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.

HPM-MVS++		87.09 4	88.92 8	84.95 3	92.61 1	87.91 33	90.23 9	76.06 3	88.85 7	81.20 4	87.33 9	87.93 7	79.47 6	88.59 5	88.23 4	90.15 27	93.60 15

ESAPD		88.45 1	91.07 1	85.40 1	91.72 2	92.05 1	91.94 2	76.73 1	90.28 3	80.34 7	92.58 1	90.41 1	80.69 3	88.99 4	87.65 8	90.99 6	95.51 1

NCCC		85.34 14	86.59 19	83.88 10	91.48 3	88.88 19	89.79 11	75.54 7	86.67 15	77.94 17	76.55 29	84.99 19	78.07 11	88.04 8	87.68 7	90.46 19	93.31 16

CNVR-MVS		86.36 9	88.19 12	84.23 6	91.33 4	89.84 9	90.34 6	75.56 6	87.36 12	78.97 11	81.19 22	86.76 11	78.74 7	89.30 2	88.58 1	90.45 20	94.33 5

APDe-MVS		88.00 2	90.50 2	85.08 2	90.95 5	91.58 4	92.03 1	75.53 8	91.15 1	80.10 8	92.27 3	88.34 6	80.80 2	88.00 10	86.99 13	91.09 4	95.16 2

SteuartSystems-ACMMP		85.99 10	88.31 11	83.27 15	90.73 6	89.84 9	90.27 8	74.31 10	84.56 24	75.88 23	87.32 10	85.04 18	77.31 18	89.01 3	88.46 2	91.14 3	93.96 7
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		86.84 7	88.91 9	84.41 4	90.66 7	90.10 7	90.78 3	75.64 5	87.38 11	78.72 12	90.68 6	86.82 10	80.15 4	87.13 19	86.45 22	90.51 14	93.83 9
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MP-MVS		85.50 13	87.40 15	83.28 14	90.65 8	89.51 14	89.16 17	74.11 13	83.70 27	78.06 16	85.54 14	84.89 21	77.31 18	87.40 16	87.14 12	90.41 21	93.65 14

train_agg		84.86 19	87.21 16	82.11 21	90.59 9	85.47 48	89.81 10	73.55 19	83.95 26	73.30 31	89.84 8	87.23 9	75.61 26	86.47 28	85.46 32	89.78 30	92.06 26

MCST-MVS		85.13 17	86.62 18	83.39 12	90.55 10	89.82 11	89.29 15	73.89 17	84.38 25	76.03 22	79.01 25	85.90 15	78.47 8	87.81 12	86.11 27	92.11 1	93.29 17

MPTG		85.71 11	86.88 17	84.34 5	90.54 11	87.11 37	89.77 12	74.17 12	88.54 8	83.08 2	78.60 26	86.10 13	78.11 10	87.80 13	87.46 10	90.35 23	92.56 20

DeepC-MVS_fast	78.24 3	84.27 23	85.50 25	82.85 17	90.46 12	89.24 16	87.83 26	74.24 11	84.88 20	76.23 21	75.26 32	81.05 35	77.62 15	88.02 9	87.62 9	90.69 10	92.41 22
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP_Plus		86.52 8	89.01 6	83.62 11	90.28 13	90.09 8	90.32 7	74.05 14	88.32 9	79.74 9	87.04 11	85.59 17	76.97 23	89.35 1	88.44 3	90.35 23	94.27 6

SD-MVS		86.96 5	89.45 4	84.05 9	90.13 14	89.23 17	89.77 12	74.59 9	89.17 5	80.70 5	89.93 7	89.67 2	78.47 8	87.57 14	86.79 16	90.67 11	93.76 11

ACMMPR		85.52 12	87.53 14	83.17 16	90.13 14	89.27 15	89.30 14	73.97 15	86.89 14	77.14 19	86.09 12	83.18 25	77.74 14	87.42 15	87.20 11	90.77 7	92.63 19

PGM-MVS		84.42 22	86.29 22	82.23 20	90.04 16	88.82 21	89.23 16	71.74 28	82.82 30	74.61 26	84.41 17	82.09 27	77.03 22	87.13 19	86.73 18	90.73 9	92.06 26

HSP-MVS		87.45 3	90.22 3	84.22 7	90.00 17	91.80 3	90.59 4	75.80 4	89.93 4	78.35 14	92.54 2	89.18 3	80.89 1	87.99 11	86.29 24	89.70 34	93.85 8

CSCG		85.28 16	87.68 13	82.49 19	89.95 18	91.99 2	88.82 18	71.20 30	86.41 16	79.63 10	79.26 23	88.36 5	73.94 33	86.64 26	86.67 19	91.40 2	94.41 3

mPP-MVS					89.90 19							81.29 34

TSAR-MVS + MP.		86.88 6	89.23 5	84.14 8	89.78 20	88.67 25	90.59 4	73.46 20	88.99 6	80.52 6	91.26 4	88.65 4	79.91 5	86.96 24	86.22 25	90.59 12	93.83 9

X-MVS		83.23 26	85.20 27	80.92 27	89.71 21	88.68 22	88.21 25	73.60 18	82.57 31	71.81 39	77.07 27	81.92 29	71.72 48	86.98 23	86.86 14	90.47 16	92.36 23

TSAR-MVS + ACMM		85.10 18	88.81 10	80.77 28	89.55 22	88.53 27	88.59 21	72.55 23	87.39 10	71.90 36	90.95 5	87.55 8	74.57 28	87.08 21	86.54 20	87.47 70	93.67 12

CP-MVS		84.74 21	86.43 21	82.77 18	89.48 23	88.13 32	88.64 19	73.93 16	84.92 19	76.77 20	81.94 20	83.50 23	77.29 20	86.92 25	86.49 21	90.49 15	93.14 18

CDPH-MVS		82.64 27	85.03 28	79.86 32	89.41 24	88.31 29	88.32 23	71.84 27	80.11 38	67.47 54	82.09 19	81.44 33	71.85 46	85.89 33	86.15 26	90.24 25	91.25 32

DeepC-MVS	78.47 2	84.81 20	86.03 23	83.37 13	89.29 25	90.38 6	88.61 20	76.50 2	86.25 17	77.22 18	75.12 33	80.28 37	77.59 16	88.39 6	88.17 5	91.02 5	93.66 13
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		79.74 40	78.62 51	81.05 26	89.23 26	86.06 45	84.95 42	71.96 26	79.39 41	75.51 24	63.16 72	68.84 78	76.51 24	83.55 48	82.85 47	88.13 57	86.46 61

EPNet		79.08 47	80.62 42	77.28 46	88.90 27	83.17 65	83.65 47	72.41 24	74.41 51	67.15 56	76.78 28	74.37 53	64.43 99	83.70 47	83.69 43	87.15 76	88.19 50
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	79.04 1	85.30 15	88.93 7	81.06 25	88.77 28	90.48 5	85.46 39	73.08 21	90.97 2	73.77 30	84.81 16	85.95 14	77.43 17	88.22 7	87.73 6	87.85 65	94.34 4

ACMMP		83.42 25	85.27 26	81.26 24	88.47 29	88.49 28	88.31 24	72.09 25	83.42 28	72.77 34	82.65 18	78.22 41	75.18 27	86.24 31	85.76 29	90.74 8	92.13 25
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
3Dnovator+	75.73 4	82.40 28	82.76 33	81.97 22	88.02 30	89.67 12	86.60 30	71.48 29	81.28 36	78.18 15	64.78 68	77.96 43	77.13 21	87.32 17	86.83 15	90.41 21	91.48 30

OPM-MVS		79.68 41	79.28 50	80.15 31	87.99 31	86.77 40	88.52 22	72.72 22	64.55 80	67.65 53	67.87 59	74.33 54	74.31 31	86.37 30	85.25 34	89.73 33	89.81 43

MAR-MVS		79.21 44	80.32 46	77.92 44	87.46 32	88.15 31	83.95 46	67.48 54	74.28 52	68.25 50	64.70 69	77.04 44	72.17 43	85.42 35	85.00 36	88.22 54	87.62 55
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
HQP-MVS		81.19 34	83.27 31	78.76 39	87.40 33	85.45 49	86.95 28	70.47 33	81.31 35	66.91 57	79.24 24	76.63 45	71.67 49	84.43 41	83.78 42	89.19 43	92.05 28

abl_6				79.05 36	87.27 34	88.85 20	83.62 48	68.25 47	81.68 34	72.94 33	73.79 39	84.45 22	72.55 41			89.66 36	90.64 37

CANet		81.62 33	83.41 30	79.53 34	87.06 35	88.59 26	85.47 38	67.96 51	76.59 46	74.05 27	74.69 34	81.98 28	72.98 39	86.14 32	85.47 31	89.68 35	90.42 40

MSLP-MVS++		82.09 30	82.66 34	81.42 23	87.03 36	87.22 36	85.82 35	70.04 35	80.30 37	78.66 13	68.67 55	81.04 36	77.81 13	85.19 37	84.88 37	89.19 43	91.31 31

ACMM	72.26 8	78.86 48	78.13 52	79.71 33	86.89 37	83.40 62	86.02 33	70.50 32	75.28 48	71.49 43	63.01 73	69.26 72	73.57 35	84.11 43	83.98 41	89.76 32	87.84 53
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					86.63 38	88.68 22	85.00 40			71.81 39		81.92 29				90.47 16

X-MVStestdata					86.63 38	88.68 22	85.00 40			71.81 39		81.92 29				90.47 16

PHI-MVS		82.36 29	85.89 24	78.24 42	86.40 40	89.52 13	85.52 37	69.52 41	82.38 33	65.67 59	81.35 21	82.36 26	73.07 38	87.31 18	86.76 17	89.24 41	91.56 29

LGP-MVS_train		79.83 37	81.22 40	78.22 43	86.28 41	85.36 51	86.76 29	69.59 39	77.34 43	65.14 61	75.68 31	70.79 64	71.37 51	84.60 39	84.01 40	90.18 26	90.74 36

MVS_0304		81.73 32	83.86 29	79.26 35	86.22 42	89.18 18	86.41 31	67.15 55	75.28 48	70.75 46	74.59 35	83.49 24	74.42 30	87.05 22	86.34 23	90.58 13	91.08 34

CPTT-MVS		81.77 31	83.10 32	80.21 30	85.93 43	86.45 43	87.72 27	70.98 31	82.54 32	71.53 42	74.23 38	81.49 32	76.31 25	82.85 55	81.87 51	88.79 50	92.26 24

MVS_111021_HR		80.13 36	81.46 38	78.58 40	85.77 44	85.17 52	83.45 49	69.28 42	74.08 54	70.31 47	74.31 37	75.26 51	73.13 37	86.46 29	85.15 35	89.53 37	89.81 43

ACMP	73.23 7	79.79 38	80.53 43	78.94 37	85.61 45	85.68 46	85.61 36	69.59 39	77.33 44	71.00 45	74.45 36	69.16 73	71.88 44	83.15 52	83.37 45	89.92 29	90.57 39
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		74.47 62	77.80 54	70.59 81	85.33 46	85.40 50	73.54 130	65.98 63	60.65 104	56.00 105	72.11 42	79.15 38	54.63 156	83.13 53	82.25 49	88.04 59	81.92 120

TSAR-MVS + GP.		83.69 24	86.58 20	80.32 29	85.14 47	86.96 38	84.91 43	70.25 34	84.71 23	73.91 29	85.16 15	85.63 16	77.92 12	85.44 34	85.71 30	89.77 31	92.45 21

LS3D		74.08 63	73.39 73	74.88 57	85.05 48	82.62 68	79.71 61	68.66 45	72.82 56	58.80 80	57.61 99	61.31 97	71.07 53	80.32 79	78.87 88	86.00 123	80.18 133

QAPM		78.47 49	80.22 47	76.43 50	85.03 49	86.75 41	80.62 56	66.00 62	73.77 55	65.35 60	65.54 66	78.02 42	72.69 40	83.71 46	83.36 46	88.87 49	90.41 41

OpenMVS	70.44 10	76.15 57	76.82 64	75.37 54	85.01 50	84.79 54	78.99 69	62.07 98	71.27 58	67.88 52	57.91 98	72.36 59	70.15 55	82.23 58	81.41 55	88.12 58	87.78 54

CLD-MVS		79.35 43	81.23 39	77.16 47	85.01 50	86.92 39	85.87 34	60.89 107	80.07 40	75.35 25	72.96 40	73.21 57	68.43 64	85.41 36	84.63 38	87.41 71	85.44 72
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
3Dnovator	73.76 5	79.75 39	80.52 44	78.84 38	84.94 52	87.35 34	84.43 45	65.54 65	78.29 42	73.97 28	63.00 74	75.62 50	74.07 32	85.00 38	85.34 33	90.11 28	89.04 46

PCF-MVS	73.28 6	79.42 42	80.41 45	78.26 41	84.88 53	88.17 30	86.08 32	69.85 36	75.23 50	68.43 49	68.03 58	78.38 40	71.76 47	81.26 69	80.65 70	88.56 53	91.18 33
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DELS-MVS		79.15 46	81.07 41	76.91 48	83.54 54	87.31 35	84.45 44	64.92 69	69.98 59	69.34 48	71.62 45	76.26 46	69.84 56	86.57 27	85.90 28	89.39 39	89.88 42
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
OMC-MVS		80.26 35	82.59 35	77.54 45	83.04 55	85.54 47	83.25 50	65.05 68	87.32 13	72.42 35	72.04 43	78.97 39	73.30 36	83.86 44	81.60 54	88.15 56	88.83 48

PLC	68.99 11	75.68 58	75.31 68	76.12 52	82.94 56	81.26 75	79.94 59	66.10 60	77.15 45	66.86 58	59.13 87	68.53 79	73.73 34	80.38 77	79.04 86	87.13 80	81.68 122
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		77.20 53	77.54 56	76.80 49	82.63 57	84.31 56	79.77 60	64.64 70	85.17 18	73.18 32	56.37 106	69.81 69	74.53 29	81.12 71	78.69 89	86.04 120	87.29 58

ACMH+	66.54 13	71.36 76	70.09 90	72.85 65	82.59 58	81.13 76	78.56 83	68.04 49	61.55 98	52.52 125	51.50 160	54.14 141	68.56 63	78.85 99	79.50 83	86.82 97	83.94 91

ACMH	65.37 14	70.71 80	70.00 91	71.54 68	82.51 59	82.47 69	77.78 95	68.13 48	56.19 143	46.06 154	54.30 126	51.20 169	68.68 62	80.66 75	80.72 63	86.07 117	84.45 87
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
canonicalmvs		79.16 45	82.37 36	75.41 53	82.33 60	86.38 44	80.80 55	63.18 79	82.90 29	67.34 55	72.79 41	76.07 47	69.62 57	83.46 51	84.41 39	89.20 42	90.60 38

MSDG		71.52 75	69.87 95	73.44 63	82.21 61	79.35 99	79.52 62	64.59 71	66.15 68	61.87 69	53.21 145	56.09 129	65.85 95	78.94 98	78.50 90	86.60 110	76.85 156

IS_MVSNet		73.33 65	77.34 60	68.65 109	81.29 62	83.47 61	74.45 118	63.58 77	65.75 72	48.49 144	67.11 63	70.61 65	54.63 156	84.51 40	83.58 44	89.48 38	86.34 62

Effi-MVS+		75.28 60	76.20 65	74.20 61	81.15 63	83.24 63	81.11 53	63.13 81	66.37 66	60.27 75	64.30 70	68.88 77	70.93 54	81.56 62	81.69 53	88.61 51	87.35 56

MVS_111021_LR		78.13 51	79.85 49	76.13 51	81.12 64	81.50 72	80.28 57	65.25 66	76.09 47	71.32 44	76.49 30	72.87 58	72.21 42	82.79 56	81.29 56	86.59 111	87.91 52

FC-MVSNet-train		72.60 71	75.07 69	69.71 100	81.10 65	78.79 103	73.74 128	65.23 67	66.10 69	53.34 118	70.36 48	63.40 92	56.92 143	81.44 63	80.96 59	87.93 61	84.46 86

MS-PatchMatch		70.17 90	70.49 88	69.79 98	80.98 66	77.97 116	77.51 97	58.95 135	62.33 91	55.22 109	53.14 146	65.90 85	62.03 110	79.08 97	77.11 113	84.08 146	77.91 146

TAPA-MVS	71.42 9	77.69 52	80.05 48	74.94 56	80.68 67	84.52 55	81.36 52	63.14 80	84.77 21	64.82 63	68.72 53	75.91 49	71.86 45	81.62 60	79.55 82	87.80 66	85.24 75
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_Blended_VisFu		76.57 54	77.90 53	75.02 55	80.56 68	86.58 42	79.24 64	66.18 59	64.81 77	68.18 51	65.61 64	71.45 61	67.05 66	84.16 42	81.80 52	88.90 47	90.92 35

EPP-MVSNet		74.00 64	77.41 59	70.02 96	80.53 69	83.91 58	74.99 115	62.68 90	65.06 75	49.77 141	68.68 54	72.09 60	63.06 105	82.49 57	80.73 62	89.12 45	88.91 47

COLMAP_ROB	62.73 15	67.66 128	66.76 143	68.70 108	80.49 70	77.98 114	75.29 108	62.95 83	63.62 84	49.96 139	47.32 178	50.72 172	58.57 129	76.87 130	75.50 144	84.94 142	75.33 166
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TSAR-MVS + COLMAP		78.34 50	81.64 37	74.48 60	80.13 71	85.01 53	81.73 51	65.93 64	84.75 22	61.68 70	85.79 13	66.27 84	71.39 50	82.91 54	80.78 61	86.01 121	85.98 63

EPNet_dtu		68.08 121	71.00 84	64.67 144	79.64 72	68.62 173	75.05 114	63.30 78	66.36 67	45.27 158	67.40 61	66.84 83	43.64 180	75.37 141	74.98 149	81.15 159	77.44 149
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		76.21 55	77.52 57	74.69 58	79.46 73	83.79 59	77.50 98	64.34 73	69.88 60	71.88 37	68.54 56	70.42 66	67.05 66	83.48 49	79.63 78	87.89 63	86.87 59

PVSNet_Blended		76.21 55	77.52 57	74.69 58	79.46 73	83.79 59	77.50 98	64.34 73	69.88 60	71.88 37	68.54 56	70.42 66	67.05 66	83.48 49	79.63 78	87.89 63	86.87 59

IB-MVS	66.94 12	71.21 77	71.66 82	70.68 78	79.18 75	82.83 67	72.61 137	61.77 102	59.66 111	63.44 68	53.26 143	59.65 102	59.16 128	76.78 132	82.11 50	87.90 62	87.33 57
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
MVS_Test		75.37 59	77.13 62	73.31 64	79.07 76	81.32 74	79.98 58	60.12 124	69.72 62	64.11 65	70.53 47	73.22 56	68.90 60	80.14 83	79.48 84	87.67 67	85.50 70

Effi-MVS+-dtu		71.82 73	71.86 81	71.78 67	78.77 77	80.47 90	78.55 84	61.67 104	60.68 103	55.49 106	58.48 91	65.48 86	68.85 61	76.92 129	75.55 143	87.35 72	85.46 71

EG-PatchMatch MVS		67.24 135	66.94 140	67.60 119	78.73 78	81.35 73	73.28 134	59.49 129	46.89 189	51.42 130	43.65 182	53.49 148	55.50 152	81.38 65	80.66 69	87.15 76	81.17 125

gg-mvs-nofinetune		62.55 160	65.05 158	59.62 169	78.72 79	77.61 119	70.83 147	53.63 164	39.71 201	22.04 206	36.36 194	64.32 89	47.53 172	81.16 70	79.03 87	85.00 141	77.17 151

Vis-MVSNet (Re-imp)		67.83 125	73.52 72	61.19 160	78.37 80	76.72 135	66.80 163	62.96 82	65.50 73	34.17 185	67.19 62	69.68 70	39.20 188	79.39 94	79.44 85	85.68 132	76.73 157

DI_MVS_plusplus_trai		75.13 61	76.12 66	73.96 62	78.18 81	81.55 71	80.97 54	62.54 94	68.59 63	65.13 62	61.43 75	74.81 52	69.32 59	81.01 73	79.59 80	87.64 68	85.89 64

thres600view7		67.68 127	68.43 125	66.80 130	77.90 82	78.86 102	73.84 125	62.75 84	56.07 144	44.70 162	52.85 151	52.81 156	55.58 150	80.41 76	77.77 99	86.05 119	80.28 132

thres400		67.95 122	68.62 124	67.17 124	77.90 82	78.59 106	74.27 123	62.72 85	56.34 142	45.77 156	53.00 148	53.35 151	56.46 144	80.21 82	78.43 91	85.91 127	80.43 131

tpmp4_e23		68.32 119	67.08 139	69.76 99	77.86 84	75.22 149	78.37 89	56.17 160	66.06 70	64.27 64	57.15 103	54.89 137	63.40 103	70.97 171	68.29 181	78.46 171	77.00 155

view600		67.63 131	68.36 126	66.77 131	77.84 85	78.66 104	73.74 128	62.62 92	56.04 145	44.98 159	52.86 150	52.83 155	55.48 153	80.36 78	77.75 100	85.95 126	80.02 135

view800		67.35 134	68.22 129	66.35 135	77.83 86	78.62 105	72.97 136	62.58 93	55.71 147	44.13 163	52.69 153	52.24 164	54.58 158	80.27 80	78.19 94	86.01 121	79.79 137

tfpn		66.58 138	67.18 138	65.88 137	77.82 87	78.45 108	72.07 141	62.52 95	55.35 150	43.21 167	52.54 155	46.12 188	53.68 159	80.02 84	78.23 93	85.99 124	79.55 139

Fast-Effi-MVS+		73.11 68	73.66 71	72.48 66	77.72 88	80.88 81	78.55 84	58.83 143	65.19 74	60.36 74	59.98 82	62.42 95	71.22 52	81.66 59	80.61 72	88.20 55	84.88 83

UniMVSNet_NR-MVSNet		70.59 81	72.19 79	68.72 107	77.72 88	80.72 82	73.81 126	69.65 38	61.99 93	43.23 165	60.54 78	57.50 108	58.57 129	79.56 91	81.07 58	89.34 40	83.97 89

IterMVS-LS		71.69 74	72.82 77	70.37 90	77.54 90	76.34 141	75.13 113	60.46 114	61.53 99	57.57 88	64.89 67	67.33 81	66.04 91	77.09 128	77.37 109	85.48 135	85.18 76
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NR-MVSNet		68.79 115	70.56 87	66.71 134	77.48 91	79.54 96	73.52 131	69.20 43	61.20 101	39.76 174	58.52 89	50.11 175	51.37 166	80.26 81	80.71 67	88.97 46	83.59 96

conf0.05thres1000		66.26 140	66.77 142	65.66 138	77.45 92	78.10 109	71.85 144	62.44 96	51.47 174	43.00 168	47.92 173	51.66 167	53.40 161	79.71 87	77.97 97	85.82 128	80.56 129

TransMVSNet (Re)		64.74 150	65.66 151	63.66 151	77.40 93	75.33 147	69.86 148	62.67 91	47.63 187	41.21 173	50.01 166	52.33 161	45.31 177	79.57 90	77.69 102	85.49 134	77.07 154

TranMVSNet+NR-MVSNet		69.25 110	70.81 86	67.43 121	77.23 94	79.46 98	73.48 132	69.66 37	60.43 106	39.56 175	58.82 88	53.48 149	55.74 149	79.59 89	81.21 57	88.89 48	82.70 110

CANet_DTU		73.29 66	76.96 63	69.00 105	77.04 95	82.06 70	79.49 63	56.30 158	67.85 64	53.29 119	71.12 46	70.37 68	61.81 115	81.59 61	80.96 59	86.09 116	84.73 84

CHOSEN 1792x2688		69.20 111	69.26 111	69.13 103	76.86 96	78.93 101	77.27 100	60.12 124	61.86 95	54.42 110	42.54 184	61.61 96	66.91 72	78.55 100	78.14 96	79.23 169	83.23 101

HyFIR lowres test		69.47 107	68.94 114	70.09 95	76.77 97	82.93 66	76.63 104	60.17 120	59.00 115	54.03 113	40.54 190	65.23 87	67.89 65	76.54 135	78.30 92	85.03 140	80.07 134

UniMVSNet (Re)		69.53 104	71.90 80	66.76 132	76.42 98	80.93 78	72.59 138	68.03 50	61.75 97	41.68 172	58.34 95	57.23 116	53.27 163	79.53 92	80.62 71	88.57 52	84.90 82

DWT-MVSNet_training		67.24 135	65.96 147	68.74 106	76.15 99	74.36 155	74.37 122	56.66 156	61.82 96	60.51 73	58.23 97	49.76 177	65.07 96	70.04 179	70.39 166	79.70 166	77.11 153

gm-plane-assit		57.00 184	57.62 190	56.28 181	76.10 100	62.43 197	47.62 206	46.57 194	33.84 209	23.24 200	37.52 191	40.19 198	59.61 127	79.81 86	77.55 104	84.55 144	72.03 177

DU-MVS		69.63 99	70.91 85	68.13 113	75.99 101	79.54 96	73.81 126	69.20 43	61.20 101	43.23 165	58.52 89	53.50 147	58.57 129	79.22 95	80.45 73	87.97 60	83.97 89

Baseline_NR-MVSNet		67.53 132	68.77 120	66.09 136	75.99 101	74.75 152	72.43 139	68.41 46	61.33 100	38.33 178	51.31 161	54.13 143	56.03 146	79.22 95	78.19 94	85.37 136	82.45 112

CostFormer		68.92 113	69.58 101	68.15 112	75.98 103	76.17 143	78.22 93	51.86 174	65.80 71	61.56 71	63.57 71	62.83 93	61.85 113	70.40 178	68.67 176	79.42 167	79.62 138

tpm cat1		65.41 143	63.81 167	67.28 123	75.61 104	72.88 158	75.32 107	52.85 168	62.97 88	63.66 67	53.24 144	53.29 153	61.83 114	65.54 190	64.14 193	74.43 187	74.60 168

CDS-MVSNet		67.65 129	69.83 98	65.09 140	75.39 105	76.55 136	74.42 121	63.75 75	53.55 163	49.37 143	59.41 85	62.45 94	44.44 178	79.71 87	79.82 76	83.17 152	77.36 150
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+-dtu		68.34 118	69.47 103	67.01 127	75.15 106	77.97 116	77.12 101	55.40 161	57.87 121	46.68 152	56.17 107	60.39 98	62.36 108	76.32 136	76.25 137	85.35 137	81.34 123

WR-MVS		63.03 156	67.40 136	57.92 175	75.14 107	77.60 120	60.56 186	66.10 60	54.11 162	23.88 197	53.94 137	53.58 146	34.50 193	73.93 149	77.71 101	87.35 72	80.94 126

test-LLR		64.42 151	64.36 163	64.49 145	75.02 108	63.93 187	66.61 165	61.96 99	54.41 158	47.77 148	57.46 100	60.25 99	55.20 154	70.80 172	69.33 171	80.40 163	74.38 170

test0.0.03 1		58.80 180	61.58 180	55.56 183	75.02 108	68.45 174	59.58 190	61.96 99	52.74 165	29.57 189	49.75 169	54.56 139	31.46 196	71.19 166	69.77 168	75.75 180	64.57 191

v1144		69.93 98	69.36 110	70.61 80	74.89 110	80.93 78	79.11 67	60.64 109	55.97 146	55.31 108	53.85 138	54.14 141	66.54 76	78.10 105	77.44 107	87.14 79	85.09 77

v13		69.52 105	68.76 121	70.41 88	74.88 111	77.02 131	78.52 88	58.86 137	56.61 139	56.91 93	54.00 136	56.17 128	66.11 90	77.93 106	76.74 123	87.21 74	82.83 103

v12		69.54 103	68.79 119	70.41 88	74.88 111	77.03 129	78.54 87	58.85 139	56.71 137	56.87 95	54.13 134	56.23 127	66.15 86	77.89 107	76.74 123	87.17 75	82.80 104

v11		69.37 108	68.65 123	70.20 92	74.87 113	76.97 132	78.29 91	58.55 147	56.38 141	56.04 104	54.02 135	54.98 136	66.47 77	78.30 102	76.91 115	86.97 88	83.02 102

V9		69.58 102	68.83 117	70.46 85	74.85 114	77.04 127	78.65 82	58.85 139	56.83 136	57.12 91	54.26 129	56.31 122	66.14 88	77.83 109	76.76 118	87.13 80	82.79 106

V14		69.59 101	68.86 116	70.45 87	74.83 115	77.04 127	78.70 81	58.83 143	56.95 133	57.08 92	54.41 125	56.34 121	66.15 86	77.77 110	76.76 118	87.08 85	82.74 109

v15		69.61 100	68.88 115	70.46 85	74.81 116	77.03 129	78.75 80	58.83 143	57.06 130	57.18 90	54.55 124	56.37 120	66.13 89	77.70 111	76.76 118	87.03 87	82.69 111

v7		70.33 87	69.87 95	70.88 69	74.79 117	81.04 77	79.22 65	60.57 111	57.70 127	56.65 101	54.23 131	55.29 134	66.95 69	78.28 103	77.47 105	87.12 83	85.05 79

v10		70.22 89	69.76 99	70.74 75	74.79 117	80.30 93	79.22 65	59.81 127	57.71 126	56.58 102	54.22 133	55.31 132	66.95 69	78.28 103	77.47 105	87.12 83	85.07 78

v1141		69.96 97	69.44 107	70.58 83	74.78 119	80.50 88	78.85 70	60.30 115	56.95 133	56.74 98	54.68 122	56.26 126	65.93 92	77.38 122	76.72 128	86.88 93	83.57 99

divwei89l23v2f112		69.97 95	69.44 107	70.58 83	74.78 119	80.50 88	78.85 70	60.30 115	56.97 132	56.75 97	54.67 123	56.27 125	65.92 93	77.37 123	76.72 128	86.88 93	83.58 98

v1		69.97 95	69.45 106	70.59 81	74.78 119	80.51 87	78.84 72	60.30 115	56.98 131	56.81 96	54.69 121	56.29 124	65.91 94	77.37 123	76.71 131	86.89 92	83.59 96

v17		70.03 94	69.43 109	70.72 77	74.75 122	77.09 124	78.78 79	58.85 139	59.53 113	58.72 81	54.87 118	57.39 110	66.38 79	77.60 115	76.75 121	86.83 96	82.80 104

v16		70.07 92	69.46 104	70.79 73	74.74 123	77.08 125	78.79 77	58.86 137	59.75 110	59.15 78	54.87 118	57.33 111	66.38 79	77.61 114	76.77 116	86.81 102	82.79 106

v8		70.23 88	69.86 97	70.67 79	74.69 124	79.82 95	78.79 77	59.18 133	58.80 117	58.20 83	55.00 114	57.33 111	66.31 85	77.51 119	76.71 131	86.82 97	83.88 92

v1neww		70.34 85	69.93 93	70.82 71	74.68 125	80.61 84	78.80 75	60.17 120	58.74 118	58.10 85	55.00 114	57.28 114	66.33 82	77.53 116	76.74 123	86.82 97	83.61 94

v7new		70.34 85	69.93 93	70.82 71	74.68 125	80.61 84	78.80 75	60.17 120	58.74 118	58.10 85	55.00 114	57.28 114	66.33 82	77.53 116	76.74 123	86.82 97	83.61 94

v6		70.35 84	69.94 92	70.83 70	74.68 125	80.62 83	78.81 74	60.16 123	58.81 116	58.17 84	55.01 113	57.31 113	66.32 84	77.53 116	76.73 127	86.82 97	83.62 93

v18		70.10 91	69.52 102	70.77 74	74.66 128	77.06 126	78.84 72	58.84 142	60.01 109	59.23 77	55.06 112	57.47 109	66.34 81	77.50 120	76.75 121	86.71 104	82.77 108

v2v482		70.05 93	69.46 104	70.74 75	74.62 129	80.32 92	79.00 68	60.62 110	57.41 128	56.89 94	55.43 111	55.14 135	66.39 78	77.25 125	77.14 112	86.90 90	83.57 99

v1192		69.50 106	68.83 117	70.29 91	74.49 130	80.92 80	78.55 84	60.54 112	55.04 154	54.21 111	52.79 152	52.33 161	66.92 71	77.88 108	77.35 110	87.04 86	85.51 69

DTE-MVSNet		61.85 169	64.96 160	58.22 174	74.32 131	74.39 154	61.01 185	67.85 52	51.76 173	21.91 207	53.28 142	48.17 181	37.74 189	72.22 159	76.44 134	86.52 113	78.49 143

Vis-MVSNet		72.77 70	77.20 61	67.59 120	74.19 132	84.01 57	76.61 105	61.69 103	60.62 105	50.61 135	70.25 49	71.31 63	55.57 151	83.85 45	82.28 48	86.90 90	88.08 51
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
diffmvs		73.13 67	75.65 67	70.19 93	74.07 133	77.17 123	78.24 92	57.45 151	72.44 57	64.02 66	69.05 51	75.92 48	64.86 97	75.18 143	75.27 145	82.47 154	84.53 85

v144192		69.34 109	68.68 122	70.12 94	74.06 134	80.54 86	78.08 94	60.54 112	54.99 156	54.13 112	52.92 149	52.80 157	66.73 74	77.13 127	76.72 128	87.15 76	85.63 65

v1921920		69.03 112	68.32 127	69.86 97	74.03 135	80.37 91	77.55 96	60.25 119	54.62 157	53.59 117	52.36 156	51.50 168	66.75 73	77.17 126	76.69 133	86.96 89	85.56 66

PEN-MVS		62.96 157	65.77 150	59.70 168	73.98 136	75.45 145	63.39 179	67.61 53	52.49 167	25.49 196	53.39 140	49.12 180	40.85 186	71.94 162	77.26 111	86.86 95	80.72 128

v1240		68.64 117	67.89 132	69.51 101	73.89 137	80.26 94	76.73 103	59.97 126	53.43 164	53.08 120	51.82 159	50.84 171	66.62 75	76.79 131	76.77 116	86.78 103	85.34 73

GA-MVS		68.14 120	69.17 112	66.93 129	73.77 138	78.50 107	74.45 118	58.28 148	55.11 153	48.44 145	60.08 80	53.99 144	61.50 116	78.43 101	77.57 103	85.13 138	80.54 130

pm-mvs1		65.62 142	67.42 135	63.53 152	73.66 139	76.39 140	69.66 149	60.87 108	49.73 182	43.97 164	51.24 162	57.00 118	48.16 171	79.89 85	77.84 98	84.85 143	79.82 136

dps		64.00 154	62.99 169	65.18 139	73.29 140	72.07 161	68.98 154	53.07 167	57.74 125	58.41 82	55.55 110	47.74 184	60.89 121	69.53 181	67.14 185	76.44 179	71.19 179

v148		67.85 124	67.53 133	68.23 111	73.25 141	77.57 121	74.26 124	57.36 153	55.70 148	57.45 89	53.53 139	55.42 131	61.96 111	75.23 142	73.92 152	85.08 139	81.32 124

PatchMatch-RL		67.78 126	66.65 144	69.10 104	73.01 142	72.69 159	68.49 155	61.85 101	62.93 89	60.20 76	56.83 105	50.42 173	69.52 58	75.62 140	74.46 151	81.51 157	73.62 175

GBi-Net		70.78 78	73.37 74	67.76 114	72.95 143	78.00 111	75.15 110	62.72 85	64.13 81	51.44 127	58.37 92	69.02 74	57.59 135	81.33 66	80.72 63	86.70 105	82.02 114

test1		70.78 78	73.37 74	67.76 114	72.95 143	78.00 111	75.15 110	62.72 85	64.13 81	51.44 127	58.37 92	69.02 74	57.59 135	81.33 66	80.72 63	86.70 105	82.02 114

FMVSNet2		70.39 83	72.67 78	67.72 117	72.95 143	78.00 111	75.15 110	62.69 89	63.29 86	51.25 131	55.64 108	68.49 80	57.59 135	80.91 74	80.35 74	86.70 105	82.02 114

FMVSNet3		70.49 82	72.90 76	67.67 118	72.88 146	77.98 114	74.96 116	62.72 85	64.13 81	51.44 127	58.37 92	69.02 74	57.43 138	79.43 93	79.57 81	86.59 111	81.81 121

LTVRE_ROB	59.44 16	61.82 172	62.64 173	60.87 162	72.83 147	77.19 122	64.37 175	58.97 134	33.56 210	28.00 193	52.59 154	42.21 194	63.93 101	74.52 145	76.28 135	77.15 176	82.13 113
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
v7n		67.05 137	66.94 140	67.17 124	72.35 148	78.97 100	73.26 135	58.88 136	51.16 175	50.90 132	48.21 171	50.11 175	60.96 118	77.70 111	77.38 108	86.68 108	85.05 79

tpm		62.41 163	63.15 168	61.55 159	72.24 149	63.79 189	71.31 146	46.12 196	57.82 122	55.33 107	59.90 83	54.74 138	53.63 160	67.24 188	64.29 191	70.65 198	74.25 172

test20.03		53.93 191	56.28 191	51.19 193	72.19 150	65.83 182	53.20 198	61.08 105	42.74 195	22.08 205	37.07 193	45.76 190	24.29 209	70.44 176	69.04 173	74.31 188	63.05 195

CP-MVSNet		62.68 159	65.49 153	59.40 171	71.84 151	75.34 146	62.87 181	67.04 56	52.64 166	27.19 194	53.38 141	48.15 182	41.40 184	71.26 165	75.68 141	86.07 117	82.00 117

PS-CasMVS		62.38 165	65.06 157	59.25 172	71.73 152	75.21 150	62.77 182	66.99 57	51.94 172	26.96 195	52.00 158	47.52 185	41.06 185	71.16 168	75.60 142	85.97 125	81.97 119

WR-MVS_H		61.83 171	65.87 149	57.12 178	71.72 153	76.87 133	61.45 184	66.19 58	51.97 171	22.92 204	53.13 147	52.30 163	33.80 194	71.03 169	75.00 148	86.65 109	80.78 127

USDC		67.36 133	67.90 131	66.74 133	71.72 153	75.23 148	71.58 145	60.28 118	67.45 65	50.54 136	60.93 76	45.20 191	62.08 109	76.56 134	74.50 150	84.25 145	75.38 165

UGNet		72.78 69	77.67 55	67.07 126	71.65 155	83.24 63	75.20 109	63.62 76	64.93 76	56.72 99	71.82 44	73.30 55	49.02 170	81.02 72	80.70 68	86.22 115	88.67 49
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
tpmrst		62.00 167	62.35 177	61.58 158	71.62 156	64.14 186	69.07 153	48.22 192	62.21 92	53.93 114	58.26 96	55.30 133	55.81 148	63.22 195	62.62 196	70.85 197	70.70 180

pmmvs4		67.89 123	67.39 137	68.48 110	71.60 157	73.57 157	74.45 118	60.98 106	64.65 78	57.97 87	54.95 117	51.73 166	61.88 112	73.78 150	75.11 147	83.99 148	77.91 146

testgi		54.39 190	57.86 188	50.35 194	71.59 158	67.24 177	54.95 196	53.25 166	43.36 194	23.78 198	44.64 181	47.87 183	24.96 205	70.45 175	68.66 177	73.60 190	62.78 196

pmmvs6		62.41 163	62.88 170	61.87 157	71.38 159	75.18 151	67.76 158	59.45 131	41.64 197	42.52 171	37.33 192	52.91 154	46.87 173	77.67 113	76.26 136	83.23 151	79.18 140

FMVSNet1		68.84 114	70.47 89	66.94 128	71.35 160	77.68 118	74.71 117	62.35 97	56.93 135	49.94 140	50.01 166	64.59 88	57.07 141	81.33 66	80.72 63	86.25 114	82.00 117

PatchmatchNet		64.21 153	64.65 161	63.69 150	71.29 161	68.66 172	69.63 150	51.70 176	63.04 87	53.77 116	59.83 84	58.34 106	60.23 125	68.54 185	66.06 188	75.56 182	68.08 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CR-MVSNet		64.83 149	65.54 152	64.01 149	70.64 162	69.41 168	65.97 168	52.74 169	57.81 123	52.65 122	54.27 127	56.31 122	60.92 119	72.20 160	73.09 156	81.12 160	75.69 162

MVSTER		72.06 72	74.24 70	69.51 101	70.39 163	75.97 144	76.91 102	57.36 153	64.64 79	61.39 72	68.86 52	63.76 90	63.46 102	81.44 63	79.70 77	87.56 69	85.31 74

Anonymous20231206		56.36 186	57.80 189	54.67 186	70.08 164	66.39 181	60.46 187	57.54 150	49.50 184	29.30 190	33.86 200	46.64 186	35.18 192	70.44 176	68.88 175	75.47 183	68.88 185

CMPMVS	47.78 17	62.49 162	62.52 174	62.46 155	70.01 165	70.66 166	62.97 180	51.84 175	51.98 170	56.71 100	42.87 183	53.62 145	57.80 134	72.23 158	70.37 167	75.45 184	75.91 159
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v748		65.12 147	65.24 154	64.98 141	69.77 166	76.45 137	69.47 151	57.06 155	49.93 180	50.70 133	47.87 174	49.50 179	57.14 140	73.64 152	75.18 146	85.75 131	84.14 88

TDRefinement		66.09 141	65.03 159	67.31 122	69.73 167	76.75 134	75.33 106	64.55 72	60.28 107	49.72 142	45.63 180	42.83 193	60.46 123	75.75 137	75.95 140	84.08 146	78.04 145

TinyColmap		62.84 158	61.03 182	64.96 142	69.61 168	71.69 162	68.48 156	59.76 128	55.41 149	47.69 150	47.33 177	34.20 203	62.76 107	74.52 145	72.59 159	81.44 158	71.47 178

RPMNet		61.71 173	62.88 170	60.34 164	69.51 169	69.41 168	63.48 178	49.23 184	57.81 123	45.64 157	50.51 164	50.12 174	53.13 164	68.17 187	68.49 179	81.07 161	75.62 164

IterMVS		66.36 139	68.30 128	64.10 146	69.48 170	74.61 153	73.41 133	50.79 180	57.30 129	48.28 146	60.64 77	59.92 101	60.85 122	74.14 148	72.66 158	81.80 156	78.82 142
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SixPastTwentyTwo		61.84 170	62.45 175	61.12 161	69.20 171	72.20 160	62.03 183	57.40 152	46.54 190	38.03 180	57.14 104	41.72 195	58.12 133	69.67 180	71.58 162	81.94 155	78.30 144

MDTV_nov1_ep13		64.37 152	65.24 154	63.37 154	68.94 172	70.81 164	72.40 140	50.29 183	60.10 108	53.91 115	60.07 81	59.15 104	57.21 139	69.43 182	67.30 183	77.47 174	69.78 182

EPMVS		60.00 178	61.97 178	57.71 176	68.46 173	63.17 193	64.54 174	48.23 191	63.30 85	44.72 161	60.19 79	56.05 130	50.85 167	65.27 192	62.02 198	69.44 200	63.81 193

Anonymous20231211		51.46 195	50.59 197	52.46 192	67.30 174	66.70 180	55.00 195	59.22 132	29.96 212	17.62 212	19.11 214	28.74 212	35.72 191	66.42 189	69.52 170	79.92 165	73.71 174

FC-MVSNet-test		56.90 185	65.20 156	47.21 197	66.98 175	63.20 192	49.11 204	58.60 146	59.38 114	11.50 217	65.60 65	56.68 119	24.66 208	71.17 167	71.36 164	72.38 193	69.02 184

CVMVSNet		62.55 160	65.89 148	58.64 173	66.95 176	69.15 170	66.49 167	56.29 159	52.46 168	32.70 186	59.27 86	58.21 107	50.09 168	71.77 163	71.39 163	79.31 168	78.99 141

FPMVS		51.87 194	50.00 199	54.07 187	66.83 177	57.25 200	60.25 188	50.91 178	50.25 177	34.36 184	36.04 197	32.02 205	41.49 183	58.98 207	56.07 207	70.56 199	59.36 202

pmmvs-eth3d		63.52 155	62.44 176	64.77 143	66.82 178	70.12 167	69.41 152	59.48 130	54.34 161	52.71 121	46.24 179	44.35 192	56.93 142	72.37 155	73.77 153	83.30 150	75.91 159

testpf		47.41 198	48.47 204	46.18 198	66.30 179	50.67 209	48.15 205	42.60 206	37.10 205	28.75 191	40.97 186	39.01 200	30.82 197	52.95 212	53.74 211	60.46 210	64.87 190

TAMVS		59.58 179	62.81 172	55.81 182	66.03 180	65.64 184	63.86 177	48.74 187	49.95 178	37.07 182	54.77 120	58.54 105	44.44 178	72.29 157	71.79 160	74.70 186	66.66 188

MDTV_nov1_ep13_2view		60.16 177	60.51 184	59.75 167	65.39 181	69.05 171	68.00 157	48.29 190	51.99 169	45.95 155	48.01 172	49.64 178	53.39 162	68.83 184	66.52 187	77.47 174	69.55 183

pmmvs5		62.37 166	64.04 165	60.42 163	65.03 182	71.67 163	67.17 160	52.70 171	50.30 176	44.80 160	54.23 131	51.19 170	49.37 169	72.88 154	73.48 155	83.45 149	74.55 169

ambc			53.42 193		64.99 183	63.36 191	49.96 202		47.07 188	37.12 181	28.97 204	16.36 219	41.82 182	75.10 144	67.34 182	71.55 196	75.72 161

V42		68.76 116	69.63 100	67.74 116	64.93 184	78.01 110	78.30 90	56.48 157	58.65 120	56.30 103	54.26 129	57.03 117	64.85 98	77.47 121	77.01 114	85.60 133	84.96 81

PMVS	39.38 18	46.06 203	43.30 208	49.28 196	62.93 185	38.75 216	41.88 209	53.50 165	33.33 211	35.46 183	28.90 205	31.01 208	33.04 195	58.61 208	54.63 210	68.86 201	57.88 205
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new-patchmatchnet		46.97 201	49.47 200	44.05 203	62.82 186	56.55 201	45.35 207	52.01 173	42.47 196	17.04 213	35.73 198	35.21 202	21.84 214	61.27 200	54.83 209	65.26 208	60.26 199

ADS-MVSNet		55.94 187	58.01 187	53.54 191	62.48 187	58.48 199	59.12 191	46.20 195	59.65 112	42.88 169	52.34 157	53.31 152	46.31 175	62.00 199	60.02 203	64.23 209	60.24 201

v52		65.23 145	66.24 145	64.06 147	61.94 188	76.42 138	72.06 142	54.30 163	49.94 179	50.04 138	47.41 176	52.42 159	60.23 125	75.71 138	76.22 138	85.78 129	85.56 66

V4		65.23 145	66.23 146	64.06 147	61.94 188	76.42 138	72.05 143	54.31 162	49.91 181	50.06 137	47.42 175	52.40 160	60.24 124	75.71 138	76.22 138	85.78 129	85.56 66

RPSCF		67.64 130	71.25 83	63.43 153	61.86 190	70.73 165	67.26 159	50.86 179	74.20 53	58.91 79	67.49 60	69.33 71	64.10 100	71.41 164	68.45 180	77.61 173	77.17 151

MIMVSNet		58.52 182	61.34 181	55.22 184	60.76 191	67.01 178	66.81 162	49.02 186	56.43 140	38.90 177	40.59 189	54.54 140	40.57 187	73.16 153	71.65 161	75.30 185	66.00 189

PatchT		61.97 168	64.04 165	59.55 170	60.49 192	67.40 176	56.54 193	48.65 188	56.69 138	52.65 122	51.10 163	52.14 165	60.92 119	72.20 160	73.09 156	78.03 172	75.69 162

N_pmnet		47.35 199	50.13 198	44.11 202	59.98 193	51.64 208	51.86 199	44.80 201	49.58 183	20.76 208	40.65 188	40.05 199	29.64 198	59.84 205	55.15 208	57.63 211	54.00 209

1111		43.08 205	44.02 207	41.98 204	59.22 194	49.27 212	41.48 210	45.63 198	35.01 206	23.06 202	28.60 206	30.15 209	27.22 200	60.42 203	57.97 205	55.27 214	46.74 211

.test1245		30.81 212	29.14 214	32.77 211	59.22 194	49.27 212	41.48 210	45.63 198	35.01 206	23.06 202	28.60 206	30.15 209	27.22 200	60.42 203	0.10 218	0.01 222	0.43 220

MVS-HIRNet		54.41 189	52.10 196	57.11 179	58.99 196	56.10 202	49.68 203	49.10 185	46.18 191	52.15 126	33.18 201	46.11 189	56.10 145	63.19 196	59.70 204	76.64 178	60.25 200

PM-MVS		60.48 176	60.94 183	59.94 166	58.85 197	66.83 179	64.27 176	51.39 177	55.03 155	48.03 147	50.00 168	40.79 197	58.26 132	69.20 183	67.13 186	78.84 170	77.60 148

anonymousdsp		65.28 144	67.98 130	62.13 156	58.73 198	73.98 156	67.10 161	50.69 181	48.41 185	47.66 151	54.27 127	52.75 158	61.45 117	76.71 133	80.20 75	87.13 80	89.53 45

LP		53.62 192	53.43 192	53.83 189	58.51 199	62.59 196	57.31 192	46.04 197	47.86 186	42.69 170	36.08 196	36.86 201	46.53 174	64.38 193	64.25 192	71.92 194	62.00 198

TESTMET0.1,1		61.10 174	64.36 163	57.29 177	57.53 200	63.93 187	66.61 165	36.22 211	54.41 158	47.77 148	57.46 100	60.25 99	55.20 154	70.80 172	69.33 171	80.40 163	74.38 170

EU-MVSNet		54.63 188	58.69 186	49.90 195	56.99 201	62.70 195	56.41 194	50.64 182	45.95 192	23.14 201	50.42 165	46.51 187	36.63 190	65.51 191	64.85 190	75.57 181	74.91 167

FMVSNet5		57.24 183	60.02 185	53.99 188	56.45 202	62.74 194	65.27 171	47.03 193	55.14 152	39.55 176	40.88 187	53.42 150	41.83 181	72.35 156	71.10 165	73.79 189	64.50 192

test2356		47.20 200	48.62 203	45.54 200	56.38 203	54.89 204	50.62 200	45.08 200	38.65 202	23.40 199	36.23 195	31.10 207	29.31 199	62.76 197	62.49 197	68.48 202	54.23 208

testus		45.61 204	49.06 202	41.59 205	56.13 204	55.28 203	43.51 208	39.64 209	37.74 203	18.23 210	35.52 199	31.28 206	24.69 207	62.46 198	62.90 195	67.33 204	58.26 204

test-mter		60.84 175	64.62 162	56.42 180	55.99 205	64.18 185	65.39 170	34.23 213	54.39 160	46.21 153	57.40 102	59.49 103	55.86 147	71.02 170	69.65 169	80.87 162	76.20 158

CHOSEN 280x420		58.70 181	61.88 179	54.98 185	55.45 206	50.55 210	64.92 172	40.36 207	55.21 151	38.13 179	48.31 170	63.76 90	63.03 106	73.73 151	68.58 178	68.00 203	73.04 176

PMMVS		65.06 148	69.17 112	60.26 165	55.25 207	63.43 190	66.71 164	43.01 205	62.41 90	50.64 134	69.44 50	67.04 82	63.29 104	74.36 147	73.54 154	82.68 153	73.99 173

testmv		42.58 206	44.36 205	40.49 206	54.63 208	52.76 206	41.21 212	44.37 202	28.83 213	12.87 214	27.16 209	25.03 214	23.01 210	60.83 201	61.13 199	66.88 205	54.81 206

test1235678		42.57 207	44.36 205	40.49 206	54.63 208	52.75 207	41.21 212	44.37 202	28.82 214	12.87 214	27.15 210	25.01 215	23.01 210	60.83 201	61.13 199	66.88 205	54.81 206

no-one		36.35 210	37.59 211	34.91 209	46.13 210	49.89 211	27.99 217	43.56 204	20.91 218	7.03 220	14.64 216	15.50 220	18.92 215	42.95 213	60.20 202	65.84 207	59.03 203

Gipuma		36.38 209	35.80 212	37.07 208	45.76 211	33.90 217	29.81 216	48.47 189	39.91 200	18.02 211	8.00 220	8.14 222	25.14 204	59.29 206	61.02 201	55.19 215	40.31 213
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs3		47.65 197	49.08 201	45.99 199	44.61 212	54.79 205	50.04 201	31.95 216	33.91 208	29.90 188	30.37 202	33.53 204	46.31 175	63.50 194	63.67 194	73.14 192	63.77 194

MIMVSNet1		49.27 196	53.25 194	44.62 201	44.61 212	61.52 198	53.61 197	52.18 172	41.62 198	18.68 209	28.14 208	41.58 196	25.50 203	68.46 186	69.04 173	73.15 191	62.37 197

test12356		35.10 211	38.50 210	31.13 212	44.14 214	43.70 215	32.27 215	34.42 212	26.51 216	9.47 218	25.22 212	20.34 216	10.86 217	53.47 210	56.15 206	55.59 213	44.11 212

MDA-MVSNet-bldmvs		53.37 193	53.01 195	53.79 190	43.67 215	67.95 175	59.69 189	57.92 149	43.69 193	32.41 187	41.47 185	27.89 213	52.38 165	56.97 209	65.99 189	76.68 177	67.13 187

E-PMN		21.77 214	18.24 216	25.89 213	40.22 216	19.58 220	12.46 221	39.87 208	18.68 220	6.71 221	9.57 217	4.31 225	22.36 213	19.89 218	27.28 216	33.73 217	28.34 217

EMVS		20.98 215	17.15 217	25.44 214	39.51 217	19.37 221	12.66 220	39.59 210	19.10 219	6.62 222	9.27 218	4.40 224	22.43 212	17.99 219	24.40 217	31.81 218	25.53 218

new_pmnet		38.40 208	42.64 209	33.44 210	37.54 218	45.00 214	36.60 214	32.72 215	40.27 199	12.72 216	29.89 203	28.90 211	24.78 206	53.17 211	52.90 212	56.31 212	48.34 210

PMMVS2		25.60 213	29.75 213	20.76 216	28.00 219	30.93 218	23.10 218	29.18 217	23.14 217	1.46 224	18.23 215	16.54 218	5.08 218	40.22 214	41.40 214	37.76 216	37.79 215

tmp_tt				14.50 218	14.68 220	7.17 223	10.46 223	2.21 219	37.73 204	28.71 192	25.26 211	16.98 217	4.37 219	31.49 215	29.77 215	26.56 219

MVE	19.12 19	20.47 216	23.27 215	17.20 217	12.66 221	25.41 219	10.52 222	34.14 214	14.79 221	6.53 223	8.79 219	4.68 223	16.64 216	29.49 216	41.63 213	22.73 220	38.11 214
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND		46.86 202	67.51 134	22.75 215	0.05 222	76.21 142	64.69 173	0.04 220	61.90 94	0.09 225	55.57 109	71.32 62	0.08 220	70.54 174	67.19 184	71.58 195	69.86 181

testmvs		0.09 217	0.15 218	0.02 219	0.01 223	0.02 224	0.05 225	0.01 221	0.11 222	0.01 226	0.26 222	0.01 226	0.06 222	0.10 220	0.10 218	0.01 222	0.43 220

sosnet-low-res		0.00 219	0.00 220	0.00 221	0.00 224	0.00 226	0.00 227	0.00 223	0.00 224	0.00 227	0.00 223	0.00 227	0.00 223	0.00 222	0.00 221	0.00 225	0.00 222

sosnet		0.00 219	0.00 220	0.00 221	0.00 224	0.00 226	0.00 227	0.00 223	0.00 224	0.00 227	0.00 223	0.00 227	0.00 223	0.00 222	0.00 221	0.00 225	0.00 222

test123		0.09 217	0.14 219	0.02 219	0.00 224	0.02 224	0.02 226	0.01 221	0.09 223	0.00 227	0.30 221	0.00 227	0.08 220	0.03 221	0.09 220	0.01 222	0.45 219

MTAPA										83.48 1		86.45 12

MTMP										82.66 3		84.91 20

Patchmatch-RL test							2.85 224

NP-MVS									80.10 39

Patchmtry						65.80 183	65.97 168	52.74 169		52.65 122

DeepMVS_CX						18.74 222	18.55 219	8.02 218	26.96 215	7.33 219	23.81 213	13.05 221	25.99 202	25.17 217		22.45 221	36.25 216

High-resolution multi-view benchmark