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 33	91.44 39	86.20 28	94.88 1	89.84 33	94.76 29	77.45 29	85.41 72	74.79 103	88.83 77	88.90 133	78.67 40	96.06 7	95.45 4	96.66 3	95.58 1

DTE-MVSNet		88.99 35	92.77 12	84.59 43	93.31 2	88.10 48	90.96 52	83.09 2	91.38 14	76.21 94	96.03 3	98.04 9	70.78 104	95.65 14	92.32 33	93.18 55	87.84 71

zzz-MVS		90.38 11	91.35 41	89.25 5	93.08 3	86.59 64	96.45 11	79.00 16	90.23 28	89.30 10	85.87 105	94.97 65	82.54 18	95.05 23	94.83 7	95.14 27	91.94 36

mPP-MVS					93.05 4							95.77 44

MP-MVS		90.84 6	91.95 34	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 60	88.75 13	89.00 73	94.38 78	84.01 9	94.94 25	94.34 11	95.45 24	93.24 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		88.86 39	92.92 9	84.11 53	92.92 5	88.05 50	90.83 55	82.67 5	91.04 18	74.83 102	95.97 4	98.47 4	70.38 105	95.70 13	92.43 31	93.05 59	88.78 64

HPM-MVS++		88.74 40	89.54 54	87.80 16	92.58 7	85.69 72	95.10 26	78.01 23	87.08 57	87.66 20	87.89 84	92.07 105	80.28 30	90.97 70	91.41 44	93.17 56	91.69 38

PS-CasMVS		89.07 32	93.23 7	84.21 51	92.44 8	88.23 47	90.54 63	82.95 3	90.50 25	75.31 100	95.80 6	98.37 7	71.16 98	96.30 5	93.32 22	92.88 60	90.11 52

CP-MVSNet		88.71 41	92.63 15	84.13 52	92.39 9	88.09 49	90.47 68	82.86 4	88.79 43	75.16 101	94.87 9	97.68 15	71.05 100	96.16 6	93.18 24	92.85 61	89.64 56

CP-MVS		91.09 5	92.33 25	89.65 2	92.16 10	90.41 27	96.46 10	80.38 8	88.26 46	89.17 11	87.00 94	96.34 31	83.95 10	95.77 11	94.72 8	95.81 17	93.78 9

ACMMPR		91.30 4	92.88 11	89.46 4	91.92 11	91.61 5	96.60 5	79.46 14	90.08 31	88.53 14	89.54 65	95.57 48	84.25 7	95.24 20	94.27 13	95.97 11	93.85 7

WR-MVS_H		88.99 35	93.28 5	83.99 54	91.92 11	89.13 39	91.95 46	83.23 1	90.14 30	71.92 122	95.85 5	98.01 11	71.83 95	95.82 9	93.19 23	93.07 58	90.83 48

SR-MVS					91.82 13			80.80 7				95.53 50

PGM-MVS		90.42 10	91.58 37	89.05 6	91.77 14	91.06 13	96.51 7	78.94 17	85.41 72	87.67 19	87.02 93	95.26 56	83.62 12	95.01 24	93.94 16	95.79 19	93.40 19

APD-MVS		89.14 29	91.25 44	86.67 25	91.73 15	91.02 15	95.50 21	77.74 25	84.04 83	79.47 83	91.48 44	94.85 67	81.14 26	92.94 41	92.20 36	94.47 39	92.24 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		90.13 15	92.26 27	87.64 18	91.68 16	90.44 26	95.22 24	77.34 33	90.79 22	87.80 17	90.42 55	92.05 107	79.05 35	93.89 33	93.59 19	94.77 34	94.62 4
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ambc			88.38 62		91.62 17	87.97 51	84.48 121		88.64 45	87.93 16	87.38 88	94.82 69	74.53 74	89.14 84	83.86 112	85.94 145	86.84 76

TSAR-MVS + MP.		89.67 24	92.25 28	86.65 26	91.53 18	90.98 17	96.15 14	73.30 56	87.88 50	81.83 67	92.92 29	95.15 60	82.23 19	93.58 35	92.25 34	94.87 31	93.01 24
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		86.67 55	87.73 71	85.43 35	91.51 19	82.72 89	94.47 31	74.22 53	81.71 98	81.54 71	89.20 71	92.87 94	78.33 42	90.12 77	88.47 70	92.51 69	89.04 61

X-MVS		89.36 28	90.73 47	87.77 17	91.50 20	91.23 8	96.76 4	78.88 18	87.29 55	87.14 26	78.98 139	94.53 72	76.47 55	95.25 19	94.28 12	95.85 14	93.55 15

HFP-MVS		90.32 13	92.37 22	87.94 14	91.46 21	90.91 18	95.69 18	79.49 12	89.94 34	83.50 51	89.06 72	94.44 76	81.68 23	94.17 31	94.19 14	95.81 17	93.87 6

ACMM	80.67 7	90.67 7	92.46 19	88.57 8	91.35 22	89.93 31	96.34 12	77.36 31	90.17 29	86.88 30	87.32 89	96.63 24	83.32 13	95.79 10	94.49 10	96.19 9	92.91 25
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 37	91.32 23	88.27 45	93.49 38	79.86 10	92.75 9	75.37 99	96.86 1	98.38 6	75.10 69	95.93 8	94.07 15	96.46 5	89.39 58

SD-MVS		89.91 18	92.23 30	87.19 22	91.31 24	89.79 34	94.31 32	75.34 47	89.26 38	81.79 68	92.68 31	95.08 62	83.88 11	93.10 39	92.69 26	96.54 4	93.02 23
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
XVS					91.28 25	91.23 8	96.89 2			87.14 26		94.53 72				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 26		94.53 72				95.84 15

DeepC-MVS	83.59 4	90.37 12	92.56 18	87.82 15	91.26 27	92.33 3	94.72 30	80.04 9	90.01 32	84.61 43	93.33 22	94.22 79	80.59 28	92.90 44	92.52 29	95.69 21	92.57 27
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 20	88.56 9	91.24 28	91.60 6	96.49 9	77.53 27	87.89 49	86.87 31	87.24 91	96.46 26	82.87 16	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 35	87.97 13	91.21 29	90.29 28	96.51 7	78.00 24	86.33 63	85.32 41	88.23 81	94.67 70	82.08 21	95.13 22	93.88 17	94.72 36	93.59 12
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		89.86 19	91.96 33	87.42 20	91.00 30	90.08 29	96.00 16	76.61 37	89.28 35	87.73 18	90.04 57	91.80 110	78.71 38	94.36 29	93.82 18	94.48 38	94.32 5

CPTT-MVS		89.63 25	90.52 49	88.59 7	90.95 31	90.74 21	95.71 17	79.13 15	87.70 51	85.68 39	80.05 134	95.74 46	84.77 6	94.28 30	92.68 27	95.28 26	92.45 31

LGP-MVS_train		90.56 9	92.38 21	88.43 10	90.88 32	91.15 11	95.35 22	77.65 26	86.26 65	87.23 24	90.45 54	97.35 18	83.20 14	95.44 16	93.41 21	96.28 8	92.63 26

OPM-MVS		89.82 21	92.24 29	86.99 23	90.86 33	89.35 37	95.07 27	75.91 43	91.16 16	86.87 31	91.07 50	97.29 19	79.13 34	93.32 36	91.99 38	94.12 41	91.49 41

ACMP	80.00 8	90.12 16	92.30 26	87.58 19	90.83 34	91.10 12	94.96 28	76.06 41	87.47 53	85.33 40	88.91 76	97.65 16	82.13 20	95.31 17	93.44 20	96.14 10	92.22 33
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
NCCC		86.74 54	87.97 70	85.31 36	90.64 35	87.25 58	93.27 39	74.59 49	86.50 61	83.72 47	75.92 164	92.39 100	77.08 52	91.72 53	90.68 49	92.57 67	91.30 43

MSP-MVS		88.51 42	91.36 40	85.19 39	90.63 36	92.01 4	95.29 23	77.52 28	90.48 26	80.21 78	90.21 56	96.08 35	76.38 57	88.30 93	91.42 42	91.12 87	91.01 45

UniMVSNet_ETH3D		85.39 64	91.12 45	78.71 99	90.48 37	83.72 82	81.76 137	82.41 6	93.84 6	64.43 156	95.41 7	98.76 1	63.72 139	93.63 34	89.74 59	89.47 104	82.74 110

APDe-MVS		89.85 20	92.91 10	86.29 27	90.47 38	91.34 7	96.04 15	76.41 40	91.11 17	78.50 88	93.44 21	95.82 43	81.55 24	93.16 38	91.90 39	94.77 34	93.58 14

PMVS	79.51 9	90.23 14	92.67 14	87.39 21	90.16 39	88.75 41	93.64 36	75.78 44	90.00 33	83.70 48	92.97 28	92.22 102	86.13 4	97.01 3	96.79 2	94.94 30	90.96 46
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CNVR-MVS		86.93 53	88.98 58	84.54 44	90.11 40	87.41 57	93.23 40	73.47 55	86.31 64	82.25 62	82.96 122	92.15 103	76.04 60	91.69 54	90.69 48	92.17 73	91.64 40

TSAR-MVS + GP.		85.32 66	87.41 75	82.89 63	90.07 41	85.69 72	89.07 82	72.99 57	82.45 91	74.52 106	85.09 112	87.67 139	79.24 33	91.11 65	90.41 51	91.45 79	89.45 57

DeepC-MVS_fast	81.78 5	87.38 51	89.64 53	84.75 41	89.89 42	90.70 22	92.74 43	74.45 50	86.02 66	82.16 65	86.05 103	91.99 109	75.84 63	91.16 64	90.44 50	93.41 50	91.09 44
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 33	91.69 36	85.91 30	89.72 43	90.81 20	92.56 44	71.69 63	90.83 21	87.24 23	89.71 63	92.07 105	78.37 41	94.43 28	92.59 28	95.86 13	91.35 42

DPE-MVS		89.81 22	92.34 24	86.86 24	89.69 44	91.00 16	95.53 19	76.91 34	88.18 47	83.43 54	93.48 20	95.19 57	81.07 27	92.75 46	92.07 37	94.55 37	93.74 10

CDPH-MVS		86.66 56	88.52 61	84.48 45	89.61 45	88.27 45	92.86 42	72.69 58	80.55 116	82.71 56	86.92 95	93.32 90	75.55 65	91.00 69	89.85 58	93.47 48	89.71 55

EPNet		79.36 118	79.44 135	79.27 98	89.51 46	77.20 132	88.35 89	77.35 32	68.27 167	74.29 107	76.31 157	79.22 166	59.63 151	85.02 123	85.45 95	86.49 137	84.61 89
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + ACMM		89.14 29	92.11 32	85.67 31	89.27 47	90.61 24	90.98 51	79.48 13	88.86 41	79.80 80	93.01 27	93.53 88	83.17 15	92.75 46	92.45 30	91.32 82	93.59 12

HQP-MVS		85.02 68	86.41 81	83.40 55	89.19 48	86.59 64	91.28 49	71.60 64	82.79 89	83.48 52	78.65 143	93.54 87	72.55 88	86.49 107	85.89 92	92.28 72	90.95 47

AdaColmap		84.15 75	85.14 96	83.00 60	89.08 49	87.14 60	90.56 62	70.90 66	82.40 92	80.41 74	73.82 175	84.69 151	75.19 68	91.58 58	89.90 57	91.87 76	86.48 78

DVP-MVS		89.40 27	92.69 13	85.56 34	89.01 50	89.85 32	93.72 35	75.42 45	92.28 11	80.49 73	94.36 13	94.87 66	81.46 25	92.49 50	91.42 42	93.27 52	93.54 16

COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 51	92.86 2	95.51 20	72.17 59	94.95 5	91.27 3	94.11 16	97.77 12	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
TDRefinement		93.16 1	95.57 1	90.36 1	88.79 52	93.57 1	97.27 1	78.23 22	95.55 2	93.00 1	93.98 17	96.01 39	87.53 1	97.69 1	96.81 1	97.33 1	95.34 3

TranMVSNet+NR-MVSNet		85.23 67	89.38 55	80.39 90	88.78 53	83.77 81	87.40 97	76.75 35	85.47 70	68.99 138	95.18 8	97.55 17	67.13 124	91.61 57	89.13 67	93.26 53	82.95 107

SED-MVS		88.96 37	92.37 22	84.99 40	88.64 54	89.65 36	95.11 25	75.98 42	90.73 23	80.15 79	94.21 15	94.51 75	76.59 54	92.94 41	91.17 45	93.46 49	93.37 21

ACMH+	79.05 11	89.62 26	93.08 8	85.58 32	88.58 55	89.26 38	92.18 45	74.23 52	93.55 8	82.66 59	92.32 36	98.35 8	80.29 29	95.28 18	92.34 32	95.52 22	90.43 50

MVS_0304		84.73 72	86.19 83	83.02 58	88.32 56	86.71 63	91.55 47	70.87 67	73.79 143	82.88 55	85.13 111	93.35 89	72.55 88	88.62 87	87.69 76	91.93 75	88.05 70

DU-MVS		84.88 70	88.27 66	80.92 79	88.30 57	83.59 84	87.06 102	78.35 20	80.64 114	70.49 130	92.67 32	96.91 22	68.13 117	91.79 51	89.29 66	93.20 54	83.02 104

Baseline_NR-MVSNet		82.79 90	86.51 78	78.44 103	88.30 57	75.62 146	87.81 92	74.97 48	81.53 102	66.84 151	94.71 12	96.46 26	66.90 125	91.79 51	83.37 118	85.83 147	82.09 115

UniMVSNet_NR-MVSNet		84.62 73	88.00 69	80.68 85	88.18 59	83.83 80	87.06 102	76.47 39	81.46 105	70.49 130	93.24 23	95.56 49	68.13 117	90.43 74	88.47 70	93.78 46	83.02 104

xxxxxxxxxxxxxcwj		88.03 47	91.29 43	84.22 49	88.17 60	87.90 52	90.80 56	71.80 61	89.28 35	82.70 57	89.90 59	97.72 13	77.91 45	91.69 54	90.04 55	93.95 44	92.47 28

SF-MVS		87.85 50	90.95 46	84.22 49	88.17 60	87.90 52	90.80 56	71.80 61	89.28 35	82.70 57	89.90 59	95.37 54	77.91 45	91.69 54	90.04 55	93.95 44	92.47 28

CSCG		88.12 45	91.45 38	84.23 48	88.12 62	90.59 25	90.57 61	68.60 87	91.37 15	83.45 53	89.94 58	95.14 61	78.71 38	91.45 59	88.21 74	95.96 12	93.44 18

CLD-MVS		82.75 92	87.22 76	77.54 109	88.01 63	85.76 71	90.23 71	54.52 181	82.28 94	82.11 66	88.48 80	95.27 55	63.95 137	89.41 81	88.29 72	86.45 138	81.01 124
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 69	88.53 60	80.78 81	87.82 64	84.21 78	88.03 90	76.50 38	81.18 109	69.29 136	92.63 34	96.83 23	69.07 113	91.23 63	89.60 62	93.97 43	84.00 97

DPM-MVS		81.42 101	82.11 126	80.62 86	87.54 65	85.30 74	90.18 73	68.96 82	81.00 112	79.15 85	70.45 192	83.29 154	67.67 121	82.81 137	83.46 113	90.19 93	88.48 66

DeepPCF-MVS	81.61 6	87.95 48	90.29 51	85.22 38	87.48 66	90.01 30	93.79 34	73.54 54	88.93 40	83.89 46	89.40 67	90.84 119	80.26 31	90.62 73	90.19 54	92.36 70	92.03 35

CANet		82.84 89	84.60 104	80.78 81	87.30 67	85.20 75	90.23 71	69.00 81	72.16 151	78.73 87	84.49 116	90.70 121	69.54 110	87.65 96	86.17 87	89.87 98	85.84 83

MCST-MVS		84.79 71	86.48 79	82.83 64	87.30 67	87.03 61	90.46 69	69.33 79	83.14 86	82.21 64	81.69 130	92.14 104	75.09 70	87.27 100	84.78 102	92.58 65	89.30 59

EIA-MVS		78.57 124	77.90 143	79.35 96	87.24 69	80.71 105	86.16 109	64.03 129	62.63 194	73.49 113	73.60 176	76.12 180	73.83 80	88.49 89	84.93 100	91.36 81	78.78 141

test_part1		87.86 49	93.26 6	81.56 74	87.23 70	86.76 62	90.91 53	70.06 71	96.50 1	76.74 92	96.63 2	98.62 2	69.45 112	92.93 43	90.92 46	94.98 29	90.46 49

OMC-MVS		88.16 43	91.34 42	84.46 46	86.85 71	90.63 23	93.01 41	67.00 100	90.35 27	87.40 22	86.86 96	96.35 30	77.66 48	92.63 48	90.84 47	94.84 32	91.68 39

3Dnovator+	83.71 3	88.13 44	90.00 52	85.94 29	86.82 72	91.06 13	94.26 33	75.39 46	88.85 42	85.76 38	85.74 107	86.92 142	78.02 43	93.03 40	92.21 35	95.39 25	92.21 34

ETV-MVS		79.01 123	77.98 142	80.22 91	86.69 73	79.73 112	88.80 85	68.27 92	63.22 189	71.56 124	70.25 194	73.63 187	73.66 82	90.30 76	86.77 84	92.33 71	81.95 117

PHI-MVS		86.37 58	88.14 67	84.30 47	86.65 74	87.56 55	90.76 58	70.16 70	82.55 90	89.65 7	84.89 114	92.40 99	75.97 61	90.88 71	89.70 60	92.58 65	89.03 62

ACMH	78.40 12	88.94 38	92.62 16	84.65 42	86.45 75	87.16 59	91.47 48	68.79 85	95.49 3	89.74 6	93.55 19	98.50 3	77.96 44	94.14 32	89.57 63	93.49 47	89.94 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		84.35 74	87.55 72	80.62 86	86.38 76	82.24 94	86.75 105	64.02 130	84.24 79	78.17 90	89.38 68	95.03 64	78.78 37	89.95 79	86.33 86	89.59 101	85.65 85

IS_MVSNet		81.72 99	85.01 97	77.90 105	86.19 77	82.64 91	85.56 111	70.02 72	80.11 119	63.52 158	87.28 90	81.18 161	67.26 122	91.08 68	89.33 65	94.82 33	83.42 101

PCF-MVS	76.59 14	84.11 76	85.27 93	82.76 65	86.12 78	88.30 44	91.24 50	69.10 80	82.36 93	84.45 44	77.56 149	90.40 123	72.91 87	85.88 112	83.88 110	92.72 63	88.53 65
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		85.51 62	88.36 64	82.19 67	86.05 79	87.69 54	90.50 66	70.60 69	86.40 62	82.33 60	89.69 64	92.52 98	74.01 79	87.53 97	86.84 83	89.63 100	87.80 72

EPP-MVSNet		82.76 91	86.47 80	78.45 102	86.00 80	84.47 77	85.39 113	68.42 89	84.17 80	62.97 160	89.26 70	76.84 176	72.13 93	92.56 49	90.40 52	95.76 20	87.56 74

PLC	76.06 15	85.38 65	87.46 73	82.95 62	85.79 81	88.84 40	88.86 84	68.70 86	87.06 58	83.60 49	79.02 137	90.05 124	77.37 51	90.88 71	89.66 61	93.37 51	86.74 77
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSLP-MVS++		86.29 59	89.10 57	83.01 59	85.71 82	89.79 34	87.04 104	74.39 51	85.17 74	78.92 86	77.59 148	93.57 86	82.60 17	93.23 37	91.88 40	89.42 105	92.46 30

CS-MVS		79.35 119	77.74 144	81.22 76	85.59 83	79.85 109	88.78 86	66.61 102	67.63 168	80.41 74	67.82 198	75.07 185	73.27 86	88.31 92	84.36 106	92.63 64	81.18 121

Effi-MVS+-dtu		82.04 97	83.39 120	80.48 89	85.48 84	86.57 66	88.40 88	68.28 91	69.04 165	73.13 116	76.26 159	91.11 118	74.74 73	88.40 90	87.76 75	92.84 62	84.57 91

v7n		87.11 52	90.46 50	83.19 57	85.22 85	83.69 83	90.03 75	68.20 93	91.01 19	86.71 34	94.80 10	98.46 5	77.69 47	91.10 66	85.98 89	91.30 83	88.19 67

MAR-MVS		81.98 98	82.92 122	80.88 80	85.18 86	85.85 69	89.13 81	69.52 74	71.21 155	82.25 62	71.28 186	88.89 134	69.69 107	88.71 85	86.96 79	89.52 102	87.57 73
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 97	84.98 87	85.78 70	90.50 66	66.88 101	77.08 132	74.02 108	73.29 179	89.34 128	68.94 114			90.49 90	85.98 81

TAPA-MVS	78.00 13	85.88 60	88.37 63	82.96 61	84.69 88	88.62 42	90.62 59	64.22 125	89.15 39	88.05 15	78.83 141	93.71 83	76.20 59	90.11 78	88.22 73	94.00 42	89.97 53
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		89.14 29	92.19 31	85.58 32	84.62 89	82.56 92	90.53 64	71.93 60	91.95 12	85.89 36	94.22 14	97.25 20	85.42 5	95.73 12	91.71 41	95.08 28	91.89 37

MVS_111021_HR		83.95 77	86.10 85	81.44 75	84.62 89	80.29 107	90.51 65	68.05 94	84.07 82	80.38 76	84.74 115	91.37 115	74.23 75	90.37 75	87.25 78	90.86 89	84.59 90

CNLPA		85.50 63	88.58 59	81.91 69	84.55 91	87.52 56	90.89 54	63.56 135	88.18 47	84.06 45	83.85 119	91.34 116	76.46 56	91.27 61	89.00 68	91.96 74	88.88 63

Effi-MVS+		82.33 93	83.87 114	80.52 88	84.51 92	81.32 100	87.53 95	68.05 94	74.94 141	79.67 81	82.37 127	92.31 101	72.21 90	85.06 119	86.91 81	91.18 85	84.20 94

gm-plane-assit		71.56 163	69.99 177	73.39 133	84.43 93	73.21 158	90.42 70	51.36 194	84.08 81	76.00 96	91.30 47	37.09 218	59.01 153	73.65 182	70.24 181	79.09 174	60.37 195

RPSCF		88.05 46	92.61 17	82.73 66	84.24 94	88.40 43	90.04 74	66.29 105	91.46 13	82.29 61	88.93 75	96.01 39	79.38 32	95.15 21	94.90 6	94.15 40	93.40 19

FC-MVSNet-train		79.20 121	86.29 82	70.94 145	84.06 95	77.67 126	85.68 110	64.11 127	82.90 88	52.22 189	92.57 35	93.69 84	49.52 189	88.30 93	86.93 80	90.03 95	81.95 117

v1192		83.61 79	85.23 94	81.72 71	84.05 96	82.15 95	89.54 77	66.20 106	81.38 107	86.76 33	91.79 41	96.03 37	74.88 72	81.81 145	80.92 134	88.91 111	82.50 112

v1240		83.57 80	84.94 100	81.97 68	84.05 96	81.27 101	89.46 79	66.06 108	81.31 108	87.50 21	91.88 40	95.46 52	76.25 58	81.16 150	80.51 138	88.52 118	82.98 106

test20.03		69.91 167	76.20 158	62.58 183	84.01 98	67.34 178	75.67 177	65.88 112	79.98 120	40.28 206	82.65 123	89.31 129	39.63 201	77.41 166	73.28 171	69.98 191	63.40 186

Anonymous202405211			84.68 103		83.92 99	79.45 114	79.03 156	67.79 96	82.01 96		88.77 79	92.58 97	55.93 165	86.68 105	84.26 107	88.92 110	78.98 139

NR-MVSNet		82.89 88	87.43 74	77.59 108	83.91 100	83.59 84	87.10 101	78.35 20	80.64 114	68.85 139	92.67 32	96.50 25	54.19 174	87.19 103	88.68 69	93.16 57	82.75 109

Gipuma		86.47 57	89.25 56	83.23 56	83.88 101	78.78 119	85.35 114	68.42 89	92.69 10	89.03 12	91.94 37	96.32 33	81.80 22	94.45 27	86.86 82	90.91 88	83.69 98
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v1921920		83.49 81	84.94 100	81.80 70	83.78 102	81.20 103	89.50 78	65.91 111	81.64 100	87.18 25	91.70 42	95.39 53	75.85 62	81.56 148	80.27 140	88.60 115	82.80 108

v1144		83.22 84	85.01 97	81.14 77	83.76 103	81.60 98	88.95 83	65.58 115	81.89 97	85.80 37	91.68 43	95.84 42	74.04 78	82.12 142	80.56 137	88.70 114	81.41 120

Vis-MVSNet (Re-imp)		76.15 138	80.84 131	70.68 146	83.66 104	74.80 153	81.66 139	69.59 73	80.48 117	46.94 198	87.44 87	80.63 163	53.14 179	86.87 104	84.56 105	89.12 107	71.12 166

v144192		83.43 82	84.97 99	81.63 73	83.43 105	81.23 102	89.42 80	66.04 110	81.45 106	86.40 35	91.46 45	95.70 47	75.76 64	82.14 141	80.23 141	88.74 112	82.57 111

TinyColmap		83.79 78	86.12 84	81.07 78	83.42 106	81.44 99	85.42 112	68.55 88	88.71 44	89.46 8	87.60 86	92.72 95	70.34 106	89.29 82	81.94 127	89.20 106	81.12 123

TransMVSNet (Re)		79.05 122	86.66 77	70.18 151	83.32 107	75.99 141	77.54 161	63.98 131	90.68 24	55.84 176	94.80 10	96.06 36	53.73 177	86.27 109	83.22 119	86.65 133	79.61 137

v10		83.17 86	85.22 95	80.78 81	83.26 108	82.99 88	88.66 87	66.49 104	79.24 125	83.60 49	91.46 45	95.47 51	74.12 76	82.60 140	80.66 135	88.53 117	84.11 96

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 109	86.35 67	93.60 37	78.79 19	95.48 4	91.79 2	93.08 26	97.21 21	86.34 3	97.06 2	96.27 3	95.46 23	95.56 2
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		81.22 105	86.04 87	75.60 117	83.17 110	83.18 87	80.29 146	65.82 113	85.97 67	67.98 146	77.74 147	91.51 113	65.17 133	88.62 87	86.15 88	91.17 86	89.09 60

FPMVS		81.56 100	84.04 113	78.66 100	82.92 111	75.96 142	86.48 108	65.66 114	84.67 78	71.47 125	77.78 146	83.22 155	77.57 49	91.24 62	90.21 53	87.84 123	85.21 87

DCV-MVSNet		80.04 110	85.67 91	73.48 132	82.91 112	81.11 104	80.44 145	66.06 108	85.01 75	62.53 163	78.84 140	94.43 77	58.51 155	88.66 86	85.91 90	90.41 91	85.73 84

MVS_111021_LR		83.20 85	85.33 92	80.73 84	82.88 113	78.23 123	89.61 76	65.23 117	82.08 95	81.19 72	85.31 109	92.04 108	75.22 67	89.50 80	85.90 91	90.24 92	84.23 93

Anonymous20231211		79.37 117	85.78 89	71.89 139	82.87 114	79.66 113	78.77 158	63.93 133	83.36 84	59.39 167	90.54 52	94.66 71	56.46 162	87.38 98	84.12 108	89.92 97	80.74 125

v2v482		82.20 95	84.26 108	79.81 93	82.67 115	80.18 108	87.67 94	63.96 132	81.69 99	84.73 42	91.27 48	96.33 32	72.05 94	81.94 144	79.56 144	87.79 124	78.84 140

v8		82.20 95	84.56 105	79.45 94	82.42 116	81.65 97	87.26 98	64.27 124	79.36 124	81.70 69	91.04 51	95.75 45	73.30 85	82.82 136	79.18 147	87.74 125	82.09 115

MSDG		81.39 103	84.23 110	78.09 104	82.40 117	82.47 93	85.31 116	60.91 156	79.73 122	80.26 77	86.30 99	88.27 137	69.67 108	87.20 102	84.98 99	89.97 96	80.67 126

Fast-Effi-MVS+		81.42 101	83.82 115	78.62 101	82.24 118	80.62 106	87.72 93	63.51 136	73.01 145	74.75 104	83.80 120	92.70 96	73.44 84	88.15 95	85.26 96	90.05 94	83.17 102

PVSNet_Blended_VisFu		83.00 87	84.16 111	81.65 72	82.17 119	86.01 68	88.03 90	71.23 65	76.05 136	79.54 82	83.88 118	83.44 152	77.49 50	87.38 98	84.93 100	91.41 80	87.40 75

pmmvs6		80.46 107	88.34 65	71.26 141	81.96 120	77.51 127	77.54 161	68.83 84	93.72 7	55.92 175	93.94 18	98.03 10	55.94 164	89.21 83	85.61 93	87.36 129	80.38 128

IterMVS-LS		79.79 112	82.56 124	76.56 114	81.83 121	77.85 125	79.90 150	69.42 78	78.93 126	71.21 126	90.47 53	85.20 150	70.86 103	80.54 155	80.57 136	86.15 140	84.36 92
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		73.07 157	77.02 150	68.46 161	81.62 122	72.89 159	79.56 154	70.78 68	69.56 160	52.52 186	77.37 151	81.12 162	42.60 197	84.20 129	83.93 109	83.65 160	70.07 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		72.68 159	75.21 165	69.73 153	81.48 123	69.04 173	70.48 190	76.67 36	86.92 59	67.80 148	88.06 83	64.67 195	42.12 199	77.60 165	73.65 170	79.81 171	66.57 178

USDC		81.39 103	83.07 121	79.43 95	81.48 123	78.95 118	82.62 132	66.17 107	87.45 54	90.73 4	82.40 126	93.65 85	66.57 127	83.63 132	77.97 150	89.00 109	77.45 148

casdiffmvs		79.93 111	84.11 112	75.05 122	81.41 125	78.99 117	82.95 129	62.90 143	81.53 102	68.60 143	91.94 37	96.03 37	65.84 131	82.89 135	77.07 158	88.59 116	80.34 132

tfpnnormal		77.16 130	84.26 108	68.88 159	81.02 126	75.02 149	76.52 168	63.30 138	87.29 55	52.40 187	91.24 49	93.97 80	54.85 171	85.46 116	81.08 132	85.18 153	75.76 153

thres600view7		74.34 150	78.43 139	69.56 155	80.47 127	76.28 139	78.65 159	62.56 145	77.39 130	52.53 185	74.03 173	76.78 177	55.90 166	85.06 119	85.19 97	87.25 130	74.29 157

OpenMVS	75.38 16	78.44 125	81.39 130	74.99 125	80.46 128	79.85 109	79.99 148	58.31 170	77.34 131	73.85 110	77.19 152	82.33 159	68.60 116	84.67 126	81.95 126	88.72 113	86.40 80

pm-mvs1		78.21 126	85.68 90	69.50 156	80.38 129	75.73 144	76.25 169	65.04 118	87.59 52	54.47 180	93.16 25	95.99 41	54.20 173	86.37 108	82.98 122	86.64 134	77.96 146

v148		79.33 120	82.32 125	75.84 116	80.14 130	75.74 143	81.98 136	57.06 173	81.51 104	79.36 84	89.42 66	96.42 28	71.32 97	81.54 149	75.29 167	85.20 152	76.32 149

pmmvs-eth3d		79.64 114	82.06 127	76.83 111	80.05 131	72.64 160	87.47 96	66.59 103	80.83 113	73.50 112	89.32 69	93.20 91	67.78 119	80.78 153	81.64 130	85.58 150	76.01 150

testgi		68.20 176	76.05 159	59.04 189	79.99 132	67.32 179	81.16 141	51.78 192	84.91 76	39.36 207	73.42 177	95.19 57	32.79 207	76.54 172	70.40 180	69.14 194	64.55 182

DI_MVS_plusplus_trai		77.64 128	79.64 134	75.31 120	79.87 133	76.89 135	81.55 140	63.64 134	76.21 135	72.03 121	85.59 108	82.97 156	66.63 126	79.27 161	77.78 152	88.14 121	78.76 142

Fast-Effi-MVS+-dtu		76.92 131	77.18 149	76.62 113	79.55 134	79.17 115	84.80 118	77.40 30	64.46 184	68.75 141	70.81 190	86.57 143	63.36 144	81.74 146	81.76 128	85.86 146	75.78 152

thres400		73.13 156	76.99 152	68.62 160	79.46 135	74.93 151	77.23 163	61.23 154	75.54 137	52.31 188	72.20 181	77.10 175	54.89 169	82.92 134	82.62 124	86.57 136	73.66 162

QAPM		80.43 108	84.34 106	75.86 115	79.40 136	82.06 96	79.86 151	61.94 149	83.28 85	74.73 105	81.74 129	85.44 148	70.97 101	84.99 124	84.71 104	88.29 119	88.14 68

DELS-MVS		79.71 113	83.74 116	75.01 124	79.31 137	82.68 90	84.79 119	60.06 162	75.43 139	69.09 137	86.13 101	89.38 127	67.16 123	85.12 118	83.87 111	89.65 99	83.57 99
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 94	86.07 86	77.71 106	79.31 137	84.61 76	87.18 99	61.02 155	85.65 68	76.11 95	85.07 113	85.38 149	70.96 102	87.22 101	86.47 85	91.66 77	88.12 69

ET-MVSNet_ETH3D		74.71 148	74.19 168	75.31 120	79.22 139	75.29 147	82.70 131	64.05 128	65.45 179	70.96 129	77.15 153	57.70 207	65.89 130	84.40 128	81.65 129	89.03 108	77.67 147

test-LLR		62.15 191	59.46 207	65.29 179	79.07 140	52.66 203	69.46 196	62.93 141	50.76 211	53.81 182	63.11 205	58.91 203	52.87 180	66.54 200	62.34 193	73.59 179	61.87 191

test0.0.03 1		61.79 193	65.33 189	57.65 192	79.07 140	64.09 187	68.51 199	62.93 141	61.59 197	33.71 210	61.58 207	71.58 191	33.43 206	70.95 190	68.68 185	68.26 196	58.82 197

baseline1		69.62 169	73.55 172	65.02 181	78.95 142	70.39 166	71.38 189	62.03 148	70.97 156	47.95 197	78.47 144	68.19 193	47.77 193	79.65 160	76.94 160	82.05 167	70.27 169

MVS_Test		76.72 133	79.40 136	73.60 131	78.85 143	74.99 150	79.91 149	61.56 151	69.67 159	72.44 117	85.98 104	90.78 120	63.50 142	78.30 163	75.74 165	85.33 151	80.31 133

FMVSNet1		78.20 127	84.83 102	70.46 149	78.62 144	79.03 116	77.90 160	67.53 99	83.02 87	55.10 178	87.19 92	93.18 92	55.65 167	85.57 113	83.39 115	87.98 122	82.40 113

GA-MVS		75.01 147	76.39 155	73.39 133	78.37 145	75.66 145	80.03 147	58.40 169	70.51 157	75.85 97	83.24 121	76.14 179	63.75 138	77.28 167	76.62 161	83.97 159	75.30 155

thres200		72.41 160	76.00 160	68.21 163	78.28 146	76.28 139	74.94 179	62.56 145	72.14 152	51.35 193	69.59 196	76.51 178	54.89 169	85.06 119	80.51 138	87.25 130	71.92 165

EPNet_dtu		71.90 162	73.03 174	70.59 147	78.28 146	61.64 191	82.44 133	64.12 126	63.26 188	69.74 133	71.47 184	82.41 157	51.89 186	78.83 162	78.01 149	77.07 176	75.60 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs4		75.92 140	77.48 148	74.10 130	78.21 148	70.94 164	84.06 122	64.78 120	75.13 140	68.47 144	84.12 117	83.32 153	64.74 136	75.93 175	79.14 148	84.31 157	73.77 160

PM-MVS		80.42 109	83.63 117	76.67 112	78.04 149	72.37 162	87.14 100	60.18 161	80.13 118	71.75 123	86.12 102	93.92 82	77.08 52	86.56 106	85.12 98	85.83 147	81.18 121

thres100view900		69.86 168	72.97 175	66.24 172	77.97 150	72.49 161	73.29 183	59.12 165	66.81 171	50.82 194	67.30 199	75.67 182	50.54 188	78.24 164	79.40 145	85.71 149	70.88 167

tfpn200view9		72.01 161	75.40 163	68.06 164	77.97 150	76.44 137	77.04 165	62.67 144	66.81 171	50.82 194	67.30 199	75.67 182	52.46 185	85.06 119	82.64 123	87.41 128	73.86 159

Vis-MVSNet		83.32 83	88.12 68	77.71 106	77.91 152	83.44 86	90.58 60	69.49 76	81.11 110	67.10 150	89.85 61	91.48 114	71.71 96	91.34 60	89.37 64	89.48 103	90.26 51
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchMatch-RL		76.05 139	76.64 153	75.36 119	77.84 153	69.87 170	81.09 142	63.43 137	71.66 153	68.34 145	71.70 182	81.76 160	74.98 71	84.83 125	83.44 114	86.45 138	73.22 163

CANet_DTU		75.04 146	78.45 138	71.07 142	77.27 154	77.96 124	83.88 124	58.00 171	64.11 185	68.67 142	75.65 166	88.37 136	53.92 176	82.05 143	81.11 131	84.67 155	79.88 135

MS-PatchMatch		71.18 166	73.99 170	67.89 167	77.16 155	71.76 163	77.18 164	56.38 175	67.35 169	55.04 179	74.63 171	75.70 181	62.38 145	76.62 170	75.97 164	79.22 173	75.90 151

new-patchmatchnet		62.59 190	73.79 171	49.53 204	76.98 156	53.57 201	53.46 212	54.64 180	85.43 71	28.81 211	91.94 37	96.41 29	25.28 209	76.80 168	53.66 207	57.99 205	58.69 198

GBi-Net		73.17 154	77.64 145	67.95 165	76.76 157	77.36 129	75.77 173	64.57 121	62.99 191	51.83 190	76.05 160	77.76 172	52.73 182	85.57 113	83.39 115	86.04 142	80.37 129

PVSNet_BlendedMVS		76.45 136	78.12 140	74.49 128	76.76 157	78.46 120	79.65 152	63.26 139	65.42 180	73.15 114	75.05 169	88.96 131	66.51 128	82.73 138	77.66 153	87.61 126	78.60 143

PVSNet_Blended		76.45 136	78.12 140	74.49 128	76.76 157	78.46 120	79.65 152	63.26 139	65.42 180	73.15 114	75.05 169	88.96 131	66.51 128	82.73 138	77.66 153	87.61 126	78.60 143

test1		73.17 154	77.64 145	67.95 165	76.76 157	77.36 129	75.77 173	64.57 121	62.99 191	51.83 190	76.05 160	77.76 172	52.73 182	85.57 113	83.39 115	86.04 142	80.37 129

FMVSNet2		74.43 149	79.70 133	68.27 162	76.76 157	77.36 129	75.77 173	65.36 116	72.28 149	52.97 184	81.92 128	85.61 147	52.73 182	80.66 154	79.73 143	86.04 142	80.37 129

IB-MVS	71.28 17	75.21 145	77.00 151	73.12 136	76.76 157	77.45 128	83.05 127	58.92 167	63.01 190	64.31 157	59.99 208	87.57 140	68.64 115	86.26 110	82.34 125	87.05 132	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
thisisatest0515		81.18 106	84.32 107	77.52 110	76.73 163	74.84 152	85.06 117	61.37 152	81.05 111	73.95 109	88.79 78	89.25 130	75.49 66	85.98 111	84.78 102	92.53 68	85.56 86

IterMVS-SCA-FT		77.23 129	79.18 137	74.96 126	76.67 164	79.85 109	75.58 178	61.34 153	73.10 144	73.79 111	86.23 100	79.61 165	79.00 36	80.28 157	75.50 166	83.41 164	79.70 136

FC-MVSNet-test		75.91 141	83.59 118	66.95 170	76.63 165	69.07 172	85.33 115	64.97 119	84.87 77	41.95 202	93.17 24	87.04 141	47.78 192	91.09 67	85.56 94	85.06 154	74.34 156

Anonymous20231206		67.28 178	73.41 173	60.12 188	76.45 166	63.61 189	74.21 181	56.52 174	76.35 133	42.23 201	75.81 165	90.47 122	41.51 200	74.52 176	69.97 182	69.83 192	63.17 187

baseline2		68.71 174	68.34 182	69.14 157	75.69 167	69.70 171	76.60 167	55.53 178	60.13 199	62.07 165	66.76 201	60.35 200	60.77 148	76.53 173	74.03 169	84.19 158	70.88 167

diffmvs		76.74 132	81.61 129	71.06 143	75.64 168	74.45 155	80.68 144	57.57 172	77.48 129	67.62 149	88.95 74	93.94 81	61.98 146	79.74 158	76.18 162	82.85 165	80.50 127

tttt0517		75.86 142	76.23 157	75.42 118	75.55 169	74.06 156	82.73 130	60.31 158	69.24 161	70.24 132	79.18 136	58.79 205	72.17 91	84.49 127	83.08 120	91.54 78	84.80 88

thisisatest0530		75.54 144	75.95 161	75.05 122	75.08 170	73.56 157	82.15 135	60.31 158	69.17 162	69.32 135	79.02 137	58.78 206	72.17 91	83.88 130	83.08 120	91.30 83	84.20 94

FMVSNet3		71.40 165	75.20 166	66.97 169	75.00 171	76.59 136	74.29 180	64.57 121	62.99 191	51.83 190	76.05 160	77.76 172	51.49 187	76.58 171	77.03 159	84.62 156	79.43 138

tpm cat1		64.79 185	62.74 198	67.17 168	74.61 172	65.91 183	76.18 170	59.32 164	64.88 183	66.41 153	71.21 187	53.56 215	59.17 152	61.53 206	58.16 201	67.33 197	63.95 183

UGNet		79.62 115	85.91 88	72.28 138	73.52 173	83.91 79	86.64 106	69.51 75	79.85 121	62.57 162	85.82 106	89.63 125	53.18 178	88.39 91	87.35 77	88.28 120	86.43 79
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					73.27 174	70.91 165	83.26 125

HyFIR lowres test		73.29 153	74.14 169	72.30 137	73.08 175	78.33 122	83.12 126	62.41 147	63.81 186	62.13 164	76.67 156	78.50 169	71.09 99	74.13 179	77.47 156	81.98 168	70.10 170

MIMVSNet1		73.40 152	81.85 128	63.55 182	72.90 176	64.37 186	84.58 120	53.60 186	90.84 20	53.92 181	87.75 85	96.10 34	45.31 195	85.37 117	79.32 146	70.98 190	69.18 175

CostFormer		66.81 180	66.94 185	66.67 171	72.79 177	68.25 175	79.55 155	55.57 177	65.52 178	62.77 161	76.98 154	60.09 201	56.73 161	65.69 202	62.35 192	72.59 182	69.71 172

CR-MVSNet		69.56 170	68.34 182	70.99 144	72.78 178	67.63 176	64.47 202	67.74 97	59.93 200	72.30 118	80.10 132	56.77 209	65.04 134	71.64 187	72.91 173	83.61 162	69.40 173

CVMVSNet		75.65 143	77.62 147	73.35 135	71.95 179	69.89 169	83.04 128	60.84 157	69.12 163	68.76 140	79.92 135	78.93 168	73.64 83	81.02 151	81.01 133	81.86 169	83.43 100

IterMVS		73.62 151	76.53 154	70.23 150	71.83 180	77.18 133	80.69 143	53.22 188	72.23 150	66.62 152	85.21 110	78.96 167	69.54 110	76.28 174	71.63 177	79.45 172	74.25 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		67.02 179	63.99 193	70.56 148	71.55 181	67.63 176	75.81 171	69.44 77	59.93 200	63.24 159	64.32 203	47.51 217	59.68 150	70.37 191	69.64 183	83.64 161	68.49 176

dps		65.14 182	64.50 191	65.89 177	71.41 182	65.81 184	71.44 188	61.59 150	58.56 203	61.43 166	75.45 167	52.70 216	58.06 157	69.57 193	64.65 190	71.39 187	64.77 181

MDTV_nov1_ep13_2view		72.96 158	75.59 162	69.88 152	71.15 183	64.86 185	82.31 134	54.45 182	76.30 134	78.32 89	86.52 97	91.58 111	61.35 147	76.80 168	66.83 188	71.70 183	66.26 179

TAMVS		63.02 186	69.30 179	55.70 196	70.12 184	56.89 197	69.63 194	45.13 199	70.23 158	38.00 208	77.79 145	75.15 184	42.60 197	74.48 177	72.81 175	68.70 195	57.75 201

tpm		62.79 188	63.25 195	62.26 186	70.09 185	53.78 200	71.65 187	47.31 198	65.72 177	76.70 93	80.62 131	56.40 212	48.11 191	64.20 204	58.54 199	59.70 203	63.47 185

V42		79.59 116	83.59 118	74.93 127	69.61 186	77.05 134	86.59 107	55.84 176	78.42 128	77.29 91	89.84 62	95.08 62	74.12 76	83.05 133	80.11 142	86.12 141	81.59 119

PatchmatchNet		64.81 184	63.74 194	66.06 176	69.21 187	58.62 195	73.16 184	60.01 163	65.92 175	66.19 154	76.27 158	59.09 202	60.45 149	66.58 199	61.47 198	67.33 197	58.24 199
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 1792x2688		68.80 173	71.09 176	66.13 174	69.11 188	68.89 174	78.98 157	54.68 179	61.63 196	56.69 172	71.56 183	78.39 170	67.69 120	72.13 186	72.01 176	69.63 193	73.02 164

MIMVSNet		63.02 186	69.02 180	56.01 194	68.20 189	59.26 194	70.01 193	53.79 185	71.56 154	41.26 205	71.38 185	82.38 158	36.38 203	71.43 189	67.32 187	66.45 199	59.83 196

CMPMVS	55.74 18	71.56 163	76.26 156	66.08 175	68.11 190	63.91 188	63.17 204	50.52 196	68.79 166	75.49 98	70.78 191	85.67 146	63.54 141	81.58 147	77.20 157	75.63 177	85.86 82
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SCA		68.54 175	67.52 184	69.73 153	67.79 191	75.04 148	76.96 166	68.94 83	66.41 173	67.86 147	74.03 173	60.96 198	65.55 132	68.99 194	65.67 189	71.30 188	61.54 194

EU-MVSNet		76.48 135	80.53 132	71.75 140	67.62 192	70.30 167	81.74 138	54.06 184	75.47 138	71.01 128	80.10 132	93.17 93	73.67 81	83.73 131	77.85 151	82.40 166	83.07 103

tpmrst		59.42 195	60.02 205	58.71 190	67.56 193	53.10 202	66.99 200	51.88 191	63.80 187	57.68 170	76.73 155	56.49 211	48.73 190	56.47 210	55.55 203	59.43 204	58.02 200

pmmvs5		68.91 172	74.35 167	62.56 184	67.45 194	66.78 180	71.70 186	51.47 193	67.17 170	56.25 174	82.41 125	88.59 135	47.21 194	73.21 185	74.23 168	81.30 170	68.03 177

MDTV_nov1_ep13		64.96 183	64.77 190	65.18 180	67.08 195	62.46 190	75.80 172	51.10 195	62.27 195	69.74 133	74.12 172	62.65 196	55.64 168	68.19 196	62.16 196	71.70 183	61.57 193

E-PMN		59.07 197	62.79 197	54.72 197	67.01 196	47.81 209	60.44 207	43.40 200	72.95 146	44.63 200	70.42 193	73.17 188	58.73 154	80.97 152	51.98 208	54.14 208	42.26 210

baseline		69.33 171	75.37 164	62.28 185	66.54 197	66.67 181	73.95 182	48.07 197	66.10 174	59.26 168	82.45 124	86.30 144	54.44 172	74.42 178	73.25 172	71.42 186	78.43 145

N_pmnet		54.95 204	65.90 187	42.18 205	66.37 198	43.86 212	57.92 209	39.79 204	79.54 123	17.24 215	86.31 98	87.91 138	25.44 208	64.68 203	51.76 209	46.33 211	47.23 208

MVSTER		68.08 177	69.73 178	66.16 173	66.33 199	70.06 168	75.71 176	52.36 190	55.18 208	58.64 169	70.23 195	56.72 210	57.34 159	79.68 159	76.03 163	86.61 135	80.20 134

EMVS		58.97 198	62.63 199	54.70 198	66.26 200	48.71 207	61.74 205	42.71 201	72.80 148	46.00 199	73.01 180	71.66 189	57.91 158	80.41 156	50.68 210	53.55 209	41.11 211

anonymousdsp		85.62 61	90.53 48	79.88 92	64.64 201	76.35 138	96.28 13	53.53 187	85.63 69	81.59 70	92.81 30	97.71 14	86.88 2	94.56 26	92.83 25	96.35 6	93.84 8

EPMVS		56.62 201	59.77 206	52.94 201	62.41 202	50.55 206	60.66 206	52.83 189	65.15 182	41.80 203	77.46 150	57.28 208	42.68 196	59.81 208	54.82 204	57.23 206	53.35 204

FMVSNet5		56.37 202	60.14 204	51.98 203	60.83 203	59.58 193	66.85 201	42.37 202	52.68 210	41.33 204	47.09 211	54.68 213	35.28 204	73.88 180	70.77 179	65.24 200	62.26 190

ADS-MVSNet		56.89 200	61.09 201	52.00 202	59.48 204	48.10 208	58.02 208	54.37 183	72.82 147	49.19 196	75.32 168	65.97 194	37.96 202	59.34 209	54.66 205	52.99 210	51.42 206

new_pmnet		52.29 205	63.16 196	39.61 207	58.89 205	44.70 211	48.78 214	34.73 207	65.88 176	17.85 214	73.42 177	80.00 164	23.06 210	67.00 198	62.28 195	54.36 207	48.81 207

MVS-HIRNet		59.74 194	58.74 210	60.92 187	57.74 206	45.81 210	56.02 210	58.69 168	55.69 206	65.17 155	70.86 189	71.66 189	56.75 160	61.11 207	53.74 206	71.17 189	52.28 205

PatchT		66.25 181	66.76 186	65.67 178	55.87 207	60.75 192	70.17 191	59.00 166	59.80 202	72.30 118	78.68 142	54.12 214	65.04 134	71.64 187	72.91 173	71.63 185	69.40 173

test-mter		59.39 196	61.59 200	56.82 193	53.21 208	54.82 199	73.12 185	26.57 211	53.19 209	56.31 173	64.71 202	60.47 199	56.36 163	68.69 195	64.27 191	75.38 178	65.00 180

CHOSEN 280x420		56.32 203	58.85 209	53.36 200	51.63 209	39.91 213	69.12 198	38.61 205	56.29 205	36.79 209	48.84 210	62.59 197	63.39 143	73.61 183	67.66 186	60.61 201	63.07 188

TESTMET0.1,1		57.21 199	59.46 207	54.60 199	50.95 210	52.66 203	69.46 196	26.91 210	50.76 211	53.81 182	63.11 205	58.91 203	52.87 180	66.54 200	62.34 193	73.59 179	61.87 191

pmmvs3		62.72 189	68.71 181	55.74 195	50.74 211	57.10 196	70.05 192	28.82 209	61.57 198	57.39 171	71.19 188	85.73 145	53.96 175	73.36 184	69.43 184	73.47 181	62.55 189

MDA-MVSNet-bldmvs		76.51 134	82.87 123	69.09 158	50.71 212	74.72 154	84.05 123	60.27 160	81.62 101	71.16 127	88.21 82	91.58 111	69.62 109	92.78 45	77.48 155	78.75 175	73.69 161

PMMVS		61.98 192	65.61 188	57.74 191	45.03 213	51.76 205	69.54 195	35.05 206	55.49 207	55.32 177	68.23 197	78.39 170	58.09 156	70.21 192	71.56 178	83.42 163	63.66 184

PMMVS2		48.13 207	64.06 192	29.55 208	44.06 214	36.69 214	51.95 213	29.97 208	74.75 142	8.90 217	76.02 163	91.24 117	7.53 211	73.78 181	55.91 202	34.87 213	40.01 212

MVE	41.12 19	51.80 206	60.92 202	41.16 206	35.21 215	34.14 215	48.45 215	41.39 203	69.11 164	19.53 213	63.33 204	73.80 186	63.56 140	67.19 197	61.51 197	38.85 212	57.38 202
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				13.54 210	16.73 216	6.42 217	8.49 217	2.36 213	28.69 214	27.44 212	18.40 213	13.51 220	3.70 212	33.23 211	36.26 211	22.54 215

test123		1.06 209	1.41 211	0.64 211	0.39 217	0.48 218	0.52 220	0.25 215	1.11 216	1.37 219	2.01 215	1.98 221	0.87 213	1.43 213	1.27 212	0.46 217	1.62 214

testmvs		0.93 210	1.37 212	0.41 212	0.36 218	0.36 219	0.62 219	0.39 214	1.48 215	0.18 220	2.41 214	1.31 222	0.41 214	1.25 214	1.08 213	0.48 216	1.68 213

GG-mvs-BLEND		41.63 208	60.36 203	19.78 209	0.14 219	66.04 182	55.66 211	0.17 216	57.64 204	2.42 218	51.82 209	69.42 192	0.28 215	64.11 205	58.29 200	60.02 202	55.18 203

uanet_test		0.00 211	0.00 213	0.00 213	0.00 220	0.00 220	0.00 221	0.00 217	0.00 217	0.00 221	0.00 216	0.00 223	0.00 216	0.00 215	0.00 214	0.00 218	0.00 215

sosnet-low-res		0.00 211	0.00 213	0.00 213	0.00 220	0.00 220	0.00 221	0.00 217	0.00 217	0.00 221	0.00 216	0.00 223	0.00 216	0.00 215	0.00 214	0.00 218	0.00 215

sosnet		0.00 211	0.00 213	0.00 213	0.00 220	0.00 220	0.00 221	0.00 217	0.00 217	0.00 221	0.00 216	0.00 223	0.00 216	0.00 215	0.00 214	0.00 218	0.00 215

RE-MVS-def										87.10 29

9.14												89.43 126

MTAPA										89.37 9		94.85 67

MTMP										90.54 5		95.16 59

Patchmatch-RL test							4.13 218

NP-MVS									78.65 127

Patchmtry						56.88 198	64.47 202	67.74 97		72.30 118

DeepMVS_CX						17.78 216	20.40 216	6.69 212	31.41 213	9.80 216	38.61 212	34.88 219	33.78 205	28.41 212		23.59 214	45.77 209

High-resolution multi-view benchmark