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 40	84.87 1	76.15 41	89.06 30	55.70 42	77.25 66	53.14 122	79.73 94	82.09 136	59.69 67	92.21 5	90.93 3	92.32 3	89.36 7

mPP-MVS					82.97 2							92.12 37

DTE-MVSNet		77.28 45	84.87 32	68.42 58	82.94 3	72.70 60	81.60 60	61.78 12	85.03 11	51.40 128	92.11 4	96.00 6	49.42 129	89.73 23	82.52 46	83.39 68	75.98 83

zzz-MVS		82.61 10	85.04 29	79.79 6	82.59 4	73.90 54	92.42 9	62.39 11	84.54 14	80.21 9	79.86 92	90.74 65	70.63 17	90.01 21	89.71 8	90.48 21	86.49 33

MP-MVS		83.50 5	86.11 19	80.45 3	82.58 5	80.60 23	92.68 5	63.48 3	81.43 39	80.21 9	81.95 74	90.76 64	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 28	67.74 61	82.29 6	72.59 61	80.86 64	61.03 19	84.66 12	50.08 135	92.19 2	96.59 4	49.12 130	89.83 22	82.35 48	83.06 71	77.14 79

HPM-MVS++		80.44 27	82.57 46	77.96 15	81.99 7	72.76 58	90.48 20	61.31 14	80.85 46	77.90 18	81.93 75	87.01 108	68.20 28	84.15 54	85.27 30	87.85 39	86.00 36

CP-MVS		84.06 3	86.79 9	80.86 2	81.81 8	79.66 29	92.67 6	64.48 1	83.13 26	82.32 3	80.89 85	92.97 29	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 62	81.24 9	72.88 57	80.63 66	61.28 15	84.14 18	50.53 131	92.13 3	96.76 2	50.12 126	91.02 9	84.46 32	82.60 77	79.19 66

APD-MVS		80.60 26	84.63 34	75.91 23	81.22 10	81.48 10	90.49 19	58.81 28	77.54 65	67.49 69	85.90 28	89.82 83	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 29	67.65 63	81.16 11	72.72 59	80.54 67	61.18 16	82.09 35	50.41 132	90.81 6	95.89 7	50.03 127	90.86 10	84.30 35	82.56 78	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 17	79.45 13	83.37 52	92.04 38	72.82 8	90.66 12	88.96 12	91.80 6	89.13 9

train_agg		77.83 39	80.47 58	74.77 28	80.92 13	69.60 71	88.87 32	56.32 38	74.03 82	71.03 44	83.67 49	87.68 98	64.75 41	83.70 58	81.85 53	86.71 46	82.73 49

TSAR-MVS + MP.		81.23 23	86.13 17	75.52 25	80.74 14	83.22 3	90.55 17	55.12 45	80.87 45	67.62 66	88.01 13	92.38 34	70.61 18	86.64 40	83.10 43	88.51 33	88.67 15

CPTT-MVS		82.32 14	85.00 31	79.19 7	80.73 15	80.86 21	91.68 13	62.59 9	82.55 31	75.53 29	73.88 123	92.28 35	73.74 5	90.07 20	87.65 20	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 48	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 60	80.54 17	74.32 51	83.23 50	61.78 12	83.47 23	47.46 144	91.81 5	95.84 8	50.50 123	90.44 16	84.37 33	83.63 64	80.89 59

SteuartSystems-ACMMP		82.16 16	85.55 26	78.21 11	80.48 18	79.28 30	92.65 7	61.03 19	80.55 49	77.00 23	81.80 79	90.71 66	68.73 26	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 77				91.52 11

X-MVStestdata					80.47 19	81.29 12	93.33 3			77.45 20		90.19 77				91.52 11

SD-MVS		82.13 17	86.80 8	76.67 20	80.36 21	80.66 22	89.48 26	56.93 33	82.50 32	67.55 67	87.05 20	91.40 51	72.84 7	88.66 28	88.32 16	92.85 2	89.04 11

X-MVS		81.61 21	84.73 33	77.97 13	80.31 22	81.29 12	93.53 2	62.50 10	81.41 40	77.45 20	72.04 133	90.19 77	62.50 52	90.57 13	88.87 13	91.54 10	88.73 14

SMA-MVS		82.46 11	86.30 14	77.99 12	80.13 23	80.41 24	91.20 15	60.85 22	85.43 9	79.65 12	84.19 41	87.27 105	66.00 36	88.65 29	87.80 19	90.12 22	90.34 4

ACMMP		83.17 6	86.75 10	79.01 8	80.11 24	82.01 7	92.29 11	60.35 25	82.20 34	78.32 16	80.59 86	93.14 25	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 31	91.77 12	60.76 23	84.43 15	76.49 25	81.58 80	93.50 19	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 12	86.28 15	77.81 16	79.94 26	80.96 18	91.13 16	63.30 4	84.04 19	71.81 38	82.39 66	89.59 84	69.16 23	89.08 26	88.83 14	91.49 13	89.10 10

ACMP	70.35 9	82.17 15	86.45 13	77.18 18	79.33 27	81.00 17	89.27 29	58.63 30	81.35 41	75.46 30	82.97 57	95.08 12	68.90 25	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 33	89.84 24	58.67 29	85.25 10	76.26 26	85.28 33	92.88 30	66.03 35	87.20 38	85.40 28	88.86 32	85.58 40

APDe-MVS		81.08 25	86.12 18	75.20 27	79.25 29	80.91 19	90.38 22	57.05 32	85.83 8	66.07 83	87.34 18	91.27 55	69.45 21	85.99 44	82.55 44	88.98 31	88.95 12

NCCC		77.82 40	80.72 57	74.43 30	79.24 30	75.72 44	88.06 34	56.36 37	79.61 56	73.22 34	67.75 147	87.05 107	63.09 48	85.62 45	84.00 37	86.62 47	85.30 42

ESAPD		80.30 28	84.42 37	75.49 26	79.20 31	79.76 27	89.40 27	58.51 31	81.15 43	69.56 54	85.14 34	88.71 91	68.92 24	85.26 49	82.30 50	87.35 42	88.64 16

ACMMP_Plus		81.79 20	85.72 23	77.21 17	79.15 32	79.68 28	91.62 14	59.66 26	83.55 22	77.74 19	83.72 48	87.34 103	65.36 37	88.61 30	87.56 21	89.73 27	89.58 6

HSP-MVS		79.66 31	84.23 38	74.34 31	78.92 33	81.86 9	90.55 17	60.49 24	80.19 51	69.08 57	85.12 35	90.92 62	62.99 49	81.15 75	78.00 67	83.99 61	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 37	94.19 17	70.52 19	90.70 11	87.19 23	91.71 8	87.37 26

DeepC-MVS	73.80 3	82.34 13	86.87 7	77.06 19	78.62 35	84.34 1	90.30 23	63.54 2	83.10 27	71.30 42	86.91 24	90.54 72	67.12 32	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
CNVR-MVS		77.79 41	81.57 51	73.38 36	78.37 36	75.91 42	87.97 35	55.11 46	79.41 57	70.98 45	74.70 121	86.43 114	61.77 55	85.10 50	83.73 39	86.10 53	85.68 39

TSAR-MVS + ACMM		81.20 24	86.92 6	74.52 29	77.60 37	82.29 5	84.41 46	62.95 8	82.99 28	64.03 90	87.71 15	89.17 87	71.98 11	88.19 32	88.10 17	86.18 51	89.95 5

HQP-MVS		75.81 54	78.91 66	72.18 41	77.41 38	75.38 46	84.75 43	53.35 54	76.12 70	73.32 33	69.48 138	88.07 93	57.76 78	79.42 88	78.44 63	86.48 48	85.50 41

CDPH-MVS		77.22 47	81.05 56	72.75 39	77.29 39	77.46 36	86.36 40	54.02 52	73.00 87	69.75 52	77.78 105	88.90 90	61.31 59	84.09 57	82.54 45	87.79 40	83.57 46

TSAR-MVS + GP.		73.42 66	76.31 78	70.05 51	77.15 40	71.13 68	81.59 61	54.11 51	69.84 119	58.65 104	66.20 157	78.77 151	65.29 39	83.65 59	83.14 42	83.54 66	81.47 56

PMVS	70.37 8	81.82 19	87.08 5	75.68 24	77.06 41	77.23 37	87.77 37	56.25 39	83.33 25	67.18 78	89.48 10	87.94 95	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 72	71.40 43	76.90 42	75.76 43	84.54 45	53.08 56	76.20 69	66.64 82	66.06 158	78.16 154	61.32 58	85.37 47	82.20 51	85.95 55	79.27 65

DeepC-MVS_fast	71.40 6	78.48 36	82.92 44	73.31 37	76.44 43	82.23 6	87.59 38	56.56 36	77.79 63	68.91 59	77.00 107	87.32 104	61.90 54	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 20	69.25 57	76.22 44	72.33 65	85.71 42	59.02 27	86.66 7	51.41 127	92.91 1	96.76 2	53.09 114	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 13	75.52 45	82.76 4	90.39 21	54.21 50	89.37 3	83.18 2	89.90 8	95.58 11	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 33	75.37 46	78.09 34	83.30 49	52.94 57	84.42 16	76.01 27	84.16 43	87.44 102	65.34 38	86.30 41	82.08 52	90.09 23	85.70 38

TDRefinement		86.29 1	90.77 1	81.06 1	75.10 47	83.76 2	93.79 1	61.08 18	89.57 2	86.19 1	90.06 7	93.01 28	76.72 2	94.71 1	92.72 1	93.47 1	91.56 2

ambc			79.96 60		74.57 48	75.48 45	73.75 119		80.32 50	72.34 37	78.46 100	92.41 33	59.05 72	80.24 86	73.95 93	75.41 134	78.85 69

MVS_0304		73.74 65	77.16 75	69.74 54	74.24 49	73.47 55	84.70 44	49.62 65	62.26 158	67.27 75	75.87 113	87.57 100	57.49 83	81.20 74	79.50 60	85.10 57	80.27 60

DeepPCF-MVS	71.57 5	79.49 32	84.05 39	74.17 32	74.14 50	80.88 20	89.33 28	56.24 40	82.41 33	71.58 40	82.27 67	86.47 113	66.47 34	84.80 51	84.16 36	87.26 43	87.34 27

CLD-MVS		71.24 75	78.12 69	63.20 101	74.03 51	71.60 66	82.82 54	32.91 201	74.23 80	69.32 55	79.65 95	91.54 46	47.02 142	81.22 73	79.01 61	73.09 155	69.63 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		66.87 119	68.89 140	64.53 90	73.97 52	61.13 128	78.46 74	61.03 19	56.78 182	53.41 120	66.91 152	70.91 173	43.49 155	76.08 103	76.68 79	76.81 126	73.73 94
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 16	73.14 38	73.82 53	76.41 40	83.59 48	54.82 48	87.35 6	70.86 46	86.98 23	96.27 5	66.50 33	89.17 25	83.39 40	89.26 29	83.56 47

MCST-MVS		73.84 64	77.44 73	69.63 55	73.75 54	74.73 49	81.38 62	48.58 71	74.77 75	69.16 56	71.97 134	86.20 117	59.50 69	78.51 92	74.06 92	85.42 56	81.85 53

CSCG		76.95 50	82.08 48	70.97 44	73.32 55	78.35 32	81.08 63	47.19 81	83.47 23	69.82 51	80.44 87	87.19 106	64.59 42	81.01 78	77.26 73	89.83 26	86.84 30

OMC-MVS		79.95 30	85.28 27	73.74 35	72.95 56	80.10 26	87.87 36	48.13 75	84.62 13	79.42 14	80.27 89	92.49 32	64.14 43	87.25 37	85.11 31	89.92 25	87.10 29

CANet		71.07 77	75.09 89	66.39 73	72.57 57	71.53 67	82.38 56	47.10 82	59.81 166	59.81 100	74.97 118	84.37 128	54.25 108	79.89 87	77.64 72	82.25 79	77.40 77

TranMVSNet+NR-MVSNet		71.66 70	79.23 65	62.83 109	72.54 58	65.64 82	74.77 104	55.27 44	75.91 71	45.50 155	89.55 9	94.25 16	45.96 146	82.74 66	77.03 75	82.96 72	69.48 127

UniMVSNet_NR-MVSNet		70.82 81	77.44 73	63.11 102	71.75 59	66.02 80	73.93 116	55.00 47	70.90 101	46.77 150	86.68 25	91.54 46	46.91 143	81.07 77	76.32 81	84.28 59	69.54 124

Anonymous20231211		71.23 76	81.58 50	59.15 122	71.63 60	60.40 133	70.12 132	52.15 60	92.79 1	42.31 165	88.89 11	98.03 1	40.61 166	80.86 80	75.96 83	78.08 118	74.11 89

PCF-MVS	65.25 14	73.99 61	76.74 77	70.79 46	71.61 61	75.33 47	83.76 47	50.40 64	74.88 74	74.50 32	67.60 148	85.36 122	58.30 74	78.61 91	74.25 91	86.15 52	81.13 58
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		75.85 53	81.06 54	69.77 53	71.15 62	76.90 38	82.93 52	52.43 59	79.25 59	70.13 49	82.78 58	87.00 109	60.02 63	80.30 84	79.61 59	81.95 83	81.61 55

PHI-MVS		75.17 57	78.37 67	71.43 42	71.13 63	72.46 63	82.28 57	50.55 63	73.39 85	79.05 15	73.65 125	87.50 101	61.98 53	81.10 76	78.48 62	83.60 65	81.99 52

DU-MVS		71.03 79	77.92 70	62.98 107	70.81 64	65.48 84	73.93 116	56.76 34	69.95 117	46.77 150	85.70 31	93.49 20	46.91 143	83.47 60	77.82 70	82.72 75	69.54 124

Baseline_NR-MVSNet		68.15 116	75.12 88	60.02 118	70.81 64	55.67 161	75.88 91	53.40 53	71.25 96	43.96 160	85.88 29	92.68 31	45.76 147	83.47 60	68.34 129	70.34 176	68.58 136

CNLPA		76.67 51	81.72 49	70.77 47	70.75 66	76.68 39	86.14 41	46.11 90	81.82 37	74.68 31	76.37 110	86.23 116	62.92 51	85.28 48	83.29 41	84.02 60	82.40 51

EG-PatchMatch MVS		71.50 72	76.82 76	65.30 79	70.74 67	66.50 78	74.23 108	43.25 116	72.02 90	59.11 102	79.85 93	86.88 111	63.95 44	80.29 85	75.25 88	80.51 88	76.98 80

3Dnovator+	72.94 4	78.78 34	83.05 43	73.80 34	70.70 68	81.34 11	88.33 33	56.01 41	81.33 42	72.87 36	78.06 102	81.15 138	63.83 45	87.39 36	85.82 26	91.06 18	86.28 35

MSLP-MVS++		76.66 52	82.32 47	70.06 50	70.51 69	80.27 25	79.77 69	55.58 43	77.79 63	63.09 92	67.25 151	89.50 85	71.01 15	88.10 33	85.74 27	80.39 89	87.56 25

PLC	64.88 15	75.76 55	80.22 59	70.57 49	70.46 70	77.75 35	82.01 58	48.84 70	80.74 48	70.85 47	71.32 135	84.82 125	63.69 46	84.73 52	82.35 48	87.54 41	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 73	78.14 68	63.30 99	70.29 71	66.57 77	75.98 89	54.74 49	70.20 112	46.20 153	85.08 36	93.21 23	48.19 134	82.50 68	78.33 65	84.40 58	71.08 118

Effi-MVS+-dtu		70.10 91	73.76 107	65.82 75	70.23 72	74.92 48	79.47 71	44.49 103	56.98 181	54.34 115	64.26 170	84.78 126	59.97 64	80.96 79	80.38 55	86.44 49	74.05 91

MAR-MVS		70.00 94	72.28 125	67.34 65	69.89 73	72.57 62	80.09 68	49.49 67	60.28 164	69.03 58	59.29 193	80.79 140	54.68 106	78.39 94	76.00 82	80.87 86	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
Anonymous20240521		70.04 93	79.64 61	58.85 125	69.78 74	63.63 110	73.45 122	47.28 80	78.93 60	38.57 172	87.92 14	93.42 21	41.94 161	84.46 53	76.82 76	82.12 81	72.28 107

ACMH	66.19 11	78.12 38	84.55 35	70.63 48	69.62 75	72.40 64	80.77 65	46.43 88	89.24 4	77.99 17	87.42 17	95.83 9	62.95 50	86.27 42	78.24 66	86.00 54	82.46 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
abl_6				65.41 78	69.37 76	74.02 53	82.50 55	47.39 79	66.39 136	56.63 111	60.61 186	82.76 135	53.68 111			82.92 73	78.39 74

FPMVS		70.46 86	74.89 91	65.28 80	69.09 77	61.42 126	77.07 83	46.92 85	76.73 68	53.53 119	67.33 149	75.07 163	67.23 31	83.41 62	81.54 54	77.86 123	78.73 70

IS_MVSNet		68.20 115	74.41 102	60.96 115	68.55 78	64.36 100	71.47 125	48.33 73	70.11 114	43.30 163	80.90 84	74.54 166	47.19 141	81.25 72	77.97 69	86.94 45	71.76 114

MVS_111021_HR		72.37 68	76.12 81	68.00 59	68.55 78	64.30 103	82.93 52	48.98 69	74.25 79	65.39 84	73.59 126	84.11 129	59.48 70	82.61 67	78.38 64	82.66 76	75.59 84

EPP-MVSNet		69.51 99	76.17 79	61.74 114	68.38 80	66.60 76	71.77 123	46.98 83	73.60 84	41.79 167	82.06 73	69.65 181	52.51 117	83.41 62	79.94 58	89.02 30	77.94 75

TAPA-MVS	66.11 12	75.37 56	79.24 64	70.86 45	67.63 81	74.09 52	83.17 51	44.75 102	81.82 37	80.83 5	65.61 160	88.04 94	61.58 56	83.21 64	80.12 56	87.17 44	81.82 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_111021_LR		71.60 71	75.21 87	67.38 64	67.42 82	62.44 122	81.73 59	46.24 89	70.89 102	66.80 81	73.19 128	84.98 123	60.09 62	81.94 70	77.77 71	82.00 82	75.29 85

Effi-MVS+		69.04 101	73.01 118	64.40 92	67.20 83	64.83 92	74.87 103	43.97 106	63.33 152	60.90 98	73.06 129	85.79 119	55.61 99	73.58 114	76.41 80	83.84 63	74.09 90

MSDG		68.98 103	73.31 114	63.92 94	67.08 84	68.27 72	75.41 96	40.77 150	67.61 127	64.89 85	75.75 114	78.96 148	53.70 110	76.72 99	73.95 93	81.71 85	71.93 113

v7n		74.47 60	81.06 54	66.77 68	66.98 85	67.10 74	76.76 84	45.88 92	81.98 36	67.43 71	88.38 12	95.67 10	61.38 57	80.76 81	73.49 95	82.21 80	80.06 61

v1240		70.94 80	74.52 99	66.76 69	66.54 86	64.40 97	77.76 78	45.29 94	70.05 115	71.45 41	83.36 54	90.96 60	60.37 61	70.50 163	68.68 120	79.14 99	73.68 95

v1192		71.06 78	74.87 92	66.61 70	66.38 87	65.80 81	78.27 75	45.28 95	70.19 113	70.79 48	83.37 52	91.79 41	58.76 73	70.86 161	69.02 118	80.16 91	73.08 100

v1921920		70.82 81	74.46 101	66.58 71	66.33 88	64.35 102	77.72 79	45.07 97	70.39 106	71.18 43	83.15 55	90.62 69	59.97 64	70.90 159	68.43 128	79.19 98	73.39 97

TinyColmap		71.85 69	76.11 82	66.87 67	66.07 89	65.34 86	74.35 106	49.30 68	79.93 55	75.93 28	75.66 115	87.74 97	54.72 105	80.66 83	70.42 112	80.85 87	73.02 102

gm-plane-assit		56.76 167	57.64 187	55.73 140	66.01 90	55.45 163	74.96 99	30.54 211	73.71 83	56.04 113	81.81 78	30.91 238	43.83 153	58.77 201	54.71 196	63.02 191	48.13 208

v144192		70.68 84	74.40 103	66.34 74	65.94 91	64.38 99	77.63 80	45.18 96	69.97 116	70.11 50	82.70 61	90.77 63	59.84 66	71.43 154	68.46 124	79.31 97	73.08 100

canonicalmvs		66.37 120	74.37 104	57.04 134	65.89 92	65.06 88	62.58 164	42.55 120	76.82 67	46.87 149	67.33 149	86.38 115	45.49 149	76.77 98	71.85 102	78.87 103	76.35 81

v1144		70.45 87	74.50 100	65.73 76	65.74 93	64.88 90	77.33 82	44.16 104	70.59 105	69.63 53	83.15 55	91.42 50	57.79 77	71.29 158	68.53 123	79.72 94	71.63 116

NR-MVSNet		68.66 108	76.15 80	59.93 119	65.49 94	65.48 84	74.42 105	56.76 34	69.95 117	45.38 156	85.70 31	91.13 56	34.68 186	74.52 106	76.75 78	82.83 74	69.49 126

v7		69.81 97	73.94 105	65.00 84	65.33 95	65.07 87	76.60 85	43.66 111	67.36 129	67.25 76	82.76 59	90.57 70	57.70 79	71.69 148	68.63 121	79.44 95	71.52 117

IterMVS-LS		65.76 123	70.85 134	59.81 121	65.33 95	57.78 140	64.63 157	48.02 76	65.65 141	51.05 130	81.31 82	77.47 157	54.94 104	69.46 170	69.36 115	74.90 136	74.95 86
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v10		70.25 89	74.59 97	65.19 83	65.32 97	66.46 79	76.60 85	44.84 100	67.38 128	67.21 77	82.75 60	90.56 71	57.70 79	71.69 148	68.63 121	79.44 95	74.67 87

FC-MVSNet-train		64.87 129	74.76 96	53.33 146	65.24 98	58.05 139	69.69 135	41.92 134	70.99 100	32.62 190	85.75 30	88.23 92	32.10 206	77.61 96	74.41 90	78.43 109	68.25 138

RPSCF		77.56 42	84.51 36	69.46 56	65.17 99	74.36 50	79.74 70	47.45 78	84.01 20	72.89 35	77.89 103	90.67 67	65.14 40	88.25 31	89.74 7	86.38 50	86.64 32

SixPastTwentyTwo		77.24 46	83.65 42	69.78 52	65.14 100	64.85 91	77.44 81	47.74 77	82.76 30	68.52 60	87.65 16	93.31 22	71.68 13	89.49 24	82.41 47	88.14 36	85.05 43

v11		70.10 91	74.82 93	64.58 88	64.83 101	64.39 98	75.89 90	43.18 118	71.34 95	67.75 64	84.19 41	91.75 42	57.23 85	71.46 153	66.85 151	78.60 108	73.78 93

test20.03		53.49 185	60.95 178	44.78 200	64.73 102	47.25 195	61.58 167	43.30 115	65.86 140	22.85 224	66.87 154	79.85 143	22.99 218	62.38 191	56.95 191	53.25 207	47.46 209

v13		70.58 85	75.49 85	64.87 85	64.66 103	64.58 94	76.18 87	43.69 110	72.34 89	67.65 65	84.36 40	92.01 39	58.05 75	73.57 115	67.06 146	78.96 102	74.48 88

Vis-MVSNet (Re-imp)		60.99 147	67.78 142	53.06 148	64.66 103	53.49 172	67.40 143	49.52 66	68.55 123	28.00 213	79.53 98	71.41 172	33.08 202	75.30 105	71.28 105	75.69 133	54.91 189

v12		70.39 88	75.25 86	64.73 86	64.60 105	64.47 95	76.00 88	43.55 112	71.92 91	67.51 68	84.15 44	91.88 40	57.83 76	73.32 116	67.00 147	78.87 103	74.02 92

V9		70.20 90	75.02 90	64.58 88	64.49 106	64.36 100	75.80 93	43.40 113	71.53 92	67.35 74	83.95 47	91.73 43	57.63 81	73.04 119	66.96 148	78.79 105	73.61 96

V14		69.99 95	74.77 95	64.41 91	64.39 107	64.25 104	75.59 95	43.25 116	71.12 99	67.14 79	83.65 50	91.58 45	57.40 84	72.75 127	66.90 150	78.70 106	73.15 99

v15		69.80 98	74.53 98	64.27 93	64.30 108	64.15 105	75.40 97	43.12 119	70.71 104	66.98 80	83.41 51	91.43 49	57.21 86	72.48 132	66.84 152	78.62 107	72.72 104

TransMVSNet (Re)		63.49 133	73.86 106	51.39 159	64.26 109	56.07 158	61.17 169	42.23 126	78.81 61	34.80 180	85.94 27	90.63 68	34.35 193	72.73 129	67.98 137	71.50 163	64.84 150

v1		68.98 103	73.38 111	63.84 96	64.12 110	62.97 118	74.95 102	41.52 139	70.28 109	67.47 70	82.49 63	91.37 52	56.59 88	71.43 154	66.51 159	78.41 110	68.62 133

v1141		68.97 105	73.38 111	63.83 97	64.11 111	62.97 118	74.96 99	41.52 139	70.29 107	67.36 73	82.47 64	91.37 52	56.59 88	71.43 154	66.49 161	78.41 110	68.61 135

divwei89l23v2f112		68.97 105	73.38 111	63.83 97	64.11 111	62.97 118	74.96 99	41.52 139	70.29 107	67.39 72	82.47 64	91.37 52	56.59 88	71.42 157	66.50 160	78.40 112	68.62 133

v2v482		69.01 102	73.39 110	63.89 95	63.86 113	62.99 117	75.26 98	42.05 130	70.22 111	68.46 61	82.64 62	91.61 44	55.38 100	70.89 160	66.93 149	78.30 113	68.48 137

Fast-Effi-MVS+		67.71 118	72.54 124	62.07 111	63.83 114	63.68 108	75.74 94	39.94 161	60.89 163	54.29 116	73.00 130	86.19 118	56.85 87	78.46 93	73.23 96	81.74 84	72.36 106

v8		68.77 107	73.50 109	63.26 100	63.74 115	64.47 95	74.22 112	42.07 128	67.30 130	64.89 85	82.08 72	90.23 74	56.50 92	71.85 147	66.57 156	78.14 114	72.02 111

v1neww		68.32 112	72.82 119	63.07 104	63.73 116	63.12 114	74.23 108	40.99 145	67.21 131	64.83 88	82.09 70	90.20 75	56.49 94	71.86 144	66.61 153	78.14 114	68.65 131

v7new		68.32 112	72.82 119	63.07 104	63.73 116	63.12 114	74.23 108	40.99 145	67.21 131	64.83 88	82.09 70	90.20 75	56.49 94	71.86 144	66.61 153	78.14 114	68.65 131

v6		68.32 112	72.82 119	63.07 104	63.73 116	63.11 116	74.23 108	40.99 145	67.21 131	64.86 87	82.11 69	90.19 77	56.51 91	71.86 144	66.61 153	78.14 114	68.66 130

v17		68.55 109	73.23 115	63.08 103	63.67 119	63.84 106	74.05 114	42.28 125	66.34 137	63.93 91	81.91 76	89.83 82	56.50 92	71.97 141	66.55 157	78.08 118	72.18 109

Gipuma		73.40 67	79.27 63	66.55 72	63.64 120	59.35 134	70.28 131	45.92 91	83.79 21	71.78 39	84.04 46	93.07 27	68.69 27	87.90 34	76.76 77	78.98 101	69.96 121
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v16		68.33 111	73.03 117	62.86 108	63.57 121	63.83 107	73.98 115	42.30 124	65.58 143	62.94 93	81.82 77	89.37 86	56.36 96	71.91 142	66.52 158	77.99 121	72.17 110

LTVRE_ROB	75.99 1	82.04 18	87.16 4	76.07 22	63.57 121	70.27 70	86.48 39	62.99 7	89.00 5	80.32 7	86.25 26	91.04 58	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	73.62 108	67.28 66	63.53 123	72.96 56	77.97 76	52.10 61	63.65 149	62.66 94	71.14 136	73.46 168	63.55 47	79.35 90	75.34 87	83.90 62	79.43 64

USDC		68.53 110	71.82 129	64.68 87	63.53 123	61.87 124	70.12 132	46.98 83	77.89 62	76.58 24	68.55 142	86.88 111	50.50 123	73.73 111	65.62 165	80.39 89	68.21 139

gg-mvs-nofinetune		56.45 173	61.04 177	51.10 162	63.42 125	49.40 191	53.71 206	52.52 58	74.77 75	46.93 147	77.31 106	53.88 212	26.42 216	62.51 190	57.81 189	63.60 190	51.57 198

v18		67.99 117	72.63 123	62.57 110	63.32 126	63.64 109	73.58 121	42.07 128	64.75 146	62.64 95	81.36 81	89.01 89	56.02 97	71.57 150	66.41 162	77.80 124	71.69 115

conf0.05thres1000		61.96 139	70.38 137	52.13 151	63.31 127	58.12 137	62.09 165	42.45 121	75.50 72	33.07 188	77.89 103	69.72 180	37.32 172	77.88 95	70.72 109	74.55 138	62.82 157

pmmvs-eth3d		65.36 127	70.09 138	59.85 120	63.05 128	53.61 171	74.29 107	46.45 87	68.14 125	51.45 126	78.83 99	85.78 120	49.87 128	70.44 164	70.45 111	74.00 141	63.38 155

tfpn		57.74 163	63.03 170	51.58 158	62.87 129	57.28 145	61.53 168	41.99 131	67.67 126	32.52 191	68.13 145	43.08 231	36.94 174	76.07 104	69.31 116	73.62 143	59.68 167

pmmvs6		64.78 130	75.82 83	51.89 153	62.41 130	57.13 146	60.24 172	45.59 93	82.90 29	34.69 182	84.83 37	93.18 24	36.22 180	76.43 100	71.13 107	72.21 160	65.12 149

DI_MVS_plusplus_trai		63.43 134	67.54 143	58.63 126	62.34 131	58.06 138	65.75 152	42.15 127	63.05 153	53.28 121	75.88 112	75.92 161	50.18 125	68.04 174	64.20 171	78.07 120	67.65 140

CDS-MVSNet		57.90 161	63.57 165	51.28 160	62.30 132	53.17 173	64.70 156	51.61 62	57.41 177	32.75 189	63.73 171	70.53 174	27.12 212	72.49 130	73.02 98	69.22 180	54.68 191
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
view800		59.22 155	66.23 146	51.03 163	61.99 133	56.71 149	60.53 170	41.20 143	66.26 138	32.46 192	66.68 155	69.93 176	36.77 175	74.52 106	70.00 114	73.24 151	59.56 168

tfpnnormal		61.41 143	71.33 132	49.83 169	61.73 134	54.90 166	58.52 181	41.24 142	75.20 73	32.00 198	82.13 68	87.87 96	35.63 184	72.75 127	66.30 163	69.87 177	60.14 164

OpenMVS	60.79 16	64.42 131	69.72 139	58.23 131	61.63 135	62.17 123	64.11 159	37.54 181	67.17 134	55.71 114	65.89 159	74.89 164	52.67 116	72.20 138	68.29 131	77.73 125	77.39 78

thres600view7		58.87 157	65.91 148	50.66 165	61.27 136	56.32 153	59.88 174	40.63 157	64.88 145	32.10 197	64.82 165	69.83 178	36.72 177	72.99 124	72.55 99	73.34 149	59.97 165

Fast-Effi-MVS+-dtu		63.22 135	65.55 149	60.49 117	61.24 137	64.70 93	74.15 113	53.24 55	51.46 198	49.67 137	58.03 199	78.42 152	48.05 136	72.03 139	71.14 106	76.60 130	63.09 156

tpmp4_e23		55.21 180	55.01 196	55.44 142	61.24 137	53.77 168	69.57 136	43.81 107	55.88 184	51.16 129	60.15 188	45.66 225	44.99 150	59.13 200	53.13 201	61.88 192	57.35 178

view600		58.47 158	65.42 150	50.36 167	61.04 139	55.84 160	59.33 177	40.34 160	64.46 147	32.31 196	64.78 166	69.85 177	36.46 178	72.46 133	71.31 104	72.68 156	59.26 172

pmmvs4		61.12 146	64.61 157	57.04 134	60.88 140	52.15 180	70.59 130	44.82 101	61.35 162	46.91 148	72.08 132	73.27 169	46.79 145	65.06 179	67.76 140	72.28 158	60.58 163

3Dnovator	65.69 13	69.43 100	75.74 84	62.06 112	60.78 141	70.50 69	75.85 92	39.57 164	74.44 77	57.41 107	75.91 111	77.73 156	55.34 101	76.86 97	75.61 86	83.44 67	79.14 67

Vis-MVSNet		69.95 96	77.69 71	60.91 116	60.67 142	66.71 75	77.94 77	48.58 71	69.10 121	45.78 154	80.21 90	83.58 133	53.41 113	82.92 65	80.11 57	79.08 100	81.21 57
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
pm-mvs1		61.97 138	72.01 128	50.25 168	60.64 143	55.23 164	58.67 180	42.44 122	74.40 78	33.63 186	81.03 83	89.86 81	34.87 185	72.93 126	67.95 138	71.28 164	62.65 158

v748		71.27 74	79.41 62	61.76 113	60.62 144	61.73 125	68.46 140	40.71 154	80.76 47	61.02 97	87.12 19	95.00 13	59.62 68	80.67 82	70.67 110	80.14 92	79.93 62

MS-PatchMatch		56.31 175	60.22 183	51.73 156	60.53 145	55.53 162	63.41 161	37.18 182	51.34 200	37.44 173	60.53 187	62.19 200	45.52 148	64.25 184	63.17 177	66.33 185	64.56 151

thres400		57.25 164	63.73 163	49.70 171	60.19 146	54.95 165	58.16 182	39.60 163	62.42 156	31.98 200	62.33 179	69.20 182	35.96 182	70.07 167	68.03 136	72.28 158	59.12 173

CANet_DTU		61.22 145	67.07 145	54.40 144	59.89 147	63.62 111	70.98 127	36.77 185	50.49 204	47.15 145	62.45 178	80.81 139	37.90 171	71.87 143	70.09 113	73.69 142	70.19 120

v148		64.92 128	70.58 136	58.32 129	59.89 147	57.09 147	66.04 148	35.27 190	69.11 120	60.66 99	79.57 96	90.93 61	53.91 109	69.81 169	62.22 180	74.14 139	65.31 148

DELS-MVS		65.54 126	71.79 130	58.24 130	59.68 149	65.55 83	70.99 126	38.69 172	62.29 157	49.27 139	75.03 117	81.42 137	50.93 120	73.71 113	71.35 103	79.90 93	73.20 98
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		66.36 121	72.76 122	58.90 124	59.57 150	65.01 89	64.05 160	41.17 144	73.09 86	56.82 109	69.42 139	77.78 155	55.07 103	73.00 123	72.07 101	76.71 127	78.96 68

tfpn_n400		57.07 165	64.44 159	48.48 184	59.55 151	52.25 177	57.99 189	38.85 166	71.25 96	29.07 209	65.20 162	63.07 196	34.41 190	73.99 108	67.52 142	70.99 168	57.83 175

tfpnconf		57.07 165	64.44 159	48.48 184	59.55 151	52.25 177	57.99 189	38.85 166	71.25 96	29.07 209	65.20 162	63.07 196	34.41 190	73.99 108	67.52 142	70.99 168	57.83 175

MVS_Test		62.58 136	67.46 144	56.89 136	59.52 153	55.90 159	64.94 155	38.83 169	57.08 180	56.55 112	76.53 108	84.49 127	47.45 137	66.95 176	62.01 181	74.04 140	69.27 128

tfpnview11		56.69 169	63.86 162	48.33 187	59.46 154	52.35 176	57.85 191	38.80 170	68.21 124	29.07 209	65.20 162	63.07 196	34.36 192	73.21 117	68.72 119	70.44 172	56.28 184

test-LLR		46.01 207	45.06 226	47.11 193	59.39 155	36.72 220	51.28 214	40.95 148	36.41 234	34.45 183	46.14 226	47.02 220	38.00 169	51.78 221	48.53 212	58.60 196	48.84 204

test0.0.03 1		45.40 209	49.55 213	40.57 209	59.39 155	44.36 203	53.37 208	40.95 148	47.14 217	19.23 230	45.49 228	60.24 206	19.24 222	54.82 214	51.98 203	51.21 212	42.82 216

GA-MVS		60.73 149	64.24 161	56.64 138	59.38 157	57.45 144	65.07 153	36.65 186	57.39 178	58.17 105	73.43 127	69.10 184	47.38 138	64.47 183	63.63 175	73.19 153	64.22 152

PatchMatch-RL		60.96 148	63.00 171	58.57 127	59.16 158	52.18 179	67.38 144	41.99 131	57.85 175	48.16 140	53.55 213	69.77 179	59.47 71	73.73 111	72.49 100	75.27 135	61.44 161

PM-MVS		65.66 124	71.25 133	59.14 123	58.92 159	54.88 167	73.66 120	38.55 173	66.12 139	49.91 136	69.87 137	86.97 110	60.61 60	76.30 101	74.75 89	73.19 153	69.83 122

thres200		56.35 174	62.36 172	49.34 173	58.87 160	56.32 153	55.91 196	40.63 157	58.51 168	31.34 201	58.81 197	67.31 186	35.96 182	72.99 124	65.51 166	73.34 149	57.07 180

tfpn111		55.56 179	60.91 179	49.32 175	58.57 161	56.49 150	58.01 184	40.73 151	53.23 189	30.91 204	49.82 219	66.40 191	34.18 194	73.03 120	68.06 132	73.54 144	59.36 169

conf200view11		56.07 177	61.85 174	49.32 175	58.57 161	56.49 150	58.01 184	40.73 151	53.23 189	30.91 204	56.41 202	66.40 191	34.18 194	73.03 120	68.06 132	73.54 144	59.36 169

thres100view900		53.88 182	59.19 184	47.68 191	58.57 161	52.74 175	54.45 202	38.07 176	53.23 189	31.01 202	56.41 202	66.40 191	32.80 203	65.03 180	64.43 170	71.18 167	56.10 185

tfpn200view9		56.07 177	61.85 174	49.34 173	58.57 161	56.48 152	58.01 184	40.72 153	53.23 189	31.01 202	56.41 202	66.40 191	34.18 194	73.02 122	68.06 132	73.53 146	59.35 171

testgi		51.94 190	61.37 176	40.94 207	58.38 165	47.03 197	65.88 149	30.49 213	70.87 103	22.64 225	57.53 201	87.59 99	18.30 224	63.01 186	54.32 198	49.93 214	49.27 202

conf0.01		53.73 184	57.58 188	49.24 178	58.35 166	56.17 155	58.01 184	40.65 155	53.23 189	30.80 207	51.96 215	43.35 230	34.18 194	72.49 130	68.06 132	73.43 147	57.80 177

tfpn1000		56.13 176	63.18 169	47.91 189	58.34 167	53.03 174	58.87 179	38.14 174	65.64 142	27.09 214	65.41 161	59.49 208	33.41 201	73.14 118	69.08 117	71.63 161	56.46 183

conf0.002		52.78 188	55.83 192	49.22 179	58.28 168	56.09 157	58.01 184	40.64 156	53.23 189	30.79 208	50.10 218	36.15 235	34.18 194	72.40 134	65.72 164	73.41 148	57.11 179

FMVSNet1		61.92 140	71.36 131	50.90 164	57.67 169	59.29 135	59.48 176	44.14 105	70.24 110	34.72 181	75.45 116	84.94 124	36.75 176	72.33 135	68.45 125	72.66 157	68.83 129

IB-MVS	57.02 17	61.37 144	65.39 151	56.69 137	56.65 170	60.85 132	70.70 129	37.90 179	49.37 210	45.37 157	48.75 222	79.14 146	53.55 112	76.26 102	70.85 108	75.97 131	72.50 105
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		49.98 197	53.83 200	45.48 197	56.47 171	49.38 192	52.01 212	36.49 187	63.51 151	28.04 212	49.82 219	36.72 234	32.63 204	64.84 181	60.66 183	67.22 184	51.91 197

PVSNet_BlendedMVS		61.75 141	65.07 154	57.87 132	56.27 172	60.99 130	65.81 150	43.75 108	51.27 201	54.08 117	62.12 180	78.84 149	50.67 121	71.49 151	63.91 173	76.64 128	66.86 142

PVSNet_Blended		61.75 141	65.07 154	57.87 132	56.27 172	60.99 130	65.81 150	43.75 108	51.27 201	54.08 117	62.12 180	78.84 149	50.67 121	71.49 151	63.91 173	76.64 128	66.86 142

GBi-Net		56.54 171	63.26 167	48.70 182	55.88 174	57.61 141	57.26 192	41.75 135	49.06 211	32.37 193	61.81 182	67.02 187	34.58 187	72.33 135	68.45 125	70.38 173	66.56 144

test1		56.54 171	63.26 167	48.70 182	55.88 174	57.61 141	57.26 192	41.75 135	49.06 211	32.37 193	61.81 182	67.02 187	34.58 187	72.33 135	68.45 125	70.38 173	66.56 144

FMVSNet2		57.80 162	65.39 151	48.94 181	55.88 174	57.61 141	57.26 192	42.37 123	58.21 170	33.19 187	68.36 144	75.55 162	34.58 187	66.91 177	64.55 169	70.38 173	66.56 144

tpm cat1		50.98 192	51.28 206	50.62 166	55.74 177	49.92 190	63.13 162	38.12 175	52.38 197	47.61 143	60.11 189	44.51 227	44.86 152	51.31 223	47.49 216	54.25 206	53.24 193

new-patchmatchnet		47.33 203	60.49 182	31.99 225	55.69 178	33.86 226	36.84 236	33.31 200	72.36 88	14.33 236	80.09 91	92.14 36	13.27 232	63.54 185	40.09 226	38.51 228	41.32 220

EPNet_dtu		56.63 170	60.77 180	51.80 154	55.47 179	44.63 201	69.83 134	38.74 171	50.27 205	47.64 142	58.01 200	72.27 170	33.71 199	68.60 173	67.72 141	65.39 187	63.86 153
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		50.28 196	57.94 186	41.35 206	55.45 180	43.65 205	58.06 183	34.12 195	62.02 160	24.25 222	59.33 192	79.80 144	24.49 217	59.55 194	54.28 199	51.74 210	46.94 211

V4		73.95 62	81.44 52	65.22 81	54.86 181	63.31 113	78.89 73	38.00 177	80.03 53	68.29 63	87.02 21	95.00 13	68.15 29	84.11 55	75.62 85	83.12 69	84.95 45

v52		73.95 62	81.43 53	65.22 81	54.85 182	63.32 112	78.90 72	38.00 177	80.00 54	68.32 62	87.02 21	94.98 15	68.14 30	84.11 55	75.63 84	83.12 69	84.96 44

CVMVSNet		60.45 150	63.72 164	56.63 139	54.82 183	53.75 169	68.41 141	41.95 133	55.07 186	48.03 141	58.08 198	68.67 185	55.09 102	69.14 172	68.34 129	71.51 162	72.97 103

FC-MVSNet-test		60.28 151	70.83 135	47.96 188	54.69 184	47.12 196	68.06 142	41.68 138	71.42 93	23.73 223	84.70 39	77.41 158	28.92 209	82.33 69	73.08 97	70.68 171	59.77 166

UGNet		65.61 125	74.79 94	54.91 143	54.54 185	68.20 73	70.97 128	48.21 74	67.14 135	41.67 168	74.15 122	80.65 141	36.10 181	79.39 89	77.99 68	77.95 122	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
diffmvs		59.30 153	64.79 156	52.90 149	54.48 186	50.17 188	64.98 154	36.44 188	60.16 165	50.33 133	76.51 109	74.56 165	44.99 150	62.52 189	62.37 179	66.18 186	67.22 141

FMVSNet3		54.77 181	60.73 181	47.81 190	54.29 187	56.88 148	55.89 197	41.75 135	49.06 211	32.37 193	61.81 182	67.02 187	33.67 200	62.88 187	61.96 182	68.88 181	65.53 147

tfpn_ndepth		51.52 191	57.21 189	44.88 198	54.05 188	52.14 181	53.58 207	37.07 183	55.55 185	24.73 219	47.12 224	56.92 210	28.92 209	69.22 171	64.80 167	70.94 170	54.74 190

our_test_3					52.72 189	53.66 170	69.11 138

CostFormer		52.59 189	55.14 195	49.61 172	52.72 189	50.40 185	66.28 147	33.78 197	52.85 195	43.43 161	66.30 156	51.37 214	41.78 163	54.92 213	51.18 206	59.68 195	58.98 174

HyFIR lowres test		59.15 156	62.28 173	55.49 141	52.42 191	62.59 121	71.76 124	39.74 162	50.25 206	41.92 166	62.88 175	69.16 183	55.85 98	62.77 188	67.18 145	71.27 165	61.11 162

dps		49.71 198	51.97 204	47.07 194	52.37 192	47.00 198	53.02 210	40.52 159	44.91 224	41.23 169	64.55 168	44.27 228	40.12 167	57.71 207	51.97 204	55.14 205	53.41 192

V42		65.79 122	72.11 127	58.42 128	51.89 193	58.69 136	73.80 118	34.50 191	65.40 144	57.10 108	79.54 97	89.09 88	57.51 82	71.98 140	67.83 139	75.70 132	72.26 108

DWT-MVSNet_training		48.57 202	47.93 218	49.31 177	51.79 194	48.05 194	61.84 166	34.33 194	41.94 227	43.42 162	50.35 216	34.74 237	47.30 139	52.62 220	52.08 202	57.20 201	55.74 186

CR-MVSNet		53.82 183	55.40 194	51.98 152	51.57 195	50.23 186	45.00 227	44.97 98	46.90 218	52.60 123	67.91 146	46.99 222	48.37 132	59.15 198	59.53 186	69.38 179	57.07 180

IterMVS		59.24 154	64.45 158	53.16 147	50.98 196	61.29 127	66.51 146	32.85 202	58.17 171	46.31 152	72.58 131	70.23 175	54.26 107	64.81 182	60.24 184	68.04 183	63.81 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1111		39.71 225	44.86 229	33.71 223	50.45 197	28.51 233	55.07 200	34.43 192	62.60 154	17.59 232	62.60 176	28.17 239	14.69 229	54.19 216	41.91 223	30.02 233	36.03 226

.test1245		31.52 233	33.91 234	28.73 228	50.45 197	28.51 233	55.07 200	34.43 192	62.60 154	17.59 232	62.60 176	28.17 239	14.69 229	54.19 216	0.54 236	0.15 240	0.77 237

RPMNet		50.92 193	50.32 209	51.62 157	50.25 199	50.23 186	59.16 178	46.70 86	46.90 218	42.39 164	48.97 221	37.23 232	41.78 163	57.30 209	56.18 193	69.44 178	55.43 187

MDTV_nov1_ep13_2view		58.09 160	63.54 166	51.74 155	50.13 200	46.56 200	66.95 145	33.41 199	63.52 150	58.77 103	74.84 119	84.10 130	43.12 156	65.95 178	54.69 197	58.04 199	55.13 188

tpm		46.67 204	49.20 215	43.72 201	49.60 201	36.60 222	53.93 205	26.84 216	52.70 196	58.05 106	69.04 140	47.96 218	30.06 208	48.33 227	42.76 221	43.88 222	47.01 210

TAMVS		46.64 205	53.62 201	38.49 212	49.56 202	36.87 219	53.16 209	25.76 218	56.33 183	22.55 227	60.72 185	61.80 202	27.12 212	59.50 195	58.33 188	52.79 208	41.82 219

PatchmatchNet		48.67 201	50.10 210	46.99 196	48.29 203	41.00 209	55.54 198	38.94 165	51.38 199	45.15 158	63.22 173	48.45 217	42.83 157	53.80 219	48.50 214	51.19 213	44.37 213
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	45.32 18	58.10 159	65.24 153	49.76 170	47.88 204	46.86 199	48.16 224	32.82 203	58.06 172	61.35 96	59.64 191	80.00 142	47.27 140	70.15 166	64.10 172	61.08 193	77.85 76
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		59.77 152	66.07 147	52.42 150	47.81 205	51.86 182	62.98 163	32.28 206	62.08 159	47.10 146	59.94 190	83.42 134	53.08 115	70.06 168	63.19 176	71.26 166	71.96 112

CHOSEN 1792x2688		52.99 187	56.91 190	48.42 186	47.32 206	50.10 189	64.18 158	33.85 196	45.46 223	36.95 175	55.20 208	66.49 190	51.20 119	59.28 196	59.81 185	57.01 202	61.99 160

MVSTER		53.08 186	56.39 191	49.21 180	47.19 207	51.08 183	60.14 173	31.74 208	40.63 229	38.97 171	55.78 205	46.74 223	42.47 159	67.29 175	62.99 178	74.73 137	70.23 119

tpmrst		43.31 217	46.14 222	40.02 211	47.05 208	36.48 223	48.01 225	32.17 207	49.50 209	37.26 174	63.66 172	47.04 219	31.98 207	42.00 234	40.55 225	43.64 223	43.75 215

pmmvs5		50.64 194	58.01 185	42.05 204	47.01 209	43.67 204	49.27 220	29.43 214	50.77 203	33.83 185	68.69 141	76.16 160	27.82 211	57.53 208	57.07 190	64.95 188	52.18 195

MIMVSNet1		56.72 168	68.69 141	42.76 203	46.70 210	42.81 206	69.13 137	30.52 212	81.01 44	32.00 198	74.82 120	91.10 57	26.83 214	73.98 110	64.72 168	51.40 211	52.38 194

MDTV_nov1_ep13		49.60 199	51.57 205	47.31 192	46.28 211	44.61 202	59.82 175	30.96 209	48.80 215	50.20 134	59.26 194	52.38 213	38.56 168	56.20 211	49.70 211	58.04 199	50.01 200

testpf		41.44 220	38.52 233	44.85 199	46.17 212	38.68 215	60.29 171	43.31 114	24.28 236	35.09 179	39.52 232	34.84 236	32.39 205	43.79 233	39.89 227	51.88 209	48.65 206

E-PMN		43.83 216	49.81 212	36.84 216	46.09 213	31.86 230	42.77 231	25.85 217	57.76 176	25.53 216	55.50 206	62.47 199	43.77 154	70.78 162	39.51 228	37.04 229	30.79 231

anonymousdsp		74.76 58	82.59 45	65.63 77	45.61 214	61.13 128	89.06 30	32.58 204	74.11 81	59.55 101	84.06 45	94.12 18	75.24 3	88.94 27	86.95 25	91.74 7	88.81 13

EMVS		43.85 215	49.91 211	36.77 217	45.46 215	32.70 228	44.09 229	25.33 219	57.88 174	26.62 215	58.99 196	61.14 204	42.77 158	70.26 165	38.52 231	36.38 230	29.87 232

MIMVSNet		45.83 208	53.46 203	36.94 215	45.38 216	39.50 212	52.20 211	30.68 210	57.09 179	24.53 221	55.22 207	71.54 171	21.74 220	55.81 212	51.08 207	47.11 218	43.96 214

N_pmnet		39.50 227	51.01 207	26.09 231	44.48 217	25.59 236	40.20 234	21.49 225	64.20 148	7.98 239	73.86 124	76.67 159	13.66 231	50.17 225	36.69 233	28.71 234	29.86 233

EPMVS		40.11 223	44.96 228	34.44 219	41.55 218	32.65 229	41.74 232	32.39 205	49.89 208	24.83 218	64.44 169	46.38 224	26.57 215	44.75 231	39.47 229	39.59 226	37.16 225

test1235678		44.92 211	54.19 197	34.11 220	41.53 219	37.95 216	54.27 203	23.09 222	53.64 187	22.14 228	53.92 210	84.05 131	16.41 227	60.66 192	50.30 209	47.20 216	38.84 223

testmv		44.91 212	54.17 198	34.11 220	41.52 220	37.93 217	54.27 203	23.09 222	53.61 188	22.14 228	53.89 211	84.00 132	16.41 227	60.64 193	50.29 210	47.20 216	38.83 224

MVS-HIRNet		44.56 213	45.52 224	43.44 202	40.98 221	31.03 231	39.52 235	36.96 184	42.80 226	44.37 159	53.80 212	60.04 207	41.85 162	47.97 229	41.08 224	56.99 203	41.95 218

ADS-MVSNet		40.61 221	46.31 220	33.96 222	40.70 222	30.42 232	40.42 233	33.44 198	58.01 173	30.87 206	63.05 174	54.48 211	22.67 219	44.35 232	39.23 230	35.64 231	34.64 227

FMVSNet5		39.83 224	45.08 225	33.71 223	39.24 223	39.56 211	48.77 222	23.55 221	39.45 230	24.55 220	33.73 234	44.57 226	20.97 221	58.27 205	54.23 200	45.16 219	45.77 212

test2356		35.97 228	39.61 232	31.71 226	38.85 224	34.29 225	45.78 226	22.27 224	38.89 233	22.59 226	37.67 233	37.07 233	16.57 226	50.72 224	45.45 218	44.20 220	33.19 228

new_pmnet		35.76 230	45.64 223	24.22 232	38.59 225	25.83 235	31.87 238	19.24 228	49.06 211	9.01 238	54.34 209	64.73 195	12.46 234	49.21 226	44.91 219	34.17 232	31.41 230

no-one		64.33 132	73.23 115	53.94 145	38.32 226	50.78 184	56.78 195	27.44 215	61.95 161	56.77 110	64.60 167	93.12 26	71.12 14	81.91 71	77.19 74	73.20 152	83.04 48

LP		49.44 200	55.77 193	42.05 204	38.31 227	42.61 207	51.74 213	36.31 189	58.35 169	40.36 170	68.52 143	60.77 205	37.08 173	58.27 205	51.76 205	48.51 215	50.13 199

testus		41.61 219	50.54 208	31.20 227	38.11 228	38.92 214	49.10 221	17.60 229	48.25 216	25.05 217	41.45 230	79.34 145	13.18 233	58.28 204	47.10 217	44.17 221	40.41 221

PatchT		50.55 195	53.55 202	47.05 195	37.59 229	42.26 208	50.55 217	37.56 180	46.37 220	52.60 123	66.91 152	43.54 229	48.37 132	59.15 198	59.53 186	55.62 204	57.07 180

MDA-MVSNet-bldmvs		62.46 137	72.13 126	51.19 161	34.32 230	56.10 156	68.65 139	38.85 166	69.05 122	49.50 138	78.17 101	85.43 121	51.32 118	86.67 39	67.40 144	64.46 189	62.08 159

test-mter		44.18 214	47.60 219	40.18 210	33.20 231	39.03 213	55.28 199	13.91 234	39.07 232	36.63 176	48.09 223	49.52 215	41.12 165	54.55 215	50.91 208	60.97 194	52.03 196

test12356		39.53 226	49.18 216	28.26 229	32.93 232	33.64 227	48.68 223	15.96 231	46.26 222	16.21 234	46.46 225	79.07 147	17.13 225	58.60 202	48.30 215	38.67 227	31.96 229

CHOSEN 280x420		40.24 222	44.14 230	35.69 218	32.36 233	23.58 237	50.30 218	21.21 226	40.94 228	18.84 231	32.75 235	48.65 216	48.13 135	59.16 197	55.31 195	43.28 224	48.62 207

TESTMET0.1,1		41.79 218	45.06 226	37.97 213	31.32 234	36.72 220	51.28 214	14.17 233	36.41 234	34.45 183	46.14 226	47.02 220	38.00 169	51.78 221	48.53 212	58.60 196	48.84 204

pmmvs3		46.64 205	54.13 199	37.90 214	31.23 235	40.68 210	49.83 219	15.34 232	46.31 221	36.34 177	53.15 214	74.40 167	36.36 179	58.43 203	56.64 192	58.32 198	49.29 201

PMMVS		45.37 210	49.29 214	40.79 208	27.75 236	35.07 224	50.88 216	19.88 227	39.27 231	35.78 178	50.11 217	61.29 203	42.04 160	54.13 218	55.95 194	68.43 182	49.19 203

PMMVS2		34.11 231	48.55 217	17.26 233	25.45 237	20.72 238	35.08 237	16.26 230	58.71 167	4.16 241	59.22 195	78.40 153	3.65 235	57.24 210	38.31 232	18.94 236	27.28 234

MVE	28.01 19	35.86 229	43.56 231	26.88 230	22.33 238	19.75 239	30.85 239	23.88 220	49.90 207	10.48 237	43.64 229	61.87 201	48.99 131	47.26 230	42.15 222	24.76 235	40.37 222
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				7.47 235	8.89 239	3.32 241	4.35 241	1.14 236	15.58 238	15.76 235	8.50 237	5.90 242	2.00 236	20.02 235	21.51 234	12.70 237

test123		0.53 234	0.60 236	0.46 236	0.22 240	0.25 242	0.33 244	0.13 238	0.66 239	1.37 242	1.10 238	0.00 244	0.43 237	0.68 237	0.61 235	0.26 239	0.88 236

testmvs		0.47 235	0.69 235	0.21 237	0.17 241	0.17 243	0.35 243	0.16 237	0.66 239	0.18 244	1.05 239	0.99 243	0.27 238	0.62 238	0.54 236	0.15 240	0.77 237

GG-mvs-BLEND		31.54 232	46.27 221	14.37 234	0.07 242	48.65 193	42.97 230	0.08 239	44.04 225	1.21 243	39.77 231	57.94 209	0.15 239	48.19 228	42.82 220	41.70 225	42.46 217

sosnet-low-res		0.00 236	0.00 237	0.00 238	0.00 243	0.00 244	0.00 245	0.00 240	0.00 241	0.00 245	0.00 240	0.00 244	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

sosnet		0.00 236	0.00 237	0.00 238	0.00 243	0.00 244	0.00 245	0.00 240	0.00 241	0.00 245	0.00 240	0.00 244	0.00 240	0.00 239	0.00 238	0.00 242	0.00 239

MTAPA										80.26 8		90.53 73

MTMP										82.07 4		91.00 59

Patchmatch-RL test							2.05 242

NP-MVS									71.39 94

Patchmtry						37.73 218	45.00 227	44.97 98		52.60 123

DeepMVS_CX						8.52 240	9.75 240	3.19 235	16.70 237	5.02 240	23.06 236	19.33 241	18.69 223	13.75 236		11.34 238	25.07 235

High-resolution multi-view benchmark