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 7	88.92 11	84.95 4	92.61 1	87.91 39	90.23 14	76.06 3	88.85 11	81.20 9	87.33 12	87.93 10	79.47 7	88.59 7	88.23 5	90.15 33	93.60 20

SMA-MVS		87.56 5	90.17 5	84.52 8	91.71 2	90.57 8	90.77 7	75.19 12	90.67 5	80.50 13	86.59 16	88.86 6	78.09 15	89.92 1	89.41 1	90.84 9	95.19 4

NCCC		85.34 19	86.59 23	83.88 15	91.48 3	88.88 24	89.79 16	75.54 10	86.67 20	77.94 22	76.55 34	84.99 24	78.07 16	88.04 10	87.68 10	90.46 24	93.31 21

CNVR-MVS		86.36 12	88.19 15	84.23 11	91.33 4	89.84 13	90.34 10	75.56 9	87.36 17	78.97 17	81.19 27	86.76 16	78.74 10	89.30 3	88.58 2	90.45 25	94.33 9

xxxxxxxxxxxxxcwj		85.35 18	85.76 29	84.86 6	91.26 5	91.10 6	90.90 4	75.65 6	89.21 7	81.25 6	91.12 6	61.35 113	78.82 8	87.42 18	86.23 29	91.28 3	93.90 12

SF-MVS		87.47 6	89.70 6	84.86 6	91.26 5	91.10 6	90.90 4	75.65 6	89.21 7	81.25 6	91.12 6	88.93 5	78.82 8	87.42 18	86.23 29	91.28 3	93.90 12

APDe-MVS		88.00 4	90.50 4	85.08 3	90.95 7	91.58 5	92.03 1	75.53 11	91.15 3	80.10 14	92.27 3	88.34 9	80.80 3	88.00 12	86.99 17	91.09 6	95.16 5

DPE-MVS		88.63 2	91.29 2	85.53 1	90.87 8	92.20 2	91.98 2	76.00 4	90.55 6	82.09 5	93.85 1	90.75 1	81.25 1	88.62 6	87.59 12	90.96 8	95.48 2

HFP-MVS		86.15 13	87.95 16	84.06 13	90.80 9	89.20 22	89.62 19	74.26 15	87.52 14	80.63 11	86.82 15	84.19 28	78.22 13	87.58 16	87.19 15	90.81 11	93.13 24

SteuartSystems-ACMMP		85.99 14	88.31 14	83.27 20	90.73 10	89.84 13	90.27 13	74.31 14	84.56 29	75.88 29	87.32 13	85.04 23	77.31 23	89.01 5	88.46 3	91.14 5	93.96 11
Skip Steuart: Steuart Systems R&D Blog.
APD-MVS		86.84 10	88.91 12	84.41 9	90.66 11	90.10 11	90.78 6	75.64 8	87.38 16	78.72 18	90.68 9	86.82 15	80.15 5	87.13 24	86.45 27	90.51 19	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MP-MVS		85.50 17	87.40 19	83.28 19	90.65 12	89.51 18	89.16 23	74.11 18	83.70 33	78.06 21	85.54 19	84.89 26	77.31 23	87.40 21	87.14 16	90.41 26	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
train_agg		84.86 24	87.21 20	82.11 26	90.59 13	85.47 54	89.81 15	73.55 25	83.95 31	73.30 37	89.84 11	87.23 13	75.61 31	86.47 33	85.46 38	89.78 38	92.06 32

MCST-MVS		85.13 22	86.62 22	83.39 17	90.55 14	89.82 15	89.29 21	73.89 22	84.38 30	76.03 28	79.01 30	85.90 20	78.47 11	87.81 14	86.11 33	92.11 1	93.29 22

zzz-MVS		85.71 15	86.88 21	84.34 10	90.54 15	87.11 43	89.77 17	74.17 17	88.54 12	83.08 2	78.60 31	86.10 18	78.11 14	87.80 15	87.46 13	90.35 28	92.56 26

MSP-MVS		88.67 1	91.62 1	85.22 2	90.47 16	92.36 1	90.69 8	76.15 2	93.08 1	82.75 3	92.19 4	90.71 2	80.45 4	89.27 4	87.91 7	90.82 10	95.84 1

DeepC-MVS_fast	78.24 3	84.27 28	85.50 30	82.85 22	90.46 17	89.24 20	87.83 32	74.24 16	84.88 25	76.23 27	75.26 37	81.05 42	77.62 20	88.02 11	87.62 11	90.69 15	92.41 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP_NAP		86.52 11	89.01 9	83.62 16	90.28 18	90.09 12	90.32 12	74.05 19	88.32 13	79.74 15	87.04 14	85.59 22	76.97 28	89.35 2	88.44 4	90.35 28	94.27 10

SD-MVS		86.96 8	89.45 7	84.05 14	90.13 19	89.23 21	89.77 17	74.59 13	89.17 9	80.70 10	89.93 10	89.67 3	78.47 11	87.57 17	86.79 21	90.67 16	93.76 16
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
ACMMPR		85.52 16	87.53 18	83.17 21	90.13 19	89.27 19	89.30 20	73.97 20	86.89 19	77.14 24	86.09 17	83.18 31	77.74 19	87.42 18	87.20 14	90.77 12	92.63 25

PGM-MVS		84.42 27	86.29 26	82.23 25	90.04 21	88.82 26	89.23 22	71.74 35	82.82 36	74.61 32	84.41 22	82.09 34	77.03 27	87.13 24	86.73 23	90.73 14	92.06 32

DVP-MVS		88.09 3	90.84 3	84.88 5	90.00 22	91.80 4	91.63 3	75.80 5	91.99 2	81.23 8	92.54 2	89.18 4	80.89 2	87.99 13	87.91 7	89.70 42	94.51 6

CSCG		85.28 21	87.68 17	82.49 24	89.95 23	91.99 3	88.82 24	71.20 37	86.41 21	79.63 16	79.26 28	88.36 8	73.94 38	86.64 31	86.67 24	91.40 2	94.41 7

mPP-MVS					89.90 24							81.29 41

TSAR-MVS + MP.		86.88 9	89.23 8	84.14 12	89.78 25	88.67 30	90.59 9	73.46 26	88.99 10	80.52 12	91.26 5	88.65 7	79.91 6	86.96 29	86.22 31	90.59 17	93.83 14
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
X-MVS		83.23 32	85.20 32	80.92 33	89.71 26	88.68 27	88.21 31	73.60 23	82.57 37	71.81 45	77.07 32	81.92 36	71.72 57	86.98 28	86.86 19	90.47 21	92.36 29

DPM-MVS		83.30 31	84.33 34	82.11 26	89.56 27	88.49 33	90.33 11	73.24 27	83.85 32	76.46 26	72.43 47	82.65 32	73.02 46	86.37 35	86.91 18	90.03 35	89.62 51

TSAR-MVS + ACMM		85.10 23	88.81 13	80.77 34	89.55 28	88.53 32	88.59 27	72.55 30	87.39 15	71.90 42	90.95 8	87.55 11	74.57 33	87.08 26	86.54 25	87.47 83	93.67 17

CP-MVS		84.74 26	86.43 25	82.77 23	89.48 29	88.13 38	88.64 25	73.93 21	84.92 24	76.77 25	81.94 25	83.50 29	77.29 25	86.92 30	86.49 26	90.49 20	93.14 23

CDPH-MVS		82.64 33	85.03 33	79.86 38	89.41 30	88.31 35	88.32 29	71.84 34	80.11 44	67.47 60	82.09 24	81.44 40	71.85 55	85.89 39	86.15 32	90.24 31	91.25 38

DeepC-MVS	78.47 2	84.81 25	86.03 27	83.37 18	89.29 31	90.38 10	88.61 26	76.50 1	86.25 22	77.22 23	75.12 38	80.28 44	77.59 21	88.39 8	88.17 6	91.02 7	93.66 18
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 46	78.62 58	81.05 32	89.23 32	86.06 51	84.95 48	71.96 33	79.39 47	75.51 30	63.16 88	68.84 91	76.51 29	83.55 56	82.85 54	88.13 68	86.46 73

SR-MVS					88.99 33			73.57 24				87.54 12

EPNet		79.08 53	80.62 48	77.28 52	88.90 34	83.17 75	83.65 53	72.41 31	74.41 57	67.15 62	76.78 33	74.37 59	64.43 93	83.70 55	83.69 50	87.15 87	88.19 58
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	79.04 1	85.30 20	88.93 10	81.06 31	88.77 35	90.48 9	85.46 45	73.08 28	90.97 4	73.77 36	84.81 21	85.95 19	77.43 22	88.22 9	87.73 9	87.85 76	94.34 8

ACMMP		83.42 30	85.27 31	81.26 30	88.47 36	88.49 33	88.31 30	72.09 32	83.42 34	72.77 40	82.65 23	78.22 48	75.18 32	86.24 37	85.76 35	90.74 13	92.13 31
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 34	82.76 39	81.97 28	88.02 37	89.67 16	86.60 36	71.48 36	81.28 42	78.18 20	64.78 82	77.96 50	77.13 26	87.32 22	86.83 20	90.41 26	91.48 36

OPM-MVS		79.68 47	79.28 56	80.15 37	87.99 38	86.77 46	88.52 28	72.72 29	64.55 91	67.65 59	67.87 70	74.33 60	74.31 36	86.37 35	85.25 40	89.73 41	89.81 49

MAR-MVS		79.21 50	80.32 52	77.92 50	87.46 39	88.15 37	83.95 52	67.48 61	74.28 58	68.25 56	64.70 83	77.04 51	72.17 51	85.42 41	85.00 42	88.22 64	87.62 63
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 40	83.27 37	78.76 45	87.40 40	85.45 55	86.95 34	70.47 40	81.31 41	66.91 63	79.24 29	76.63 52	71.67 58	84.43 49	83.78 49	89.19 52	92.05 34

abl_6				79.05 42	87.27 41	88.85 25	83.62 54	68.25 54	81.68 40	72.94 39	73.79 44	84.45 27	72.55 49			89.66 44	90.64 43

CANet		81.62 39	83.41 36	79.53 40	87.06 42	88.59 31	85.47 44	67.96 58	76.59 52	74.05 33	74.69 39	81.98 35	72.98 47	86.14 38	85.47 37	89.68 43	90.42 46

MSLP-MVS++		82.09 36	82.66 40	81.42 29	87.03 43	87.22 42	85.82 41	70.04 42	80.30 43	78.66 19	68.67 66	81.04 43	77.81 18	85.19 45	84.88 43	89.19 52	91.31 37

ACMM	72.26 8	78.86 54	78.13 60	79.71 39	86.89 44	83.40 72	86.02 39	70.50 39	75.28 54	71.49 49	63.01 89	69.26 85	73.57 40	84.11 51	83.98 47	89.76 40	87.84 61
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					86.63 45	88.68 27	85.00 46			71.81 45		81.92 36				90.47 21

X-MVStestdata					86.63 45	88.68 27	85.00 46			71.81 45		81.92 36				90.47 21

PHI-MVS		82.36 35	85.89 28	78.24 48	86.40 47	89.52 17	85.52 43	69.52 48	82.38 39	65.67 67	81.35 26	82.36 33	73.07 44	87.31 23	86.76 22	89.24 49	91.56 35

LGP-MVS_train		79.83 43	81.22 46	78.22 49	86.28 48	85.36 57	86.76 35	69.59 46	77.34 49	65.14 69	75.68 36	70.79 74	71.37 61	84.60 47	84.01 46	90.18 32	90.74 42

MVS_0304		81.73 38	83.86 35	79.26 41	86.22 49	89.18 23	86.41 37	67.15 62	75.28 54	70.75 52	74.59 40	83.49 30	74.42 35	87.05 27	86.34 28	90.58 18	91.08 40

CPTT-MVS		81.77 37	83.10 38	80.21 36	85.93 50	86.45 49	87.72 33	70.98 38	82.54 38	71.53 48	74.23 43	81.49 39	76.31 30	82.85 63	81.87 59	88.79 60	92.26 30

MVS_111021_HR		80.13 42	81.46 44	78.58 46	85.77 51	85.17 58	83.45 55	69.28 49	74.08 60	70.31 53	74.31 42	75.26 57	73.13 43	86.46 34	85.15 41	89.53 45	89.81 49

ACMP	73.23 7	79.79 44	80.53 49	78.94 43	85.61 52	85.68 52	85.61 42	69.59 46	77.33 50	71.00 51	74.45 41	69.16 86	71.88 53	83.15 60	83.37 52	89.92 36	90.57 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		74.47 73	77.80 63	70.59 87	85.33 53	85.40 56	73.54 134	65.98 71	60.65 122	56.00 104	72.11 48	79.15 45	54.63 159	83.13 61	82.25 57	88.04 70	81.92 121

TSAR-MVS + GP.		83.69 29	86.58 24	80.32 35	85.14 54	86.96 44	84.91 49	70.25 41	84.71 28	73.91 35	85.16 20	85.63 21	77.92 17	85.44 40	85.71 36	89.77 39	92.45 27

LS3D		74.08 74	73.39 86	74.88 65	85.05 55	82.62 78	79.71 71	68.66 52	72.82 63	58.80 87	57.61 117	61.31 114	71.07 63	80.32 94	78.87 106	86.00 125	80.18 135

QAPM		78.47 55	80.22 53	76.43 56	85.03 56	86.75 47	80.62 64	66.00 70	73.77 61	65.35 68	65.54 78	78.02 49	72.69 48	83.71 54	83.36 53	88.87 58	90.41 47

OpenMVS	70.44 10	76.15 66	76.82 74	75.37 62	85.01 57	84.79 60	78.99 79	62.07 114	71.27 65	67.88 58	57.91 116	72.36 67	70.15 65	82.23 68	81.41 64	88.12 69	87.78 62

CLD-MVS		79.35 49	81.23 45	77.16 53	85.01 57	86.92 45	85.87 40	60.89 124	80.07 46	75.35 31	72.96 45	73.21 64	68.43 75	85.41 42	84.63 44	87.41 84	85.44 84
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 45	80.52 50	78.84 44	84.94 59	87.35 40	84.43 51	65.54 73	78.29 48	73.97 34	63.00 90	75.62 56	74.07 37	85.00 46	85.34 39	90.11 34	89.04 53

PCF-MVS	73.28 6	79.42 48	80.41 51	78.26 47	84.88 60	88.17 36	86.08 38	69.85 43	75.23 56	68.43 55	68.03 69	78.38 47	71.76 56	81.26 81	80.65 81	88.56 63	91.18 39
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DELS-MVS		79.15 52	81.07 47	76.91 54	83.54 61	87.31 41	84.45 50	64.92 78	69.98 66	69.34 54	71.62 51	76.26 53	69.84 66	86.57 32	85.90 34	89.39 47	89.88 48
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 41	82.59 41	77.54 51	83.04 62	85.54 53	83.25 56	65.05 77	87.32 18	72.42 41	72.04 49	78.97 46	73.30 42	83.86 52	81.60 63	88.15 67	88.83 55

PLC	68.99 11	75.68 67	75.31 79	76.12 58	82.94 63	81.26 87	79.94 68	66.10 68	77.15 51	66.86 64	59.13 106	68.53 92	73.73 39	80.38 93	79.04 102	87.13 91	81.68 123
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		77.20 60	77.54 65	76.80 55	82.63 64	84.31 62	79.77 70	64.64 79	85.17 23	73.18 38	56.37 123	69.81 82	74.53 34	81.12 84	78.69 107	86.04 123	87.29 67

ACMH+	66.54 13	71.36 91	70.09 109	72.85 75	82.59 65	81.13 89	78.56 81	68.04 56	61.55 115	52.52 126	51.50 162	54.14 148	68.56 74	78.85 114	79.50 98	86.82 99	83.94 103

ACMH	65.37 14	70.71 95	70.00 110	71.54 79	82.51 66	82.47 79	77.78 89	68.13 55	56.19 149	46.06 158	54.30 133	51.20 175	68.68 73	80.66 89	80.72 74	86.07 119	84.45 100
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EIA-MVS		75.64 68	76.60 75	74.53 69	82.43 67	83.84 65	78.32 85	62.28 113	65.96 81	63.28 77	68.95 62	67.54 95	71.61 59	82.55 65	81.63 62	89.24 49	85.72 78

canonicalmvs		79.16 51	82.37 42	75.41 61	82.33 68	86.38 50	80.80 61	63.18 91	82.90 35	67.34 61	72.79 46	76.07 54	69.62 67	83.46 59	84.41 45	89.20 51	90.60 44

ETV-MVS		77.32 59	78.81 57	75.58 60	82.24 69	83.64 69	79.98 66	64.02 85	69.64 70	63.90 74	70.89 55	69.94 81	73.41 41	85.39 43	83.91 48	89.92 36	88.31 57

MSDG		71.52 88	69.87 111	73.44 73	82.21 70	79.35 106	79.52 72	64.59 80	66.15 79	61.87 78	53.21 147	56.09 138	65.85 91	78.94 113	78.50 109	86.60 108	76.85 157

CS-MVS		76.92 61	78.01 61	75.64 59	81.47 71	83.59 70	80.68 62	62.47 110	68.39 72	65.83 66	67.84 71	70.74 75	73.07 44	85.31 44	82.79 55	90.33 30	87.42 64

IS_MVSNet		73.33 77	77.34 70	68.65 107	81.29 72	83.47 71	74.45 116	63.58 88	65.75 83	48.49 143	67.11 75	70.61 76	54.63 159	84.51 48	83.58 51	89.48 46	86.34 74

Effi-MVS+		75.28 70	76.20 76	74.20 71	81.15 73	83.24 73	81.11 59	63.13 93	66.37 77	60.27 83	64.30 86	68.88 90	70.93 64	81.56 72	81.69 61	88.61 61	87.35 65

MVS_111021_LR		78.13 57	79.85 55	76.13 57	81.12 74	81.50 84	80.28 65	65.25 75	76.09 53	71.32 50	76.49 35	72.87 66	72.21 50	82.79 64	81.29 65	86.59 109	87.91 60

FC-MVSNet-train		72.60 82	75.07 80	69.71 96	81.10 75	78.79 113	73.74 133	65.23 76	66.10 80	53.34 119	70.36 57	63.40 108	56.92 144	81.44 74	80.96 70	87.93 72	84.46 99

MS-PatchMatch		70.17 102	70.49 106	69.79 95	80.98 76	77.97 125	77.51 91	58.95 147	62.33 109	55.22 108	53.14 148	65.90 100	62.03 109	79.08 111	77.11 131	84.08 148	77.91 149

Anonymous202405211			72.16 97		80.85 77	81.85 81	76.88 99	65.40 74	62.89 106		46.35 178	67.99 94	62.05 108	81.15 83	80.38 85	85.97 126	84.50 98

TAPA-MVS	71.42 9	77.69 58	80.05 54	74.94 64	80.68 78	84.52 61	81.36 58	63.14 92	84.77 26	64.82 71	68.72 64	75.91 55	71.86 54	81.62 70	79.55 97	87.80 78	85.24 87
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_Blended_VisFu		76.57 63	77.90 62	75.02 63	80.56 79	86.58 48	79.24 75	66.18 67	64.81 88	68.18 57	65.61 76	71.45 69	67.05 77	84.16 50	81.80 60	88.90 56	90.92 41

EPP-MVSNet		74.00 75	77.41 68	70.02 93	80.53 80	83.91 64	74.99 112	62.68 105	65.06 86	49.77 139	68.68 65	72.09 68	63.06 101	82.49 67	80.73 73	89.12 54	88.91 54

COLMAP_ROB	62.73 15	67.66 131	66.76 147	68.70 106	80.49 81	77.98 123	75.29 105	62.95 95	63.62 100	49.96 137	47.32 177	50.72 178	58.57 129	76.87 135	75.50 147	84.94 143	75.33 168
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
casdiffmvs		76.76 62	78.46 59	74.77 66	80.32 82	83.73 68	80.65 63	63.24 90	73.58 62	66.11 65	69.39 61	74.09 61	69.49 69	82.52 66	79.35 101	88.84 59	86.52 72

DCV-MVSNet		73.65 76	75.78 78	71.16 81	80.19 83	79.27 107	77.45 94	61.68 120	66.73 76	58.72 88	65.31 79	69.96 80	62.19 106	81.29 80	80.97 69	86.74 102	86.91 68

Anonymous20231211		71.90 85	72.48 94	71.21 80	80.14 84	81.53 83	76.92 97	62.89 96	64.46 93	58.94 85	43.80 182	70.98 73	62.22 105	80.70 88	80.19 88	86.18 116	85.73 77

TSAR-MVS + COLMAP		78.34 56	81.64 43	74.48 70	80.13 85	85.01 59	81.73 57	65.93 72	84.75 27	61.68 79	85.79 18	66.27 99	71.39 60	82.91 62	80.78 72	86.01 124	85.98 75

baseline1		70.10 103	72.17 96	67.69 116	79.74 86	76.80 135	73.91 127	64.38 82	62.74 107	48.30 145	64.94 80	64.08 105	54.17 161	81.46 73	78.92 104	85.66 131	76.22 159

EPNet_dtu		68.08 123	71.00 102	64.67 145	79.64 87	68.62 176	75.05 111	63.30 89	66.36 78	45.27 162	67.40 73	66.84 98	43.64 181	75.37 144	74.98 150	81.15 160	77.44 152
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_BlendedMVS		76.21 64	77.52 66	74.69 67	79.46 88	83.79 66	77.50 92	64.34 83	69.88 67	71.88 43	68.54 67	70.42 77	67.05 77	83.48 57	79.63 93	87.89 74	86.87 69

PVSNet_Blended		76.21 64	77.52 66	74.69 67	79.46 88	83.79 66	77.50 92	64.34 83	69.88 67	71.88 43	68.54 67	70.42 77	67.05 77	83.48 57	79.63 93	87.89 74	86.87 69

IB-MVS	66.94 12	71.21 92	71.66 100	70.68 84	79.18 90	82.83 77	72.61 140	61.77 118	59.66 127	63.44 76	53.26 145	59.65 121	59.16 128	76.78 137	82.11 58	87.90 73	87.33 66
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 69	77.13 72	73.31 74	79.07 91	81.32 86	79.98 66	60.12 135	69.72 69	64.11 73	70.53 56	73.22 63	68.90 71	80.14 99	79.48 99	87.67 80	85.50 82

Effi-MVS+-dtu		71.82 86	71.86 99	71.78 78	78.77 92	80.47 96	78.55 82	61.67 121	60.68 121	55.49 105	58.48 110	65.48 101	68.85 72	76.92 134	75.55 146	87.35 85	85.46 83

EG-PatchMatch MVS		67.24 138	66.94 145	67.60 118	78.73 93	81.35 85	73.28 138	59.49 140	46.89 190	51.42 131	43.65 183	53.49 156	55.50 156	81.38 76	80.66 80	87.15 87	81.17 127

gg-mvs-nofinetune		62.55 161	65.05 159	59.62 170	78.72 94	77.61 129	70.83 148	53.63 163	39.71 202	22.04 202	36.36 195	64.32 104	47.53 174	81.16 82	79.03 103	85.00 142	77.17 154

Vis-MVSNet (Re-imp)		67.83 128	73.52 85	61.19 161	78.37 95	76.72 137	66.80 166	62.96 94	65.50 84	34.17 185	67.19 74	69.68 83	39.20 189	79.39 108	79.44 100	85.68 130	76.73 158

DI_MVS_plusplus_trai		75.13 71	76.12 77	73.96 72	78.18 96	81.55 82	80.97 60	62.54 107	68.59 71	65.13 70	61.43 92	74.81 58	69.32 70	81.01 86	79.59 95	87.64 81	85.89 76

thres600view7		67.68 130	68.43 132	66.80 133	77.90 97	78.86 111	73.84 129	62.75 98	56.07 150	44.70 165	52.85 153	52.81 165	55.58 154	80.41 90	77.77 118	86.05 121	80.28 134

thres400		67.95 125	68.62 130	67.17 126	77.90 97	78.59 116	74.27 122	62.72 100	56.34 148	45.77 160	53.00 150	53.35 161	56.46 146	80.21 98	78.43 110	85.91 128	80.43 133

thres200		67.98 124	68.55 131	67.30 124	77.89 99	78.86 111	74.18 125	62.75 98	56.35 147	46.48 156	52.98 151	53.54 154	56.46 146	80.41 90	77.97 116	86.05 121	79.78 139

thres100view900		67.60 134	68.02 135	67.12 128	77.83 100	77.75 127	73.90 128	62.52 108	56.64 144	46.82 153	52.65 155	53.47 158	55.92 150	78.77 115	77.62 121	85.72 129	79.23 142

tfpn200view9		68.11 122	68.72 128	67.40 121	77.83 100	78.93 109	74.28 121	62.81 97	56.64 144	46.82 153	52.65 155	53.47 158	56.59 145	80.41 90	78.43 110	86.11 117	80.52 132

Fast-Effi-MVS+		73.11 79	73.66 84	72.48 76	77.72 102	80.88 93	78.55 82	58.83 150	65.19 85	60.36 82	59.98 101	62.42 111	71.22 62	81.66 69	80.61 83	88.20 65	84.88 94

UniMVSNet_NR-MVSNet		70.59 96	72.19 95	68.72 105	77.72 102	80.72 94	73.81 131	69.65 45	61.99 111	43.23 167	60.54 97	57.50 130	58.57 129	79.56 105	81.07 68	89.34 48	83.97 101

IterMVS-LS		71.69 87	72.82 92	70.37 89	77.54 104	76.34 140	75.13 110	60.46 130	61.53 116	57.57 95	64.89 81	67.33 96	66.04 90	77.09 133	77.37 127	85.48 134	85.18 88
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NR-MVSNet		68.79 117	70.56 105	66.71 136	77.48 105	79.54 103	73.52 135	69.20 50	61.20 119	39.76 174	58.52 108	50.11 181	51.37 168	80.26 97	80.71 78	88.97 55	83.59 107

TransMVSNet (Re)		64.74 150	65.66 153	63.66 152	77.40 106	75.33 149	69.86 149	62.67 106	47.63 188	41.21 173	50.01 168	52.33 168	45.31 178	79.57 104	77.69 120	85.49 133	77.07 156

TranMVSNet+NR-MVSNet		69.25 112	70.81 104	67.43 120	77.23 107	79.46 105	73.48 136	69.66 44	60.43 124	39.56 175	58.82 107	53.48 157	55.74 153	79.59 103	81.21 66	88.89 57	82.70 111

CANet_DTU		73.29 78	76.96 73	69.00 104	77.04 108	82.06 80	79.49 73	56.30 160	67.85 74	53.29 120	71.12 54	70.37 79	61.81 115	81.59 71	80.96 70	86.09 118	84.73 95

CHOSEN 1792x2688		69.20 113	69.26 120	69.13 101	76.86 109	78.93 109	77.27 95	60.12 135	61.86 113	54.42 109	42.54 186	61.61 112	66.91 82	78.55 118	78.14 114	79.23 168	83.23 110

HyFIR lowres test		69.47 110	68.94 124	70.09 92	76.77 110	82.93 76	76.63 101	60.17 133	59.00 130	54.03 113	40.54 191	65.23 102	67.89 76	76.54 140	78.30 112	85.03 141	80.07 136

UniMVSNet (Re)		69.53 108	71.90 98	66.76 134	76.42 111	80.93 90	72.59 141	68.03 57	61.75 114	41.68 172	58.34 114	57.23 132	53.27 164	79.53 106	80.62 82	88.57 62	84.90 93

gm-plane-assit		57.00 185	57.62 192	56.28 182	76.10 112	62.43 198	47.62 205	46.57 196	33.84 205	23.24 198	37.52 192	40.19 202	59.61 127	79.81 101	77.55 123	84.55 146	72.03 178

DU-MVS		69.63 107	70.91 103	68.13 111	75.99 113	79.54 103	73.81 131	69.20 50	61.20 119	43.23 167	58.52 108	53.50 155	58.57 129	79.22 109	80.45 84	87.97 71	83.97 101

Baseline_NR-MVSNet		67.53 135	68.77 127	66.09 138	75.99 113	74.75 154	72.43 142	68.41 53	61.33 118	38.33 178	51.31 163	54.13 150	56.03 149	79.22 109	78.19 113	85.37 136	82.45 113

CostFormer		68.92 115	69.58 116	68.15 110	75.98 115	76.17 142	78.22 87	51.86 176	65.80 82	61.56 80	63.57 87	62.83 109	61.85 113	70.40 180	68.67 177	79.42 166	79.62 140

tfpnnormal		64.27 153	63.64 169	65.02 142	75.84 116	75.61 146	71.24 147	62.52 108	47.79 187	42.97 169	42.65 185	44.49 195	52.66 166	78.77 115	76.86 133	84.88 144	79.29 141

baseline2		69.69 106	70.27 108	69.01 103	75.72 117	77.13 133	73.82 130	58.94 148	61.35 117	57.09 98	61.68 91	57.17 133	61.99 110	78.10 122	76.58 138	86.48 112	79.85 137

diffmvs		74.86 72	77.37 69	71.93 77	75.62 118	80.35 98	79.42 74	60.15 134	72.81 64	64.63 72	71.51 52	73.11 65	66.53 87	79.02 112	77.98 115	85.25 138	86.83 71

tpm cat1		65.41 145	63.81 168	67.28 125	75.61 119	72.88 160	75.32 104	52.85 170	62.97 104	63.66 75	53.24 146	53.29 163	61.83 114	65.54 191	64.14 193	74.43 188	74.60 170

CDS-MVSNet		67.65 132	69.83 113	65.09 141	75.39 120	76.55 138	74.42 119	63.75 86	53.55 167	49.37 141	59.41 104	62.45 110	44.44 179	79.71 102	79.82 91	83.17 154	77.36 153
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+-dtu		68.34 120	69.47 117	67.01 130	75.15 121	77.97 125	77.12 96	55.40 162	57.87 133	46.68 155	56.17 124	60.39 115	62.36 104	76.32 141	76.25 142	85.35 137	81.34 125

WR-MVS		63.03 157	67.40 142	57.92 176	75.14 122	77.60 130	60.56 189	66.10 68	54.11 166	23.88 196	53.94 139	53.58 153	34.50 193	73.93 153	77.71 119	87.35 85	80.94 128

test-LLR		64.42 151	64.36 164	64.49 146	75.02 123	63.93 189	66.61 168	61.96 115	54.41 162	47.77 148	57.46 118	60.25 116	55.20 157	70.80 174	69.33 172	80.40 164	74.38 172

test0.0.03 1		58.80 181	61.58 182	55.56 184	75.02 123	68.45 177	59.58 193	61.96 115	52.74 169	29.57 189	49.75 171	54.56 146	31.46 196	71.19 169	69.77 170	75.75 181	64.57 192

v1144		69.93 105	69.36 119	70.61 86	74.89 125	80.93 90	79.11 77	60.64 126	55.97 151	55.31 107	53.85 140	54.14 148	66.54 86	78.10 122	77.44 125	87.14 90	85.09 89

v10		70.22 101	69.76 114	70.74 82	74.79 126	80.30 100	79.22 76	59.81 138	57.71 138	56.58 102	54.22 138	55.31 141	66.95 80	78.28 120	77.47 124	87.12 93	85.07 90

v8		70.23 100	69.86 112	70.67 85	74.69 127	79.82 102	78.79 80	59.18 143	58.80 131	58.20 93	55.00 130	57.33 131	66.31 89	77.51 127	76.71 136	86.82 99	83.88 104

v2v482		70.05 104	69.46 118	70.74 82	74.62 128	80.32 99	79.00 78	60.62 127	57.41 140	56.89 99	55.43 129	55.14 143	66.39 88	77.25 130	77.14 130	86.90 96	83.57 108

v1192		69.50 109	68.83 125	70.29 90	74.49 129	80.92 92	78.55 82	60.54 128	55.04 157	54.21 110	52.79 154	52.33 168	66.92 81	77.88 124	77.35 128	87.04 94	85.51 81

UniMVSNet_ETH3D		67.18 139	67.03 144	67.36 122	74.44 130	78.12 118	74.07 126	66.38 65	52.22 173	46.87 152	48.64 172	51.84 172	56.96 142	77.29 129	78.53 108	85.42 135	82.59 112

DTE-MVSNet		61.85 170	64.96 161	58.22 175	74.32 131	74.39 156	61.01 188	67.85 59	51.76 178	21.91 203	53.28 144	48.17 185	37.74 190	72.22 162	76.44 139	86.52 111	78.49 146

Vis-MVSNet		72.77 81	77.20 71	67.59 119	74.19 132	84.01 63	76.61 102	61.69 119	60.62 123	50.61 135	70.25 58	71.31 72	55.57 155	83.85 53	82.28 56	86.90 96	88.08 59
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v144192		69.34 111	68.68 129	70.12 91	74.06 133	80.54 95	78.08 88	60.54 128	54.99 159	54.13 112	52.92 152	52.80 166	66.73 84	77.13 132	76.72 135	87.15 87	85.63 79

v1921920		69.03 114	68.32 133	69.86 94	74.03 134	80.37 97	77.55 90	60.25 132	54.62 161	53.59 118	52.36 158	51.50 174	66.75 83	77.17 131	76.69 137	86.96 95	85.56 80

PEN-MVS		62.96 158	65.77 152	59.70 169	73.98 135	75.45 147	63.39 182	67.61 60	52.49 171	25.49 195	53.39 142	49.12 184	40.85 187	71.94 165	77.26 129	86.86 98	80.72 130

v1240		68.64 119	67.89 138	69.51 99	73.89 136	80.26 101	76.73 100	59.97 137	53.43 168	53.08 121	51.82 161	50.84 177	66.62 85	76.79 136	76.77 134	86.78 101	85.34 85

thisisatest0530		71.48 89	73.01 89	69.70 97	73.83 137	78.62 115	74.53 115	59.12 144	64.13 94	58.63 89	64.60 84	58.63 125	64.27 94	80.28 96	80.17 89	87.82 77	84.64 97

GA-MVS		68.14 121	69.17 122	66.93 132	73.77 138	78.50 117	74.45 116	58.28 152	55.11 156	48.44 144	60.08 99	53.99 151	61.50 117	78.43 119	77.57 122	85.13 139	80.54 131

tttt0517		71.41 90	72.95 90	69.60 98	73.70 139	78.70 114	74.42 119	59.12 144	63.89 98	58.35 92	64.56 85	58.39 127	64.27 94	80.29 95	80.17 89	87.74 79	84.69 96

pm-mvs1		65.62 144	67.42 141	63.53 153	73.66 140	76.39 139	69.66 150	60.87 125	49.73 183	43.97 166	51.24 164	57.00 135	48.16 173	79.89 100	77.84 117	84.85 145	79.82 138

dps		64.00 155	62.99 171	65.18 140	73.29 141	72.07 163	68.98 155	53.07 169	57.74 137	58.41 91	55.55 127	47.74 188	60.89 123	69.53 183	67.14 186	76.44 180	71.19 180

v148		67.85 127	67.53 139	68.23 109	73.25 142	77.57 131	74.26 123	57.36 157	55.70 152	57.45 97	53.53 141	55.42 140	61.96 111	75.23 145	73.92 154	85.08 140	81.32 126

PatchMatch-RL		67.78 129	66.65 148	69.10 102	73.01 143	72.69 161	68.49 156	61.85 117	62.93 105	60.20 84	56.83 122	50.42 179	69.52 68	75.62 143	74.46 153	81.51 158	73.62 176

GBi-Net		70.78 93	73.37 87	67.76 112	72.95 144	78.00 120	75.15 107	62.72 100	64.13 94	51.44 128	58.37 111	69.02 87	57.59 136	81.33 77	80.72 74	86.70 103	82.02 115

test1		70.78 93	73.37 87	67.76 112	72.95 144	78.00 120	75.15 107	62.72 100	64.13 94	51.44 128	58.37 111	69.02 87	57.59 136	81.33 77	80.72 74	86.70 103	82.02 115

FMVSNet2		70.39 99	72.67 93	67.72 115	72.95 144	78.00 120	75.15 107	62.69 104	63.29 102	51.25 132	55.64 125	68.49 93	57.59 136	80.91 87	80.35 86	86.70 103	82.02 115

FMVSNet3		70.49 97	72.90 91	67.67 117	72.88 147	77.98 123	74.96 113	62.72 100	64.13 94	51.44 128	58.37 111	69.02 87	57.43 139	79.43 107	79.57 96	86.59 109	81.81 122

LTVRE_ROB	59.44 16	61.82 173	62.64 175	60.87 163	72.83 148	77.19 132	64.37 178	58.97 146	33.56 206	28.00 192	52.59 157	42.21 198	63.93 97	74.52 149	76.28 140	77.15 175	82.13 114
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		67.05 140	66.94 145	67.17 126	72.35 149	78.97 108	73.26 139	58.88 149	51.16 179	50.90 133	48.21 174	50.11 181	60.96 120	77.70 125	77.38 126	86.68 106	85.05 91

tpm		62.41 164	63.15 170	61.55 160	72.24 150	63.79 191	71.31 146	46.12 198	57.82 134	55.33 106	59.90 102	54.74 145	53.63 162	67.24 190	64.29 192	70.65 198	74.25 174

test20.03		53.93 192	56.28 193	51.19 192	72.19 151	65.83 184	53.20 199	61.08 122	42.74 196	22.08 201	37.07 194	45.76 193	24.29 204	70.44 178	69.04 174	74.31 189	63.05 196

CP-MVSNet		62.68 160	65.49 155	59.40 172	71.84 152	75.34 148	62.87 184	67.04 63	52.64 170	27.19 193	53.38 143	48.15 186	41.40 185	71.26 168	75.68 144	86.07 119	82.00 118

PS-CasMVS		62.38 166	65.06 158	59.25 173	71.73 153	75.21 152	62.77 185	66.99 64	51.94 177	26.96 194	52.00 160	47.52 189	41.06 186	71.16 171	75.60 145	85.97 126	81.97 120

WR-MVS_H		61.83 172	65.87 151	57.12 179	71.72 154	76.87 134	61.45 187	66.19 66	51.97 176	22.92 200	53.13 149	52.30 170	33.80 194	71.03 172	75.00 149	86.65 107	80.78 129

USDC		67.36 137	67.90 137	66.74 135	71.72 154	75.23 151	71.58 144	60.28 131	67.45 75	50.54 136	60.93 93	45.20 194	62.08 107	76.56 139	74.50 152	84.25 147	75.38 167

UGNet		72.78 80	77.67 64	67.07 129	71.65 156	83.24 73	75.20 106	63.62 87	64.93 87	56.72 100	71.82 50	73.30 62	49.02 172	81.02 85	80.70 79	86.22 115	88.67 56
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	62.35 179	61.58 159	71.62 157	64.14 188	69.07 154	48.22 194	62.21 110	53.93 114	58.26 115	55.30 142	55.81 152	63.22 195	62.62 195	70.85 197	70.70 181

pmmvs4		67.89 126	67.39 143	68.48 108	71.60 158	73.57 158	74.45 116	60.98 123	64.65 89	57.97 94	54.95 131	51.73 173	61.88 112	73.78 154	75.11 148	83.99 150	77.91 149

testgi		54.39 191	57.86 190	50.35 193	71.59 159	67.24 180	54.95 197	53.25 167	43.36 195	23.78 197	44.64 181	47.87 187	24.96 201	70.45 177	68.66 178	73.60 191	62.78 197

pmmvs6		62.41 164	62.88 172	61.87 158	71.38 160	75.18 153	67.76 159	59.45 142	41.64 198	42.52 171	37.33 193	52.91 164	46.87 175	77.67 126	76.26 141	83.23 153	79.18 143

FMVSNet1		68.84 116	70.47 107	66.94 131	71.35 161	77.68 128	74.71 114	62.35 112	56.93 142	49.94 138	50.01 168	64.59 103	57.07 141	81.33 77	80.72 74	86.25 114	82.00 118

IterMVS-SCA-FT		66.89 141	69.22 121	64.17 147	71.30 162	75.64 145	71.33 145	53.17 168	57.63 139	49.08 142	60.72 95	60.05 119	63.09 100	74.99 147	73.92 154	77.07 176	81.57 124

PatchmatchNet		64.21 154	64.65 162	63.69 151	71.29 163	68.66 175	69.63 151	51.70 178	63.04 103	53.77 116	59.83 103	58.34 128	60.23 126	68.54 187	66.06 189	75.56 183	68.08 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
baseline		70.45 98	74.09 83	66.20 137	70.95 164	75.67 144	74.26 123	53.57 164	68.33 73	58.42 90	69.87 59	71.45 69	61.55 116	74.84 148	74.76 151	78.42 170	83.72 106

SCA		65.40 146	66.58 149	64.02 149	70.65 165	73.37 159	67.35 160	53.46 166	63.66 99	54.14 111	60.84 94	60.20 118	61.50 117	69.96 181	68.14 182	77.01 177	69.91 182

CR-MVSNet		64.83 149	65.54 154	64.01 150	70.64 166	69.41 171	65.97 171	52.74 171	57.81 135	52.65 123	54.27 134	56.31 137	60.92 121	72.20 163	73.09 159	81.12 161	75.69 164

MVSTER		72.06 84	74.24 81	69.51 99	70.39 167	75.97 143	76.91 98	57.36 157	64.64 90	61.39 81	68.86 63	63.76 106	63.46 98	81.44 74	79.70 92	87.56 82	85.31 86

Anonymous20231206		56.36 187	57.80 191	54.67 187	70.08 168	66.39 183	60.46 190	57.54 154	49.50 185	29.30 190	33.86 198	46.64 190	35.18 192	70.44 178	68.88 176	75.47 184	68.88 187

thisisatest0515		67.40 136	68.78 126	65.80 139	70.02 169	75.24 150	69.36 153	57.37 156	54.94 160	53.67 117	55.53 128	54.85 144	58.00 134	78.19 121	78.91 105	86.39 113	83.78 105

CMPMVS	47.78 17	62.49 163	62.52 176	62.46 156	70.01 170	70.66 169	62.97 183	51.84 177	51.98 175	56.71 101	42.87 184	53.62 152	57.80 135	72.23 161	70.37 169	75.45 185	75.91 161
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TDRefinement		66.09 143	65.03 160	67.31 123	69.73 171	76.75 136	75.33 103	64.55 81	60.28 125	49.72 140	45.63 180	42.83 197	60.46 125	75.75 142	75.95 143	84.08 148	78.04 148

TinyColmap		62.84 159	61.03 184	64.96 143	69.61 172	71.69 164	68.48 157	59.76 139	55.41 153	47.69 150	47.33 176	34.20 205	62.76 103	74.52 149	72.59 162	81.44 159	71.47 179

RPMNet		61.71 174	62.88 172	60.34 165	69.51 173	69.41 171	63.48 181	49.23 186	57.81 135	45.64 161	50.51 166	50.12 180	53.13 165	68.17 189	68.49 180	81.07 162	75.62 166

IterMVS		66.36 142	68.30 134	64.10 148	69.48 174	74.61 155	73.41 137	50.79 182	57.30 141	48.28 146	60.64 96	59.92 120	60.85 124	74.14 152	72.66 161	81.80 157	78.82 145
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SixPastTwentyTwo		61.84 171	62.45 177	61.12 162	69.20 175	72.20 162	62.03 186	57.40 155	46.54 191	38.03 180	57.14 121	41.72 199	58.12 133	69.67 182	71.58 165	81.94 156	78.30 147

MDTV_nov1_ep13		64.37 152	65.24 156	63.37 155	68.94 176	70.81 167	72.40 143	50.29 185	60.10 126	53.91 115	60.07 100	59.15 123	57.21 140	69.43 184	67.30 184	77.47 173	69.78 184

EPMVS		60.00 179	61.97 180	57.71 177	68.46 177	63.17 195	64.54 177	48.23 193	63.30 101	44.72 164	60.19 98	56.05 139	50.85 169	65.27 193	62.02 196	69.44 200	63.81 194

our_test_3					67.93 178	70.99 166	66.89 164

FC-MVSNet-test		56.90 186	65.20 157	47.21 196	66.98 179	63.20 194	49.11 204	58.60 151	59.38 129	11.50 209	65.60 77	56.68 136	24.66 203	71.17 170	71.36 167	72.38 194	69.02 186

CVMVSNet		62.55 161	65.89 150	58.64 174	66.95 180	69.15 173	66.49 170	56.29 161	52.46 172	32.70 186	59.27 105	58.21 129	50.09 170	71.77 166	71.39 166	79.31 167	78.99 144

FPMVS		51.87 194	50.00 199	54.07 188	66.83 181	57.25 201	60.25 191	50.91 180	50.25 181	34.36 184	36.04 196	32.02 207	41.49 184	58.98 201	56.07 200	70.56 199	59.36 202

pmmvs-eth3d		63.52 156	62.44 178	64.77 144	66.82 182	70.12 170	69.41 152	59.48 141	54.34 165	52.71 122	46.24 179	44.35 196	56.93 143	72.37 158	73.77 156	83.30 152	75.91 161

TAMVS		59.58 180	62.81 174	55.81 183	66.03 183	65.64 186	63.86 180	48.74 189	49.95 182	37.07 182	54.77 132	58.54 126	44.44 179	72.29 160	71.79 163	74.70 187	66.66 190

MDTV_nov1_ep13_2view		60.16 178	60.51 186	59.75 168	65.39 184	69.05 174	68.00 158	48.29 192	51.99 174	45.95 159	48.01 175	49.64 183	53.39 163	68.83 186	66.52 188	77.47 173	69.55 185

pmmvs5		62.37 167	64.04 166	60.42 164	65.03 185	71.67 165	67.17 162	52.70 173	50.30 180	44.80 163	54.23 137	51.19 176	49.37 171	72.88 157	73.48 158	83.45 151	74.55 171

ambc			53.42 194		64.99 186	63.36 193	49.96 202		47.07 189	37.12 181	28.97 202	16.36 213	41.82 183	75.10 146	67.34 183	71.55 196	75.72 163

V42		68.76 118	69.63 115	67.74 114	64.93 187	78.01 119	78.30 86	56.48 159	58.65 132	56.30 103	54.26 136	57.03 134	64.85 92	77.47 128	77.01 132	85.60 132	84.96 92

PMVS	39.38 18	46.06 200	43.30 202	49.28 195	62.93 188	38.75 208	41.88 207	53.50 165	33.33 207	35.46 183	28.90 203	31.01 208	33.04 195	58.61 202	54.63 203	68.86 201	57.88 203
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new-patchmatchnet		46.97 198	49.47 200	44.05 200	62.82 189	56.55 202	45.35 206	52.01 175	42.47 197	17.04 207	35.73 197	35.21 204	21.84 207	61.27 198	54.83 202	65.26 203	60.26 199

ET-MVSNet_ETH3D		72.46 83	74.19 82	70.44 88	62.50 190	81.17 88	79.90 69	62.46 111	64.52 92	57.52 96	71.49 53	59.15 123	72.08 52	78.61 117	81.11 67	88.16 66	83.29 109

ADS-MVSNet		55.94 188	58.01 189	53.54 191	62.48 191	58.48 200	59.12 194	46.20 197	59.65 128	42.88 170	52.34 159	53.31 162	46.31 176	62.00 197	60.02 198	64.23 204	60.24 201

RPSCF		67.64 133	71.25 101	63.43 154	61.86 192	70.73 168	67.26 161	50.86 181	74.20 59	58.91 86	67.49 72	69.33 84	64.10 96	71.41 167	68.45 181	77.61 172	77.17 154

MIMVSNet		58.52 183	61.34 183	55.22 185	60.76 193	67.01 181	66.81 165	49.02 188	56.43 146	38.90 177	40.59 190	54.54 147	40.57 188	73.16 156	71.65 164	75.30 186	66.00 191

PatchT		61.97 169	64.04 166	59.55 171	60.49 194	67.40 179	56.54 195	48.65 190	56.69 143	52.65 123	51.10 165	52.14 171	60.92 121	72.20 163	73.09 159	78.03 171	75.69 164

N_pmnet		47.35 197	50.13 198	44.11 199	59.98 195	51.64 205	51.86 200	44.80 199	49.58 184	20.76 204	40.65 189	40.05 203	29.64 197	59.84 199	55.15 201	57.63 205	54.00 204

MVS-HIRNet		54.41 190	52.10 197	57.11 180	58.99 196	56.10 203	49.68 203	49.10 187	46.18 192	52.15 127	33.18 199	46.11 192	56.10 148	63.19 196	59.70 199	76.64 179	60.25 200

PM-MVS		60.48 177	60.94 185	59.94 167	58.85 197	66.83 182	64.27 179	51.39 179	55.03 158	48.03 147	50.00 170	40.79 201	58.26 132	69.20 185	67.13 187	78.84 169	77.60 151

anonymousdsp		65.28 147	67.98 136	62.13 157	58.73 198	73.98 157	67.10 163	50.69 183	48.41 186	47.66 151	54.27 134	52.75 167	61.45 119	76.71 138	80.20 87	87.13 91	89.53 52

TESTMET0.1,1		61.10 175	64.36 164	57.29 178	57.53 199	63.93 189	66.61 168	36.22 204	54.41 162	47.77 148	57.46 118	60.25 116	55.20 157	70.80 174	69.33 172	80.40 164	74.38 172

EU-MVSNet		54.63 189	58.69 188	49.90 194	56.99 200	62.70 197	56.41 196	50.64 184	45.95 193	23.14 199	50.42 167	46.51 191	36.63 191	65.51 192	64.85 191	75.57 182	74.91 169

FMVSNet5		57.24 184	60.02 187	53.99 189	56.45 201	62.74 196	65.27 174	47.03 195	55.14 155	39.55 176	40.88 188	53.42 160	41.83 182	72.35 159	71.10 168	73.79 190	64.50 193

test-mter		60.84 176	64.62 163	56.42 181	55.99 202	64.18 187	65.39 173	34.23 205	54.39 164	46.21 157	57.40 120	59.49 122	55.86 151	71.02 173	69.65 171	80.87 163	76.20 160

CHOSEN 280x420		58.70 182	61.88 181	54.98 186	55.45 203	50.55 206	64.92 175	40.36 201	55.21 154	38.13 179	48.31 173	63.76 106	63.03 102	73.73 155	68.58 179	68.00 202	73.04 177

PMMVS		65.06 148	69.17 122	60.26 166	55.25 204	63.43 192	66.71 167	43.01 200	62.41 108	50.64 134	69.44 60	67.04 97	63.29 99	74.36 151	73.54 157	82.68 155	73.99 175

Gipuma		36.38 202	35.80 204	37.07 201	45.76 205	33.90 209	29.81 209	48.47 191	39.91 201	18.02 206	8.00 211	8.14 215	25.14 200	59.29 200	61.02 197	55.19 207	40.31 206
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs3		47.65 196	49.08 201	45.99 197	44.61 206	54.79 204	50.04 201	31.95 208	33.91 204	29.90 188	30.37 200	33.53 206	46.31 176	63.50 194	63.67 194	73.14 193	63.77 195

MIMVSNet1		49.27 195	53.25 195	44.62 198	44.61 206	61.52 199	53.61 198	52.18 174	41.62 199	18.68 205	28.14 204	41.58 200	25.50 199	68.46 188	69.04 174	73.15 192	62.37 198

MDA-MVSNet-bldmvs		53.37 193	53.01 196	53.79 190	43.67 208	67.95 178	59.69 192	57.92 153	43.69 194	32.41 187	41.47 187	27.89 210	52.38 167	56.97 203	65.99 190	76.68 178	67.13 189

E-PMN		21.77 204	18.24 207	25.89 203	40.22 209	19.58 212	12.46 213	39.87 202	18.68 211	6.71 211	9.57 208	4.31 218	22.36 206	19.89 209	27.28 208	33.73 209	28.34 210

EMVS		20.98 205	17.15 208	25.44 204	39.51 210	19.37 213	12.66 212	39.59 203	19.10 210	6.62 212	9.27 209	4.40 217	22.43 205	17.99 210	24.40 209	31.81 210	25.53 211

new_pmnet		38.40 201	42.64 203	33.44 202	37.54 211	45.00 207	36.60 208	32.72 207	40.27 200	12.72 208	29.89 201	28.90 209	24.78 202	53.17 204	52.90 204	56.31 206	48.34 205

PMMVS2		25.60 203	29.75 205	20.76 206	28.00 212	30.93 210	23.10 210	29.18 209	23.14 209	1.46 214	18.23 207	16.54 212	5.08 209	40.22 205	41.40 206	37.76 208	37.79 208

tmp_tt				14.50 208	14.68 213	7.17 215	10.46 215	2.21 211	37.73 203	28.71 191	25.26 205	16.98 211	4.37 210	31.49 206	29.77 207	26.56 211

MVE	19.12 19	20.47 206	23.27 206	17.20 207	12.66 214	25.41 211	10.52 214	34.14 206	14.79 212	6.53 213	8.79 210	4.68 216	16.64 208	29.49 207	41.63 205	22.73 212	38.11 207
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GG-mvs-BLEND		46.86 199	67.51 140	22.75 205	0.05 215	76.21 141	64.69 176	0.04 212	61.90 112	0.09 215	55.57 126	71.32 71	0.08 211	70.54 176	67.19 185	71.58 195	69.86 183

testmvs		0.09 207	0.15 209	0.02 209	0.01 216	0.02 216	0.05 217	0.01 213	0.11 213	0.01 216	0.26 213	0.01 219	0.06 213	0.10 211	0.10 210	0.01 214	0.43 213

uanet_test		0.00 209	0.00 211	0.00 211	0.00 217	0.00 218	0.00 219	0.00 215	0.00 215	0.00 217	0.00 214	0.00 220	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet-low-res		0.00 209	0.00 211	0.00 211	0.00 217	0.00 218	0.00 219	0.00 215	0.00 215	0.00 217	0.00 214	0.00 220	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

sosnet		0.00 209	0.00 211	0.00 211	0.00 217	0.00 218	0.00 219	0.00 215	0.00 215	0.00 217	0.00 214	0.00 220	0.00 214	0.00 213	0.00 212	0.00 216	0.00 214

test123		0.09 207	0.14 210	0.02 209	0.00 217	0.02 216	0.02 218	0.01 213	0.09 214	0.00 217	0.30 212	0.00 220	0.08 211	0.03 212	0.09 211	0.01 214	0.45 212

9.14												86.88 14

test_part1																	95.35 3

MTAPA										83.48 1		86.45 17

MTMP										82.66 4		84.91 25

Patchmatch-RL test							2.85 216

NP-MVS									80.10 45

Patchmtry						65.80 185	65.97 171	52.74 171		52.65 123

DeepMVS_CX						18.74 214	18.55 211	8.02 210	26.96 208	7.33 210	23.81 206	13.05 214	25.99 198	25.17 208		22.45 213	36.25 209

High-resolution multi-view benchmark