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 65	53.14 122	79.73 93	82.09 135	59.69 67	92.21 5	90.93 3	92.32 3	89.36 7

mPP-MVS					82.97 2							92.12 36

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 91	90.74 64	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 73	90.76 63	72.86 6	90.14 19	89.30 11	90.92 19	88.59 19

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 74	87.01 107	68.20 28	84.15 53	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 84	92.97 28	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 64	67.49 69	85.90 27	89.82 82	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 51	92.04 37	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 81	71.03 44	83.67 48	87.68 97	64.75 41	83.70 57	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 33	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	73.88 122	92.28 34	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 87	91.44 47	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 78	90.71 65	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 76				91.52 11

X-MVStestdata					80.47 19	81.29 12	93.33 3			77.45 20		90.19 76				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 19	91.40 50	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	72.04 132	90.19 76	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 40	87.27 104	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 85	93.14 24	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 79	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 65	89.59 83	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 56	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 32	92.88 29	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 17	91.27 54	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	67.75 146	87.05 106	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 33	88.71 90	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 47	87.34 102	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 34	90.92 61	62.99 49	81.15 74	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 36	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 23	90.54 71	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	74.70 120	86.43 113	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 14	89.17 86	71.98 11	88.19 32	88.10 17	86.18 51	89.95 5

HQP-MVS		75.81 54	78.91 65	72.18 41	77.41 38	75.38 46	84.75 43	53.35 54	76.12 69	73.32 33	69.48 137	88.07 92	57.76 78	79.42 87	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 86	69.75 52	77.78 104	88.90 89	61.31 59	84.09 56	82.54 45	87.79 40	83.57 46

TSAR-MVS + GP.		73.42 66	76.31 77	70.05 51	77.15 40	71.13 68	81.59 61	54.11 51	69.84 118	58.65 104	66.20 156	78.77 150	65.29 39	83.65 58	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 94	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 71	71.40 43	76.90 42	75.76 43	84.54 45	53.08 56	76.20 68	66.64 82	66.06 157	78.16 153	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 62	68.91 59	77.00 106	87.32 103	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 42	87.44 101	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 27	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 99	92.41 32	59.05 72	80.24 85	73.95 92	75.41 133	78.85 69

MVS_0304		73.74 65	77.16 74	69.74 54	74.24 49	73.47 55	84.70 44	49.62 65	62.26 157	67.27 75	75.87 112	87.57 99	57.49 83	81.20 73	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 66	86.47 112	66.47 34	84.80 51	84.16 36	87.26 43	87.34 27

CLD-MVS		71.24 75	78.12 68	63.20 101	74.03 51	71.60 66	82.82 54	32.91 200	74.23 79	69.32 55	79.65 94	91.54 45	47.02 142	81.22 72	79.01 61	73.09 154	69.63 122
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
EPNet		66.87 118	68.89 139	64.53 90	73.97 52	61.13 127	78.46 74	61.03 19	56.78 181	53.41 120	66.91 151	70.91 172	43.49 155	76.08 102	76.68 78	76.81 125	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 22	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 72	69.63 55	73.75 54	74.73 49	81.38 62	48.58 71	74.77 74	69.16 56	71.97 133	86.20 116	59.50 69	78.51 91	74.06 91	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 80	83.47 23	69.82 51	80.44 86	87.19 105	64.59 42	81.01 77	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 88	92.49 31	64.14 43	87.25 37	85.11 31	89.92 25	87.10 29

CANet		71.07 77	75.09 88	66.39 73	72.57 57	71.53 67	82.38 56	47.10 81	59.81 165	59.81 100	74.97 117	84.37 127	54.25 108	79.89 86	77.64 72	82.25 79	77.40 77

TranMVSNet+NR-MVSNet		71.66 70	79.23 64	62.83 109	72.54 58	65.64 82	74.77 104	55.27 44	75.91 70	45.50 155	89.55 9	94.25 16	45.96 146	82.74 65	77.03 75	82.96 72	69.48 126

UniMVSNet_NR-MVSNet		70.82 81	77.44 72	63.11 102	71.75 59	66.02 80	73.93 116	55.00 47	70.90 100	46.77 150	86.68 24	91.54 45	46.91 143	81.07 76	76.32 80	84.28 59	69.54 123

Anonymous20231211		71.23 76	81.58 50	59.15 122	71.63 60	60.40 132	70.12 131	52.15 60	92.79 1	42.31 165	88.89 11	98.03 1	40.61 165	80.86 79	75.96 82	78.08 117	74.11 89

PCF-MVS	65.25 14	73.99 61	76.74 76	70.79 46	71.61 61	75.33 47	83.76 47	50.40 64	74.88 73	74.50 32	67.60 147	85.36 121	58.30 74	78.61 90	74.25 90	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 57	87.00 108	60.02 63	80.30 83	79.61 59	81.95 82	81.61 55

PHI-MVS		75.17 57	78.37 66	71.43 42	71.13 63	72.46 63	82.28 57	50.55 63	73.39 84	79.05 15	73.65 124	87.50 100	61.98 53	81.10 75	78.48 62	83.60 65	81.99 52

DU-MVS		71.03 79	77.92 69	62.98 107	70.81 64	65.48 84	73.93 116	56.76 34	69.95 116	46.77 150	85.70 30	93.49 20	46.91 143	83.47 59	77.82 70	82.72 75	69.54 123

Baseline_NR-MVSNet		68.15 115	75.12 87	60.02 118	70.81 64	55.67 160	75.88 91	53.40 53	71.25 95	43.96 160	85.88 28	92.68 30	45.76 147	83.47 59	68.34 128	70.34 175	68.58 135

CNLPA		76.67 51	81.72 49	70.77 47	70.75 66	76.68 39	86.14 41	46.11 89	81.82 37	74.68 31	76.37 109	86.23 115	62.92 51	85.28 48	83.29 41	84.02 60	82.40 51

EG-PatchMatch MVS		71.50 72	76.82 75	65.30 79	70.74 67	66.50 78	74.23 108	43.25 115	72.02 89	59.11 102	79.85 92	86.88 110	63.95 44	80.29 84	75.25 87	80.51 87	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	78.06 101	81.15 137	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 62	63.09 92	67.25 150	89.50 84	71.01 15	88.10 33	85.74 27	80.39 88	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	71.32 134	84.82 124	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 67	63.30 99	70.29 71	66.57 77	75.98 89	54.74 49	70.20 111	46.20 153	85.08 35	93.21 22	48.19 134	82.50 67	78.33 65	84.40 58	71.08 117

Effi-MVS+-dtu		70.10 91	73.76 106	65.82 75	70.23 72	74.92 48	79.47 71	44.49 102	56.98 180	54.34 115	64.26 169	84.78 125	59.97 64	80.96 78	80.38 55	86.44 49	74.05 91

MAR-MVS		70.00 93	72.28 124	67.34 65	69.89 73	72.57 62	80.09 68	49.49 67	60.28 163	69.03 58	59.29 192	80.79 139	54.68 106	78.39 93	76.00 81	80.87 85	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 35	70.63 48	69.62 74	72.40 64	80.77 65	46.43 87	89.24 4	77.99 17	87.42 16	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 75	74.02 53	82.50 55	47.39 79	66.39 135	56.63 111	60.61 185	82.76 134	53.68 111			82.92 73	78.39 74

FPMVS		70.46 86	74.89 90	65.28 80	69.09 76	61.42 125	77.07 83	46.92 84	76.73 67	53.53 119	67.33 148	75.07 162	67.23 31	83.41 61	81.54 54	77.86 122	78.73 70

IS_MVSNet		68.20 114	74.41 101	60.96 115	68.55 77	64.36 100	71.47 124	48.33 73	70.11 113	43.30 163	80.90 83	74.54 165	47.19 141	81.25 71	77.97 69	86.94 45	71.76 113

MVS_111021_HR		72.37 68	76.12 80	68.00 59	68.55 77	64.30 103	82.93 52	48.98 69	74.25 78	65.39 84	73.59 125	84.11 128	59.48 70	82.61 66	78.38 64	82.66 76	75.59 84

EPP-MVSNet		69.51 98	76.17 78	61.74 114	68.38 79	66.60 76	71.77 122	46.98 82	73.60 83	41.79 167	82.06 72	69.65 180	52.51 117	83.41 61	79.94 58	89.02 30	77.94 75

TAPA-MVS	66.11 12	75.37 56	79.24 63	70.86 45	67.63 80	74.09 52	83.17 51	44.75 101	81.82 37	80.83 5	65.61 159	88.04 93	61.58 56	83.21 63	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 86	67.38 64	67.42 81	62.44 121	81.73 59	46.24 88	70.89 101	66.80 81	73.19 127	84.98 122	60.09 62	81.94 69	77.77 71	82.00 81	75.29 85

Effi-MVS+		69.04 100	73.01 117	64.40 92	67.20 82	64.83 92	74.87 103	43.97 105	63.33 151	60.90 98	73.06 128	85.79 118	55.61 99	73.58 113	76.41 79	83.84 63	74.09 90

MSDG		68.98 102	73.31 113	63.92 94	67.08 83	68.27 72	75.41 96	40.77 149	67.61 126	64.89 85	75.75 113	78.96 147	53.70 110	76.72 98	73.95 92	81.71 84	71.93 112

v7n		74.47 60	81.06 54	66.77 68	66.98 84	67.10 74	76.76 84	45.88 91	81.98 36	67.43 71	88.38 12	95.67 10	61.38 57	80.76 80	73.49 94	82.21 80	80.06 61

v1240		70.94 80	74.52 98	66.76 69	66.54 85	64.40 97	77.76 78	45.29 93	70.05 114	71.45 41	83.36 53	90.96 59	60.37 61	70.50 162	68.68 119	79.14 98	73.68 95

v1192		71.06 78	74.87 91	66.61 70	66.38 86	65.80 81	78.27 75	45.28 94	70.19 112	70.79 48	83.37 51	91.79 40	58.76 73	70.86 160	69.02 117	80.16 90	73.08 100

v1921920		70.82 81	74.46 100	66.58 71	66.33 87	64.35 102	77.72 79	45.07 96	70.39 105	71.18 43	83.15 54	90.62 68	59.97 64	70.90 158	68.43 127	79.19 97	73.39 97

TinyColmap		71.85 69	76.11 81	66.87 67	66.07 88	65.34 86	74.35 106	49.30 68	79.93 55	75.93 28	75.66 114	87.74 96	54.72 105	80.66 82	70.42 111	80.85 86	73.02 102

gm-plane-assit		56.76 166	57.64 186	55.73 139	66.01 89	55.45 162	74.96 99	30.54 210	73.71 82	56.04 113	81.81 77	30.91 237	43.83 153	58.77 200	54.71 195	63.02 190	48.13 207

v144192		70.68 84	74.40 102	66.34 74	65.94 90	64.38 99	77.63 80	45.18 95	69.97 115	70.11 50	82.70 60	90.77 62	59.84 66	71.43 153	68.46 123	79.31 96	73.08 100

canonicalmvs		66.37 119	74.37 103	57.04 133	65.89 91	65.06 88	62.58 162	42.55 119	76.82 66	46.87 149	67.33 148	86.38 114	45.49 149	76.77 97	71.85 101	78.87 102	76.35 81

v1144		70.45 87	74.50 99	65.73 76	65.74 92	64.88 90	77.33 82	44.16 103	70.59 104	69.63 53	83.15 54	91.42 49	57.79 77	71.29 157	68.53 122	79.72 93	71.63 115

NR-MVSNet		68.66 107	76.15 79	59.93 119	65.49 93	65.48 84	74.42 105	56.76 34	69.95 116	45.38 156	85.70 30	91.13 55	34.68 185	74.52 105	76.75 77	82.83 74	69.49 125

v7		69.81 96	73.94 104	65.00 84	65.33 94	65.07 87	76.60 85	43.66 110	67.36 128	67.25 76	82.76 58	90.57 69	57.70 79	71.69 147	68.63 120	79.44 94	71.52 116

IterMVS-LS		65.76 122	70.85 133	59.81 121	65.33 94	57.78 139	64.63 155	48.02 76	65.65 140	51.05 130	81.31 81	77.47 156	54.94 104	69.46 169	69.36 114	74.90 135	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 96	65.19 83	65.32 96	66.46 79	76.60 85	44.84 99	67.38 127	67.21 77	82.75 59	90.56 70	57.70 79	71.69 147	68.63 120	79.44 94	74.67 87

FC-MVSNet-train		64.87 128	74.76 95	53.33 145	65.24 97	58.05 138	69.69 134	41.92 133	70.99 99	32.62 189	85.75 29	88.23 91	32.10 205	77.61 95	74.41 89	78.43 108	68.25 137

RPSCF		77.56 42	84.51 36	69.46 56	65.17 98	74.36 50	79.74 70	47.45 78	84.01 20	72.89 35	77.89 102	90.67 66	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 99	64.85 91	77.44 81	47.74 77	82.76 30	68.52 60	87.65 15	93.31 21	71.68 13	89.49 24	82.41 47	88.14 36	85.05 43

v11		70.10 91	74.82 92	64.58 88	64.83 100	64.39 98	75.89 90	43.18 117	71.34 94	67.75 64	84.19 40	91.75 41	57.23 85	71.46 152	66.85 150	78.60 107	73.78 93

test20.03		53.49 184	60.95 177	44.78 199	64.73 101	47.25 193	61.58 165	43.30 114	65.86 139	22.85 223	66.87 153	79.85 142	22.99 217	62.38 190	56.95 190	53.25 206	47.46 208

v13		70.58 85	75.49 84	64.87 85	64.66 102	64.58 94	76.18 87	43.69 109	72.34 88	67.65 65	84.36 39	92.01 38	58.05 75	73.57 114	67.06 145	78.96 101	74.48 88

Vis-MVSNet (Re-imp)		60.99 146	67.78 141	53.06 147	64.66 102	53.49 170	67.40 141	49.52 66	68.55 122	28.00 212	79.53 97	71.41 171	33.08 201	75.30 104	71.28 104	75.69 132	54.91 188

v12		70.39 88	75.25 85	64.73 86	64.60 104	64.47 95	76.00 88	43.55 111	71.92 90	67.51 68	84.15 43	91.88 39	57.83 76	73.32 115	67.00 146	78.87 102	74.02 92

V9		70.20 90	75.02 89	64.58 88	64.49 105	64.36 100	75.80 93	43.40 112	71.53 91	67.35 74	83.95 46	91.73 42	57.63 81	73.04 118	66.96 147	78.79 104	73.61 96

V14		69.99 94	74.77 94	64.41 91	64.39 106	64.25 104	75.59 95	43.25 115	71.12 98	67.14 79	83.65 49	91.58 44	57.40 84	72.75 126	66.90 149	78.70 105	73.15 99

v15		69.80 97	74.53 97	64.27 93	64.30 107	64.15 105	75.40 97	43.12 118	70.71 103	66.98 80	83.41 50	91.43 48	57.21 86	72.48 131	66.84 151	78.62 106	72.72 104

TransMVSNet (Re)		63.49 132	73.86 105	51.39 158	64.26 108	56.07 157	61.17 167	42.23 125	78.81 60	34.80 179	85.94 26	90.63 67	34.35 192	72.73 128	67.98 136	71.50 162	64.84 149

v1		68.98 102	73.38 110	63.84 96	64.12 109	62.97 117	74.95 102	41.52 138	70.28 108	67.47 70	82.49 62	91.37 51	56.59 88	71.43 153	66.51 158	78.41 109	68.62 132

v1141		68.97 104	73.38 110	63.83 97	64.11 110	62.97 117	74.96 99	41.52 138	70.29 106	67.36 73	82.47 63	91.37 51	56.59 88	71.43 153	66.49 160	78.41 109	68.61 134

divwei89l23v2f112		68.97 104	73.38 110	63.83 97	64.11 110	62.97 117	74.96 99	41.52 138	70.29 106	67.39 72	82.47 63	91.37 51	56.59 88	71.42 156	66.50 159	78.40 111	68.62 132

v2v482		69.01 101	73.39 109	63.89 95	63.86 112	62.99 116	75.26 98	42.05 129	70.22 110	68.46 61	82.64 61	91.61 43	55.38 100	70.89 159	66.93 148	78.30 112	68.48 136

Fast-Effi-MVS+		67.71 117	72.54 123	62.07 111	63.83 113	63.68 108	75.74 94	39.94 160	60.89 162	54.29 116	73.00 129	86.19 117	56.85 87	78.46 92	73.23 95	81.74 83	72.36 106

v8		68.77 106	73.50 108	63.26 100	63.74 114	64.47 95	74.22 112	42.07 127	67.30 129	64.89 85	82.08 71	90.23 73	56.50 92	71.85 146	66.57 155	78.14 113	72.02 110

v1neww		68.32 111	72.82 118	63.07 104	63.73 115	63.12 113	74.23 108	40.99 144	67.21 130	64.83 88	82.09 69	90.20 74	56.49 94	71.86 143	66.61 152	78.14 113	68.65 130

v7new		68.32 111	72.82 118	63.07 104	63.73 115	63.12 113	74.23 108	40.99 144	67.21 130	64.83 88	82.09 69	90.20 74	56.49 94	71.86 143	66.61 152	78.14 113	68.65 130

v6		68.32 111	72.82 118	63.07 104	63.73 115	63.11 115	74.23 108	40.99 144	67.21 130	64.86 87	82.11 68	90.19 76	56.51 91	71.86 143	66.61 152	78.14 113	68.66 129

v17		68.55 108	73.23 114	63.08 103	63.67 118	63.84 106	74.05 114	42.28 124	66.34 136	63.93 91	81.91 75	89.83 81	56.50 92	71.97 140	66.55 156	78.08 117	72.18 108

Gipuma		73.40 67	79.27 62	66.55 72	63.64 119	59.35 133	70.28 130	45.92 90	83.79 21	71.78 39	84.04 45	93.07 26	68.69 27	87.90 34	76.76 76	78.98 100	69.96 120
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v16		68.33 110	73.03 116	62.86 108	63.57 120	63.83 107	73.98 115	42.30 123	65.58 142	62.94 93	81.82 76	89.37 85	56.36 96	71.91 141	66.52 157	77.99 120	72.17 109

LTVRE_ROB	75.99 1	82.04 18	87.16 4	76.07 22	63.57 120	70.27 70	86.48 39	62.99 7	89.00 5	80.32 7	86.25 25	91.04 57	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 66	63.53 122	72.96 56	77.97 76	52.10 61	63.65 148	62.66 94	71.14 135	73.46 167	63.55 47	79.35 89	75.34 86	83.90 62	79.43 64

USDC		68.53 109	71.82 128	64.68 87	63.53 122	61.87 123	70.12 131	46.98 82	77.89 61	76.58 24	68.55 141	86.88 110	50.50 123	73.73 110	65.62 164	80.39 88	68.21 138

gg-mvs-nofinetune		56.45 172	61.04 176	51.10 161	63.42 124	49.40 189	53.71 204	52.52 58	74.77 74	46.93 147	77.31 105	53.88 211	26.42 215	62.51 189	57.81 188	63.60 189	51.57 197

v18		67.99 116	72.63 122	62.57 110	63.32 125	63.64 109	73.58 121	42.07 127	64.75 145	62.64 95	81.36 80	89.01 88	56.02 97	71.57 149	66.41 161	77.80 123	71.69 114

conf0.05thres1000		61.96 138	70.38 136	52.13 150	63.31 126	58.12 136	62.09 163	42.45 120	75.50 71	33.07 187	77.89 102	69.72 179	37.32 171	77.88 94	70.72 108	74.55 137	62.82 156

pmmvs-eth3d		65.36 126	70.09 137	59.85 120	63.05 127	53.61 169	74.29 107	46.45 86	68.14 124	51.45 126	78.83 98	85.78 119	49.87 128	70.44 163	70.45 110	74.00 140	63.38 154

tfpn		57.74 162	63.03 169	51.58 157	62.87 128	57.28 144	61.53 166	41.99 130	67.67 125	32.52 190	68.13 144	43.08 230	36.94 173	76.07 103	69.31 115	73.62 142	59.68 166

pmmvs6		64.78 129	75.82 82	51.89 152	62.41 129	57.13 145	60.24 170	45.59 92	82.90 29	34.69 181	84.83 36	93.18 23	36.22 179	76.43 99	71.13 106	72.21 159	65.12 148

DI_MVS_plusplus_trai		63.43 133	67.54 142	58.63 125	62.34 130	58.06 137	65.75 150	42.15 126	63.05 152	53.28 121	75.88 111	75.92 160	50.18 125	68.04 173	64.20 170	78.07 119	67.65 139

CDS-MVSNet		57.90 160	63.57 164	51.28 159	62.30 131	53.17 171	64.70 154	51.61 62	57.41 176	32.75 188	63.73 170	70.53 173	27.12 211	72.49 129	73.02 97	69.22 179	54.68 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
view800		59.22 154	66.23 145	51.03 162	61.99 132	56.71 148	60.53 168	41.20 142	66.26 137	32.46 191	66.68 154	69.93 175	36.77 174	74.52 105	70.00 113	73.24 150	59.56 167

tfpnnormal		61.41 142	71.33 131	49.83 168	61.73 133	54.90 165	58.52 179	41.24 141	75.20 72	32.00 197	82.13 67	87.87 95	35.63 183	72.75 126	66.30 162	69.87 176	60.14 163

OpenMVS	60.79 16	64.42 130	69.72 138	58.23 130	61.63 134	62.17 122	64.11 157	37.54 180	67.17 133	55.71 114	65.89 158	74.89 163	52.67 116	72.20 137	68.29 130	77.73 124	77.39 78

thres600view7		58.87 156	65.91 147	50.66 164	61.27 135	56.32 152	59.88 172	40.63 156	64.88 144	32.10 196	64.82 164	69.83 177	36.72 176	72.99 123	72.55 98	73.34 148	59.97 164

Fast-Effi-MVS+-dtu		63.22 134	65.55 148	60.49 117	61.24 136	64.70 93	74.15 113	53.24 55	51.46 197	49.67 137	58.03 198	78.42 151	48.05 136	72.03 138	71.14 105	76.60 129	63.09 155

tpmp4_e23		55.21 179	55.01 195	55.44 141	61.24 136	53.77 167	69.57 135	43.81 106	55.88 183	51.16 129	60.15 187	45.66 224	44.99 150	59.13 199	53.13 200	61.88 191	57.35 177

view600		58.47 157	65.42 149	50.36 166	61.04 138	55.84 159	59.33 175	40.34 159	64.46 146	32.31 195	64.78 165	69.85 176	36.46 177	72.46 132	71.31 103	72.68 155	59.26 171

pmmvs4		61.12 145	64.61 156	57.04 133	60.88 139	52.15 178	70.59 129	44.82 100	61.35 161	46.91 148	72.08 131	73.27 168	46.79 145	65.06 178	67.76 139	72.28 157	60.58 162

3Dnovator	65.69 13	69.43 99	75.74 83	62.06 112	60.78 140	70.50 69	75.85 92	39.57 163	74.44 76	57.41 107	75.91 110	77.73 155	55.34 101	76.86 96	75.61 85	83.44 67	79.14 67

Vis-MVSNet		69.95 95	77.69 70	60.91 116	60.67 141	66.71 75	77.94 77	48.58 71	69.10 120	45.78 154	80.21 89	83.58 132	53.41 113	82.92 64	80.11 57	79.08 99	81.21 57
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
pm-mvs1		61.97 137	72.01 127	50.25 167	60.64 142	55.23 163	58.67 178	42.44 121	74.40 77	33.63 185	81.03 82	89.86 80	34.87 184	72.93 125	67.95 137	71.28 163	62.65 157

v748		71.27 74	79.41 61	61.76 113	60.62 143	61.73 124	68.46 138	40.71 153	80.76 47	61.02 97	87.12 18	95.00 13	59.62 68	80.67 81	70.67 109	80.14 91	79.93 62

MS-PatchMatch		56.31 174	60.22 182	51.73 155	60.53 144	55.53 161	63.41 159	37.18 181	51.34 199	37.44 172	60.53 186	62.19 199	45.52 148	64.25 183	63.17 176	66.33 184	64.56 150

thres400		57.25 163	63.73 162	49.70 170	60.19 145	54.95 164	58.16 180	39.60 162	62.42 155	31.98 199	62.33 178	69.20 181	35.96 181	70.07 166	68.03 135	72.28 157	59.12 172

CANet_DTU		61.22 144	67.07 144	54.40 143	59.89 146	63.62 110	70.98 126	36.77 184	50.49 203	47.15 145	62.45 177	80.81 138	37.90 170	71.87 142	70.09 112	73.69 141	70.19 119

v148		64.92 127	70.58 135	58.32 128	59.89 146	57.09 146	66.04 146	35.27 189	69.11 119	60.66 99	79.57 95	90.93 60	53.91 109	69.81 168	62.22 179	74.14 138	65.31 147

DELS-MVS		65.54 125	71.79 129	58.24 129	59.68 148	65.55 83	70.99 125	38.69 171	62.29 156	49.27 139	75.03 116	81.42 136	50.93 120	73.71 112	71.35 102	79.90 92	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		66.36 120	72.76 121	58.90 124	59.57 149	65.01 89	64.05 158	41.17 143	73.09 85	56.82 109	69.42 138	77.78 154	55.07 103	73.00 122	72.07 100	76.71 126	78.96 68

tfpn_n400		57.07 164	64.44 158	48.48 183	59.55 150	52.25 175	57.99 187	38.85 165	71.25 95	29.07 208	65.20 161	63.07 195	34.41 189	73.99 107	67.52 141	70.99 167	57.83 174

tfpnconf		57.07 164	64.44 158	48.48 183	59.55 150	52.25 175	57.99 187	38.85 165	71.25 95	29.07 208	65.20 161	63.07 195	34.41 189	73.99 107	67.52 141	70.99 167	57.83 174

MVS_Test		62.58 135	67.46 143	56.89 135	59.52 152	55.90 158	64.94 153	38.83 168	57.08 179	56.55 112	76.53 107	84.49 126	47.45 137	66.95 175	62.01 180	74.04 139	69.27 127

tfpnview11		56.69 168	63.86 161	48.33 186	59.46 153	52.35 174	57.85 189	38.80 169	68.21 123	29.07 208	65.20 161	63.07 195	34.36 191	73.21 116	68.72 118	70.44 171	56.28 183

test-LLR		46.01 206	45.06 225	47.11 192	59.39 154	36.72 218	51.28 212	40.95 147	36.41 233	34.45 182	46.14 225	47.02 219	38.00 168	51.78 220	48.53 211	58.60 195	48.84 203

test0.0.03 1		45.40 208	49.55 212	40.57 208	59.39 154	44.36 201	53.37 206	40.95 147	47.14 216	19.23 229	45.49 227	60.24 205	19.24 221	54.82 213	51.98 202	51.21 211	42.82 215

GA-MVS		60.73 148	64.24 160	56.64 137	59.38 156	57.45 143	65.07 151	36.65 185	57.39 177	58.17 105	73.43 126	69.10 183	47.38 138	64.47 182	63.63 174	73.19 152	64.22 151

PatchMatch-RL		60.96 147	63.00 170	58.57 126	59.16 157	52.18 177	67.38 142	41.99 130	57.85 174	48.16 140	53.55 212	69.77 178	59.47 71	73.73 110	72.49 99	75.27 134	61.44 160

PM-MVS		65.66 123	71.25 132	59.14 123	58.92 158	54.88 166	73.66 120	38.55 172	66.12 138	49.91 136	69.87 136	86.97 109	60.61 60	76.30 100	74.75 88	73.19 152	69.83 121

thres200		56.35 173	62.36 171	49.34 172	58.87 159	56.32 152	55.91 194	40.63 156	58.51 167	31.34 200	58.81 196	67.31 185	35.96 181	72.99 123	65.51 165	73.34 148	57.07 179

tfpn111		55.56 178	60.91 178	49.32 174	58.57 160	56.49 149	58.01 182	40.73 150	53.23 188	30.91 203	49.82 218	66.40 190	34.18 193	73.03 119	68.06 131	73.54 143	59.36 168

conf200view11		56.07 176	61.85 173	49.32 174	58.57 160	56.49 149	58.01 182	40.73 150	53.23 188	30.91 203	56.41 201	66.40 190	34.18 193	73.03 119	68.06 131	73.54 143	59.36 168

thres100view900		53.88 181	59.19 183	47.68 190	58.57 160	52.74 173	54.45 200	38.07 175	53.23 188	31.01 201	56.41 201	66.40 190	32.80 202	65.03 179	64.43 169	71.18 166	56.10 184

tfpn200view9		56.07 176	61.85 173	49.34 172	58.57 160	56.48 151	58.01 182	40.72 152	53.23 188	31.01 201	56.41 201	66.40 190	34.18 193	73.02 121	68.06 131	73.53 145	59.35 170

testgi		51.94 189	61.37 175	40.94 206	58.38 164	47.03 195	65.88 147	30.49 212	70.87 102	22.64 224	57.53 200	87.59 98	18.30 223	63.01 185	54.32 197	49.93 213	49.27 201

conf0.01		53.73 183	57.58 187	49.24 177	58.35 165	56.17 154	58.01 182	40.65 154	53.23 188	30.80 206	51.96 214	43.35 229	34.18 193	72.49 129	68.06 131	73.43 146	57.80 176

tfpn1000		56.13 175	63.18 168	47.91 188	58.34 166	53.03 172	58.87 177	38.14 173	65.64 141	27.09 213	65.41 160	59.49 207	33.41 200	73.14 117	69.08 116	71.63 160	56.46 182

conf0.002		52.78 187	55.83 191	49.22 178	58.28 167	56.09 156	58.01 182	40.64 155	53.23 188	30.79 207	50.10 217	36.15 234	34.18 193	72.40 133	65.72 163	73.41 147	57.11 178

FMVSNet1		61.92 139	71.36 130	50.90 163	57.67 168	59.29 134	59.48 174	44.14 104	70.24 109	34.72 180	75.45 115	84.94 123	36.75 175	72.33 134	68.45 124	72.66 156	68.83 128

IB-MVS	57.02 17	61.37 143	65.39 150	56.69 136	56.65 169	60.85 131	70.70 128	37.90 178	49.37 209	45.37 157	48.75 221	79.14 145	53.55 112	76.26 101	70.85 107	75.97 130	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		49.98 196	53.83 199	45.48 196	56.47 170	49.38 190	52.01 210	36.49 186	63.51 150	28.04 211	49.82 218	36.72 233	32.63 203	64.84 180	60.66 182	67.22 183	51.91 196

PVSNet_BlendedMVS		61.75 140	65.07 153	57.87 131	56.27 171	60.99 129	65.81 148	43.75 107	51.27 200	54.08 117	62.12 179	78.84 148	50.67 121	71.49 150	63.91 172	76.64 127	66.86 141

PVSNet_Blended		61.75 140	65.07 153	57.87 131	56.27 171	60.99 129	65.81 148	43.75 107	51.27 200	54.08 117	62.12 179	78.84 148	50.67 121	71.49 150	63.91 172	76.64 127	66.86 141

GBi-Net		56.54 170	63.26 166	48.70 181	55.88 173	57.61 140	57.26 190	41.75 134	49.06 210	32.37 192	61.81 181	67.02 186	34.58 186	72.33 134	68.45 124	70.38 172	66.56 143

test1		56.54 170	63.26 166	48.70 181	55.88 173	57.61 140	57.26 190	41.75 134	49.06 210	32.37 192	61.81 181	67.02 186	34.58 186	72.33 134	68.45 124	70.38 172	66.56 143

FMVSNet2		57.80 161	65.39 150	48.94 180	55.88 173	57.61 140	57.26 190	42.37 122	58.21 169	33.19 186	68.36 143	75.55 161	34.58 186	66.91 176	64.55 168	70.38 172	66.56 143

tpm cat1		50.98 191	51.28 205	50.62 165	55.74 176	49.92 188	63.13 160	38.12 174	52.38 196	47.61 143	60.11 188	44.51 226	44.86 152	51.31 222	47.49 215	54.25 205	53.24 192

new-patchmatchnet		47.33 202	60.49 181	31.99 224	55.69 177	33.86 224	36.84 234	33.31 199	72.36 87	14.33 235	80.09 90	92.14 35	13.27 231	63.54 184	40.09 225	38.51 227	41.32 219

EPNet_dtu		56.63 169	60.77 179	51.80 153	55.47 178	44.63 199	69.83 133	38.74 170	50.27 204	47.64 142	58.01 199	72.27 169	33.71 198	68.60 172	67.72 140	65.39 186	63.86 152
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20231206		50.28 195	57.94 185	41.35 205	55.45 179	43.65 203	58.06 181	34.12 194	62.02 159	24.25 221	59.33 191	79.80 143	24.49 216	59.55 193	54.28 198	51.74 209	46.94 210

V4		73.95 62	81.44 52	65.22 81	54.86 180	63.31 112	78.89 73	38.00 176	80.03 53	68.29 63	87.02 20	95.00 13	68.15 29	84.11 54	75.62 84	83.12 69	84.95 45

v52		73.95 62	81.43 53	65.22 81	54.85 181	63.32 111	78.90 72	38.00 176	80.00 54	68.32 62	87.02 20	94.98 15	68.14 30	84.11 54	75.63 83	83.12 69	84.96 44

CVMVSNet		60.45 149	63.72 163	56.63 138	54.82 182	53.75 168	68.41 139	41.95 132	55.07 185	48.03 141	58.08 197	68.67 184	55.09 102	69.14 171	68.34 128	71.51 161	72.97 103

FC-MVSNet-test		60.28 150	70.83 134	47.96 187	54.69 183	47.12 194	68.06 140	41.68 137	71.42 92	23.73 222	84.70 38	77.41 157	28.92 208	82.33 68	73.08 96	70.68 170	59.77 165

UGNet		65.61 124	74.79 93	54.91 142	54.54 184	68.20 73	70.97 127	48.21 74	67.14 134	41.67 168	74.15 121	80.65 140	36.10 180	79.39 88	77.99 68	77.95 121	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		59.30 152	64.79 155	52.90 148	54.48 185	50.17 186	64.98 152	36.44 187	60.16 164	50.33 133	76.51 108	74.56 164	44.99 150	62.52 188	62.37 178	66.18 185	67.22 140

FMVSNet3		54.77 180	60.73 180	47.81 189	54.29 186	56.88 147	55.89 195	41.75 134	49.06 210	32.37 192	61.81 181	67.02 186	33.67 199	62.88 186	61.96 181	68.88 180	65.53 146

tfpn_ndepth		51.52 190	57.21 188	44.88 197	54.05 187	52.14 179	53.58 205	37.07 182	55.55 184	24.73 218	47.12 223	56.92 209	28.92 208	69.22 170	64.80 166	70.94 169	54.74 189

CostFormer		52.59 188	55.14 194	49.61 171	52.72 188	50.40 183	66.28 145	33.78 196	52.85 194	43.43 161	66.30 155	51.37 213	41.78 162	54.92 212	51.18 205	59.68 194	58.98 173

HyFIR lowres test		59.15 155	62.28 172	55.49 140	52.42 189	62.59 120	71.76 123	39.74 161	50.25 205	41.92 166	62.88 174	69.16 182	55.85 98	62.77 187	67.18 144	71.27 164	61.11 161

dps		49.71 197	51.97 203	47.07 193	52.37 190	47.00 196	53.02 208	40.52 158	44.91 223	41.23 169	64.55 167	44.27 227	40.12 166	57.71 206	51.97 203	55.14 204	53.41 191

V42		65.79 121	72.11 126	58.42 127	51.89 191	58.69 135	73.80 118	34.50 190	65.40 143	57.10 108	79.54 96	89.09 87	57.51 82	71.98 139	67.83 138	75.70 131	72.26 107

DWT-MVSNet_training		48.57 201	47.93 217	49.31 176	51.79 192	48.05 192	61.84 164	34.33 193	41.94 226	43.42 162	50.35 215	34.74 236	47.30 139	52.62 219	52.08 201	57.20 200	55.74 185

CR-MVSNet		53.82 182	55.40 193	51.98 151	51.57 193	50.23 184	45.00 225	44.97 97	46.90 217	52.60 123	67.91 145	46.99 221	48.37 132	59.15 197	59.53 185	69.38 178	57.07 179

IterMVS		59.24 153	64.45 157	53.16 146	50.98 194	61.29 126	66.51 144	32.85 201	58.17 170	46.31 152	72.58 130	70.23 174	54.26 107	64.81 181	60.24 183	68.04 182	63.81 153
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1111		39.71 224	44.86 228	33.71 222	50.45 195	28.51 231	55.07 198	34.43 191	62.60 153	17.59 231	62.60 175	28.17 238	14.69 228	54.19 215	41.91 222	30.02 232	36.03 225

.test1245		31.52 232	33.91 233	28.73 227	50.45 195	28.51 231	55.07 198	34.43 191	62.60 153	17.59 231	62.60 175	28.17 238	14.69 228	54.19 215	0.54 235	0.15 239	0.77 236

RPMNet		50.92 192	50.32 208	51.62 156	50.25 197	50.23 184	59.16 176	46.70 85	46.90 217	42.39 164	48.97 220	37.23 231	41.78 162	57.30 208	56.18 192	69.44 177	55.43 186

MDTV_nov1_ep13_2view		58.09 159	63.54 165	51.74 154	50.13 198	46.56 198	66.95 143	33.41 198	63.52 149	58.77 103	74.84 118	84.10 129	43.12 156	65.95 177	54.69 196	58.04 198	55.13 187

tpm		46.67 203	49.20 214	43.72 200	49.60 199	36.60 220	53.93 203	26.84 215	52.70 195	58.05 106	69.04 139	47.96 217	30.06 207	48.33 226	42.76 220	43.88 221	47.01 209

TAMVS		46.64 204	53.62 200	38.49 211	49.56 200	36.87 217	53.16 207	25.76 217	56.33 182	22.55 226	60.72 184	61.80 201	27.12 211	59.50 194	58.33 187	52.79 207	41.82 218

PatchmatchNet		48.67 200	50.10 209	46.99 195	48.29 201	41.00 207	55.54 196	38.94 164	51.38 198	45.15 158	63.22 172	48.45 216	42.83 157	53.80 218	48.50 213	51.19 212	44.37 212
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	45.32 18	58.10 158	65.24 152	49.76 169	47.88 202	46.86 197	48.16 222	32.82 202	58.06 171	61.35 96	59.64 190	80.00 141	47.27 140	70.15 165	64.10 171	61.08 192	77.85 76
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		59.77 151	66.07 146	52.42 149	47.81 203	51.86 180	62.98 161	32.28 205	62.08 158	47.10 146	59.94 189	83.42 133	53.08 115	70.06 167	63.19 175	71.26 165	71.96 111

CHOSEN 1792x2688		52.99 186	56.91 189	48.42 185	47.32 204	50.10 187	64.18 156	33.85 195	45.46 222	36.95 174	55.20 207	66.49 189	51.20 119	59.28 195	59.81 184	57.01 201	61.99 159

MVSTER		53.08 185	56.39 190	49.21 179	47.19 205	51.08 181	60.14 171	31.74 207	40.63 228	38.97 171	55.78 204	46.74 222	42.47 159	67.29 174	62.99 177	74.73 136	70.23 118

tpmrst		43.31 216	46.14 221	40.02 210	47.05 206	36.48 221	48.01 223	32.17 206	49.50 208	37.26 173	63.66 171	47.04 218	31.98 206	42.00 233	40.55 224	43.64 222	43.75 214

pmmvs5		50.64 193	58.01 184	42.05 203	47.01 207	43.67 202	49.27 218	29.43 213	50.77 202	33.83 184	68.69 140	76.16 159	27.82 210	57.53 207	57.07 189	64.95 187	52.18 194

MIMVSNet1		56.72 167	68.69 140	42.76 202	46.70 208	42.81 204	69.13 136	30.52 211	81.01 44	32.00 197	74.82 119	91.10 56	26.83 213	73.98 109	64.72 167	51.40 210	52.38 193

MDTV_nov1_ep13		49.60 198	51.57 204	47.31 191	46.28 209	44.61 200	59.82 173	30.96 208	48.80 214	50.20 134	59.26 193	52.38 212	38.56 167	56.20 210	49.70 210	58.04 198	50.01 199

testpf		41.44 219	38.52 232	44.85 198	46.17 210	38.68 213	60.29 169	43.31 113	24.28 235	35.09 178	39.52 231	34.84 235	32.39 204	43.79 232	39.89 226	51.88 208	48.65 205

E-PMN		43.83 215	49.81 211	36.84 215	46.09 211	31.86 228	42.77 229	25.85 216	57.76 175	25.53 215	55.50 205	62.47 198	43.77 154	70.78 161	39.51 227	37.04 228	30.79 230

anonymousdsp		74.76 58	82.59 45	65.63 77	45.61 212	61.13 127	89.06 30	32.58 203	74.11 80	59.55 101	84.06 44	94.12 18	75.24 3	88.94 27	86.95 25	91.74 7	88.81 13

EMVS		43.85 214	49.91 210	36.77 216	45.46 213	32.70 226	44.09 227	25.33 218	57.88 173	26.62 214	58.99 195	61.14 203	42.77 158	70.26 164	38.52 230	36.38 229	29.87 231

MIMVSNet		45.83 207	53.46 202	36.94 214	45.38 214	39.50 210	52.20 209	30.68 209	57.09 178	24.53 220	55.22 206	71.54 170	21.74 219	55.81 211	51.08 206	47.11 217	43.96 213

N_pmnet		39.50 226	51.01 206	26.09 230	44.48 215	25.59 234	40.20 232	21.49 224	64.20 147	7.98 238	73.86 123	76.67 158	13.66 230	50.17 224	36.69 232	28.71 233	29.86 232

EPMVS		40.11 222	44.96 227	34.44 218	41.55 216	32.65 227	41.74 230	32.39 204	49.89 207	24.83 217	64.44 168	46.38 223	26.57 214	44.75 230	39.47 228	39.59 225	37.16 224

test1235678		44.92 210	54.19 196	34.11 219	41.53 217	37.95 214	54.27 201	23.09 221	53.64 186	22.14 227	53.92 209	84.05 130	16.41 226	60.66 191	50.30 208	47.20 215	38.84 222

testmv		44.91 211	54.17 197	34.11 219	41.52 218	37.93 215	54.27 201	23.09 221	53.61 187	22.14 227	53.89 210	84.00 131	16.41 226	60.64 192	50.29 209	47.20 215	38.83 223

MVS-HIRNet		44.56 212	45.52 223	43.44 201	40.98 219	31.03 229	39.52 233	36.96 183	42.80 225	44.37 159	53.80 211	60.04 206	41.85 161	47.97 228	41.08 223	56.99 202	41.95 217

ADS-MVSNet		40.61 220	46.31 219	33.96 221	40.70 220	30.42 230	40.42 231	33.44 197	58.01 172	30.87 205	63.05 173	54.48 210	22.67 218	44.35 231	39.23 229	35.64 230	34.64 226

FMVSNet5		39.83 223	45.08 224	33.71 222	39.24 221	39.56 209	48.77 220	23.55 220	39.45 229	24.55 219	33.73 233	44.57 225	20.97 220	58.27 204	54.23 199	45.16 218	45.77 211

test2356		35.97 227	39.61 231	31.71 225	38.85 222	34.29 223	45.78 224	22.27 223	38.89 232	22.59 225	37.67 232	37.07 232	16.57 225	50.72 223	45.45 217	44.20 219	33.19 227

new_pmnet		35.76 229	45.64 222	24.22 231	38.59 223	25.83 233	31.87 236	19.24 227	49.06 210	9.01 237	54.34 208	64.73 194	12.46 233	49.21 225	44.91 218	34.17 231	31.41 229

no-one		64.33 131	73.23 114	53.94 144	38.32 224	50.78 182	56.78 193	27.44 214	61.95 160	56.77 110	64.60 166	93.12 25	71.12 14	81.91 70	77.19 74	73.20 151	83.04 48

LP		49.44 199	55.77 192	42.05 203	38.31 225	42.61 205	51.74 211	36.31 188	58.35 168	40.36 170	68.52 142	60.77 204	37.08 172	58.27 204	51.76 204	48.51 214	50.13 198

testus		41.61 218	50.54 207	31.20 226	38.11 226	38.92 212	49.10 219	17.60 228	48.25 215	25.05 216	41.45 229	79.34 144	13.18 232	58.28 203	47.10 216	44.17 220	40.41 220

PatchT		50.55 194	53.55 201	47.05 194	37.59 227	42.26 206	50.55 215	37.56 179	46.37 219	52.60 123	66.91 151	43.54 228	48.37 132	59.15 197	59.53 185	55.62 203	57.07 179

MDA-MVSNet-bldmvs		62.46 136	72.13 125	51.19 160	34.32 228	56.10 155	68.65 137	38.85 165	69.05 121	49.50 138	78.17 100	85.43 120	51.32 118	86.67 39	67.40 143	64.46 188	62.08 158

test-mter		44.18 213	47.60 218	40.18 209	33.20 229	39.03 211	55.28 197	13.91 233	39.07 231	36.63 175	48.09 222	49.52 214	41.12 164	54.55 214	50.91 207	60.97 193	52.03 195

test12356		39.53 225	49.18 215	28.26 228	32.93 230	33.64 225	48.68 221	15.96 230	46.26 221	16.21 233	46.46 224	79.07 146	17.13 224	58.60 201	48.30 214	38.67 226	31.96 228

CHOSEN 280x420		40.24 221	44.14 229	35.69 217	32.36 231	23.58 235	50.30 216	21.21 225	40.94 227	18.84 230	32.75 234	48.65 215	48.13 135	59.16 196	55.31 194	43.28 223	48.62 206

TESTMET0.1,1		41.79 217	45.06 225	37.97 212	31.32 232	36.72 218	51.28 212	14.17 232	36.41 233	34.45 182	46.14 225	47.02 219	38.00 168	51.78 220	48.53 211	58.60 195	48.84 203

pmmvs3		46.64 204	54.13 198	37.90 213	31.23 233	40.68 208	49.83 217	15.34 231	46.31 220	36.34 176	53.15 213	74.40 166	36.36 178	58.43 202	56.64 191	58.32 197	49.29 200

PMMVS		45.37 209	49.29 213	40.79 207	27.75 234	35.07 222	50.88 214	19.88 226	39.27 230	35.78 177	50.11 216	61.29 202	42.04 160	54.13 217	55.95 193	68.43 181	49.19 202

PMMVS2		34.11 230	48.55 216	17.26 232	25.45 235	20.72 236	35.08 235	16.26 229	58.71 166	4.16 240	59.22 194	78.40 152	3.65 234	57.24 209	38.31 231	18.94 235	27.28 233

MVE	28.01 19	35.86 228	43.56 230	26.88 229	22.33 236	19.75 237	30.85 237	23.88 219	49.90 206	10.48 236	43.64 228	61.87 200	48.99 131	47.26 229	42.15 221	24.76 234	40.37 221
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				7.47 234	8.89 237	3.32 239	4.35 239	1.14 235	15.58 237	15.76 234	8.50 236	5.90 241	2.00 235	20.02 234	21.51 233	12.70 236

test123		0.53 233	0.60 235	0.46 235	0.22 238	0.25 240	0.33 242	0.13 237	0.66 238	1.37 241	1.10 237	0.00 243	0.43 236	0.68 236	0.61 234	0.26 238	0.88 235

testmvs		0.47 234	0.69 234	0.21 236	0.17 239	0.17 241	0.35 241	0.16 236	0.66 238	0.18 243	1.05 238	0.99 242	0.27 237	0.62 237	0.54 235	0.15 239	0.77 236

GG-mvs-BLEND		31.54 231	46.27 220	14.37 233	0.07 240	48.65 191	42.97 228	0.08 238	44.04 224	1.21 242	39.77 230	57.94 208	0.15 238	48.19 227	42.82 219	41.70 224	42.46 216

sosnet-low-res		0.00 235	0.00 236	0.00 237	0.00 241	0.00 242	0.00 243	0.00 239	0.00 240	0.00 244	0.00 239	0.00 243	0.00 239	0.00 238	0.00 237	0.00 241	0.00 238

sosnet		0.00 235	0.00 236	0.00 237	0.00 241	0.00 242	0.00 243	0.00 239	0.00 240	0.00 244	0.00 239	0.00 243	0.00 239	0.00 238	0.00 237	0.00 241	0.00 238

MTAPA										80.26 8		90.53 72

MTMP										82.07 4		91.00 58

Patchmatch-RL test							2.05 240

NP-MVS									71.39 93

Patchmtry						37.73 216	45.00 225	44.97 97		52.60 123

DeepMVS_CX						8.52 238	9.75 238	3.19 234	16.70 236	5.02 239	23.06 235	19.33 240	18.69 222	13.75 235		11.34 237	25.07 234

High-resolution multi-view benchmark