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.

TDRefinement		93.16 1	95.57 1	90.36 1	88.79 52	93.57 1	97.27 1	78.23 22	95.55 1	93.00 1	93.98 15	96.01 37	87.53 1	97.69 1	96.81 1	97.33 1	95.34 3

XVS					91.28 25	91.23 8	96.89 2			87.14 26		94.53 69				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 26		94.53 69				95.84 15

X-MVS		89.36 28	90.73 43	87.77 17	91.50 20	91.23 8	96.76 4	78.88 18	87.29 51	87.14 26	78.98 135	94.53 69	76.47 52	95.25 19	94.28 12	95.85 14	93.55 15

ACMMPR		91.30 4	92.88 10	89.46 4	91.92 11	91.61 5	96.60 5	79.46 14	90.08 29	88.53 14	89.54 61	95.57 46	84.25 7	95.24 20	94.27 13	95.97 11	93.85 7

MP-MVS		90.84 6	91.95 32	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 56	88.75 13	89.00 69	94.38 74	84.01 9	94.94 25	94.34 11	95.45 24	93.24 22
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PGM-MVS		90.42 10	91.58 35	89.05 6	91.77 14	91.06 13	96.51 7	78.94 17	85.41 68	87.67 19	87.02 89	95.26 53	83.62 12	95.01 24	93.94 16	95.79 19	93.40 20

SteuartSystems-ACMMP		90.00 17	91.73 33	87.97 13	91.21 29	90.29 28	96.51 7	78.00 24	86.33 59	85.32 40	88.23 77	94.67 67	82.08 21	95.13 22	93.88 17	94.72 35	93.59 12
Skip Steuart: Steuart Systems R&D Blog.
ACMMP		90.63 8	92.40 19	88.56 9	91.24 28	91.60 6	96.49 9	77.53 27	87.89 45	86.87 30	87.24 87	96.46 24	82.87 16	95.59 15	94.50 9	96.35 6	93.51 17
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CP-MVS		91.09 5	92.33 23	89.65 2	92.16 10	90.41 27	96.46 10	80.38 8	88.26 42	89.17 11	87.00 90	96.34 29	83.95 10	95.77 11	94.72 8	95.81 17	93.78 9

zzz-MVS		90.38 11	91.35 39	89.25 5	93.08 3	86.59 60	96.45 11	79.00 16	90.23 26	89.30 10	85.87 101	94.97 62	82.54 18	95.05 23	94.83 7	95.14 27	91.94 34

ACMM	80.67 7	90.67 7	92.46 18	88.57 8	91.35 22	89.93 31	96.34 12	77.36 31	90.17 27	86.88 29	87.32 85	96.63 22	83.32 13	95.79 10	94.49 10	96.19 9	92.91 25
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
anonymousdsp		85.62 57	90.53 44	79.88 87	64.64 198	76.35 134	96.28 13	53.53 184	85.63 65	81.59 67	92.81 28	97.71 12	86.88 2	94.56 26	92.83 25	96.35 6	93.84 8

TSAR-MVS + MP.		89.67 24	92.25 26	86.65 26	91.53 18	90.98 17	96.15 14	73.30 55	87.88 46	81.83 64	92.92 27	95.15 57	82.23 19	93.58 35	92.25 34	94.87 30	93.01 24
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APDe-MVS		89.85 20	92.91 9	86.29 27	90.47 38	91.34 7	96.04 15	76.41 40	91.11 16	78.50 84	93.44 19	95.82 41	81.55 24	93.16 38	91.90 39	94.77 33	93.58 14

ACMMP_NAP		89.86 19	91.96 31	87.42 20	91.00 30	90.08 29	96.00 16	76.61 37	89.28 33	87.73 18	90.04 55	91.80 106	78.71 38	94.36 29	93.82 18	94.48 37	94.32 5

CPTT-MVS		89.63 25	90.52 45	88.59 7	90.95 31	90.74 21	95.71 17	79.13 15	87.70 47	85.68 38	80.05 130	95.74 44	84.77 6	94.28 30	92.68 27	95.28 26	92.45 29

HFP-MVS		90.32 13	92.37 21	87.94 14	91.46 21	90.91 18	95.69 18	79.49 12	89.94 32	83.50 50	89.06 68	94.44 72	81.68 23	94.17 31	94.19 14	95.81 17	93.87 6

DPE-MVS		89.81 22	92.34 22	86.86 24	89.69 44	91.00 16	95.53 19	76.91 34	88.18 43	83.43 53	93.48 18	95.19 54	81.07 27	92.75 44	92.07 37	94.55 36	93.74 10

COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 51	92.86 2	95.51 20	72.17 58	94.95 4	91.27 3	94.11 14	97.77 11	84.22 8	96.49 4	95.27 5	96.79 2	93.60 11
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
APD-MVS		89.14 29	91.25 41	86.67 25	91.73 15	91.02 15	95.50 21	77.74 25	84.04 79	79.47 79	91.48 42	94.85 64	81.14 26	92.94 41	92.20 36	94.47 38	92.24 30
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
LGP-MVS_train		90.56 9	92.38 20	88.43 10	90.88 32	91.15 11	95.35 22	77.65 26	86.26 61	87.23 24	90.45 52	97.35 16	83.20 14	95.44 16	93.41 21	96.28 8	92.63 26

MSP-MVS		88.51 41	91.36 38	85.19 39	90.63 36	92.01 4	95.29 23	77.52 28	90.48 24	80.21 75	90.21 54	96.08 33	76.38 54	88.30 89	91.42 42	91.12 83	91.01 43

SMA-MVS		90.13 15	92.26 25	87.64 18	91.68 16	90.44 26	95.22 24	77.34 33	90.79 21	87.80 17	90.42 53	92.05 103	79.05 35	93.89 33	93.59 19	94.77 33	94.62 4

HPM-MVS++		88.74 39	89.54 50	87.80 16	92.58 7	85.69 68	95.10 25	78.01 23	87.08 53	87.66 20	87.89 80	92.07 101	80.28 30	90.97 66	91.41 44	93.17 52	91.69 36

OPM-MVS		89.82 21	92.24 27	86.99 23	90.86 33	89.35 36	95.07 26	75.91 42	91.16 15	86.87 30	91.07 48	97.29 17	79.13 34	93.32 36	91.99 38	94.12 40	91.49 39

ACMP	80.00 8	90.12 16	92.30 24	87.58 19	90.83 34	91.10 12	94.96 27	76.06 41	87.47 49	85.33 39	88.91 72	97.65 14	82.13 20	95.31 17	93.44 20	96.14 10	92.22 31
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		89.02 33	91.44 37	86.20 28	94.88 1	89.84 33	94.76 28	77.45 29	85.41 68	74.79 98	88.83 73	88.90 128	78.67 40	96.06 7	95.45 4	96.66 3	95.58 1

DeepC-MVS	83.59 4	90.37 12	92.56 17	87.82 15	91.26 27	92.33 3	94.72 29	80.04 9	90.01 30	84.61 42	93.33 20	94.22 75	80.59 28	92.90 42	92.52 29	95.69 21	92.57 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
train_agg		86.67 51	87.73 67	85.43 35	91.51 19	82.72 85	94.47 30	74.22 52	81.71 94	81.54 68	89.20 67	92.87 90	78.33 42	90.12 72	88.47 66	92.51 65	89.04 58

SD-MVS		89.91 18	92.23 28	87.19 22	91.31 24	89.79 34	94.31 31	75.34 46	89.26 34	81.79 65	92.68 29	95.08 59	83.88 11	93.10 39	92.69 26	96.54 4	93.02 23
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
3Dnovator+	83.71 3	88.13 43	90.00 48	85.94 29	86.82 68	91.06 13	94.26 32	75.39 45	88.85 38	85.76 37	85.74 103	86.92 137	78.02 43	93.03 40	92.21 35	95.39 25	92.21 32

DeepPCF-MVS	81.61 6	87.95 46	90.29 47	85.22 38	87.48 63	90.01 30	93.79 33	73.54 53	88.93 36	83.89 45	89.40 63	90.84 115	80.26 31	90.62 69	90.19 52	92.36 66	92.03 33

DVP-MVS		89.40 27	92.69 12	85.56 34	89.01 50	89.85 32	93.72 34	75.42 44	92.28 10	80.49 70	94.36 12	94.87 63	81.46 25	92.49 48	91.42 42	93.27 48	93.54 16

PMVS	79.51 9	90.23 14	92.67 13	87.39 21	90.16 39	88.75 40	93.64 35	75.78 43	90.00 31	83.70 47	92.97 26	92.22 98	86.13 4	97.01 3	96.79 2	94.94 29	90.96 44
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 105	86.35 63	93.60 36	78.79 19	95.48 3	91.79 2	93.08 24	97.21 19	86.34 3	97.06 2	96.27 3	95.46 23	95.56 2
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
WR-MVS		89.79 23	93.66 4	85.27 37	91.32 23	88.27 44	93.49 37	79.86 10	92.75 8	75.37 94	96.86 1	98.38 5	75.10 66	95.93 8	94.07 15	96.46 5	89.39 55

NCCC		86.74 50	87.97 66	85.31 36	90.64 35	87.25 55	93.27 38	74.59 48	86.50 57	83.72 46	75.92 160	92.39 96	77.08 50	91.72 51	90.68 47	92.57 63	91.30 41

CNVR-MVS		86.93 49	88.98 54	84.54 43	90.11 40	87.41 54	93.23 39	73.47 54	86.31 60	82.25 59	82.96 118	92.15 99	76.04 57	91.69 52	90.69 46	92.17 68	91.64 38

OMC-MVS		88.16 42	91.34 40	84.46 45	86.85 67	90.63 23	93.01 40	67.00 95	90.35 25	87.40 22	86.86 92	96.35 28	77.66 46	92.63 46	90.84 45	94.84 31	91.68 37

CDPH-MVS		86.66 52	88.52 57	84.48 44	89.61 45	88.27 44	92.86 41	72.69 57	80.55 112	82.71 55	86.92 91	93.32 86	75.55 62	91.00 65	89.85 54	93.47 45	89.71 52

DeepC-MVS_fast	81.78 5	87.38 47	89.64 49	84.75 40	89.89 42	90.70 22	92.74 42	74.45 49	86.02 62	82.16 62	86.05 99	91.99 105	75.84 60	91.16 60	90.44 48	93.41 46	91.09 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		89.02 33	91.69 34	85.91 30	89.72 43	90.81 20	92.56 43	71.69 60	90.83 20	87.24 23	89.71 59	92.07 101	78.37 41	94.43 28	92.59 28	95.86 13	91.35 40

ACMH+	79.05 11	89.62 26	93.08 7	85.58 32	88.58 54	89.26 37	92.18 44	74.23 51	93.55 7	82.66 56	92.32 34	98.35 7	80.29 29	95.28 18	92.34 32	95.52 22	90.43 47

WR-MVS_H		88.99 35	93.28 5	83.99 51	91.92 11	89.13 38	91.95 45	83.23 1	90.14 28	71.92 117	95.85 4	98.01 10	71.83 92	95.82 9	93.19 23	93.07 54	90.83 46

MVS_0304		84.73 68	86.19 79	83.02 55	88.32 55	86.71 59	91.55 46	70.87 64	73.79 139	82.88 54	85.13 107	93.35 85	72.55 85	88.62 83	87.69 72	91.93 71	88.05 67

ACMH	78.40 12	88.94 37	92.62 15	84.65 41	86.45 70	87.16 56	91.47 47	68.79 81	95.49 2	89.74 6	93.55 17	98.50 2	77.96 44	94.14 32	89.57 59	93.49 44	89.94 51
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		85.02 64	86.41 77	83.40 52	89.19 48	86.59 60	91.28 48	71.60 61	82.79 85	83.48 51	78.65 139	93.54 83	72.55 85	86.49 103	85.89 88	92.28 67	90.95 45

PCF-MVS	76.59 14	84.11 72	85.27 89	82.76 62	86.12 73	88.30 43	91.24 49	69.10 76	82.36 89	84.45 43	77.56 145	90.40 119	72.91 83	85.88 108	83.88 106	92.72 59	88.53 62
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + ACMM		89.14 29	92.11 30	85.67 31	89.27 47	90.61 24	90.98 50	79.48 13	88.86 37	79.80 76	93.01 25	93.53 84	83.17 15	92.75 44	92.45 30	91.32 78	93.59 12

DTE-MVSNet		88.99 35	92.77 11	84.59 42	93.31 2	88.10 47	90.96 51	83.09 2	91.38 13	76.21 89	96.03 2	98.04 8	70.78 101	95.65 14	92.32 33	93.18 51	87.84 68

CNLPA		85.50 59	88.58 55	81.91 66	84.55 87	87.52 53	90.89 52	63.56 131	88.18 43	84.06 44	83.85 115	91.34 112	76.46 53	91.27 57	89.00 64	91.96 70	88.88 60

PEN-MVS		88.86 38	92.92 8	84.11 50	92.92 5	88.05 49	90.83 53	82.67 5	91.04 17	74.83 97	95.97 3	98.47 3	70.38 102	95.70 13	92.43 31	93.05 55	88.78 61

PHI-MVS		86.37 54	88.14 63	84.30 46	86.65 69	87.56 52	90.76 54	70.16 67	82.55 86	89.65 7	84.89 110	92.40 95	75.97 58	90.88 67	89.70 56	92.58 61	89.03 59

TAPA-MVS	78.00 13	85.88 56	88.37 59	82.96 58	84.69 84	88.62 41	90.62 55	64.22 121	89.15 35	88.05 15	78.83 137	93.71 79	76.20 56	90.11 73	88.22 69	94.00 41	89.97 50
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Vis-MVSNet		83.32 79	88.12 64	77.71 102	77.91 148	83.44 82	90.58 56	69.49 72	81.11 106	67.10 145	89.85 57	91.48 110	71.71 93	91.34 56	89.37 60	89.48 99	90.26 48
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CSCG		88.12 44	91.45 36	84.23 47	88.12 59	90.59 25	90.57 57	68.60 83	91.37 14	83.45 52	89.94 56	95.14 58	78.71 38	91.45 55	88.21 70	95.96 12	93.44 19

AdaColmap		84.15 71	85.14 92	83.00 57	89.08 49	87.14 57	90.56 58	70.90 63	82.40 88	80.41 71	73.82 172	84.69 146	75.19 65	91.58 54	89.90 53	91.87 72	86.48 75

PS-CasMVS		89.07 32	93.23 6	84.21 48	92.44 8	88.23 46	90.54 59	82.95 3	90.50 23	75.31 95	95.80 5	98.37 6	71.16 95	96.30 5	93.32 22	92.88 56	90.11 49

SixPastTwentyTwo		89.14 29	92.19 29	85.58 32	84.62 85	82.56 88	90.53 60	71.93 59	91.95 11	85.89 35	94.22 13	97.25 18	85.42 5	95.73 12	91.71 41	95.08 28	91.89 35

MVS_111021_HR		83.95 73	86.10 81	81.44 71	84.62 85	80.29 103	90.51 61	68.05 89	84.07 78	80.38 73	84.74 111	91.37 111	74.23 72	90.37 71	87.25 74	90.86 85	84.59 87

TSAR-MVS + COLMAP		85.51 58	88.36 60	82.19 64	86.05 74	87.69 51	90.50 62	70.60 66	86.40 58	82.33 57	89.69 60	92.52 94	74.01 76	87.53 93	86.84 79	89.63 96	87.80 69

abl_6				79.30 92	84.98 83	85.78 66	90.50 62	66.88 96	77.08 128	74.02 103	73.29 176	89.34 123	68.94 110			90.49 86	85.98 78

CP-MVSNet		88.71 40	92.63 14	84.13 49	92.39 9	88.09 48	90.47 64	82.86 4	88.79 39	75.16 96	94.87 8	97.68 13	71.05 97	96.16 6	93.18 24	92.85 57	89.64 53

MCST-MVS		84.79 67	86.48 75	82.83 61	87.30 64	87.03 58	90.46 65	69.33 75	83.14 82	82.21 61	81.69 126	92.14 100	75.09 67	87.27 96	84.78 98	92.58 61	89.30 56

gm-plane-assit		71.56 159	69.99 173	73.39 129	84.43 89	73.21 154	90.42 66	51.36 191	84.08 77	76.00 91	91.30 45	37.09 214	59.01 150	73.65 178	70.24 177	79.09 170	60.37 193

CANet		82.84 85	84.60 100	80.78 77	87.30 64	85.20 71	90.23 67	69.00 77	72.16 147	78.73 83	84.49 112	90.70 117	69.54 107	87.65 92	86.17 82	89.87 94	85.84 80

CLD-MVS		82.75 88	87.22 72	77.54 105	88.01 60	85.76 67	90.23 67	54.52 177	82.28 90	82.11 63	88.48 76	95.27 52	63.95 133	89.41 77	88.29 68	86.45 134	81.01 121
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DPM-MVS		81.42 97	82.11 122	80.62 82	87.54 62	85.30 70	90.18 69	68.96 78	81.00 108	79.15 81	70.45 189	83.29 149	67.67 117	82.81 133	83.46 109	90.19 89	88.48 63

RPSCF		88.05 45	92.61 16	82.73 63	84.24 90	88.40 42	90.04 70	66.29 100	91.46 12	82.29 58	88.93 71	96.01 37	79.38 32	95.15 21	94.90 6	94.15 39	93.40 20

v7n		87.11 48	90.46 46	83.19 54	85.22 81	83.69 79	90.03 71	68.20 88	91.01 18	86.71 33	94.80 9	98.46 4	77.69 45	91.10 62	85.98 85	91.30 79	88.19 64

MVS_111021_LR		83.20 81	85.33 88	80.73 80	82.88 109	78.23 119	89.61 72	65.23 113	82.08 91	81.19 69	85.31 105	92.04 104	75.22 64	89.50 76	85.90 87	90.24 88	84.23 90

v1192		83.61 75	85.23 90	81.72 68	84.05 92	82.15 91	89.54 73	66.20 101	81.38 103	86.76 32	91.79 39	96.03 35	74.88 69	81.81 141	80.92 130	88.91 107	82.50 109

v1921920		83.49 77	84.94 96	81.80 67	83.78 98	81.20 99	89.50 74	65.91 106	81.64 96	87.18 25	91.70 40	95.39 51	75.85 59	81.56 144	80.27 136	88.60 111	82.80 105

v1240		83.57 76	84.94 96	81.97 65	84.05 92	81.27 97	89.46 75	66.06 103	81.31 104	87.50 21	91.88 38	95.46 50	76.25 55	81.16 146	80.51 134	88.52 114	82.98 103

v144192		83.43 78	84.97 95	81.63 70	83.43 101	81.23 98	89.42 76	66.04 105	81.45 102	86.40 34	91.46 43	95.70 45	75.76 61	82.14 137	80.23 137	88.74 108	82.57 108

MAR-MVS		81.98 94	82.92 118	80.88 76	85.18 82	85.85 65	89.13 77	69.52 70	71.21 151	82.25 59	71.28 183	88.89 129	69.69 104	88.71 81	86.96 75	89.52 98	87.57 70
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
TSAR-MVS + GP.		85.32 62	87.41 71	82.89 60	90.07 41	85.69 68	89.07 78	72.99 56	82.45 87	74.52 101	85.09 108	87.67 134	79.24 33	91.11 61	90.41 49	91.45 75	89.45 54

v1144		83.22 80	85.01 93	81.14 73	83.76 99	81.60 94	88.95 79	65.58 111	81.89 93	85.80 36	91.68 41	95.84 40	74.04 75	82.12 138	80.56 133	88.70 110	81.41 117

PLC	76.06 15	85.38 61	87.46 69	82.95 59	85.79 77	88.84 39	88.86 80	68.70 82	87.06 54	83.60 48	79.02 133	90.05 120	77.37 49	90.88 67	89.66 57	93.37 47	86.74 74
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CS-MVS		79.35 115	77.74 140	81.22 72	85.59 79	79.85 105	88.78 81	66.61 97	67.63 165	80.41 71	67.82 194	75.07 180	73.27 82	88.31 88	84.36 102	92.63 60	81.18 118

v10		83.17 82	85.22 91	80.78 77	83.26 104	82.99 84	88.66 82	66.49 99	79.24 121	83.60 48	91.46 43	95.47 49	74.12 73	82.60 136	80.66 131	88.53 113	84.11 93

Effi-MVS+-dtu		82.04 93	83.39 116	80.48 85	85.48 80	86.57 62	88.40 83	68.28 87	69.04 162	73.13 111	76.26 155	91.11 114	74.74 70	88.40 86	87.76 71	92.84 58	84.57 88

EPNet		79.36 114	79.44 131	79.27 93	89.51 46	77.20 128	88.35 84	77.35 32	68.27 164	74.29 102	76.31 153	79.22 161	59.63 148	85.02 119	85.45 91	86.49 133	84.61 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ETV-MVS		79.04 119	79.09 134	78.98 94	86.03 75	78.98 113	88.25 85	65.59 110	70.75 153	69.32 129	75.83 161	70.44 186	72.62 84	89.62 75	85.99 84	92.09 69	82.04 114

UniMVSNet (Re)		84.95 65	88.53 56	80.78 77	87.82 61	84.21 74	88.03 86	76.50 38	81.18 105	69.29 131	92.63 32	96.83 21	69.07 109	91.23 59	89.60 58	93.97 42	84.00 94

PVSNet_Blended_VisFu		83.00 83	84.16 107	81.65 69	82.17 115	86.01 64	88.03 86	71.23 62	76.05 132	79.54 78	83.88 114	83.44 147	77.49 48	87.38 94	84.93 96	91.41 76	87.40 72

Baseline_NR-MVSNet		82.79 86	86.51 74	78.44 99	88.30 56	75.62 142	87.81 88	74.97 47	81.53 98	66.84 146	94.71 11	96.46 24	66.90 121	91.79 49	83.37 114	85.83 143	82.09 112

Fast-Effi-MVS+		81.42 97	83.82 111	78.62 97	82.24 114	80.62 102	87.72 89	63.51 132	73.01 141	74.75 99	83.80 116	92.70 92	73.44 80	88.15 91	85.26 92	90.05 90	83.17 99

v2v482		82.20 91	84.26 104	79.81 88	82.67 111	80.18 104	87.67 90	63.96 128	81.69 95	84.73 41	91.27 46	96.33 30	72.05 91	81.94 140	79.56 140	87.79 120	78.84 137

Effi-MVS+		82.33 89	83.87 110	80.52 84	84.51 88	81.32 96	87.53 91	68.05 89	74.94 137	79.67 77	82.37 123	92.31 97	72.21 87	85.06 115	86.91 77	91.18 81	84.20 91

pmmvs-eth3d		79.64 110	82.06 123	76.83 107	80.05 127	72.64 156	87.47 92	66.59 98	80.83 109	73.50 107	89.32 65	93.20 87	67.78 115	80.78 149	81.64 126	85.58 146	76.01 147

TranMVSNet+NR-MVSNet		85.23 63	89.38 51	80.39 86	88.78 53	83.77 77	87.40 93	76.75 35	85.47 66	68.99 133	95.18 7	97.55 15	67.13 120	91.61 53	89.13 63	93.26 49	82.95 104

v8		82.20 91	84.56 101	79.45 89	82.42 112	81.65 93	87.26 94	64.27 120	79.36 120	81.70 66	91.04 49	95.75 43	73.30 81	82.82 132	79.18 143	87.74 121	82.09 112

3Dnovator	79.41 10	82.21 90	86.07 82	77.71 102	79.31 133	84.61 72	87.18 95	61.02 151	85.65 64	76.11 90	85.07 109	85.38 144	70.96 99	87.22 97	86.47 80	91.66 73	88.12 66

PM-MVS		80.42 105	83.63 113	76.67 108	78.04 145	72.37 158	87.14 96	60.18 157	80.13 114	71.75 118	86.12 98	93.92 78	77.08 50	86.56 102	85.12 94	85.83 143	81.18 118

NR-MVSNet		82.89 84	87.43 70	77.59 104	83.91 96	83.59 80	87.10 97	78.35 20	80.64 110	68.85 134	92.67 30	96.50 23	54.19 171	87.19 99	88.68 65	93.16 53	82.75 106

UniMVSNet_NR-MVSNet		84.62 69	88.00 65	80.68 81	88.18 58	83.83 76	87.06 98	76.47 39	81.46 101	70.49 124	93.24 21	95.56 47	68.13 113	90.43 70	88.47 66	93.78 43	83.02 101

DU-MVS		84.88 66	88.27 62	80.92 75	88.30 56	83.59 80	87.06 98	78.35 20	80.64 110	70.49 124	92.67 30	96.91 20	68.13 113	91.79 49	89.29 62	93.20 50	83.02 101

MSLP-MVS++		86.29 55	89.10 53	83.01 56	85.71 78	89.79 34	87.04 100	74.39 50	85.17 70	78.92 82	77.59 144	93.57 82	82.60 17	93.23 37	91.88 40	89.42 101	92.46 28

EG-PatchMatch MVS		84.35 70	87.55 68	80.62 82	86.38 71	82.24 90	86.75 101	64.02 126	84.24 75	78.17 86	89.38 64	95.03 61	78.78 37	89.95 74	86.33 81	89.59 97	85.65 82

UGNet		79.62 111	85.91 84	72.28 134	73.52 169	83.91 75	86.64 102	69.51 71	79.85 117	62.57 158	85.82 102	89.63 121	53.18 175	88.39 87	87.35 73	88.28 116	86.43 76
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
V42		79.59 112	83.59 114	74.93 123	69.61 183	77.05 130	86.59 103	55.84 172	78.42 124	77.29 87	89.84 58	95.08 59	74.12 73	83.05 129	80.11 138	86.12 137	81.59 116

FPMVS		81.56 96	84.04 109	78.66 96	82.92 107	75.96 138	86.48 104	65.66 109	84.67 74	71.47 119	77.78 142	83.22 150	77.57 47	91.24 58	90.21 51	87.84 119	85.21 84

EIA-MVS		78.57 120	77.90 139	79.35 91	87.24 66	80.71 101	86.16 105	64.03 125	62.63 190	73.49 108	73.60 173	76.12 175	73.83 77	88.49 85	84.93 96	91.36 77	78.78 138

FC-MVSNet-train		79.20 117	86.29 78	70.94 141	84.06 91	77.67 122	85.68 106	64.11 123	82.90 84	52.22 185	92.57 33	93.69 80	49.52 186	88.30 89	86.93 76	90.03 91	81.95 115

IS_MVSNet		81.72 95	85.01 93	77.90 101	86.19 72	82.64 87	85.56 107	70.02 68	80.11 115	63.52 153	87.28 86	81.18 156	67.26 118	91.08 64	89.33 61	94.82 32	83.42 98

TinyColmap		83.79 74	86.12 80	81.07 74	83.42 102	81.44 95	85.42 108	68.55 84	88.71 40	89.46 8	87.60 82	92.72 91	70.34 103	89.29 78	81.94 123	89.20 102	81.12 120

EPP-MVSNet		82.76 87	86.47 76	78.45 98	86.00 76	84.47 73	85.39 109	68.42 85	84.17 76	62.97 156	89.26 66	76.84 171	72.13 90	92.56 47	90.40 50	95.76 20	87.56 71

Gipuma		86.47 53	89.25 52	83.23 53	83.88 97	78.78 115	85.35 110	68.42 85	92.69 9	89.03 12	91.94 35	96.32 31	81.80 22	94.45 27	86.86 78	90.91 84	83.69 95
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FC-MVSNet-test		75.91 137	83.59 114	66.95 166	76.63 161	69.07 168	85.33 111	64.97 115	84.87 73	41.95 198	93.17 22	87.04 136	47.78 189	91.09 63	85.56 90	85.06 150	74.34 153

MSDG		81.39 99	84.23 106	78.09 100	82.40 113	82.47 89	85.31 112	60.91 152	79.73 118	80.26 74	86.30 95	88.27 132	69.67 105	87.20 98	84.98 95	89.97 92	80.67 123

thisisatest0515		81.18 102	84.32 103	77.52 106	76.73 159	74.84 148	85.06 113	61.37 148	81.05 107	73.95 104	88.79 74	89.25 125	75.49 63	85.98 107	84.78 98	92.53 64	85.56 83

Fast-Effi-MVS+-dtu		76.92 127	77.18 145	76.62 109	79.55 130	79.17 110	84.80 114	77.40 30	64.46 181	68.75 136	70.81 187	86.57 138	63.36 140	81.74 142	81.76 124	85.86 142	75.78 149

DELS-MVS		79.71 109	83.74 112	75.01 120	79.31 133	82.68 86	84.79 115	60.06 158	75.43 135	69.09 132	86.13 97	89.38 122	67.16 119	85.12 114	83.87 107	89.65 95	83.57 96
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
MIMVSNet1		73.40 148	81.85 124	63.55 179	72.90 172	64.37 183	84.58 116	53.60 183	90.84 19	53.92 177	87.75 81	96.10 32	45.31 192	85.37 113	79.32 142	70.98 187	69.18 172

ambc			88.38 58		91.62 17	87.97 50	84.48 117		88.64 41	87.93 16	87.38 84	94.82 66	74.53 71	89.14 80	83.86 108	85.94 141	86.84 73

pmmvs4		75.92 136	77.48 144	74.10 126	78.21 144	70.94 160	84.06 118	64.78 116	75.13 136	68.47 139	84.12 113	83.32 148	64.74 132	75.93 171	79.14 144	84.31 153	73.77 157

MDA-MVSNet-bldmvs		76.51 130	82.87 119	69.09 154	50.71 209	74.72 150	84.05 119	60.27 156	81.62 97	71.16 121	88.21 78	91.58 107	69.62 106	92.78 43	77.48 151	78.75 171	73.69 158

CANet_DTU		75.04 142	78.45 135	71.07 138	77.27 150	77.96 120	83.88 120	58.00 167	64.11 182	68.67 137	75.65 163	88.37 131	53.92 173	82.05 139	81.11 127	84.67 151	79.88 132

our_test_3					73.27 170	70.91 161	83.26 121

HyFIR lowres test		73.29 149	74.14 165	72.30 133	73.08 171	78.33 118	83.12 122	62.41 143	63.81 183	62.13 160	76.67 152	78.50 164	71.09 96	74.13 175	77.47 152	81.98 164	70.10 167

IB-MVS	71.28 17	75.21 141	77.00 147	73.12 132	76.76 153	77.45 124	83.05 123	58.92 163	63.01 186	64.31 152	59.99 205	87.57 135	68.64 111	86.26 106	82.34 121	87.05 128	82.36 111
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
CVMVSNet		75.65 139	77.62 143	73.35 131	71.95 175	69.89 165	83.04 124	60.84 153	69.12 160	68.76 135	79.92 131	78.93 163	73.64 79	81.02 147	81.01 129	81.86 165	83.43 97

casdiffmvs		79.93 107	84.11 108	75.05 118	81.41 121	78.99 112	82.95 125	62.90 139	81.53 98	68.60 138	91.94 35	96.03 35	65.84 127	82.89 131	77.07 154	88.59 112	80.34 129

tttt0517		75.86 138	76.23 153	75.42 114	75.55 165	74.06 152	82.73 126	60.31 154	69.24 158	70.24 126	79.18 132	58.79 200	72.17 88	84.49 123	83.08 116	91.54 74	84.80 85

ET-MVSNet_ETH3D		74.71 144	74.19 164	75.31 116	79.22 135	75.29 143	82.70 127	64.05 124	65.45 176	70.96 123	77.15 149	57.70 202	65.89 126	84.40 124	81.65 125	89.03 104	77.67 144

USDC		81.39 99	83.07 117	79.43 90	81.48 119	78.95 114	82.62 128	66.17 102	87.45 50	90.73 4	82.40 122	93.65 81	66.57 123	83.63 128	77.97 146	89.00 105	77.45 145

EPNet_dtu		71.90 158	73.03 170	70.59 143	78.28 142	61.64 188	82.44 129	64.12 122	63.26 185	69.74 127	71.47 181	82.41 152	51.89 183	78.83 158	78.01 145	77.07 172	75.60 151
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MDTV_nov1_ep13_2view		72.96 154	75.59 158	69.88 148	71.15 180	64.86 182	82.31 130	54.45 178	76.30 130	78.32 85	86.52 93	91.58 107	61.35 144	76.80 164	66.83 184	71.70 180	66.26 177

thisisatest0530		75.54 140	75.95 157	75.05 118	75.08 166	73.56 153	82.15 131	60.31 154	69.17 159	69.32 129	79.02 133	58.78 201	72.17 88	83.88 126	83.08 116	91.30 79	84.20 91

v148		79.33 116	82.32 121	75.84 112	80.14 126	75.74 139	81.98 132	57.06 169	81.51 100	79.36 80	89.42 62	96.42 26	71.32 94	81.54 145	75.29 163	85.20 148	76.32 146

UniMVSNet_ETH3D		85.39 60	91.12 42	78.71 95	90.48 37	83.72 78	81.76 133	82.41 6	93.84 5	64.43 151	95.41 6	98.76 1	63.72 135	93.63 34	89.74 55	89.47 100	82.74 107

EU-MVSNet		76.48 131	80.53 128	71.75 136	67.62 189	70.30 163	81.74 134	54.06 180	75.47 134	71.01 122	80.10 128	93.17 89	73.67 78	83.73 127	77.85 147	82.40 162	83.07 100

Vis-MVSNet (Re-imp)		76.15 134	80.84 127	70.68 142	83.66 100	74.80 149	81.66 135	69.59 69	80.48 113	46.94 194	87.44 83	80.63 158	53.14 176	86.87 100	84.56 101	89.12 103	71.12 163

DI_MVS_plusplus_trai		77.64 124	79.64 130	75.31 116	79.87 129	76.89 131	81.55 136	63.64 130	76.21 131	72.03 116	85.59 104	82.97 151	66.63 122	79.27 157	77.78 148	88.14 117	78.76 139

testgi		68.20 172	76.05 155	59.04 186	79.99 128	67.32 175	81.16 137	51.78 189	84.91 72	39.36 203	73.42 174	95.19 54	32.79 204	76.54 168	70.40 176	69.14 191	64.55 180

PatchMatch-RL		76.05 135	76.64 149	75.36 115	77.84 149	69.87 166	81.09 138	63.43 133	71.66 149	68.34 140	71.70 179	81.76 155	74.98 68	84.83 121	83.44 110	86.45 134	73.22 160

IterMVS		73.62 147	76.53 150	70.23 146	71.83 176	77.18 129	80.69 139	53.22 185	72.23 146	66.62 147	85.21 106	78.96 162	69.54 107	76.28 170	71.63 173	79.45 168	74.25 155
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
diffmvs		76.74 128	81.61 125	71.06 139	75.64 164	74.45 151	80.68 140	57.57 168	77.48 125	67.62 144	88.95 70	93.94 77	61.98 143	79.74 154	76.18 158	82.85 161	80.50 124

DCV-MVSNet		80.04 106	85.67 87	73.48 128	82.91 108	81.11 100	80.44 141	66.06 103	85.01 71	62.53 159	78.84 136	94.43 73	58.51 152	88.66 82	85.91 86	90.41 87	85.73 81

canonicalmvs		81.22 101	86.04 83	75.60 113	83.17 106	83.18 83	80.29 142	65.82 108	85.97 63	67.98 141	77.74 143	91.51 109	65.17 129	88.62 83	86.15 83	91.17 82	89.09 57

GA-MVS		75.01 143	76.39 151	73.39 129	78.37 141	75.66 141	80.03 143	58.40 165	70.51 154	75.85 92	83.24 117	76.14 174	63.75 134	77.28 163	76.62 157	83.97 155	75.30 152

OpenMVS	75.38 16	78.44 121	81.39 126	74.99 121	80.46 124	79.85 105	79.99 144	58.31 166	77.34 127	73.85 105	77.19 148	82.33 154	68.60 112	84.67 122	81.95 122	88.72 109	86.40 77

MVS_Test		76.72 129	79.40 132	73.60 127	78.85 139	74.99 146	79.91 145	61.56 147	69.67 156	72.44 112	85.98 100	90.78 116	63.50 138	78.30 159	75.74 161	85.33 147	80.31 130

IterMVS-LS		79.79 108	82.56 120	76.56 110	81.83 117	77.85 121	79.90 146	69.42 74	78.93 122	71.21 120	90.47 51	85.20 145	70.86 100	80.54 151	80.57 132	86.15 136	84.36 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
QAPM		80.43 104	84.34 102	75.86 111	79.40 132	82.06 92	79.86 147	61.94 145	83.28 81	74.73 100	81.74 125	85.44 143	70.97 98	84.99 120	84.71 100	88.29 115	88.14 65

PVSNet_BlendedMVS		76.45 132	78.12 137	74.49 124	76.76 153	78.46 116	79.65 148	63.26 135	65.42 177	73.15 109	75.05 166	88.96 126	66.51 124	82.73 134	77.66 149	87.61 122	78.60 140

PVSNet_Blended		76.45 132	78.12 137	74.49 124	76.76 153	78.46 116	79.65 148	63.26 135	65.42 177	73.15 109	75.05 166	88.96 126	66.51 124	82.73 134	77.66 149	87.61 122	78.60 140

CDS-MVSNet		73.07 153	77.02 146	68.46 157	81.62 118	72.89 155	79.56 150	70.78 65	69.56 157	52.52 182	77.37 147	81.12 157	42.60 194	84.20 125	83.93 105	83.65 156	70.07 168
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		66.81 176	66.94 181	66.67 167	72.79 173	68.25 171	79.55 151	55.57 173	65.52 175	62.77 157	76.98 150	60.09 196	56.73 158	65.69 198	62.35 189	72.59 178	69.71 169

Anonymous202405211			84.68 99		83.92 95	79.45 109	79.03 152	67.79 91	82.01 92		88.77 75	92.58 93	55.93 162	86.68 101	84.26 103	88.92 106	78.98 136

CHOSEN 1792x2688		68.80 169	71.09 172	66.13 171	69.11 185	68.89 170	78.98 153	54.68 175	61.63 192	56.69 168	71.56 180	78.39 165	67.69 116	72.13 182	72.01 172	69.63 190	73.02 161

Anonymous20231211		79.37 113	85.78 85	71.89 135	82.87 110	79.66 108	78.77 154	63.93 129	83.36 80	59.39 163	90.54 50	94.66 68	56.46 159	87.38 94	84.12 104	89.92 93	80.74 122

thres600view7		74.34 146	78.43 136	69.56 151	80.47 123	76.28 135	78.65 155	62.56 141	77.39 126	52.53 181	74.03 170	76.78 172	55.90 163	85.06 115	85.19 93	87.25 126	74.29 154

FMVSNet1		78.20 123	84.83 98	70.46 145	78.62 140	79.03 111	77.90 156	67.53 94	83.02 83	55.10 174	87.19 88	93.18 88	55.65 164	85.57 109	83.39 111	87.98 118	82.40 110

pmmvs6		80.46 103	88.34 61	71.26 137	81.96 116	77.51 123	77.54 157	68.83 80	93.72 6	55.92 171	93.94 16	98.03 9	55.94 161	89.21 79	85.61 89	87.36 125	80.38 125

TransMVSNet (Re)		79.05 118	86.66 73	70.18 147	83.32 103	75.99 137	77.54 157	63.98 127	90.68 22	55.84 172	94.80 9	96.06 34	53.73 174	86.27 105	83.22 115	86.65 129	79.61 134

thres400		73.13 152	76.99 148	68.62 156	79.46 131	74.93 147	77.23 159	61.23 150	75.54 133	52.31 184	72.20 178	77.10 170	54.89 166	82.92 130	82.62 120	86.57 132	73.66 159

MS-PatchMatch		71.18 162	73.99 166	67.89 163	77.16 151	71.76 159	77.18 160	56.38 171	67.35 166	55.04 175	74.63 168	75.70 176	62.38 142	76.62 166	75.97 160	79.22 169	75.90 148

tfpn200view9		72.01 157	75.40 159	68.06 160	77.97 146	76.44 133	77.04 161	62.67 140	66.81 168	50.82 190	67.30 195	75.67 177	52.46 182	85.06 115	82.64 119	87.41 124	73.86 156

SCA		68.54 171	67.52 180	69.73 149	67.79 188	75.04 144	76.96 162	68.94 79	66.41 170	67.86 142	74.03 170	60.96 193	65.55 128	68.99 190	65.67 185	71.30 185	61.54 192

DWT-MVSNet_training		63.07 182	60.04 201	66.61 168	71.64 177	65.27 181	76.80 163	53.82 181	55.90 202	63.07 155	62.23 203	41.87 213	62.54 141	64.32 200	63.71 188	71.78 179	66.97 175

baseline2		68.71 170	68.34 178	69.14 153	75.69 163	69.70 167	76.60 164	55.53 174	60.13 195	62.07 161	66.76 197	60.35 195	60.77 145	76.53 169	74.03 165	84.19 154	70.88 164

tfpnnormal		77.16 126	84.26 104	68.88 155	81.02 122	75.02 145	76.52 165	63.30 134	87.29 51	52.40 183	91.24 47	93.97 76	54.85 168	85.46 112	81.08 128	85.18 149	75.76 150

pm-mvs1		78.21 122	85.68 86	69.50 152	80.38 125	75.73 140	76.25 166	65.04 114	87.59 48	54.47 176	93.16 23	95.99 39	54.20 170	86.37 104	82.98 118	86.64 130	77.96 143

tpm cat1		64.79 181	62.74 194	67.17 164	74.61 168	65.91 179	76.18 167	59.32 160	64.88 180	66.41 148	71.21 184	53.56 210	59.17 149	61.53 203	58.16 198	67.33 194	63.95 181

RPMNet		67.02 175	63.99 189	70.56 144	71.55 178	67.63 172	75.81 168	69.44 73	59.93 196	63.24 154	64.32 199	47.51 212	59.68 147	70.37 187	69.64 179	83.64 157	68.49 173

MDTV_nov1_ep13		64.96 179	64.77 186	65.18 177	67.08 192	62.46 187	75.80 169	51.10 192	62.27 191	69.74 127	74.12 169	62.65 191	55.64 165	68.19 192	62.16 193	71.70 180	61.57 191

GBi-Net		73.17 150	77.64 141	67.95 161	76.76 153	77.36 125	75.77 170	64.57 117	62.99 187	51.83 186	76.05 156	77.76 167	52.73 179	85.57 109	83.39 111	86.04 138	80.37 126

test1		73.17 150	77.64 141	67.95 161	76.76 153	77.36 125	75.77 170	64.57 117	62.99 187	51.83 186	76.05 156	77.76 167	52.73 179	85.57 109	83.39 111	86.04 138	80.37 126

FMVSNet2		74.43 145	79.70 129	68.27 158	76.76 153	77.36 125	75.77 170	65.36 112	72.28 145	52.97 180	81.92 124	85.61 142	52.73 179	80.66 150	79.73 139	86.04 138	80.37 126

MVSTER		68.08 173	69.73 174	66.16 170	66.33 196	70.06 164	75.71 173	52.36 187	55.18 205	58.64 165	70.23 191	56.72 205	57.34 156	79.68 155	76.03 159	86.61 131	80.20 131

test20.03		69.91 163	76.20 154	62.58 180	84.01 94	67.34 174	75.67 174	65.88 107	79.98 116	40.28 202	82.65 119	89.31 124	39.63 198	77.41 162	73.28 167	69.98 188	63.40 184

IterMVS-SCA-FT		77.23 125	79.18 133	74.96 122	76.67 160	79.85 105	75.58 175	61.34 149	73.10 140	73.79 106	86.23 96	79.61 160	79.00 36	80.28 153	75.50 162	83.41 160	79.70 133

thres200		72.41 156	76.00 156	68.21 159	78.28 142	76.28 135	74.94 176	62.56 141	72.14 148	51.35 189	69.59 192	76.51 173	54.89 166	85.06 115	80.51 134	87.25 126	71.92 162

FMVSNet3		71.40 161	75.20 162	66.97 165	75.00 167	76.59 132	74.29 177	64.57 117	62.99 187	51.83 186	76.05 156	77.76 167	51.49 184	76.58 167	77.03 155	84.62 152	79.43 135

Anonymous20231206		67.28 174	73.41 169	60.12 185	76.45 162	63.61 186	74.21 178	56.52 170	76.35 129	42.23 197	75.81 162	90.47 118	41.51 197	74.52 172	69.97 178	69.83 189	63.17 185

baseline		69.33 167	75.37 160	62.28 182	66.54 194	66.67 177	73.95 179	48.07 194	66.10 171	59.26 164	82.45 120	86.30 139	54.44 169	74.42 174	73.25 168	71.42 183	78.43 142

thres100view900		69.86 164	72.97 171	66.24 169	77.97 146	72.49 157	73.29 180	59.12 161	66.81 168	50.82 190	67.30 195	75.67 177	50.54 185	78.24 160	79.40 141	85.71 145	70.88 164

PatchmatchNet		64.81 180	63.74 190	66.06 173	69.21 184	58.62 192	73.16 181	60.01 159	65.92 172	66.19 149	76.27 154	59.09 197	60.45 146	66.58 195	61.47 195	67.33 194	58.24 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test-mter		59.39 193	61.59 196	56.82 190	53.21 205	54.82 196	73.12 182	26.57 208	53.19 206	56.31 169	64.71 198	60.47 194	56.36 160	68.69 191	64.27 187	75.38 174	65.00 178

pmmvs5		68.91 168	74.35 163	62.56 181	67.45 191	66.78 176	71.70 183	51.47 190	67.17 167	56.25 170	82.41 121	88.59 130	47.21 191	73.21 181	74.23 164	81.30 166	68.03 174

tpm		62.79 185	63.25 191	62.26 183	70.09 182	53.78 197	71.65 184	47.31 195	65.72 174	76.70 88	80.62 127	56.40 207	48.11 188	64.20 201	58.54 196	59.70 200	63.47 183

dps		65.14 178	64.50 187	65.89 174	71.41 179	65.81 180	71.44 185	61.59 146	58.56 199	61.43 162	75.45 164	52.70 211	58.06 154	69.57 189	64.65 186	71.39 184	64.77 179

baseline1		69.62 165	73.55 168	65.02 178	78.95 138	70.39 162	71.38 186	62.03 144	70.97 152	47.95 193	78.47 140	68.19 188	47.77 190	79.65 156	76.94 156	82.05 163	70.27 166

gg-mvs-nofinetune		72.68 155	75.21 161	69.73 149	81.48 119	69.04 169	70.48 187	76.67 36	86.92 55	67.80 143	88.06 79	64.67 190	42.12 196	77.60 161	73.65 166	79.81 167	66.57 176

PatchT		66.25 177	66.76 182	65.67 175	55.87 204	60.75 189	70.17 188	59.00 162	59.80 198	72.30 113	78.68 138	54.12 209	65.04 130	71.64 183	72.91 169	71.63 182	69.40 170

pmmvs3		62.72 186	68.71 177	55.74 192	50.74 208	57.10 193	70.05 189	28.82 206	61.57 194	57.39 167	71.19 185	85.73 140	53.96 172	73.36 180	69.43 180	73.47 177	62.55 187

MIMVSNet		63.02 183	69.02 176	56.01 191	68.20 186	59.26 191	70.01 190	53.79 182	71.56 150	41.26 201	71.38 182	82.38 153	36.38 200	71.43 185	67.32 183	66.45 196	59.83 194

TAMVS		63.02 183	69.30 175	55.70 193	70.12 181	56.89 194	69.63 191	45.13 196	70.23 155	38.00 204	77.79 141	75.15 179	42.60 194	74.48 173	72.81 171	68.70 192	57.75 199

PMMVS		61.98 189	65.61 184	57.74 188	45.03 210	51.76 202	69.54 192	35.05 203	55.49 204	55.32 173	68.23 193	78.39 165	58.09 153	70.21 188	71.56 174	83.42 159	63.66 182

test-LLR		62.15 188	59.46 204	65.29 176	79.07 136	52.66 200	69.46 193	62.93 137	50.76 208	53.81 178	63.11 201	58.91 198	52.87 177	66.54 196	62.34 190	73.59 175	61.87 189

TESTMET0.1,1		57.21 196	59.46 204	54.60 196	50.95 207	52.66 200	69.46 193	26.91 207	50.76 208	53.81 178	63.11 201	58.91 198	52.87 177	66.54 196	62.34 190	73.59 175	61.87 189

CHOSEN 280x420		56.32 200	58.85 206	53.36 197	51.63 206	39.91 210	69.12 195	38.61 202	56.29 201	36.79 205	48.84 207	62.59 192	63.39 139	73.61 179	67.66 182	60.61 198	63.07 186

test0.0.03 1		61.79 190	65.33 185	57.65 189	79.07 136	64.09 184	68.51 196	62.93 137	61.59 193	33.71 206	61.58 204	71.58 185	33.43 203	70.95 186	68.68 181	68.26 193	58.82 195

tpmrst		59.42 192	60.02 202	58.71 187	67.56 190	53.10 199	66.99 197	51.88 188	63.80 184	57.68 166	76.73 151	56.49 206	48.73 187	56.47 207	55.55 200	59.43 201	58.02 198

FMVSNet5		56.37 199	60.14 200	51.98 200	60.83 200	59.58 190	66.85 198	42.37 199	52.68 207	41.33 200	47.09 208	54.68 208	35.28 201	73.88 176	70.77 175	65.24 197	62.26 188

CR-MVSNet		69.56 166	68.34 178	70.99 140	72.78 174	67.63 172	64.47 199	67.74 92	59.93 196	72.30 113	80.10 128	56.77 204	65.04 130	71.64 183	72.91 169	83.61 158	69.40 170

Patchmtry						56.88 195	64.47 199	67.74 92		72.30 113

CMPMVS	55.74 18	71.56 159	76.26 152	66.08 172	68.11 187	63.91 185	63.17 201	50.52 193	68.79 163	75.49 93	70.78 188	85.67 141	63.54 137	81.58 143	77.20 153	75.63 173	85.86 79
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EMVS		58.97 195	62.63 195	54.70 195	66.26 197	48.71 204	61.74 202	42.71 198	72.80 144	46.00 195	73.01 177	71.66 183	57.91 155	80.41 152	50.68 207	53.55 206	41.11 209

EPMVS		56.62 198	59.77 203	52.94 198	62.41 199	50.55 203	60.66 203	52.83 186	65.15 179	41.80 199	77.46 146	57.28 203	42.68 193	59.81 205	54.82 201	57.23 203	53.35 202

E-PMN		59.07 194	62.79 193	54.72 194	67.01 193	47.81 206	60.44 204	43.40 197	72.95 142	44.63 196	70.42 190	73.17 182	58.73 151	80.97 148	51.98 205	54.14 205	42.26 208

ADS-MVSNet		56.89 197	61.09 197	52.00 199	59.48 201	48.10 205	58.02 205	54.37 179	72.82 143	49.19 192	75.32 165	65.97 189	37.96 199	59.34 206	54.66 202	52.99 207	51.42 204

N_pmnet		54.95 201	65.90 183	42.18 202	66.37 195	43.86 209	57.92 206	39.79 201	79.54 119	17.24 211	86.31 94	87.91 133	25.44 205	64.68 199	51.76 206	46.33 208	47.23 206

MVS-HIRNet		59.74 191	58.74 207	60.92 184	57.74 203	45.81 207	56.02 207	58.69 164	55.69 203	65.17 150	70.86 186	71.66 183	56.75 157	61.11 204	53.74 203	71.17 186	52.28 203

GG-mvs-BLEND		41.63 205	60.36 199	19.78 206	0.14 216	66.04 178	55.66 208	0.17 213	57.64 200	2.42 214	51.82 206	69.42 187	0.28 212	64.11 202	58.29 197	60.02 199	55.18 201

new-patchmatchnet		62.59 187	73.79 167	49.53 201	76.98 152	53.57 198	53.46 209	54.64 176	85.43 67	28.81 207	91.94 35	96.41 27	25.28 206	76.80 164	53.66 204	57.99 202	58.69 196

PMMVS2		48.13 204	64.06 188	29.55 205	44.06 211	36.69 211	51.95 210	29.97 205	74.75 138	8.90 213	76.02 159	91.24 113	7.53 208	73.78 177	55.91 199	34.87 210	40.01 210

new_pmnet		52.29 202	63.16 192	39.61 204	58.89 202	44.70 208	48.78 211	34.73 204	65.88 173	17.85 210	73.42 174	80.00 159	23.06 207	67.00 194	62.28 192	54.36 204	48.81 205

MVE	41.12 19	51.80 203	60.92 198	41.16 203	35.21 212	34.14 212	48.45 212	41.39 200	69.11 161	19.53 209	63.33 200	73.80 181	63.56 136	67.19 193	61.51 194	38.85 209	57.38 200
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						17.78 213	20.40 213	6.69 209	31.41 210	9.80 212	38.61 209	34.88 215	33.78 202	28.41 209		23.59 211	45.77 207

tmp_tt				13.54 207	16.73 213	6.42 214	8.49 214	2.36 210	28.69 211	27.44 208	18.40 210	13.51 216	3.70 209	33.23 208	36.26 208	22.54 212

Patchmatch-RL test							4.13 215

testmvs		0.93 207	1.37 209	0.41 209	0.36 215	0.36 216	0.62 216	0.39 211	1.48 212	0.18 216	2.41 211	1.31 218	0.41 211	1.25 211	1.08 210	0.48 213	1.68 211

test123		1.06 206	1.41 208	0.64 208	0.39 214	0.48 215	0.52 217	0.25 212	1.11 213	1.37 215	2.01 212	1.98 217	0.87 210	1.43 210	1.27 209	0.46 214	1.62 212

sosnet-low-res		0.00 208	0.00 210	0.00 210	0.00 217	0.00 217	0.00 218	0.00 214	0.00 214	0.00 217	0.00 213	0.00 219	0.00 213	0.00 212	0.00 211	0.00 215	0.00 213

sosnet		0.00 208	0.00 210	0.00 210	0.00 217	0.00 217	0.00 218	0.00 214	0.00 214	0.00 217	0.00 213	0.00 219	0.00 213	0.00 212	0.00 211	0.00 215	0.00 213

SR-MVS					91.82 13			80.80 7				95.53 48

test_part1																	93.49 18

MTAPA										89.37 9		94.85 64

MTMP										90.54 5		95.16 56

mPP-MVS					93.05 4							95.77 42

NP-MVS									78.65 123

High-resolution multi-view benchmark