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.

HSP-MVS		88.32 40	90.71 44	85.53 34	90.63 35	92.01 4	96.15 14	77.52 26	86.02 64	81.39 84	90.21 70	96.08 46	76.38 56	88.30 89	86.70 81	91.12 78	95.64 1

UA-Net		89.02 32	91.44 37	86.20 28	94.88 1	89.84 32	94.76 28	77.45 28	85.41 71	74.79 115	88.83 88	88.90 143	78.67 41	96.06 7	95.45 4	96.66 3	95.58 2

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 103	86.35 62	93.60 35	78.79 17	95.48 4	91.79 2	93.08 25	97.21 23	86.34 3	97.06 2	96.27 3	95.46 23	95.56 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
TDRefinement		93.16 1	95.57 1	90.36 1	88.79 49	93.57 1	97.27 1	78.23 20	95.55 2	93.00 1	93.98 17	96.01 49	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

SMA-MVS		90.37 12	92.54 17	87.83 15	91.78 13	90.56 25	95.35 22	77.47 27	90.80 20	88.51 15	91.24 58	92.22 113	79.16 36	94.32 30	93.72 19	94.75 34	94.93 5

ACMMP_Plus		89.86 19	91.96 29	87.42 20	91.00 29	90.08 29	96.00 17	76.61 35	89.28 34	87.73 18	90.04 71	91.80 121	78.71 39	94.36 29	93.82 18	94.48 36	94.32 6

HFP-MVS		90.32 14	92.37 21	87.94 14	91.46 20	90.91 17	95.69 19	79.49 10	89.94 33	83.50 63	89.06 84	94.44 87	81.68 26	94.17 32	94.19 14	95.81 17	93.87 7

ACMMPR		91.30 4	92.88 10	89.46 4	91.92 11	91.61 5	96.60 5	79.46 12	90.08 30	88.53 14	89.54 77	95.57 61	84.25 7	95.24 20	94.27 13	95.97 11	93.85 8

anonymousdsp		85.62 58	90.53 45	79.88 94	64.64 215	76.35 148	96.28 13	53.53 204	85.63 68	81.59 82	92.81 29	97.71 16	86.88 2	94.56 26	92.83 25	96.35 6	93.84 9

CP-MVS		91.09 5	92.33 22	89.65 2	92.16 10	90.41 26	96.46 10	80.38 6	88.26 43	89.17 11	87.00 104	96.34 38	83.95 10	95.77 11	94.72 8	95.81 17	93.78 10

COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 48	92.86 2	95.51 20	72.17 56	94.95 5	91.27 3	94.11 16	97.77 14	84.22 8	96.49 4	95.27 5	96.79 2	93.60 11
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TSAR-MVS + ACMM		89.14 28	92.11 28	85.67 31	89.27 45	90.61 23	90.98 49	79.48 11	88.86 38	79.80 91	93.01 26	93.53 98	83.17 16	92.75 45	92.45 30	91.32 74	93.59 12

SteuartSystems-ACMMP		90.00 17	91.73 32	87.97 13	91.21 28	90.29 28	96.51 7	78.00 22	86.33 61	85.32 42	88.23 90	94.67 83	82.08 24	95.13 22	93.88 17	94.72 35	93.59 12
Skip Steuart: Steuart Systems R&D Blog.
APDe-MVS		89.85 20	92.91 9	86.29 27	90.47 37	91.34 7	96.04 16	76.41 38	91.11 15	78.50 100	93.44 20	95.82 53	81.55 27	93.16 37	91.90 38	94.77 33	93.58 14

X-MVS		89.36 26	90.73 43	87.77 18	91.50 19	91.23 8	96.76 4	78.88 16	87.29 52	87.14 28	78.98 150	94.53 84	76.47 54	95.25 19	94.28 12	95.85 14	93.55 15

ACMMP		90.63 8	92.40 19	88.56 9	91.24 27	91.60 6	96.49 9	77.53 25	87.89 45	86.87 32	87.24 100	96.46 32	82.87 19	95.59 15	94.50 9	96.35 6	93.51 16
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
ESAPD		89.27 27	91.76 31	86.36 26	90.60 36	90.40 27	95.08 25	77.43 29	87.49 49	80.35 89	92.38 38	94.32 89	80.59 29	92.69 46	91.58 41	94.13 39	93.44 17

CSCG		88.12 43	91.45 36	84.23 46	88.12 57	90.59 24	90.57 56	68.60 79	91.37 13	83.45 65	89.94 72	95.14 74	78.71 39	91.45 56	88.21 68	95.96 12	93.44 17

PGM-MVS		90.42 10	91.58 35	89.05 6	91.77 14	91.06 13	96.51 7	78.94 15	85.41 71	87.67 19	87.02 103	95.26 69	83.62 13	95.01 24	93.94 16	95.79 19	93.40 19

RPSCF		88.05 44	92.61 15	82.73 62	84.24 84	88.40 41	90.04 70	66.29 94	91.46 11	82.29 70	88.93 86	96.01 49	79.38 34	95.15 21	94.90 6	94.15 38	93.40 19

MP-MVS		90.84 6	91.95 30	89.55 3	92.92 5	90.90 18	96.56 6	79.60 9	86.83 57	88.75 13	89.00 85	94.38 88	84.01 9	94.94 25	94.34 11	95.45 24	93.24 21

SD-MVS		89.91 18	92.23 26	87.19 22	91.31 23	89.79 33	94.31 31	75.34 43	89.26 35	81.79 77	92.68 30	95.08 75	83.88 11	93.10 38	92.69 26	96.54 4	93.02 22

TSAR-MVS + MP.		89.67 23	92.25 24	86.65 25	91.53 17	90.98 16	96.15 14	73.30 53	87.88 46	81.83 76	92.92 28	95.15 73	82.23 22	93.58 34	92.25 34	94.87 30	93.01 23

ACMM	80.67 7	90.67 7	92.46 18	88.57 8	91.35 21	89.93 31	96.34 12	77.36 31	90.17 28	86.88 31	87.32 98	96.63 28	83.32 14	95.79 10	94.49 10	96.19 9	92.91 24
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LGP-MVS_train		90.56 9	92.38 20	88.43 10	90.88 31	91.15 11	95.35 22	77.65 24	86.26 63	87.23 25	90.45 69	97.35 20	83.20 15	95.44 16	93.41 21	96.28 8	92.63 25

DeepC-MVS	83.59 4	90.37 12	92.56 16	87.82 16	91.26 26	92.33 3	94.72 29	80.04 7	90.01 31	84.61 45	93.33 21	94.22 90	80.59 29	92.90 41	92.52 29	95.69 21	92.57 26
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		86.29 54	89.10 55	83.01 55	85.71 73	89.79 33	87.04 113	74.39 48	85.17 73	78.92 98	77.59 157	93.57 96	82.60 20	93.23 36	91.88 39	89.42 94	92.46 27

CPTT-MVS		89.63 24	90.52 46	88.59 7	90.95 30	90.74 20	95.71 18	79.13 13	87.70 47	85.68 40	80.05 146	95.74 56	84.77 6	94.28 31	92.68 27	95.28 26	92.45 28

APD-MVS		89.14 28	91.25 40	86.67 24	91.73 15	91.02 15	95.50 21	77.74 23	84.04 83	79.47 95	91.48 49	94.85 80	81.14 28	92.94 40	92.20 36	94.47 37	92.24 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMP	80.00 8	90.12 16	92.30 23	87.58 19	90.83 33	91.10 12	94.96 27	76.06 39	87.47 50	85.33 41	88.91 87	97.65 18	82.13 23	95.31 17	93.44 20	96.14 10	92.22 30
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
3Dnovator+	83.71 3	88.13 42	90.00 49	85.94 29	86.82 64	91.06 13	94.26 32	75.39 42	88.85 39	85.76 39	85.74 116	86.92 153	78.02 44	93.03 39	92.21 35	95.39 25	92.21 31

DeepPCF-MVS	81.61 6	87.95 45	90.29 48	85.22 38	87.48 60	90.01 30	93.79 33	73.54 51	88.93 37	83.89 54	89.40 79	90.84 130	80.26 33	90.62 72	90.19 50	92.36 63	92.03 32

zzz-MVS		90.38 11	91.35 38	89.25 5	93.08 3	86.59 59	96.45 11	79.00 14	90.23 27	89.30 10	85.87 114	94.97 79	82.54 21	95.05 23	94.83 7	95.14 27	91.94 33

SixPastTwentyTwo		89.14 28	92.19 27	85.58 32	84.62 79	82.56 85	90.53 61	71.93 57	91.95 10	85.89 37	94.22 14	97.25 22	85.42 5	95.73 12	91.71 40	95.08 28	91.89 34

HPM-MVS++		88.74 38	89.54 52	87.80 17	92.58 7	85.69 67	95.10 24	78.01 21	87.08 54	87.66 20	87.89 93	92.07 117	80.28 32	90.97 68	91.41 42	93.17 51	91.69 35

OMC-MVS		88.16 41	91.34 39	84.46 44	86.85 63	90.63 22	93.01 39	67.00 90	90.35 26	87.40 22	86.86 106	96.35 37	77.66 47	92.63 47	90.84 43	94.84 31	91.68 36

v52		86.26 55	90.85 41	80.91 74	72.49 189	81.25 104	90.55 58	60.30 171	90.43 25	87.24 23	94.64 11	98.30 10	83.16 18	92.86 43	86.82 79	91.69 69	91.65 37

V4		86.26 55	90.85 41	80.91 74	72.49 189	81.25 104	90.55 58	60.31 170	90.44 24	87.23 25	94.64 11	98.31 9	83.17 16	92.87 42	86.82 79	91.69 69	91.64 38

CNVR-MVS		86.93 48	88.98 56	84.54 42	90.11 39	87.41 53	93.23 38	73.47 52	86.31 62	82.25 71	82.96 132	92.15 115	76.04 59	91.69 52	90.69 44	92.17 65	91.64 38

OPM-MVS		89.82 21	92.24 25	86.99 23	90.86 32	89.35 35	95.07 26	75.91 40	91.16 14	86.87 32	91.07 61	97.29 21	79.13 37	93.32 35	91.99 37	94.12 40	91.49 40

LS3D		89.02 32	91.69 33	85.91 30	89.72 42	90.81 19	92.56 42	71.69 58	90.83 19	87.24 23	89.71 75	92.07 117	78.37 42	94.43 28	92.59 28	95.86 13	91.35 41

NCCC		86.74 49	87.97 68	85.31 36	90.64 34	87.25 54	93.27 37	74.59 46	86.50 59	83.72 56	75.92 177	92.39 111	77.08 51	91.72 51	90.68 45	92.57 61	91.30 42

DeepC-MVS_fast	81.78 5	87.38 46	89.64 50	84.75 39	89.89 41	90.70 21	92.74 41	74.45 47	86.02 64	82.16 74	86.05 112	91.99 120	75.84 62	91.16 61	90.44 46	93.41 46	91.09 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PMVS	79.51 9	90.23 15	92.67 12	87.39 21	90.16 38	88.75 39	93.64 34	75.78 41	90.00 32	83.70 57	92.97 27	92.22 113	86.13 4	97.01 3	96.79 2	94.94 29	90.96 44
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
HQP-MVS		85.02 66	86.41 79	83.40 51	89.19 46	86.59 59	91.28 47	71.60 59	82.79 91	83.48 64	78.65 153	93.54 97	72.55 99	86.49 102	85.89 88	92.28 64	90.95 45

WR-MVS_H		88.99 34	93.28 5	83.99 50	91.92 11	89.13 37	91.95 44	83.23 1	90.14 29	71.92 131	95.85 4	98.01 13	71.83 104	95.82 9	93.19 23	93.07 53	90.83 46

ACMH+	79.05 11	89.62 25	93.08 7	85.58 32	88.58 51	89.26 36	92.18 43	74.23 49	93.55 7	82.66 68	92.32 40	98.35 8	80.29 31	95.28 18	92.34 32	95.52 22	90.43 47

Vis-MVSNet		83.32 84	88.12 66	77.71 115	77.91 163	83.44 79	90.58 55	69.49 70	81.11 117	67.10 154	89.85 73	91.48 125	71.71 105	91.34 57	89.37 58	89.48 93	90.26 48
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
no-one		78.59 131	85.28 95	70.79 149	59.01 222	68.77 187	76.62 177	46.06 215	80.25 123	75.75 109	81.85 138	97.75 15	83.63 12	90.99 67	87.20 73	83.67 174	90.14 49

PS-CasMVS		89.07 31	93.23 6	84.21 47	92.44 8	88.23 45	90.54 60	82.95 3	90.50 22	75.31 112	95.80 5	98.37 7	71.16 107	96.30 5	93.32 22	92.88 55	90.11 50

TAPA-MVS	78.00 13	85.88 57	88.37 61	82.96 57	84.69 78	88.62 40	90.62 54	64.22 126	89.15 36	88.05 16	78.83 151	93.71 93	76.20 58	90.11 76	88.22 67	94.00 41	89.97 51
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMH	78.40 12	88.94 36	92.62 14	84.65 40	86.45 66	87.16 55	91.47 46	68.79 77	95.49 3	89.74 6	93.55 19	98.50 3	77.96 45	94.14 33	89.57 57	93.49 44	89.94 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		86.66 51	88.52 59	84.48 43	89.61 43	88.27 43	92.86 40	72.69 55	80.55 121	82.71 67	86.92 105	93.32 100	75.55 64	91.00 66	89.85 52	93.47 45	89.71 53

CP-MVSNet		88.71 39	92.63 13	84.13 48	92.39 9	88.09 47	90.47 65	82.86 4	88.79 40	75.16 113	94.87 7	97.68 17	71.05 109	96.16 6	93.18 24	92.85 56	89.64 54

TSAR-MVS + GP.		85.32 62	87.41 73	82.89 59	90.07 40	85.69 67	89.07 78	72.99 54	82.45 95	74.52 118	85.09 122	87.67 150	79.24 35	91.11 62	90.41 47	91.45 72	89.45 55

WR-MVS		89.79 22	93.66 4	85.27 37	91.32 22	88.27 43	93.49 36	79.86 8	92.75 8	75.37 111	96.86 1	98.38 6	75.10 67	95.93 8	94.07 15	96.46 5	89.39 56

MCST-MVS		84.79 69	86.48 77	82.83 60	87.30 61	87.03 57	90.46 66	69.33 73	83.14 87	82.21 73	81.69 140	92.14 116	75.09 68	87.27 96	84.78 97	92.58 59	89.30 57

canonicalmvs		81.22 118	86.04 86	75.60 126	83.17 104	83.18 80	80.29 149	65.82 103	85.97 66	67.98 152	77.74 156	91.51 124	65.17 137	88.62 85	86.15 85	91.17 77	89.09 58

train_agg		86.67 50	87.73 69	85.43 35	91.51 18	82.72 82	94.47 30	74.22 50	81.71 105	81.54 83	89.20 83	92.87 104	78.33 43	90.12 75	88.47 64	92.51 62	89.04 59

PHI-MVS		86.37 53	88.14 65	84.30 45	86.65 65	87.56 51	90.76 53	70.16 65	82.55 93	89.65 7	84.89 124	92.40 110	75.97 60	90.88 70	89.70 54	92.58 59	89.03 60

CNLPA		85.50 60	88.58 57	81.91 65	84.55 81	87.52 52	90.89 51	63.56 135	88.18 44	84.06 50	83.85 129	91.34 127	76.46 55	91.27 58	89.00 62	91.96 66	88.88 61

PEN-MVS		88.86 37	92.92 8	84.11 49	92.92 5	88.05 48	90.83 52	82.67 5	91.04 16	74.83 114	95.97 3	98.47 4	70.38 114	95.70 13	92.43 31	93.05 54	88.78 62

v748		85.21 64	89.62 51	80.08 93	80.71 132	80.27 117	85.05 126	63.79 133	90.47 23	83.54 62	94.21 15	98.52 2	76.84 53	90.97 68	84.25 101	90.53 82	88.62 63

PCF-MVS	76.59 14	84.11 74	85.27 96	82.76 61	86.12 69	88.30 42	91.24 48	69.10 74	82.36 97	84.45 46	77.56 158	90.40 134	72.91 98	85.88 109	83.88 104	92.72 58	88.53 64
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v7n		87.11 47	90.46 47	83.19 53	85.22 75	83.69 76	90.03 71	68.20 84	91.01 17	86.71 35	94.80 8	98.46 5	77.69 46	91.10 63	85.98 86	91.30 75	88.19 65

QAPM		80.43 120	84.34 110	75.86 124	79.40 146	82.06 89	79.86 154	61.94 162	83.28 85	74.73 117	81.74 139	85.44 158	70.97 110	84.99 125	84.71 98	88.29 108	88.14 66

3Dnovator	79.41 10	82.21 102	86.07 85	77.71 115	79.31 147	84.61 70	87.18 108	61.02 167	85.65 67	76.11 106	85.07 123	85.38 159	70.96 111	87.22 97	86.47 82	91.66 71	88.12 67

MVS_0304		84.73 70	86.19 82	83.02 54	88.32 53	86.71 58	91.55 45	70.87 62	73.79 163	82.88 66	85.13 121	93.35 99	72.55 99	88.62 85	87.69 70	91.93 67	88.05 68

DTE-MVSNet		88.99 34	92.77 11	84.59 41	93.31 2	88.10 46	90.96 50	83.09 2	91.38 12	76.21 105	96.03 2	98.04 11	70.78 113	95.65 14	92.32 33	93.18 50	87.84 69

Anonymous20231211		85.16 65	91.64 34	77.61 117	88.54 52	79.81 120	83.12 134	74.68 45	98.37 1	66.79 156	94.56 13	99.60 1	61.64 150	91.49 55	89.82 53	90.91 79	87.80 70

TSAR-MVS + COLMAP		85.51 59	88.36 62	82.19 63	86.05 70	87.69 50	90.50 63	70.60 64	86.40 60	82.33 69	89.69 76	92.52 108	74.01 82	87.53 93	86.84 78	89.63 90	87.80 70

MAR-MVS		81.98 107	82.92 132	80.88 77	85.18 76	85.85 64	89.13 77	69.52 68	71.21 175	82.25 71	71.28 199	88.89 144	69.69 116	88.71 84	86.96 74	89.52 92	87.57 72
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
EPP-MVSNet		82.76 95	86.47 78	78.45 111	86.00 71	84.47 71	85.39 122	68.42 81	84.17 80	62.97 165	89.26 82	76.84 186	72.13 102	92.56 48	90.40 48	95.76 20	87.56 73

PVSNet_Blended_VisFu		83.00 91	84.16 118	81.65 68	82.17 122	86.01 63	88.03 90	71.23 60	76.05 155	79.54 94	83.88 128	83.44 162	77.49 49	87.38 94	84.93 96	91.41 73	87.40 74

ambc			88.38 60		91.62 16	87.97 49	84.48 130		88.64 42	87.93 17	87.38 97	94.82 82	74.53 73	89.14 82	83.86 106	85.94 159	86.84 75

PLC	76.06 15	85.38 61	87.46 71	82.95 58	85.79 72	88.84 38	88.86 80	68.70 78	87.06 55	83.60 59	79.02 149	90.05 135	77.37 50	90.88 70	89.66 55	93.37 47	86.74 76
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
AdaColmap		84.15 73	85.14 99	83.00 56	89.08 47	87.14 56	90.56 57	70.90 61	82.40 96	80.41 87	73.82 189	84.69 161	75.19 66	91.58 54	89.90 51	91.87 68	86.48 77

UGNet		79.62 125	85.91 88	72.28 141	73.52 183	83.91 73	86.64 116	69.51 69	79.85 127	62.57 167	85.82 115	89.63 136	53.18 187	88.39 88	87.35 71	88.28 109	86.43 78
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
OpenMVS	75.38 16	78.44 132	81.39 139	74.99 130	80.46 134	79.85 119	79.99 151	58.31 184	77.34 147	73.85 121	77.19 162	82.33 169	68.60 124	84.67 128	81.95 124	88.72 100	86.40 79

abl_6				79.30 102	84.98 77	85.78 65	90.50 63	66.88 91	77.08 149	74.02 120	73.29 192	89.34 138	68.94 122			90.49 83	85.98 80

CMPMVS	55.74 18	71.56 176	76.26 168	66.08 190	68.11 205	63.91 201	63.17 226	50.52 213	68.79 184	75.49 110	70.78 206	85.67 156	63.54 144	81.58 163	77.20 174	75.63 191	85.86 81
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CANet		82.84 93	84.60 107	80.78 78	87.30 61	85.20 69	90.23 68	69.00 75	72.16 171	78.73 99	84.49 126	90.70 132	69.54 119	87.65 92	86.17 84	89.87 88	85.84 82

EG-PatchMatch MVS		84.35 72	87.55 70	80.62 86	86.38 67	82.24 87	86.75 115	64.02 130	84.24 79	78.17 102	89.38 80	95.03 77	78.78 38	89.95 77	86.33 83	89.59 91	85.65 83

FPMVS		81.56 114	84.04 119	78.66 109	82.92 107	75.96 154	86.48 118	65.66 105	84.67 76	71.47 133	77.78 155	83.22 164	77.57 48	91.24 59	90.21 49	87.84 120	85.21 84

EPNet		79.36 127	79.44 144	79.27 103	89.51 44	77.20 138	88.35 86	77.35 32	68.27 185	74.29 119	76.31 167	79.22 175	59.63 155	85.02 124	85.45 91	86.49 148	84.61 85
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_111021_HR		83.95 75	86.10 84	81.44 70	84.62 79	80.29 116	90.51 62	68.05 85	84.07 82	80.38 88	84.74 125	91.37 126	74.23 76	90.37 74	87.25 72	90.86 81	84.59 86

Effi-MVS+-dtu		82.04 106	83.39 130	80.48 89	85.48 74	86.57 61	88.40 85	68.28 83	69.04 183	73.13 125	76.26 169	91.11 129	74.74 71	88.40 87	87.76 69	92.84 57	84.57 87

IterMVS-LS		79.79 122	82.56 134	76.56 123	81.83 126	77.85 131	79.90 153	69.42 72	78.93 138	71.21 134	90.47 68	85.20 160	70.86 112	80.54 171	80.57 136	86.15 152	84.36 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v13		83.75 77	86.20 81	80.89 76	83.38 97	81.93 90	88.58 83	66.09 97	83.55 84	84.28 47	92.67 31	96.79 26	74.67 72	84.42 131	79.72 146	88.36 106	84.31 89

MVS_111021_LR		83.20 88	85.33 94	80.73 82	82.88 108	78.23 128	89.61 72	65.23 112	82.08 100	81.19 85	85.31 119	92.04 119	75.22 65	89.50 78	85.90 87	90.24 84	84.23 90

Effi-MVS+		82.33 98	83.87 124	80.52 88	84.51 82	81.32 100	87.53 99	68.05 85	74.94 160	79.67 93	82.37 136	92.31 112	72.21 101	85.06 118	86.91 76	91.18 76	84.20 91

v10		83.17 89	85.22 98	80.78 78	83.26 101	82.99 81	88.66 81	66.49 93	79.24 136	83.60 59	91.46 51	95.47 64	74.12 77	82.60 152	80.66 134	88.53 103	84.11 92

UniMVSNet (Re)		84.95 67	88.53 58	80.78 78	87.82 59	84.21 72	88.03 90	76.50 36	81.18 116	69.29 141	92.63 34	96.83 25	69.07 121	91.23 60	89.60 56	93.97 42	84.00 93

v12		83.59 79	86.00 87	80.77 81	83.30 99	81.83 91	88.45 84	65.95 100	83.20 86	84.15 48	92.54 36	96.71 27	74.50 74	84.19 133	79.64 147	88.30 107	83.93 94

Gipuma		86.47 52	89.25 54	83.23 52	83.88 90	78.78 124	85.35 123	68.42 81	92.69 9	89.03 12	91.94 43	96.32 40	81.80 25	94.45 27	86.86 77	90.91 79	83.69 95
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v11		83.30 85	85.58 92	80.64 84	83.53 94	81.74 93	88.30 87	65.46 109	82.75 92	84.63 44	92.49 37	96.17 44	73.90 83	82.69 150	79.59 148	88.04 115	83.66 96

DELS-MVS		79.71 123	83.74 126	75.01 129	79.31 147	82.68 83	84.79 128	60.06 174	75.43 158	69.09 143	86.13 110	89.38 137	67.16 130	85.12 117	83.87 105	89.65 89	83.57 97
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
V9		83.42 83	85.81 89	80.63 85	83.20 102	81.73 94	88.29 88	65.78 104	82.87 90	83.99 53	92.38 38	96.60 29	74.30 75	83.93 134	79.58 149	88.24 110	83.55 98

CVMVSNet		75.65 148	77.62 156	73.35 138	71.95 193	69.89 180	83.04 137	60.84 169	69.12 181	68.76 146	79.92 147	78.93 177	73.64 86	81.02 167	81.01 132	81.86 182	83.43 99

IS_MVSNet		81.72 112	85.01 100	77.90 114	86.19 68	82.64 84	85.56 120	70.02 66	80.11 125	63.52 162	87.28 99	81.18 171	67.26 129	91.08 65	89.33 59	94.82 32	83.42 100

Fast-Effi-MVS+		81.42 115	83.82 125	78.62 110	82.24 121	80.62 109	87.72 94	63.51 136	73.01 164	74.75 116	83.80 130	92.70 106	73.44 87	88.15 91	85.26 92	90.05 85	83.17 101

V14		83.23 86	85.59 91	80.48 89	83.09 105	81.63 96	88.13 89	65.61 106	82.53 94	83.81 55	92.17 41	96.50 30	74.07 80	83.66 136	79.51 151	88.17 112	83.16 102

EU-MVSNet		76.48 141	80.53 141	71.75 142	67.62 206	70.30 178	81.74 142	54.06 200	75.47 157	71.01 136	80.10 144	93.17 103	73.67 85	83.73 135	77.85 168	82.40 180	83.07 103

UniMVSNet_NR-MVSNet		84.62 71	88.00 67	80.68 83	88.18 56	83.83 74	87.06 111	76.47 37	81.46 111	70.49 137	93.24 22	95.56 63	68.13 125	90.43 73	88.47 64	93.78 43	83.02 104

DU-MVS		84.88 68	88.27 64	80.92 73	88.30 54	83.59 77	87.06 111	78.35 18	80.64 119	70.49 137	92.67 31	96.91 24	68.13 125	91.79 49	89.29 60	93.20 49	83.02 104

v1240		83.57 80	84.94 103	81.97 64	84.05 86	81.27 103	89.46 75	66.06 98	81.31 115	87.50 21	91.88 45	95.46 66	76.25 57	81.16 166	80.51 138	88.52 104	82.98 106

TranMVSNet+NR-MVSNet		85.23 63	89.38 53	80.39 91	88.78 50	83.77 75	87.40 101	76.75 33	85.47 69	68.99 144	95.18 6	97.55 19	67.13 131	91.61 53	89.13 61	93.26 48	82.95 107

v1921920		83.49 81	84.94 103	81.80 66	83.78 91	81.20 107	89.50 74	65.91 101	81.64 107	87.18 27	91.70 47	95.39 67	75.85 61	81.56 164	80.27 141	88.60 102	82.80 108

v15		83.06 90	85.39 93	80.35 92	83.01 106	81.53 98	87.98 92	65.47 108	82.19 99	83.66 58	92.00 42	96.40 36	73.87 84	83.39 138	79.44 152	88.10 114	82.76 109

NR-MVSNet		82.89 92	87.43 72	77.59 118	83.91 89	83.59 77	87.10 110	78.35 18	80.64 119	68.85 145	92.67 31	96.50 30	54.19 180	87.19 99	88.68 63	93.16 52	82.75 110

v144192		83.43 82	84.97 102	81.63 69	83.43 95	81.23 106	89.42 76	66.04 99	81.45 112	86.40 36	91.46 51	95.70 60	75.76 63	82.14 157	80.23 142	88.74 99	82.57 111

v1192		83.61 78	85.23 97	81.72 67	84.05 86	82.15 88	89.54 73	66.20 95	81.38 113	86.76 34	91.79 46	96.03 48	74.88 70	81.81 161	80.92 133	88.91 98	82.50 112

FMVSNet1		78.20 134	84.83 105	70.46 153	78.62 153	79.03 122	77.90 166	67.53 89	83.02 88	55.10 180	87.19 101	93.18 102	55.65 172	85.57 110	83.39 109	87.98 116	82.40 113

IB-MVS	71.28 17	75.21 149	77.00 162	73.12 139	76.76 172	77.45 134	83.05 136	58.92 180	63.01 210	64.31 161	59.99 228	87.57 151	68.64 123	86.26 106	82.34 123	87.05 141	82.36 114
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
v17		82.09 105	84.45 109	79.33 101	82.41 114	81.31 101	87.26 102	64.50 123	78.72 139	80.73 86	90.90 65	95.57 61	73.37 88	83.06 139	79.25 156	87.70 126	82.35 115

v16		81.92 108	84.32 111	79.12 107	82.31 119	81.29 102	87.20 107	64.51 122	78.16 143	79.76 92	90.86 66	95.23 70	73.29 93	83.05 140	79.29 155	87.63 127	82.34 116

v8		82.20 103	84.56 108	79.45 99	82.42 113	81.65 95	87.26 102	64.27 124	79.36 132	81.70 78	91.04 64	95.75 55	73.30 92	82.82 146	79.18 160	87.74 122	82.09 117

Baseline_NR-MVSNet		82.79 94	86.51 76	78.44 112	88.30 54	75.62 159	87.81 93	74.97 44	81.53 109	66.84 155	94.71 10	96.46 32	66.90 132	91.79 49	83.37 112	85.83 161	82.09 117

FC-MVSNet-train		79.20 129	86.29 80	70.94 148	84.06 85	77.67 132	85.68 119	64.11 129	82.90 89	52.22 196	92.57 35	93.69 94	49.52 204	88.30 89	86.93 75	90.03 86	81.95 119

v18		81.62 113	83.99 120	78.86 108	82.08 123	81.12 108	86.93 114	64.24 125	77.44 145	79.47 95	90.53 67	94.99 78	72.99 97	82.72 149	79.18 160	87.48 130	81.91 120

V42		79.59 126	83.59 128	74.93 131	69.61 201	77.05 141	86.59 117	55.84 193	78.42 142	77.29 103	89.84 74	95.08 75	74.12 77	83.05 140	80.11 144	86.12 153	81.59 121

v1144		83.22 87	85.01 100	81.14 71	83.76 92	81.60 97	88.95 79	65.58 107	81.89 101	85.80 38	91.68 48	95.84 52	74.04 81	82.12 158	80.56 137	88.70 101	81.41 122

v7		82.76 95	84.65 106	80.55 87	83.27 100	81.77 92	88.66 81	65.10 113	79.23 137	83.60 59	91.47 50	95.47 64	74.12 77	82.61 151	80.66 134	88.52 104	81.35 123

PM-MVS		80.42 121	83.63 127	76.67 121	78.04 158	72.37 174	87.14 109	60.18 173	80.13 124	71.75 132	86.12 111	93.92 92	77.08 51	86.56 101	85.12 94	85.83 161	81.18 124

TinyColmap		83.79 76	86.12 83	81.07 72	83.42 96	81.44 99	85.42 121	68.55 80	88.71 41	89.46 8	87.60 95	92.72 105	70.34 115	89.29 80	81.94 125	89.20 95	81.12 125

CLD-MVS		82.75 97	87.22 74	77.54 119	88.01 58	85.76 66	90.23 68	54.52 197	82.28 98	82.11 75	88.48 89	95.27 68	63.95 141	89.41 79	88.29 66	86.45 149	81.01 126
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSDG		81.39 116	84.23 117	78.09 113	82.40 118	82.47 86	85.31 125	60.91 168	79.73 128	80.26 90	86.30 109	88.27 148	69.67 117	87.20 98	84.98 95	89.97 87	80.67 127

pmmvs6		80.46 119	88.34 63	71.26 143	81.96 124	77.51 133	77.54 167	68.83 76	93.72 6	55.92 177	93.94 18	98.03 12	55.94 170	89.21 81	85.61 89	87.36 134	80.38 128

GBi-Net		73.17 162	77.64 154	67.95 173	76.76 172	77.36 135	75.77 187	64.57 119	62.99 211	51.83 197	76.05 173	77.76 181	52.73 191	85.57 110	83.39 109	86.04 156	80.37 129

test1		73.17 162	77.64 154	67.95 173	76.76 172	77.36 135	75.77 187	64.57 119	62.99 211	51.83 197	76.05 173	77.76 181	52.73 191	85.57 110	83.39 109	86.04 156	80.37 129

FMVSNet2		74.43 153	79.70 142	68.27 168	76.76 172	77.36 135	75.77 187	65.36 111	72.28 169	52.97 190	81.92 137	85.61 157	52.73 191	80.66 170	79.73 145	86.04 156	80.37 129

MVS_Test		76.72 139	79.40 145	73.60 135	78.85 152	74.99 161	79.91 152	61.56 164	69.67 179	72.44 126	85.98 113	90.78 131	63.50 145	78.30 177	75.74 180	85.33 166	80.31 132

MVSTER		68.08 190	69.73 191	66.16 188	66.33 213	70.06 179	75.71 190	52.36 207	55.18 229	58.64 171	70.23 209	56.72 221	57.34 163	79.68 173	76.03 178	86.61 145	80.20 133

CANet_DTU		75.04 150	78.45 147	71.07 144	77.27 168	77.96 129	83.88 133	58.00 185	64.11 206	68.67 148	75.65 179	88.37 147	53.92 182	82.05 159	81.11 130	84.67 170	79.88 134

TransMVSNet (Re)		79.05 130	86.66 75	70.18 156	83.32 98	75.99 153	77.54 167	63.98 131	90.68 21	55.84 178	94.80 8	96.06 47	53.73 186	86.27 105	83.22 113	86.65 143	79.61 135

FMVSNet3		71.40 178	75.20 177	66.97 182	75.00 180	76.59 143	74.29 193	64.57 119	62.99 211	51.83 197	76.05 173	77.76 181	51.49 201	76.58 185	77.03 175	84.62 171	79.43 136

v1neww		81.76 110	83.95 122	79.21 105	82.41 114	80.46 110	87.26 102	62.93 145	79.28 134	81.62 80	91.06 62	95.72 58	73.31 90	82.83 144	79.22 157	87.73 123	79.07 137

v7new		81.76 110	83.95 122	79.21 105	82.41 114	80.46 110	87.26 102	62.93 145	79.28 134	81.62 80	91.06 62	95.72 58	73.31 90	82.83 144	79.22 157	87.73 123	79.07 137

v6		81.77 109	83.96 121	79.22 104	82.41 114	80.45 112	87.26 102	62.91 149	79.29 133	81.65 79	91.08 60	95.74 56	73.32 89	82.84 143	79.21 159	87.73 123	79.07 137

v1		82.27 99	84.32 111	79.87 95	82.86 109	80.32 113	87.57 98	63.47 139	81.87 103	84.13 49	91.34 53	96.29 41	73.23 94	82.39 153	79.08 163	87.94 117	78.98 140

v1141		82.26 100	84.32 111	79.85 96	82.86 109	80.31 114	87.58 96	63.48 137	81.86 104	84.03 52	91.33 54	96.28 42	73.23 94	82.39 153	79.08 163	87.93 118	78.97 141

divwei89l23v2f112		82.26 100	84.32 111	79.85 96	82.86 109	80.31 114	87.58 96	63.48 137	81.88 102	84.05 51	91.33 54	96.27 43	73.23 94	82.39 153	79.08 163	87.93 118	78.97 141

v2v482		82.20 103	84.26 115	79.81 98	82.67 112	80.18 118	87.67 95	63.96 132	81.69 106	84.73 43	91.27 57	96.33 39	72.05 103	81.94 160	79.56 150	87.79 121	78.84 143

DI_MVS_plusplus_trai		77.64 135	79.64 143	75.31 128	79.87 142	76.89 142	81.55 144	63.64 134	76.21 154	72.03 130	85.59 118	82.97 165	66.63 133	79.27 174	77.78 169	88.14 113	78.76 144

PVSNet_BlendedMVS		76.45 142	78.12 150	74.49 132	76.76 172	78.46 125	79.65 156	63.26 142	65.42 201	73.15 123	75.05 183	88.96 141	66.51 135	82.73 147	77.66 170	87.61 128	78.60 145

PVSNet_Blended		76.45 142	78.12 150	74.49 132	76.76 172	78.46 125	79.65 156	63.26 142	65.42 201	73.15 123	75.05 183	88.96 141	66.51 135	82.73 147	77.66 170	87.61 128	78.60 145

diffmvs		73.65 156	77.10 160	69.63 160	73.21 184	69.52 182	79.35 160	57.48 186	73.80 162	68.08 151	87.10 102	82.39 167	61.36 151	74.27 191	74.51 182	78.31 189	78.14 147

pm-mvs1		78.21 133	85.68 90	69.50 162	80.38 135	75.73 157	76.25 182	65.04 114	87.59 48	54.47 183	93.16 24	95.99 51	54.20 179	86.37 103	82.98 115	86.64 144	77.96 148

conf0.05thres1000		77.12 137	82.38 135	70.98 146	82.30 120	77.95 130	79.86 154	64.74 118	86.63 58	53.93 184	85.74 116	75.63 196	56.85 164	88.98 83	84.10 102	88.20 111	77.61 149

USDC		81.39 116	83.07 131	79.43 100	81.48 128	78.95 123	82.62 138	66.17 96	87.45 51	90.73 4	82.40 135	93.65 95	66.57 134	83.63 137	77.97 167	89.00 97	77.45 150

v148		79.33 128	82.32 136	75.84 125	80.14 137	75.74 156	81.98 141	57.06 189	81.51 110	79.36 97	89.42 78	96.42 34	71.32 106	81.54 165	75.29 181	85.20 167	76.32 151

pmmvs-eth3d		79.64 124	82.06 137	76.83 120	80.05 138	72.64 172	87.47 100	66.59 92	80.83 118	73.50 122	89.32 81	93.20 101	67.78 127	80.78 169	81.64 127	85.58 164	76.01 152

MS-PatchMatch		71.18 179	73.99 181	67.89 177	77.16 169	71.76 175	77.18 170	56.38 192	67.35 187	55.04 181	74.63 185	75.70 191	62.38 149	76.62 184	75.97 179	79.22 186	75.90 153

Fast-Effi-MVS+-dtu		76.92 138	77.18 159	76.62 122	79.55 144	79.17 121	84.80 127	77.40 30	64.46 205	68.75 147	70.81 205	86.57 154	63.36 147	81.74 162	81.76 126	85.86 160	75.78 154

tfpnnormal		77.16 136	84.26 115	68.88 165	81.02 131	75.02 160	76.52 179	63.30 141	87.29 52	52.40 194	91.24 58	93.97 91	54.85 178	85.46 113	81.08 131	85.18 168	75.76 155

EPNet_dtu		71.90 174	73.03 184	70.59 151	78.28 155	61.64 204	82.44 139	64.12 128	63.26 209	69.74 139	71.47 197	82.41 166	51.89 200	78.83 176	78.01 166	77.07 190	75.60 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GA-MVS		75.01 151	76.39 167	73.39 136	78.37 154	75.66 158	80.03 150	58.40 183	70.51 177	75.85 108	83.24 131	76.14 190	63.75 142	77.28 181	76.62 176	83.97 173	75.30 157

FC-MVSNet-test		75.91 147	83.59 128	66.95 183	76.63 178	69.07 184	85.33 124	64.97 116	84.87 75	41.95 218	93.17 23	87.04 152	47.78 207	91.09 64	85.56 90	85.06 169	74.34 158

tfpn		72.99 166	75.25 175	70.36 154	81.87 125	77.09 140	79.28 161	64.16 127	79.58 130	53.14 188	76.97 164	48.75 230	56.35 168	87.31 95	82.75 117	87.35 135	74.31 159

thres600view7		74.34 154	78.43 148	69.56 161	80.47 133	76.28 149	78.65 164	62.56 154	77.39 146	52.53 192	74.03 188	76.78 187	55.90 171	85.06 118	85.19 93	87.25 138	74.29 160

IterMVS		73.62 157	76.53 166	70.23 155	71.83 194	77.18 139	80.69 148	53.22 205	72.23 170	66.62 157	85.21 120	78.96 176	69.54 119	76.28 187	71.63 190	79.45 185	74.25 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
view800		74.68 152	78.74 146	69.94 157	81.12 130	76.59 143	78.94 163	63.24 144	78.56 141	53.06 189	75.61 180	76.26 189	56.07 169	86.32 104	83.75 107	87.18 140	74.10 162

tfpn111		71.60 175	74.66 178	68.04 171	77.97 159	76.44 145	77.04 171	62.68 150	66.81 191	50.69 203	62.10 223	75.67 192	52.46 195	85.06 118	82.64 118	87.42 131	73.87 163

conf200view11		72.00 173	75.40 173	68.04 171	77.97 159	76.44 145	77.04 171	62.68 150	66.81 191	50.69 203	67.30 212	75.67 192	52.46 195	85.06 118	82.64 118	87.42 131	73.87 163

tfpn200view9		72.01 172	75.40 173	68.06 170	77.97 159	76.44 145	77.04 171	62.67 152	66.81 191	50.82 201	67.30 212	75.67 192	52.46 195	85.06 118	82.64 118	87.41 133	73.86 165

pmmvs4		75.92 146	77.48 157	74.10 134	78.21 157	70.94 176	84.06 131	64.78 117	75.13 159	68.47 149	84.12 127	83.32 163	64.74 140	75.93 188	79.14 162	84.31 172	73.77 166

view600		74.08 155	78.15 149	69.32 163	80.27 136	75.82 155	78.27 165	62.20 158	77.26 148	52.80 191	74.07 187	76.86 185	55.57 174	84.90 126	84.43 100	86.84 142	73.71 167

MDA-MVSNet-bldmvs		76.51 140	82.87 133	69.09 164	50.71 233	74.72 164	84.05 132	60.27 172	81.62 108	71.16 135	88.21 91	91.58 122	69.62 118	92.78 44	77.48 172	78.75 188	73.69 168

thres400		73.13 164	76.99 163	68.62 166	79.46 145	74.93 162	77.23 169	61.23 165	75.54 156	52.31 195	72.20 194	77.10 184	54.89 176	82.92 142	82.62 122	86.57 146	73.66 169

PatchMatch-RL		76.05 145	76.64 165	75.36 127	77.84 164	69.87 181	81.09 146	63.43 140	71.66 173	68.34 150	71.70 195	81.76 170	74.98 69	84.83 127	83.44 108	86.45 149	73.22 170

CHOSEN 1792x2688		68.80 185	71.09 187	66.13 189	69.11 203	68.89 186	78.98 162	54.68 195	61.63 217	56.69 174	71.56 196	78.39 179	67.69 128	72.13 203	72.01 189	69.63 207	73.02 171

tfpn_n400		73.26 160	77.94 152	67.79 178	79.91 140	73.32 167	76.38 180	62.04 159	84.26 77	48.53 208	76.23 170	71.50 203	53.83 183	86.22 107	81.59 128	86.05 154	72.47 172

tfpnconf		73.26 160	77.94 152	67.79 178	79.91 140	73.32 167	76.38 180	62.04 159	84.26 77	48.53 208	76.23 170	71.50 203	53.83 183	86.22 107	81.59 128	86.05 154	72.47 172

conf0.01		69.59 182	71.01 188	67.95 173	77.74 165	76.09 151	77.04 171	62.58 153	66.81 191	50.54 205	63.00 221	51.78 229	52.46 195	84.53 129	82.64 118	87.32 136	72.19 174

thres200		72.41 170	76.00 171	68.21 169	78.28 155	76.28 149	74.94 192	62.56 154	72.14 172	51.35 200	69.59 210	76.51 188	54.89 176	85.06 118	80.51 138	87.25 138	71.92 175

conf0.002		68.60 186	69.17 193	67.92 176	77.66 166	76.01 152	77.04 171	62.56 154	66.81 191	50.51 206	61.21 226	44.01 234	52.46 195	84.44 130	80.29 140	87.31 137	71.44 176

Vis-MVSNet (Re-imp)		76.15 144	80.84 140	70.68 150	83.66 93	74.80 163	81.66 143	69.59 67	80.48 122	46.94 212	87.44 96	80.63 173	53.14 188	86.87 100	84.56 99	89.12 96	71.12 177

tfpn1000		72.27 171	76.88 164	66.88 184	79.01 151	74.04 165	76.60 178	61.15 166	79.65 129	45.52 214	77.41 160	67.98 209	52.47 194	85.22 116	82.99 114	86.54 147	70.89 178

thres100view900		69.86 181	72.97 185	66.24 187	77.97 159	72.49 173	73.29 197	59.12 178	66.81 191	50.82 201	67.30 212	75.67 192	50.54 203	78.24 178	79.40 153	85.71 163	70.88 179

tfpnview11		72.88 168	77.37 158	67.65 180	79.81 143	73.43 166	76.23 183	61.97 161	81.37 114	48.53 208	76.23 170	71.50 203	53.78 185	85.45 114	82.77 116	85.56 165	70.87 180

HyFIR lowres test		73.29 159	74.14 180	72.30 140	73.08 185	78.33 127	83.12 134	62.41 157	63.81 207	62.13 168	76.67 166	78.50 178	71.09 108	74.13 192	77.47 173	81.98 181	70.10 181

CDS-MVSNet		73.07 165	77.02 161	68.46 167	81.62 127	72.89 171	79.56 158	70.78 63	69.56 180	52.52 193	77.37 161	81.12 172	42.60 213	84.20 132	83.93 103	83.65 175	70.07 182
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		66.81 193	66.94 200	66.67 185	72.79 187	68.25 188	79.55 159	55.57 194	65.52 200	62.77 166	76.98 163	60.09 215	56.73 166	65.69 222	62.35 210	72.59 197	69.71 183

tfpn_ndepth		68.20 188	72.18 186	63.55 197	74.64 181	73.24 169	72.41 200	59.76 176	70.54 176	41.93 219	60.96 227	68.69 208	46.23 209	82.16 156	80.14 143	86.34 151	69.56 184

CR-MVSNet		69.56 183	68.34 198	70.99 145	72.78 188	67.63 189	64.47 223	67.74 87	59.93 220	72.30 127	80.10 144	56.77 220	65.04 138	71.64 205	72.91 186	83.61 178	69.40 185

PatchT		66.25 195	66.76 201	65.67 193	55.87 227	60.75 206	70.17 207	59.00 179	59.80 222	72.30 127	78.68 152	54.12 225	65.04 138	71.64 205	72.91 186	71.63 201	69.40 185

MIMVSNet1		73.40 158	81.85 138	63.55 197	72.90 186	64.37 199	84.58 129	53.60 203	90.84 18	53.92 185	87.75 94	96.10 45	45.31 210	85.37 115	79.32 154	70.98 204	69.18 187

RPMNet		67.02 192	63.99 210	70.56 152	71.55 196	67.63 189	75.81 185	69.44 71	59.93 220	63.24 163	64.32 217	47.51 231	59.68 154	70.37 209	69.64 196	83.64 176	68.49 188

tpmp4_e23		68.32 187	66.04 202	70.98 146	77.52 167	69.23 183	80.99 147	65.46 109	68.09 186	69.25 142	70.77 207	54.03 226	59.35 156	69.01 212	63.02 209	73.34 196	68.15 189

pmmvs5		68.91 184	74.35 179	62.56 200	67.45 208	66.78 193	71.70 202	51.47 210	67.17 190	56.25 176	82.41 134	88.59 145	47.21 208	73.21 201	74.23 183	81.30 183	68.03 190

DWT-MVSNet_training		63.07 201	60.04 223	66.61 186	71.64 195	65.27 197	76.80 176	53.82 201	55.90 226	63.07 164	62.23 222	41.87 236	62.54 148	64.32 225	63.71 207	71.78 198	66.97 191

thresconf0.02		66.71 194	68.28 199	64.89 196	76.83 171	70.38 177	71.62 204	58.90 181	77.64 144	47.04 211	62.10 223	46.01 232	51.32 202	78.85 175	76.09 177	83.62 177	66.85 192

gg-mvs-nofinetune		72.68 169	75.21 176	69.73 159	81.48 128	69.04 185	70.48 206	76.67 34	86.92 56	67.80 153	88.06 92	64.67 211	42.12 215	77.60 179	73.65 184	79.81 184	66.57 193

MDTV_nov1_ep13_2view		72.96 167	75.59 172	69.88 158	71.15 198	64.86 198	82.31 140	54.45 198	76.30 153	78.32 101	86.52 107	91.58 122	61.35 152	76.80 182	66.83 202	71.70 199	66.26 194

test-mter		59.39 214	61.59 218	56.82 210	53.21 228	54.82 216	73.12 199	26.57 233	53.19 230	56.31 175	64.71 215	60.47 214	56.36 167	68.69 213	64.27 206	75.38 192	65.00 195

dps		65.14 197	64.50 208	65.89 192	71.41 197	65.81 196	71.44 205	61.59 163	58.56 223	61.43 169	75.45 181	52.70 228	58.06 161	69.57 211	64.65 205	71.39 202	64.77 196

LP		65.71 196	69.91 190	60.81 204	56.75 226	61.37 205	69.55 213	56.80 190	73.01 164	60.48 170	79.76 148	70.57 206	55.47 175	72.77 202	67.19 201	65.81 214	64.71 197

testgi		68.20 188	76.05 170	59.04 206	79.99 139	67.32 192	81.16 145	51.78 209	84.91 74	39.36 226	73.42 190	95.19 71	32.79 223	76.54 186	70.40 193	69.14 208	64.55 198

tpm cat1		64.79 200	62.74 216	67.17 181	74.61 182	65.91 195	76.18 184	59.32 177	64.88 204	66.41 158	71.21 200	53.56 227	59.17 157	61.53 228	58.16 221	67.33 211	63.95 199

PMMVS		61.98 208	65.61 204	57.74 208	45.03 234	51.76 225	69.54 214	35.05 226	55.49 228	55.32 179	68.23 211	78.39 179	58.09 160	70.21 210	71.56 191	83.42 179	63.66 200

tpm		62.79 204	63.25 213	62.26 201	70.09 200	53.78 218	71.65 203	47.31 214	65.72 199	76.70 104	80.62 141	56.40 223	48.11 206	64.20 226	58.54 219	59.70 223	63.47 201

test20.03		69.91 180	76.20 169	62.58 199	84.01 88	67.34 191	75.67 191	65.88 102	79.98 126	40.28 223	82.65 133	89.31 139	39.63 217	77.41 180	73.28 185	69.98 205	63.40 202

Anonymous20231206		67.28 191	73.41 183	60.12 205	76.45 179	63.61 202	74.21 194	56.52 191	76.35 152	42.23 217	75.81 178	90.47 133	41.51 216	74.52 189	69.97 195	69.83 206	63.17 203

CHOSEN 280x420		56.32 222	58.85 229	53.36 217	51.63 230	39.91 235	69.12 217	38.61 225	56.29 225	36.79 229	48.84 233	62.59 213	63.39 146	73.61 198	67.66 199	60.61 221	63.07 204

pmmvs3		62.72 205	68.71 195	55.74 212	50.74 232	57.10 211	70.05 208	28.82 231	61.57 219	57.39 173	71.19 201	85.73 155	53.96 181	73.36 200	69.43 197	73.47 195	62.55 205

FMVSNet5		56.37 221	60.14 222	51.98 220	60.83 219	59.58 207	66.85 221	42.37 219	52.68 231	41.33 221	47.09 234	54.68 224	35.28 220	73.88 193	70.77 192	65.24 215	62.26 206

test-LLR		62.15 207	59.46 227	65.29 194	79.07 149	52.66 221	69.46 215	62.93 145	50.76 233	53.81 186	63.11 219	58.91 217	52.87 189	66.54 220	62.34 211	73.59 193	61.87 207

TESTMET0.1,1		57.21 218	59.46 227	54.60 216	50.95 231	52.66 221	69.46 215	26.91 232	50.76 233	53.81 186	63.11 219	58.91 217	52.87 189	66.54 220	62.34 211	73.59 193	61.87 207

MDTV_nov1_ep13		64.96 198	64.77 207	65.18 195	67.08 209	62.46 203	75.80 186	51.10 212	62.27 216	69.74 139	74.12 186	62.65 212	55.64 173	68.19 214	62.16 214	71.70 199	61.57 209

gm-plane-assit		71.56 176	69.99 189	73.39 136	84.43 83	73.21 170	90.42 67	51.36 211	84.08 81	76.00 107	91.30 56	37.09 237	59.01 158	73.65 197	70.24 194	79.09 187	60.37 210

testpf		55.64 223	50.84 232	61.24 202	67.03 210	54.45 217	72.29 201	65.04 114	37.23 235	54.99 182	53.99 230	43.12 235	44.34 211	55.22 233	51.59 231	63.76 218	60.25 211

MIMVSNet		63.02 202	69.02 194	56.01 211	68.20 204	59.26 208	70.01 209	53.79 202	71.56 174	41.26 222	71.38 198	82.38 168	36.38 219	71.43 207	67.32 200	66.45 213	59.83 212

test0.0.03 1		61.79 209	65.33 205	57.65 209	79.07 149	64.09 200	68.51 219	62.93 145	61.59 218	33.71 230	61.58 225	71.58 202	33.43 222	70.95 208	68.68 198	68.26 210	58.82 213

new-patchmatchnet		62.59 206	73.79 182	49.53 224	76.98 170	53.57 219	53.46 234	54.64 196	85.43 70	28.81 234	91.94 43	96.41 35	25.28 231	76.80 182	53.66 228	57.99 225	58.69 214

PatchmatchNet		64.81 199	63.74 212	66.06 191	69.21 202	58.62 209	73.16 198	60.01 175	65.92 197	66.19 159	76.27 168	59.09 216	60.45 153	66.58 219	61.47 217	67.33 211	58.24 215
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		59.42 213	60.02 224	58.71 207	67.56 207	53.10 220	66.99 220	51.88 208	63.80 208	57.68 172	76.73 165	56.49 222	48.73 205	56.47 232	55.55 224	59.43 224	58.02 216

TAMVS		63.02 202	69.30 192	55.70 213	70.12 199	56.89 212	69.63 212	45.13 216	70.23 178	38.00 228	77.79 154	75.15 197	42.60 213	74.48 190	72.81 188	68.70 209	57.75 217

MVE	41.12 19	51.80 228	60.92 220	41.16 230	35.21 236	34.14 237	48.45 237	41.39 222	69.11 182	19.53 236	63.33 218	73.80 198	63.56 143	67.19 217	61.51 216	38.85 234	57.38 218
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND		41.63 232	60.36 221	19.78 233	0.14 240	66.04 194	55.66 233	0.17 238	57.64 224	2.42 241	51.82 232	69.42 207	0.28 238	64.11 227	58.29 220	60.02 222	55.18 219

testus		57.41 217	64.98 206	48.58 226	59.39 221	57.17 210	68.81 218	32.86 228	62.32 215	43.25 216	57.59 229	88.49 146	24.19 232	71.68 204	63.20 208	62.99 219	54.42 220

EPMVS		56.62 220	59.77 225	52.94 218	62.41 216	50.55 226	60.66 228	52.83 206	65.15 203	41.80 220	77.46 159	57.28 219	42.68 212	59.81 230	54.82 225	57.23 226	53.35 221

MVS-HIRNet		59.74 212	58.74 230	60.92 203	57.74 225	45.81 232	56.02 232	58.69 182	55.69 227	65.17 160	70.86 204	71.66 200	56.75 165	61.11 229	53.74 227	71.17 203	52.28 222

test1235678		60.73 210	68.46 196	51.71 221	61.76 217	56.73 214	73.40 195	42.24 220	67.34 188	39.55 224	70.90 202	92.54 107	28.75 226	73.84 194	66.00 203	64.57 216	51.90 223

testmv		60.72 211	68.44 197	51.71 221	61.76 217	56.70 215	73.40 195	42.24 220	67.31 189	39.54 225	70.88 203	92.49 109	28.75 226	73.83 195	66.00 203	64.56 217	51.89 224

ADS-MVSNet		56.89 219	61.09 219	52.00 219	59.48 220	48.10 230	58.02 230	54.37 199	72.82 167	49.19 207	75.32 182	65.97 210	37.96 218	59.34 231	54.66 226	52.99 231	51.42 225

1111		55.38 224	59.51 226	50.57 223	72.41 191	48.16 228	69.76 210	57.08 187	76.79 150	32.10 231	80.12 142	35.41 238	25.87 228	67.23 215	57.74 222	46.17 233	51.09 226

new_pmnet		52.29 227	63.16 214	39.61 231	58.89 223	44.70 233	48.78 236	34.73 227	65.88 198	17.85 237	73.42 190	80.00 174	23.06 233	67.00 218	62.28 213	54.36 228	48.81 227

N_pmnet		54.95 225	65.90 203	42.18 229	66.37 212	43.86 234	57.92 231	39.79 224	79.54 131	17.24 238	86.31 108	87.91 149	25.44 230	64.68 223	51.76 230	46.33 232	47.23 228

test2356		51.28 229	53.40 231	48.80 225	58.53 224	52.10 223	63.63 225	40.83 223	51.94 232	39.35 227	53.46 231	45.22 233	28.78 225	64.39 224	60.77 218	61.70 220	45.92 229

DeepMVS_CX						17.78 238	20.40 238	6.69 234	31.41 236	9.80 239	38.61 235	34.88 240	33.78 221	28.41 235		23.59 236	45.77 230

test12356		54.63 226	63.78 211	43.96 227	51.77 229	51.90 224	65.92 222	30.12 229	62.44 214	30.38 233	64.65 216	89.07 140	30.62 224	73.53 199	62.11 215	54.92 227	42.78 231

E-PMN		59.07 215	62.79 215	54.72 214	67.01 211	47.81 231	60.44 229	43.40 217	72.95 166	44.63 215	70.42 208	73.17 199	58.73 159	80.97 168	51.98 229	54.14 229	42.26 232

EMVS		58.97 216	62.63 217	54.70 215	66.26 214	48.71 227	61.74 227	42.71 218	72.80 168	46.00 213	73.01 193	71.66 200	57.91 162	80.41 172	50.68 232	53.55 230	41.11 233

PMMVS2		48.13 230	64.06 209	29.55 232	44.06 235	36.69 236	51.95 235	29.97 230	74.75 161	8.90 240	76.02 176	91.24 128	7.53 234	73.78 196	55.91 223	34.87 235	40.01 234

.test1245		43.71 231	44.35 233	42.95 228	72.41 191	48.16 228	69.76 210	57.08 187	76.79 150	32.10 231	80.12 142	35.41 238	25.87 228	67.23 215	1.08 235	0.48 238	1.68 235

testmvs		0.93 234	1.37 235	0.41 236	0.36 239	0.36 241	0.62 241	0.39 236	1.48 238	0.18 243	2.41 237	1.31 243	0.41 237	1.25 237	1.08 235	0.48 238	1.68 235

test123		1.06 233	1.41 234	0.64 235	0.39 238	0.48 240	0.52 242	0.25 237	1.11 239	1.37 242	2.01 238	1.98 242	0.87 236	1.43 236	1.27 234	0.46 240	1.62 237

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	0.00 244	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	0.00 244	0.00 239	0.00 238	0.00 237	0.00 241	0.00 238

MTAPA										89.37 9		94.85 80

MTMP										90.54 5		95.16 72

Patchmatch-RL test							4.13 240

tmp_tt				13.54 234	16.73 237	6.42 239	8.49 239	2.36 235	28.69 237	27.44 235	18.40 236	13.51 241	3.70 235	33.23 234	36.26 233	22.54 237

XVS					91.28 24	91.23 8	96.89 2			87.14 28		94.53 84				95.84 15

X-MVStestdata					91.28 24	91.23 8	96.89 2			87.14 28		94.53 84				95.84 15

mPP-MVS					93.05 4							95.77 54

NP-MVS									78.65 140

Patchmtry						56.88 213	64.47 223	67.74 87		72.30 127

High-resolution multi-view benchmark