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		89.02 32	91.44 36	86.20 29	94.88 1	89.84 33	94.76 29	77.45 27	85.41 71	74.79 118	88.83 89	88.90 151	78.67 42	96.06 7	95.45 4	96.66 3	95.58 2

DTE-MVSNet		88.99 34	92.77 11	84.59 42	93.31 2	88.10 47	90.96 51	83.09 2	91.38 11	76.21 108	96.03 2	98.04 10	70.78 117	95.65 14	92.32 33	93.18 51	87.84 69

zzz-MVS		90.38 11	91.35 37	89.25 5	93.08 3	86.59 60	96.45 11	79.00 14	90.23 26	89.30 10	85.87 118	94.97 79	82.54 21	95.05 23	94.83 7	95.14 27	91.94 33

mPP-MVS					93.05 4							95.77 53

MP-MVS		90.84 6	91.95 31	89.55 3	92.92 5	90.90 19	96.56 6	79.60 9	86.83 57	88.75 13	89.00 86	94.38 90	84.01 9	94.94 25	94.34 11	95.45 24	93.24 21
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		88.86 37	92.92 8	84.11 50	92.92 5	88.05 49	90.83 53	82.67 5	91.04 15	74.83 117	95.97 3	98.47 3	70.38 118	95.70 13	92.43 31	93.05 55	88.78 62

HPM-MVS++		88.74 38	89.54 51	87.80 16	92.58 7	85.69 68	95.10 25	78.01 21	87.08 54	87.66 20	87.89 97	92.07 123	80.28 33	90.97 68	91.41 43	93.17 52	91.69 35

PS-CasMVS		89.07 31	93.23 6	84.21 48	92.44 8	88.23 46	90.54 61	82.95 3	90.50 21	75.31 115	95.80 5	98.37 6	71.16 111	96.30 5	93.32 22	92.88 56	90.11 50

CP-MVSNet		88.71 39	92.63 13	84.13 49	92.39 9	88.09 48	90.47 66	82.86 4	88.79 39	75.16 116	94.87 7	97.68 16	71.05 113	96.16 6	93.18 24	92.85 57	89.64 54

CP-MVS		91.09 5	92.33 22	89.65 2	92.16 10	90.41 27	96.46 10	80.38 6	88.26 42	89.17 11	87.00 107	96.34 37	83.95 10	95.77 11	94.72 8	95.81 17	93.78 10

ACMMPR		91.30 4	92.88 10	89.46 4	91.92 11	91.61 5	96.60 5	79.46 12	90.08 29	88.53 14	89.54 78	95.57 60	84.25 7	95.24 20	94.27 13	95.97 11	93.85 8

WR-MVS_H		88.99 34	93.28 5	83.99 51	91.92 11	89.13 38	91.95 45	83.23 1	90.14 28	71.92 135	95.85 4	98.01 12	71.83 108	95.82 9	93.19 23	93.07 54	90.83 46

PGM-MVS		90.42 10	91.58 34	89.05 6	91.77 13	91.06 13	96.51 7	78.94 15	85.41 71	87.67 19	87.02 106	95.26 68	83.62 13	95.01 24	93.94 16	95.79 19	93.40 19

APD-MVS		89.14 28	91.25 39	86.67 25	91.73 14	91.02 15	95.50 22	77.74 23	84.04 84	79.47 96	91.48 49	94.85 80	81.14 28	92.94 40	92.20 36	94.47 38	92.24 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		90.13 15	92.26 24	87.64 18	91.68 15	90.44 26	95.22 24	77.34 32	90.79 19	87.80 17	90.42 70	92.05 125	79.05 38	93.89 33	93.59 19	94.77 33	94.62 5

ambc			88.38 59		91.62 16	87.97 50	84.48 134		88.64 41	87.93 16	87.38 101	94.82 82	74.53 75	89.14 82	83.86 110	85.94 167	86.84 74

TSAR-MVS + MP.		89.67 24	92.25 25	86.65 26	91.53 17	90.98 17	96.15 14	73.30 53	87.88 46	81.83 77	92.92 28	95.15 73	82.23 22	93.58 34	92.25 34	94.87 30	93.01 23

train_agg		86.67 50	87.73 68	85.43 36	91.51 18	82.72 85	94.47 31	74.22 50	81.71 109	81.54 84	89.20 84	92.87 109	78.33 44	90.12 75	88.47 64	92.51 64	89.04 59

X-MVS		89.36 27	90.73 42	87.77 17	91.50 19	91.23 8	96.76 4	78.88 16	87.29 52	87.14 28	78.98 158	94.53 85	76.47 55	95.25 19	94.28 12	95.85 14	93.55 16

HFP-MVS		90.32 13	92.37 20	87.94 14	91.46 20	90.91 18	95.69 19	79.49 10	89.94 32	83.50 63	89.06 85	94.44 88	81.68 26	94.17 31	94.19 14	95.81 17	93.87 7

ACMM	80.67 7	90.67 7	92.46 17	88.57 8	91.35 21	89.93 32	96.34 12	77.36 30	90.17 27	86.88 31	87.32 102	96.63 27	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
WR-MVS		89.79 23	93.66 4	85.27 38	91.32 22	88.27 44	93.49 37	79.86 8	92.75 7	75.37 114	96.86 1	98.38 5	75.10 69	95.93 8	94.07 15	96.46 5	89.39 56

SD-MVS		89.91 18	92.23 27	87.19 22	91.31 23	89.79 34	94.31 32	75.34 44	89.26 34	81.79 78	92.68 30	95.08 75	83.88 11	93.10 38	92.69 26	96.54 4	93.02 22

XVS					91.28 24	91.23 8	96.89 2			87.14 28		94.53 85				95.84 15

X-MVStestdata					91.28 24	91.23 8	96.89 2			87.14 28		94.53 85				95.84 15

DeepC-MVS	83.59 4	90.37 12	92.56 16	87.82 15	91.26 26	92.33 3	94.72 30	80.04 7	90.01 30	84.61 45	93.33 21	94.22 92	80.59 30	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
ACMMP		90.63 8	92.40 18	88.56 9	91.24 27	91.60 6	96.49 9	77.53 25	87.89 45	86.87 32	87.24 104	96.46 31	82.87 19	95.59 15	94.50 9	96.35 6	93.51 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
SteuartSystems-ACMMP		90.00 17	91.73 32	87.97 13	91.21 28	90.29 29	96.51 7	78.00 22	86.33 61	85.32 42	88.23 93	94.67 83	82.08 24	95.13 22	93.88 17	94.72 35	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_Plus		89.86 19	91.96 30	87.42 20	91.00 29	90.08 30	96.00 17	76.61 36	89.28 33	87.73 18	90.04 72	91.80 128	78.71 40	94.36 29	93.82 18	94.48 37	94.32 6

CPTT-MVS		89.63 25	90.52 45	88.59 7	90.95 30	90.74 21	95.71 18	79.13 13	87.70 47	85.68 40	80.05 152	95.74 55	84.77 6	94.28 30	92.68 27	95.28 26	92.45 28

LGP-MVS_train		90.56 9	92.38 19	88.43 10	90.88 31	91.15 11	95.35 23	77.65 24	86.26 63	87.23 25	90.45 69	97.35 19	83.20 15	95.44 16	93.41 21	96.28 8	92.63 25

OPM-MVS		89.82 21	92.24 26	86.99 23	90.86 32	89.35 36	95.07 27	75.91 41	91.16 13	86.87 32	91.07 60	97.29 20	79.13 37	93.32 35	91.99 38	94.12 41	91.49 40

ACMP	80.00 8	90.12 16	92.30 23	87.58 19	90.83 33	91.10 12	94.96 28	76.06 40	87.47 50	85.33 41	88.91 88	97.65 17	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
NCCC		86.74 49	87.97 67	85.31 37	90.64 34	87.25 55	93.27 38	74.59 46	86.50 59	83.72 56	75.92 186	92.39 118	77.08 52	91.72 52	90.68 46	92.57 62	91.30 42

HSP-MVS		88.32 40	90.71 43	85.53 35	90.63 35	92.01 4	96.15 14	77.52 26	86.02 64	81.39 85	90.21 71	96.08 45	76.38 57	88.30 90	86.70 81	91.12 82	95.64 1

v1.0		82.08 106	78.41 156	86.36 27	90.60 36	90.40 28	95.08 26	77.43 28	87.49 49	80.35 90	92.38 38	94.32 91	80.59 30	92.69 47	91.58 42	94.13 40	0.00 246

APDe-MVS		89.85 20	92.91 9	86.29 28	90.47 37	91.34 7	96.04 16	76.41 39	91.11 14	78.50 102	93.44 20	95.82 52	81.55 27	93.16 37	91.90 39	94.77 33	93.58 15

PMVS	79.51 9	90.23 14	92.67 12	87.39 21	90.16 38	88.75 40	93.64 35	75.78 42	90.00 31	83.70 57	92.97 27	92.22 120	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)
CNVR-MVS		86.93 48	88.98 55	84.54 43	90.11 39	87.41 54	93.23 39	73.47 52	86.31 62	82.25 72	82.96 137	92.15 121	76.04 60	91.69 53	90.69 45	92.17 67	91.64 38

TSAR-MVS + GP.		85.32 62	87.41 72	82.89 60	90.07 40	85.69 68	89.07 81	72.99 54	82.45 98	74.52 121	85.09 126	87.67 158	79.24 36	91.11 62	90.41 48	91.45 75	89.45 55

DeepC-MVS_fast	81.78 5	87.38 46	89.64 49	84.75 40	89.89 41	90.70 22	92.74 42	74.45 47	86.02 64	82.16 75	86.05 116	91.99 127	75.84 63	91.16 61	90.44 47	93.41 47	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
LS3D		89.02 32	91.69 33	85.91 31	89.72 42	90.81 20	92.56 43	71.69 58	90.83 18	87.24 23	89.71 76	92.07 123	78.37 43	94.43 28	92.59 28	95.86 13	91.35 41

ESAPD		89.81 22	92.34 21	86.86 24	89.69 43	91.00 16	95.53 20	76.91 33	88.18 43	83.43 66	93.48 19	95.19 70	81.07 29	92.75 45	92.07 37	94.55 36	93.74 11

CDPH-MVS		86.66 51	88.52 58	84.48 44	89.61 44	88.27 44	92.86 41	72.69 55	80.55 127	82.71 68	86.92 108	93.32 105	75.55 65	91.00 66	89.85 53	93.47 46	89.71 53

EPNet		79.36 132	79.44 151	79.27 106	89.51 45	77.20 144	88.35 89	77.35 31	68.27 194	74.29 122	76.31 176	79.22 182	59.63 161	85.02 128	85.45 92	86.49 156	84.61 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + ACMM		89.14 28	92.11 29	85.67 32	89.27 46	90.61 24	90.98 50	79.48 11	88.86 37	79.80 92	93.01 26	93.53 103	83.17 16	92.75 45	92.45 30	91.32 77	93.59 13

HQP-MVS		85.02 65	86.41 78	83.40 52	89.19 47	86.59 60	91.28 48	71.60 59	82.79 94	83.48 64	78.65 162	93.54 102	72.55 101	86.49 105	85.89 89	92.28 66	90.95 45

AdaColmap		84.15 72	85.14 100	83.00 57	89.08 48	87.14 57	90.56 58	70.90 61	82.40 99	80.41 88	73.82 198	84.69 169	75.19 68	91.58 55	89.90 52	91.87 70	86.48 76

COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 49	92.86 2	95.51 21	72.17 56	94.95 4	91.27 3	94.11 15	97.77 13	84.22 8	96.49 4	95.27 5	96.79 2	93.60 12
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TDRefinement		93.16 1	95.57 1	90.36 1	88.79 50	93.57 1	97.27 1	78.23 20	95.55 1	93.00 1	93.98 16	96.01 48	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

TranMVSNet+NR-MVSNet		85.23 63	89.38 52	80.39 92	88.78 51	83.77 76	87.40 104	76.75 34	85.47 69	68.99 152	95.18 6	97.55 18	67.13 137	91.61 54	89.13 61	93.26 49	82.95 114

ACMH+	79.05 11	89.62 26	93.08 7	85.58 33	88.58 52	89.26 37	92.18 44	74.23 49	93.55 6	82.66 69	92.32 40	98.35 7	80.29 32	95.28 18	92.34 32	95.52 22	90.43 47

MVS_0304		84.73 69	86.19 81	83.02 55	88.32 53	86.71 59	91.55 46	70.87 62	73.79 168	82.88 67	85.13 125	93.35 104	72.55 101	88.62 86	87.69 70	91.93 69	88.05 68

DU-MVS		84.88 67	88.27 63	80.92 74	88.30 54	83.59 79	87.06 114	78.35 18	80.64 125	70.49 141	92.67 31	96.91 23	68.13 131	91.79 50	89.29 60	93.20 50	83.02 111

Baseline_NR-MVSNet		82.79 93	86.51 75	78.44 115	88.30 54	75.62 166	87.81 96	74.97 45	81.53 113	66.84 162	94.71 10	96.46 31	66.90 138	91.79 50	83.37 116	85.83 169	82.09 124

UniMVSNet_NR-MVSNet		84.62 70	88.00 66	80.68 84	88.18 56	83.83 75	87.06 114	76.47 38	81.46 115	70.49 141	93.24 22	95.56 62	68.13 131	90.43 73	88.47 64	93.78 44	83.02 111

CSCG		88.12 43	91.45 35	84.23 47	88.12 57	90.59 25	90.57 57	68.60 79	91.37 12	83.45 65	89.94 73	95.14 74	78.71 40	91.45 56	88.21 68	95.96 12	93.44 18

CLD-MVS		82.75 96	87.22 73	77.54 121	88.01 58	85.76 67	90.23 70	54.52 206	82.28 101	82.11 76	88.48 92	95.27 67	63.95 148	89.41 79	88.29 66	86.45 157	81.01 133
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet (Re)		84.95 66	88.53 57	80.78 79	87.82 59	84.21 73	88.03 93	76.50 37	81.18 120	69.29 149	92.63 34	96.83 24	69.07 127	91.23 60	89.60 56	93.97 43	84.00 99

DeepPCF-MVS	81.61 6	87.95 45	90.29 47	85.22 39	87.48 60	90.01 31	93.79 34	73.54 51	88.93 36	83.89 54	89.40 80	90.84 137	80.26 34	90.62 72	90.19 51	92.36 65	92.03 32

CANet		82.84 92	84.60 109	80.78 79	87.30 61	85.20 70	90.23 70	69.00 75	72.16 178	78.73 101	84.49 131	90.70 139	69.54 125	87.65 93	86.17 84	89.87 93	85.84 81

MCST-MVS		84.79 68	86.48 76	82.83 61	87.30 61	87.03 58	90.46 67	69.33 73	83.14 89	82.21 74	81.69 146	92.14 122	75.09 70	87.27 98	84.78 98	92.58 60	89.30 57

OMC-MVS		88.16 41	91.34 38	84.46 45	86.85 63	90.63 23	93.01 40	67.00 92	90.35 25	87.40 22	86.86 109	96.35 36	77.66 48	92.63 48	90.84 44	94.84 31	91.68 36

3Dnovator+	83.71 3	88.13 42	90.00 48	85.94 30	86.82 64	91.06 13	94.26 33	75.39 43	88.85 38	85.76 39	85.74 120	86.92 161	78.02 45	93.03 39	92.21 35	95.39 25	92.21 31

PHI-MVS		86.37 53	88.14 64	84.30 46	86.65 65	87.56 52	90.76 54	70.16 65	82.55 96	89.65 7	84.89 129	92.40 117	75.97 61	90.88 70	89.70 54	92.58 60	89.03 60

ACMH	78.40 12	88.94 36	92.62 14	84.65 41	86.45 66	87.16 56	91.47 47	68.79 77	95.49 2	89.74 6	93.55 18	98.50 2	77.96 46	94.14 32	89.57 57	93.49 45	89.94 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		84.35 71	87.55 69	80.62 87	86.38 67	82.24 90	86.75 118	64.02 134	84.24 80	78.17 104	89.38 81	95.03 77	78.78 39	89.95 77	86.33 83	89.59 96	85.65 83

IS_MVSNet		81.72 113	85.01 101	77.90 117	86.19 68	82.64 87	85.56 123	70.02 66	80.11 131	63.52 168	87.28 103	81.18 178	67.26 135	91.08 65	89.33 59	94.82 32	83.42 107

PCF-MVS	76.59 14	84.11 73	85.27 97	82.76 62	86.12 69	88.30 43	91.24 49	69.10 74	82.36 100	84.45 46	77.56 167	90.40 141	72.91 100	85.88 113	83.88 108	92.72 59	88.53 64
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		85.51 59	88.36 61	82.19 64	86.05 70	87.69 51	90.50 64	70.60 64	86.40 60	82.33 70	89.69 77	92.52 114	74.01 84	87.53 94	86.84 78	89.63 95	87.80 70

EPP-MVSNet		82.76 94	86.47 77	78.45 114	86.00 71	84.47 72	85.39 125	68.42 82	84.17 81	62.97 171	89.26 83	76.84 193	72.13 106	92.56 49	90.40 49	95.76 20	87.56 72

casdiffmvs1		82.28 98	84.49 111	79.70 100	85.87 72	83.66 78	90.32 69	65.29 115	83.11 90	78.97 99	86.09 115	93.86 96	70.23 120	81.79 168	77.87 175	87.52 137	85.07 86

PLC	76.06 15	85.38 61	87.46 70	82.95 59	85.79 73	88.84 39	88.86 83	68.70 78	87.06 55	83.60 59	79.02 156	90.05 142	77.37 51	90.88 70	89.66 55	93.37 48	86.74 75
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSLP-MVS++		86.29 54	89.10 54	83.01 56	85.71 74	89.79 34	87.04 116	74.39 48	85.17 73	78.92 100	77.59 166	93.57 101	82.60 20	93.23 36	91.88 40	89.42 99	92.46 27

Effi-MVS+-dtu		82.04 107	83.39 135	80.48 90	85.48 75	86.57 62	88.40 88	68.28 84	69.04 192	73.13 129	76.26 178	91.11 136	74.74 73	88.40 88	87.76 69	92.84 58	84.57 91

v7n		87.11 47	90.46 46	83.19 54	85.22 76	83.69 77	90.03 73	68.20 85	91.01 16	86.71 35	94.80 8	98.46 4	77.69 47	91.10 63	85.98 86	91.30 78	88.19 65

MAR-MVS		81.98 108	82.92 137	80.88 78	85.18 77	85.85 65	89.13 80	69.52 68	71.21 182	82.25 72	71.28 208	88.89 152	69.69 121	88.71 84	86.96 74	89.52 97	87.57 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
abl_6				79.30 105	84.98 78	85.78 66	90.50 64	66.88 93	77.08 155	74.02 123	73.29 201	89.34 145	68.94 128			90.49 86	85.98 79

TAPA-MVS	78.00 13	85.88 57	88.37 60	82.96 58	84.69 79	88.62 41	90.62 55	64.22 130	89.15 35	88.05 15	78.83 160	93.71 98	76.20 59	90.11 76	88.22 67	94.00 42	89.97 51
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		89.14 28	92.19 28	85.58 33	84.62 80	82.56 88	90.53 62	71.93 57	91.95 9	85.89 37	94.22 13	97.25 21	85.42 5	95.73 12	91.71 41	95.08 28	91.89 34

MVS_111021_HR		83.95 74	86.10 83	81.44 71	84.62 80	80.29 120	90.51 63	68.05 86	84.07 83	80.38 89	84.74 130	91.37 133	74.23 78	90.37 74	87.25 72	90.86 84	84.59 90

CNLPA		85.50 60	88.58 56	81.91 66	84.55 82	87.52 53	90.89 52	63.56 140	88.18 43	84.06 50	83.85 134	91.34 134	76.46 56	91.27 58	89.00 62	91.96 68	88.88 61

Effi-MVS+		82.33 97	83.87 128	80.52 89	84.51 83	81.32 103	87.53 102	68.05 86	74.94 166	79.67 94	82.37 142	92.31 119	72.21 103	85.06 122	86.91 76	91.18 80	84.20 96

gm-plane-assit		71.56 184	69.99 198	73.39 143	84.43 84	73.21 180	90.42 68	51.36 220	84.08 82	76.00 110	91.30 56	37.09 246	59.01 164	73.65 206	70.24 203	79.09 197	60.37 218

RPSCF		88.05 44	92.61 15	82.73 63	84.24 85	88.40 42	90.04 72	66.29 96	91.46 10	82.29 71	88.93 87	96.01 48	79.38 35	95.15 21	94.90 6	94.15 39	93.40 19

FC-MVSNet-train		79.20 134	86.29 79	70.94 157	84.06 86	77.67 138	85.68 122	64.11 133	82.90 92	52.22 204	92.57 35	93.69 99	49.52 213	88.30 90	86.93 75	90.03 90	81.95 126

v1192		83.61 77	85.23 98	81.72 68	84.05 87	82.15 91	89.54 75	66.20 97	81.38 117	86.76 34	91.79 46	96.03 47	74.88 72	81.81 167	80.92 139	88.91 104	82.50 119

v1240		83.57 79	84.94 104	81.97 65	84.05 87	81.27 106	89.46 77	66.06 100	81.31 119	87.50 21	91.88 45	95.46 65	76.25 58	81.16 174	80.51 144	88.52 110	82.98 113

test20.03		69.91 188	76.20 177	62.58 207	84.01 89	67.34 201	75.67 201	65.88 105	79.98 132	40.28 231	82.65 138	89.31 146	39.63 226	77.41 190	73.28 194	69.98 214	63.40 210

Anonymous202405211			84.68 107		83.92 90	79.45 125	79.03 170	67.79 88	82.01 104		88.77 91	92.58 112	55.93 179	86.68 103	84.26 103	88.92 103	78.98 148

NR-MVSNet		82.89 91	87.43 71	77.59 120	83.91 91	83.59 79	87.10 113	78.35 18	80.64 125	68.85 153	92.67 31	96.50 29	54.19 189	87.19 101	88.68 63	93.16 53	82.75 117

Gipuma		86.47 52	89.25 53	83.23 53	83.88 92	78.78 129	85.35 126	68.42 82	92.69 8	89.03 12	91.94 43	96.32 39	81.80 25	94.45 27	86.86 77	90.91 83	83.69 101
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v1921920		83.49 80	84.94 104	81.80 67	83.78 93	81.20 110	89.50 76	65.91 104	81.64 111	87.18 27	91.70 47	95.39 66	75.85 62	81.56 171	80.27 147	88.60 108	82.80 115

v1144		83.22 86	85.01 101	81.14 72	83.76 94	81.60 100	88.95 82	65.58 110	81.89 105	85.80 38	91.68 48	95.84 51	74.04 83	82.12 164	80.56 143	88.70 107	81.41 129

Vis-MVSNet (Re-imp)		76.15 151	80.84 147	70.68 159	83.66 95	74.80 171	81.66 150	69.59 67	80.48 128	46.94 220	87.44 100	80.63 180	53.14 197	86.87 102	84.56 101	89.12 101	71.12 185

v11		83.30 84	85.58 93	80.64 85	83.53 96	81.74 96	88.30 90	65.46 112	82.75 95	84.63 44	92.49 37	96.17 43	73.90 85	82.69 156	79.59 154	88.04 121	83.66 102

casdiffmvs		80.70 121	81.81 144	79.40 103	83.45 97	83.07 83	89.44 78	68.54 81	73.64 169	77.68 105	82.44 139	92.44 116	69.64 123	80.06 182	77.46 182	87.65 133	83.58 103

v144192		83.43 81	84.97 103	81.63 70	83.43 98	81.23 109	89.42 79	66.04 102	81.45 116	86.40 36	91.46 51	95.70 59	75.76 64	82.14 163	80.23 148	88.74 105	82.57 118

TinyColmap		83.79 75	86.12 82	81.07 73	83.42 99	81.44 102	85.42 124	68.55 80	88.71 40	89.46 8	87.60 99	92.72 110	70.34 119	89.29 80	81.94 131	89.20 100	81.12 132

v13		83.75 76	86.20 80	80.89 77	83.38 100	81.93 93	88.58 86	66.09 99	83.55 85	84.28 47	92.67 31	96.79 25	74.67 74	84.42 136	79.72 152	88.36 112	84.31 94

TransMVSNet (Re)		79.05 135	86.66 74	70.18 165	83.32 101	75.99 160	77.54 177	63.98 135	90.68 20	55.84 186	94.80 8	96.06 46	53.73 195	86.27 108	83.22 117	86.65 151	79.61 143

v12		83.59 78	86.00 86	80.77 82	83.30 102	81.83 94	88.45 87	65.95 103	83.20 88	84.15 48	92.54 36	96.71 26	74.50 76	84.19 138	79.64 153	88.30 113	83.93 100

v7		82.76 94	84.65 108	80.55 88	83.27 103	81.77 95	88.66 84	65.10 117	79.23 143	83.60 59	91.47 50	95.47 63	74.12 79	82.61 157	80.66 140	88.52 110	81.35 130

v10		83.17 88	85.22 99	80.78 79	83.26 104	82.99 84	88.66 84	66.49 95	79.24 142	83.60 59	91.46 51	95.47 63	74.12 79	82.60 158	80.66 140	88.53 109	84.11 98

V9		83.42 82	85.81 88	80.63 86	83.20 105	81.73 97	88.29 91	65.78 107	82.87 93	83.99 53	92.38 38	96.60 28	74.30 77	83.93 139	79.58 155	88.24 116	83.55 105

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 106	86.35 63	93.60 36	78.79 17	95.48 3	91.79 2	93.08 25	97.21 22	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
canonicalmvs		81.22 119	86.04 85	75.60 129	83.17 107	83.18 82	80.29 158	65.82 106	85.97 66	67.98 159	77.74 165	91.51 131	65.17 143	88.62 86	86.15 85	91.17 81	89.09 58

V14		83.23 85	85.59 92	80.48 90	83.09 108	81.63 99	88.13 92	65.61 109	82.53 97	83.81 55	92.17 41	96.50 29	74.07 82	83.66 142	79.51 157	88.17 118	83.16 109

v15		83.06 89	85.39 94	80.35 93	83.01 109	81.53 101	87.98 95	65.47 111	82.19 102	83.66 58	92.00 42	96.40 35	73.87 86	83.39 144	79.44 158	88.10 120	82.76 116

FPMVS		81.56 115	84.04 123	78.66 112	82.92 110	75.96 161	86.48 121	65.66 108	84.67 77	71.47 137	77.78 164	83.22 172	77.57 49	91.24 59	90.21 50	87.84 126	85.21 85

Anonymous20240521		80.04 125	85.67 91	73.48 142	82.91 111	81.11 112	80.44 157	66.06 100	85.01 74	62.53 174	78.84 159	94.43 89	58.51 166	88.66 85	85.91 87	90.41 87	85.73 82

MVS_111021_LR		83.20 87	85.33 95	80.73 83	82.88 112	78.23 133	89.61 74	65.23 116	82.08 103	81.19 86	85.31 123	92.04 126	75.22 67	89.50 78	85.90 88	90.24 88	84.23 95

Anonymous20231211		79.37 131	85.78 89	71.89 150	82.87 113	79.66 124	78.77 173	63.93 137	83.36 86	59.39 178	90.54 66	94.66 84	56.46 174	87.38 95	84.12 105	89.92 92	80.74 134

v1141		82.26 100	84.32 114	79.85 97	82.86 114	80.31 118	87.58 99	63.48 142	81.86 108	84.03 52	91.33 54	96.28 41	73.23 96	82.39 159	79.08 169	87.93 124	78.97 150

divwei89l23v2f112		82.26 100	84.32 114	79.85 97	82.86 114	80.31 118	87.58 99	63.48 142	81.88 106	84.05 51	91.33 54	96.27 42	73.23 96	82.39 159	79.08 169	87.93 124	78.97 150

v1		82.27 99	84.32 114	79.87 96	82.86 114	80.32 117	87.57 101	63.47 144	81.87 107	84.13 49	91.34 53	96.29 40	73.23 96	82.39 159	79.08 169	87.94 123	78.98 148

v2v482		82.20 103	84.26 119	79.81 99	82.67 117	80.18 122	87.67 98	63.96 136	81.69 110	84.73 43	91.27 57	96.33 38	72.05 107	81.94 166	79.56 156	87.79 127	78.84 152

v8		82.20 103	84.56 110	79.45 101	82.42 118	81.65 98	87.26 105	64.27 128	79.36 138	81.70 79	91.04 63	95.75 54	73.30 94	82.82 152	79.18 166	87.74 128	82.09 124

v1neww		81.76 111	83.95 126	79.21 108	82.41 119	80.46 114	87.26 105	62.93 151	79.28 140	81.62 81	91.06 61	95.72 57	73.31 92	82.83 150	79.22 163	87.73 129	79.07 145

v7new		81.76 111	83.95 126	79.21 108	82.41 119	80.46 114	87.26 105	62.93 151	79.28 140	81.62 81	91.06 61	95.72 57	73.31 92	82.83 150	79.22 163	87.73 129	79.07 145

v17		82.09 105	84.45 112	79.33 104	82.41 119	81.31 104	87.26 105	64.50 127	78.72 145	80.73 87	90.90 64	95.57 60	73.37 90	83.06 145	79.25 162	87.70 132	82.35 122

v6		81.77 110	83.96 125	79.22 107	82.41 119	80.45 116	87.26 105	62.91 155	79.29 139	81.65 80	91.08 59	95.74 55	73.32 91	82.84 149	79.21 165	87.73 129	79.07 145

MSDG		81.39 117	84.23 121	78.09 116	82.40 123	82.47 89	85.31 128	60.91 176	79.73 134	80.26 91	86.30 112	88.27 156	69.67 122	87.20 100	84.98 96	89.97 91	80.67 135

v16		81.92 109	84.32 114	79.12 110	82.31 124	81.29 105	87.20 110	64.51 126	78.16 149	79.76 93	90.86 65	95.23 69	73.29 95	83.05 146	79.29 161	87.63 134	82.34 123

conf0.05thres1000		77.12 144	82.38 140	70.98 155	82.30 125	77.95 136	79.86 163	64.74 122	86.63 58	53.93 192	85.74 120	75.63 203	56.85 171	88.98 83	84.10 106	88.20 117	77.61 157

Fast-Effi-MVS+		81.42 116	83.82 129	78.62 113	82.24 126	80.62 113	87.72 97	63.51 141	73.01 171	74.75 119	83.80 135	92.70 111	73.44 89	88.15 92	85.26 93	90.05 89	83.17 108

PVSNet_Blended_VisFu		83.00 90	84.16 122	81.65 69	82.17 127	86.01 64	88.03 93	71.23 60	76.05 161	79.54 95	83.88 133	83.44 170	77.49 50	87.38 95	84.93 97	91.41 76	87.40 73

v18		81.62 114	83.99 124	78.86 111	82.08 128	81.12 111	86.93 117	64.24 129	77.44 151	79.47 96	90.53 67	94.99 78	72.99 99	82.72 155	79.18 166	87.48 138	81.91 127

pmmvs6		80.46 122	88.34 62	71.26 152	81.96 129	77.51 139	77.54 177	68.83 76	93.72 5	55.92 185	93.94 17	98.03 11	55.94 178	89.21 81	85.61 90	87.36 142	80.38 136

tfpn		72.99 174	75.25 184	70.36 163	81.87 130	77.09 147	79.28 169	64.16 131	79.58 136	53.14 196	76.97 173	48.75 239	56.35 176	87.31 97	82.75 123	87.35 143	74.31 167

IterMVS-LS		79.79 126	82.56 139	76.56 126	81.83 131	77.85 137	79.90 162	69.42 72	78.93 144	71.21 138	90.47 68	85.20 168	70.86 116	80.54 180	80.57 142	86.15 160	84.36 93
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		73.07 173	77.02 168	68.46 175	81.62 132	72.89 181	79.56 167	70.78 63	69.56 187	52.52 201	77.37 170	81.12 179	42.60 222	84.20 137	83.93 107	83.65 183	70.07 190
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		72.68 177	75.21 185	69.73 168	81.48 133	69.04 195	70.48 216	76.67 35	86.92 56	67.80 160	88.06 95	64.67 218	42.12 224	77.60 189	73.65 193	79.81 194	66.57 201

USDC		81.39 117	83.07 136	79.43 102	81.48 133	78.95 128	82.62 143	66.17 98	87.45 51	90.73 4	82.40 141	93.65 100	66.57 140	83.63 143	77.97 174	89.00 102	77.45 158

view800		74.68 161	78.74 153	69.94 166	81.12 135	76.59 150	78.94 172	63.24 149	78.56 147	53.06 197	75.61 189	76.26 196	56.07 177	86.32 107	83.75 111	87.18 148	74.10 170

tfpnnormal		77.16 143	84.26 119	68.88 173	81.02 136	75.02 167	76.52 189	63.30 146	87.29 52	52.40 202	91.24 58	93.97 94	54.85 187	85.46 117	81.08 137	85.18 176	75.76 163

v748		85.21 64	89.62 50	80.08 94	80.71 137	80.27 121	85.05 130	63.79 138	90.47 22	83.54 62	94.21 14	98.52 1	76.84 54	90.97 68	84.25 104	90.53 85	88.62 63

thres600view7		74.34 163	78.43 155	69.56 169	80.47 138	76.28 156	78.65 174	62.56 161	77.39 152	52.53 200	74.03 197	76.78 194	55.90 180	85.06 122	85.19 94	87.25 146	74.29 168

OpenMVS	75.38 16	78.44 138	81.39 146	74.99 135	80.46 139	79.85 123	79.99 160	58.31 194	77.34 153	73.85 125	77.19 171	82.33 176	68.60 130	84.67 132	81.95 130	88.72 106	86.40 78

pm-mvs1		78.21 139	85.68 90	69.50 170	80.38 140	75.73 164	76.25 192	65.04 118	87.59 48	54.47 191	93.16 24	95.99 50	54.20 188	86.37 106	82.98 121	86.64 152	77.96 156

view600		74.08 164	78.15 157	69.32 171	80.27 141	75.82 162	78.27 175	62.20 165	77.26 154	52.80 199	74.07 196	76.86 192	55.57 183	84.90 130	84.43 102	86.84 150	73.71 175

v148		79.33 133	82.32 141	75.84 128	80.14 142	75.74 163	81.98 147	57.06 198	81.51 114	79.36 98	89.42 79	96.42 33	71.32 110	81.54 172	75.29 191	85.20 175	76.32 159

pmmvs-eth3d		79.64 128	82.06 142	76.83 123	80.05 143	72.64 182	87.47 103	66.59 94	80.83 123	73.50 126	89.32 82	93.20 106	67.78 133	80.78 178	81.64 133	85.58 172	76.01 160

testgi		68.20 196	76.05 178	59.04 214	79.99 144	67.32 202	81.16 152	51.78 218	84.91 75	39.36 234	73.42 199	95.19 70	32.79 232	76.54 196	70.40 202	69.14 217	64.55 206

tfpn_n400		73.26 168	77.94 160	67.79 186	79.91 145	73.32 177	76.38 190	62.04 166	84.26 78	48.53 216	76.23 179	71.50 210	53.83 192	86.22 110	81.59 134	86.05 162	72.47 180

tfpnconf		73.26 168	77.94 160	67.79 186	79.91 145	73.32 177	76.38 190	62.04 166	84.26 78	48.53 216	76.23 179	71.50 210	53.83 192	86.22 110	81.59 134	86.05 162	72.47 180

DI_MVS_plusplus_trai		77.64 142	79.64 150	75.31 132	79.87 147	76.89 149	81.55 151	63.64 139	76.21 160	72.03 134	85.59 122	82.97 173	66.63 139	79.27 184	77.78 177	88.14 119	78.76 153

tfpnview11		72.88 176	77.37 166	67.65 188	79.81 148	73.43 176	76.23 193	61.97 168	81.37 118	48.53 216	76.23 179	71.50 210	53.78 194	85.45 118	82.77 122	85.56 173	70.87 188

Fast-Effi-MVS+-dtu		76.92 145	77.18 167	76.62 125	79.55 149	79.17 126	84.80 131	77.40 29	64.46 214	68.75 155	70.81 214	86.57 162	63.36 155	81.74 169	81.76 132	85.86 168	75.78 162

thres400		73.13 172	76.99 170	68.62 174	79.46 150	74.93 169	77.23 179	61.23 173	75.54 162	52.31 203	72.20 203	77.10 191	54.89 185	82.92 148	82.62 128	86.57 154	73.66 177

QAPM		80.43 123	84.34 113	75.86 127	79.40 151	82.06 92	79.86 163	61.94 169	83.28 87	74.73 120	81.74 145	85.44 166	70.97 114	84.99 129	84.71 100	88.29 114	88.14 66

DELS-MVS		79.71 127	83.74 130	75.01 134	79.31 152	82.68 86	84.79 132	60.06 184	75.43 164	69.09 151	86.13 113	89.38 144	67.16 136	85.12 121	83.87 109	89.65 94	83.57 104
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
3Dnovator	79.41 10	82.21 102	86.07 84	77.71 118	79.31 152	84.61 71	87.18 111	61.02 175	85.65 67	76.11 109	85.07 127	85.38 167	70.96 115	87.22 99	86.47 82	91.66 73	88.12 67

test-LLR		62.15 215	59.46 236	65.29 202	79.07 154	52.66 231	69.46 225	62.93 151	50.76 242	53.81 194	63.11 228	58.91 224	52.87 198	66.54 229	62.34 220	73.59 202	61.87 215

test0.0.03 1		61.79 217	65.33 214	57.65 217	79.07 154	64.09 210	68.51 229	62.93 151	61.59 227	33.71 238	61.58 234	71.58 209	33.43 231	70.95 217	68.68 207	68.26 219	58.82 221

tfpn1000		72.27 179	76.88 171	66.88 192	79.01 156	74.04 174	76.60 188	61.15 174	79.65 135	45.52 222	77.41 169	67.98 216	52.47 203	85.22 120	82.99 120	86.54 155	70.89 186

MVS_Test		76.72 146	79.40 152	73.60 140	78.85 157	74.99 168	79.91 161	61.56 171	69.67 186	72.44 130	85.98 117	90.78 138	63.50 152	78.30 187	75.74 190	85.33 174	80.31 140

FMVSNet1		78.20 140	84.83 106	70.46 162	78.62 158	79.03 127	77.90 176	67.53 91	83.02 91	55.10 188	87.19 105	93.18 107	55.65 181	85.57 114	83.39 113	87.98 122	82.40 120

diffmvs1		78.99 136	83.65 131	73.55 141	78.53 159	78.00 134	81.81 148	63.15 150	80.82 124	69.45 147	87.93 96	94.22 92	65.03 146	81.54 172	78.24 172	83.30 188	84.81 87

GA-MVS		75.01 160	76.39 174	73.39 143	78.37 160	75.66 165	80.03 159	58.40 193	70.51 184	75.85 111	83.24 136	76.14 197	63.75 149	77.28 191	76.62 186	83.97 181	75.30 165

thres200		72.41 178	76.00 179	68.21 177	78.28 161	76.28 156	74.94 202	62.56 161	72.14 179	51.35 208	69.59 219	76.51 195	54.89 185	85.06 122	80.51 144	87.25 146	71.92 183

EPNet_dtu		71.90 182	73.03 193	70.59 160	78.28 161	61.64 214	82.44 144	64.12 132	63.26 218	69.74 145	71.47 206	82.41 174	51.89 209	78.83 186	78.01 173	77.07 199	75.60 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs4		75.92 153	77.48 165	74.10 139	78.21 163	70.94 186	84.06 135	64.78 121	75.13 165	68.47 157	84.12 132	83.32 171	64.74 147	75.93 198	79.14 168	84.31 180	73.77 174

PM-MVS		80.42 124	83.63 132	76.67 124	78.04 164	72.37 184	87.14 112	60.18 183	80.13 130	71.75 136	86.12 114	93.92 95	77.08 52	86.56 104	85.12 95	85.83 169	81.18 131

tfpn111		71.60 183	74.66 187	68.04 179	77.97 165	76.44 152	77.04 181	62.68 157	66.81 200	50.69 211	62.10 232	75.67 199	52.46 204	85.06 122	82.64 124	87.42 139	73.87 171

conf200view11		72.00 181	75.40 182	68.04 179	77.97 165	76.44 152	77.04 181	62.68 157	66.81 200	50.69 211	67.30 221	75.67 199	52.46 204	85.06 122	82.64 124	87.42 139	73.87 171

thres100view900		69.86 189	72.97 194	66.24 195	77.97 165	72.49 183	73.29 207	59.12 188	66.81 200	50.82 209	67.30 221	75.67 199	50.54 212	78.24 188	79.40 159	85.71 171	70.88 187

tfpn200view9		72.01 180	75.40 182	68.06 178	77.97 165	76.44 152	77.04 181	62.67 159	66.81 200	50.82 209	67.30 221	75.67 199	52.46 204	85.06 122	82.64 124	87.41 141	73.86 173

Vis-MVSNet		83.32 83	88.12 65	77.71 118	77.91 169	83.44 81	90.58 56	69.49 70	81.11 121	67.10 161	89.85 74	91.48 132	71.71 109	91.34 57	89.37 58	89.48 98	90.26 48
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchMatch-RL		76.05 152	76.64 172	75.36 131	77.84 170	69.87 192	81.09 153	63.43 145	71.66 180	68.34 158	71.70 204	81.76 177	74.98 71	84.83 131	83.44 112	86.45 157	73.22 178

diffmvs		77.65 141	81.71 145	72.92 147	77.79 171	77.13 146	80.70 155	62.82 156	73.16 170	70.22 144	84.92 128	93.82 97	63.41 153	81.10 175	77.40 183	82.58 189	84.42 92

conf0.01		69.59 190	71.01 197	67.95 181	77.74 172	76.09 158	77.04 181	62.58 160	66.81 200	50.54 213	63.00 230	51.78 238	52.46 204	84.53 133	82.64 124	87.32 144	72.19 182

conf0.002		68.60 194	69.17 202	67.92 184	77.66 173	76.01 159	77.04 181	62.56 161	66.81 200	50.51 214	61.21 235	44.01 243	52.46 204	84.44 135	80.29 146	87.31 145	71.44 184

tpmp4_e23		68.32 195	66.04 211	70.98 155	77.52 174	69.23 193	80.99 154	65.46 112	68.09 195	69.25 150	70.77 216	54.03 235	59.35 162	69.01 221	63.02 218	73.34 205	68.15 197

CANet_DTU		75.04 159	78.45 154	71.07 153	77.27 175	77.96 135	83.88 137	58.00 195	64.11 215	68.67 156	75.65 188	88.37 155	53.92 191	82.05 165	81.11 136	84.67 178	79.88 142

MS-PatchMatch		71.18 187	73.99 190	67.89 185	77.16 176	71.76 185	77.18 180	56.38 201	67.35 196	55.04 189	74.63 194	75.70 198	62.38 157	76.62 194	75.97 189	79.22 196	75.90 161

new-patchmatchnet		62.59 214	73.79 191	49.53 232	76.98 177	53.57 229	53.46 244	54.64 205	85.43 70	28.81 242	91.94 43	96.41 34	25.28 240	76.80 192	53.66 237	57.99 234	58.69 222

thresconf0.02		66.71 202	68.28 208	64.89 204	76.83 178	70.38 188	71.62 214	58.90 191	77.64 150	47.04 219	62.10 232	46.01 241	51.32 211	78.85 185	76.09 187	83.62 185	66.85 200

GBi-Net		73.17 170	77.64 162	67.95 181	76.76 179	77.36 141	75.77 197	64.57 123	62.99 220	51.83 205	76.05 182	77.76 188	52.73 200	85.57 114	83.39 113	86.04 164	80.37 137

PVSNet_BlendedMVS		76.45 149	78.12 158	74.49 137	76.76 179	78.46 130	79.65 165	63.26 147	65.42 210	73.15 127	75.05 192	88.96 149	66.51 141	82.73 153	77.66 178	87.61 135	78.60 154

PVSNet_Blended		76.45 149	78.12 158	74.49 137	76.76 179	78.46 130	79.65 165	63.26 147	65.42 210	73.15 127	75.05 192	88.96 149	66.51 141	82.73 153	77.66 178	87.61 135	78.60 154

test1		73.17 170	77.64 162	67.95 181	76.76 179	77.36 141	75.77 197	64.57 123	62.99 220	51.83 205	76.05 182	77.76 188	52.73 200	85.57 114	83.39 113	86.04 164	80.37 137

FMVSNet2		74.43 162	79.70 149	68.27 176	76.76 179	77.36 141	75.77 197	65.36 114	72.28 176	52.97 198	81.92 143	85.61 165	52.73 200	80.66 179	79.73 151	86.04 164	80.37 137

IB-MVS	71.28 17	75.21 158	77.00 169	73.12 146	76.76 179	77.45 140	83.05 140	58.92 190	63.01 219	64.31 167	59.99 237	87.57 159	68.64 129	86.26 109	82.34 129	87.05 149	82.36 121
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
thisisatest0515		81.18 120	84.32 114	77.52 122	76.73 185	74.84 170	85.06 129	61.37 172	81.05 122	73.95 124	88.79 90	89.25 147	75.49 66	85.98 112	84.78 98	92.53 63	85.56 84

FC-MVSNet-test		75.91 154	83.59 133	66.95 191	76.63 186	69.07 194	85.33 127	64.97 120	84.87 76	41.95 226	93.17 23	87.04 160	47.78 216	91.09 64	85.56 91	85.06 177	74.34 166

Anonymous20231206		67.28 199	73.41 192	60.12 213	76.45 187	63.61 212	74.21 204	56.52 200	76.35 158	42.23 225	75.81 187	90.47 140	41.51 225	74.52 199	69.97 204	69.83 215	63.17 211

tttt0517		75.86 155	76.23 176	75.42 130	75.55 188	74.06 173	82.73 142	60.31 178	69.24 188	70.24 143	79.18 155	58.79 226	72.17 104	84.49 134	83.08 118	91.54 74	84.80 88

thisisatest0530		75.54 157	75.95 180	75.05 133	75.08 189	73.56 175	82.15 146	60.31 178	69.17 189	69.32 148	79.02 156	58.78 227	72.17 104	83.88 140	83.08 118	91.30 78	84.20 96

FMVSNet3		71.40 186	75.20 186	66.97 190	75.00 190	76.59 150	74.29 203	64.57 123	62.99 220	51.83 205	76.05 182	77.76 188	51.49 210	76.58 195	77.03 185	84.62 179	79.43 144

tfpn_ndepth		68.20 196	72.18 195	63.55 205	74.64 191	73.24 179	72.41 210	59.76 186	70.54 183	41.93 227	60.96 236	68.69 215	46.23 218	82.16 162	80.14 149	86.34 159	69.56 192

tpm cat1		64.79 208	62.74 225	67.17 189	74.61 192	65.91 205	76.18 194	59.32 187	64.88 213	66.41 164	71.21 209	53.56 236	59.17 163	61.53 237	58.16 230	67.33 220	63.95 207

UGNet		79.62 129	85.91 87	72.28 149	73.52 193	83.91 74	86.64 119	69.51 69	79.85 133	62.57 173	85.82 119	89.63 143	53.18 196	88.39 89	87.35 71	88.28 115	86.43 77
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
our_test_3					73.27 194	70.91 187	83.26 138

HyFIR lowres test		73.29 167	74.14 189	72.30 148	73.08 195	78.33 132	83.12 139	62.41 164	63.81 216	62.13 175	76.67 175	78.50 185	71.09 112	74.13 201	77.47 181	81.98 191	70.10 189

MIMVSNet1		73.40 166	81.85 143	63.55 205	72.90 196	64.37 209	84.58 133	53.60 212	90.84 17	53.92 193	87.75 98	96.10 44	45.31 219	85.37 119	79.32 160	70.98 213	69.18 195

CostFormer		66.81 201	66.94 209	66.67 193	72.79 197	68.25 198	79.55 168	55.57 203	65.52 209	62.77 172	76.98 172	60.09 222	56.73 173	65.69 231	62.35 219	72.59 206	69.71 191

CR-MVSNet		69.56 191	68.34 207	70.99 154	72.78 198	67.63 199	64.47 233	67.74 89	59.93 229	72.30 131	80.10 150	56.77 229	65.04 144	71.64 214	72.91 195	83.61 186	69.40 193

v52		86.26 55	90.85 40	80.91 75	72.49 199	81.25 107	90.55 59	60.30 181	90.43 24	87.24 23	94.64 11	98.30 9	83.16 18	92.86 43	86.82 79	91.69 71	91.65 37

V4		86.26 55	90.85 40	80.91 75	72.49 199	81.25 107	90.55 59	60.31 178	90.44 23	87.23 25	94.64 11	98.31 8	83.17 16	92.87 42	86.82 79	91.69 71	91.64 38

1111		55.38 232	59.51 235	50.57 231	72.41 201	48.16 238	69.76 220	57.08 196	76.79 156	32.10 239	80.12 148	35.41 247	25.87 237	67.23 224	57.74 231	46.17 242	51.09 234

.test1245		43.71 239	44.35 242	42.95 236	72.41 201	48.16 238	69.76 220	57.08 196	76.79 156	32.10 239	80.12 148	35.41 247	25.87 237	67.23 224	1.08 244	0.48 247	1.68 243

CVMVSNet		75.65 156	77.62 164	73.35 145	71.95 203	69.89 191	83.04 141	60.84 177	69.12 190	68.76 154	79.92 153	78.93 184	73.64 88	81.02 176	81.01 138	81.86 192	83.43 106

IterMVS		73.62 165	76.53 173	70.23 164	71.83 204	77.18 145	80.69 156	53.22 214	72.23 177	66.62 163	85.21 124	78.96 183	69.54 125	76.28 197	71.63 199	79.45 195	74.25 169
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DWT-MVSNet_training		63.07 209	60.04 232	66.61 194	71.64 205	65.27 207	76.80 186	53.82 210	55.90 235	63.07 170	62.23 231	41.87 245	62.54 156	64.32 234	63.71 216	71.78 207	66.97 199

RPMNet		67.02 200	63.99 219	70.56 161	71.55 206	67.63 199	75.81 195	69.44 71	59.93 229	63.24 169	64.32 226	47.51 240	59.68 160	70.37 218	69.64 205	83.64 184	68.49 196

dps		65.14 205	64.50 217	65.89 200	71.41 207	65.81 206	71.44 215	61.59 170	58.56 232	61.43 176	75.45 190	52.70 237	58.06 168	69.57 220	64.65 214	71.39 211	64.77 204

MDTV_nov1_ep13_2view		72.96 175	75.59 181	69.88 167	71.15 208	64.86 208	82.31 145	54.45 207	76.30 159	78.32 103	86.52 110	91.58 129	61.35 158	76.80 192	66.83 211	71.70 208	66.26 202

TAMVS		63.02 210	69.30 201	55.70 221	70.12 209	56.89 222	69.63 222	45.13 225	70.23 185	38.00 236	77.79 163	75.15 204	42.60 222	74.48 200	72.81 197	68.70 218	57.75 225

tpm		62.79 212	63.25 222	62.26 209	70.09 210	53.78 228	71.65 213	47.31 223	65.72 208	76.70 107	80.62 147	56.40 232	48.11 215	64.20 235	58.54 228	59.70 232	63.47 209

V42		79.59 130	83.59 133	74.93 136	69.61 211	77.05 148	86.59 120	55.84 202	78.42 148	77.29 106	89.84 75	95.08 75	74.12 79	83.05 146	80.11 150	86.12 161	81.59 128

PatchmatchNet		64.81 207	63.74 221	66.06 199	69.21 212	58.62 219	73.16 208	60.01 185	65.92 206	66.19 165	76.27 177	59.09 223	60.45 159	66.58 228	61.47 226	67.33 220	58.24 223
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 1792x2688		68.80 193	71.09 196	66.13 197	69.11 213	68.89 196	78.98 171	54.68 204	61.63 226	56.69 182	71.56 205	78.39 186	67.69 134	72.13 212	72.01 198	69.63 216	73.02 179

MIMVSNet		63.02 210	69.02 203	56.01 219	68.20 214	59.26 218	70.01 219	53.79 211	71.56 181	41.26 230	71.38 207	82.38 175	36.38 228	71.43 216	67.32 209	66.45 222	59.83 220

CMPMVS	55.74 18	71.56 184	76.26 175	66.08 198	68.11 215	63.91 211	63.17 236	50.52 222	68.79 193	75.49 113	70.78 215	85.67 164	63.54 151	81.58 170	77.20 184	75.63 200	85.86 80
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EU-MVSNet		76.48 148	80.53 148	71.75 151	67.62 216	70.30 189	81.74 149	54.06 209	75.47 163	71.01 140	80.10 150	93.17 108	73.67 87	83.73 141	77.85 176	82.40 190	83.07 110

tpmrst		59.42 221	60.02 233	58.71 215	67.56 217	53.10 230	66.99 230	51.88 217	63.80 217	57.68 180	76.73 174	56.49 231	48.73 214	56.47 241	55.55 233	59.43 233	58.02 224

pmmvs5		68.91 192	74.35 188	62.56 208	67.45 218	66.78 203	71.70 212	51.47 219	67.17 199	56.25 184	82.41 140	88.59 153	47.21 217	73.21 210	74.23 192	81.30 193	68.03 198

MDTV_nov1_ep13		64.96 206	64.77 216	65.18 203	67.08 219	62.46 213	75.80 196	51.10 221	62.27 225	69.74 145	74.12 195	62.65 219	55.64 182	68.19 223	62.16 223	71.70 208	61.57 217

testpf		55.64 231	50.84 241	61.24 210	67.03 220	54.45 227	72.29 211	65.04 118	37.23 244	54.99 190	53.99 239	43.12 244	44.34 220	55.22 242	51.59 240	63.76 227	60.25 219

E-PMN		59.07 223	62.79 224	54.72 222	67.01 221	47.81 241	60.44 239	43.40 226	72.95 173	44.63 223	70.42 217	73.17 206	58.73 165	80.97 177	51.98 238	54.14 238	42.26 240

N_pmnet		54.95 233	65.90 212	42.18 237	66.37 222	43.86 244	57.92 241	39.79 233	79.54 137	17.24 246	86.31 111	87.91 157	25.44 239	64.68 232	51.76 239	46.33 241	47.23 236

MVSTER		68.08 198	69.73 200	66.16 196	66.33 223	70.06 190	75.71 200	52.36 216	55.18 238	58.64 179	70.23 218	56.72 230	57.34 170	79.68 183	76.03 188	86.61 153	80.20 141

EMVS		58.97 224	62.63 226	54.70 223	66.26 224	48.71 237	61.74 237	42.71 227	72.80 175	46.00 221	73.01 202	71.66 207	57.91 169	80.41 181	50.68 241	53.55 239	41.11 241

anonymousdsp		85.62 58	90.53 44	79.88 95	64.64 225	76.35 155	96.28 13	53.53 213	85.63 68	81.59 83	92.81 29	97.71 15	86.88 2	94.56 26	92.83 25	96.35 6	93.84 9

EPMVS		56.62 228	59.77 234	52.94 226	62.41 226	50.55 236	60.66 238	52.83 215	65.15 212	41.80 228	77.46 168	57.28 228	42.68 221	59.81 239	54.82 234	57.23 235	53.35 229

testmv		60.72 219	68.44 206	51.71 229	61.76 227	56.70 225	73.40 205	42.24 229	67.31 198	39.54 233	70.88 212	92.49 115	28.75 235	73.83 204	66.00 212	64.56 226	51.89 232

test1235678		60.73 218	68.46 205	51.71 229	61.76 227	56.73 224	73.40 205	42.24 229	67.34 197	39.55 232	70.90 211	92.54 113	28.75 235	73.84 203	66.00 212	64.57 225	51.90 231

FMVSNet5		56.37 229	60.14 231	51.98 228	60.83 229	59.58 217	66.85 231	42.37 228	52.68 240	41.33 229	47.09 243	54.68 233	35.28 229	73.88 202	70.77 201	65.24 224	62.26 214

ADS-MVSNet		56.89 227	61.09 228	52.00 227	59.48 230	48.10 240	58.02 240	54.37 208	72.82 174	49.19 215	75.32 191	65.97 217	37.96 227	59.34 240	54.66 235	52.99 240	51.42 233

testus		57.41 225	64.98 215	48.58 234	59.39 231	57.17 220	68.81 228	32.86 237	62.32 224	43.25 224	57.59 238	88.49 154	24.19 241	71.68 213	63.20 217	62.99 228	54.42 228

no-one		78.59 137	85.28 96	70.79 158	59.01 232	68.77 197	76.62 187	46.06 224	80.25 129	75.75 112	81.85 144	97.75 14	83.63 12	90.99 67	87.20 73	83.67 182	90.14 49

new_pmnet		52.29 235	63.16 223	39.61 239	58.89 233	44.70 243	48.78 246	34.73 236	65.88 207	17.85 245	73.42 199	80.00 181	23.06 242	67.00 227	62.28 222	54.36 237	48.81 235

test2356		51.28 237	53.40 240	48.80 233	58.53 234	52.10 233	63.63 235	40.83 232	51.94 241	39.35 235	53.46 240	45.22 242	28.78 234	64.39 233	60.77 227	61.70 229	45.92 237

MVS-HIRNet		59.74 220	58.74 239	60.92 211	57.74 235	45.81 242	56.02 242	58.69 192	55.69 236	65.17 166	70.86 213	71.66 207	56.75 172	61.11 238	53.74 236	71.17 212	52.28 230

LP		65.71 204	69.91 199	60.81 212	56.75 236	61.37 215	69.55 223	56.80 199	73.01 171	60.48 177	79.76 154	70.57 213	55.47 184	72.77 211	67.19 210	65.81 223	64.71 205

PatchT		66.25 203	66.76 210	65.67 201	55.87 237	60.75 216	70.17 217	59.00 189	59.80 231	72.30 131	78.68 161	54.12 234	65.04 144	71.64 214	72.91 195	71.63 210	69.40 193

test-mter		59.39 222	61.59 227	56.82 218	53.21 238	54.82 226	73.12 209	26.57 242	53.19 239	56.31 183	64.71 224	60.47 221	56.36 175	68.69 222	64.27 215	75.38 201	65.00 203

test12356		54.63 234	63.78 220	43.96 235	51.77 239	51.90 234	65.92 232	30.12 238	62.44 223	30.38 241	64.65 225	89.07 148	30.62 233	73.53 208	62.11 224	54.92 236	42.78 239

CHOSEN 280x420		56.32 230	58.85 238	53.36 225	51.63 240	39.91 245	69.12 227	38.61 234	56.29 234	36.79 237	48.84 242	62.59 220	63.39 154	73.61 207	67.66 208	60.61 230	63.07 212

TESTMET0.1,1		57.21 226	59.46 236	54.60 224	50.95 241	52.66 231	69.46 225	26.91 241	50.76 242	53.81 194	63.11 228	58.91 224	52.87 198	66.54 229	62.34 220	73.59 202	61.87 215

pmmvs3		62.72 213	68.71 204	55.74 220	50.74 242	57.10 221	70.05 218	28.82 240	61.57 228	57.39 181	71.19 210	85.73 163	53.96 190	73.36 209	69.43 206	73.47 204	62.55 213

MDA-MVSNet-bldmvs		76.51 147	82.87 138	69.09 172	50.71 243	74.72 172	84.05 136	60.27 182	81.62 112	71.16 139	88.21 94	91.58 129	69.62 124	92.78 44	77.48 180	78.75 198	73.69 176

PMMVS		61.98 216	65.61 213	57.74 216	45.03 244	51.76 235	69.54 224	35.05 235	55.49 237	55.32 187	68.23 220	78.39 186	58.09 167	70.21 219	71.56 200	83.42 187	63.66 208

PMMVS2		48.13 238	64.06 218	29.55 240	44.06 245	36.69 246	51.95 245	29.97 239	74.75 167	8.90 248	76.02 185	91.24 135	7.53 243	73.78 205	55.91 232	34.87 244	40.01 242

MVE	41.12 19	51.80 236	60.92 229	41.16 238	35.21 246	34.14 247	48.45 247	41.39 231	69.11 191	19.53 244	63.33 227	73.80 205	63.56 150	67.19 226	61.51 225	38.85 243	57.38 226
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				13.54 242	16.73 247	6.42 249	8.49 249	2.36 244	28.69 246	27.44 243	18.40 245	13.51 250	3.70 244	33.23 243	36.26 242	22.54 246

test123		1.06 241	1.41 243	0.64 243	0.39 248	0.48 250	0.52 252	0.25 246	1.11 248	1.37 250	2.01 247	1.98 251	0.87 245	1.43 245	1.27 243	0.46 249	1.62 245

testmvs		0.93 242	1.37 244	0.41 244	0.36 249	0.36 251	0.62 251	0.39 245	1.48 247	0.18 251	2.41 246	1.31 252	0.41 246	1.25 246	1.08 244	0.48 247	1.68 243

GG-mvs-BLEND		41.63 240	60.36 230	19.78 241	0.14 250	66.04 204	55.66 243	0.17 247	57.64 233	2.42 249	51.82 241	69.42 214	0.28 247	64.11 236	58.29 229	60.02 231	55.18 227

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

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

MTAPA										89.37 9		94.85 80

MTMP										90.54 5		95.16 72

Patchmatch-RL test							4.13 250

NP-MVS									78.65 146

Patchmtry						56.88 223	64.47 233	67.74 89		72.30 131

DeepMVS_CX						17.78 248	20.40 248	6.69 243	31.41 245	9.80 247	38.61 244	34.88 249	33.78 230	28.41 244		23.59 245	45.77 238

High-resolution multi-view benchmark