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 3	88.92 7	84.95 2	92.61 1	87.91 32	90.23 8	76.06 2	88.85 6	81.20 4	87.33 8	87.93 6	79.47 5	88.59 4	88.23 4	90.15 26	93.60 14

NCCC		85.34 13	86.59 18	83.88 9	91.48 2	88.88 18	89.79 10	75.54 6	86.67 14	77.94 16	76.55 28	84.99 18	78.07 10	88.04 7	87.68 7	90.46 18	93.31 15

CNVR-MVS		86.36 8	88.19 11	84.23 5	91.33 3	89.84 8	90.34 5	75.56 5	87.36 11	78.97 10	81.19 21	86.76 10	78.74 6	89.30 2	88.58 1	90.45 19	94.33 4

APDe-MVS		88.00 1	90.50 1	85.08 1	90.95 4	91.58 3	92.03 1	75.53 7	91.15 1	80.10 7	92.27 2	88.34 5	80.80 2	88.00 9	86.99 12	91.09 4	95.16 1

SteuartSystems-ACMMP		85.99 9	88.31 10	83.27 14	90.73 5	89.84 8	90.27 7	74.31 9	84.56 23	75.88 22	87.32 9	85.04 17	77.31 17	89.01 3	88.46 2	91.14 3	93.96 6
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		86.84 6	88.91 8	84.41 3	90.66 6	90.10 6	90.78 2	75.64 4	87.38 10	78.72 11	90.68 5	86.82 9	80.15 3	87.13 18	86.45 21	90.51 13	93.83 8
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MP-MVS		85.50 12	87.40 14	83.28 13	90.65 7	89.51 13	89.16 16	74.11 12	83.70 26	78.06 15	85.54 13	84.89 20	77.31 17	87.40 15	87.14 11	90.41 20	93.65 13

train_agg		84.86 18	87.21 15	82.11 20	90.59 8	85.47 47	89.81 9	73.55 18	83.95 25	73.30 30	89.84 7	87.23 8	75.61 25	86.47 27	85.46 31	89.78 29	92.06 25

MCST-MVS		85.13 16	86.62 17	83.39 11	90.55 9	89.82 10	89.29 14	73.89 16	84.38 24	76.03 21	79.01 24	85.90 14	78.47 7	87.81 11	86.11 26	92.11 1	93.29 16

MPTG		85.71 10	86.88 16	84.34 4	90.54 10	87.11 36	89.77 11	74.17 11	88.54 7	83.08 2	78.60 25	86.10 12	78.11 9	87.80 12	87.46 9	90.35 22	92.56 19

DeepC-MVS_fast	78.24 3	84.27 22	85.50 24	82.85 16	90.46 11	89.24 15	87.83 25	74.24 10	84.88 19	76.23 20	75.26 31	81.05 34	77.62 14	88.02 8	87.62 8	90.69 9	92.41 21
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 7	89.01 5	83.62 10	90.28 12	90.09 7	90.32 6	74.05 13	88.32 8	79.74 8	87.04 10	85.59 16	76.97 22	89.35 1	88.44 3	90.35 22	94.27 5

SD-MVS		86.96 4	89.45 3	84.05 8	90.13 13	89.23 16	89.77 11	74.59 8	89.17 4	80.70 5	89.93 6	89.67 1	78.47 7	87.57 13	86.79 15	90.67 10	93.76 10

ACMMPR		85.52 11	87.53 13	83.17 15	90.13 13	89.27 14	89.30 13	73.97 14	86.89 13	77.14 18	86.09 11	83.18 24	77.74 13	87.42 14	87.20 10	90.77 6	92.63 18

PGM-MVS		84.42 21	86.29 21	82.23 19	90.04 15	88.82 20	89.23 15	71.74 27	82.82 29	74.61 25	84.41 16	82.09 26	77.03 21	87.13 18	86.73 17	90.73 8	92.06 25

HSP-MVS		87.45 2	90.22 2	84.22 6	90.00 16	91.80 2	90.59 3	75.80 3	89.93 3	78.35 13	92.54 1	89.18 2	80.89 1	87.99 10	86.29 23	89.70 33	93.85 7

CSCG		85.28 15	87.68 12	82.49 18	89.95 17	91.99 1	88.82 17	71.20 29	86.41 15	79.63 9	79.26 22	88.36 4	73.94 32	86.64 25	86.67 18	91.40 2	94.41 2

mPP-MVS					89.90 18							81.29 33

TSAR-MVS + MP.		86.88 5	89.23 4	84.14 7	89.78 19	88.67 24	90.59 3	73.46 19	88.99 5	80.52 6	91.26 3	88.65 3	79.91 4	86.96 23	86.22 24	90.59 11	93.83 8

X-MVS		83.23 25	85.20 26	80.92 26	89.71 20	88.68 21	88.21 24	73.60 17	82.57 30	71.81 38	77.07 26	81.92 28	71.72 47	86.98 22	86.86 13	90.47 15	92.36 22

TSAR-MVS + ACMM		85.10 17	88.81 9	80.77 27	89.55 21	88.53 26	88.59 20	72.55 22	87.39 9	71.90 35	90.95 4	87.55 7	74.57 27	87.08 20	86.54 19	87.47 69	93.67 11

CP-MVS		84.74 20	86.43 20	82.77 17	89.48 22	88.13 31	88.64 18	73.93 15	84.92 18	76.77 19	81.94 19	83.50 22	77.29 19	86.92 24	86.49 20	90.49 14	93.14 17

CDPH-MVS		82.64 26	85.03 27	79.86 31	89.41 23	88.31 28	88.32 22	71.84 26	80.11 37	67.47 53	82.09 18	81.44 32	71.85 45	85.89 32	86.15 25	90.24 24	91.25 31

DeepC-MVS	78.47 2	84.81 19	86.03 22	83.37 12	89.29 24	90.38 5	88.61 19	76.50 1	86.25 16	77.22 17	75.12 32	80.28 36	77.59 15	88.39 5	88.17 5	91.02 5	93.66 12
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 39	78.62 50	81.05 25	89.23 25	86.06 44	84.95 41	71.96 25	79.39 40	75.51 23	63.16 71	68.84 77	76.51 23	83.55 47	82.85 46	88.13 56	86.46 60

EPNet		79.08 46	80.62 41	77.28 45	88.90 26	83.17 64	83.65 46	72.41 23	74.41 50	67.15 55	76.78 27	74.37 52	64.43 98	83.70 46	83.69 42	87.15 75	88.19 49
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	79.04 1	85.30 14	88.93 6	81.06 24	88.77 27	90.48 4	85.46 38	73.08 20	90.97 2	73.77 29	84.81 15	85.95 13	77.43 16	88.22 6	87.73 6	87.85 64	94.34 3

ACMMP		83.42 24	85.27 25	81.26 23	88.47 28	88.49 27	88.31 23	72.09 24	83.42 27	72.77 33	82.65 17	78.22 40	75.18 26	86.24 30	85.76 28	90.74 7	92.13 24
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 27	82.76 32	81.97 21	88.02 29	89.67 11	86.60 29	71.48 28	81.28 35	78.18 14	64.78 67	77.96 42	77.13 20	87.32 16	86.83 14	90.41 20	91.48 29

OPM-MVS		79.68 40	79.28 49	80.15 30	87.99 30	86.77 39	88.52 21	72.72 21	64.55 79	67.65 52	67.87 58	74.33 53	74.31 30	86.37 29	85.25 33	89.73 32	89.81 42

MAR-MVS		79.21 43	80.32 45	77.92 43	87.46 31	88.15 30	83.95 45	67.48 53	74.28 51	68.25 49	64.70 68	77.04 43	72.17 42	85.42 34	85.00 35	88.22 53	87.62 54
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 33	83.27 30	78.76 38	87.40 32	85.45 48	86.95 27	70.47 32	81.31 34	66.91 56	79.24 23	76.63 44	71.67 48	84.43 40	83.78 41	89.19 42	92.05 27

abl_6				79.05 35	87.27 33	88.85 19	83.62 47	68.25 46	81.68 33	72.94 32	73.79 38	84.45 21	72.55 40			89.66 35	90.64 36

CANet		81.62 32	83.41 29	79.53 33	87.06 34	88.59 25	85.47 37	67.96 50	76.59 45	74.05 26	74.69 33	81.98 27	72.98 38	86.14 31	85.47 30	89.68 34	90.42 39

MSLP-MVS++		82.09 29	82.66 33	81.42 22	87.03 35	87.22 35	85.82 34	70.04 34	80.30 36	78.66 12	68.67 54	81.04 35	77.81 12	85.19 36	84.88 36	89.19 42	91.31 30

ACMM	72.26 8	78.86 47	78.13 51	79.71 32	86.89 36	83.40 61	86.02 32	70.50 31	75.28 47	71.49 42	63.01 72	69.26 71	73.57 34	84.11 42	83.98 40	89.76 31	87.84 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					86.63 37	88.68 21	85.00 39			71.81 38		81.92 28				90.47 15

X-MVStestdata					86.63 37	88.68 21	85.00 39			71.81 38		81.92 28				90.47 15

PHI-MVS		82.36 28	85.89 23	78.24 41	86.40 39	89.52 12	85.52 36	69.52 40	82.38 32	65.67 58	81.35 20	82.36 25	73.07 37	87.31 17	86.76 16	89.24 40	91.56 28

LGP-MVS_train		79.83 36	81.22 39	78.22 42	86.28 40	85.36 50	86.76 28	69.59 38	77.34 42	65.14 60	75.68 30	70.79 63	71.37 50	84.60 38	84.01 39	90.18 25	90.74 35

MVS_0304		81.73 31	83.86 28	79.26 34	86.22 41	89.18 17	86.41 30	67.15 54	75.28 47	70.75 45	74.59 34	83.49 23	74.42 29	87.05 21	86.34 22	90.58 12	91.08 33

CPTT-MVS		81.77 30	83.10 31	80.21 29	85.93 42	86.45 42	87.72 26	70.98 30	82.54 31	71.53 41	74.23 37	81.49 31	76.31 24	82.85 54	81.87 50	88.79 49	92.26 23

MVS_111021_HR		80.13 35	81.46 37	78.58 39	85.77 43	85.17 51	83.45 48	69.28 41	74.08 53	70.31 46	74.31 36	75.26 50	73.13 36	86.46 28	85.15 34	89.53 36	89.81 42

ACMP	73.23 7	79.79 37	80.53 42	78.94 36	85.61 44	85.68 45	85.61 35	69.59 38	77.33 43	71.00 44	74.45 35	69.16 72	71.88 43	83.15 51	83.37 44	89.92 28	90.57 38
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		74.47 61	77.80 53	70.59 80	85.33 45	85.40 49	73.54 131	65.98 62	60.65 103	56.00 104	72.11 41	79.15 37	54.63 157	83.13 52	82.25 48	88.04 58	81.92 119

TSAR-MVS + GP.		83.69 23	86.58 19	80.32 28	85.14 46	86.96 37	84.91 42	70.25 33	84.71 22	73.91 28	85.16 14	85.63 15	77.92 11	85.44 33	85.71 29	89.77 30	92.45 20

LS3D		74.08 62	73.39 72	74.88 56	85.05 47	82.62 67	79.71 60	68.66 44	72.82 55	58.80 79	57.61 98	61.31 96	71.07 52	80.32 80	78.87 87	86.00 124	80.18 133

QAPM		78.47 48	80.22 46	76.43 49	85.03 48	86.75 40	80.62 55	66.00 61	73.77 54	65.35 59	65.54 65	78.02 41	72.69 39	83.71 45	83.36 45	88.87 48	90.41 40

OpenMVS	70.44 10	76.15 56	76.82 63	75.37 53	85.01 49	84.79 53	78.99 68	62.07 99	71.27 57	67.88 51	57.91 97	72.36 58	70.15 54	82.23 57	81.41 54	88.12 57	87.78 53

CLD-MVS		79.35 42	81.23 38	77.16 46	85.01 49	86.92 38	85.87 33	60.89 108	80.07 39	75.35 24	72.96 39	73.21 56	68.43 63	85.41 35	84.63 37	87.41 70	85.44 71
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 38	80.52 43	78.84 37	84.94 51	87.35 33	84.43 44	65.54 64	78.29 41	73.97 27	63.00 73	75.62 49	74.07 31	85.00 37	85.34 32	90.11 27	89.04 45

PCF-MVS	73.28 6	79.42 41	80.41 44	78.26 40	84.88 52	88.17 29	86.08 31	69.85 35	75.23 49	68.43 48	68.03 57	78.38 39	71.76 46	81.26 68	80.65 69	88.56 52	91.18 32
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DELS-MVS		79.15 45	81.07 40	76.91 47	83.54 53	87.31 34	84.45 43	64.92 68	69.98 58	69.34 47	71.62 44	76.26 45	69.84 55	86.57 26	85.90 27	89.39 38	89.88 41
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 34	82.59 34	77.54 44	83.04 54	85.54 46	83.25 49	65.05 67	87.32 12	72.42 34	72.04 42	78.97 38	73.30 35	83.86 43	81.60 53	88.15 55	88.83 47

PLC	68.99 11	75.68 57	75.31 67	76.12 51	82.94 55	81.26 74	79.94 58	66.10 59	77.15 44	66.86 57	59.13 86	68.53 78	73.73 33	80.38 78	79.04 85	87.13 79	81.68 121
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		77.20 52	77.54 55	76.80 48	82.63 56	84.31 55	79.77 59	64.64 69	85.17 17	73.18 31	56.37 105	69.81 68	74.53 28	81.12 70	78.69 88	86.04 121	87.29 57

ACMH+	66.54 13	71.36 75	70.09 89	72.85 64	82.59 57	81.13 75	78.56 82	68.04 48	61.55 97	52.52 124	51.50 161	54.14 140	68.56 62	78.85 100	79.50 82	86.82 96	83.94 90

ACMH	65.37 14	70.71 79	70.00 90	71.54 67	82.51 58	82.47 68	77.78 94	68.13 47	56.19 144	46.06 155	54.30 125	51.20 170	68.68 61	80.66 74	80.72 62	86.07 117	84.45 86
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
canonicalmvs		79.16 44	82.37 35	75.41 52	82.33 59	86.38 43	80.80 54	63.18 78	82.90 28	67.34 54	72.79 40	76.07 46	69.62 56	83.46 50	84.41 38	89.20 41	90.60 37

MSDG		71.52 74	69.87 94	73.44 62	82.21 60	79.35 98	79.52 61	64.59 70	66.15 67	61.87 68	53.21 144	56.09 128	65.85 94	78.94 99	78.50 89	86.60 109	76.85 157

IS_MVSNet		73.33 64	77.34 59	68.65 108	81.29 61	83.47 60	74.45 117	63.58 76	65.75 71	48.49 143	67.11 62	70.61 64	54.63 157	84.51 39	83.58 43	89.48 37	86.34 61

Effi-MVS+		75.28 59	76.20 64	74.20 60	81.15 62	83.24 62	81.11 52	63.13 80	66.37 65	60.27 74	64.30 69	68.88 76	70.93 53	81.56 61	81.69 52	88.61 50	87.35 55

MVS_111021_LR		78.13 50	79.85 48	76.13 50	81.12 63	81.50 71	80.28 56	65.25 65	76.09 46	71.32 43	76.49 29	72.87 57	72.21 41	82.79 55	81.29 55	86.59 110	87.91 51

FC-MVSNet-train		72.60 70	75.07 68	69.71 99	81.10 64	78.79 104	73.74 129	65.23 66	66.10 68	53.34 117	70.36 47	63.40 91	56.92 142	81.44 62	80.96 58	87.93 60	84.46 85

MS-PatchMatch		70.17 89	70.49 87	69.79 97	80.98 65	77.97 117	77.51 96	58.95 136	62.33 90	55.22 108	53.14 145	65.90 84	62.03 109	79.08 98	77.11 114	84.08 147	77.91 147

TAPA-MVS	71.42 9	77.69 51	80.05 47	74.94 55	80.68 66	84.52 54	81.36 51	63.14 79	84.77 20	64.82 62	68.72 52	75.91 48	71.86 44	81.62 59	79.55 81	87.80 65	85.24 74
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_Blended_VisFu		76.57 53	77.90 52	75.02 54	80.56 67	86.58 41	79.24 63	66.18 58	64.81 76	68.18 50	65.61 63	71.45 60	67.05 65	84.16 41	81.80 51	88.90 46	90.92 34

EPP-MVSNet		74.00 63	77.41 58	70.02 95	80.53 68	83.91 57	74.99 114	62.68 91	65.06 74	49.77 140	68.68 53	72.09 59	63.06 104	82.49 56	80.73 61	89.12 44	88.91 46

COLMAP_ROB	62.73 15	67.66 129	66.76 144	68.70 107	80.49 69	77.98 115	75.29 107	62.95 82	63.62 83	49.96 138	47.32 179	50.72 173	58.57 128	76.87 131	75.50 145	84.94 143	75.33 167
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 49	81.64 36	74.48 59	80.13 70	85.01 52	81.73 50	65.93 63	84.75 21	61.68 69	85.79 12	66.27 83	71.39 49	82.91 53	80.78 60	86.01 122	85.98 62

EPNet_dtu		68.08 121	71.00 83	64.67 145	79.64 71	68.62 174	75.05 113	63.30 77	66.36 66	45.27 159	67.40 60	66.84 82	43.64 181	75.37 142	74.98 150	81.15 160	77.44 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		76.21 54	77.52 56	74.69 57	79.46 72	83.79 58	77.50 97	64.34 72	69.88 59	71.88 36	68.54 55	70.42 65	67.05 65	83.48 48	79.63 77	87.89 62	86.87 58

PVSNet_Blended		76.21 54	77.52 56	74.69 57	79.46 72	83.79 58	77.50 97	64.34 72	69.88 59	71.88 36	68.54 55	70.42 65	67.05 65	83.48 48	79.63 77	87.89 62	86.87 58

IB-MVS	66.94 12	71.21 76	71.66 81	70.68 77	79.18 74	82.83 66	72.61 138	61.77 103	59.66 110	63.44 67	53.26 142	59.65 101	59.16 127	76.78 133	82.11 49	87.90 61	87.33 56
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 58	77.13 61	73.31 63	79.07 75	81.32 73	79.98 57	60.12 125	69.72 61	64.11 64	70.53 46	73.22 55	68.90 59	80.14 84	79.48 83	87.67 66	85.50 69

Effi-MVS+-dtu		71.82 72	71.86 80	71.78 66	78.77 76	80.47 89	78.55 83	61.67 105	60.68 102	55.49 105	58.48 90	65.48 85	68.85 60	76.92 130	75.55 144	87.35 71	85.46 70

EG-PatchMatch MVS		67.24 136	66.94 141	67.60 118	78.73 77	81.35 72	73.28 135	59.49 130	46.89 190	51.42 129	43.65 183	53.49 148	55.50 153	81.38 64	80.66 68	87.15 75	81.17 124

gg-mvs-nofinetune		62.55 161	65.05 159	59.62 170	78.72 78	77.61 120	70.83 148	53.63 165	39.71 202	22.04 207	36.36 195	64.32 88	47.53 173	81.16 69	79.03 86	85.00 142	77.17 152

Vis-MVSNet (Re-imp)		67.83 126	73.52 71	61.19 161	78.37 79	76.72 136	66.80 164	62.96 81	65.50 72	34.17 186	67.19 61	69.68 69	39.20 189	79.39 95	79.44 84	85.68 133	76.73 158

DI_MVS_plusplus_trai		75.13 60	76.12 65	73.96 61	78.18 80	81.55 70	80.97 53	62.54 95	68.59 62	65.13 61	61.43 74	74.81 51	69.32 58	81.01 72	79.59 79	87.64 67	85.89 63

thres600view7		67.68 128	68.43 126	66.80 131	77.90 81	78.86 102	73.84 126	62.75 84	56.07 145	44.70 163	52.85 151	52.81 157	55.58 151	80.41 75	77.77 100	86.05 119	80.28 132

thres400		67.95 123	68.62 124	67.17 125	77.90 81	78.59 107	74.27 123	62.72 86	56.34 143	45.77 157	53.00 147	53.35 152	56.46 144	80.21 83	78.43 90	85.91 128	80.43 131

thres200		67.98 122	68.55 125	67.30 123	77.89 83	78.86 102	74.18 125	62.75 84	56.35 142	46.48 153	52.98 148	53.54 146	56.46 144	80.41 75	77.97 97	86.05 119	79.78 138

tpmp4_e23		68.32 118	67.08 140	69.76 98	77.86 84	75.22 150	78.37 88	56.17 161	66.06 69	64.27 63	57.15 102	54.89 136	63.40 102	70.97 172	68.29 182	78.46 172	77.00 156

view600		67.63 132	68.36 127	66.77 132	77.84 85	78.66 105	73.74 129	62.62 93	56.04 146	44.98 160	52.86 150	52.83 156	55.48 154	80.36 79	77.75 101	85.95 127	80.02 135

tfpn200view9		68.11 120	68.72 121	67.40 121	77.83 86	78.93 100	74.28 122	62.81 83	56.64 138	46.82 151	52.65 154	53.47 150	56.59 143	80.41 75	78.43 90	86.11 115	80.52 130

view800		67.35 135	68.22 130	66.35 136	77.83 86	78.62 106	72.97 137	62.58 94	55.71 148	44.13 164	52.69 153	52.24 165	54.58 159	80.27 81	78.19 94	86.01 122	79.79 137

tfpn		66.58 139	67.18 139	65.88 138	77.82 88	78.45 109	72.07 142	62.52 96	55.35 151	43.21 168	52.54 156	46.12 189	53.68 160	80.02 85	78.23 93	85.99 125	79.55 140

Fast-Effi-MVS+		73.11 67	73.66 70	72.48 65	77.72 89	80.88 80	78.55 83	58.83 144	65.19 73	60.36 73	59.98 81	62.42 94	71.22 51	81.66 58	80.61 71	88.20 54	84.88 82

UniMVSNet_NR-MVSNet		70.59 80	72.19 78	68.72 106	77.72 89	80.72 81	73.81 127	69.65 37	61.99 92	43.23 166	60.54 77	57.50 107	58.57 128	79.56 92	81.07 57	89.34 39	83.97 88

IterMVS-LS		71.69 73	72.82 76	70.37 89	77.54 91	76.34 142	75.13 112	60.46 115	61.53 98	57.57 87	64.89 66	67.33 80	66.04 90	77.09 129	77.37 110	85.48 136	85.18 75
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NR-MVSNet		68.79 114	70.56 86	66.71 135	77.48 92	79.54 95	73.52 132	69.20 42	61.20 100	39.76 175	58.52 88	50.11 176	51.37 167	80.26 82	80.71 66	88.97 45	83.59 95

conf0.05thres1000		66.26 141	66.77 143	65.66 139	77.45 93	78.10 110	71.85 145	62.44 97	51.47 175	43.00 169	47.92 174	51.66 168	53.40 162	79.71 88	77.97 97	85.82 129	80.56 128

TransMVSNet (Re)		64.74 151	65.66 152	63.66 152	77.40 94	75.33 148	69.86 149	62.67 92	47.63 188	41.21 174	50.01 167	52.33 162	45.31 178	79.57 91	77.69 103	85.49 135	77.07 155

TranMVSNet+NR-MVSNet		69.25 109	70.81 85	67.43 120	77.23 95	79.46 97	73.48 133	69.66 36	60.43 105	39.56 176	58.82 87	53.48 149	55.74 150	79.59 90	81.21 56	88.89 47	82.70 109

CANet_DTU		73.29 65	76.96 62	69.00 104	77.04 96	82.06 69	79.49 62	56.30 159	67.85 63	53.29 118	71.12 45	70.37 67	61.81 114	81.59 60	80.96 58	86.09 116	84.73 83

CHOSEN 1792x2688		69.20 110	69.26 110	69.13 102	76.86 97	78.93 100	77.27 99	60.12 125	61.86 94	54.42 109	42.54 185	61.61 95	66.91 71	78.55 101	78.14 96	79.23 170	83.23 100

HyFIR lowres test		69.47 106	68.94 113	70.09 94	76.77 98	82.93 65	76.63 103	60.17 121	59.00 114	54.03 112	40.54 191	65.23 86	67.89 64	76.54 136	78.30 92	85.03 141	80.07 134

UniMVSNet (Re)		69.53 103	71.90 79	66.76 133	76.42 99	80.93 77	72.59 139	68.03 49	61.75 96	41.68 173	58.34 94	57.23 115	53.27 164	79.53 93	80.62 70	88.57 51	84.90 81

DWT-MVSNet_training		67.24 136	65.96 148	68.74 105	76.15 100	74.36 156	74.37 121	56.66 157	61.82 95	60.51 72	58.23 96	49.76 178	65.07 95	70.04 180	70.39 167	79.70 167	77.11 154

gm-plane-assit		57.00 185	57.62 191	56.28 182	76.10 101	62.43 198	47.62 207	46.57 195	33.84 210	23.24 201	37.52 192	40.19 199	59.61 126	79.81 87	77.55 105	84.55 145	72.03 178

DU-MVS		69.63 98	70.91 84	68.13 112	75.99 102	79.54 95	73.81 127	69.20 42	61.20 100	43.23 166	58.52 88	53.50 147	58.57 128	79.22 96	80.45 72	87.97 59	83.97 88

Baseline_NR-MVSNet		67.53 133	68.77 119	66.09 137	75.99 102	74.75 153	72.43 140	68.41 45	61.33 99	38.33 179	51.31 162	54.13 142	56.03 147	79.22 96	78.19 94	85.37 137	82.45 111

CostFormer		68.92 112	69.58 100	68.15 111	75.98 104	76.17 144	78.22 92	51.86 175	65.80 70	61.56 70	63.57 70	62.83 92	61.85 112	70.40 179	68.67 177	79.42 168	79.62 139

tpm cat1		65.41 144	63.81 168	67.28 124	75.61 105	72.88 159	75.32 106	52.85 169	62.97 87	63.66 66	53.24 143	53.29 154	61.83 113	65.54 191	64.14 194	74.43 188	74.60 169

CDS-MVSNet		67.65 130	69.83 97	65.09 141	75.39 106	76.55 137	74.42 120	63.75 74	53.55 164	49.37 142	59.41 84	62.45 93	44.44 179	79.71 88	79.82 75	83.17 153	77.36 151
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+-dtu		68.34 117	69.47 102	67.01 128	75.15 107	77.97 117	77.12 100	55.40 162	57.87 120	46.68 152	56.17 106	60.39 97	62.36 107	76.32 137	76.25 138	85.35 138	81.34 122

WR-MVS		63.03 157	67.40 137	57.92 176	75.14 108	77.60 121	60.56 187	66.10 59	54.11 163	23.88 198	53.94 136	53.58 145	34.50 194	73.93 150	77.71 102	87.35 71	80.94 125

test-LLR		64.42 152	64.36 164	64.49 146	75.02 109	63.93 188	66.61 166	61.96 100	54.41 159	47.77 147	57.46 99	60.25 98	55.20 155	70.80 173	69.33 172	80.40 164	74.38 171

test0.0.03 1		58.80 181	61.58 181	55.56 184	75.02 109	68.45 175	59.58 191	61.96 100	52.74 166	29.57 190	49.75 170	54.56 138	31.46 197	71.19 167	69.77 169	75.75 181	64.57 192

v1144		69.93 97	69.36 109	70.61 79	74.89 111	80.93 77	79.11 66	60.64 110	55.97 147	55.31 107	53.85 137	54.14 140	66.54 75	78.10 106	77.44 108	87.14 78	85.09 76

v13		69.52 104	68.76 120	70.41 87	74.88 112	77.02 132	78.52 87	58.86 138	56.61 139	56.91 92	54.00 135	56.17 127	66.11 89	77.93 107	76.74 124	87.21 73	82.83 102

v12		69.54 102	68.79 118	70.41 87	74.88 112	77.03 130	78.54 86	58.85 140	56.71 136	56.87 94	54.13 133	56.23 126	66.15 85	77.89 108	76.74 124	87.17 74	82.80 103

v11		69.37 107	68.65 123	70.20 91	74.87 114	76.97 133	78.29 90	58.55 148	56.38 141	56.04 103	54.02 134	54.98 135	66.47 76	78.30 103	76.91 116	86.97 87	83.02 101

V9		69.58 101	68.83 116	70.46 84	74.85 115	77.04 128	78.65 81	58.85 140	56.83 135	57.12 90	54.26 128	56.31 121	66.14 87	77.83 110	76.76 119	87.13 79	82.79 105

V14		69.59 100	68.86 115	70.45 86	74.83 116	77.04 128	78.70 80	58.83 144	56.95 132	57.08 91	54.41 124	56.34 120	66.15 85	77.77 111	76.76 119	87.08 84	82.74 108

v15		69.61 99	68.88 114	70.46 84	74.81 117	77.03 130	78.75 79	58.83 144	57.06 129	57.18 89	54.55 123	56.37 119	66.13 88	77.70 112	76.76 119	87.03 86	82.69 110

v7		70.33 86	69.87 94	70.88 68	74.79 118	81.04 76	79.22 64	60.57 112	57.70 126	56.65 100	54.23 130	55.29 133	66.95 68	78.28 104	77.47 106	87.12 82	85.05 78

v10		70.22 88	69.76 98	70.74 74	74.79 118	80.30 92	79.22 64	59.81 128	57.71 125	56.58 101	54.22 132	55.31 131	66.95 68	78.28 104	77.47 106	87.12 82	85.07 77

v1141		69.96 96	69.44 106	70.58 82	74.78 120	80.50 87	78.85 69	60.30 116	56.95 132	56.74 97	54.68 121	56.26 125	65.93 91	77.38 123	76.72 129	86.88 92	83.57 98

divwei89l23v2f112		69.97 94	69.44 106	70.58 82	74.78 120	80.50 87	78.85 69	60.30 116	56.97 131	56.75 96	54.67 122	56.27 124	65.92 92	77.37 124	76.72 129	86.88 92	83.58 97

v1		69.97 94	69.45 105	70.59 80	74.78 120	80.51 86	78.84 71	60.30 116	56.98 130	56.81 95	54.69 120	56.29 123	65.91 93	77.37 124	76.71 132	86.89 91	83.59 95

v17		70.03 93	69.43 108	70.72 76	74.75 123	77.09 125	78.78 78	58.85 140	59.53 112	58.72 80	54.87 117	57.39 109	66.38 78	77.60 116	76.75 122	86.83 95	82.80 103

v16		70.07 91	69.46 103	70.79 72	74.74 124	77.08 126	78.79 76	58.86 138	59.75 109	59.15 77	54.87 117	57.33 110	66.38 78	77.61 115	76.77 117	86.81 101	82.79 105

v8		70.23 87	69.86 96	70.67 78	74.69 125	79.82 94	78.79 76	59.18 134	58.80 116	58.20 82	55.00 113	57.33 110	66.31 84	77.51 120	76.71 132	86.82 96	83.88 91

v1neww		70.34 84	69.93 92	70.82 70	74.68 126	80.61 83	78.80 74	60.17 121	58.74 117	58.10 84	55.00 113	57.28 113	66.33 81	77.53 117	76.74 124	86.82 96	83.61 93

v7new		70.34 84	69.93 92	70.82 70	74.68 126	80.61 83	78.80 74	60.17 121	58.74 117	58.10 84	55.00 113	57.28 113	66.33 81	77.53 117	76.74 124	86.82 96	83.61 93

v6		70.35 83	69.94 91	70.83 69	74.68 126	80.62 82	78.81 73	60.16 124	58.81 115	58.17 83	55.01 112	57.31 112	66.32 83	77.53 117	76.73 128	86.82 96	83.62 92

v18		70.10 90	69.52 101	70.77 73	74.66 129	77.06 127	78.84 71	58.84 143	60.01 108	59.23 76	55.06 111	57.47 108	66.34 80	77.50 121	76.75 122	86.71 103	82.77 107

v2v482		70.05 92	69.46 103	70.74 74	74.62 130	80.32 91	79.00 67	60.62 111	57.41 127	56.89 93	55.43 110	55.14 134	66.39 77	77.25 126	77.14 113	86.90 89	83.57 98

v1192		69.50 105	68.83 116	70.29 90	74.49 131	80.92 79	78.55 83	60.54 113	55.04 155	54.21 110	52.79 152	52.33 162	66.92 70	77.88 109	77.35 111	87.04 85	85.51 68

DTE-MVSNet		61.85 170	64.96 161	58.22 175	74.32 132	74.39 155	61.01 186	67.85 51	51.76 174	21.91 208	53.28 141	48.17 182	37.74 190	72.22 160	76.44 135	86.52 112	78.49 144

Vis-MVSNet		72.77 69	77.20 60	67.59 119	74.19 133	84.01 56	76.61 104	61.69 104	60.62 104	50.61 134	70.25 48	71.31 62	55.57 152	83.85 44	82.28 47	86.90 89	88.08 50
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
diffmvs		73.13 66	75.65 66	70.19 92	74.07 134	77.17 124	78.24 91	57.45 152	72.44 56	64.02 65	69.05 50	75.92 47	64.86 96	75.18 144	75.27 146	82.47 155	84.53 84

v144192		69.34 108	68.68 122	70.12 93	74.06 135	80.54 85	78.08 93	60.54 113	54.99 157	54.13 111	52.92 149	52.80 158	66.73 73	77.13 128	76.72 129	87.15 75	85.63 64

v1921920		69.03 111	68.32 128	69.86 96	74.03 136	80.37 90	77.55 95	60.25 120	54.62 158	53.59 116	52.36 157	51.50 169	66.75 72	77.17 127	76.69 134	86.96 88	85.56 65

PEN-MVS		62.96 158	65.77 151	59.70 169	73.98 137	75.45 146	63.39 180	67.61 52	52.49 168	25.49 197	53.39 139	49.12 181	40.85 187	71.94 163	77.26 112	86.86 94	80.72 127

v1240		68.64 116	67.89 133	69.51 100	73.89 138	80.26 93	76.73 102	59.97 127	53.43 165	53.08 119	51.82 160	50.84 172	66.62 74	76.79 132	76.77 117	86.78 102	85.34 72

GA-MVS		68.14 119	69.17 111	66.93 130	73.77 139	78.50 108	74.45 117	58.28 149	55.11 154	48.44 144	60.08 79	53.99 143	61.50 115	78.43 102	77.57 104	85.13 139	80.54 129

pm-mvs1		65.62 143	67.42 136	63.53 153	73.66 140	76.39 141	69.66 150	60.87 109	49.73 183	43.97 165	51.24 163	57.00 117	48.16 172	79.89 86	77.84 99	84.85 144	79.82 136

dps		64.00 155	62.99 170	65.18 140	73.29 141	72.07 162	68.98 155	53.07 168	57.74 124	58.41 81	55.55 109	47.74 185	60.89 120	69.53 182	67.14 186	76.44 180	71.19 180

v148		67.85 125	67.53 134	68.23 110	73.25 142	77.57 122	74.26 124	57.36 154	55.70 149	57.45 88	53.53 138	55.42 130	61.96 110	75.23 143	73.92 153	85.08 140	81.32 123

PatchMatch-RL		67.78 127	66.65 145	69.10 103	73.01 143	72.69 160	68.49 156	61.85 102	62.93 88	60.20 75	56.83 104	50.42 174	69.52 57	75.62 141	74.46 152	81.51 158	73.62 176

GBi-Net		70.78 77	73.37 73	67.76 113	72.95 144	78.00 112	75.15 109	62.72 86	64.13 80	51.44 126	58.37 91	69.02 73	57.59 134	81.33 65	80.72 62	86.70 104	82.02 113

test1		70.78 77	73.37 73	67.76 113	72.95 144	78.00 112	75.15 109	62.72 86	64.13 80	51.44 126	58.37 91	69.02 73	57.59 134	81.33 65	80.72 62	86.70 104	82.02 113

FMVSNet2		70.39 82	72.67 77	67.72 116	72.95 144	78.00 112	75.15 109	62.69 90	63.29 85	51.25 130	55.64 107	68.49 79	57.59 134	80.91 73	80.35 73	86.70 104	82.02 113

FMVSNet3		70.49 81	72.90 75	67.67 117	72.88 147	77.98 115	74.96 115	62.72 86	64.13 80	51.44 126	58.37 91	69.02 73	57.43 137	79.43 94	79.57 80	86.59 110	81.81 120

LTVRE_ROB	59.44 16	61.82 173	62.64 174	60.87 163	72.83 148	77.19 123	64.37 176	58.97 135	33.56 211	28.00 194	52.59 155	42.21 195	63.93 100	74.52 146	76.28 136	77.15 177	82.13 112
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		67.05 138	66.94 141	67.17 125	72.35 149	78.97 99	73.26 136	58.88 137	51.16 176	50.90 131	48.21 172	50.11 176	60.96 117	77.70 112	77.38 109	86.68 107	85.05 78

tpm		62.41 164	63.15 169	61.55 160	72.24 150	63.79 190	71.31 147	46.12 197	57.82 121	55.33 106	59.90 82	54.74 137	53.63 161	67.24 189	64.29 192	70.65 199	74.25 173

test20.03		53.93 192	56.28 192	51.19 194	72.19 151	65.83 183	53.20 199	61.08 106	42.74 196	22.08 206	37.07 194	45.76 191	24.29 210	70.44 177	69.04 174	74.31 189	63.05 196

CP-MVSNet		62.68 160	65.49 154	59.40 172	71.84 152	75.34 147	62.87 182	67.04 55	52.64 167	27.19 195	53.38 140	48.15 183	41.40 185	71.26 166	75.68 142	86.07 117	82.00 116

PS-CasMVS		62.38 166	65.06 158	59.25 173	71.73 153	75.21 151	62.77 183	66.99 56	51.94 173	26.96 196	52.00 159	47.52 186	41.06 186	71.16 169	75.60 143	85.97 126	81.97 118

WR-MVS_H		61.83 172	65.87 150	57.12 179	71.72 154	76.87 134	61.45 185	66.19 57	51.97 172	22.92 205	53.13 146	52.30 164	33.80 195	71.03 170	75.00 149	86.65 108	80.78 126

USDC		67.36 134	67.90 132	66.74 134	71.72 154	75.23 149	71.58 146	60.28 119	67.45 64	50.54 135	60.93 75	45.20 192	62.08 108	76.56 135	74.50 151	84.25 146	75.38 166

UGNet		72.78 68	77.67 54	67.07 127	71.65 156	83.24 62	75.20 108	63.62 75	64.93 75	56.72 98	71.82 43	73.30 54	49.02 171	81.02 71	80.70 67	86.22 114	88.67 48
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		62.00 168	62.35 178	61.58 159	71.62 157	64.14 187	69.07 154	48.22 193	62.21 91	53.93 113	58.26 95	55.30 132	55.81 149	63.22 196	62.62 197	70.85 198	70.70 181

pmmvs4		67.89 124	67.39 138	68.48 109	71.60 158	73.57 158	74.45 117	60.98 107	64.65 77	57.97 86	54.95 116	51.73 167	61.88 111	73.78 151	75.11 148	83.99 149	77.91 147

testgi		54.39 191	57.86 189	50.35 195	71.59 159	67.24 178	54.95 197	53.25 167	43.36 195	23.78 199	44.64 182	47.87 184	24.96 206	70.45 176	68.66 178	73.60 191	62.78 197

pmmvs6		62.41 164	62.88 171	61.87 158	71.38 160	75.18 152	67.76 159	59.45 132	41.64 198	42.52 172	37.33 193	52.91 155	46.87 174	77.67 114	76.26 137	83.23 152	79.18 141

FMVSNet1		68.84 113	70.47 88	66.94 129	71.35 161	77.68 119	74.71 116	62.35 98	56.93 134	49.94 139	50.01 167	64.59 87	57.07 140	81.33 65	80.72 62	86.25 113	82.00 116

PatchmatchNet		64.21 154	64.65 162	63.69 151	71.29 162	68.66 173	69.63 151	51.70 177	63.04 86	53.77 115	59.83 83	58.34 105	60.23 124	68.54 186	66.06 189	75.56 183	68.08 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CR-MVSNet		64.83 150	65.54 153	64.01 150	70.64 163	69.41 169	65.97 169	52.74 170	57.81 122	52.65 121	54.27 126	56.31 121	60.92 118	72.20 161	73.09 157	81.12 161	75.69 163

MVSTER		72.06 71	74.24 69	69.51 100	70.39 164	75.97 145	76.91 101	57.36 154	64.64 78	61.39 71	68.86 51	63.76 89	63.46 101	81.44 62	79.70 76	87.56 68	85.31 73

Anonymous20231206		56.36 187	57.80 190	54.67 187	70.08 165	66.39 182	60.46 188	57.54 151	49.50 185	29.30 191	33.86 201	46.64 187	35.18 193	70.44 177	68.88 176	75.47 184	68.88 186

CMPMVS	47.78 17	62.49 163	62.52 175	62.46 156	70.01 166	70.66 167	62.97 181	51.84 176	51.98 171	56.71 99	42.87 184	53.62 144	57.80 133	72.23 159	70.37 168	75.45 185	75.91 160
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v748		65.12 148	65.24 155	64.98 142	69.77 167	76.45 138	69.47 152	57.06 156	49.93 181	50.70 132	47.87 175	49.50 180	57.14 139	73.64 153	75.18 147	85.75 132	84.14 87

TDRefinement		66.09 142	65.03 160	67.31 122	69.73 168	76.75 135	75.33 105	64.55 71	60.28 106	49.72 141	45.63 181	42.83 194	60.46 122	75.75 138	75.95 141	84.08 147	78.04 146

TinyColmap		62.84 159	61.03 183	64.96 143	69.61 169	71.69 163	68.48 157	59.76 129	55.41 150	47.69 149	47.33 178	34.20 204	62.76 106	74.52 146	72.59 160	81.44 159	71.47 179

RPMNet		61.71 174	62.88 171	60.34 165	69.51 170	69.41 169	63.48 179	49.23 185	57.81 122	45.64 158	50.51 165	50.12 175	53.13 165	68.17 188	68.49 180	81.07 162	75.62 165

IterMVS		66.36 140	68.30 129	64.10 147	69.48 171	74.61 154	73.41 134	50.79 181	57.30 128	48.28 145	60.64 76	59.92 100	60.85 121	74.14 149	72.66 159	81.80 157	78.82 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SixPastTwentyTwo		61.84 171	62.45 176	61.12 162	69.20 172	72.20 161	62.03 184	57.40 153	46.54 191	38.03 181	57.14 103	41.72 196	58.12 132	69.67 181	71.58 163	81.94 156	78.30 145

MDTV_nov1_ep13		64.37 153	65.24 155	63.37 155	68.94 173	70.81 165	72.40 141	50.29 184	60.10 107	53.91 114	60.07 80	59.15 103	57.21 138	69.43 183	67.30 184	77.47 175	69.78 183

EPMVS		60.00 179	61.97 179	57.71 177	68.46 174	63.17 194	64.54 175	48.23 192	63.30 84	44.72 162	60.19 78	56.05 129	50.85 168	65.27 193	62.02 199	69.44 201	63.81 194

Anonymous20231211		51.46 196	50.59 198	52.46 193	67.30 175	66.70 181	55.00 196	59.22 133	29.96 213	17.62 213	19.11 215	28.74 213	35.72 192	66.42 190	69.52 171	79.92 166	73.71 175

FC-MVSNet-test		56.90 186	65.20 157	47.21 198	66.98 176	63.20 193	49.11 205	58.60 147	59.38 113	11.50 218	65.60 64	56.68 118	24.66 209	71.17 168	71.36 165	72.38 194	69.02 185

CVMVSNet		62.55 161	65.89 149	58.64 174	66.95 177	69.15 171	66.49 168	56.29 160	52.46 169	32.70 187	59.27 85	58.21 106	50.09 169	71.77 164	71.39 164	79.31 169	78.99 142

FPMVS		51.87 195	50.00 200	54.07 188	66.83 178	57.25 201	60.25 189	50.91 179	50.25 178	34.36 185	36.04 198	32.02 206	41.49 184	58.98 208	56.07 208	70.56 200	59.36 203

pmmvs-eth3d		63.52 156	62.44 177	64.77 144	66.82 179	70.12 168	69.41 153	59.48 131	54.34 162	52.71 120	46.24 180	44.35 193	56.93 141	72.37 156	73.77 154	83.30 151	75.91 160

testpf		47.41 199	48.47 205	46.18 199	66.30 180	50.67 210	48.15 206	42.60 207	37.10 206	28.75 192	40.97 187	39.01 201	30.82 198	52.95 213	53.74 212	60.46 211	64.87 191

TAMVS		59.58 180	62.81 173	55.81 183	66.03 181	65.64 185	63.86 178	48.74 188	49.95 179	37.07 183	54.77 119	58.54 104	44.44 179	72.29 158	71.79 161	74.70 187	66.66 189

MDTV_nov1_ep13_2view		60.16 178	60.51 185	59.75 168	65.39 182	69.05 172	68.00 158	48.29 191	51.99 170	45.95 156	48.01 173	49.64 179	53.39 163	68.83 185	66.52 188	77.47 175	69.55 184

pmmvs5		62.37 167	64.04 166	60.42 164	65.03 183	71.67 164	67.17 161	52.70 172	50.30 177	44.80 161	54.23 130	51.19 171	49.37 170	72.88 155	73.48 156	83.45 150	74.55 170

ambc			53.42 194		64.99 184	63.36 192	49.96 203		47.07 189	37.12 182	28.97 205	16.36 220	41.82 183	75.10 145	67.34 183	71.55 197	75.72 162

V42		68.76 115	69.63 99	67.74 115	64.93 185	78.01 111	78.30 89	56.48 158	58.65 119	56.30 102	54.26 128	57.03 116	64.85 97	77.47 122	77.01 115	85.60 134	84.96 80

PMVS	39.38 18	46.06 204	43.30 209	49.28 197	62.93 186	38.75 217	41.88 210	53.50 166	33.33 212	35.46 184	28.90 206	31.01 209	33.04 196	58.61 209	54.63 211	68.86 202	57.88 206
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new-patchmatchnet		46.97 202	49.47 201	44.05 204	62.82 187	56.55 202	45.35 208	52.01 174	42.47 197	17.04 214	35.73 199	35.21 203	21.84 215	61.27 201	54.83 210	65.26 209	60.26 200

ADS-MVSNet		55.94 188	58.01 188	53.54 192	62.48 188	58.48 200	59.12 192	46.20 196	59.65 111	42.88 170	52.34 158	53.31 153	46.31 176	62.00 200	60.02 204	64.23 210	60.24 202

v52		65.23 146	66.24 146	64.06 148	61.94 189	76.42 139	72.06 143	54.30 164	49.94 180	50.04 137	47.41 177	52.42 160	60.23 124	75.71 139	76.22 139	85.78 130	85.56 65

V4		65.23 146	66.23 147	64.06 148	61.94 189	76.42 139	72.05 144	54.31 163	49.91 182	50.06 136	47.42 176	52.40 161	60.24 123	75.71 139	76.22 139	85.78 130	85.56 65

RPSCF		67.64 131	71.25 82	63.43 154	61.86 191	70.73 166	67.26 160	50.86 180	74.20 52	58.91 78	67.49 59	69.33 70	64.10 99	71.41 165	68.45 181	77.61 174	77.17 152

MIMVSNet		58.52 183	61.34 182	55.22 185	60.76 192	67.01 179	66.81 163	49.02 187	56.43 140	38.90 178	40.59 190	54.54 139	40.57 188	73.16 154	71.65 162	75.30 186	66.00 190

PatchT		61.97 169	64.04 166	59.55 171	60.49 193	67.40 177	56.54 194	48.65 189	56.69 137	52.65 121	51.10 164	52.14 166	60.92 118	72.20 161	73.09 157	78.03 173	75.69 163

N_pmnet		47.35 200	50.13 199	44.11 203	59.98 194	51.64 209	51.86 200	44.80 202	49.58 184	20.76 209	40.65 189	40.05 200	29.64 199	59.84 206	55.15 209	57.63 212	54.00 210

1111		43.08 206	44.02 208	41.98 205	59.22 195	49.27 213	41.48 211	45.63 199	35.01 207	23.06 203	28.60 207	30.15 210	27.22 201	60.42 204	57.97 206	55.27 215	46.74 212

.test1245		30.81 213	29.14 215	32.77 212	59.22 195	49.27 213	41.48 211	45.63 199	35.01 207	23.06 203	28.60 207	30.15 210	27.22 201	60.42 204	0.10 219	0.01 223	0.43 221

MVS-HIRNet		54.41 190	52.10 197	57.11 180	58.99 197	56.10 203	49.68 204	49.10 186	46.18 192	52.15 125	33.18 202	46.11 190	56.10 146	63.19 197	59.70 205	76.64 179	60.25 201

PM-MVS		60.48 177	60.94 184	59.94 167	58.85 198	66.83 180	64.27 177	51.39 178	55.03 156	48.03 146	50.00 169	40.79 198	58.26 131	69.20 184	67.13 187	78.84 171	77.60 149

anonymousdsp		65.28 145	67.98 131	62.13 157	58.73 199	73.98 157	67.10 162	50.69 182	48.41 186	47.66 150	54.27 126	52.75 159	61.45 116	76.71 134	80.20 74	87.13 79	89.53 44

LP		53.62 193	53.43 193	53.83 190	58.51 200	62.59 197	57.31 193	46.04 198	47.86 187	42.69 171	36.08 197	36.86 202	46.53 175	64.38 194	64.25 193	71.92 195	62.00 199

TESTMET0.1,1		61.10 175	64.36 164	57.29 178	57.53 201	63.93 188	66.61 166	36.22 212	54.41 159	47.77 147	57.46 99	60.25 98	55.20 155	70.80 173	69.33 172	80.40 164	74.38 171

EU-MVSNet		54.63 189	58.69 187	49.90 196	56.99 202	62.70 196	56.41 195	50.64 183	45.95 193	23.14 202	50.42 166	46.51 188	36.63 191	65.51 192	64.85 191	75.57 182	74.91 168

FMVSNet5		57.24 184	60.02 186	53.99 189	56.45 203	62.74 195	65.27 172	47.03 194	55.14 153	39.55 177	40.88 188	53.42 151	41.83 182	72.35 157	71.10 166	73.79 190	64.50 193

test2356		47.20 201	48.62 204	45.54 201	56.38 204	54.89 205	50.62 201	45.08 201	38.65 203	23.40 200	36.23 196	31.10 208	29.31 200	62.76 198	62.49 198	68.48 203	54.23 209

testus		45.61 205	49.06 203	41.59 206	56.13 205	55.28 204	43.51 209	39.64 210	37.74 204	18.23 211	35.52 200	31.28 207	24.69 208	62.46 199	62.90 196	67.33 205	58.26 205

test-mter		60.84 176	64.62 163	56.42 181	55.99 206	64.18 186	65.39 171	34.23 214	54.39 161	46.21 154	57.40 101	59.49 102	55.86 148	71.02 171	69.65 170	80.87 163	76.20 159

CHOSEN 280x420		58.70 182	61.88 180	54.98 186	55.45 207	50.55 211	64.92 173	40.36 208	55.21 152	38.13 180	48.31 171	63.76 89	63.03 105	73.73 152	68.58 179	68.00 204	73.04 177

PMMVS		65.06 149	69.17 111	60.26 166	55.25 208	63.43 191	66.71 165	43.01 206	62.41 89	50.64 133	69.44 49	67.04 81	63.29 103	74.36 148	73.54 155	82.68 154	73.99 174

testmv		42.58 207	44.36 206	40.49 207	54.63 209	52.76 207	41.21 213	44.37 203	28.83 214	12.87 215	27.16 210	25.03 215	23.01 211	60.83 202	61.13 200	66.88 206	54.81 207

test1235678		42.57 208	44.36 206	40.49 207	54.63 209	52.75 208	41.21 213	44.37 203	28.82 215	12.87 215	27.15 211	25.01 216	23.01 211	60.83 202	61.13 200	66.88 206	54.81 207

no-one		36.35 211	37.59 212	34.91 210	46.13 211	49.89 212	27.99 218	43.56 205	20.91 219	7.03 221	14.64 217	15.50 221	18.92 216	42.95 214	60.20 203	65.84 208	59.03 204

Gipuma		36.38 210	35.80 213	37.07 209	45.76 212	33.90 218	29.81 217	48.47 190	39.91 201	18.02 212	8.00 221	8.14 223	25.14 205	59.29 207	61.02 202	55.19 216	40.31 214
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs3		47.65 198	49.08 202	45.99 200	44.61 213	54.79 206	50.04 202	31.95 217	33.91 209	29.90 189	30.37 203	33.53 205	46.31 176	63.50 195	63.67 195	73.14 193	63.77 195

MIMVSNet1		49.27 197	53.25 195	44.62 202	44.61 213	61.52 199	53.61 198	52.18 173	41.62 199	18.68 210	28.14 209	41.58 197	25.50 204	68.46 187	69.04 174	73.15 192	62.37 198

test12356		35.10 212	38.50 211	31.13 213	44.14 215	43.70 216	32.27 216	34.42 213	26.51 217	9.47 219	25.22 213	20.34 217	10.86 218	53.47 211	56.15 207	55.59 214	44.11 213

MDA-MVSNet-bldmvs		53.37 194	53.01 196	53.79 191	43.67 216	67.95 176	59.69 190	57.92 150	43.69 194	32.41 188	41.47 186	27.89 214	52.38 166	56.97 210	65.99 190	76.68 178	67.13 188

E-PMN		21.77 215	18.24 217	25.89 214	40.22 217	19.58 221	12.46 222	39.87 209	18.68 221	6.71 222	9.57 218	4.31 226	22.36 214	19.89 219	27.28 217	33.73 218	28.34 218

EMVS		20.98 216	17.15 218	25.44 215	39.51 218	19.37 222	12.66 221	39.59 211	19.10 220	6.62 223	9.27 219	4.40 225	22.43 213	17.99 220	24.40 218	31.81 219	25.53 219

new_pmnet		38.40 209	42.64 210	33.44 211	37.54 219	45.00 215	36.60 215	32.72 216	40.27 200	12.72 217	29.89 204	28.90 212	24.78 207	53.17 212	52.90 213	56.31 213	48.34 211

PMMVS2		25.60 214	29.75 214	20.76 217	28.00 220	30.93 219	23.10 219	29.18 218	23.14 218	1.46 225	18.23 216	16.54 219	5.08 219	40.22 215	41.40 215	37.76 217	37.79 216

tmp_tt				14.50 219	14.68 221	7.17 224	10.46 224	2.21 220	37.73 205	28.71 193	25.26 212	16.98 218	4.37 220	31.49 216	29.77 216	26.56 220

MVE	19.12 19	20.47 217	23.27 216	17.20 218	12.66 222	25.41 220	10.52 223	34.14 215	14.79 222	6.53 224	8.79 220	4.68 224	16.64 217	29.49 217	41.63 214	22.73 221	38.11 215
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND		46.86 203	67.51 135	22.75 216	0.05 223	76.21 143	64.69 174	0.04 221	61.90 93	0.09 226	55.57 108	71.32 61	0.08 221	70.54 175	67.19 185	71.58 196	69.86 182

testmvs		0.09 218	0.15 219	0.02 220	0.01 224	0.02 225	0.05 226	0.01 222	0.11 223	0.01 227	0.26 223	0.01 227	0.06 223	0.10 221	0.10 219	0.01 223	0.43 221

ESAPD		0.00 220	0.00 221	0.00 222	0.00 225	0.00 227	0.00 228	0.00 224	0.00 225	0.00 228	0.00 224	0.00 228	0.00 224	0.00 223	0.00 222	0.00 226	0.00 223

sosnet-low-res		0.00 220	0.00 221	0.00 222	0.00 225	0.00 227	0.00 228	0.00 224	0.00 225	0.00 228	0.00 224	0.00 228	0.00 224	0.00 223	0.00 222	0.00 226	0.00 223

sosnet		0.00 220	0.00 221	0.00 222	0.00 225	0.00 227	0.00 228	0.00 224	0.00 225	0.00 228	0.00 224	0.00 228	0.00 224	0.00 223	0.00 222	0.00 226	0.00 223

test123		0.09 218	0.14 220	0.02 220	0.00 225	0.02 225	0.02 227	0.01 222	0.09 224	0.00 228	0.30 222	0.00 228	0.08 221	0.03 222	0.09 221	0.01 223	0.45 220

MTAPA										83.48 1		86.45 11

MTMP										82.66 3		84.91 19

Patchmatch-RL test							2.85 225

NP-MVS									80.10 38

Patchmtry						65.80 184	65.97 169	52.74 170		52.65 121

DeepMVS_CX						18.74 223	18.55 220	8.02 219	26.96 216	7.33 220	23.81 214	13.05 222	25.99 203	25.17 218		22.45 222	36.25 217

High-resolution multi-view benchmark