High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

UA-Net		89.02 34	91.44 40	86.20 29	94.88 1	89.84 34	94.76 30	77.45 29	85.41 73	74.79 107	88.83 78	88.90 139	78.67 40	96.06 7	95.45 4	96.66 3	95.58 2

DTE-MVSNet		88.99 36	92.77 13	84.59 44	93.31 2	88.10 49	90.96 53	83.09 2	91.38 15	76.21 96	96.03 3	98.04 9	70.78 108	95.65 14	92.32 33	93.18 59	87.84 73

zzz-MVS		90.38 12	91.35 42	89.25 5	93.08 3	86.59 65	96.45 11	79.00 16	90.23 29	89.30 10	85.87 109	94.97 66	82.54 18	95.05 23	94.83 7	95.14 27	91.94 37

mPP-MVS					93.05 4							95.77 45

MP-MVS		90.84 6	91.95 35	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 61	88.75 13	89.00 74	94.38 79	84.01 9	94.94 25	94.34 11	95.45 24	93.24 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		88.86 40	92.92 10	84.11 54	92.92 5	88.05 51	90.83 56	82.67 5	91.04 19	74.83 106	95.97 4	98.47 4	70.38 109	95.70 13	92.43 31	93.05 63	88.78 65

HPM-MVS++		88.74 41	89.54 55	87.80 16	92.58 7	85.69 73	95.10 27	78.01 23	87.08 58	87.66 20	87.89 86	92.07 109	80.28 30	90.97 72	91.41 44	93.17 60	91.69 39

DVP-MVS++.		90.50 10	94.18 4	86.21 28	92.52 8	90.29 28	95.29 23	76.02 42	94.24 6	82.82 57	95.84 6	97.56 17	76.82 57	93.13 39	91.20 45	93.78 49	97.01 1

PS-CasMVS		89.07 33	93.23 8	84.21 52	92.44 9	88.23 48	90.54 64	82.95 3	90.50 26	75.31 104	95.80 7	98.37 7	71.16 102	96.30 5	93.32 22	92.88 64	90.11 53

CP-MVSNet		88.71 42	92.63 16	84.13 53	92.39 10	88.09 50	90.47 69	82.86 4	88.79 44	75.16 105	94.87 10	97.68 15	71.05 104	96.16 6	93.18 24	92.85 65	89.64 57

CP-MVS		91.09 5	92.33 26	89.65 2	92.16 11	90.41 27	96.46 10	80.38 8	88.26 47	89.17 11	87.00 98	96.34 32	83.95 10	95.77 11	94.72 8	95.81 17	93.78 10

ACMMPR		91.30 4	92.88 12	89.46 4	91.92 12	91.61 5	96.60 5	79.46 14	90.08 32	88.53 14	89.54 66	95.57 49	84.25 7	95.24 20	94.27 13	95.97 11	93.85 8

WR-MVS_H		88.99 36	93.28 6	83.99 55	91.92 12	89.13 40	91.95 47	83.23 1	90.14 31	71.92 126	95.85 5	98.01 11	71.83 99	95.82 9	93.19 23	93.07 62	90.83 49

SR-MVS					91.82 14			80.80 7				95.53 51

PGM-MVS		90.42 11	91.58 38	89.05 6	91.77 15	91.06 13	96.51 7	78.94 17	85.41 73	87.67 19	87.02 97	95.26 57	83.62 12	95.01 24	93.94 16	95.79 19	93.40 20

APD-MVS		89.14 30	91.25 45	86.67 25	91.73 16	91.02 15	95.50 21	77.74 25	84.04 85	79.47 84	91.48 45	94.85 68	81.14 26	92.94 42	92.20 36	94.47 41	92.24 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		90.13 16	92.26 28	87.64 18	91.68 17	90.44 26	95.22 25	77.34 33	90.79 23	87.80 17	90.42 56	92.05 111	79.05 35	93.89 33	93.59 19	94.77 34	94.62 5
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
ambc			88.38 63		91.62 18	87.97 52	84.48 125		88.64 46	87.93 16	87.38 92	94.82 70	74.53 78	89.14 90	83.86 117	85.94 151	86.84 78

TSAR-MVS + MP.		89.67 25	92.25 29	86.65 26	91.53 19	90.98 17	96.15 14	73.30 57	87.88 51	81.83 69	92.92 30	95.15 61	82.23 19	93.58 35	92.25 34	94.87 31	93.01 25
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		86.67 56	87.73 72	85.43 36	91.51 20	82.72 91	94.47 32	74.22 54	81.71 101	81.54 73	89.20 72	92.87 95	78.33 42	90.12 82	88.47 72	92.51 72	89.04 62

X-MVS		89.36 29	90.73 48	87.77 17	91.50 21	91.23 8	96.76 4	78.88 18	87.29 56	87.14 26	78.98 147	94.53 73	76.47 59	95.25 19	94.28 12	95.85 14	93.55 16

HFP-MVS		90.32 14	92.37 23	87.94 14	91.46 22	90.91 18	95.69 18	79.49 12	89.94 35	83.50 51	89.06 73	94.44 77	81.68 23	94.17 31	94.19 14	95.81 17	93.87 7

ACMM	80.67 7	90.67 7	92.46 20	88.57 8	91.35 23	89.93 32	96.34 12	77.36 31	90.17 30	86.88 30	87.32 93	96.63 25	83.32 13	95.79 10	94.49 10	96.19 9	92.91 26
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		89.79 24	93.66 5	85.27 38	91.32 24	88.27 46	93.49 39	79.86 10	92.75 10	75.37 103	96.86 1	98.38 6	75.10 73	95.93 8	94.07 15	96.46 5	89.39 59

SD-MVS		89.91 19	92.23 31	87.19 22	91.31 25	89.79 35	94.31 33	75.34 48	89.26 39	81.79 70	92.68 32	95.08 63	83.88 11	93.10 40	92.69 26	96.54 4	93.02 24
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
XVS					91.28 26	91.23 8	96.89 2			87.14 26		94.53 73				95.84 15

X-MVStestdata					91.28 26	91.23 8	96.89 2			87.14 26		94.53 73				95.84 15

DeepC-MVS	83.59 4	90.37 13	92.56 19	87.82 15	91.26 28	92.33 3	94.72 31	80.04 9	90.01 33	84.61 43	93.33 23	94.22 80	80.59 28	92.90 45	92.52 29	95.69 21	92.57 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP		90.63 8	92.40 21	88.56 9	91.24 29	91.60 6	96.49 9	77.53 27	87.89 50	86.87 31	87.24 95	96.46 27	82.87 16	95.59 15	94.50 9	96.35 6	93.51 18
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
SteuartSystems-ACMMP		90.00 18	91.73 36	87.97 13	91.21 30	90.29 28	96.51 7	78.00 24	86.33 64	85.32 41	88.23 83	94.67 71	82.08 21	95.13 22	93.88 17	94.72 36	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		89.86 20	91.96 34	87.42 20	91.00 31	90.08 30	96.00 16	76.61 37	89.28 36	87.73 18	90.04 58	91.80 114	78.71 38	94.36 29	93.82 18	94.48 40	94.32 6

CPTT-MVS		89.63 26	90.52 50	88.59 7	90.95 32	90.74 21	95.71 17	79.13 15	87.70 52	85.68 39	80.05 142	95.74 47	84.77 6	94.28 30	92.68 27	95.28 26	92.45 32

LGP-MVS_train		90.56 9	92.38 22	88.43 10	90.88 33	91.15 11	95.35 22	77.65 26	86.26 66	87.23 24	90.45 55	97.35 19	83.20 14	95.44 16	93.41 21	96.28 8	92.63 27

OPM-MVS		89.82 22	92.24 30	86.99 23	90.86 34	89.35 38	95.07 28	75.91 44	91.16 17	86.87 31	91.07 51	97.29 20	79.13 34	93.32 36	91.99 38	94.12 43	91.49 42
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	80.00 8	90.12 17	92.30 27	87.58 19	90.83 35	91.10 12	94.96 29	76.06 41	87.47 54	85.33 40	88.91 77	97.65 16	82.13 20	95.31 17	93.44 20	96.14 10	92.22 34
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
NCCC		86.74 55	87.97 71	85.31 37	90.64 36	87.25 59	93.27 40	74.59 50	86.50 62	83.72 47	75.92 172	92.39 103	77.08 55	91.72 55	90.68 50	92.57 70	91.30 44

MSP-MVS		88.51 43	91.36 41	85.19 40	90.63 37	92.01 4	95.29 23	77.52 28	90.48 27	80.21 79	90.21 57	96.08 36	76.38 61	88.30 98	91.42 42	91.12 90	91.01 46
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
UniMVSNet_ETH3D		85.39 65	91.12 46	78.71 103	90.48 38	83.72 83	81.76 141	82.41 6	93.84 7	64.43 160	95.41 8	98.76 1	63.72 143	93.63 34	89.74 60	89.47 108	82.74 115

APDe-MVS		89.85 21	92.91 11	86.29 27	90.47 39	91.34 7	96.04 15	76.41 40	91.11 18	78.50 89	93.44 22	95.82 44	81.55 24	93.16 38	91.90 39	94.77 34	93.58 15

PMVS	79.51 9	90.23 15	92.67 15	87.39 21	90.16 40	88.75 42	93.64 37	75.78 45	90.00 34	83.70 48	92.97 29	92.22 106	86.13 4	97.01 3	96.79 2	94.94 30	90.96 47
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CNVR-MVS		86.93 54	88.98 59	84.54 45	90.11 41	87.41 58	93.23 41	73.47 56	86.31 65	82.25 64	82.96 130	92.15 107	76.04 64	91.69 56	90.69 49	92.17 76	91.64 41

TSAR-MVS + GP.		85.32 67	87.41 76	82.89 65	90.07 42	85.69 73	89.07 85	72.99 60	82.45 94	74.52 110	85.09 117	87.67 145	79.24 33	91.11 67	90.41 52	91.45 82	89.45 58

DeepC-MVS_fast	81.78 5	87.38 52	89.64 54	84.75 42	89.89 43	90.70 22	92.74 44	74.45 51	86.02 67	82.16 67	86.05 107	91.99 113	75.84 67	91.16 66	90.44 51	93.41 54	91.09 45
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 34	91.69 37	85.91 31	89.72 44	90.81 20	92.56 45	71.69 68	90.83 22	87.24 23	89.71 64	92.07 109	78.37 41	94.43 28	92.59 28	95.86 13	91.35 43

DPE-MVS		89.81 23	92.34 25	86.86 24	89.69 45	91.00 16	95.53 19	76.91 34	88.18 48	83.43 54	93.48 21	95.19 58	81.07 27	92.75 47	92.07 37	94.55 38	93.74 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CDPH-MVS		86.66 57	88.52 62	84.48 46	89.61 46	88.27 46	92.86 43	72.69 61	80.55 119	82.71 58	86.92 99	93.32 91	75.55 69	91.00 71	89.85 59	93.47 52	89.71 56

EPNet		79.36 124	79.44 142	79.27 102	89.51 47	77.20 138	88.35 91	77.35 32	68.27 174	74.29 111	76.31 165	79.22 174	59.63 156	85.02 129	85.45 101	86.49 143	84.61 93
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + ACMM		89.14 30	92.11 33	85.67 32	89.27 48	90.61 24	90.98 52	79.48 13	88.86 42	79.80 81	93.01 28	93.53 89	83.17 15	92.75 47	92.45 30	91.32 85	93.59 13

HQP-MVS		85.02 69	86.41 82	83.40 56	89.19 49	86.59 65	91.28 50	71.60 69	82.79 91	83.48 52	78.65 151	93.54 88	72.55 91	86.49 113	85.89 97	92.28 75	90.95 48

AdaColmap		84.15 76	85.14 97	83.00 62	89.08 50	87.14 61	90.56 63	70.90 71	82.40 95	80.41 76	73.82 183	84.69 159	75.19 72	91.58 60	89.90 58	91.87 79	86.48 80

DVP-MVS		89.40 28	92.69 14	85.56 35	89.01 51	89.85 33	93.72 36	75.42 46	92.28 12	80.49 75	94.36 14	94.87 67	81.46 25	92.49 51	91.42 42	93.27 56	93.54 17
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 12	88.98 52	92.86 2	95.51 20	72.17 62	94.95 5	91.27 3	94.11 17	97.77 12	84.22 8	96.49 4	95.27 5	96.79 2	93.60 12
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TDRefinement		93.16 1	95.57 1	90.36 1	88.79 53	93.57 1	97.27 1	78.23 22	95.55 2	93.00 1	93.98 18	96.01 40	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

TranMVSNet+NR-MVSNet		85.23 68	89.38 56	80.39 93	88.78 54	83.77 82	87.40 99	76.75 35	85.47 71	68.99 142	95.18 9	97.55 18	67.13 128	91.61 59	89.13 68	93.26 57	82.95 112

SED-MVS		88.96 38	92.37 23	84.99 41	88.64 55	89.65 37	95.11 26	75.98 43	90.73 24	80.15 80	94.21 16	94.51 76	76.59 58	92.94 42	91.17 46	93.46 53	93.37 22

ACMH+	79.05 11	89.62 27	93.08 9	85.58 33	88.58 56	89.26 39	92.18 46	74.23 53	93.55 9	82.66 61	92.32 37	98.35 8	80.29 29	95.28 18	92.34 32	95.52 22	90.43 51

MVS_0304		84.73 73	86.19 84	83.02 60	88.32 57	86.71 64	91.55 48	70.87 72	73.79 148	82.88 56	85.13 116	93.35 90	72.55 91	88.62 93	87.69 79	91.93 78	88.05 72

DU-MVS		84.88 71	88.27 67	80.92 82	88.30 58	83.59 85	87.06 104	78.35 20	80.64 117	70.49 134	92.67 33	96.91 23	68.13 121	91.79 53	89.29 67	93.20 58	83.02 109

Baseline_NR-MVSNet		82.79 94	86.51 79	78.44 107	88.30 58	75.62 152	87.81 94	74.97 49	81.53 105	66.84 155	94.71 13	96.46 27	66.90 129	91.79 53	83.37 124	85.83 153	82.09 120

UniMVSNet_NR-MVSNet		84.62 74	88.00 70	80.68 88	88.18 60	83.83 81	87.06 104	76.47 39	81.46 108	70.49 134	93.24 24	95.56 50	68.13 121	90.43 76	88.47 72	93.78 49	83.02 109

xxxxxxxxxxxxxcwj		88.03 48	91.29 44	84.22 50	88.17 61	87.90 53	90.80 57	71.80 66	89.28 36	82.70 59	89.90 60	97.72 13	77.91 47	91.69 56	90.04 56	93.95 47	92.47 29

SF-MVS		87.85 51	90.95 47	84.22 50	88.17 61	87.90 53	90.80 57	71.80 66	89.28 36	82.70 59	89.90 60	95.37 55	77.91 47	91.69 56	90.04 56	93.95 47	92.47 29

CSCG		88.12 46	91.45 39	84.23 49	88.12 63	90.59 25	90.57 62	68.60 92	91.37 16	83.45 53	89.94 59	95.14 62	78.71 38	91.45 61	88.21 76	95.96 12	93.44 19

CLD-MVS		82.75 96	87.22 77	77.54 113	88.01 64	85.76 72	90.23 72	54.52 187	82.28 97	82.11 68	88.48 81	95.27 56	63.95 141	89.41 87	88.29 74	86.45 144	81.01 128
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet (Re)		84.95 70	88.53 61	80.78 84	87.82 65	84.21 79	88.03 92	76.50 38	81.18 112	69.29 140	92.63 35	96.83 24	69.07 117	91.23 65	89.60 63	93.97 46	84.00 101

DPM-MVS		81.42 106	82.11 133	80.62 89	87.54 66	85.30 75	90.18 74	68.96 87	81.00 115	79.15 86	70.45 200	83.29 162	67.67 125	82.81 143	83.46 119	90.19 96	88.48 67

DeepPCF-MVS	81.61 6	87.95 49	90.29 52	85.22 39	87.48 67	90.01 31	93.79 35	73.54 55	88.93 41	83.89 46	89.40 68	90.84 123	80.26 31	90.62 75	90.19 55	92.36 73	92.03 36

DROMVSNet		83.70 81	84.77 105	82.46 69	87.47 68	82.79 90	85.50 114	72.00 63	69.81 165	77.66 92	85.02 119	89.63 130	78.14 43	90.40 77	87.56 80	94.00 44	88.16 69

CANet		82.84 93	84.60 107	80.78 84	87.30 69	85.20 76	90.23 72	69.00 86	72.16 157	78.73 88	84.49 124	90.70 126	69.54 114	87.65 101	86.17 92	89.87 101	85.84 86

MCST-MVS		84.79 72	86.48 80	82.83 66	87.30 69	87.03 62	90.46 70	69.33 84	83.14 88	82.21 66	81.69 138	92.14 108	75.09 74	87.27 105	84.78 108	92.58 68	89.30 60

EIA-MVS		78.57 130	77.90 150	79.35 100	87.24 71	80.71 107	86.16 111	64.03 134	62.63 201	73.49 117	73.60 184	76.12 188	73.83 84	88.49 95	84.93 106	91.36 84	78.78 145

test_part1		87.86 50	93.26 7	81.56 77	87.23 72	86.76 63	90.91 54	70.06 76	96.50 1	76.74 94	96.63 2	98.62 2	69.45 116	92.93 44	90.92 47	94.98 29	90.46 50

OMC-MVS		88.16 44	91.34 43	84.46 47	86.85 73	90.63 23	93.01 42	67.00 105	90.35 28	87.40 22	86.86 100	96.35 31	77.66 50	92.63 49	90.84 48	94.84 32	91.68 40

3Dnovator+	83.71 3	88.13 45	90.00 53	85.94 30	86.82 74	91.06 13	94.26 34	75.39 47	88.85 43	85.76 38	85.74 111	86.92 148	78.02 45	93.03 41	92.21 35	95.39 25	92.21 35

ETV-MVS		79.01 129	77.98 149	80.22 94	86.69 75	79.73 116	88.80 88	68.27 97	63.22 196	71.56 128	70.25 202	73.63 194	73.66 86	90.30 81	86.77 88	92.33 74	81.95 122

PHI-MVS		86.37 59	88.14 68	84.30 48	86.65 76	87.56 56	90.76 59	70.16 75	82.55 93	89.65 7	84.89 120	92.40 102	75.97 65	90.88 73	89.70 61	92.58 68	89.03 63

ACMH	78.40 12	88.94 39	92.62 17	84.65 43	86.45 77	87.16 60	91.47 49	68.79 90	95.49 3	89.74 6	93.55 20	98.50 3	77.96 46	94.14 32	89.57 64	93.49 51	89.94 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS-test		83.73 80	84.09 118	83.31 57	86.38 78	80.24 111	85.50 114	72.00 63	65.58 184	83.11 55	84.64 122	92.52 100	78.14 43	90.40 77	88.92 70	94.71 37	86.34 83

EG-PatchMatch MVS		84.35 75	87.55 73	80.62 89	86.38 78	82.24 96	86.75 107	64.02 135	84.24 81	78.17 91	89.38 69	95.03 65	78.78 37	89.95 84	86.33 91	89.59 105	85.65 89

IS_MVSNet		81.72 104	85.01 99	77.90 109	86.19 80	82.64 93	85.56 113	70.02 77	80.11 122	63.52 162	87.28 94	81.18 169	67.26 126	91.08 70	89.33 66	94.82 33	83.42 106

PCF-MVS	76.59 14	84.11 77	85.27 94	82.76 67	86.12 81	88.30 45	91.24 51	69.10 85	82.36 96	84.45 44	77.56 157	90.40 128	72.91 90	85.88 118	83.88 115	92.72 67	88.53 66
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		85.51 63	88.36 65	82.19 70	86.05 82	87.69 55	90.50 67	70.60 74	86.40 63	82.33 62	89.69 65	92.52 100	74.01 83	87.53 102	86.84 87	89.63 104	87.80 74

EPP-MVSNet		82.76 95	86.47 81	78.45 106	86.00 83	84.47 78	85.39 117	68.42 94	84.17 82	62.97 164	89.26 71	76.84 184	72.13 96	92.56 50	90.40 53	95.76 20	87.56 76

PLC	76.06 15	85.38 66	87.46 74	82.95 64	85.79 84	88.84 41	88.86 87	68.70 91	87.06 59	83.60 49	79.02 145	90.05 129	77.37 53	90.88 73	89.66 62	93.37 55	86.74 79
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSLP-MVS++		86.29 60	89.10 58	83.01 61	85.71 85	89.79 35	87.04 106	74.39 52	85.17 75	78.92 87	77.59 156	93.57 87	82.60 17	93.23 37	91.88 40	89.42 109	92.46 31

CS-MVS		83.23 87	85.14 97	81.00 81	85.59 86	79.28 120	89.80 77	63.29 144	73.02 150	75.70 101	85.28 114	92.81 96	77.09 54	91.92 52	87.93 77	94.53 39	85.76 87

Effi-MVS+-dtu		82.04 101	83.39 127	80.48 92	85.48 87	86.57 67	88.40 90	68.28 96	69.04 172	73.13 120	76.26 167	91.11 122	74.74 77	88.40 96	87.76 78	92.84 66	84.57 95

ECVR-MVS		79.67 119	84.40 109	74.16 134	85.29 88	79.56 118	81.16 145	73.13 59	84.65 80	56.08 179	88.38 82	86.14 152	60.49 153	89.78 85	85.59 99	88.79 116	76.68 153

v7n		87.11 53	90.46 51	83.19 59	85.22 89	83.69 84	90.03 76	68.20 98	91.01 20	86.71 34	94.80 11	98.46 5	77.69 49	91.10 68	85.98 94	91.30 86	88.19 68

MAR-MVS		81.98 102	82.92 129	80.88 83	85.18 90	85.85 70	89.13 84	69.52 79	71.21 161	82.25 64	71.28 194	88.89 140	69.69 111	88.71 91	86.96 83	89.52 106	87.57 75
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
abl_6				79.30 101	84.98 91	85.78 71	90.50 67	66.88 106	77.08 136	74.02 112	73.29 187	89.34 134	68.94 118			90.49 93	85.98 84

TAPA-MVS	78.00 13	85.88 61	88.37 64	82.96 63	84.69 92	88.62 43	90.62 60	64.22 130	89.15 40	88.05 15	78.83 149	93.71 84	76.20 63	90.11 83	88.22 75	94.00 44	89.97 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		81.92 103	83.87 120	79.66 97	84.64 93	79.87 113	89.75 78	65.90 116	76.12 140	75.87 99	84.62 123	92.23 105	71.96 98	86.83 110	83.60 118	89.83 102	83.81 102

SixPastTwentyTwo		89.14 30	92.19 32	85.58 33	84.62 94	82.56 94	90.53 65	71.93 65	91.95 13	85.89 36	94.22 15	97.25 21	85.42 5	95.73 12	91.71 41	95.08 28	91.89 38

MVS_111021_HR		83.95 78	86.10 86	81.44 78	84.62 94	80.29 110	90.51 66	68.05 99	84.07 84	80.38 77	84.74 121	91.37 119	74.23 79	90.37 79	87.25 82	90.86 92	84.59 94

ECVR-MVS1		79.31 126	84.20 115	73.60 136	84.55 96	80.37 109	79.63 159	73.23 58	82.64 92	55.98 180	87.50 89	86.85 149	59.61 157	90.35 80	86.46 90	88.58 122	75.26 161

CNLPA		85.50 64	88.58 60	81.91 72	84.55 96	87.52 57	90.89 55	63.56 140	88.18 48	84.06 45	83.85 127	91.34 120	76.46 60	91.27 63	89.00 69	91.96 77	88.88 64

Effi-MVS+		82.33 97	83.87 120	80.52 91	84.51 98	81.32 102	87.53 97	68.05 99	74.94 146	79.67 82	82.37 135	92.31 104	72.21 93	85.06 125	86.91 85	91.18 88	84.20 98

gm-plane-assit		71.56 169	69.99 184	73.39 139	84.43 99	73.21 164	90.42 71	51.36 200	84.08 83	76.00 98	91.30 48	37.09 226	59.01 159	73.65 188	70.24 187	79.09 180	60.37 201

RPSCF		88.05 47	92.61 18	82.73 68	84.24 100	88.40 44	90.04 75	66.29 109	91.46 14	82.29 63	88.93 76	96.01 40	79.38 32	95.15 21	94.90 6	94.15 42	93.40 20

FC-MVSNet-train		79.20 127	86.29 83	70.94 151	84.06 101	77.67 132	85.68 112	64.11 132	82.90 90	52.22 195	92.57 36	93.69 85	49.52 195	88.30 98	86.93 84	90.03 98	81.95 122

v1192		83.61 82	85.23 95	81.72 74	84.05 102	82.15 97	89.54 80	66.20 110	81.38 110	86.76 33	91.79 42	96.03 38	74.88 76	81.81 151	80.92 140	88.91 115	82.50 117

v1240		83.57 83	84.94 102	81.97 71	84.05 102	81.27 103	89.46 82	66.06 112	81.31 111	87.50 21	91.88 41	95.46 53	76.25 62	81.16 156	80.51 144	88.52 124	82.98 111

test20.03		69.91 173	76.20 164	62.58 189	84.01 104	67.34 184	75.67 183	65.88 117	79.98 123	40.28 213	82.65 131	89.31 135	39.63 208	77.41 172	73.28 177	69.98 197	63.40 192

Anonymous202405211			84.68 106		83.92 105	79.45 119	79.03 162	67.79 101	82.01 99		88.77 80	92.58 99	55.93 171	86.68 111	84.26 112	88.92 114	78.98 143

NR-MVSNet		82.89 92	87.43 75	77.59 112	83.91 106	83.59 85	87.10 103	78.35 20	80.64 117	68.85 143	92.67 33	96.50 26	54.19 180	87.19 108	88.68 71	93.16 61	82.75 114

Gipuma		86.47 58	89.25 57	83.23 58	83.88 107	78.78 125	85.35 118	68.42 94	92.69 11	89.03 12	91.94 38	96.32 34	81.80 22	94.45 27	86.86 86	90.91 91	83.69 103
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
v1921920		83.49 84	84.94 102	81.80 73	83.78 108	81.20 105	89.50 81	65.91 115	81.64 103	87.18 25	91.70 43	95.39 54	75.85 66	81.56 154	80.27 146	88.60 120	82.80 113

v1144		83.22 88	85.01 99	81.14 79	83.76 109	81.60 100	88.95 86	65.58 120	81.89 100	85.80 37	91.68 44	95.84 43	74.04 82	82.12 148	80.56 143	88.70 119	81.41 125

Vis-MVSNet (Re-imp)		76.15 144	80.84 138	70.68 152	83.66 110	74.80 159	81.66 143	69.59 78	80.48 120	46.94 204	87.44 91	80.63 171	53.14 185	86.87 109	84.56 111	89.12 111	71.12 172

v144192		83.43 85	84.97 101	81.63 76	83.43 111	81.23 104	89.42 83	66.04 114	81.45 109	86.40 35	91.46 46	95.70 48	75.76 68	82.14 147	80.23 147	88.74 117	82.57 116

TinyColmap		83.79 79	86.12 85	81.07 80	83.42 112	81.44 101	85.42 116	68.55 93	88.71 45	89.46 8	87.60 88	92.72 97	70.34 110	89.29 88	81.94 133	89.20 110	81.12 127

TransMVSNet (Re)		79.05 128	86.66 78	70.18 157	83.32 113	75.99 147	77.54 167	63.98 136	90.68 25	55.84 182	94.80 11	96.06 37	53.73 183	86.27 115	83.22 125	86.65 139	79.61 141

v10		83.17 90	85.22 96	80.78 84	83.26 114	82.99 89	88.66 89	66.49 108	79.24 128	83.60 49	91.46 46	95.47 52	74.12 80	82.60 146	80.66 141	88.53 123	84.11 100

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 11	83.19 115	86.35 68	93.60 38	78.79 19	95.48 4	91.79 2	93.08 27	97.21 22	86.34 3	97.06 2	96.27 3	95.46 23	95.56 3
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
canonicalmvs		81.22 110	86.04 88	75.60 121	83.17 116	83.18 88	80.29 151	65.82 118	85.97 68	67.98 150	77.74 155	91.51 117	65.17 137	88.62 93	86.15 93	91.17 89	89.09 61

FPMVS		81.56 105	84.04 119	78.66 104	82.92 117	75.96 148	86.48 110	65.66 119	84.67 79	71.47 129	77.78 154	83.22 163	77.57 51	91.24 64	90.21 54	87.84 129	85.21 91

DCV-MVSNet		80.04 115	85.67 92	73.48 138	82.91 118	81.11 106	80.44 150	66.06 112	85.01 76	62.53 167	78.84 148	94.43 78	58.51 161	88.66 92	85.91 95	90.41 94	85.73 88

MVS_111021_LR		83.20 89	85.33 93	80.73 87	82.88 119	78.23 129	89.61 79	65.23 122	82.08 98	81.19 74	85.31 113	92.04 112	75.22 71	89.50 86	85.90 96	90.24 95	84.23 97

Anonymous20231211		79.37 123	85.78 90	71.89 145	82.87 120	79.66 117	78.77 164	63.93 138	83.36 86	59.39 171	90.54 53	94.66 72	56.46 168	87.38 103	84.12 113	89.92 100	80.74 129

v2v482		82.20 99	84.26 112	79.81 96	82.67 121	80.18 112	87.67 96	63.96 137	81.69 102	84.73 42	91.27 49	96.33 33	72.05 97	81.94 150	79.56 150	87.79 130	78.84 144

v8		82.20 99	84.56 108	79.45 98	82.42 122	81.65 99	87.26 100	64.27 129	79.36 127	81.70 71	91.04 52	95.75 46	73.30 89	82.82 142	79.18 153	87.74 131	82.09 120

MSDG		81.39 108	84.23 114	78.09 108	82.40 123	82.47 95	85.31 120	60.91 162	79.73 125	80.26 78	86.30 103	88.27 143	69.67 112	87.20 107	84.98 105	89.97 99	80.67 130

Fast-Effi-MVS+		81.42 106	83.82 122	78.62 105	82.24 124	80.62 108	87.72 95	63.51 141	73.01 151	74.75 108	83.80 128	92.70 98	73.44 88	88.15 100	85.26 102	90.05 97	83.17 107

PVSNet_Blended_VisFu		83.00 91	84.16 116	81.65 75	82.17 125	86.01 69	88.03 92	71.23 70	76.05 141	79.54 83	83.88 126	83.44 160	77.49 52	87.38 103	84.93 106	91.41 83	87.40 77

pmmvs6		80.46 112	88.34 66	71.26 147	81.96 126	77.51 133	77.54 167	68.83 89	93.72 8	55.92 181	93.94 19	98.03 10	55.94 170	89.21 89	85.61 98	87.36 135	80.38 132

IterMVS-LS		79.79 117	82.56 131	76.56 118	81.83 127	77.85 131	79.90 155	69.42 83	78.93 130	71.21 130	90.47 54	85.20 158	70.86 107	80.54 161	80.57 142	86.15 146	84.36 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		73.07 163	77.02 156	68.46 167	81.62 128	72.89 165	79.56 160	70.78 73	69.56 167	52.52 192	77.37 159	81.12 170	42.60 203	84.20 135	83.93 114	83.65 166	70.07 177
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		72.68 165	75.21 171	69.73 159	81.48 129	69.04 179	70.48 196	76.67 36	86.92 60	67.80 152	88.06 85	64.67 202	42.12 205	77.60 171	73.65 176	79.81 177	66.57 184

USDC		81.39 108	83.07 128	79.43 99	81.48 129	78.95 124	82.62 136	66.17 111	87.45 55	90.73 4	82.40 134	93.65 86	66.57 131	83.63 138	77.97 156	89.00 113	77.45 152

casdiffmvs		79.93 116	84.11 117	75.05 126	81.41 131	78.99 123	82.95 133	62.90 149	81.53 105	68.60 147	91.94 38	96.03 38	65.84 135	82.89 141	77.07 164	88.59 121	80.34 136

tfpnnormal		77.16 136	84.26 112	68.88 165	81.02 132	75.02 155	76.52 174	63.30 143	87.29 56	52.40 193	91.24 50	93.97 81	54.85 177	85.46 122	81.08 138	85.18 159	75.76 158

thres600view7		74.34 156	78.43 146	69.56 161	80.47 133	76.28 145	78.65 165	62.56 151	77.39 134	52.53 191	74.03 181	76.78 185	55.90 172	85.06 125	85.19 103	87.25 136	74.29 163

OpenMVS	75.38 16	78.44 131	81.39 137	74.99 129	80.46 134	79.85 114	79.99 153	58.31 176	77.34 135	73.85 114	77.19 160	82.33 167	68.60 120	84.67 132	81.95 132	88.72 118	86.40 82

pm-mvs1		78.21 132	85.68 91	69.50 162	80.38 135	75.73 150	76.25 175	65.04 123	87.59 53	54.47 186	93.16 26	95.99 42	54.20 179	86.37 114	82.98 128	86.64 140	77.96 150

v148		79.33 125	82.32 132	75.84 120	80.14 136	75.74 149	81.98 140	57.06 179	81.51 107	79.36 85	89.42 67	96.42 29	71.32 101	81.54 155	75.29 173	85.20 158	76.32 154

pmmvs-eth3d		79.64 120	82.06 134	76.83 115	80.05 137	72.64 166	87.47 98	66.59 107	80.83 116	73.50 116	89.32 70	93.20 92	67.78 123	80.78 159	81.64 136	85.58 156	76.01 155

testgi		68.20 182	76.05 165	59.04 195	79.99 138	67.32 185	81.16 145	51.78 198	84.91 77	39.36 214	73.42 185	95.19 58	32.79 214	76.54 178	70.40 186	69.14 200	64.55 188

DI_MVS_plusplus_trai		77.64 134	79.64 141	75.31 124	79.87 139	76.89 141	81.55 144	63.64 139	76.21 139	72.03 125	85.59 112	82.97 164	66.63 130	79.27 167	77.78 158	88.14 127	78.76 146

Fast-Effi-MVS+-dtu		76.92 137	77.18 155	76.62 117	79.55 140	79.17 121	84.80 122	77.40 30	64.46 191	68.75 145	70.81 198	86.57 150	63.36 148	81.74 152	81.76 134	85.86 152	75.78 157

thres400		73.13 162	76.99 158	68.62 166	79.46 141	74.93 157	77.23 169	61.23 160	75.54 142	52.31 194	72.20 189	77.10 183	54.89 175	82.92 140	82.62 130	86.57 142	73.66 168

QAPM		80.43 113	84.34 110	75.86 119	79.40 142	82.06 98	79.86 156	61.94 155	83.28 87	74.73 109	81.74 137	85.44 156	70.97 105	84.99 130	84.71 110	88.29 125	88.14 70

DELS-MVS		79.71 118	83.74 123	75.01 128	79.31 143	82.68 92	84.79 123	60.06 168	75.43 144	69.09 141	86.13 105	89.38 133	67.16 127	85.12 124	83.87 116	89.65 103	83.57 104
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
3Dnovator	79.41 10	82.21 98	86.07 87	77.71 110	79.31 143	84.61 77	87.18 101	61.02 161	85.65 69	76.11 97	85.07 118	85.38 157	70.96 106	87.22 106	86.47 89	91.66 80	88.12 71

ET-MVSNet_ETH3D		74.71 154	74.19 174	75.31 124	79.22 145	75.29 153	82.70 135	64.05 133	65.45 186	70.96 133	77.15 161	57.70 214	65.89 134	84.40 134	81.65 135	89.03 112	77.67 151

test-LLR		62.15 198	59.46 214	65.29 185	79.07 146	52.66 209	69.46 202	62.93 147	50.76 218	53.81 188	63.11 212	58.91 210	52.87 186	66.54 207	62.34 199	73.59 185	61.87 197

test0.0.03 1		61.79 200	65.33 196	57.65 198	79.07 146	64.09 193	68.51 205	62.93 147	61.59 204	33.71 217	61.58 214	71.58 198	33.43 213	70.95 196	68.68 191	68.26 202	58.82 204

baseline1		69.62 175	73.55 178	65.02 187	78.95 148	70.39 172	71.38 195	62.03 154	70.97 162	47.95 203	78.47 152	68.19 200	47.77 199	79.65 166	76.94 166	82.05 173	70.27 175

MVS_Test		76.72 139	79.40 143	73.60 136	78.85 149	74.99 156	79.91 154	61.56 157	69.67 166	72.44 121	85.98 108	90.78 124	63.50 146	78.30 169	75.74 171	85.33 157	80.31 137

FMVSNet1		78.20 133	84.83 104	70.46 155	78.62 150	79.03 122	77.90 166	67.53 104	83.02 89	55.10 184	87.19 96	93.18 93	55.65 173	85.57 119	83.39 121	87.98 128	82.40 118

GA-MVS		75.01 153	76.39 161	73.39 139	78.37 151	75.66 151	80.03 152	58.40 175	70.51 163	75.85 100	83.24 129	76.14 187	63.75 142	77.28 173	76.62 167	83.97 165	75.30 160

thres200		72.41 166	76.00 166	68.21 169	78.28 152	76.28 145	74.94 185	62.56 151	72.14 158	51.35 199	69.59 204	76.51 186	54.89 175	85.06 125	80.51 144	87.25 136	71.92 171

EPNet_dtu		71.90 168	73.03 180	70.59 153	78.28 152	61.64 197	82.44 137	64.12 131	63.26 195	69.74 137	71.47 192	82.41 165	51.89 192	78.83 168	78.01 155	77.07 182	75.60 159
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs4		75.92 146	77.48 154	74.10 135	78.21 154	70.94 170	84.06 126	64.78 125	75.13 145	68.47 148	84.12 125	83.32 161	64.74 140	75.93 181	79.14 154	84.31 163	73.77 166

PM-MVS		80.42 114	83.63 124	76.67 116	78.04 155	72.37 168	87.14 102	60.18 167	80.13 121	71.75 127	86.12 106	93.92 83	77.08 55	86.56 112	85.12 104	85.83 153	81.18 126

thres100view900		69.86 174	72.97 181	66.24 178	77.97 156	72.49 167	73.29 189	59.12 171	66.81 177	50.82 200	67.30 206	75.67 190	50.54 194	78.24 170	79.40 151	85.71 155	70.88 173

tfpn200view9		72.01 167	75.40 169	68.06 170	77.97 156	76.44 143	77.04 171	62.67 150	66.81 177	50.82 200	67.30 206	75.67 190	52.46 191	85.06 125	82.64 129	87.41 134	73.86 165

Vis-MVSNet		83.32 86	88.12 69	77.71 110	77.91 158	83.44 87	90.58 61	69.49 81	81.11 113	67.10 154	89.85 62	91.48 118	71.71 100	91.34 62	89.37 65	89.48 107	90.26 52
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchMatch-RL		76.05 145	76.64 159	75.36 123	77.84 159	69.87 176	81.09 147	63.43 142	71.66 159	68.34 149	71.70 190	81.76 168	74.98 75	84.83 131	83.44 120	86.45 144	73.22 169

CANet_DTU		75.04 152	78.45 145	71.07 148	77.27 160	77.96 130	83.88 128	58.00 177	64.11 192	68.67 146	75.65 174	88.37 142	53.92 182	82.05 149	81.11 137	84.67 161	79.88 139

MS-PatchMatch		71.18 172	73.99 176	67.89 173	77.16 161	71.76 169	77.18 170	56.38 181	67.35 175	55.04 185	74.63 179	75.70 189	62.38 149	76.62 176	75.97 170	79.22 179	75.90 156

new-patchmatchnet		62.59 197	73.79 177	49.53 211	76.98 162	53.57 207	53.46 219	54.64 186	85.43 72	28.81 218	91.94 38	96.41 30	25.28 216	76.80 174	53.66 214	57.99 212	58.69 205

GBi-Net		73.17 160	77.64 151	67.95 171	76.76 163	77.36 135	75.77 179	64.57 126	62.99 198	51.83 196	76.05 168	77.76 180	52.73 188	85.57 119	83.39 121	86.04 148	80.37 133

PVSNet_BlendedMVS		76.45 142	78.12 147	74.49 132	76.76 163	78.46 126	79.65 157	63.26 145	65.42 187	73.15 118	75.05 177	88.96 137	66.51 132	82.73 144	77.66 159	87.61 132	78.60 147

PVSNet_Blended		76.45 142	78.12 147	74.49 132	76.76 163	78.46 126	79.65 157	63.26 145	65.42 187	73.15 118	75.05 177	88.96 137	66.51 132	82.73 144	77.66 159	87.61 132	78.60 147

test1		73.17 160	77.64 151	67.95 171	76.76 163	77.36 135	75.77 179	64.57 126	62.99 198	51.83 196	76.05 168	77.76 180	52.73 188	85.57 119	83.39 121	86.04 148	80.37 133

FMVSNet2		74.43 155	79.70 140	68.27 168	76.76 163	77.36 135	75.77 179	65.36 121	72.28 155	52.97 190	81.92 136	85.61 155	52.73 188	80.66 160	79.73 149	86.04 148	80.37 133

IB-MVS	71.28 17	75.21 151	77.00 157	73.12 142	76.76 163	77.45 134	83.05 131	58.92 173	63.01 197	64.31 161	59.99 215	87.57 146	68.64 119	86.26 116	82.34 131	87.05 138	82.36 119
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
thisisatest0515		81.18 111	84.32 111	77.52 114	76.73 169	74.84 158	85.06 121	61.37 158	81.05 114	73.95 113	88.79 79	89.25 136	75.49 70	85.98 117	84.78 108	92.53 71	85.56 90

IterMVS-SCA-FT		77.23 135	79.18 144	74.96 130	76.67 170	79.85 114	75.58 184	61.34 159	73.10 149	73.79 115	86.23 104	79.61 173	79.00 36	80.28 163	75.50 172	83.41 170	79.70 140

FC-MVSNet-test		75.91 147	83.59 125	66.95 176	76.63 171	69.07 178	85.33 119	64.97 124	84.87 78	41.95 209	93.17 25	87.04 147	47.78 198	91.09 69	85.56 100	85.06 160	74.34 162

Anonymous20231206		67.28 184	73.41 179	60.12 194	76.45 172	63.61 195	74.21 187	56.52 180	76.35 137	42.23 208	75.81 173	90.47 127	41.51 206	74.52 182	69.97 188	69.83 198	63.17 193

baseline2		68.71 180	68.34 189	69.14 163	75.69 173	69.70 177	76.60 173	55.53 184	60.13 206	62.07 169	66.76 208	60.35 207	60.77 152	76.53 179	74.03 175	84.19 164	70.88 173

diffmvs		76.74 138	81.61 136	71.06 149	75.64 174	74.45 161	80.68 149	57.57 178	77.48 133	67.62 153	88.95 75	93.94 82	61.98 150	79.74 164	76.18 168	82.85 171	80.50 131

tttt0517		75.86 148	76.23 163	75.42 122	75.55 175	74.06 162	82.73 134	60.31 164	69.24 168	70.24 136	79.18 144	58.79 212	72.17 94	84.49 133	83.08 126	91.54 81	84.80 92

thisisatest0530		75.54 150	75.95 167	75.05 126	75.08 176	73.56 163	82.15 139	60.31 164	69.17 169	69.32 139	79.02 145	58.78 213	72.17 94	83.88 136	83.08 126	91.30 86	84.20 98

FMVSNet3		71.40 171	75.20 172	66.97 175	75.00 177	76.59 142	74.29 186	64.57 126	62.99 198	51.83 196	76.05 168	77.76 180	51.49 193	76.58 177	77.03 165	84.62 162	79.43 142

tpm cat1		64.79 191	62.74 205	67.17 174	74.61 178	65.91 189	76.18 176	59.32 170	64.88 190	66.41 157	71.21 195	53.56 222	59.17 158	61.53 213	58.16 207	67.33 203	63.95 189

UGNet		79.62 121	85.91 89	72.28 144	73.52 179	83.91 80	86.64 108	69.51 80	79.85 124	62.57 166	85.82 110	89.63 130	53.18 184	88.39 97	87.35 81	88.28 126	86.43 81
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
our_test_3					73.27 180	70.91 171	83.26 129

HyFIR lowres test		73.29 159	74.14 175	72.30 143	73.08 181	78.33 128	83.12 130	62.41 153	63.81 193	62.13 168	76.67 164	78.50 177	71.09 103	74.13 185	77.47 162	81.98 174	70.10 176

MIMVSNet1		73.40 158	81.85 135	63.55 188	72.90 182	64.37 192	84.58 124	53.60 192	90.84 21	53.92 187	87.75 87	96.10 35	45.31 201	85.37 123	79.32 152	70.98 196	69.18 181

CostFormer		66.81 186	66.94 192	66.67 177	72.79 183	68.25 181	79.55 161	55.57 183	65.52 185	62.77 165	76.98 162	60.09 208	56.73 167	65.69 209	62.35 198	72.59 188	69.71 178

CR-MVSNet		69.56 176	68.34 189	70.99 150	72.78 184	67.63 182	64.47 208	67.74 102	59.93 207	72.30 122	80.10 140	56.77 216	65.04 138	71.64 193	72.91 179	83.61 168	69.40 179

CVMVSNet		75.65 149	77.62 153	73.35 141	71.95 185	69.89 175	83.04 132	60.84 163	69.12 170	68.76 144	79.92 143	78.93 176	73.64 87	81.02 157	81.01 139	81.86 175	83.43 105

IterMVS		73.62 157	76.53 160	70.23 156	71.83 186	77.18 139	80.69 148	53.22 194	72.23 156	66.62 156	85.21 115	78.96 175	69.54 114	76.28 180	71.63 183	79.45 178	74.25 164
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		67.02 185	63.99 200	70.56 154	71.55 187	67.63 182	75.81 177	69.44 82	59.93 207	63.24 163	64.32 210	47.51 225	59.68 155	70.37 198	69.64 189	83.64 167	68.49 182

dps		65.14 188	64.50 198	65.89 183	71.41 188	65.81 190	71.44 194	61.59 156	58.56 210	61.43 170	75.45 175	52.70 223	58.06 163	69.57 200	64.65 196	71.39 193	64.77 187

MDTV_nov1_ep13_2view		72.96 164	75.59 168	69.88 158	71.15 189	64.86 191	82.31 138	54.45 188	76.30 138	78.32 90	86.52 101	91.58 115	61.35 151	76.80 174	66.83 194	71.70 189	66.26 185

TAMVS		63.02 192	69.30 186	55.70 202	70.12 190	56.89 203	69.63 200	45.13 206	70.23 164	38.00 215	77.79 153	75.15 192	42.60 203	74.48 183	72.81 181	68.70 201	57.75 208

tpm		62.79 194	63.25 202	62.26 192	70.09 191	53.78 206	71.65 193	47.31 204	65.72 183	76.70 95	80.62 139	56.40 219	48.11 197	64.20 211	58.54 205	59.70 209	63.47 191

V42		79.59 122	83.59 125	74.93 131	69.61 192	77.05 140	86.59 109	55.84 182	78.42 132	77.29 93	89.84 63	95.08 63	74.12 80	83.05 139	80.11 148	86.12 147	81.59 124

PatchmatchNet		64.81 190	63.74 201	66.06 182	69.21 193	58.62 201	73.16 190	60.01 169	65.92 181	66.19 158	76.27 166	59.09 209	60.45 154	66.58 206	61.47 204	67.33 203	58.24 206
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 1792x2688		68.80 179	71.09 182	66.13 180	69.11 194	68.89 180	78.98 163	54.68 185	61.63 203	56.69 176	71.56 191	78.39 178	67.69 124	72.13 192	72.01 182	69.63 199	73.02 170

MIMVSNet		63.02 192	69.02 187	56.01 200	68.20 195	59.26 200	70.01 199	53.79 191	71.56 160	41.26 212	71.38 193	82.38 166	36.38 210	71.43 195	67.32 193	66.45 205	59.83 203

CMPMVS	55.74 18	71.56 169	76.26 162	66.08 181	68.11 196	63.91 194	63.17 210	50.52 202	68.79 173	75.49 102	70.78 199	85.67 154	63.54 145	81.58 153	77.20 163	75.63 183	85.86 85
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SCA		68.54 181	67.52 191	69.73 159	67.79 197	75.04 154	76.96 172	68.94 88	66.41 179	67.86 151	74.03 181	60.96 205	65.55 136	68.99 201	65.67 195	71.30 194	61.54 200

EU-MVSNet		76.48 141	80.53 139	71.75 146	67.62 198	70.30 173	81.74 142	54.06 190	75.47 143	71.01 132	80.10 140	93.17 94	73.67 85	83.73 137	77.85 157	82.40 172	83.07 108

tpmrst		59.42 202	60.02 212	58.71 196	67.56 199	53.10 208	66.99 206	51.88 197	63.80 194	57.68 174	76.73 163	56.49 218	48.73 196	56.47 217	55.55 210	59.43 210	58.02 207

pmmvs5		68.91 178	74.35 173	62.56 190	67.45 200	66.78 186	71.70 192	51.47 199	67.17 176	56.25 178	82.41 133	88.59 141	47.21 200	73.21 191	74.23 174	81.30 176	68.03 183

MDTV_nov1_ep13		64.96 189	64.77 197	65.18 186	67.08 201	62.46 196	75.80 178	51.10 201	62.27 202	69.74 137	74.12 180	62.65 203	55.64 174	68.19 203	62.16 202	71.70 189	61.57 199

E-PMN		59.07 204	62.79 204	54.72 203	67.01 202	47.81 216	60.44 214	43.40 207	72.95 152	44.63 206	70.42 201	73.17 195	58.73 160	80.97 158	51.98 215	54.14 215	42.26 217

pmnet_mix02		62.60 196	70.81 183	53.02 207	66.56 203	50.44 213	62.81 211	46.84 205	79.13 129	43.76 207	87.45 90	90.75 125	39.85 207	70.48 197	57.09 208	58.27 211	60.32 202

baseline		69.33 177	75.37 170	62.28 191	66.54 204	66.67 187	73.95 188	48.07 203	66.10 180	59.26 172	82.45 132	86.30 151	54.44 178	74.42 184	73.25 178	71.42 192	78.43 149

N_pmnet		54.95 211	65.90 194	42.18 212	66.37 205	43.86 219	57.92 216	39.79 211	79.54 126	17.24 223	86.31 102	87.91 144	25.44 215	64.68 210	51.76 216	46.33 218	47.23 215

MVSTER		68.08 183	69.73 185	66.16 179	66.33 206	70.06 174	75.71 182	52.36 196	55.18 215	58.64 173	70.23 203	56.72 217	57.34 165	79.68 165	76.03 169	86.61 141	80.20 138

EMVS		58.97 205	62.63 206	54.70 204	66.26 207	48.71 214	61.74 212	42.71 208	72.80 154	46.00 205	73.01 188	71.66 196	57.91 164	80.41 162	50.68 217	53.55 216	41.11 218

anonymousdsp		85.62 62	90.53 49	79.88 95	64.64 208	76.35 144	96.28 13	53.53 193	85.63 70	81.59 72	92.81 31	97.71 14	86.88 2	94.56 26	92.83 25	96.35 6	93.84 9

EPMVS		56.62 208	59.77 213	52.94 208	62.41 209	50.55 212	60.66 213	52.83 195	65.15 189	41.80 210	77.46 158	57.28 215	42.68 202	59.81 215	54.82 211	57.23 213	53.35 211

FMVSNet5		56.37 209	60.14 211	51.98 210	60.83 210	59.58 199	66.85 207	42.37 209	52.68 217	41.33 211	47.09 218	54.68 220	35.28 211	73.88 186	70.77 185	65.24 206	62.26 196

ADS-MVSNet		56.89 207	61.09 208	52.00 209	59.48 211	48.10 215	58.02 215	54.37 189	72.82 153	49.19 202	75.32 176	65.97 201	37.96 209	59.34 216	54.66 212	52.99 217	51.42 213

new_pmnet		52.29 212	63.16 203	39.61 214	58.89 212	44.70 218	48.78 221	34.73 214	65.88 182	17.85 222	73.42 185	80.00 172	23.06 217	67.00 205	62.28 201	54.36 214	48.81 214

MVS-HIRNet		59.74 201	58.74 217	60.92 193	57.74 213	45.81 217	56.02 217	58.69 174	55.69 213	65.17 159	70.86 197	71.66 196	56.75 166	61.11 214	53.74 213	71.17 195	52.28 212

PatchT		66.25 187	66.76 193	65.67 184	55.87 214	60.75 198	70.17 197	59.00 172	59.80 209	72.30 122	78.68 150	54.12 221	65.04 138	71.64 193	72.91 179	71.63 191	69.40 179

test-mter		59.39 203	61.59 207	56.82 199	53.21 215	54.82 205	73.12 191	26.57 218	53.19 216	56.31 177	64.71 209	60.47 206	56.36 169	68.69 202	64.27 197	75.38 184	65.00 186

CHOSEN 280x420		56.32 210	58.85 216	53.36 206	51.63 216	39.91 220	69.12 204	38.61 212	56.29 212	36.79 216	48.84 217	62.59 204	63.39 147	73.61 189	67.66 192	60.61 207	63.07 194

TESTMET0.1,1		57.21 206	59.46 214	54.60 205	50.95 217	52.66 209	69.46 202	26.91 217	50.76 218	53.81 188	63.11 212	58.91 210	52.87 186	66.54 207	62.34 199	73.59 185	61.87 197

pmmvs3		62.72 195	68.71 188	55.74 201	50.74 218	57.10 202	70.05 198	28.82 216	61.57 205	57.39 175	71.19 196	85.73 153	53.96 181	73.36 190	69.43 190	73.47 187	62.55 195

MDA-MVSNet-bldmvs		76.51 140	82.87 130	69.09 164	50.71 219	74.72 160	84.05 127	60.27 166	81.62 104	71.16 131	88.21 84	91.58 115	69.62 113	92.78 46	77.48 161	78.75 181	73.69 167

PMMVS		61.98 199	65.61 195	57.74 197	45.03 220	51.76 211	69.54 201	35.05 213	55.49 214	55.32 183	68.23 205	78.39 178	58.09 162	70.21 199	71.56 184	83.42 169	63.66 190

PMMVS2		48.13 214	64.06 199	29.55 215	44.06 221	36.69 221	51.95 220	29.97 215	74.75 147	8.90 225	76.02 171	91.24 121	7.53 219	73.78 187	55.91 209	34.87 220	40.01 219

MVE	41.12 19	51.80 213	60.92 209	41.16 213	35.21 222	34.14 222	48.45 222	41.39 210	69.11 171	19.53 221	63.33 211	73.80 193	63.56 144	67.19 204	61.51 203	38.85 219	57.38 209
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				13.54 218	16.73 223	6.42 224	8.49 225	2.36 221	28.69 222	27.44 219	18.40 221	13.51 228	3.70 220	33.23 218	36.26 218	22.54 223

test_method		22.69 216	26.99 218	17.67 217	2.13 224	4.31 225	27.50 223	4.53 220	37.94 220	24.52 220	36.20 220	51.40 224	15.26 218	29.86 219	17.09 219	32.07 221	12.16 220

test123		1.06 217	1.41 219	0.64 219	0.39 225	0.48 226	0.52 228	0.25 223	1.11 224	1.37 227	2.01 223	1.98 229	0.87 221	1.43 221	1.27 220	0.46 225	1.62 222

testmvs		0.93 218	1.37 220	0.41 220	0.36 226	0.36 227	0.62 227	0.39 222	1.48 223	0.18 228	2.41 222	1.31 230	0.41 222	1.25 222	1.08 221	0.48 224	1.68 221

GG-mvs-BLEND		41.63 215	60.36 210	19.78 216	0.14 227	66.04 188	55.66 218	0.17 224	57.64 211	2.42 226	51.82 216	69.42 199	0.28 223	64.11 212	58.29 206	60.02 208	55.18 210

uanet_test		0.00 219	0.00 221	0.00 221	0.00 228	0.00 228	0.00 229	0.00 225	0.00 225	0.00 229	0.00 224	0.00 231	0.00 224	0.00 223	0.00 222	0.00 226	0.00 223

sosnet-low-res		0.00 219	0.00 221	0.00 221	0.00 228	0.00 228	0.00 229	0.00 225	0.00 225	0.00 229	0.00 224	0.00 231	0.00 224	0.00 223	0.00 222	0.00 226	0.00 223

sosnet		0.00 219	0.00 221	0.00 221	0.00 228	0.00 228	0.00 229	0.00 225	0.00 225	0.00 229	0.00 224	0.00 231	0.00 224	0.00 223	0.00 222	0.00 226	0.00 223

RE-MVS-def										87.10 29

9.14												89.43 132

MTAPA										89.37 9		94.85 68

MTMP										90.54 5		95.16 60

Patchmatch-RL test							4.13 226

NP-MVS									78.65 131

Patchmtry						56.88 204	64.47 208	67.74 102		72.30 122

DeepMVS_CX						17.78 223	20.40 224	6.69 219	31.41 221	9.80 224	38.61 219	34.88 227	33.78 212	28.41 220		23.59 222	45.77 216

High-resolution multi-view benchmark