237	74.21 160	97.45 157	82.86 141	81.56 267	93.53 236

VPA-MVSNet		89.62 100	88.96 102	91.60 123	93.86 167	82.89 107	95.46 57	97.33 14	87.91 73	88.43 99	93.31 143	74.17 161	97.40 175	87.32 93	82.86 247	94.52 178

ab-mvs		89.41 110	88.35 116	92.60 83	95.15 120	82.65 116	92.20 240	95.60 129	83.97 153	88.55 97	93.70 138	74.16 162	98.21 104	82.46 149	89.37 174	96.94 89

1314		87.51 173	86.57 173	90.34 171	92.42 203	79.74 179	92.63 225	95.35 155	78.35 258	80.14 265	91.62 207	74.05 163	97.15 196	81.05 166	93.53 118	94.12 194

test_djsdf		89.03 121	88.64 109	90.21 173	90.74 272	79.28 202	95.96 38	95.90 108	84.66 140	85.33 180	92.94 161	74.02 164	97.30 182	89.64 67	88.53 192	94.05 199

AdaColmap		89.89 97	89.07 100	92.37 94	97.41 42	83.03 101	94.42 125	95.92 105	82.81 192	86.34 140	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 86	80.63 157	90.01 271	95.79 116	73.42 296	87.68 117	92.10 189	73.86 166	97.96 129	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	94.17 153	81.56 129	94.39 128	96.04 99	88.81 50	85.43 171	93.97 125	73.83 167	97.96 129	87.11 97	89.77 169	94.50 180

3Dnovator	86.66 5	91.73 63	90.82 71	94.44 35	94.59 140	86.37 32	97.18 6	97.02 31	89.20 42	84.31 207	96.66 41	73.74 169	99.17 35	86.74 100	97.96 50	97.79 63

EPNet_dtu		86.49 200	85.94 189	88.14 258	90.24 286	72.82 288	94.11 152	92.20 246	86.66 104	79.42 272	92.36 178	73.52 170	95.81 267	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)		84.43 250	83.06 251	88.54 246	91.72 217	78.44 226	95.18 74	92.82 234	82.73 194	79.67 269	92.12 186	73.49 171	95.96 260	71.10 266	68.73 329	91.21 292

Effi-MVS+-dtu		88.65 129	88.35 116	89.54 209	93.33 181	76.39 265	94.47 121	94.36 197	87.70 79	85.43 171	89.56 264	73.45 172	97.26 188	85.57 109	91.28 143	94.97 147

mvs-test1		89.45 107	89.14 98	90.38 168	93.33 181	77.63 250	94.95 87	94.36 197	87.70 79	87.10 125	92.81 166	73.45 172	98.03 126	85.57 109	93.04 130	95.48 134

PEN-MVS		86.80 191	86.27 180	88.40 250	92.32 205	75.71 271	95.18 74	96.38 78	87.97 71	82.82 231	93.15 150	73.39 174	95.92 261	76.15 233	79.03 295	93.59 234

v1192		87.25 181	86.33 177	90.00 193	90.76 271	79.04 210	93.80 175	95.48 140	82.57 197	85.48 166	91.18 231	73.38 175	97.42 168	82.30 151	82.06 254	93.53 236

QAPM		89.51 104	88.15 124	93.59 57	94.92 127	84.58 61	96.82 18	96.70 58	78.43 257	83.41 225	96.19 62	73.18 176	99.30 29	77.11 225	96.54 75	96.89 92

tpmrst		85.35 226	84.99 205	86.43 288	90.88 268	67.88 319	88.71 289	91.43 270	80.13 238	86.08 145	88.80 271	73.05 177	96.02 257	82.48 147	83.40 244	95.40 137

PS-CasMVS		87.32 178	86.88 153	88.63 237	92.99 194	76.33 267	95.33 58	96.61 66	88.22 68	83.30 227	93.07 154	73.03 178	95.79 268	78.36 211	81.00 275	93.75 219

DTE-MVSNet		86.11 204	85.48 198	87.98 260	91.65 221	74.92 274	94.93 89	95.75 119	87.36 86	82.26 236	93.04 155	72.85 179	95.82 266	74.04 249	77.46 300	93.20 246

MVSTER		88.84 125	88.29 121	90.51 160	92.95 195	80.44 163	93.73 181	95.01 172	84.66 140	87.15 123	93.12 152	72.79 180	97.21 194	87.86 84	87.36 208	93.87 208

pcd1.5k->3k		37.02 326	38.84 327	31.53 339	92.33 204	0.00 359	0.00 350	96.13 92	0.00 354	0.00 355	0.00 356	72.70 181	0.00 357	0.00 354	88.43 196	94.60 172

v1921920		86.97 189	86.06 186	89.69 206	90.53 281	78.11 236	93.80 175	95.43 148	81.90 211	85.33 180	91.05 237	72.66 182	97.41 173	82.05 155	81.80 262	93.53 236

DP-MVS		87.25 181	85.36 201	92.90 75	97.65 34	83.24 95	94.81 97	92.00 252	74.99 285	81.92 244	95.00 93	72.66 182	99.05 46	66.92 295	92.33 138	96.40 101

v7n		86.81 190	85.76 192	89.95 194	90.72 273	79.25 204	95.07 80	95.92 105	84.45 146	82.29 235	90.86 239	72.60 184	97.53 150	79.42 203	80.52 283	93.08 253

v748		86.27 202	85.28 202	89.25 224	90.26 285	77.58 257	94.89 91	95.50 139	84.28 150	81.41 249	90.46 250	72.57 185	97.32 181	79.81 195	78.36 296	92.84 258

OPM-MVS		90.12 89	89.56 88	91.82 116	93.14 187	83.90 79	94.16 149	95.74 120	88.96 49	87.86 107	95.43 83	72.48 186	97.91 133	88.10 82	90.18 163	93.65 227

LS3D		87.89 149	86.32 178	92.59 84	96.07 84	82.92 106	95.23 71	94.92 180	75.66 279	82.89 230	95.98 68	72.48 186	99.21 32	68.43 286	95.23 94	95.64 131

pm-mvs1		86.61 196	85.54 194	89.82 197	91.44 225	80.18 164	95.28 69	94.85 183	83.84 155	81.66 246	92.62 171	72.45 188	96.48 239	79.67 197	78.06 297	92.82 260

PMMVS		85.71 222	84.96 208	87.95 261	88.90 303	77.09 259	88.68 290	90.06 299	72.32 306	86.47 134	90.76 241	72.15 189	94.40 300	81.78 161	93.49 119	92.36 272

PatchmatchNet		85.85 211	84.70 216	89.29 223	91.76 216	75.54 272	88.49 292	91.30 272	81.63 224	85.05 183	88.70 273	71.71 190	96.24 250	74.61 246	89.05 187	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		86.50 198	85.54 194	89.39 216	89.13 299	78.99 211	94.73 101	95.54 134	83.59 161	82.10 239	90.61 244	71.60 192	97.45 157	82.52 145	80.01 288	91.74 282

v52		86.50 198	85.53 197	89.39 216	89.17 298	78.99 211	94.72 104	95.54 134	83.59 161	82.10 239	90.60 245	71.59 193	97.45 157	82.52 145	79.99 289	91.73 283

patchmatchnet-post											83.76 315	71.53 194	96.48 239

v1240		86.78 192	85.85 190	89.56 208	90.45 282	77.79 244	93.61 189	95.37 153	81.65 222	85.43 171	91.15 233	71.50 195	97.43 166	81.47 164	82.05 256	93.47 240

anonymousdsp		87.84 151	87.09 146	90.12 181	89.13 299	80.54 160	94.67 109	95.55 132	82.05 204	83.82 215	92.12 186	71.47 196	97.15 196	87.15 95	87.80 205	92.67 262

Patchmatch-test		81.37 277	79.30 281	87.58 267	90.92 265	74.16 278	80.99 332	87.68 328	70.52 317	76.63 286	88.81 270	71.21 197	92.76 317	60.01 323	86.93 214	95.83 124

F-COLMAP		87.95 148	86.80 158	91.40 128	96.35 70	80.88 152	94.73 101	95.45 145	79.65 244	82.04 242	94.61 105	71.13 198	98.50 90	76.24 232	91.05 149	94.80 163

pmmvs4		85.43 224	83.86 231	90.16 175	90.02 291	82.97 105	90.27 266	92.67 238	75.93 278	80.73 256	91.74 202	71.05 199	95.73 270	78.85 207	83.46 242	91.78 281

CR-MVSNet		85.35 226	83.76 232	90.12 181	90.58 277	79.34 198	85.24 315	91.96 256	78.27 259	85.55 160	87.87 287	71.03 200	95.61 271	73.96 251	89.36 175	95.40 137

Patchmtry		82.71 264	80.93 267	88.06 259	90.05 290	76.37 266	84.74 317	91.96 256	72.28 307	81.32 251	87.87 287	71.03 200	95.50 278	68.97 282	80.15 286	92.32 274

PatchFormer-LS_test		86.02 207	85.13 204	88.70 235	91.52 222	74.12 279	91.19 261	92.09 248	82.71 195	84.30 208	87.24 293	70.87 202	96.98 209	81.04 167	85.17 225	95.00 146

RPMNet		83.18 262	80.87 268	90.12 181	90.58 277	79.34 198	85.24 315	90.78 288	71.44 311	85.55 160	82.97 320	70.87 202	95.61 271	61.01 319	89.36 175	95.40 137

Patchmatch-RL test		81.67 271	79.96 275	86.81 286	85.42 320	71.23 302	82.17 330	87.50 330	78.47 256	77.19 285	82.50 321	70.81 204	93.48 309	82.66 144	72.89 310	95.71 129

CostFormer		85.77 216	84.94 209	88.26 254	91.16 255	72.58 295	89.47 280	91.04 281	76.26 275	86.45 137	89.97 257	70.74 205	96.86 218	82.35 150	87.07 213	95.34 140

sam_mvs												70.60 206

xiu_mvs_v1_base_debu		90.64 80	90.05 82	92.40 91	93.97 164	84.46 67	93.32 197	95.46 141	85.17 128	92.25 53	94.03 119	70.59 207	98.57 87	90.97 54	94.67 97	94.18 190

xiu_mvs_v1_base		90.64 80	90.05 82	92.40 91	93.97 164	84.46 67	93.32 197	95.46 141	85.17 128	92.25 53	94.03 119	70.59 207	98.57 87	90.97 54	94.67 97	94.18 190

xiu_mvs_v1_base_debi		90.64 80	90.05 82	92.40 91	93.97 164	84.46 67	93.32 197	95.46 141	85.17 128	92.25 53	94.03 119	70.59 207	98.57 87	90.97 54	94.67 97	94.18 190

test_post											10.29 351	70.57 210	95.91 263

CANet_DTU		90.26 88	89.41 92	92.81 77	93.46 179	83.01 103	93.48 193	94.47 194	89.43 37	87.76 116	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	95.28 110	79.45 188	92.89 219	93.07 230	85.45 124	86.91 128	94.84 100	70.35 212	97.76 138	73.97 250	94.59 101	95.85 122

Fast-Effi-MVS+-dtu		87.44 175	86.72 161	89.63 207	92.04 210	77.68 249	94.03 163	93.94 216	85.81 115	82.42 234	91.32 224	70.33 213	97.06 204	80.33 183	90.23 162	94.14 193

MDTV_nov1_ep13_2view						55.91 341	87.62 301		73.32 297	84.59 196		70.33 213		74.65 245		95.50 133

ACMM	84.12 9	89.14 116	88.48 115	91.12 135	94.65 139	81.22 141	95.31 59	96.12 93	85.31 127	85.92 146	94.34 109	70.19 215	98.06 124	85.65 108	88.86 189	94.08 198
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	94.47 144	81.49 132	95.30 61	96.14 90	86.73 102	85.45 168	95.16 89	69.89 216	98.10 114	87.70 86	89.23 178	93.77 217

LGP-MVS_train				91.12 135	94.47 144	81.49 132		96.14 90	86.73 102	85.45 168	95.16 89	69.89 216	98.10 114	87.70 86	89.23 178	93.77 217

CHOSEN 280x420		85.15 230	83.99 229	88.65 236	92.47 202	78.40 228	79.68 335	92.76 235	74.90 287	81.41 249	89.59 262	69.85 218	95.51 276	79.92 191	95.29 92	92.03 278

LTVRE_ROB	82.13 13	86.26 203	84.90 211	90.34 171	94.44 147	81.50 131	92.31 236	94.89 181	83.03 183	79.63 270	92.67 169	69.69 219	97.79 136	71.20 263	86.26 216	91.72 284
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
OpenMVS	83.78 11	88.74 128	87.29 139	93.08 67	92.70 199	85.39 52	96.57 22	96.43 74	78.74 254	80.85 255	96.07 66	69.64 220	99.01 55	78.01 216	96.65 72	94.83 161

MDTV_nov1_ep13			83.56 240		91.69 220	69.93 313	87.75 299	91.54 267	78.60 255	84.86 192	88.90 269	69.54 221	96.03 256	70.25 268	88.93 188

PatchT		82.68 265	81.27 263	86.89 284	90.09 289	70.94 307	84.06 322	90.15 296	74.91 286	85.63 159	83.57 316	69.37 222	94.87 298	65.19 306	88.50 194	94.84 160

VPNet		88.20 139	87.47 135	90.39 166	93.56 177	79.46 186	94.04 162	95.54 134	88.67 55	86.96 126	94.58 107	69.33 223	97.15 196	84.05 130	80.53 282	94.56 176

ACMP	84.23 8	89.01 123	88.35 116	90.99 144	94.73 133	81.27 138	95.07 80	95.89 110	86.48 105	83.67 219	94.30 112	69.33 223	97.99 128	87.10 99	88.55 191	93.72 221
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 296				9.81 352	69.31 225	95.53 274	76.65 228

tpmvs		83.35 261	82.07 258	87.20 279	91.07 257	71.00 306	88.31 294	91.70 260	78.91 248	80.49 261	87.18 294	69.30 226	97.08 202	68.12 290	83.56 240	93.51 239

thres200		87.21 184	86.24 181	90.12 181	95.36 106	78.53 219	93.26 204	92.10 247	86.42 107	88.00 106	91.11 235	69.24 227	98.00 127	69.58 276	91.04 150	93.83 212

tfpn200view9		87.58 171	86.64 170	90.41 165	95.99 87	78.64 215	94.58 113	91.98 254	86.94 98	88.09 101	91.77 200	69.18 228	98.10 114	70.13 271	91.10 144	94.48 183

thres400		87.62 165	86.64 170	90.57 151	95.99 87	78.64 215	94.58 113	91.98 254	86.94 98	88.09 101	91.77 200	69.18 228	98.10 114	70.13 271	91.10 144	94.96 150

tfpnnormal		84.72 245	83.23 249	89.20 226	92.79 198	80.05 169	94.48 118	95.81 114	82.38 199	81.08 253	91.21 229	69.01 230	96.95 212	61.69 317	80.59 280	90.58 309

conf200view11		87.65 159	86.71 162	90.46 164	96.12 78	78.55 217	95.03 83	91.58 263	87.15 87	88.06 104	92.29 181	68.91 231	98.10 114	70.13 271	91.10 144	94.71 165

thres100view900		87.63 163	86.71 162	90.38 168	96.12 78	78.55 217	95.03 83	91.58 263	87.15 87	88.06 104	92.29 181	68.91 231	98.10 114	70.13 271	91.10 144	94.48 183

thres600view7		87.65 159	86.67 165	90.59 150	96.08 83	78.72 213	94.88 93	91.58 263	87.06 95	88.08 103	92.30 180	68.91 231	98.10 114	70.05 275	91.10 144	94.96 150

view600		87.62 165	86.65 166	90.53 153	96.19 73	78.52 220	95.29 63	91.09 274	87.08 91	87.84 109	93.03 156	68.86 234	98.11 110	69.44 277	91.02 151	94.96 150

view800		87.62 165	86.65 166	90.53 153	96.19 73	78.52 220	95.29 63	91.09 274	87.08 91	87.84 109	93.03 156	68.86 234	98.11 110	69.44 277	91.02 151	94.96 150

conf0.05thres1000		87.62 165	86.65 166	90.53 153	96.19 73	78.52 220	95.29 63	91.09 274	87.08 91	87.84 109	93.03 156	68.86 234	98.11 110	69.44 277	91.02 151	94.96 150

tfpn		87.62 165	86.65 166	90.53 153	96.19 73	78.52 220	95.29 63	91.09 274	87.08 91	87.84 109	93.03 156	68.86 234	98.11 110	69.44 277	91.02 151	94.96 150

PatchMatch-RL		86.77 194	85.54 194	90.47 163	95.88 90	82.71 114	90.54 264	92.31 243	79.82 242	84.32 206	91.57 210	68.77 238	96.39 244	73.16 255	93.48 121	92.32 274

XVG-OURS		89.40 112	88.70 108	91.52 124	94.06 156	81.46 134	91.27 259	96.07 96	86.14 113	88.89 95	95.77 76	68.73 239	97.26 188	87.39 91	89.96 166	95.83 124

TR-MVS		86.78 192	85.76 192	89.82 197	94.37 148	78.41 227	92.47 231	92.83 233	81.11 232	86.36 139	92.40 176	68.73 239	97.48 153	73.75 253	89.85 168	93.57 235

tpm		84.73 244	84.02 228	86.87 285	90.33 283	68.90 316	89.06 286	89.94 302	80.85 234	85.75 151	89.86 259	68.54 241	95.97 259	77.76 217	84.05 234	95.75 128

DI_MVS_plusplus_test		88.15 141	86.82 156	92.14 102	90.67 275	81.07 145	93.01 214	94.59 191	83.83 157	77.78 280	90.63 243	68.51 242	98.16 106	88.02 83	94.37 108	97.17 81

test_normal		88.13 142	86.78 160	92.18 100	90.55 280	81.19 143	92.74 222	94.64 190	83.84 155	77.49 283	90.51 249	68.49 243	98.16 106	88.22 78	94.55 102	97.21 79

tfpn_ndepth		86.10 205	84.98 206	89.43 215	95.52 103	78.29 231	94.62 111	89.60 309	81.88 219	85.43 171	90.54 246	68.47 244	96.85 219	68.46 285	90.34 160	93.15 250

FMVSNet3		87.40 177	86.11 183	91.30 131	93.79 172	83.64 86	94.20 148	94.81 186	83.89 154	84.37 202	91.87 199	68.45 245	96.56 234	78.23 213	85.36 222	93.70 222

conf0.01		85.83 213	84.54 219	89.71 203	95.26 112	77.63 250	94.21 142	89.33 311	81.89 212	84.94 186	91.51 214	68.43 246	96.80 220	66.05 298	89.23 178	94.71 165

conf0.002		85.83 213	84.54 219	89.71 203	95.26 112	77.63 250	94.21 142	89.33 311	81.89 212	84.94 186	91.51 214	68.43 246	96.80 220	66.05 298	89.23 178	94.71 165

thresconf0.02		85.75 217	84.54 219	89.38 218	95.26 112	77.63 250	94.21 142	89.33 311	81.89 212	84.94 186	91.51 214	68.43 246	96.80 220	66.05 298	89.23 178	93.70 222

tfpn_n400		85.75 217	84.54 219	89.38 218	95.26 112	77.63 250	94.21 142	89.33 311	81.89 212	84.94 186	91.51 214	68.43 246	96.80 220	66.05 298	89.23 178	93.70 222

tfpnconf		85.75 217	84.54 219	89.38 218	95.26 112	77.63 250	94.21 142	89.33 311	81.89 212	84.94 186	91.51 214	68.43 246	96.80 220	66.05 298	89.23 178	93.70 222

tfpnview11		85.75 217	84.54 219	89.38 218	95.26 112	77.63 250	94.21 142	89.33 311	81.89 212	84.94 186	91.51 214	68.43 246	96.80 220	66.05 298	89.23 178	93.70 222

MVP-Stereo		85.97 209	84.86 212	89.32 222	90.92 265	82.19 122	92.11 243	94.19 202	78.76 253	78.77 275	91.63 206	68.38 252	96.56 234	75.01 243	93.95 111	89.20 316
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tfpn1000		86.06 206	84.92 210	89.49 213	95.54 100	77.79 244	94.72 104	89.07 318	82.05 204	85.36 179	91.94 196	68.32 253	96.65 229	67.04 292	90.24 161	94.02 201

tpm cat1		81.96 269	80.27 271	87.01 280	91.09 256	71.02 305	87.38 302	91.53 268	66.25 327	80.17 263	86.35 305	68.22 254	96.15 253	69.16 281	82.29 251	93.86 210

tpm2		84.08 252	82.94 252	87.48 271	91.39 231	71.27 301	89.23 284	90.37 292	71.95 309	84.64 194	89.33 265	67.30 255	96.55 236	75.17 240	87.09 212	94.63 169

test-LLR		85.87 210	85.41 199	87.25 275	90.95 261	71.67 299	89.55 276	89.88 304	83.41 169	84.54 197	87.95 284	67.25 256	95.11 293	81.82 159	93.37 124	94.97 147

test0.0.03 1		82.41 267	81.69 260	84.59 301	88.23 308	72.89 287	90.24 267	87.83 326	83.41 169	79.86 268	89.78 260	67.25 256	88.99 329	65.18 307	83.42 243	91.90 280

CVMVSNet		84.69 247	84.79 214	84.37 303	91.84 213	64.92 327	93.70 185	91.47 269	66.19 328	86.16 144	95.28 85	67.18 258	93.33 311	80.89 172	90.42 158	94.88 159

Patchmatch-test1		85.81 215	84.71 215	89.12 227	92.15 206	76.60 263	91.12 262	91.69 261	83.53 166	85.50 165	88.56 276	66.79 259	95.00 296	72.69 257	90.35 159	95.76 127

IterMVS		84.88 238	83.98 230	87.60 266	91.44 225	76.03 269	90.18 269	92.41 242	83.24 175	81.06 254	90.42 251	66.60 260	94.28 301	79.46 199	80.98 276	92.48 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 179	85.98 187	91.08 138	94.01 159	83.10 98	95.14 77	94.94 176	83.57 163	84.37 202	91.64 203	66.59 261	96.34 247	78.23 213	85.36 222	93.79 213

test1		87.26 179	85.98 187	91.08 138	94.01 159	83.10 98	95.14 77	94.94 176	83.57 163	84.37 202	91.64 203	66.59 261	96.34 247	78.23 213	85.36 222	93.79 213

FMVSNet2		87.19 185	85.82 191	91.30 131	94.01 159	83.67 85	94.79 98	94.94 176	83.57 163	83.88 213	92.05 193	66.59 261	96.51 237	77.56 220	85.01 226	93.73 220

EPMVS		83.90 255	82.70 256	87.51 268	90.23 287	72.67 291	88.62 291	81.96 341	81.37 230	85.01 184	88.34 279	66.31 264	94.45 299	75.30 239	87.12 211	95.43 136

semantic-postprocess				88.18 257	91.71 218	76.87 262		92.65 239	85.40 125	81.44 248	90.54 246	66.21 265	95.00 296	81.04 167	81.05 271	92.66 263

tpmp4_e23		83.87 256	82.33 257	88.48 247	91.46 224	72.82 288	89.82 274	91.57 266	73.02 301	81.86 245	89.05 267	66.20 266	96.97 210	71.57 261	86.39 215	95.66 130

MDA-MVSNet_test_wron		79.21 293	77.19 293	85.29 296	88.22 309	72.77 290	85.87 310	90.06 299	74.34 291	62.62 334	87.56 290	66.14 267	91.99 321	66.90 296	73.01 308	91.10 295

YYNet1		79.22 292	77.20 292	85.28 297	88.20 310	72.66 292	85.87 310	90.05 301	74.33 292	62.70 333	87.61 289	66.09 268	92.03 320	66.94 293	72.97 309	91.15 293

JIA-IIPM		81.04 280	78.98 286	87.25 275	88.64 304	73.48 284	81.75 331	89.61 308	73.19 298	82.05 241	73.71 335	66.07 269	95.87 264	71.18 265	84.60 229	92.41 270

MSDG		84.86 239	83.09 250	90.14 180	93.80 170	80.05 169	89.18 285	93.09 229	78.89 249	78.19 276	91.91 197	65.86 270	97.27 186	68.47 284	88.45 195	93.11 251

jajsoiax		88.24 138	87.50 133	90.48 162	90.89 267	80.14 166	95.31 59	95.65 127	84.97 134	84.24 209	94.02 122	65.31 271	97.42 168	88.56 75	88.52 193	93.89 205

cascas		86.43 201	84.98 206	90.80 148	92.10 209	80.92 151	90.24 267	95.91 107	73.10 299	83.57 222	88.39 278	65.15 272	97.46 155	84.90 116	91.43 142	94.03 200

ADS-MVSNet2		81.66 272	79.71 278	87.50 269	91.35 238	74.19 277	83.33 326	88.48 322	72.90 302	82.24 237	85.77 308	64.98 273	93.20 313	64.57 309	83.74 236	95.12 142

ADS-MVSNet		81.56 274	79.78 276	86.90 283	91.35 238	71.82 298	83.33 326	89.16 317	72.90 302	82.24 237	85.77 308	64.98 273	93.76 305	64.57 309	83.74 236	95.12 142

pmmvs5		84.21 251	82.84 255	88.34 252	88.95 302	76.94 261	92.41 232	91.91 258	75.63 280	80.28 262	91.18 231	64.59 275	95.57 273	77.09 226	83.47 241	92.53 266

PVSNet	78.82 18	85.55 223	84.65 217	88.23 256	94.72 134	71.93 297	87.12 303	92.75 236	78.80 252	84.95 185	90.53 248	64.43 276	96.71 228	74.74 244	93.86 113	96.06 115

UGNet		89.95 94	88.95 103	92.95 73	94.51 143	83.31 94	95.70 48	95.23 164	89.37 39	87.58 118	93.94 126	64.00 277	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		85.07 231	84.27 225	87.48 271	92.91 196	70.62 309	91.69 252	92.46 241	76.20 276	82.67 233	95.22 88	63.94 278	97.29 185	77.51 221	85.80 219	94.53 177

mvs_tets		88.06 144	87.28 140	90.38 168	90.94 263	79.88 174	95.22 72	95.66 125	85.10 132	84.21 210	93.94 126	63.53 279	97.40 175	88.50 76	88.40 198	93.87 208

dp		81.47 276	80.23 272	85.17 298	89.92 293	65.49 326	86.74 304	90.10 298	76.30 274	81.10 252	87.12 295	62.81 280	95.92 261	68.13 289	79.88 291	94.09 197

LFMVS		90.08 90	89.13 99	92.95 73	96.71 60	82.32 121	96.08 32	89.91 303	86.79 101	92.15 58	96.81 33	62.60 281	98.34 98	87.18 94	93.90 112	98.19 36

DWT-MVSNet_test		84.95 236	83.68 237	88.77 232	91.43 228	73.75 282	91.74 249	90.98 282	80.66 235	83.84 214	87.36 291	62.44 282	97.11 200	78.84 208	85.81 218	95.46 135

Anonymous20231206		81.03 281	79.77 277	84.82 300	87.85 315	70.26 311	91.42 256	92.08 249	73.67 294	77.75 281	89.25 266	62.43 283	93.08 315	61.50 318	82.00 257	91.12 294

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	62.09 284	98.64 82	90.95 57	92.62 136	97.93 56

MS-PatchMatch		85.05 232	84.16 226	87.73 264	91.42 229	78.51 224	91.25 260	93.53 223	77.50 264	80.15 264	91.58 208	61.99 285	95.51 276	75.69 235	94.35 109	89.16 317

OurMVSNet-221017-0		85.35 226	84.64 218	87.49 270	90.77 270	72.59 294	94.01 165	94.40 196	84.72 139	79.62 271	93.17 149	61.91 286	96.72 226	81.99 156	81.16 268	93.16 248

test20.03		79.95 287	79.08 284	82.55 310	85.79 319	67.74 320	91.09 263	91.08 278	81.23 231	74.48 306	89.96 258	61.63 287	90.15 327	60.08 321	76.38 302	89.76 311

DSMNet-mixed		76.94 297	76.29 296	78.89 314	83.10 328	56.11 340	87.78 298	79.77 344	60.65 336	75.64 300	88.71 272	61.56 288	88.34 331	60.07 322	89.29 177	92.21 277

IB-MVS	80.51 15	85.24 229	83.26 248	91.19 133	92.13 208	79.86 175	91.75 248	91.29 273	83.28 174	80.66 258	88.49 277	61.28 289	98.46 92	80.99 170	79.46 294	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		86.61 196	85.27 203	90.66 149	91.33 240	78.71 214	90.40 265	93.81 221	85.34 126	85.12 182	89.57 263	61.25 290	97.11 200	80.99 170	89.59 172	96.15 107

N_pmnet		68.89 310	68.44 311	70.23 326	89.07 301	28.79 355	88.06 295	19.50 356	69.47 320	71.86 318	84.93 311	61.24 291	91.75 323	54.70 327	77.15 301	90.15 310

EU-MVSNet		81.32 278	80.95 266	82.42 311	88.50 306	63.67 328	93.32 197	91.33 271	64.02 332	80.57 260	92.83 164	61.21 292	92.27 319	76.34 230	80.38 285	91.32 290

VDDNet		89.56 103	88.49 114	92.76 80	95.07 121	82.09 123	96.30 26	93.19 228	81.05 233	91.88 61	96.86 30	61.16 293	98.33 99	88.43 77	92.49 137	97.84 60

PVSNet_0	73.20 20	77.22 296	74.83 299	84.37 303	90.70 274	71.10 304	83.09 328	89.67 307	72.81 304	73.93 308	83.13 319	60.79 294	93.70 306	68.54 283	50.84 341	88.30 328

SixPastTwentyTwo		83.91 254	82.90 253	86.92 282	90.99 259	70.67 308	93.48 193	91.99 253	85.54 122	77.62 282	92.11 188	60.59 295	96.87 217	76.05 234	77.75 298	93.20 246

gg-mvs-nofinetune		81.77 270	79.37 280	88.99 230	90.85 269	77.73 248	86.29 307	79.63 345	74.88 288	83.19 228	69.05 338	60.34 296	96.11 254	75.46 237	94.64 100	93.11 251

MDA-MVSNet-bldmvs		78.85 294	76.31 295	86.46 287	89.76 295	73.88 281	88.79 288	90.42 291	79.16 247	59.18 335	88.33 280	60.20 297	94.04 303	62.00 316	68.96 327	91.48 288

pmmvs6		83.42 258	81.60 261	88.87 231	88.01 312	77.87 242	94.96 86	94.24 201	74.67 289	78.80 274	91.09 236	60.17 298	96.49 238	77.06 227	75.40 305	92.23 276

ACMH	80.38 17	85.36 225	83.68 237	90.39 166	94.45 146	80.63 157	94.73 101	94.85 183	82.09 203	77.24 284	92.65 170	60.01 299	97.58 146	72.25 259	84.87 227	92.96 254
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 262	89.73 296	77.91 239	87.80 297	78.23 347		80.58 259	83.86 314	59.88 300	95.33 290	71.20 263	92.22 139	90.60 308

pmmvs-eth3d		80.97 282	78.72 287	87.74 263	84.99 323	79.97 173	90.11 270	91.65 262	75.36 281	73.51 309	86.03 307	59.45 301	93.96 304	75.17 240	72.21 311	89.29 315

test_0402		81.30 279	79.17 283	87.67 265	93.19 186	78.17 234	92.98 216	91.71 259	75.25 282	76.02 297	90.31 252	59.23 302	96.37 245	50.22 333	83.63 239	88.47 327

FMVSNet1		85.85 211	84.11 227	91.08 138	92.81 197	83.10 98	95.14 77	94.94 176	81.64 223	82.68 232	91.64 203	59.01 303	96.34 247	75.37 238	83.78 235	93.79 213

COLMAP_ROB	80.39 16	83.96 253	82.04 259	89.74 201	95.28 110	79.75 178	94.25 139	92.28 244	75.17 283	78.02 279	93.77 135	58.60 304	97.84 135	65.06 308	85.92 217	91.63 285
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	85.05 232	83.46 244	89.82 197	94.66 138	79.37 196	94.44 123	94.12 206	82.19 202	78.04 278	92.82 165	58.23 305	97.54 149	73.77 252	82.90 246	92.54 265

LP		75.51 300	72.15 304	85.61 294	87.86 314	73.93 280	80.20 334	88.43 323	67.39 323	70.05 320	80.56 328	58.18 306	93.18 314	46.28 339	70.36 324	89.71 313

CMPMVS	59.16 21	80.52 284	79.20 282	84.48 302	83.98 325	67.63 321	89.95 273	93.84 220	64.79 331	66.81 328	91.14 234	57.93 307	95.17 291	76.25 231	88.10 200	90.65 305
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ITE_SJBPF				88.24 255	91.88 212	77.05 260		92.92 231	85.54 122	80.13 266	93.30 144	57.29 308	96.20 251	72.46 258	84.71 228	91.49 287

TESTMET0.1,1		83.74 257	82.85 254	86.42 289	89.96 292	71.21 303	89.55 276	87.88 325	77.41 265	83.37 226	87.31 292	56.71 309	93.65 307	80.62 176	92.85 135	94.40 186

UnsupCasMVSNet_eth		80.07 286	78.27 288	85.46 295	85.24 321	72.63 293	88.45 293	94.87 182	82.99 187	71.64 319	88.07 283	56.34 310	91.75 323	73.48 254	63.36 336	92.01 279

K. test v3		81.59 273	80.15 274	85.91 292	89.89 294	69.42 315	92.57 228	87.71 327	85.56 121	73.44 310	89.71 261	55.58 311	95.52 275	77.17 224	69.76 325	92.78 261

test-mter		84.54 249	83.64 239	87.25 275	90.95 261	71.67 299	89.55 276	89.88 304	79.17 246	84.54 197	87.95 284	55.56 312	95.11 293	81.82 159	93.37 124	94.97 147

lessismore_v0				86.04 290	88.46 307	68.78 317		80.59 343		73.01 313	90.11 255	55.39 313	96.43 243	75.06 242	65.06 331	92.90 255

MVS-HIRNet		73.70 303	72.20 303	78.18 317	91.81 215	56.42 339	82.94 329	82.58 339	55.24 338	68.88 322	66.48 339	55.32 314	95.13 292	58.12 324	88.42 197	83.01 334

new-patchmatchnet		76.41 298	75.17 298	80.13 313	82.65 331	59.61 333	87.66 300	91.08 278	78.23 261	69.85 321	83.22 318	54.76 315	91.63 325	64.14 311	64.89 332	89.16 317

XVG-ACMP-BASELINE		86.00 208	84.84 213	89.45 214	91.20 250	78.00 237	91.70 251	95.55 132	85.05 133	82.97 229	92.25 184	54.49 316	97.48 153	82.93 140	87.45 207	92.89 256

USDC		82.76 263	81.26 264	87.26 274	91.17 253	74.55 275	89.27 282	93.39 226	78.26 260	75.30 301	92.08 190	54.43 317	96.63 230	71.64 260	85.79 220	90.61 306

AllTest		83.42 258	81.39 262	89.52 210	95.01 122	77.79 244	93.12 208	90.89 285	77.41 265	76.12 294	93.34 140	54.08 318	97.51 151	68.31 287	84.27 232	93.26 244

TestCases				89.52 210	95.01 122	77.79 244		90.89 285	77.41 265	76.12 294	93.34 140	54.08 318	97.51 151	68.31 287	84.27 232	93.26 244

MIMVSNet		82.59 266	80.53 269	88.76 233	91.51 223	78.32 229	86.57 306	90.13 297	79.32 245	80.70 257	88.69 274	52.98 320	93.07 316	66.03 304	88.86 189	94.90 158

FMVSNet5		81.52 275	79.60 279	87.27 273	91.17 253	77.95 238	91.49 255	92.26 245	76.87 270	76.16 293	87.91 286	51.67 321	92.34 318	67.74 291	81.16 268	91.52 286

testgi		80.94 283	80.20 273	83.18 307	87.96 313	66.29 323	91.28 258	90.70 290	83.70 159	78.12 277	92.84 163	51.37 322	90.82 326	63.34 312	82.46 250	92.43 269

Test4		85.75 217	83.72 235	91.83 115	88.08 311	81.03 147	92.48 230	95.54 134	83.38 171	73.40 311	88.57 275	50.99 323	97.37 179	86.61 105	94.47 105	97.09 85

UnsupCasMVSNet_bld		76.23 299	73.27 301	85.09 299	83.79 326	72.92 286	85.65 314	93.47 225	71.52 310	68.84 323	79.08 331	49.77 324	93.21 312	66.81 297	60.52 338	89.13 319

OpenMVS_ROB	74.94 19	79.51 290	77.03 294	86.93 281	87.00 316	76.23 268	92.33 235	90.74 289	68.93 321	74.52 305	88.23 281	49.58 325	96.62 231	57.64 325	84.29 231	87.94 329

testing_2		83.40 260	81.02 265	90.56 152	85.06 322	80.51 161	91.37 257	95.57 130	82.92 189	67.06 327	85.54 310	49.47 326	97.24 190	86.74 100	85.44 221	93.93 203

TDRefinement		79.81 288	77.34 290	87.22 278	79.24 337	75.48 273	93.12 208	92.03 251	76.45 271	75.01 302	91.58 208	49.19 327	96.44 242	70.22 270	69.18 326	89.75 312

MIMVSNet1		79.38 291	77.28 291	85.69 293	86.35 318	73.67 283	91.61 254	92.75 236	78.11 263	72.64 315	88.12 282	48.16 328	91.97 322	60.32 320	77.49 299	91.43 289

LF4IMVS		80.37 285	79.07 285	84.27 305	86.64 317	69.87 314	89.39 281	91.05 280	76.38 272	74.97 303	90.00 256	47.85 329	94.25 302	74.55 247	80.82 278	88.69 322

EG-PatchMatch MVS		82.37 268	80.34 270	88.46 248	90.27 284	79.35 197	92.80 221	94.33 199	77.14 269	73.26 312	90.18 254	47.47 330	96.72 226	70.25 268	87.32 210	89.30 314

testpf		71.41 308	72.11 305	69.30 328	84.53 324	59.79 332	62.74 345	83.14 338	71.11 314	68.83 324	81.57 326	46.70 331	84.83 342	74.51 248	75.86 304	63.30 342

TinyColmap		79.76 289	77.69 289	85.97 291	91.71 218	73.12 285	89.55 276	90.36 293	75.03 284	72.03 317	90.19 253	46.22 332	96.19 252	63.11 313	81.03 272	88.59 323

test2356		74.50 301	73.27 301	78.20 315	80.81 333	59.84 331	83.76 325	88.33 324	71.43 312	72.37 316	81.84 324	45.60 333	86.26 337	50.97 331	84.32 230	88.50 324

tmp_tt		35.64 327	39.24 326	24.84 340	14.87 355	23.90 356	62.71 346	51.51 355	6.58 351	36.66 345	62.08 343	44.37 334	30.34 354	52.40 328	22.00 350	20.27 350

new_pmnet		72.15 306	70.13 307	78.20 315	82.95 330	65.68 324	83.91 323	82.40 340	62.94 334	64.47 331	79.82 330	42.85 335	86.26 337	57.41 326	74.44 307	82.65 335

test1235678		72.22 305	70.31 306	77.93 318	78.04 338	58.04 335	85.76 312	89.80 306	70.15 319	63.43 332	80.20 329	42.24 336	87.24 334	48.68 335	74.50 306	88.50 324

1111		70.54 309	69.71 308	73.04 323	79.30 335	44.83 348	84.23 320	88.96 319	67.33 324	65.42 329	82.28 322	41.11 337	88.11 332	47.12 337	71.60 316	86.19 331

.test1245		57.63 319	61.79 316	45.14 337	79.30 335	44.83 348	84.23 320	88.96 319	67.33 324	65.42 329	82.28 322	41.11 337	88.11 332	47.12 337	0.39 352	2.46 353

testus		74.41 302	73.35 300	77.59 319	82.49 332	57.08 336	86.02 308	90.21 295	72.28 307	72.89 314	84.32 313	37.08 339	86.96 335	52.24 329	82.65 248	88.73 320

pmmvs3		71.81 307	68.71 310	81.11 312	75.86 339	70.42 310	86.74 304	83.66 337	58.95 337	68.64 325	80.89 327	36.93 340	89.52 328	63.10 314	63.59 335	83.39 333

PM-MVS		78.11 295	76.12 297	84.09 306	83.54 327	70.08 312	88.97 287	85.27 335	79.93 240	74.73 304	86.43 299	34.70 341	93.48 309	79.43 202	72.06 312	88.72 321

Anonymous20231211		72.97 304	69.63 309	83.00 309	83.05 329	66.91 322	92.69 223	89.45 310	61.06 335	67.50 326	83.46 317	34.34 342	93.61 308	51.11 330	63.97 334	88.48 326

ambc				83.06 308	79.99 334	63.51 329	77.47 338	92.86 232		74.34 307	84.45 312	28.74 343	95.06 295	73.06 256	68.89 328	90.61 306

test12356		64.99 313	63.78 312	68.61 330	72.69 341	39.14 351	78.46 336	87.61 329	64.91 330	55.77 336	77.48 332	28.10 344	85.59 339	44.69 340	64.35 333	81.12 337

DeepMVS_CX				56.31 335	74.23 340	51.81 344		56.67 354	44.85 342	48.54 341	75.16 333	27.87 345	58.74 352	40.92 343	52.22 340	58.39 346

no-one		61.56 315	56.58 317	76.49 321	67.80 347	62.76 330	78.13 337	86.11 331	63.16 333	43.24 342	64.70 341	26.12 346	88.95 330	50.84 332	29.15 344	77.77 339

testmv		65.49 312	62.66 313	73.96 322	68.78 344	53.14 343	84.70 318	88.56 321	65.94 329	52.35 338	74.65 334	25.02 347	85.14 340	43.54 341	60.40 339	83.60 332

FPMVS		64.63 314	62.55 314	70.88 325	70.80 342	56.71 337	84.42 319	84.42 336	51.78 340	49.57 339	81.61 325	23.49 348	81.48 344	40.61 344	76.25 303	74.46 341

ANet_high		58.88 317	54.22 320	72.86 324	56.50 353	56.67 338	80.75 333	86.00 332	73.09 300	37.39 344	64.63 342	22.17 349	79.49 347	43.51 342	23.96 348	82.43 336

EMVS		42.07 325	41.12 325	44.92 338	63.45 350	35.56 354	73.65 339	63.48 351	33.05 348	26.88 350	45.45 349	21.27 350	67.14 350	19.80 350	23.02 349	32.06 349

Gipuma		57.99 318	54.91 319	67.24 331	88.51 305	65.59 325	52.21 348	90.33 294	43.58 344	42.84 343	51.18 346	20.29 351	85.07 341	34.77 346	70.45 323	51.05 347
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 324	42.29 324	46.03 336	65.58 348	37.41 352	73.51 340	64.62 350	33.99 347	28.47 349	47.87 347	19.90 352	67.91 349	22.23 349	24.45 347	32.77 348

PMMVS2		59.60 316	56.40 318	69.21 329	68.83 343	46.58 346	73.02 343	77.48 348	55.07 339	49.21 340	72.95 337	17.43 353	80.04 345	49.32 334	44.33 342	80.99 338

LCM-MVSNet		66.00 311	62.16 315	77.51 320	64.51 349	58.29 334	83.87 324	90.90 284	48.17 341	54.69 337	73.31 336	16.83 354	86.75 336	65.47 305	61.67 337	87.48 330

PNet_i23d		50.48 322	47.18 322	60.36 333	68.59 345	44.56 350	72.75 344	72.61 349	43.92 343	33.91 346	60.19 344	6.16 355	73.52 348	38.50 345	28.04 345	63.01 343

PMVS	47.18 22	52.22 320	48.46 321	63.48 332	45.72 354	46.20 347	73.41 341	78.31 346	41.03 345	30.06 347	65.68 340	6.05 356	83.43 343	30.04 347	65.86 330	60.80 344
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 323	38.59 328	57.77 334	56.52 352	48.77 345	55.38 347	58.64 353	29.33 349	28.96 348	52.65 345	4.68 357	64.62 351	28.11 348	33.07 343	59.93 345
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 329	20.48 330	23.63 341	68.59 345	36.41 353	49.57 349	6.85 357	9.37 350	7.89 352	4.46 355	4.03 358	31.37 353	17.47 351	16.07 351	3.12 351

wuykxyi23d		50.55 321	44.13 323	69.81 327	56.77 351	54.58 342	73.22 342	80.78 342	39.79 346	22.08 351	46.69 348	4.03 358	79.71 346	47.65 336	26.13 346	75.14 340

test123		8.76 331	11.22 332	1.39 342	0.85 357	0.97 357	85.76 312	0.35 359	0.54 353	2.45 354	8.14 354	0.60 360	0.48 355	2.16 353	0.17 354	2.71 352

testmvs		8.92 330	11.52 331	1.12 343	1.06 356	0.46 358	86.02 308	0.65 358	0.62 352	2.74 353	9.52 353	0.31 361	0.45 356	2.38 352	0.39 352	2.46 353

sosnet-low-res		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

sosnet		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

uncertanet		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

Regformer		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

ab-mvs-re		7.82 332	10.43 333	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	93.88 131	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

uanet		0.00 334	0.00 335	0.00 344	0.00 358	0.00 359	0.00 350	0.00 360	0.00 354	0.00 355	0.00 356	0.00 362	0.00 357	0.00 354	0.00 355	0.00 355

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								60.64 352

gm-plane-assit					89.60 297	68.00 318			77.28 268		88.99 268		97.57 147	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	94.11 152

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

旧先验2							93.36 196		71.25 313	94.37 13			97.13 199	86.74 100

新几何2							93.11 210

无先验							93.28 203	96.26 82	73.95 293				99.05 46	80.56 177		96.59 98

原ACMM2							92.94 218

testdata2													98.75 78	78.30 212

testdata1							92.15 241		87.94 72

plane_prior7					94.70 136	82.74 111

plane_prior5								96.22 86					98.12 108	88.15 79	89.99 164	94.63 169

plane_prior4											94.86 97

plane_prior3						82.75 109			90.26 25	86.91 128

plane_prior2							95.85 42		90.81 18

plane_prior1					94.59 140

plane_prior						82.73 112	95.21 73		89.66 35						89.88 167

n2								0.00 360

nn								0.00 360

door-mid								85.49 333

test11								96.57 70

door								85.33 334

HQP5-MVS						81.56 129

HQP-NCC					94.17 153		94.39 128		88.81 50	85.43 171

ACMP_Plane					94.17 153		94.39 128		88.81 50	85.43 171

BP-MVS														87.11 97

HQP4-MVS										85.43 171			97.96 129			94.51 179

HQP3-MVS								96.04 99							89.77 169

NP-MVS					94.37 148	82.42 119					93.98 124

ACMMP++_ref															87.47 206

ACMMP++															88.01 203

High-resolution multi-view benchmark