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 7				91.93 1			99.02 2	98.67 4

HSP-MVS		95.30 3	95.48 2	94.76 23	98.49 9	86.52 27	96.91 15	96.73 54	91.73 9	96.10 4	96.69 36	89.90 2	99.30 27	94.70 3	98.04 48	98.45 17

DeepPCF-MVS	89.96 1	94.20 24	94.77 8	92.49 87	96.52 65	80.00 171	94.00 158	97.08 29	90.05 26	95.65 6	97.29 10	89.66 3	98.97 59	93.95 8	98.71 18	98.50 10

SD-MVS		94.96 6	95.33 4	93.88 48	97.25 51	86.69 20	96.19 29	97.11 28	90.42 24	96.95 1	97.27 11	89.53 4	96.91 213	94.38 5	98.85 7	98.03 48

CNVR-MVS		95.40 2	95.37 3	95.50 3	98.11 24	88.51 3	95.29 61	96.96 37	92.09 3	95.32 8	97.08 23	89.49 5	99.33 24	95.10 2	98.85 7	98.66 5

APDe-MVS		95.46 1	95.64 1	94.91 11	98.26 19	86.29 37	97.46 2	97.40 9	89.03 47	96.20 3	98.10 1	89.39 6	99.34 21	95.88 1	99.03 1	99.10 1

MCST-MVS		94.45 12	94.20 19	95.19 5	98.46 11	87.50 8	95.00 83	97.12 26	87.13 87	92.51 49	96.30 52	89.24 7	99.34 21	93.46 12	98.62 31	98.73 3

TSAR-MVS + MP.		94.85 7	94.94 6	94.58 30	98.25 20	86.33 33	96.11 31	96.62 65	88.14 68	96.10 4	96.96 26	89.09 8	98.94 63	94.48 4	98.68 23	98.48 12

SteuartSystems-ACMMP		95.20 4	95.32 5	94.85 15	96.99 54	86.33 33	97.33 3	97.30 17	91.38 12	95.39 7	97.46 7	88.98 9	99.40 19	94.12 7	98.89 6	98.82 2
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		95.14 5	94.91 7	95.83 1	98.25 20	89.65 1	95.92 38	96.96 37	91.75 8	94.02 18	96.83 30	88.12 10	99.55 5	93.41 15	98.94 4	98.28 27

agg_prior1		93.29 42	92.97 44	94.26 41	97.38 42	85.92 43	93.92 161	96.72 56	81.96 205	92.16 55	96.23 55	87.85 11	98.97 59	91.95 39	98.55 36	97.90 57

CSCG		93.23 47	93.05 41	93.76 54	98.04 28	84.07 76	96.22 28	97.37 10	84.15 149	90.05 83	95.66 77	87.77 12	99.15 36	89.91 63	98.27 41	98.07 44

NCCC		94.81 8	94.69 9	95.17 6	97.83 31	87.46 9	95.66 49	96.93 40	92.34 2	93.94 19	96.58 43	87.74 13	99.44 18	92.83 20	98.40 38	98.62 6

TEST9					97.53 35	86.49 28	94.07 150	96.78 50	81.61 217	92.77 39	96.20 57	87.71 14	99.12 39

train_agg		93.44 38	93.08 40	94.52 32	97.53 35	86.49 28	94.07 150	96.78 50	81.86 212	92.77 39	96.20 57	87.63 15	99.12 39	92.14 33	98.69 20	97.94 52

test_8					97.49 38	86.30 36	94.02 156	96.76 53	81.86 212	92.70 43	96.20 57	87.63 15	99.02 51

TSAR-MVS + GP.		93.66 34	93.41 35	94.41 37	96.59 62	86.78 17	94.40 124	93.93 217	89.77 32	94.21 14	95.59 79	87.35 17	98.61 83	92.72 21	96.15 79	97.83 60

APD-MVS		94.24 21	94.07 23	94.75 24	98.06 27	86.90 14	95.88 39	96.94 39	85.68 118	95.05 10	97.18 19	87.31 18	99.07 42	91.90 43	98.61 32	98.28 27
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Regformer-2		94.33 18	94.22 16	94.68 26	95.54 99	86.75 19	94.57 113	96.70 58	91.84 6	94.41 11	96.56 45	87.19 19	99.13 38	93.50 11	97.65 56	98.16 37

segment_acmp												87.16 20

Regformer-1		94.22 22	94.13 21	94.51 33	95.54 99	86.36 32	94.57 113	96.44 72	91.69 10	94.32 13	96.56 45	87.05 21	99.03 48	93.35 16	97.65 56	98.15 38

agg_prior3		93.27 43	92.89 46	94.40 38	97.49 38	86.12 40	94.07 150	96.73 54	81.46 220	92.46 51	96.05 65	86.90 22	99.15 36	92.14 33	98.69 20	97.94 52

旧先验1					96.79 58	81.81 126		95.67 123			96.81 31	86.69 23			97.66 55	96.97 87

test_prior3		93.60 35	93.53 34	93.82 50	97.29 47	84.49 63	94.12 142	96.88 43	87.67 79	92.63 44	96.39 50	86.62 24	98.87 65	91.50 47	98.67 25	98.11 42

test_prior2							94.12 142		87.67 79	92.63 44	96.39 50	86.62 24		91.50 47	98.67 25

CDPH-MVS		92.83 51	92.30 53	94.44 34	97.79 32	86.11 41	94.06 153	96.66 62	80.09 231	92.77 39	96.63 40	86.62 24	99.04 47	87.40 88	98.66 27	98.17 36

DELS-MVS		93.43 39	93.25 37	93.97 45	95.42 104	85.04 54	93.06 205	97.13 25	90.74 20	91.84 61	95.09 90	86.32 27	99.21 30	91.22 50	98.45 37	97.65 64
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 10	94.40 11	94.86 13	98.61 3	86.81 15	96.94 10	97.34 11	88.63 56	93.65 22	97.21 16	86.10 28	99.49 14	92.35 27	98.77 13	98.30 25

#test#		94.32 19	94.14 20	94.86 13	98.61 3	86.81 15	96.43 23	97.34 11	87.51 82	93.65 22	97.21 16	86.10 28	99.49 14	91.68 45	98.77 13	98.30 25

MVS_111021_HR		93.45 37	93.31 36	93.84 49	96.99 54	84.84 55	93.24 198	97.24 19	88.76 53	91.60 67	95.85 71	86.07 30	98.66 78	91.91 40	98.16 44	98.03 48

Regformer-4		93.91 29	93.81 27	94.19 43	95.36 105	85.47 50	94.68 105	96.41 75	91.60 11	93.75 21	96.71 34	85.95 31	99.10 41	93.21 17	96.65 71	98.01 50

ACMMP_Plus		94.74 9	94.56 10	95.28 4	98.02 29	87.70 4	95.68 47	97.34 11	88.28 65	95.30 9	97.67 3	85.90 32	99.54 8	93.91 9	98.95 3	98.60 7

Regformer-3		93.68 33	93.64 33	93.81 52	95.36 105	84.61 59	94.68 105	95.83 113	91.27 13	93.60 25	96.71 34	85.75 33	98.86 68	92.87 19	96.65 71	97.96 51

PHI-MVS		93.89 30	93.65 32	94.62 29	96.84 57	86.43 30	96.69 21	97.49 4	85.15 129	93.56 28	96.28 53	85.60 34	99.31 26	92.45 23	98.79 10	98.12 41

MP-MVS-pluss		94.21 23	94.00 25	94.85 15	98.17 23	86.65 23	94.82 94	97.17 24	86.26 108	92.83 37	97.87 2	85.57 35	99.56 1	94.37 6	98.92 5	98.34 22
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		94.25 20	94.07 23	94.77 22	98.47 10	86.31 35	96.71 20	96.98 33	89.04 46	91.98 59	97.19 18	85.43 36	99.56 1	92.06 35	98.79 10	98.44 18

DeepC-MVS_fast	89.43 2	94.04 25	93.79 28	94.80 21	97.48 40	86.78 17	95.65 51	96.89 42	89.40 38	92.81 38	96.97 25	85.37 37	99.24 29	90.87 56	98.69 20	98.38 21
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 14	94.27 15	94.92 10	98.65 1	86.67 22	96.92 14	97.23 21	88.60 58	93.58 26	97.27 11	85.22 38	99.54 8	92.21 29	98.74 17	98.56 9

CP-MVS		94.34 17	94.21 18	94.74 25	98.39 15	86.64 24	97.60 1	97.24 19	88.53 60	92.73 42	97.23 14	85.20 39	99.32 25	92.15 32	98.83 9	98.25 33

test12				94.34 39	97.13 52	86.15 39		96.29 81		91.04 74		85.08 40	99.01 53		98.13 45	97.86 58

ACMMPR		94.43 14	94.28 14	94.91 11	98.63 2	86.69 20	96.94 10	97.32 16	88.63 56	93.53 29	97.26 13	85.04 41	99.54 8	92.35 27	98.78 12	98.50 10

XVS		94.45 12	94.32 12	94.85 15	98.54 6	86.60 25	96.93 12	97.19 22	90.66 22	92.85 35	97.16 21	85.02 42	99.49 14	91.99 36	98.56 34	98.47 13

X-MVStestdata		88.31 135	86.13 181	94.85 15	98.54 6	86.60 25	96.93 12	97.19 22	90.66 22	92.85 35	23.41 342	85.02 42	99.49 14	91.99 36	98.56 34	98.47 13

MSLP-MVS++		93.72 32	94.08 22	92.65 81	97.31 45	83.43 90	95.79 42	97.33 14	90.03 27	93.58 26	96.96 26	84.87 44	97.76 136	92.19 31	98.66 27	96.76 93

HPM-MVS		94.02 26	93.88 26	94.43 36	98.39 15	85.78 48	97.25 5	97.07 30	86.90 98	92.62 46	96.80 33	84.85 45	99.17 33	92.43 24	98.65 29	98.33 23

PGM-MVS		93.96 28	93.72 31	94.68 26	98.43 12	86.22 38	95.30 59	97.78 1	87.45 83	93.26 30	97.33 9	84.62 46	99.51 12	90.75 58	98.57 33	98.32 24

EI-MVSNet-Vis-set		93.01 50	92.92 45	93.29 58	95.01 115	83.51 89	94.48 116	95.77 117	90.87 16	92.52 48	96.67 38	84.50 47	99.00 56	91.99 36	94.44 106	97.36 73

MPTG		94.47 11	94.30 13	95.00 8	98.42 13	86.95 11	95.06 80	96.97 34	91.07 14	93.14 33	97.56 4	84.30 48	99.56 1	93.43 13	98.75 15	98.47 13

MTAPA		94.42 16	94.22 16	95.00 8	98.42 13	86.95 11	94.36 134	96.97 34	91.07 14	93.14 33	97.56 4	84.30 48	99.56 1	93.43 13	98.75 15	98.47 13

EI-MVSNet-UG-set		92.74 53	92.62 49	93.12 64	94.86 123	83.20 95	94.40 124	95.74 120	90.71 21	92.05 58	96.60 42	84.00 50	98.99 57	91.55 46	93.63 115	97.17 80

mPP-MVS		93.99 27	93.78 29	94.63 28	98.50 8	85.90 46	96.87 16	96.91 41	88.70 54	91.83 63	97.17 20	83.96 51	99.55 5	91.44 49	98.64 30	98.43 19

APD-MVS_3200maxsize		93.78 31	93.77 30	93.80 53	97.92 30	84.19 74	96.30 26	96.87 45	86.96 94	93.92 20	97.47 6	83.88 52	98.96 62	92.71 22	97.87 51	98.26 32

EPP-MVSNet		91.70 63	91.56 58	92.13 102	95.88 89	80.50 161	97.33 3	95.25 160	86.15 110	89.76 85	95.60 78	83.42 53	98.32 98	87.37 90	93.25 125	97.56 69

UA-Net		92.83 51	92.54 51	93.68 55	96.10 81	84.71 58	95.66 49	96.39 77	91.92 4	93.22 31	96.49 47	83.16 54	98.87 65	84.47 119	95.47 87	97.45 72

UniMVSNet_NR-MVSNet		89.92 95	89.29 94	91.81 117	93.39 173	83.72 82	94.43 122	97.12 26	89.80 31	86.46 134	93.32 140	83.16 54	97.23 190	84.92 112	81.02 266	94.49 177

1121		90.42 84	89.49 88	93.20 61	97.27 49	84.46 66	92.63 217	95.51 138	71.01 308	91.20 72	96.21 56	82.92 56	99.05 44	80.56 175	98.07 47	96.10 109

新几何1				93.10 65	97.30 46	84.35 72		95.56 131	71.09 307	91.26 71	96.24 54	82.87 57	98.86 68	79.19 203	98.10 46	96.07 111

原ACMM1				92.01 103	97.34 44	81.05 145		96.81 48	78.89 241	90.45 78	95.92 68	82.65 58	98.84 73	80.68 173	98.26 42	96.14 107

DeepC-MVS	88.79 3	93.31 41	92.99 43	94.26 41	96.07 83	85.83 47	94.89 89	96.99 32	89.02 48	89.56 86	97.37 8	82.51 59	99.38 20	92.20 30	98.30 40	97.57 68
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 40	93.22 38	93.94 47	98.36 17	84.83 56	97.15 7	96.80 49	85.77 115	92.47 50	97.13 22	82.38 60	99.07 42	90.51 60	98.40 38	97.92 56

canonicalmvs		93.27 43	92.75 48	94.85 15	95.70 95	87.66 5	96.33 25	96.41 75	90.00 28	94.09 16	94.60 104	82.33 61	98.62 82	92.40 26	92.86 133	98.27 30

DP-MVS Recon		91.95 58	91.28 61	93.96 46	98.33 18	85.92 43	94.66 108	96.66 62	82.69 194	90.03 84	95.82 72	82.30 62	99.03 48	84.57 118	96.48 76	96.91 89

PAPR		90.02 90	89.27 96	92.29 96	95.78 92	80.95 149	92.68 216	96.22 86	81.91 208	86.66 132	93.75 135	82.23 63	98.44 92	79.40 202	94.79 95	97.48 71

MVS_Test		91.31 68	91.11 63	91.93 109	94.37 141	80.14 165	93.46 187	95.80 115	86.46 104	91.35 70	93.77 133	82.21 64	98.09 119	87.57 86	94.95 94	97.55 70

nrg030		91.08 73	90.39 73	93.17 63	93.07 182	86.91 13	96.41 24	96.26 82	88.30 64	88.37 99	94.85 97	82.19 65	97.64 143	91.09 51	82.95 238	94.96 147

UniMVSNet (Re)		89.80 97	89.07 99	92.01 103	93.60 169	84.52 62	94.78 97	97.47 5	89.26 41	86.44 137	92.32 177	82.10 66	97.39 176	84.81 115	80.84 270	94.12 189

testdata				90.49 160	96.40 66	77.89 240		95.37 153	72.51 297	93.63 24	96.69 36	82.08 67	97.65 141	83.08 135	97.39 59	95.94 115

PAPM_NR		91.22 70	90.78 71	92.52 86	97.60 34	81.46 133	94.37 130	96.24 85	86.39 106	87.41 118	94.80 99	82.06 68	98.48 89	82.80 141	95.37 89	97.61 66

MG-MVS		91.77 60	91.70 57	92.00 105	97.08 53	80.03 170	93.60 182	95.18 167	87.85 74	90.89 75	96.47 48	82.06 68	98.36 93	85.07 110	97.04 64	97.62 65

CANet		93.54 36	93.20 39	94.55 31	95.65 96	85.73 49	94.94 86	96.69 60	91.89 5	90.69 76	95.88 70	81.99 70	99.54 8	93.14 18	97.95 50	98.39 20

FC-MVSNet-test		90.27 86	90.18 78	90.53 152	93.71 166	79.85 175	95.77 43	97.59 2	89.31 40	86.27 140	94.67 101	81.93 71	97.01 205	84.26 124	88.09 195	94.71 162

FIs		90.51 83	90.35 74	90.99 143	93.99 156	80.98 147	95.73 44	97.54 3	89.15 44	86.72 131	94.68 100	81.83 72	97.24 188	85.18 109	88.31 192	94.76 161

ACMMP		93.24 46	92.88 47	94.30 40	98.09 26	85.33 52	96.86 17	97.45 7	88.33 63	90.15 82	97.03 24	81.44 73	99.51 12	90.85 57	95.74 82	98.04 47
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 65	91.11 63	93.01 70	94.35 144	83.39 92	94.60 110	95.10 169	87.10 88	90.57 77	93.10 151	81.43 74	98.07 121	89.29 67	94.48 103	97.59 67

MVS_111021_LR		92.47 54	92.29 54	92.98 71	95.99 86	84.43 70	93.08 203	96.09 94	88.20 67	91.12 73	95.72 76	81.33 75	97.76 136	91.74 44	97.37 60	96.75 94

mvs_anonymous		89.37 112	89.32 93	89.51 209	93.47 171	74.22 269	91.65 245	94.83 185	82.91 188	85.45 167	93.79 132	81.23 76	96.36 238	86.47 104	94.09 109	97.94 52

PVSNet_BlendedMVS		89.98 91	89.70 85	90.82 146	96.12 77	81.25 138	93.92 161	96.83 46	83.49 165	89.10 91	92.26 181	81.04 77	98.85 71	86.72 101	87.86 197	92.35 264

PVSNet_Blended		90.73 77	90.32 75	91.98 106	96.12 77	81.25 138	92.55 221	96.83 46	82.04 204	89.10 91	92.56 170	81.04 77	98.85 71	86.72 101	95.91 80	95.84 120

alignmvs		93.08 49	92.50 52	94.81 20	95.62 98	87.61 6	95.99 35	96.07 96	89.77 32	94.12 15	94.87 94	80.56 79	98.66 78	92.42 25	93.10 128	98.15 38

abl_6		93.18 48	93.05 41	93.57 57	97.52 37	84.27 73	95.53 54	96.67 61	87.85 74	93.20 32	97.22 15	80.35 80	99.18 32	91.91 40	97.21 61	97.26 74

API-MVS		90.66 78	90.07 80	92.45 89	96.36 68	84.57 61	96.06 33	95.22 166	82.39 196	89.13 90	94.27 114	80.32 81	98.46 90	80.16 184	96.71 69	94.33 182

PVSNet_Blended_VisFu		91.38 67	90.91 68	92.80 77	96.39 67	83.17 96	94.87 92	96.66 62	83.29 171	89.27 89	94.46 106	80.29 82	99.17 33	87.57 86	95.37 89	96.05 113

test222					96.55 64	81.70 127	92.22 231	95.01 172	68.36 314	90.20 81	96.14 62	80.26 83			97.80 53	96.05 113

Test By Simon												80.02 84

IterMVS-LS		88.36 134	87.91 129	89.70 202	93.80 163	78.29 230	93.73 173	95.08 171	85.73 116	84.75 186	91.90 196	79.88 85	96.92 212	83.83 130	82.51 242	93.89 200
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 116	88.86 106	89.80 199	91.84 206	78.30 229	93.70 177	95.01 172	85.73 116	87.15 122	95.28 83	79.87 86	97.21 192	83.81 131	87.36 201	93.88 202

TAPA-MVS	84.62 6	88.16 139	87.01 150	91.62 121	96.64 60	80.65 155	94.39 126	96.21 89	76.38 264	86.19 142	95.44 80	79.75 87	98.08 120	62.75 307	95.29 91	96.13 108
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 109	88.64 108	91.71 119	94.74 125	80.81 153	93.54 183	95.10 169	83.11 174	86.82 130	90.67 234	79.74 88	97.75 139	80.51 177	93.55 116	96.57 98

pcd_1.5k_mvsjas		6.64 326	8.86 327	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	0.00 348	79.70 89	0.00 349	0.00 346	0.00 348	0.00 346

PS-MVSNAJss		89.97 92	89.62 86	91.02 141	91.90 204	80.85 152	95.26 68	95.98 101	86.26 108	86.21 141	94.29 111	79.70 89	97.65 141	88.87 71	88.10 193	94.57 170

PS-MVSNAJ		91.18 71	90.92 67	91.96 107	95.26 111	82.60 117	92.09 236	95.70 122	86.27 107	91.84 61	92.46 171	79.70 89	98.99 57	89.08 68	95.86 81	94.29 183

xiu_mvs_v2_base		91.13 72	90.89 69	91.86 112	94.97 118	82.42 118	92.24 230	95.64 128	86.11 112	91.74 66	93.14 149	79.67 92	98.89 64	89.06 69	95.46 88	94.28 184

WR-MVS_H		87.80 154	87.37 136	89.10 222	93.23 178	78.12 234	95.61 52	97.30 17	87.90 72	83.72 210	92.01 192	79.65 93	96.01 250	76.36 227	80.54 274	93.16 239

EPNet		91.79 59	91.02 66	94.10 44	90.10 281	85.25 53	96.03 34	92.05 250	92.83 1	87.39 120	95.78 73	79.39 94	99.01 53	88.13 79	97.48 58	98.05 46
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
NR-MVSNet		88.58 130	87.47 134	91.93 109	93.04 184	84.16 75	94.77 98	96.25 84	89.05 45	80.04 260	93.29 143	79.02 95	97.05 203	81.71 160	80.05 280	94.59 168

TAMVS		89.21 114	88.29 120	91.96 107	93.71 166	82.62 116	93.30 193	94.19 202	82.22 199	87.78 114	93.94 124	78.83 96	96.95 210	77.70 216	92.98 130	96.32 102

1112_ss		88.42 131	87.33 137	91.72 118	94.92 120	80.98 147	92.97 209	94.54 192	78.16 254	83.82 208	93.88 129	78.78 97	97.91 131	79.45 198	89.41 172	96.26 104

CDS-MVSNet		89.45 106	88.51 110	92.29 96	93.62 168	83.61 87	93.01 206	94.68 189	81.95 206	87.82 113	93.24 145	78.69 98	96.99 206	80.34 180	93.23 126	96.28 103
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 100	88.92 103	91.67 120	95.47 103	81.15 143	92.38 226	94.78 187	83.11 174	89.06 93	94.32 109	78.67 99	96.61 225	81.57 161	90.89 154	97.24 75

CPTT-MVS		91.99 57	91.80 56	92.55 84	98.24 22	81.98 125	96.76 19	96.49 71	81.89 210	90.24 80	96.44 49	78.59 100	98.61 83	89.68 64	97.85 52	97.06 85

IS-MVSNet		91.43 66	91.09 65	92.46 88	95.87 91	81.38 136	96.95 9	93.69 222	89.72 34	89.50 88	95.98 66	78.57 101	97.77 135	83.02 137	96.50 75	98.22 34

OMC-MVS		91.23 69	90.62 72	93.08 66	96.27 70	84.07 76	93.52 184	95.93 104	86.95 95	89.51 87	96.13 63	78.50 102	98.35 95	85.84 105	92.90 132	96.83 92

PCF-MVS	84.11 10	87.74 156	86.08 184	92.70 80	94.02 151	84.43 70	89.27 274	95.87 111	73.62 287	84.43 194	94.33 108	78.48 103	98.86 68	70.27 265	94.45 105	94.81 159
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 136	88.32 118	88.27 246	94.71 128	72.41 289	93.15 199	90.98 282	87.77 76	79.25 266	91.96 193	78.35 104	95.75 261	83.04 136	95.62 83	96.65 96

HY-MVS	83.01 12	89.03 120	87.94 128	92.29 96	94.86 123	82.77 107	92.08 237	94.49 193	81.52 219	86.93 126	92.79 166	78.32 105	98.23 100	79.93 188	90.55 155	95.88 118

diffmvs		89.07 117	88.32 118	91.34 128	93.24 177	79.79 176	92.29 229	94.98 175	80.24 228	87.38 121	92.45 172	78.02 106	97.33 178	83.29 134	92.93 131	96.91 89

MVS		87.44 174	86.10 183	91.44 126	92.61 194	83.62 86	92.63 217	95.66 125	67.26 318	81.47 240	92.15 183	77.95 107	98.22 101	79.71 194	95.48 86	92.47 259

MVSFormer		91.68 64	91.30 60	92.80 77	93.86 160	83.88 79	95.96 36	95.90 108	84.66 138	91.76 64	94.91 92	77.92 108	97.30 180	89.64 65	97.11 62	97.24 75

lupinMVS		90.92 74	90.21 76	93.03 69	93.86 160	83.88 79	92.81 212	93.86 218	79.84 233	91.76 64	94.29 111	77.92 108	98.04 123	90.48 61	97.11 62	97.17 80

Test_1112_low_res		87.65 158	86.51 173	91.08 137	94.94 119	79.28 201	91.77 239	94.30 200	76.04 269	83.51 216	92.37 175	77.86 110	97.73 140	78.69 207	89.13 179	96.22 105

VNet		92.24 56	91.91 55	93.24 60	96.59 62	83.43 90	94.84 93	96.44 72	89.19 43	94.08 17	95.90 69	77.85 111	98.17 103	88.90 70	93.38 122	98.13 40

DU-MVS		89.34 113	88.50 111	91.85 113	93.04 184	83.72 82	94.47 119	96.59 67	89.50 36	86.46 134	93.29 143	77.25 112	97.23 190	84.92 112	81.02 266	94.59 168

Baseline_NR-MVSNet		87.07 186	86.63 171	88.40 243	91.44 218	77.87 241	94.23 139	92.57 240	84.12 150	85.74 152	92.08 188	77.25 112	96.04 247	82.29 150	79.94 283	91.30 282

jason		90.80 75	90.10 79	92.90 74	93.04 184	83.53 88	93.08 203	94.15 204	80.22 229	91.41 69	94.91 92	76.87 114	97.93 130	90.28 62	96.90 65	97.24 75
jason: jason.
PAPM		86.68 194	85.39 199	90.53 152	93.05 183	79.33 200	89.79 267	94.77 188	78.82 243	81.95 236	93.24 145	76.81 115	97.30 180	66.94 291	93.16 127	94.95 154

Vis-MVSNet (Re-imp)		89.59 101	89.44 90	90.03 189	95.74 93	75.85 263	95.61 52	90.80 287	87.66 81	87.83 112	95.40 82	76.79 116	96.46 233	78.37 208	96.73 68	97.80 61

114514_t		89.51 103	88.50 111	92.54 85	98.11 24	81.99 124	95.16 74	96.36 79	70.19 310	85.81 146	95.25 85	76.70 117	98.63 81	82.07 152	96.86 67	97.00 86

PLC	84.53 7	89.06 119	88.03 125	92.15 100	97.27 49	82.69 114	94.29 135	95.44 147	79.71 235	84.01 205	94.18 116	76.68 118	98.75 76	77.28 220	93.41 121	95.02 142
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 124	87.95 127	91.49 124	92.68 193	83.01 102	94.92 88	96.31 80	89.88 30	85.53 161	93.85 131	76.63 119	96.96 209	81.91 156	79.87 285	94.50 175

MAR-MVS		90.30 85	89.37 92	93.07 68	96.61 61	84.48 65	95.68 47	95.67 123	82.36 198	87.85 107	92.85 160	76.63 119	98.80 74	80.01 185	96.68 70	95.91 116
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		84.97 227	83.76 225	88.60 233	91.36 228	79.41 189	93.82 166	94.04 207	83.00 184	76.61 280	86.60 288	76.19 121	95.43 273	80.39 178	71.79 307	90.96 287

v6		87.98 144	87.25 141	90.16 174	91.36 228	79.39 194	94.37 130	95.27 159	84.48 141	85.78 147	91.51 212	76.15 122	97.46 153	84.46 120	81.88 253	93.62 222

v1neww		87.98 144	87.25 141	90.16 174	91.38 225	79.41 189	94.37 130	95.28 156	84.48 141	85.77 148	91.53 210	76.12 123	97.45 155	84.45 121	81.89 251	93.61 223

v7new		87.98 144	87.25 141	90.16 174	91.38 225	79.41 189	94.37 130	95.28 156	84.48 141	85.77 148	91.53 210	76.12 123	97.45 155	84.45 121	81.89 251	93.61 223

WR-MVS		88.38 132	87.67 131	90.52 158	93.30 176	80.18 163	93.26 196	95.96 103	88.57 59	85.47 166	92.81 164	76.12 123	96.91 213	81.24 163	82.29 244	94.47 180

v16		84.96 228	83.74 227	88.62 231	91.40 223	79.48 183	93.83 164	94.04 207	83.03 181	76.54 281	86.59 289	76.11 126	95.42 274	80.33 181	71.80 306	90.95 289

v17		84.93 230	83.70 229	88.62 231	91.36 228	79.48 183	93.83 164	94.03 209	83.04 180	76.51 282	86.57 290	76.05 127	95.42 274	80.31 183	71.65 308	90.96 287

v8		87.50 173	86.71 161	89.89 194	91.37 227	79.40 193	94.50 115	95.38 151	84.81 135	83.60 214	91.33 214	76.05 127	97.42 166	82.84 140	80.51 277	92.84 249

v148		87.04 187	86.32 177	89.21 218	90.94 256	77.26 251	93.71 176	94.43 195	84.84 134	84.36 198	90.80 232	76.04 129	97.05 203	82.12 151	79.60 286	93.31 234

v15		84.79 233	83.53 234	88.57 237	91.30 239	79.41 189	93.70 177	94.01 210	83.06 177	76.27 283	86.42 294	76.03 130	95.38 276	80.01 185	71.00 311	90.92 290

V14		84.79 233	83.52 235	88.57 237	91.32 235	79.43 188	93.72 175	94.01 210	83.06 177	76.22 284	86.43 291	76.01 131	95.37 277	79.96 187	70.99 312	90.91 291

V9		84.77 235	83.50 236	88.58 234	91.33 233	79.46 185	93.75 171	94.00 213	83.07 176	76.07 289	86.43 291	75.97 132	95.37 277	79.91 190	70.93 314	90.91 291

v1		87.85 149	87.10 144	90.11 185	91.21 242	79.24 205	94.09 146	95.24 161	84.44 145	85.70 153	91.31 217	75.96 133	97.45 155	84.18 125	81.73 258	93.64 219

3Dnovator+	87.14 4	92.42 55	91.37 59	95.55 2	95.63 97	88.73 2	97.07 8	96.77 52	90.84 17	84.02 204	96.62 41	75.95 134	99.34 21	87.77 83	97.68 54	98.59 8

v1141		87.84 150	87.09 145	90.11 185	91.23 240	79.25 203	94.08 148	95.24 161	84.44 145	85.69 155	91.31 217	75.91 135	97.44 162	84.17 126	81.74 257	93.63 221

divwei89l23v2f112		87.84 150	87.09 145	90.10 187	91.23 240	79.24 205	94.09 146	95.24 161	84.44 145	85.70 153	91.31 217	75.91 135	97.44 162	84.17 126	81.73 258	93.64 219

v13		84.72 238	83.44 239	88.58 234	91.31 238	79.52 179	93.77 169	94.00 213	83.03 181	75.85 292	86.38 296	75.84 137	95.35 280	79.83 192	70.95 313	90.87 294

v12		84.74 236	83.46 237	88.58 234	91.32 235	79.50 180	93.75 171	94.01 210	83.06 177	75.98 291	86.41 295	75.82 138	95.36 279	79.87 191	70.89 315	90.89 293

BH-untuned		88.60 129	88.13 124	90.01 191	95.24 112	78.50 224	93.29 194	94.15 204	84.75 136	84.46 192	93.40 137	75.76 139	97.40 173	77.59 217	94.52 102	94.12 189

BH-w/o		87.57 171	87.05 149	89.12 220	94.90 122	77.90 239	92.41 224	93.51 224	82.89 189	83.70 211	91.34 213	75.75 140	97.07 201	75.49 234	93.49 118	92.39 262

cdsmvs_eth3d_5k		22.14 321	29.52 322	0.00 337	0.00 351	0.00 352	0.00 342	95.76 118	0.00 346	0.00 348	94.29 111	75.66 141	0.00 349	0.00 346	0.00 348	0.00 346

CNLPA		89.07 117	87.98 126	92.34 94	96.87 56	84.78 57	94.08 148	93.24 227	81.41 221	84.46 192	95.13 89	75.57 142	96.62 223	77.21 221	93.84 113	95.61 129

v11		84.67 241	83.41 240	88.44 242	91.32 235	79.13 208	93.69 180	93.99 215	82.81 190	76.20 285	86.24 298	75.48 143	95.35 280	79.53 196	71.48 310	90.85 295

CHOSEN 1792x2688		88.84 124	87.69 130	92.30 95	96.14 76	81.42 135	90.01 263	95.86 112	74.52 282	87.41 118	93.94 124	75.46 144	98.36 93	80.36 179	95.53 84	97.12 83

MVS_0304		93.25 45	92.62 49	95.14 7	95.72 94	87.58 7	94.71 104	96.59 67	91.78 7	91.46 68	96.18 61	75.45 145	99.55 5	93.53 10	98.19 43	98.28 27

CP-MVSNet		87.63 162	87.26 140	88.74 227	93.12 181	76.59 257	95.29 61	96.58 69	88.43 61	83.49 217	92.98 158	75.28 146	95.83 257	78.97 204	81.15 263	93.79 208

v7		87.75 155	86.96 151	90.12 180	91.20 243	79.50 180	94.28 136	95.46 141	83.45 166	85.75 150	91.56 209	75.13 147	97.43 164	83.60 132	82.18 246	93.42 232

v10		87.25 180	86.38 174	89.85 195	91.19 245	79.50 180	94.48 116	95.45 145	83.79 156	83.62 213	91.19 222	75.13 147	97.42 166	81.94 155	80.60 272	92.63 255

Vis-MVSNet		91.75 61	91.23 62	93.29 58	95.32 108	83.78 81	96.14 30	95.98 101	89.89 29	90.45 78	96.58 43	75.09 149	98.31 99	84.75 116	96.90 65	97.78 63
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 123	88.26 122	90.94 145	94.05 150	80.78 154	91.71 242	95.38 151	81.55 218	88.63 95	93.91 128	75.04 150	95.47 272	82.47 146	91.61 140	96.57 98

v1144		87.61 169	86.79 158	90.06 188	91.01 251	79.34 197	93.95 160	95.42 150	83.36 170	85.66 157	91.31 217	74.98 151	97.42 166	83.37 133	82.06 247	93.42 232

V42		87.68 157	86.86 153	90.15 178	90.58 270	80.14 165	94.24 138	95.28 156	83.66 158	85.67 156	91.33 214	74.73 152	97.41 171	84.43 123	81.83 254	92.89 247

XVG-OURS-SEG-HR		89.95 93	89.45 89	91.47 125	94.00 155	81.21 141	91.87 238	96.06 98	85.78 114	88.55 96	95.73 75	74.67 153	97.27 184	88.71 72	89.64 170	95.91 116

v2v482		87.84 150	87.06 148	90.17 173	90.99 252	79.23 207	94.00 158	95.13 168	84.87 133	85.53 161	92.07 190	74.45 154	97.45 155	84.71 117	81.75 256	93.85 206

CLD-MVS		89.47 105	88.90 104	91.18 133	94.22 145	82.07 123	92.13 234	96.09 94	87.90 72	85.37 177	92.45 172	74.38 155	97.56 146	87.15 93	90.43 156	93.93 198
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 158	86.85 154	90.03 189	92.14 200	80.60 158	93.76 170	95.23 164	82.94 186	84.60 188	94.02 120	74.27 156	95.49 271	81.04 165	83.68 231	94.01 197

HQP_MVS		90.60 82	90.19 77	91.82 115	94.70 129	82.73 111	95.85 40	96.22 86	90.81 18	86.91 127	94.86 95	74.23 157	98.12 106	88.15 77	89.99 163	94.63 164

plane_prior6					94.52 135	82.75 108						74.23 157

v144192		87.19 184	86.35 175	89.74 200	90.64 269	78.24 232	93.92 161	95.43 148	81.93 207	85.51 163	91.05 229	74.21 159	97.45 155	82.86 139	81.56 260	93.53 227

VPA-MVSNet		89.62 99	88.96 101	91.60 122	93.86 160	82.89 106	95.46 55	97.33 14	87.91 71	88.43 98	93.31 141	74.17 160	97.40 173	87.32 91	82.86 240	94.52 173

ab-mvs		89.41 109	88.35 115	92.60 82	95.15 113	82.65 115	92.20 232	95.60 129	83.97 151	88.55 96	93.70 136	74.16 161	98.21 102	82.46 147	89.37 173	96.94 88

1314		87.51 172	86.57 172	90.34 170	92.42 196	79.74 178	92.63 217	95.35 155	78.35 250	80.14 258	91.62 205	74.05 162	97.15 194	81.05 164	93.53 117	94.12 189

test_djsdf		89.03 120	88.64 108	90.21 172	90.74 265	79.28 201	95.96 36	95.90 108	84.66 138	85.33 179	92.94 159	74.02 163	97.30 180	89.64 65	88.53 185	94.05 194

AdaColmap		89.89 96	89.07 99	92.37 93	97.41 41	83.03 100	94.42 123	95.92 105	82.81 190	86.34 139	94.65 102	73.89 164	99.02 51	80.69 172	95.51 85	95.05 141

HyFIR lowres test		88.09 142	86.81 156	91.93 109	96.00 85	80.63 156	90.01 263	95.79 116	73.42 288	87.68 116	92.10 187	73.86 165	97.96 127	80.75 171	91.70 139	97.19 79

HQP2-MVS												73.83 166

HQP-MVS		89.80 97	89.28 95	91.34 128	94.17 146	81.56 128	94.39 126	96.04 99	88.81 50	85.43 170	93.97 123	73.83 166	97.96 127	87.11 95	89.77 168	94.50 175

3Dnovator	86.66 5	91.73 62	90.82 70	94.44 34	94.59 133	86.37 31	97.18 6	97.02 31	89.20 42	84.31 200	96.66 39	73.74 168	99.17 33	86.74 98	97.96 49	97.79 62

EPNet_dtu		86.49 199	85.94 188	88.14 251	90.24 279	72.82 281	94.11 144	92.20 246	86.66 102	79.42 265	92.36 176	73.52 169	95.81 259	71.26 260	93.66 114	95.80 123
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 243	83.06 244	88.54 239	91.72 210	78.44 225	95.18 72	92.82 234	82.73 192	79.67 262	92.12 184	73.49 170	95.96 252	71.10 264	68.73 322	91.21 283

Effi-MVS+-dtu		88.65 128	88.35 115	89.54 206	93.33 174	76.39 258	94.47 119	94.36 197	87.70 77	85.43 170	89.56 256	73.45 171	97.26 186	85.57 107	91.28 142	94.97 144

mvs-test1		89.45 106	89.14 97	90.38 167	93.33 174	77.63 249	94.95 85	94.36 197	87.70 77	87.10 124	92.81 164	73.45 171	98.03 124	85.57 107	93.04 129	95.48 131

PEN-MVS		86.80 190	86.27 179	88.40 243	92.32 198	75.71 264	95.18 72	96.38 78	87.97 69	82.82 224	93.15 148	73.39 173	95.92 253	76.15 231	79.03 288	93.59 225

v1192		87.25 180	86.33 176	90.00 192	90.76 264	79.04 209	93.80 167	95.48 140	82.57 195	85.48 165	91.18 223	73.38 174	97.42 166	82.30 149	82.06 247	93.53 227

QAPM		89.51 103	88.15 123	93.59 56	94.92 120	84.58 60	96.82 18	96.70 58	78.43 249	83.41 218	96.19 60	73.18 175	99.30 27	77.11 223	96.54 74	96.89 91

tpmrst		85.35 219	84.99 204	86.43 281	90.88 261	67.88 312	88.71 281	91.43 270	80.13 230	86.08 144	88.80 263	73.05 176	96.02 249	82.48 145	83.40 237	95.40 134

PS-CasMVS		87.32 177	86.88 152	88.63 230	92.99 187	76.33 260	95.33 56	96.61 66	88.22 66	83.30 220	93.07 152	73.03 177	95.79 260	78.36 209	81.00 268	93.75 214

DTE-MVSNet		86.11 203	85.48 197	87.98 253	91.65 214	74.92 267	94.93 87	95.75 119	87.36 84	82.26 229	93.04 153	72.85 178	95.82 258	74.04 247	77.46 293	93.20 237

MVSTER		88.84 124	88.29 120	90.51 159	92.95 188	80.44 162	93.73 173	95.01 172	84.66 138	87.15 122	93.12 150	72.79 179	97.21 192	87.86 82	87.36 201	93.87 203

pcd1.5k->3k		37.02 319	38.84 320	31.53 332	92.33 197	0.00 352	0.00 342	96.13 92	0.00 346	0.00 348	0.00 348	72.70 180	0.00 349	0.00 346	88.43 189	94.60 167

v1921920		86.97 188	86.06 185	89.69 203	90.53 274	78.11 235	93.80 167	95.43 148	81.90 209	85.33 179	91.05 229	72.66 181	97.41 171	82.05 153	81.80 255	93.53 227

DP-MVS		87.25 180	85.36 200	92.90 74	97.65 33	83.24 94	94.81 95	92.00 252	74.99 277	81.92 237	95.00 91	72.66 181	99.05 44	66.92 293	92.33 137	96.40 100

v7n		86.81 189	85.76 191	89.95 193	90.72 266	79.25 203	95.07 78	95.92 105	84.45 144	82.29 228	90.86 231	72.60 183	97.53 148	79.42 201	80.52 276	93.08 244

v748		86.27 201	85.28 201	89.25 217	90.26 278	77.58 250	94.89 89	95.50 139	84.28 148	81.41 242	90.46 242	72.57 184	97.32 179	79.81 193	78.36 289	92.84 249

OPM-MVS		90.12 88	89.56 87	91.82 115	93.14 180	83.90 78	94.16 141	95.74 120	88.96 49	87.86 106	95.43 81	72.48 185	97.91 131	88.10 80	90.18 162	93.65 218

LS3D		87.89 148	86.32 177	92.59 83	96.07 83	82.92 105	95.23 69	94.92 180	75.66 271	82.89 223	95.98 66	72.48 185	99.21 30	68.43 284	95.23 93	95.64 128

pm-mvs1		86.61 195	85.54 193	89.82 196	91.44 218	80.18 163	95.28 67	94.85 183	83.84 153	81.66 239	92.62 169	72.45 187	96.48 231	79.67 195	78.06 290	92.82 251

PMMVS		85.71 215	84.96 207	87.95 254	88.90 296	77.09 252	88.68 282	90.06 299	72.32 298	86.47 133	90.76 233	72.15 188	94.40 292	81.78 159	93.49 118	92.36 263

PatchmatchNet		85.85 210	84.70 215	89.29 216	91.76 209	75.54 265	88.49 284	91.30 272	81.63 216	85.05 182	88.70 265	71.71 189	96.24 242	74.61 244	89.05 180	96.08 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 190

V4		86.50 197	85.54 193	89.39 213	89.13 292	78.99 210	94.73 99	95.54 134	83.59 159	82.10 232	90.61 236	71.60 191	97.45 155	82.52 143	80.01 281	91.74 273

v52		86.50 197	85.53 196	89.39 213	89.17 291	78.99 210	94.72 102	95.54 134	83.59 159	82.10 232	90.60 237	71.59 192	97.45 155	82.52 143	79.99 282	91.73 274

patchmatchnet-post											83.76 307	71.53 193	96.48 231

v1240		86.78 191	85.85 189	89.56 205	90.45 275	77.79 243	93.61 181	95.37 153	81.65 214	85.43 170	91.15 225	71.50 194	97.43 164	81.47 162	82.05 249	93.47 231

anonymousdsp		87.84 150	87.09 145	90.12 180	89.13 292	80.54 159	94.67 107	95.55 132	82.05 202	83.82 208	92.12 184	71.47 195	97.15 194	87.15 93	87.80 198	92.67 253

Patchmatch-test		81.37 270	79.30 274	87.58 260	90.92 258	74.16 271	80.99 324	87.68 322	70.52 309	76.63 279	88.81 262	71.21 196	92.76 309	60.01 315	86.93 207	95.83 121

F-COLMAP		87.95 147	86.80 157	91.40 127	96.35 69	80.88 151	94.73 99	95.45 145	79.65 236	82.04 235	94.61 103	71.13 197	98.50 88	76.24 230	91.05 148	94.80 160

pmmvs4		85.43 217	83.86 224	90.16 174	90.02 284	82.97 104	90.27 258	92.67 238	75.93 270	80.73 249	91.74 200	71.05 198	95.73 262	78.85 205	83.46 235	91.78 272

CR-MVSNet		85.35 219	83.76 225	90.12 180	90.58 270	79.34 197	85.24 307	91.96 256	78.27 251	85.55 159	87.87 279	71.03 199	95.61 263	73.96 249	89.36 174	95.40 134

Patchmtry		82.71 257	80.93 260	88.06 252	90.05 283	76.37 259	84.74 309	91.96 256	72.28 299	81.32 244	87.87 279	71.03 199	95.50 270	68.97 280	80.15 279	92.32 265

PatchFormer-LS_test		86.02 206	85.13 203	88.70 228	91.52 215	74.12 272	91.19 253	92.09 248	82.71 193	84.30 201	87.24 285	70.87 201	96.98 207	81.04 165	85.17 218	95.00 143

RPMNet		83.18 255	80.87 261	90.12 180	90.58 270	79.34 197	85.24 307	90.78 288	71.44 303	85.55 159	82.97 312	70.87 201	95.61 263	61.01 311	89.36 174	95.40 134

Patchmatch-RL test		81.67 264	79.96 268	86.81 279	85.42 313	71.23 295	82.17 322	87.50 324	78.47 248	77.19 278	82.50 313	70.81 203	93.48 301	82.66 142	72.89 303	95.71 126

CostFormer		85.77 213	84.94 208	88.26 247	91.16 248	72.58 288	89.47 272	91.04 281	76.26 267	86.45 136	89.97 249	70.74 204	96.86 216	82.35 148	87.07 206	95.34 137

sam_mvs												70.60 205

xiu_mvs_v1_base_debu		90.64 79	90.05 81	92.40 90	93.97 157	84.46 66	93.32 189	95.46 141	85.17 126	92.25 52	94.03 117	70.59 206	98.57 85	90.97 52	94.67 96	94.18 185

xiu_mvs_v1_base		90.64 79	90.05 81	92.40 90	93.97 157	84.46 66	93.32 189	95.46 141	85.17 126	92.25 52	94.03 117	70.59 206	98.57 85	90.97 52	94.67 96	94.18 185

xiu_mvs_v1_base_debi		90.64 79	90.05 81	92.40 90	93.97 157	84.46 66	93.32 189	95.46 141	85.17 126	92.25 52	94.03 117	70.59 206	98.57 85	90.97 52	94.67 96	94.18 185

test_post											10.29 343	70.57 209	95.91 255

CANet_DTU		90.26 87	89.41 91	92.81 76	93.46 172	83.01 102	93.48 185	94.47 194	89.43 37	87.76 115	94.23 115	70.54 210	99.03 48	84.97 111	96.39 77	96.38 101

BH-RMVSNet		88.37 133	87.48 133	91.02 141	95.28 109	79.45 187	92.89 211	93.07 230	85.45 122	86.91 127	94.84 98	70.35 211	97.76 136	73.97 248	94.59 100	95.85 119

Fast-Effi-MVS+-dtu		87.44 174	86.72 160	89.63 204	92.04 203	77.68 248	94.03 155	93.94 216	85.81 113	82.42 227	91.32 216	70.33 212	97.06 202	80.33 181	90.23 161	94.14 188

MDTV_nov1_ep13_2view						55.91 334	87.62 293		73.32 289	84.59 189		70.33 212		74.65 243		95.50 130

ACMM	84.12 9	89.14 115	88.48 114	91.12 134	94.65 132	81.22 140	95.31 57	96.12 93	85.31 125	85.92 145	94.34 107	70.19 214	98.06 122	85.65 106	88.86 182	94.08 193
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LPG-MVS_test		89.45 106	88.90 104	91.12 134	94.47 137	81.49 131	95.30 59	96.14 90	86.73 100	85.45 167	95.16 87	69.89 215	98.10 112	87.70 84	89.23 177	93.77 212

LGP-MVS_train				91.12 134	94.47 137	81.49 131		96.14 90	86.73 100	85.45 167	95.16 87	69.89 215	98.10 112	87.70 84	89.23 177	93.77 212

CHOSEN 280x420		85.15 223	83.99 222	88.65 229	92.47 195	78.40 227	79.68 327	92.76 235	74.90 279	81.41 242	89.59 254	69.85 217	95.51 268	79.92 189	95.29 91	92.03 269

LTVRE_ROB	82.13 13	86.26 202	84.90 210	90.34 170	94.44 140	81.50 130	92.31 228	94.89 181	83.03 181	79.63 263	92.67 167	69.69 218	97.79 134	71.20 261	86.26 209	91.72 275
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	88.74 127	87.29 138	93.08 66	92.70 192	85.39 51	96.57 22	96.43 74	78.74 246	80.85 248	96.07 64	69.64 219	99.01 53	78.01 214	96.65 71	94.83 158

MDTV_nov1_ep13			83.56 233		91.69 213	69.93 306	87.75 291	91.54 267	78.60 247	84.86 185	88.90 261	69.54 220	96.03 248	70.25 266	88.93 181

PatchT		82.68 258	81.27 256	86.89 277	90.09 282	70.94 300	84.06 314	90.15 296	74.91 278	85.63 158	83.57 308	69.37 221	94.87 290	65.19 298	88.50 187	94.84 157

VPNet		88.20 138	87.47 134	90.39 165	93.56 170	79.46 185	94.04 154	95.54 134	88.67 55	86.96 125	94.58 105	69.33 222	97.15 194	84.05 128	80.53 275	94.56 171

ACMP	84.23 8	89.01 122	88.35 115	90.99 143	94.73 126	81.27 137	95.07 78	95.89 110	86.48 103	83.67 212	94.30 110	69.33 222	97.99 126	87.10 97	88.55 184	93.72 216
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 288				9.81 344	69.31 224	95.53 266	76.65 226

tpmvs		83.35 254	82.07 251	87.20 272	91.07 250	71.00 299	88.31 286	91.70 260	78.91 240	80.49 254	87.18 286	69.30 225	97.08 200	68.12 288	83.56 233	93.51 230

thres200		87.21 183	86.24 180	90.12 180	95.36 105	78.53 218	93.26 196	92.10 247	86.42 105	88.00 105	91.11 227	69.24 226	98.00 125	69.58 274	91.04 149	93.83 207

tfpn200view9		87.58 170	86.64 169	90.41 164	95.99 86	78.64 214	94.58 111	91.98 254	86.94 96	88.09 100	91.77 198	69.18 227	98.10 112	70.13 269	91.10 143	94.48 178

thres400		87.62 164	86.64 169	90.57 150	95.99 86	78.64 214	94.58 111	91.98 254	86.94 96	88.09 100	91.77 198	69.18 227	98.10 112	70.13 269	91.10 143	94.96 147

tfpnnormal		84.72 238	83.23 242	89.20 219	92.79 191	80.05 168	94.48 116	95.81 114	82.38 197	81.08 246	91.21 221	69.01 229	96.95 210	61.69 309	80.59 273	90.58 300

conf200view11		87.65 158	86.71 161	90.46 163	96.12 77	78.55 216	95.03 81	91.58 263	87.15 85	88.06 103	92.29 179	68.91 230	98.10 112	70.13 269	91.10 143	94.71 162

thres100view900		87.63 162	86.71 161	90.38 167	96.12 77	78.55 216	95.03 81	91.58 263	87.15 85	88.06 103	92.29 179	68.91 230	98.10 112	70.13 269	91.10 143	94.48 178

thres600view7		87.65 158	86.67 164	90.59 149	96.08 82	78.72 212	94.88 91	91.58 263	87.06 93	88.08 102	92.30 178	68.91 230	98.10 112	70.05 273	91.10 143	94.96 147

view600		87.62 164	86.65 165	90.53 152	96.19 72	78.52 219	95.29 61	91.09 274	87.08 89	87.84 108	93.03 154	68.86 233	98.11 108	69.44 275	91.02 150	94.96 147

view800		87.62 164	86.65 165	90.53 152	96.19 72	78.52 219	95.29 61	91.09 274	87.08 89	87.84 108	93.03 154	68.86 233	98.11 108	69.44 275	91.02 150	94.96 147

conf0.05thres1000		87.62 164	86.65 165	90.53 152	96.19 72	78.52 219	95.29 61	91.09 274	87.08 89	87.84 108	93.03 154	68.86 233	98.11 108	69.44 275	91.02 150	94.96 147

tfpn		87.62 164	86.65 165	90.53 152	96.19 72	78.52 219	95.29 61	91.09 274	87.08 89	87.84 108	93.03 154	68.86 233	98.11 108	69.44 275	91.02 150	94.96 147

PatchMatch-RL		86.77 193	85.54 193	90.47 162	95.88 89	82.71 113	90.54 256	92.31 243	79.82 234	84.32 199	91.57 208	68.77 237	96.39 236	73.16 253	93.48 120	92.32 265

XVG-OURS		89.40 111	88.70 107	91.52 123	94.06 149	81.46 133	91.27 251	96.07 96	86.14 111	88.89 94	95.77 74	68.73 238	97.26 186	87.39 89	89.96 165	95.83 121

TR-MVS		86.78 191	85.76 191	89.82 196	94.37 141	78.41 226	92.47 223	92.83 233	81.11 224	86.36 138	92.40 174	68.73 238	97.48 151	73.75 251	89.85 167	93.57 226

tpm		84.73 237	84.02 221	86.87 278	90.33 276	68.90 309	89.06 278	89.94 302	80.85 226	85.75 150	89.86 251	68.54 240	95.97 251	77.76 215	84.05 227	95.75 125

DI_MVS_plusplus_test		88.15 140	86.82 155	92.14 101	90.67 268	81.07 144	93.01 206	94.59 191	83.83 155	77.78 273	90.63 235	68.51 241	98.16 104	88.02 81	94.37 107	97.17 80

test_normal		88.13 141	86.78 159	92.18 99	90.55 273	81.19 142	92.74 214	94.64 190	83.84 153	77.49 276	90.51 241	68.49 242	98.16 104	88.22 76	94.55 101	97.21 78

tfpn_ndepth		86.10 204	84.98 205	89.43 212	95.52 102	78.29 230	94.62 109	89.60 309	81.88 211	85.43 170	90.54 238	68.47 243	96.85 217	68.46 283	90.34 159	93.15 241

FMVSNet3		87.40 176	86.11 182	91.30 130	93.79 165	83.64 85	94.20 140	94.81 186	83.89 152	84.37 195	91.87 197	68.45 244	96.56 226	78.23 211	85.36 215	93.70 217

MVP-Stereo		85.97 208	84.86 211	89.32 215	90.92 258	82.19 121	92.11 235	94.19 202	78.76 245	78.77 268	91.63 204	68.38 245	96.56 226	75.01 241	93.95 110	89.20 307
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tfpn1000		86.06 205	84.92 209	89.49 210	95.54 99	77.79 243	94.72 102	89.07 312	82.05 202	85.36 178	91.94 194	68.32 246	96.65 221	67.04 290	90.24 160	94.02 196

tpm cat1		81.96 262	80.27 264	87.01 273	91.09 249	71.02 298	87.38 294	91.53 268	66.25 319	80.17 256	86.35 297	68.22 247	96.15 245	69.16 279	82.29 244	93.86 205

tpm2		84.08 245	82.94 245	87.48 264	91.39 224	71.27 294	89.23 276	90.37 292	71.95 301	84.64 187	89.33 257	67.30 248	96.55 228	75.17 238	87.09 205	94.63 164

test-LLR		85.87 209	85.41 198	87.25 268	90.95 254	71.67 292	89.55 268	89.88 304	83.41 167	84.54 190	87.95 276	67.25 249	95.11 285	81.82 157	93.37 123	94.97 144

test0.0.03 1		82.41 260	81.69 253	84.59 294	88.23 301	72.89 280	90.24 259	87.83 320	83.41 167	79.86 261	89.78 252	67.25 249	88.99 321	65.18 299	83.42 236	91.90 271

CVMVSNet		84.69 240	84.79 213	84.37 296	91.84 206	64.92 320	93.70 177	91.47 269	66.19 320	86.16 143	95.28 83	67.18 251	93.33 303	80.89 170	90.42 157	94.88 156

Patchmatch-test1		85.81 212	84.71 214	89.12 220	92.15 199	76.60 256	91.12 254	91.69 261	83.53 164	85.50 164	88.56 268	66.79 252	95.00 288	72.69 255	90.35 158	95.76 124

IterMVS		84.88 231	83.98 223	87.60 259	91.44 218	76.03 262	90.18 261	92.41 242	83.24 173	81.06 247	90.42 243	66.60 253	94.28 293	79.46 197	80.98 269	92.48 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 178	85.98 186	91.08 137	94.01 152	83.10 97	95.14 75	94.94 176	83.57 161	84.37 195	91.64 201	66.59 254	96.34 239	78.23 211	85.36 215	93.79 208

test1		87.26 178	85.98 186	91.08 137	94.01 152	83.10 97	95.14 75	94.94 176	83.57 161	84.37 195	91.64 201	66.59 254	96.34 239	78.23 211	85.36 215	93.79 208

FMVSNet2		87.19 184	85.82 190	91.30 130	94.01 152	83.67 84	94.79 96	94.94 176	83.57 161	83.88 206	92.05 191	66.59 254	96.51 229	77.56 218	85.01 219	93.73 215

EPMVS		83.90 248	82.70 249	87.51 261	90.23 280	72.67 284	88.62 283	81.96 335	81.37 222	85.01 183	88.34 271	66.31 257	94.45 291	75.30 237	87.12 204	95.43 133

semantic-postprocess				88.18 250	91.71 211	76.87 255		92.65 239	85.40 123	81.44 241	90.54 238	66.21 258	95.00 288	81.04 165	81.05 264	92.66 254

tpmp4_e23		83.87 249	82.33 250	88.48 240	91.46 217	72.82 281	89.82 266	91.57 266	73.02 293	81.86 238	89.05 259	66.20 259	96.97 208	71.57 259	86.39 208	95.66 127

MDA-MVSNet_test_wron		79.21 286	77.19 286	85.29 289	88.22 302	72.77 283	85.87 302	90.06 299	74.34 283	62.62 327	87.56 282	66.14 260	91.99 313	66.90 294	73.01 301	91.10 286

YYNet1		79.22 285	77.20 285	85.28 290	88.20 303	72.66 285	85.87 302	90.05 301	74.33 284	62.70 326	87.61 281	66.09 261	92.03 312	66.94 291	72.97 302	91.15 284

JIA-IIPM		81.04 273	78.98 279	87.25 268	88.64 297	73.48 277	81.75 323	89.61 308	73.19 290	82.05 234	73.71 327	66.07 262	95.87 256	71.18 263	84.60 222	92.41 261

MSDG		84.86 232	83.09 243	90.14 179	93.80 163	80.05 168	89.18 277	93.09 229	78.89 241	78.19 269	91.91 195	65.86 263	97.27 184	68.47 282	88.45 188	93.11 242

jajsoiax		88.24 137	87.50 132	90.48 161	90.89 260	80.14 165	95.31 57	95.65 127	84.97 132	84.24 202	94.02 120	65.31 264	97.42 166	88.56 73	88.52 186	93.89 200

cascas		86.43 200	84.98 205	90.80 147	92.10 202	80.92 150	90.24 259	95.91 107	73.10 291	83.57 215	88.39 270	65.15 265	97.46 153	84.90 114	91.43 141	94.03 195

ADS-MVSNet2		81.66 265	79.71 271	87.50 262	91.35 231	74.19 270	83.33 318	88.48 316	72.90 294	82.24 230	85.77 300	64.98 266	93.20 305	64.57 301	83.74 229	95.12 139

ADS-MVSNet		81.56 267	79.78 269	86.90 276	91.35 231	71.82 291	83.33 318	89.16 311	72.90 294	82.24 230	85.77 300	64.98 266	93.76 297	64.57 301	83.74 229	95.12 139

pmmvs5		84.21 244	82.84 248	88.34 245	88.95 295	76.94 254	92.41 224	91.91 258	75.63 272	80.28 255	91.18 223	64.59 268	95.57 265	77.09 224	83.47 234	92.53 257

PVSNet	78.82 18	85.55 216	84.65 216	88.23 249	94.72 127	71.93 290	87.12 295	92.75 236	78.80 244	84.95 184	90.53 240	64.43 269	96.71 220	74.74 242	93.86 112	96.06 112

UGNet		89.95 93	88.95 102	92.95 72	94.51 136	83.31 93	95.70 46	95.23 164	89.37 39	87.58 117	93.94 124	64.00 270	98.78 75	83.92 129	96.31 78	96.74 95
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		85.07 224	84.27 218	87.48 264	92.91 189	70.62 302	91.69 244	92.46 241	76.20 268	82.67 226	95.22 86	63.94 271	97.29 183	77.51 219	85.80 212	94.53 172

mvs_tets		88.06 143	87.28 139	90.38 167	90.94 256	79.88 173	95.22 70	95.66 125	85.10 130	84.21 203	93.94 124	63.53 272	97.40 173	88.50 74	88.40 191	93.87 203

dp		81.47 269	80.23 265	85.17 291	89.92 286	65.49 319	86.74 296	90.10 298	76.30 266	81.10 245	87.12 287	62.81 273	95.92 253	68.13 287	79.88 284	94.09 192

LFMVS		90.08 89	89.13 98	92.95 72	96.71 59	82.32 120	96.08 32	89.91 303	86.79 99	92.15 57	96.81 31	62.60 274	98.34 96	87.18 92	93.90 111	98.19 35

DWT-MVSNet_test		84.95 229	83.68 230	88.77 225	91.43 221	73.75 275	91.74 241	90.98 282	80.66 227	83.84 207	87.36 283	62.44 275	97.11 198	78.84 206	85.81 211	95.46 132

Anonymous20231206		81.03 274	79.77 270	84.82 293	87.85 308	70.26 304	91.42 248	92.08 249	73.67 286	77.75 274	89.25 258	62.43 276	93.08 307	61.50 310	82.00 250	91.12 285

VDD-MVS		90.74 76	89.92 84	93.20 61	96.27 70	83.02 101	95.73 44	93.86 218	88.42 62	92.53 47	96.84 29	62.09 277	98.64 80	90.95 55	92.62 135	97.93 55

MS-PatchMatch		85.05 225	84.16 219	87.73 257	91.42 222	78.51 223	91.25 252	93.53 223	77.50 256	80.15 257	91.58 206	61.99 278	95.51 268	75.69 233	94.35 108	89.16 308

OurMVSNet-221017-0		85.35 219	84.64 217	87.49 263	90.77 263	72.59 287	94.01 157	94.40 196	84.72 137	79.62 264	93.17 147	61.91 279	96.72 218	81.99 154	81.16 261	93.16 239

test20.03		79.95 280	79.08 277	82.55 303	85.79 312	67.74 313	91.09 255	91.08 278	81.23 223	74.48 299	89.96 250	61.63 280	90.15 319	60.08 313	76.38 295	89.76 302

DSMNet-mixed		76.94 290	76.29 289	78.89 307	83.10 321	56.11 333	87.78 290	79.77 338	60.65 328	75.64 293	88.71 264	61.56 281	88.34 323	60.07 314	89.29 176	92.21 268

IB-MVS	80.51 15	85.24 222	83.26 241	91.19 132	92.13 201	79.86 174	91.75 240	91.29 273	83.28 172	80.66 251	88.49 269	61.28 282	98.46 90	80.99 168	79.46 287	95.25 138
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		86.61 195	85.27 202	90.66 148	91.33 233	78.71 213	90.40 257	93.81 221	85.34 124	85.12 181	89.57 255	61.25 283	97.11 198	80.99 168	89.59 171	96.15 106

N_pmnet		68.89 303	68.44 304	70.23 319	89.07 294	28.79 348	88.06 287	19.50 350	69.47 312	71.86 311	84.93 303	61.24 284	91.75 315	54.70 319	77.15 294	90.15 301

EU-MVSNet		81.32 271	80.95 259	82.42 304	88.50 299	63.67 321	93.32 189	91.33 271	64.02 324	80.57 253	92.83 162	61.21 285	92.27 311	76.34 228	80.38 278	91.32 281

VDDNet		89.56 102	88.49 113	92.76 79	95.07 114	82.09 122	96.30 26	93.19 228	81.05 225	91.88 60	96.86 28	61.16 286	98.33 97	88.43 75	92.49 136	97.84 59

PVSNet_0	73.20 20	77.22 289	74.83 292	84.37 296	90.70 267	71.10 297	83.09 320	89.67 307	72.81 296	73.93 301	83.13 311	60.79 287	93.70 298	68.54 281	50.84 334	88.30 319

SixPastTwentyTwo		83.91 247	82.90 246	86.92 275	90.99 252	70.67 301	93.48 185	91.99 253	85.54 120	77.62 275	92.11 186	60.59 288	96.87 215	76.05 232	77.75 291	93.20 237

gg-mvs-nofinetune		81.77 263	79.37 273	88.99 223	90.85 262	77.73 247	86.29 299	79.63 339	74.88 280	83.19 221	69.05 330	60.34 289	96.11 246	75.46 235	94.64 99	93.11 242

MDA-MVSNet-bldmvs		78.85 287	76.31 288	86.46 280	89.76 288	73.88 274	88.79 280	90.42 291	79.16 239	59.18 328	88.33 272	60.20 290	94.04 295	62.00 308	68.96 320	91.48 279

pmmvs6		83.42 251	81.60 254	88.87 224	88.01 305	77.87 241	94.96 84	94.24 201	74.67 281	78.80 267	91.09 228	60.17 291	96.49 230	77.06 225	75.40 298	92.23 267

ACMH	80.38 17	85.36 218	83.68 230	90.39 165	94.45 139	80.63 156	94.73 99	94.85 183	82.09 201	77.24 277	92.65 168	60.01 292	97.58 144	72.25 257	84.87 220	92.96 245
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 255	89.73 289	77.91 238	87.80 289	78.23 341		80.58 252	83.86 306	59.88 293	95.33 282	71.20 261	92.22 138	90.60 299

pmmvs-eth3d		80.97 275	78.72 280	87.74 256	84.99 316	79.97 172	90.11 262	91.65 262	75.36 273	73.51 302	86.03 299	59.45 294	93.96 296	75.17 238	72.21 304	89.29 306

test_0402		81.30 272	79.17 276	87.67 258	93.19 179	78.17 233	92.98 208	91.71 259	75.25 274	76.02 290	90.31 244	59.23 295	96.37 237	50.22 325	83.63 232	88.47 318

FMVSNet1		85.85 210	84.11 220	91.08 137	92.81 190	83.10 97	95.14 75	94.94 176	81.64 215	82.68 225	91.64 201	59.01 296	96.34 239	75.37 236	83.78 228	93.79 208

COLMAP_ROB	80.39 16	83.96 246	82.04 252	89.74 200	95.28 109	79.75 177	94.25 137	92.28 244	75.17 275	78.02 272	93.77 133	58.60 297	97.84 133	65.06 300	85.92 210	91.63 276
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	85.05 225	83.46 237	89.82 196	94.66 131	79.37 195	94.44 121	94.12 206	82.19 200	78.04 271	92.82 163	58.23 298	97.54 147	73.77 250	82.90 239	92.54 256

LP		75.51 293	72.15 297	85.61 287	87.86 307	73.93 273	80.20 326	88.43 317	67.39 315	70.05 313	80.56 320	58.18 299	93.18 306	46.28 331	70.36 317	89.71 304

CMPMVS	59.16 21	80.52 277	79.20 275	84.48 295	83.98 318	67.63 314	89.95 265	93.84 220	64.79 323	66.81 321	91.14 226	57.93 300	95.17 283	76.25 229	88.10 193	90.65 296
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ITE_SJBPF				88.24 248	91.88 205	77.05 253		92.92 231	85.54 120	80.13 259	93.30 142	57.29 301	96.20 243	72.46 256	84.71 221	91.49 278

TESTMET0.1,1		83.74 250	82.85 247	86.42 282	89.96 285	71.21 296	89.55 268	87.88 319	77.41 257	83.37 219	87.31 284	56.71 302	93.65 299	80.62 174	92.85 134	94.40 181

UnsupCasMVSNet_eth		80.07 279	78.27 281	85.46 288	85.24 314	72.63 286	88.45 285	94.87 182	82.99 185	71.64 312	88.07 275	56.34 303	91.75 315	73.48 252	63.36 329	92.01 270

K. test v3		81.59 266	80.15 267	85.91 285	89.89 287	69.42 308	92.57 220	87.71 321	85.56 119	73.44 303	89.71 253	55.58 304	95.52 267	77.17 222	69.76 318	92.78 252

test-mter		84.54 242	83.64 232	87.25 268	90.95 254	71.67 292	89.55 268	89.88 304	79.17 238	84.54 190	87.95 276	55.56 305	95.11 285	81.82 157	93.37 123	94.97 144

lessismore_v0				86.04 283	88.46 300	68.78 310		80.59 337		73.01 306	90.11 247	55.39 306	96.43 235	75.06 240	65.06 324	92.90 246

MVS-HIRNet		73.70 296	72.20 296	78.18 310	91.81 208	56.42 332	82.94 321	82.58 333	55.24 330	68.88 315	66.48 331	55.32 307	95.13 284	58.12 316	88.42 190	83.01 325

new-patchmatchnet		76.41 291	75.17 291	80.13 306	82.65 324	59.61 326	87.66 292	91.08 278	78.23 253	69.85 314	83.22 310	54.76 308	91.63 317	64.14 303	64.89 325	89.16 308

XVG-ACMP-BASELINE		86.00 207	84.84 212	89.45 211	91.20 243	78.00 236	91.70 243	95.55 132	85.05 131	82.97 222	92.25 182	54.49 309	97.48 151	82.93 138	87.45 200	92.89 247

USDC		82.76 256	81.26 257	87.26 267	91.17 246	74.55 268	89.27 274	93.39 226	78.26 252	75.30 294	92.08 188	54.43 310	96.63 222	71.64 258	85.79 213	90.61 297

AllTest		83.42 251	81.39 255	89.52 207	95.01 115	77.79 243	93.12 200	90.89 285	77.41 257	76.12 287	93.34 138	54.08 311	97.51 149	68.31 285	84.27 225	93.26 235

TestCases				89.52 207	95.01 115	77.79 243		90.89 285	77.41 257	76.12 287	93.34 138	54.08 311	97.51 149	68.31 285	84.27 225	93.26 235

MIMVSNet		82.59 259	80.53 262	88.76 226	91.51 216	78.32 228	86.57 298	90.13 297	79.32 237	80.70 250	88.69 266	52.98 313	93.07 308	66.03 296	88.86 182	94.90 155

FMVSNet5		81.52 268	79.60 272	87.27 266	91.17 246	77.95 237	91.49 247	92.26 245	76.87 262	76.16 286	87.91 278	51.67 314	92.34 310	67.74 289	81.16 261	91.52 277

testgi		80.94 276	80.20 266	83.18 300	87.96 306	66.29 316	91.28 250	90.70 290	83.70 157	78.12 270	92.84 161	51.37 315	90.82 318	63.34 304	82.46 243	92.43 260

Test4		85.75 214	83.72 228	91.83 114	88.08 304	81.03 146	92.48 222	95.54 134	83.38 169	73.40 304	88.57 267	50.99 316	97.37 177	86.61 103	94.47 104	97.09 84

UnsupCasMVSNet_bld		76.23 292	73.27 294	85.09 292	83.79 319	72.92 279	85.65 306	93.47 225	71.52 302	68.84 316	79.08 323	49.77 317	93.21 304	66.81 295	60.52 331	89.13 310

OpenMVS_ROB	74.94 19	79.51 283	77.03 287	86.93 274	87.00 309	76.23 261	92.33 227	90.74 289	68.93 313	74.52 298	88.23 273	49.58 318	96.62 223	57.64 317	84.29 224	87.94 320

testing_2		83.40 253	81.02 258	90.56 151	85.06 315	80.51 160	91.37 249	95.57 130	82.92 187	67.06 320	85.54 302	49.47 319	97.24 188	86.74 98	85.44 214	93.93 198

TDRefinement		79.81 281	77.34 283	87.22 271	79.24 330	75.48 266	93.12 200	92.03 251	76.45 263	75.01 295	91.58 206	49.19 320	96.44 234	70.22 268	69.18 319	89.75 303

MIMVSNet1		79.38 284	77.28 284	85.69 286	86.35 311	73.67 276	91.61 246	92.75 236	78.11 255	72.64 308	88.12 274	48.16 321	91.97 314	60.32 312	77.49 292	91.43 280

LF4IMVS		80.37 278	79.07 278	84.27 298	86.64 310	69.87 307	89.39 273	91.05 280	76.38 264	74.97 296	90.00 248	47.85 322	94.25 294	74.55 245	80.82 271	88.69 313

EG-PatchMatch MVS		82.37 261	80.34 263	88.46 241	90.27 277	79.35 196	92.80 213	94.33 199	77.14 261	73.26 305	90.18 246	47.47 323	96.72 218	70.25 266	87.32 203	89.30 305

testpf		71.41 301	72.11 298	69.30 321	84.53 317	59.79 325	62.74 337	83.14 332	71.11 306	68.83 317	81.57 318	46.70 324	84.83 334	74.51 246	75.86 297	63.30 333

TinyColmap		79.76 282	77.69 282	85.97 284	91.71 211	73.12 278	89.55 268	90.36 293	75.03 276	72.03 310	90.19 245	46.22 325	96.19 244	63.11 305	81.03 265	88.59 314

test2356		74.50 294	73.27 294	78.20 308	80.81 326	59.84 324	83.76 317	88.33 318	71.43 304	72.37 309	81.84 316	45.60 326	86.26 329	50.97 323	84.32 223	88.50 315

tmp_tt		35.64 320	39.24 319	24.84 333	14.87 348	23.90 349	62.71 338	51.51 349	6.58 343	36.66 338	62.08 335	44.37 327	30.34 346	52.40 320	22.00 343	20.27 341

new_pmnet		72.15 299	70.13 300	78.20 308	82.95 323	65.68 317	83.91 315	82.40 334	62.94 326	64.47 324	79.82 322	42.85 328	86.26 329	57.41 318	74.44 300	82.65 326

test1235678		72.22 298	70.31 299	77.93 311	78.04 331	58.04 328	85.76 304	89.80 306	70.15 311	63.43 325	80.20 321	42.24 329	87.24 326	48.68 327	74.50 299	88.50 315

1111		70.54 302	69.71 301	73.04 316	79.30 328	44.83 341	84.23 312	88.96 313	67.33 316	65.42 322	82.28 314	41.11 330	88.11 324	47.12 329	71.60 309	86.19 322

.test1245		57.63 312	61.79 309	45.14 330	79.30 328	44.83 341	84.23 312	88.96 313	67.33 316	65.42 322	82.28 314	41.11 330	88.11 324	47.12 329	0.39 345	2.46 344

testus		74.41 295	73.35 293	77.59 312	82.49 325	57.08 329	86.02 300	90.21 295	72.28 299	72.89 307	84.32 305	37.08 332	86.96 327	52.24 321	82.65 241	88.73 311

pmmvs3		71.81 300	68.71 303	81.11 305	75.86 332	70.42 303	86.74 296	83.66 331	58.95 329	68.64 318	80.89 319	36.93 333	89.52 320	63.10 306	63.59 328	83.39 324

PM-MVS		78.11 288	76.12 290	84.09 299	83.54 320	70.08 305	88.97 279	85.27 329	79.93 232	74.73 297	86.43 291	34.70 334	93.48 301	79.43 200	72.06 305	88.72 312

Anonymous20231211		72.97 297	69.63 302	83.00 302	83.05 322	66.91 315	92.69 215	89.45 310	61.06 327	67.50 319	83.46 309	34.34 335	93.61 300	51.11 322	63.97 327	88.48 317

ambc				83.06 301	79.99 327	63.51 322	77.47 330	92.86 232		74.34 300	84.45 304	28.74 336	95.06 287	73.06 254	68.89 321	90.61 297

test12356		64.99 306	63.78 305	68.61 323	72.69 334	39.14 344	78.46 328	87.61 323	64.91 322	55.77 329	77.48 324	28.10 337	85.59 331	44.69 332	64.35 326	81.12 328

DeepMVS_CX				56.31 328	74.23 333	51.81 337		56.67 348	44.85 334	48.54 334	75.16 325	27.87 338	58.74 344	40.92 335	52.22 333	58.39 337

no-one		61.56 308	56.58 310	76.49 314	67.80 340	62.76 323	78.13 329	86.11 325	63.16 325	43.24 335	64.70 333	26.12 339	88.95 322	50.84 324	29.15 337	77.77 330

testmv		65.49 305	62.66 306	73.96 315	68.78 337	53.14 336	84.70 310	88.56 315	65.94 321	52.35 331	74.65 326	25.02 340	85.14 332	43.54 333	60.40 332	83.60 323

FPMVS		64.63 307	62.55 307	70.88 318	70.80 335	56.71 330	84.42 311	84.42 330	51.78 332	49.57 332	81.61 317	23.49 341	81.48 336	40.61 336	76.25 296	74.46 332

ANet_high		58.88 310	54.22 313	72.86 317	56.50 346	56.67 331	80.75 325	86.00 326	73.09 292	37.39 337	64.63 334	22.17 342	79.49 339	43.51 334	23.96 341	82.43 327

EMVS		42.07 318	41.12 318	44.92 331	63.45 343	35.56 347	73.65 331	63.48 345	33.05 340	26.88 343	45.45 341	21.27 343	67.14 342	19.80 342	23.02 342	32.06 340

Gipuma		57.99 311	54.91 312	67.24 324	88.51 298	65.59 318	52.21 340	90.33 294	43.58 336	42.84 336	51.18 338	20.29 344	85.07 333	34.77 338	70.45 316	51.05 338
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 317	42.29 317	46.03 329	65.58 341	37.41 345	73.51 332	64.62 344	33.99 339	28.47 342	47.87 339	19.90 345	67.91 341	22.23 341	24.45 340	32.77 339

PMMVS2		59.60 309	56.40 311	69.21 322	68.83 336	46.58 339	73.02 335	77.48 342	55.07 331	49.21 333	72.95 329	17.43 346	80.04 337	49.32 326	44.33 335	80.99 329

LCM-MVSNet		66.00 304	62.16 308	77.51 313	64.51 342	58.29 327	83.87 316	90.90 284	48.17 333	54.69 330	73.31 328	16.83 347	86.75 328	65.47 297	61.67 330	87.48 321

PNet_i23d		50.48 315	47.18 315	60.36 326	68.59 338	44.56 343	72.75 336	72.61 343	43.92 335	33.91 339	60.19 336	6.16 348	73.52 340	38.50 337	28.04 338	63.01 334

PMVS	47.18 22	52.22 313	48.46 314	63.48 325	45.72 347	46.20 340	73.41 333	78.31 340	41.03 337	30.06 340	65.68 332	6.05 349	83.43 335	30.04 339	65.86 323	60.80 335
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.65 23	43.39 316	38.59 321	57.77 327	56.52 345	48.77 338	55.38 339	58.64 347	29.33 341	28.96 341	52.65 337	4.68 350	64.62 343	28.11 340	33.07 336	59.93 336
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		21.27 322	20.48 323	23.63 334	68.59 338	36.41 346	49.57 341	6.85 351	9.37 342	7.89 345	4.46 347	4.03 351	31.37 345	17.47 343	16.07 344	3.12 342

wuykxyi23d		50.55 314	44.13 316	69.81 320	56.77 344	54.58 335	73.22 334	80.78 336	39.79 338	22.08 344	46.69 340	4.03 351	79.71 338	47.65 328	26.13 339	75.14 331

test123		8.76 324	11.22 325	1.39 335	0.85 350	0.97 350	85.76 304	0.35 353	0.54 345	2.45 347	8.14 346	0.60 353	0.48 347	2.16 345	0.17 347	2.71 343

testmvs		8.92 323	11.52 324	1.12 336	1.06 349	0.46 351	86.02 300	0.65 352	0.62 344	2.74 346	9.52 345	0.31 354	0.45 348	2.38 344	0.39 345	2.46 344

sosnet-low-res		0.00 327	0.00 328	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	0.00 348	0.00 355	0.00 349	0.00 346	0.00 348	0.00 346

sosnet		0.00 327	0.00 328	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	0.00 348	0.00 355	0.00 349	0.00 346	0.00 348	0.00 346

uncertanet		0.00 327	0.00 328	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	0.00 348	0.00 355	0.00 349	0.00 346	0.00 348	0.00 346

Regformer		0.00 327	0.00 328	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	0.00 348	0.00 355	0.00 349	0.00 346	0.00 348	0.00 346

ab-mvs-re		7.82 325	10.43 326	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	93.88 129	0.00 355	0.00 349	0.00 346	0.00 348	0.00 346

uanet		0.00 327	0.00 328	0.00 337	0.00 351	0.00 352	0.00 342	0.00 354	0.00 346	0.00 348	0.00 348	0.00 355	0.00 349	0.00 346	0.00 348	0.00 346

test_part2					98.55 5	87.22 10				96.40 2

test11111								97.46 6

MTGPA								96.97 34

MTMP								60.64 346

gm-plane-assit					89.60 290	68.00 311			77.28 260		88.99 260		97.57 145	79.44 199

test9_res														91.91 40	98.71 18	98.07 44

agg_prior2														90.54 59	98.68 23	98.27 30

agg_prior					97.38 42	85.92 43		96.72 56		92.16 55			98.97 59

test_prior4						85.96 42	94.11 144

test_prior				93.82 50	97.29 47	84.49 63		96.88 43					98.87 65			98.11 42

旧先验2							93.36 188		71.25 305	94.37 12			97.13 197	86.74 98

新几何2							93.11 202

无先验							93.28 195	96.26 82	73.95 285				99.05 44	80.56 175		96.59 97

原ACMM2							92.94 210

testdata2													98.75 76	78.30 210

testdata1							92.15 233		87.94 70

plane_prior7					94.70 129	82.74 110

plane_prior5								96.22 86					98.12 106	88.15 77	89.99 163	94.63 164

plane_prior4											94.86 95

plane_prior3						82.75 108			90.26 25	86.91 127

plane_prior2							95.85 40		90.81 18

plane_prior1					94.59 133

plane_prior						82.73 111	95.21 71		89.66 35						89.88 166

n2								0.00 354

nn								0.00 354

door-mid								85.49 327

test11								96.57 70

door								85.33 328

HQP5-MVS						81.56 128

HQP-NCC					94.17 146		94.39 126		88.81 50	85.43 170

ACMP_Plane					94.17 146		94.39 126		88.81 50	85.43 170

BP-MVS														87.11 95

HQP4-MVS										85.43 170			97.96 127			94.51 174

HQP3-MVS								96.04 99							89.77 168

NP-MVS					94.37 141	82.42 118					93.98 122

ACMMP++_ref															87.47 199

ACMMP++															88.01 196

High-resolution multi-view benchmark