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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

UA-Net		78.65 35	83.96 41	72.46 41	84.87 1	76.15 42	89.06 31	55.70 43	77.25 65	53.14 128	79.73 94	82.09 142	59.69 69	92.21 5	90.93 3	92.32 3	89.36 7

mPP-MVS					82.97 2							92.12 35

DTE-MVSNet		77.28 45	84.87 33	68.42 59	82.94 3	72.70 61	81.60 62	61.78 12	85.03 10	51.40 134	92.11 4	96.00 5	49.42 135	89.73 23	82.52 47	83.39 70	75.98 83

zzz-MVS		82.61 10	85.04 30	79.79 6	82.59 4	73.90 55	92.42 9	62.39 11	84.54 13	80.21 9	79.86 92	90.74 63	70.63 17	90.01 21	89.71 8	90.48 21	86.49 33

MP-MVS		83.50 5	86.11 18	80.45 3	82.58 5	80.60 24	92.68 5	63.48 3	81.43 39	80.21 9	81.95 73	90.76 62	72.86 6	90.14 19	89.30 11	90.92 19	88.59 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		77.06 48	85.05 29	67.74 62	82.29 6	72.59 62	80.86 67	61.03 19	84.66 11	50.08 140	92.19 2	96.59 3	49.12 136	89.83 22	82.35 49	83.06 73	77.14 79

HPM-MVS++		80.44 28	82.57 46	77.96 14	81.99 7	72.76 59	90.48 20	61.31 14	80.85 46	77.90 18	81.93 74	87.01 112	68.20 29	84.15 54	85.27 30	87.85 40	86.00 36

CP-MVS		84.06 3	86.79 9	80.86 2	81.81 8	79.66 30	92.67 6	64.48 1	83.13 25	82.32 3	80.89 85	92.97 27	72.51 9	91.74 6	90.02 6	91.40 17	89.14 8

PS-CasMVS		77.46 44	85.80 22	67.73 63	81.24 9	72.88 58	80.63 69	61.28 15	84.14 17	50.53 137	92.13 3	96.76 1	50.12 132	91.02 9	84.46 32	82.60 80	79.19 66

APD-MVS		80.60 27	84.63 35	75.91 24	81.22 10	81.48 10	90.49 19	58.81 28	77.54 64	67.49 70	85.90 27	89.82 81	69.43 22	86.08 43	83.80 38	88.01 38	87.77 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVSNet		77.01 49	85.04 30	67.65 64	81.16 11	72.72 60	80.54 70	61.18 16	82.09 34	50.41 138	90.81 6	95.89 6	50.03 133	90.86 10	84.30 35	82.56 82	78.65 72

ACMMPR		83.94 4	87.20 3	80.14 4	81.04 12	81.92 8	92.57 8	63.14 5	84.35 16	79.45 12	83.37 50	92.04 36	72.82 8	90.66 12	88.96 12	91.80 6	89.13 9

train_agg		77.83 39	80.47 57	74.77 29	80.92 13	69.60 72	88.87 33	56.32 39	74.03 82	71.03 45	83.67 47	87.68 102	64.75 42	83.70 58	81.85 54	86.71 47	82.73 49

TSAR-MVS + MP.		81.23 23	86.13 16	75.52 26	80.74 14	83.22 3	90.55 17	55.12 46	80.87 45	67.62 67	88.01 12	92.38 32	70.61 18	86.64 40	83.10 43	88.51 33	88.67 16

CPTT-MVS		82.32 13	85.00 32	79.19 7	80.73 15	80.86 21	91.68 13	62.59 9	82.55 30	75.53 29	73.88 127	92.28 33	73.74 5	90.07 20	87.65 19	90.87 20	87.74 24

PGM-MVS		83.03 7	85.67 25	79.95 5	80.69 16	81.09 15	92.40 10	63.06 6	79.38 58	80.21 9	80.31 88	91.44 46	71.75 12	90.46 15	88.53 15	91.57 9	88.50 20

WR-MVS_H		77.56 42	85.88 21	67.86 61	80.54 17	74.32 52	83.23 51	61.78 12	83.47 22	47.46 151	91.81 5	95.84 7	50.50 129	90.44 16	84.37 33	83.63 66	80.89 59

SteuartSystems-ACMMP		82.16 15	85.55 26	78.21 11	80.48 18	79.28 31	92.65 7	61.03 19	80.55 49	77.00 23	81.80 78	90.71 64	68.73 27	90.25 17	87.94 18	89.36 28	88.30 22
Skip Steuart: Steuart Systems R&D Blog.
XVS					80.47 19	81.29 12	93.33 3			77.45 20		90.19 75				91.52 11

X-MVStestdata					80.47 19	81.29 12	93.33 3			77.45 20		90.19 75				91.52 11

SD-MVS		82.13 17	86.80 8	76.67 20	80.36 21	80.66 22	89.48 27	56.93 34	82.50 31	67.55 68	87.05 18	91.40 49	72.84 7	88.66 28	88.32 16	92.85 2	89.04 11

X-MVS		81.61 21	84.73 34	77.97 12	80.31 22	81.29 12	93.53 2	62.50 10	81.41 40	77.45 20	72.04 138	90.19 75	62.50 53	90.57 13	88.87 13	91.54 10	88.73 15

SMA-MVS		82.15 16	85.93 20	77.74 16	80.13 23	80.25 26	91.01 16	60.61 23	85.54 8	78.61 15	83.21 53	86.96 115	65.95 37	88.10 32	87.59 20	90.11 22	89.83 5

ACMMP		83.17 6	86.75 10	79.01 8	80.11 24	82.01 7	92.29 11	60.35 25	82.20 33	78.32 16	80.59 86	93.14 23	70.67 16	91.30 8	89.36 10	92.30 4	88.62 17
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
ACMM	71.24 7	82.85 9	86.59 11	78.50 10	80.10 25	78.59 32	91.77 12	60.76 22	84.43 14	76.49 25	81.58 80	93.50 18	70.45 20	91.38 7	89.42 9	91.42 16	87.22 28
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HFP-MVS		82.37 11	86.28 14	77.81 15	79.94 26	80.96 18	91.13 15	63.30 4	84.04 18	71.81 39	82.39 65	89.59 83	69.16 24	89.08 26	88.83 14	91.49 13	89.10 10

ACMP	70.35 9	82.17 14	86.45 13	77.18 18	79.33 27	81.00 17	89.27 30	58.63 30	81.35 41	75.46 30	82.97 56	95.08 11	68.90 26	90.49 14	87.43 22	91.48 14	86.84 30
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		81.44 22	85.68 24	76.49 21	79.27 28	78.21 34	89.84 24	58.67 29	85.25 9	76.26 26	85.28 32	92.88 28	66.03 36	87.20 38	85.40 28	88.86 32	85.58 40

APDe-MVS		81.08 25	86.12 17	75.20 28	79.25 29	80.91 19	90.38 22	57.05 33	85.83 7	66.07 84	87.34 16	91.27 53	69.45 21	85.99 44	82.55 45	88.98 31	88.95 13

NCCC		77.82 40	80.72 56	74.43 31	79.24 30	75.72 45	88.06 35	56.36 38	79.61 56	73.22 35	67.75 152	87.05 111	63.09 49	85.62 45	84.00 37	86.62 48	85.30 42

v1.0		73.48 66	71.76 136	75.49 27	79.20 31	79.76 28	89.40 28	58.51 31	81.15 43	69.56 55	85.14 33	88.71 91	68.92 25	85.26 50	82.30 51	87.35 43	0.00 246

ACMMP_Plus		81.79 20	85.72 23	77.21 17	79.15 32	79.68 29	91.62 14	59.66 26	83.55 21	77.74 19	83.72 46	87.34 108	65.36 38	88.61 29	87.56 21	89.73 27	89.58 6

HSP-MVS		79.66 31	84.23 38	74.34 32	78.92 33	81.86 9	90.55 17	60.49 24	80.19 51	69.08 58	85.12 34	90.92 60	62.99 50	81.15 75	78.00 68	83.99 63	92.37 1

LGP-MVS_train		82.91 8	86.50 12	78.72 9	78.72 34	81.03 16	89.78 25	61.16 17	80.15 52	80.44 6	84.83 36	94.19 16	70.52 19	90.70 11	87.19 23	91.71 8	87.37 26

DeepC-MVS	73.80 3	82.34 12	86.87 7	77.06 19	78.62 35	84.34 1	90.30 23	63.54 2	83.10 26	71.30 43	86.91 22	90.54 70	67.12 33	87.81 35	87.05 24	91.46 15	88.37 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ESAPD		81.01 26	85.18 28	76.15 22	78.58 36	80.64 23	89.77 26	57.92 32	81.66 38	73.45 33	86.84 23	89.80 82	69.33 23	85.40 46	82.91 44	87.87 39	89.01 12

CNVR-MVS		77.79 41	81.57 50	73.38 37	78.37 37	75.91 43	87.97 36	55.11 47	79.41 57	70.98 46	74.70 125	86.43 119	61.77 56	85.10 51	83.73 39	86.10 54	85.68 39

TSAR-MVS + ACMM		81.20 24	86.92 6	74.52 30	77.60 38	82.29 5	84.41 47	62.95 8	82.99 27	64.03 92	87.71 13	89.17 86	71.98 11	88.19 31	88.10 17	86.18 52	89.95 4

HQP-MVS		75.81 54	78.91 64	72.18 42	77.41 39	75.38 47	84.75 44	53.35 55	76.12 69	73.32 34	69.48 143	88.07 97	57.76 80	79.42 87	78.44 64	86.48 49	85.50 41

CDPH-MVS		77.22 47	81.05 55	72.75 40	77.29 40	77.46 37	86.36 41	54.02 53	73.00 88	69.75 53	77.78 108	88.90 90	61.31 60	84.09 57	82.54 46	87.79 41	83.57 46

TSAR-MVS + GP.		73.42 67	76.31 76	70.05 52	77.15 41	71.13 69	81.59 63	54.11 52	69.84 122	58.65 107	66.20 165	78.77 158	65.29 40	83.65 59	83.14 42	83.54 68	81.47 56

PMVS	70.37 8	81.82 19	87.08 5	75.68 25	77.06 42	77.23 38	87.77 38	56.25 40	83.33 24	67.18 79	89.48 10	87.94 99	77.70 1	93.02 2	92.57 2	88.13 37	86.00 36
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
AdaColmap		74.73 59	77.57 70	71.40 44	76.90 43	75.76 44	84.54 46	53.08 57	76.20 68	66.64 83	66.06 166	78.16 161	61.32 59	85.37 48	82.20 52	85.95 56	79.27 65

DeepC-MVS_fast	71.40 6	78.48 36	82.92 44	73.31 38	76.44 44	82.23 6	87.59 39	56.56 37	77.79 62	68.91 60	77.00 111	87.32 109	61.90 55	85.40 46	84.37 33	88.46 34	86.33 34
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS		78.32 37	86.09 19	69.25 58	76.22 45	72.33 66	85.71 43	59.02 27	86.66 6	51.41 133	92.91 1	96.76 1	53.09 120	90.21 18	85.30 29	90.05 24	78.46 73

COLMAP_ROB	75.87 2	84.34 2	89.80 2	77.97 12	75.52 46	82.76 4	90.39 21	54.21 51	89.37 2	83.18 2	89.90 8	95.58 10	72.34 10	92.31 4	90.04 5	92.17 5	88.61 18
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
LS3D		79.33 33	84.03 40	73.84 34	75.37 47	78.09 35	83.30 50	52.94 58	84.42 15	76.01 27	84.16 41	87.44 107	65.34 39	86.30 41	82.08 53	90.09 23	85.70 38

TDRefinement		86.29 1	90.77 1	81.06 1	75.10 48	83.76 2	93.79 1	61.08 18	89.57 1	86.19 1	90.06 7	93.01 26	76.72 2	94.71 1	92.72 1	93.47 1	91.56 2

ambc			79.96 59		74.57 49	75.48 46	73.75 122		80.32 50	72.34 38	78.46 102	92.41 31	59.05 74	80.24 85	73.95 92	75.41 141	78.85 69

MVS_0304		73.74 65	77.16 73	69.74 55	74.24 50	73.47 56	84.70 45	49.62 65	62.26 164	67.27 76	75.87 116	87.57 104	57.49 85	81.20 74	79.50 61	85.10 58	80.27 60

DeepPCF-MVS	71.57 5	79.49 32	84.05 39	74.17 33	74.14 51	80.88 20	89.33 29	56.24 41	82.41 32	71.58 41	82.27 66	86.47 118	66.47 35	84.80 52	84.16 36	87.26 44	87.34 27

CLD-MVS		71.24 76	78.12 67	63.20 104	74.03 52	71.60 67	82.82 55	32.91 209	74.23 80	69.32 56	79.65 95	91.54 44	47.02 149	81.22 73	79.01 62	73.09 162	69.63 129
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		66.87 121	68.89 147	64.53 93	73.97 53	61.13 131	78.46 77	61.03 19	56.78 188	53.41 125	66.91 159	70.91 179	43.49 162	76.08 102	76.68 79	76.81 131	73.73 100
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMH+	67.97 10	80.15 29	86.16 15	73.14 39	73.82 54	76.41 41	83.59 49	54.82 49	87.35 5	70.86 47	86.98 21	96.27 4	66.50 34	89.17 25	83.39 40	89.26 29	83.56 47

MCST-MVS		73.84 64	77.44 71	69.63 56	73.75 55	74.73 50	81.38 64	48.58 71	74.77 74	69.16 57	71.97 139	86.20 122	59.50 71	78.51 91	74.06 91	85.42 57	81.85 53

CSCG		76.95 50	82.08 48	70.97 45	73.32 56	78.35 33	81.08 65	47.19 81	83.47 22	69.82 52	80.44 87	87.19 110	64.59 43	81.01 78	77.26 74	89.83 26	86.84 30

OMC-MVS		79.95 30	85.28 27	73.74 36	72.95 57	80.10 27	87.87 37	48.13 76	84.62 12	79.42 13	80.27 89	92.49 30	64.14 44	87.25 37	85.11 31	89.92 25	87.10 29

CANet		71.07 77	75.09 87	66.39 74	72.57 58	71.53 68	82.38 57	47.10 82	59.81 171	59.81 103	74.97 122	84.37 134	54.25 114	79.89 86	77.64 73	82.25 83	77.40 77

TranMVSNet+NR-MVSNet		71.66 71	79.23 63	62.83 112	72.54 59	65.64 85	74.77 107	55.27 45	75.91 70	45.50 162	89.55 9	94.25 15	45.96 154	82.74 66	77.03 76	82.96 75	69.48 133

UniMVSNet_NR-MVSNet		70.82 81	77.44 71	63.11 105	71.75 60	66.02 83	73.93 119	55.00 48	70.90 104	46.77 157	86.68 24	91.54 44	46.91 150	81.07 77	76.32 81	84.28 61	69.54 130

PCF-MVS	65.25 14	73.99 61	76.74 75	70.79 47	71.61 61	75.33 48	83.76 48	50.40 64	74.88 73	74.50 32	67.60 153	85.36 128	58.30 76	78.61 90	74.25 90	86.15 53	81.13 58
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs1		70.58 85	74.72 95	65.75 77	71.33 62	68.44 73	81.94 60	43.71 111	73.30 86	64.64 91	77.09 110	89.14 87	54.94 108	72.66 135	66.50 166	77.91 126	75.92 84

TSAR-MVS + COLMAP		75.85 53	81.06 53	69.77 54	71.15 63	76.90 39	82.93 53	52.43 60	79.25 59	70.13 50	82.78 57	87.00 113	60.02 65	80.30 83	79.61 60	81.95 86	81.61 55

PHI-MVS		75.17 57	78.37 65	71.43 43	71.13 64	72.46 64	82.28 58	50.55 63	73.39 85	79.05 14	73.65 129	87.50 105	61.98 54	81.10 76	78.48 63	83.60 67	81.99 52

DU-MVS		71.03 79	77.92 68	62.98 110	70.81 65	65.48 87	73.93 119	56.76 35	69.95 120	46.77 157	85.70 30	93.49 19	46.91 150	83.47 60	77.82 71	82.72 78	69.54 130

Baseline_NR-MVSNet		68.15 117	75.12 86	60.02 122	70.81 65	55.67 168	75.88 94	53.40 54	71.25 98	43.96 167	85.88 28	92.68 29	45.76 155	83.47 60	68.34 133	70.34 185	68.58 142

CNLPA		76.67 51	81.72 49	70.77 48	70.75 67	76.68 40	86.14 42	46.11 90	81.82 36	74.68 31	76.37 113	86.23 121	62.92 52	85.28 49	83.29 41	84.02 62	82.40 51

EG-PatchMatch MVS		71.50 73	76.82 74	65.30 82	70.74 68	66.50 81	74.23 111	43.25 118	72.02 92	59.11 105	79.85 93	86.88 116	63.95 45	80.29 84	75.25 87	80.51 91	76.98 80

3Dnovator+	72.94 4	78.78 34	83.05 43	73.80 35	70.70 69	81.34 11	88.33 34	56.01 42	81.33 42	72.87 37	78.06 105	81.15 144	63.83 46	87.39 36	85.82 26	91.06 18	86.28 35

MSLP-MVS++		76.66 52	82.32 47	70.06 51	70.51 70	80.27 25	79.77 72	55.58 44	77.79 62	63.09 95	67.25 156	89.50 84	71.01 15	88.10 32	85.74 27	80.39 92	87.56 25

PLC	64.88 15	75.76 55	80.22 58	70.57 50	70.46 71	77.75 36	82.01 59	48.84 70	80.74 48	70.85 48	71.32 140	84.82 131	63.69 47	84.73 53	82.35 49	87.54 42	79.80 63
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UniMVSNet (Re)		71.29 74	78.14 66	63.30 102	70.29 72	66.57 80	75.98 92	54.74 50	70.20 115	46.20 160	85.08 35	93.21 21	48.19 140	82.50 68	78.33 66	84.40 60	71.08 124

Effi-MVS+-dtu		70.10 92	73.76 106	65.82 76	70.23 73	74.92 49	79.47 74	44.49 104	56.98 187	54.34 119	64.26 178	84.78 132	59.97 66	80.96 79	80.38 56	86.44 50	74.05 97

MAR-MVS		70.00 94	72.28 128	67.34 66	69.89 74	72.57 63	80.09 71	49.49 67	60.28 170	69.03 59	59.29 201	80.79 146	54.68 111	78.39 93	76.00 82	80.87 89	78.67 71
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
ACMH	66.19 11	78.12 38	84.55 36	70.63 49	69.62 75	72.40 65	80.77 68	46.43 88	89.24 3	77.99 17	87.42 15	95.83 8	62.95 51	86.27 42	78.24 67	86.00 55	82.46 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
abl_6				65.41 81	69.37 76	74.02 54	82.50 56	47.39 80	66.39 141	56.63 114	60.61 194	82.76 141	53.68 117			82.92 76	78.39 74

FPMVS		70.46 87	74.89 89	65.28 83	69.09 77	61.42 129	77.07 86	46.92 85	76.73 67	53.53 124	67.33 154	75.07 170	67.23 32	83.41 62	81.54 55	77.86 127	78.73 70

IS_MVSNet		68.20 116	74.41 101	60.96 118	68.55 78	64.36 103	71.47 127	48.33 74	70.11 117	43.30 170	80.90 84	74.54 172	47.19 148	81.25 72	77.97 70	86.94 46	71.76 120

MVS_111021_HR		72.37 69	76.12 79	68.00 60	68.55 78	64.30 106	82.93 53	48.98 69	74.25 79	65.39 85	73.59 130	84.11 135	59.48 72	82.61 67	78.38 65	82.66 79	75.59 86

EPP-MVSNet		69.51 99	76.17 77	61.74 117	68.38 80	66.60 79	71.77 125	46.98 83	73.60 84	41.79 173	82.06 72	69.65 187	52.51 123	83.41 62	79.94 59	89.02 30	77.94 75

casdiffmvs		68.96 107	71.83 133	65.61 80	67.84 81	67.61 76	80.93 66	48.34 73	62.61 159	63.42 94	72.75 135	87.50 105	54.35 112	71.06 165	67.00 152	78.77 109	74.30 94

TAPA-MVS	66.11 12	75.37 56	79.24 62	70.86 46	67.63 82	74.09 53	83.17 52	44.75 103	81.82 36	80.83 5	65.61 168	88.04 98	61.58 57	83.21 64	80.12 57	87.17 45	81.82 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_111021_LR		71.60 72	75.21 85	67.38 65	67.42 83	62.44 124	81.73 61	46.24 89	70.89 105	66.80 82	73.19 132	84.98 129	60.09 64	81.94 70	77.77 72	82.00 85	75.29 88

Effi-MVS+		69.04 101	73.01 117	64.40 95	67.20 84	64.83 95	74.87 106	43.97 107	63.33 157	60.90 101	73.06 133	85.79 125	55.61 103	73.58 116	76.41 80	83.84 65	74.09 96

MSDG		68.98 103	73.31 113	63.92 97	67.08 85	68.27 74	75.41 99	40.77 156	67.61 131	64.89 86	75.75 117	78.96 155	53.70 116	76.72 98	73.95 92	81.71 88	71.93 119

v7n		74.47 60	81.06 53	66.77 69	66.98 86	67.10 77	76.76 87	45.88 92	81.98 35	67.43 72	88.38 11	95.67 9	61.38 58	80.76 80	73.49 94	82.21 84	80.06 61

v1240		70.94 80	74.52 98	66.76 70	66.54 87	64.40 100	77.76 81	45.29 95	70.05 118	71.45 42	83.36 52	90.96 58	60.37 62	70.50 170	68.68 124	79.14 102	73.68 101

v1192		71.06 78	74.87 90	66.61 71	66.38 88	65.80 84	78.27 78	45.28 96	70.19 116	70.79 49	83.37 50	91.79 39	58.76 75	70.86 168	69.02 122	80.16 94	73.08 106

v1921920		70.82 81	74.46 100	66.58 72	66.33 89	64.35 105	77.72 82	45.07 98	70.39 109	71.18 44	83.15 54	90.62 67	59.97 66	70.90 166	68.43 132	79.19 101	73.39 103

Anonymous202405211			72.22 129		66.19 90	61.09 133	62.23 171	45.87 93	71.25 98		79.33 100	86.16 124	37.36 179	73.54 118	69.84 118	75.45 140	64.32 158

TinyColmap		71.85 70	76.11 80	66.87 68	66.07 91	65.34 89	74.35 109	49.30 68	79.93 55	75.93 28	75.66 118	87.74 101	54.72 110	80.66 82	70.42 114	80.85 90	73.02 108

gm-plane-assit		56.76 174	57.64 195	55.73 146	66.01 92	55.45 171	74.96 102	30.54 219	73.71 83	56.04 116	81.81 77	30.91 246	43.83 160	58.77 209	54.71 204	63.02 199	48.13 215

v144192		70.68 84	74.40 102	66.34 75	65.94 93	64.38 102	77.63 83	45.18 97	69.97 119	70.11 51	82.70 60	90.77 61	59.84 68	71.43 160	68.46 128	79.31 100	73.08 106

canonicalmvs		66.37 122	74.37 103	57.04 140	65.89 94	65.06 91	62.58 169	42.55 123	76.82 66	46.87 156	67.33 154	86.38 120	45.49 157	76.77 97	71.85 102	78.87 106	76.35 81

v1144		70.45 88	74.50 99	65.73 78	65.74 95	64.88 93	77.33 85	44.16 105	70.59 108	69.63 54	83.15 54	91.42 48	57.79 79	71.29 164	68.53 127	79.72 97	71.63 122

NR-MVSNet		68.66 109	76.15 78	59.93 123	65.49 96	65.48 87	74.42 108	56.76 35	69.95 120	45.38 163	85.70 30	91.13 54	34.68 194	74.52 107	76.75 78	82.83 77	69.49 132

v7		69.81 97	73.94 104	65.00 87	65.33 97	65.07 90	76.60 88	43.66 113	67.36 134	67.25 77	82.76 58	90.57 68	57.70 81	71.69 154	68.63 125	79.44 98	71.52 123

IterMVS-LS		65.76 125	70.85 140	59.81 125	65.33 97	57.78 146	64.63 162	48.02 77	65.65 146	51.05 136	81.31 82	77.47 164	54.94 108	69.46 179	69.36 119	74.90 143	74.95 90
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		70.25 90	74.59 96	65.19 86	65.32 99	66.46 82	76.60 88	44.84 101	67.38 133	67.21 78	82.75 59	90.56 69	57.70 81	71.69 154	68.63 125	79.44 98	74.67 92

FC-MVSNet-train		64.87 132	74.76 94	53.33 153	65.24 100	58.05 144	69.69 137	41.92 137	70.99 103	32.62 197	85.75 29	88.23 94	32.10 214	77.61 95	74.41 89	78.43 113	68.25 144

RPSCF		77.56 42	84.51 37	69.46 57	65.17 101	74.36 51	79.74 73	47.45 79	84.01 19	72.89 36	77.89 106	90.67 65	65.14 41	88.25 30	89.74 7	86.38 51	86.64 32

SixPastTwentyTwo		77.24 46	83.65 42	69.78 53	65.14 102	64.85 94	77.44 84	47.74 78	82.76 29	68.52 61	87.65 14	93.31 20	71.68 13	89.49 24	82.41 48	88.14 36	85.05 43

v11		70.10 92	74.82 91	64.58 91	64.83 103	64.39 101	75.89 93	43.18 120	71.34 97	67.75 65	84.19 40	91.75 40	57.23 87	71.46 159	66.85 157	78.60 112	73.78 99

test20.03		53.49 192	60.95 186	44.78 207	64.73 104	47.25 203	61.58 174	43.30 117	65.86 145	22.85 231	66.87 161	79.85 149	22.99 226	62.38 199	56.95 199	53.25 215	47.46 216

v13		70.58 85	75.49 83	64.87 88	64.66 105	64.58 97	76.18 90	43.69 112	72.34 91	67.65 66	84.36 39	92.01 37	58.05 77	73.57 117	67.06 151	78.96 105	74.48 93

Vis-MVSNet (Re-imp)		60.99 155	67.78 149	53.06 155	64.66 105	53.49 181	67.40 149	49.52 66	68.55 126	28.00 220	79.53 98	71.41 178	33.08 210	75.30 105	71.28 105	75.69 139	54.91 196

v12		70.39 89	75.25 84	64.73 89	64.60 107	64.47 98	76.00 91	43.55 114	71.92 93	67.51 69	84.15 42	91.88 38	57.83 78	73.32 119	67.00 152	78.87 106	74.02 98

V9		70.20 91	75.02 88	64.58 91	64.49 108	64.36 103	75.80 96	43.40 115	71.53 94	67.35 75	83.95 45	91.73 41	57.63 83	73.04 124	66.96 154	78.79 108	73.61 102

V14		69.99 95	74.77 93	64.41 94	64.39 109	64.25 107	75.59 98	43.25 118	71.12 102	67.14 80	83.65 48	91.58 43	57.40 86	72.75 132	66.90 156	78.70 110	73.15 105

v15		69.80 98	74.53 97	64.27 96	64.30 110	64.15 108	75.40 100	43.12 121	70.71 107	66.98 81	83.41 49	91.43 47	57.21 88	72.48 138	66.84 158	78.62 111	72.72 110

TransMVSNet (Re)		63.49 139	73.86 105	51.39 166	64.26 111	56.07 164	61.17 176	42.23 129	78.81 60	34.80 187	85.94 26	90.63 66	34.35 201	72.73 134	67.98 142	71.50 171	64.84 156

v1		68.98 103	73.38 110	63.84 99	64.12 112	62.97 120	74.95 105	41.52 143	70.28 112	67.47 71	82.49 62	91.37 50	56.59 92	71.43 160	66.51 165	78.41 114	68.62 139

v1141		68.97 105	73.38 110	63.83 100	64.11 113	62.97 120	74.96 102	41.52 143	70.29 110	67.36 74	82.47 63	91.37 50	56.59 92	71.43 160	66.49 168	78.41 114	68.61 141

divwei89l23v2f112		68.97 105	73.38 110	63.83 100	64.11 113	62.97 120	74.96 102	41.52 143	70.29 110	67.39 73	82.47 63	91.37 50	56.59 92	71.42 163	66.50 166	78.40 116	68.62 139

v2v482		69.01 102	73.39 109	63.89 98	63.86 115	62.99 119	75.26 101	42.05 133	70.22 114	68.46 62	82.64 61	91.61 42	55.38 104	70.89 167	66.93 155	78.30 117	68.48 143

Fast-Effi-MVS+		67.71 119	72.54 125	62.07 114	63.83 116	63.68 111	75.74 97	39.94 167	60.89 169	54.29 120	73.00 134	86.19 123	56.85 89	78.46 92	73.23 95	81.74 87	72.36 113

Anonymous20240521		64.34 135	72.84 119	54.42 150	63.79 117	62.09 126	62.50 170	42.72 122	74.32 78	41.34 175	66.96 157	88.57 92	39.18 173	75.20 106	70.35 115	77.01 130	72.37 112

v8		68.77 108	73.50 108	63.26 103	63.74 118	64.47 98	74.22 115	42.07 131	67.30 135	64.89 86	82.08 71	90.23 72	56.50 96	71.85 153	66.57 162	78.14 118	72.02 117

v1neww		68.32 113	72.82 120	63.07 107	63.73 119	63.12 116	74.23 111	40.99 150	67.21 136	64.83 89	82.09 69	90.20 73	56.49 98	71.86 150	66.61 159	78.14 118	68.65 137

v7new		68.32 113	72.82 120	63.07 107	63.73 119	63.12 116	74.23 111	40.99 150	67.21 136	64.83 89	82.09 69	90.20 73	56.49 98	71.86 150	66.61 159	78.14 118	68.65 137

v6		68.32 113	72.82 120	63.07 107	63.73 119	63.11 118	74.23 111	40.99 150	67.21 136	64.86 88	82.11 68	90.19 75	56.51 95	71.86 150	66.61 159	78.14 118	68.66 136

Anonymous20231211		63.69 138	72.86 118	53.00 156	63.72 122	60.25 137	60.33 178	40.96 153	72.49 89	38.91 179	81.77 79	88.17 96	37.60 178	73.30 120	68.01 141	76.47 136	66.06 152

v17		68.55 110	73.23 114	63.08 106	63.67 123	63.84 109	74.05 117	42.28 128	66.34 142	63.93 93	81.91 75	89.83 80	56.50 96	71.97 147	66.55 163	78.08 122	72.18 115

Gipuma		73.40 68	79.27 61	66.55 73	63.64 124	59.35 138	70.28 134	45.92 91	83.79 20	71.78 40	84.04 44	93.07 25	68.69 28	87.90 34	76.76 77	78.98 104	69.96 127
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v16		68.33 112	73.03 116	62.86 111	63.57 125	63.83 110	73.98 118	42.30 127	65.58 148	62.94 96	81.82 76	89.37 85	56.36 100	71.91 148	66.52 164	77.99 124	72.17 116

LTVRE_ROB	75.99 1	82.04 18	87.16 4	76.07 23	63.57 125	70.27 71	86.48 40	62.99 7	89.00 4	80.32 7	86.25 25	91.04 56	74.66 4	92.58 3	90.29 4	88.42 35	90.72 3
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
PVSNet_Blended_VisFu		70.70 83	73.62 107	67.28 67	63.53 127	72.96 57	77.97 79	52.10 61	63.65 154	62.66 97	71.14 141	73.46 174	63.55 48	79.35 89	75.34 86	83.90 64	79.43 64

USDC		68.53 111	71.82 134	64.68 90	63.53 127	61.87 127	70.12 135	46.98 83	77.89 61	76.58 24	68.55 147	86.88 116	50.50 129	73.73 113	65.62 173	80.39 92	68.21 145

gg-mvs-nofinetune		56.45 180	61.04 185	51.10 169	63.42 129	49.40 199	53.71 214	52.52 59	74.77 74	46.93 154	77.31 109	53.88 218	26.42 224	62.51 198	57.81 197	63.60 198	51.57 205

v18		67.99 118	72.63 124	62.57 113	63.32 130	63.64 112	73.58 124	42.07 131	64.75 151	62.64 98	81.36 81	89.01 89	56.02 101	71.57 156	66.41 169	77.80 128	71.69 121

conf0.05thres1000		61.96 145	70.38 143	52.13 158	63.31 131	58.12 142	62.09 172	42.45 124	75.50 71	33.07 195	77.89 106	69.72 186	37.32 180	77.88 94	70.72 111	74.55 145	62.82 164

pmmvs-eth3d		65.36 130	70.09 145	59.85 124	63.05 132	53.61 180	74.29 110	46.45 87	68.14 128	51.45 132	78.83 101	85.78 126	49.87 134	70.44 171	70.45 113	74.00 148	63.38 162

tfpn		57.74 170	63.03 178	51.58 165	62.87 133	57.28 151	61.53 175	41.99 134	67.67 130	32.52 198	68.13 150	43.08 239	36.94 182	76.07 103	69.31 120	73.62 150	59.68 174

pmmvs6		64.78 133	75.82 81	51.89 160	62.41 134	57.13 152	60.24 180	45.59 94	82.90 28	34.69 189	84.83 36	93.18 22	36.22 188	76.43 99	71.13 107	72.21 167	65.12 155

DI_MVS_plusplus_trai		63.43 140	67.54 150	58.63 128	62.34 135	58.06 143	65.75 158	42.15 130	63.05 158	53.28 126	75.88 115	75.92 168	50.18 131	68.04 183	64.20 180	78.07 123	67.65 146

CDS-MVSNet		57.90 168	63.57 172	51.28 167	62.30 136	53.17 182	64.70 161	51.61 62	57.41 183	32.75 196	63.73 179	70.53 180	27.12 220	72.49 136	73.02 97	69.22 189	54.68 198
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
diffmvs1		65.64 127	72.40 126	57.76 138	62.01 137	59.11 140	68.90 141	41.83 138	68.05 129	53.87 123	79.46 99	88.52 93	48.19 140	70.08 174	65.99 171	71.76 168	75.58 87

view800		59.22 162	66.23 153	51.03 170	61.99 138	56.71 155	60.53 177	41.20 148	66.26 143	32.46 199	66.68 162	69.93 182	36.77 183	74.52 107	70.00 117	73.24 158	59.56 175

tfpnnormal		61.41 150	71.33 138	49.83 176	61.73 139	54.90 175	58.52 189	41.24 147	75.20 72	32.00 205	82.13 67	87.87 100	35.63 192	72.75 132	66.30 170	69.87 186	60.14 171

OpenMVS	60.79 16	64.42 134	69.72 146	58.23 134	61.63 140	62.17 125	64.11 164	37.54 190	67.17 139	55.71 117	65.89 167	74.89 171	52.67 122	72.20 144	68.29 135	77.73 129	77.39 78

thres600view7		58.87 164	65.91 155	50.66 172	61.27 141	56.32 159	59.88 182	40.63 163	64.88 150	32.10 204	64.82 173	69.83 184	36.72 185	72.99 129	72.55 99	73.34 156	59.97 172

Fast-Effi-MVS+-dtu		63.22 141	65.55 156	60.49 121	61.24 142	64.70 96	74.15 116	53.24 56	51.46 206	49.67 143	58.03 207	78.42 159	48.05 143	72.03 145	71.14 106	76.60 135	63.09 163

tpmp4_e23		55.21 187	55.01 204	55.44 148	61.24 142	53.77 177	69.57 138	43.81 108	55.88 190	51.16 135	60.15 196	45.66 233	44.99 158	59.13 208	53.13 209	61.88 200	57.35 185

view600		58.47 165	65.42 157	50.36 174	61.04 144	55.84 167	59.33 185	40.34 166	64.46 152	32.31 203	64.78 174	69.85 183	36.46 186	72.46 139	71.31 104	72.68 163	59.26 179

diffmvs		64.17 137	70.24 144	57.09 139	61.02 145	57.87 145	67.54 148	41.48 146	59.57 172	54.70 118	75.51 119	88.20 95	46.84 152	69.86 177	65.47 175	70.95 178	75.21 89

pmmvs4		61.12 153	64.61 163	57.04 140	60.88 146	52.15 189	70.59 133	44.82 102	61.35 168	46.91 155	72.08 137	73.27 175	46.79 153	65.06 188	67.76 145	72.28 165	60.58 170

3Dnovator	65.69 13	69.43 100	75.74 82	62.06 115	60.78 147	70.50 70	75.85 95	39.57 170	74.44 76	57.41 110	75.91 114	77.73 163	55.34 105	76.86 96	75.61 85	83.44 69	79.14 67

Vis-MVSNet		69.95 96	77.69 69	60.91 119	60.67 148	66.71 78	77.94 80	48.58 71	69.10 124	45.78 161	80.21 90	83.58 139	53.41 119	82.92 65	80.11 58	79.08 103	81.21 57
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
pm-mvs1		61.97 144	72.01 132	50.25 175	60.64 149	55.23 172	58.67 188	42.44 125	74.40 77	33.63 193	81.03 83	89.86 79	34.87 193	72.93 131	67.95 143	71.28 172	62.65 165

v748		71.27 75	79.41 60	61.76 116	60.62 150	61.73 128	68.46 144	40.71 160	80.76 47	61.02 100	87.12 17	95.00 12	59.62 70	80.67 81	70.67 112	80.14 95	79.93 62

MS-PatchMatch		56.31 182	60.22 191	51.73 163	60.53 151	55.53 170	63.41 166	37.18 191	51.34 208	37.44 180	60.53 195	62.19 206	45.52 156	64.25 193	63.17 186	66.33 194	64.56 157

thres400		57.25 171	63.73 170	49.70 178	60.19 152	54.95 174	58.16 190	39.60 169	62.42 162	31.98 207	62.33 187	69.20 188	35.96 190	70.07 175	68.03 140	72.28 165	59.12 180

CANet_DTU		61.22 152	67.07 152	54.40 151	59.89 153	63.62 113	70.98 130	36.77 194	50.49 212	47.15 152	62.45 186	80.81 145	37.90 177	71.87 149	70.09 116	73.69 149	70.19 126

v148		64.92 131	70.58 142	58.32 132	59.89 153	57.09 153	66.04 154	35.27 198	69.11 123	60.66 102	79.57 96	90.93 59	53.91 115	69.81 178	62.22 188	74.14 146	65.31 154

DELS-MVS		65.54 129	71.79 135	58.24 133	59.68 155	65.55 86	70.99 129	38.69 179	62.29 163	49.27 145	75.03 121	81.42 143	50.93 126	73.71 115	71.35 103	79.90 96	73.20 104
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
QAPM		66.36 123	72.76 123	58.90 127	59.57 156	65.01 92	64.05 165	41.17 149	73.09 87	56.82 112	69.42 144	77.78 162	55.07 107	73.00 128	72.07 101	76.71 132	78.96 68

tfpn_n400		57.07 172	64.44 165	48.48 191	59.55 157	52.25 186	57.99 197	38.85 172	71.25 98	29.07 216	65.20 170	63.07 202	34.41 198	73.99 109	67.52 147	70.99 176	57.83 182

tfpnconf		57.07 172	64.44 165	48.48 191	59.55 157	52.25 186	57.99 197	38.85 172	71.25 98	29.07 216	65.20 170	63.07 202	34.41 198	73.99 109	67.52 147	70.99 176	57.83 182

MVS_Test		62.58 142	67.46 151	56.89 142	59.52 159	55.90 166	64.94 160	38.83 175	57.08 186	56.55 115	76.53 112	84.49 133	47.45 144	66.95 185	62.01 189	74.04 147	69.27 134

tfpnview11		56.69 176	63.86 168	48.33 194	59.46 160	52.35 185	57.85 199	38.80 177	68.21 127	29.07 216	65.20 170	63.07 202	34.36 200	73.21 121	68.72 123	70.44 181	56.28 191

test-LLR		46.01 214	45.06 234	47.11 200	59.39 161	36.72 228	51.28 222	40.95 154	36.41 242	34.45 190	46.14 234	47.02 228	38.00 175	51.78 229	48.53 220	58.60 204	48.84 211

test0.0.03 1		45.40 216	49.55 221	40.57 216	59.39 161	44.36 211	53.37 216	40.95 154	47.14 225	19.23 237	45.49 236	60.24 212	19.24 230	54.82 222	51.98 211	51.21 220	42.82 223

GA-MVS		60.73 157	64.24 167	56.64 144	59.38 163	57.45 150	65.07 159	36.65 195	57.39 184	58.17 108	73.43 131	69.10 190	47.38 145	64.47 192	63.63 184	73.19 160	64.22 159

PatchMatch-RL		60.96 156	63.00 179	58.57 130	59.16 164	52.18 188	67.38 150	41.99 134	57.85 181	48.16 147	53.55 221	69.77 185	59.47 73	73.73 113	72.49 100	75.27 142	61.44 168

PM-MVS		65.66 126	71.25 139	59.14 126	58.92 165	54.88 176	73.66 123	38.55 180	66.12 144	49.91 142	69.87 142	86.97 114	60.61 61	76.30 100	74.75 88	73.19 160	69.83 128

thres200		56.35 181	62.36 180	49.34 180	58.87 166	56.32 159	55.91 204	40.63 163	58.51 174	31.34 208	58.81 205	67.31 192	35.96 190	72.99 129	65.51 174	73.34 156	57.07 187

tfpn111		55.56 186	60.91 187	49.32 182	58.57 167	56.49 156	58.01 192	40.73 157	53.23 197	30.91 211	49.82 227	66.40 197	34.18 202	73.03 125	68.06 136	73.54 151	59.36 176

conf200view11		56.07 184	61.85 182	49.32 182	58.57 167	56.49 156	58.01 192	40.73 157	53.23 197	30.91 211	56.41 210	66.40 197	34.18 202	73.03 125	68.06 136	73.54 151	59.36 176

thres100view900		53.88 189	59.19 192	47.68 198	58.57 167	52.74 184	54.45 210	38.07 183	53.23 197	31.01 209	56.41 210	66.40 197	32.80 211	65.03 189	64.43 179	71.18 175	56.10 192

tfpn200view9		56.07 184	61.85 182	49.34 180	58.57 167	56.48 158	58.01 192	40.72 159	53.23 197	31.01 209	56.41 210	66.40 197	34.18 202	73.02 127	68.06 136	73.53 153	59.35 178

testgi		51.94 197	61.37 184	40.94 214	58.38 171	47.03 205	65.88 155	30.49 221	70.87 106	22.64 232	57.53 209	87.59 103	18.30 232	63.01 195	54.32 206	49.93 222	49.27 209

conf0.01		53.73 191	57.58 196	49.24 185	58.35 172	56.17 161	58.01 192	40.65 161	53.23 197	30.80 214	51.96 223	43.35 238	34.18 202	72.49 136	68.06 136	73.43 154	57.80 184

tfpn1000		56.13 183	63.18 177	47.91 196	58.34 173	53.03 183	58.87 187	38.14 181	65.64 147	27.09 221	65.41 169	59.49 214	33.41 209	73.14 122	69.08 121	71.63 169	56.46 190

conf0.002		52.78 195	55.83 200	49.22 186	58.28 174	56.09 163	58.01 192	40.64 162	53.23 197	30.79 215	50.10 226	36.15 243	34.18 202	72.40 140	65.72 172	73.41 155	57.11 186

FMVSNet1		61.92 146	71.36 137	50.90 171	57.67 175	59.29 139	59.48 184	44.14 106	70.24 113	34.72 188	75.45 120	84.94 130	36.75 184	72.33 141	68.45 129	72.66 164	68.83 135

IB-MVS	57.02 17	61.37 151	65.39 158	56.69 143	56.65 176	60.85 136	70.70 132	37.90 188	49.37 218	45.37 164	48.75 230	79.14 153	53.55 118	76.26 101	70.85 110	75.97 137	72.50 111
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
thresconf0.02		49.98 204	53.83 208	45.48 204	56.47 177	49.38 200	52.01 220	36.49 196	63.51 156	28.04 219	49.82 227	36.72 242	32.63 212	64.84 190	60.66 191	67.22 193	51.91 204

thisisatest0515		66.95 120	72.29 127	60.72 120	56.37 178	56.05 165	71.08 128	38.81 176	67.59 132	53.26 127	78.21 103	79.79 151	60.11 63	75.69 104	73.02 97	84.69 59	75.66 85

PVSNet_BlendedMVS		61.75 147	65.07 161	57.87 136	56.27 179	60.99 134	65.81 156	43.75 109	51.27 209	54.08 121	62.12 188	78.84 156	50.67 127	71.49 157	63.91 182	76.64 133	66.86 147

PVSNet_Blended		61.75 147	65.07 161	57.87 136	56.27 179	60.99 134	65.81 156	43.75 109	51.27 209	54.08 121	62.12 188	78.84 156	50.67 127	71.49 157	63.91 182	76.64 133	66.86 147

GBi-Net		56.54 178	63.26 175	48.70 189	55.88 181	57.61 147	57.26 200	41.75 139	49.06 219	32.37 200	61.81 190	67.02 193	34.58 195	72.33 141	68.45 129	70.38 182	66.56 149

test1		56.54 178	63.26 175	48.70 189	55.88 181	57.61 147	57.26 200	41.75 139	49.06 219	32.37 200	61.81 190	67.02 193	34.58 195	72.33 141	68.45 129	70.38 182	66.56 149

FMVSNet2		57.80 169	65.39 158	48.94 188	55.88 181	57.61 147	57.26 200	42.37 126	58.21 176	33.19 194	68.36 149	75.55 169	34.58 195	66.91 186	64.55 178	70.38 182	66.56 149

tpm cat1		50.98 199	51.28 214	50.62 173	55.74 184	49.92 198	63.13 167	38.12 182	52.38 205	47.61 150	60.11 197	44.51 235	44.86 159	51.31 231	47.49 224	54.25 214	53.24 200

new-patchmatchnet		47.33 210	60.49 190	31.99 232	55.69 185	33.86 234	36.84 244	33.31 208	72.36 90	14.33 243	80.09 91	92.14 34	13.27 240	63.54 194	40.09 234	38.51 236	41.32 227

EPNet_dtu		56.63 177	60.77 188	51.80 161	55.47 186	44.63 209	69.83 136	38.74 178	50.27 213	47.64 149	58.01 208	72.27 176	33.71 207	68.60 182	67.72 146	65.39 195	63.86 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		50.28 203	57.94 194	41.35 213	55.45 187	43.65 213	58.06 191	34.12 203	62.02 166	24.25 229	59.33 200	79.80 150	24.49 225	59.55 202	54.28 207	51.74 218	46.94 218

tttt0517		61.44 149	63.85 169	58.62 129	55.20 188	55.61 169	68.80 142	38.02 184	55.70 191	50.01 141	66.93 158	48.90 222	56.69 90	73.84 112	71.10 108	82.99 74	74.89 91

V4		73.95 62	81.44 51	65.22 84	54.86 189	63.31 115	78.89 76	38.00 186	80.03 53	68.29 64	87.02 19	95.00 12	68.15 30	84.11 55	75.62 84	83.12 71	84.95 45

v52		73.95 62	81.43 52	65.22 84	54.85 190	63.32 114	78.90 75	38.00 186	80.00 54	68.32 63	87.02 19	94.98 14	68.14 31	84.11 55	75.63 83	83.12 71	84.96 44

CVMVSNet		60.45 158	63.72 171	56.63 145	54.82 191	53.75 178	68.41 145	41.95 136	55.07 194	48.03 148	58.08 206	68.67 191	55.09 106	69.14 181	68.34 133	71.51 170	72.97 109

thisisatest0530		61.02 154	63.44 174	58.19 135	54.75 192	55.09 173	68.03 147	38.02 184	55.45 193	49.06 146	66.58 163	48.69 223	56.69 90	73.07 123	71.10 108	82.60 80	74.14 95

FC-MVSNet-test		60.28 159	70.83 141	47.96 195	54.69 193	47.12 204	68.06 146	41.68 142	71.42 95	23.73 230	84.70 38	77.41 165	28.92 217	82.33 69	73.08 96	70.68 180	59.77 173

UGNet		65.61 128	74.79 92	54.91 149	54.54 194	68.20 75	70.97 131	48.21 75	67.14 140	41.67 174	74.15 126	80.65 147	36.10 189	79.39 88	77.99 69	77.95 125	76.01 82
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
FMVSNet3		54.77 188	60.73 189	47.81 197	54.29 195	56.88 154	55.89 205	41.75 139	49.06 219	32.37 200	61.81 190	67.02 193	33.67 208	62.88 196	61.96 190	68.88 190	65.53 153

tfpn_ndepth		51.52 198	57.21 197	44.88 205	54.05 196	52.14 190	53.58 215	37.07 192	55.55 192	24.73 226	47.12 232	56.92 216	28.92 217	69.22 180	64.80 176	70.94 179	54.74 197

our_test_3					52.72 197	53.66 179	69.11 140

CostFormer		52.59 196	55.14 203	49.61 179	52.72 197	50.40 194	66.28 153	33.78 205	52.85 203	43.43 168	66.30 164	51.37 220	41.78 169	54.92 221	51.18 214	59.68 203	58.98 181

HyFIR lowres test		59.15 163	62.28 181	55.49 147	52.42 199	62.59 123	71.76 126	39.74 168	50.25 214	41.92 172	62.88 183	69.16 189	55.85 102	62.77 197	67.18 150	71.27 173	61.11 169

dps		49.71 205	51.97 212	47.07 201	52.37 200	47.00 206	53.02 218	40.52 165	44.91 232	41.23 176	64.55 176	44.27 236	40.12 172	57.71 215	51.97 212	55.14 213	53.41 199

V42		65.79 124	72.11 131	58.42 131	51.89 201	58.69 141	73.80 121	34.50 199	65.40 149	57.10 111	79.54 97	89.09 88	57.51 84	71.98 146	67.83 144	75.70 138	72.26 114

DWT-MVSNet_training		48.57 209	47.93 226	49.31 184	51.79 202	48.05 202	61.84 173	34.33 202	41.94 235	43.42 169	50.35 224	34.74 245	47.30 146	52.62 228	52.08 210	57.20 209	55.74 193

CR-MVSNet		53.82 190	55.40 202	51.98 159	51.57 203	50.23 195	45.00 235	44.97 99	46.90 226	52.60 129	67.91 151	46.99 230	48.37 138	59.15 206	59.53 194	69.38 188	57.07 187

IterMVS		59.24 161	64.45 164	53.16 154	50.98 204	61.29 130	66.51 152	32.85 210	58.17 177	46.31 159	72.58 136	70.23 181	54.26 113	64.81 191	60.24 192	68.04 192	63.81 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1111		39.71 232	44.86 237	33.71 230	50.45 205	28.51 241	55.07 208	34.43 200	62.60 160	17.59 239	62.60 184	28.17 247	14.69 237	54.19 224	41.91 231	30.02 241	36.03 233

.test1245		31.52 240	33.91 242	28.73 235	50.45 205	28.51 241	55.07 208	34.43 200	62.60 160	17.59 239	62.60 184	28.17 247	14.69 237	54.19 224	0.54 244	0.15 248	0.77 244

RPMNet		50.92 200	50.32 217	51.62 164	50.25 207	50.23 195	59.16 186	46.70 86	46.90 226	42.39 171	48.97 229	37.23 240	41.78 169	57.30 217	56.18 201	69.44 187	55.43 194

MDTV_nov1_ep13_2view		58.09 167	63.54 173	51.74 162	50.13 208	46.56 208	66.95 151	33.41 207	63.52 155	58.77 106	74.84 123	84.10 136	43.12 163	65.95 187	54.69 205	58.04 207	55.13 195

tpm		46.67 211	49.20 223	43.72 208	49.60 209	36.60 230	53.93 213	26.84 224	52.70 204	58.05 109	69.04 145	47.96 226	30.06 216	48.33 235	42.76 229	43.88 230	47.01 217

TAMVS		46.64 212	53.62 209	38.49 219	49.56 210	36.87 227	53.16 217	25.76 226	56.33 189	22.55 234	60.72 193	61.80 208	27.12 220	59.50 203	58.33 196	52.79 216	41.82 226

PatchmatchNet		48.67 208	50.10 218	46.99 203	48.29 211	41.00 217	55.54 206	38.94 171	51.38 207	45.15 165	63.22 181	48.45 225	42.83 164	53.80 227	48.50 222	51.19 221	44.37 220
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	45.32 18	58.10 166	65.24 160	49.76 177	47.88 212	46.86 207	48.16 232	32.82 211	58.06 178	61.35 99	59.64 199	80.00 148	47.27 147	70.15 173	64.10 181	61.08 201	77.85 76
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		59.77 160	66.07 154	52.42 157	47.81 213	51.86 191	62.98 168	32.28 214	62.08 165	47.10 153	59.94 198	83.42 140	53.08 121	70.06 176	63.19 185	71.26 174	71.96 118

CHOSEN 1792x2688		52.99 194	56.91 198	48.42 193	47.32 214	50.10 197	64.18 163	33.85 204	45.46 231	36.95 182	55.20 216	66.49 196	51.20 125	59.28 204	59.81 193	57.01 210	61.99 167

MVSTER		53.08 193	56.39 199	49.21 187	47.19 215	51.08 192	60.14 181	31.74 216	40.63 237	38.97 178	55.78 213	46.74 231	42.47 166	67.29 184	62.99 187	74.73 144	70.23 125

tpmrst		43.31 224	46.14 230	40.02 218	47.05 216	36.48 231	48.01 233	32.17 215	49.50 217	37.26 181	63.66 180	47.04 227	31.98 215	42.00 242	40.55 233	43.64 231	43.75 222

pmmvs5		50.64 201	58.01 193	42.05 211	47.01 217	43.67 212	49.27 228	29.43 222	50.77 211	33.83 192	68.69 146	76.16 167	27.82 219	57.53 216	57.07 198	64.95 196	52.18 202

MIMVSNet1		56.72 175	68.69 148	42.76 210	46.70 218	42.81 214	69.13 139	30.52 220	81.01 44	32.00 205	74.82 124	91.10 55	26.83 222	73.98 111	64.72 177	51.40 219	52.38 201

MDTV_nov1_ep13		49.60 206	51.57 213	47.31 199	46.28 219	44.61 210	59.82 183	30.96 217	48.80 223	50.20 139	59.26 202	52.38 219	38.56 174	56.20 219	49.70 219	58.04 207	50.01 207

testpf		41.44 227	38.52 241	44.85 206	46.17 220	38.68 223	60.29 179	43.31 116	24.28 244	35.09 186	39.52 240	34.84 244	32.39 213	43.79 241	39.89 235	51.88 217	48.65 213

E-PMN		43.83 223	49.81 220	36.84 223	46.09 221	31.86 238	42.77 239	25.85 225	57.76 182	25.53 223	55.50 214	62.47 205	43.77 161	70.78 169	39.51 236	37.04 237	30.79 238

anonymousdsp		74.76 58	82.59 45	65.63 79	45.61 222	61.13 131	89.06 31	32.58 212	74.11 81	59.55 104	84.06 43	94.12 17	75.24 3	88.94 27	86.95 25	91.74 7	88.81 14

EMVS		43.85 222	49.91 219	36.77 224	45.46 223	32.70 236	44.09 237	25.33 227	57.88 180	26.62 222	58.99 204	61.14 210	42.77 165	70.26 172	38.52 239	36.38 238	29.87 239

MIMVSNet		45.83 215	53.46 211	36.94 222	45.38 224	39.50 220	52.20 219	30.68 218	57.09 185	24.53 228	55.22 215	71.54 177	21.74 228	55.81 220	51.08 215	47.11 226	43.96 221

N_pmnet		39.50 234	51.01 215	26.09 238	44.48 225	25.59 244	40.20 242	21.49 233	64.20 153	7.98 246	73.86 128	76.67 166	13.66 239	50.17 233	36.69 241	28.71 242	29.86 240

EPMVS		40.11 230	44.96 236	34.44 226	41.55 226	32.65 237	41.74 240	32.39 213	49.89 216	24.83 225	64.44 177	46.38 232	26.57 223	44.75 239	39.47 237	39.59 234	37.16 232

test1235678		44.92 218	54.19 205	34.11 227	41.53 227	37.95 224	54.27 211	23.09 230	53.64 195	22.14 235	53.92 218	84.05 137	16.41 235	60.66 200	50.30 217	47.20 224	38.84 230

testmv		44.91 219	54.17 206	34.11 227	41.52 228	37.93 225	54.27 211	23.09 230	53.61 196	22.14 235	53.89 219	84.00 138	16.41 235	60.64 201	50.29 218	47.20 224	38.83 231

MVS-HIRNet		44.56 220	45.52 232	43.44 209	40.98 229	31.03 239	39.52 243	36.96 193	42.80 234	44.37 166	53.80 220	60.04 213	41.85 168	47.97 237	41.08 232	56.99 211	41.95 225

ADS-MVSNet		40.61 228	46.31 228	33.96 229	40.70 230	30.42 240	40.42 241	33.44 206	58.01 179	30.87 213	63.05 182	54.48 217	22.67 227	44.35 240	39.23 238	35.64 239	34.64 234

FMVSNet5		39.83 231	45.08 233	33.71 230	39.24 231	39.56 219	48.77 230	23.55 229	39.45 238	24.55 227	33.73 242	44.57 234	20.97 229	58.27 213	54.23 208	45.16 227	45.77 219

test2356		35.97 235	39.61 240	31.71 233	38.85 232	34.29 233	45.78 234	22.27 232	38.89 241	22.59 233	37.67 241	37.07 241	16.57 234	50.72 232	45.45 226	44.20 228	33.19 235

new_pmnet		35.76 237	45.64 231	24.22 239	38.59 233	25.83 243	31.87 246	19.24 236	49.06 219	9.01 245	54.34 217	64.73 201	12.46 242	49.21 234	44.91 227	34.17 240	31.41 237

no-one		64.33 136	73.23 114	53.94 152	38.32 234	50.78 193	56.78 203	27.44 223	61.95 167	56.77 113	64.60 175	93.12 24	71.12 14	81.91 71	77.19 75	73.20 159	83.04 48

LP		49.44 207	55.77 201	42.05 211	38.31 235	42.61 215	51.74 221	36.31 197	58.35 175	40.36 177	68.52 148	60.77 211	37.08 181	58.27 213	51.76 213	48.51 223	50.13 206

testus		41.61 226	50.54 216	31.20 234	38.11 236	38.92 222	49.10 229	17.60 237	48.25 224	25.05 224	41.45 238	79.34 152	13.18 241	58.28 212	47.10 225	44.17 229	40.41 228

PatchT		50.55 202	53.55 210	47.05 202	37.59 237	42.26 216	50.55 225	37.56 189	46.37 228	52.60 129	66.91 159	43.54 237	48.37 138	59.15 206	59.53 194	55.62 212	57.07 187

MDA-MVSNet-bldmvs		62.46 143	72.13 130	51.19 168	34.32 238	56.10 162	68.65 143	38.85 172	69.05 125	49.50 144	78.17 104	85.43 127	51.32 124	86.67 39	67.40 149	64.46 197	62.08 166

test-mter		44.18 221	47.60 227	40.18 217	33.20 239	39.03 221	55.28 207	13.91 242	39.07 240	36.63 183	48.09 231	49.52 221	41.12 171	54.55 223	50.91 216	60.97 202	52.03 203

test12356		39.53 233	49.18 224	28.26 236	32.93 240	33.64 235	48.68 231	15.96 239	46.26 230	16.21 241	46.46 233	79.07 154	17.13 233	58.60 210	48.30 223	38.67 235	31.96 236

CHOSEN 280x420		40.24 229	44.14 238	35.69 225	32.36 241	23.58 245	50.30 226	21.21 234	40.94 236	18.84 238	32.75 243	48.65 224	48.13 142	59.16 205	55.31 203	43.28 232	48.62 214

TESTMET0.1,1		41.79 225	45.06 234	37.97 220	31.32 242	36.72 228	51.28 222	14.17 241	36.41 242	34.45 190	46.14 234	47.02 228	38.00 175	51.78 229	48.53 220	58.60 204	48.84 211

pmmvs3		46.64 212	54.13 207	37.90 221	31.23 243	40.68 218	49.83 227	15.34 240	46.31 229	36.34 184	53.15 222	74.40 173	36.36 187	58.43 211	56.64 200	58.32 206	49.29 208

PMMVS		45.37 217	49.29 222	40.79 215	27.75 244	35.07 232	50.88 224	19.88 235	39.27 239	35.78 185	50.11 225	61.29 209	42.04 167	54.13 226	55.95 202	68.43 191	49.19 210

PMMVS2		34.11 238	48.55 225	17.26 240	25.45 245	20.72 246	35.08 245	16.26 238	58.71 173	4.16 248	59.22 203	78.40 160	3.65 243	57.24 218	38.31 240	18.94 244	27.28 241

MVE	28.01 19	35.86 236	43.56 239	26.88 237	22.33 246	19.75 247	30.85 247	23.88 228	49.90 215	10.48 244	43.64 237	61.87 207	48.99 137	47.26 238	42.15 230	24.76 243	40.37 229
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				7.47 242	8.89 247	3.32 249	4.35 249	1.14 244	15.58 246	15.76 242	8.50 245	5.90 250	2.00 244	20.02 243	21.51 242	12.70 245

test123		0.53 241	0.60 244	0.46 243	0.22 248	0.25 250	0.33 252	0.13 246	0.66 247	1.37 249	1.10 246	0.00 252	0.43 245	0.68 245	0.61 243	0.26 247	0.88 243

testmvs		0.47 242	0.69 243	0.21 244	0.17 249	0.17 251	0.35 251	0.16 245	0.66 247	0.18 251	1.05 247	0.99 251	0.27 246	0.62 246	0.54 244	0.15 248	0.77 244

GG-mvs-BLEND		31.54 239	46.27 229	14.37 241	0.07 250	48.65 201	42.97 238	0.08 247	44.04 233	1.21 250	39.77 239	57.94 215	0.15 247	48.19 236	42.82 228	41.70 233	42.46 224

sosnet-low-res		0.00 243	0.00 245	0.00 245	0.00 251	0.00 252	0.00 253	0.00 248	0.00 249	0.00 252	0.00 248	0.00 252	0.00 248	0.00 247	0.00 246	0.00 250	0.00 246

sosnet		0.00 243	0.00 245	0.00 245	0.00 251	0.00 252	0.00 253	0.00 248	0.00 249	0.00 252	0.00 248	0.00 252	0.00 248	0.00 247	0.00 246	0.00 250	0.00 246

MTAPA										80.26 8		90.53 71

MTMP										82.07 4		91.00 57

Patchmatch-RL test							2.05 250

NP-MVS									71.39 96

Patchmtry						37.73 226	45.00 235	44.97 99		52.60 129

DeepMVS_CX						8.52 248	9.75 248	3.19 243	16.70 245	5.02 247	23.06 244	19.33 249	18.69 231	13.75 244		11.34 246	25.07 242

High-resolution multi-view benchmark