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.

MCST-MVS		93.81 17	94.06 19	93.53 18	96.79 24	96.85 21	95.95 14	91.69 17	92.20 27	87.17 33	90.83 28	93.41 7	91.96 15	94.49 26	93.50 32	97.61 1	97.12 23

xxxxxxxxxxxxxcwj		92.95 25	91.88 34	94.20 9	96.75 25	97.07 12	95.82 19	92.60 7	93.98 13	91.09 9	95.89 6	71.01 130	91.93 16	94.40 28	93.56 29	97.04 2	97.27 17

SF-MVS		94.61 8	94.96 10	94.20 9	96.75 25	97.07 12	95.82 19	92.60 7	93.98 13	91.09 9	95.89 6	92.54 13	91.93 16	94.40 28	93.56 29	97.04 2	97.27 17

DVP-MVS++		95.79 1	96.42 1	95.06 1	97.84 2	98.17 2	97.03 4	92.84 3	96.68 1	92.83 3	95.90 5	94.38 4	92.90 5	95.98 2	94.85 5	96.93 4	98.99 1

SED-MVS		95.61 2	96.36 2	94.73 3	96.84 20	98.15 3	97.08 3	92.92 2	95.64 3	91.84 5	95.98 4	95.33 1	92.83 7	96.00 1	94.94 3	96.90 5	98.45 3

DVP-MVS		95.56 3	96.26 3	94.73 3	96.93 17	98.19 1	96.62 7	92.81 5	96.15 2	91.73 6	95.01 8	95.31 2	93.41 1	95.95 3	94.77 8	96.90 5	98.46 2
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
DPE-MVS		95.53 4	96.13 4	94.82 2	96.81 23	98.05 4	97.42 1	93.09 1	94.31 9	91.49 7	97.12 1	95.03 3	93.27 3	95.55 6	94.58 12	96.86 7	98.25 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + GP.		92.71 29	93.91 21	91.30 36	91.96 75	96.00 42	93.43 42	87.94 42	92.53 23	86.27 41	93.57 16	91.94 19	91.44 26	93.29 46	92.89 46	96.78 8	97.15 22

DROMVSNet		89.96 49	90.77 45	89.01 58	90.54 92	95.15 58	91.34 62	81.43 108	85.27 64	83.08 56	82.83 49	87.22 50	90.97 31	94.79 18	93.38 36	96.73 9	96.71 34

ETV-MVS		89.22 54	89.76 51	88.60 64	91.60 79	94.61 69	89.48 83	83.46 87	85.20 66	81.58 65	82.75 50	82.59 67	88.80 42	94.57 24	93.28 40	96.68 10	95.31 59

APDe-MVS		95.23 5	95.69 6	94.70 5	97.12 11	97.81 6	97.19 2	92.83 4	95.06 6	90.98 11	96.47 2	92.77 11	93.38 2	95.34 9	94.21 16	96.68 10	98.17 5

MVS_0304		90.88 41	91.35 39	90.34 43	93.91 53	96.79 24	94.49 35	86.54 51	86.57 58	82.85 59	81.68 57	89.70 34	87.57 58	94.64 22	93.93 21	96.67 12	96.15 44

3Dnovator	85.17 5	90.48 43	89.90 50	91.16 38	94.88 44	95.74 49	93.82 38	85.36 58	89.28 46	87.81 29	74.34 96	87.40 49	88.56 46	93.07 49	93.74 26	96.53 13	95.71 50

TSAR-MVS + MP.		94.48 11	94.97 9	93.90 14	95.53 38	97.01 16	96.69 6	90.71 25	94.24 10	90.92 12	94.97 9	92.19 16	93.03 4	94.83 16	93.60 27	96.51 14	97.97 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS		90.34 44	90.58 46	90.07 46	93.11 62	95.82 47	90.57 67	83.62 78	87.07 56	85.35 43	82.98 48	83.47 62	91.37 28	94.94 13	93.37 38	96.37 15	96.41 39

MSP-MVS		95.12 6	95.83 5	94.30 6	96.82 22	97.94 5	96.98 5	92.37 12	95.40 4	90.59 14	96.16 3	93.71 6	92.70 8	94.80 17	94.77 8	96.37 15	97.99 8
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
QAPM		89.49 52	89.58 53	89.38 55	94.73 46	95.94 43	92.35 50	85.00 61	85.69 63	80.03 76	76.97 81	87.81 47	87.87 53	92.18 64	92.10 54	96.33 17	96.40 41

MVS_111021_HR		90.56 42	91.29 40	89.70 51	94.71 47	95.63 50	91.81 58	86.38 52	87.53 54	81.29 67	87.96 33	85.43 54	87.69 55	93.90 36	92.93 44	96.33 17	95.69 51

test1111		84.86 92	84.21 98	85.61 86	91.75 78	95.14 59	88.63 101	84.57 64	81.88 87	71.21 115	65.66 145	68.51 142	81.19 98	93.74 41	92.68 50	96.31 19	91.86 127

CANet		91.33 39	91.46 37	91.18 37	95.01 41	96.71 25	93.77 39	87.39 47	87.72 53	87.26 32	81.77 55	89.73 33	87.32 62	94.43 27	93.86 22	96.31 19	96.02 46

APD-MVS		94.37 12	94.47 16	94.26 7	97.18 9	96.99 17	96.53 8	92.68 6	92.45 25	89.96 18	94.53 12	91.63 21	92.89 6	94.58 23	93.82 23	96.31 19	97.26 19
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test2506		85.20 87	84.11 99	86.47 78	91.84 76	95.28 54	89.18 86	84.49 65	82.59 77	75.34 97	74.66 94	58.07 189	81.68 94	93.76 38	92.71 48	96.28 22	91.71 130

ECVR-MVS		85.25 86	84.47 95	86.16 81	91.84 76	95.28 54	89.18 86	84.49 65	82.59 77	73.49 106	66.12 139	69.28 138	81.68 94	93.76 38	92.71 48	96.28 22	91.58 137

SteuartSystems-ACMMP		94.06 14	94.65 12	93.38 20	96.97 16	97.36 9	96.12 10	91.78 15	92.05 29	87.34 31	94.42 13	90.87 25	91.87 20	95.47 8	94.59 11	96.21 24	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		92.05 33	93.74 22	90.08 45	94.96 42	97.06 14	93.11 46	87.71 45	90.71 38	80.78 72	92.40 23	91.03 23	87.68 56	94.32 30	94.48 13	96.21 24	96.16 43

CNVR-MVS		94.37 12	94.65 12	94.04 12	97.29 7	97.11 11	96.00 11	92.43 11	93.45 17	89.85 20	90.92 26	93.04 9	92.59 10	95.77 5	94.82 6	96.11 26	97.42 16

baseline1		84.54 95	84.43 96	84.67 93	90.62 90	91.16 112	88.63 101	83.75 76	79.78 107	71.16 116	75.14 90	74.10 112	77.84 140	91.56 69	90.67 74	96.04 27	88.58 158

MSLP-MVS++		92.02 35	91.40 38	92.75 25	96.01 33	95.88 45	93.73 41	89.00 35	89.89 45	90.31 16	81.28 60	88.85 40	91.45 24	92.88 53	94.24 15	96.00 28	96.76 31

NCCC		93.69 20	93.66 23	93.72 17	97.37 6	96.66 30	95.93 17	92.50 10	93.40 20	88.35 26	87.36 36	92.33 15	92.18 13	94.89 15	94.09 18	96.00 28	96.91 27

CS-MVS-test		90.29 45	90.96 41	89.51 54	93.18 61	95.87 46	89.18 86	83.72 77	88.32 51	84.82 48	84.89 44	85.23 55	90.25 35	94.04 31	92.66 51	95.94 30	95.69 51

ACMMP		92.03 34	92.16 32	91.87 35	95.88 35	96.55 32	94.47 36	89.49 34	91.71 32	85.26 44	91.52 25	84.48 58	90.21 36	92.82 54	91.63 58	95.92 31	96.42 38
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
zzz-MVS		93.80 18	93.45 26	94.20 9	97.53 4	96.43 37	95.88 18	91.12 21	94.09 12	92.74 4	87.68 34	90.77 26	92.04 14	94.74 20	93.56 29	95.91 32	96.85 28

SMA-MVS		94.70 7	95.35 7	93.93 13	97.57 3	97.57 8	95.98 12	91.91 14	94.50 7	90.35 15	93.46 18	92.72 12	91.89 19	95.89 4	95.22 1	95.88 33	98.10 6
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
ACMMPR		93.72 19	93.94 20	93.48 19	97.07 12	96.93 18	95.78 22	90.66 27	93.88 15	89.24 22	93.53 17	89.08 39	92.24 12	93.89 37	93.50 32	95.88 33	96.73 32

HFP-MVS		94.02 15	94.22 18	93.78 15	97.25 8	96.85 21	95.81 21	90.94 24	94.12 11	90.29 17	94.09 15	89.98 32	92.52 11	93.94 35	93.49 34	95.87 35	97.10 24

PVSNet_BlendedMVS		88.19 65	88.00 65	88.42 66	92.71 71	94.82 66	89.08 91	83.81 74	84.91 69	86.38 38	79.14 68	78.11 93	82.66 86	93.05 50	91.10 62	95.86 36	94.86 66

PVSNet_Blended		88.19 65	88.00 65	88.42 66	92.71 71	94.82 66	89.08 91	83.81 74	84.91 69	86.38 38	79.14 68	78.11 93	82.66 86	93.05 50	91.10 62	95.86 36	94.86 66

DeepC-MVS_fast	88.76 1	93.10 23	93.02 30	93.19 23	97.13 10	96.51 34	95.35 27	91.19 20	93.14 22	88.14 27	85.26 42	89.49 36	91.45 24	95.17 10	95.07 2	95.85 38	96.48 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PGM-MVS		92.76 27	93.03 29	92.45 29	97.03 14	96.67 29	95.73 24	87.92 43	90.15 44	86.53 37	92.97 21	88.33 45	91.69 22	93.62 43	93.03 42	95.83 39	96.41 39

SD-MVS		94.53 10	95.22 8	93.73 16	95.69 37	97.03 15	95.77 23	91.95 13	94.41 8	91.35 8	94.97 9	93.34 8	91.80 21	94.72 21	93.99 20	95.82 40	98.07 7
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
DeepC-MVS	87.86 3	92.26 32	91.86 35	92.73 26	96.18 30	96.87 20	95.19 29	91.76 16	92.17 28	86.58 36	81.79 54	85.85 52	90.88 32	94.57 24	94.61 10	95.80 41	97.18 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS					93.11 62	96.70 26	91.91 55			83.95 51		88.82 41				95.79 42

X-MVStestdata					93.11 62	96.70 26	91.91 55			83.95 51		88.82 41				95.79 42

DELS-MVS		89.71 50	89.68 52	89.74 49	93.75 55	96.22 39	93.76 40	85.84 54	82.53 79	85.05 46	78.96 71	84.24 59	84.25 78	94.91 14	94.91 4	95.78 44	96.02 46
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
X-MVS		92.36 31	92.75 31	91.90 34	96.89 18	96.70 26	95.25 28	90.48 30	91.50 34	83.95 51	88.20 32	88.82 41	89.11 40	93.75 40	93.43 35	95.75 45	96.83 30

casdiffmvs		87.45 71	87.15 73	87.79 72	90.15 103	94.22 72	89.96 74	83.93 73	85.08 67	80.91 69	75.81 86	77.88 96	86.08 70	91.86 67	90.86 68	95.74 46	94.37 74

CP-MVS		93.25 22	93.26 27	93.24 22	96.84 20	96.51 34	95.52 25	90.61 28	92.37 26	88.88 23	90.91 27	89.52 35	91.91 18	93.64 42	92.78 47	95.69 47	97.09 25

MVSTER		86.03 79	86.12 81	85.93 83	88.62 115	89.93 131	89.33 85	79.91 128	81.87 88	81.35 66	81.07 61	74.91 107	80.66 106	92.13 65	90.10 84	95.68 48	92.80 104

3Dnovator+	86.06 4	91.60 37	90.86 44	92.47 28	96.00 34	96.50 36	94.70 33	87.83 44	90.49 40	89.92 19	74.68 93	89.35 37	90.66 33	94.02 33	94.14 17	95.67 49	96.85 28

OpenMVS	82.53 11	87.71 68	86.84 75	88.73 61	94.42 49	95.06 61	91.02 65	83.49 84	82.50 81	82.24 64	67.62 134	85.48 53	85.56 73	91.19 75	91.30 61	95.67 49	94.75 68

EIA-MVS		87.94 67	88.05 64	87.81 70	91.46 80	95.00 63	88.67 98	82.81 92	82.53 79	80.81 71	80.04 64	80.20 78	87.48 59	92.58 57	91.61 59	95.63 51	94.36 75

ET-MVSNet_ETH3D		84.65 93	85.58 88	83.56 112	74.99 213	92.62 101	90.29 71	80.38 116	82.16 84	73.01 111	83.41 46	71.10 129	87.05 65	87.77 126	90.17 83	95.62 52	91.82 128

CDPH-MVS		91.14 40	92.01 33	90.11 44	96.18 30	96.18 40	94.89 32	88.80 39	88.76 49	77.88 88	89.18 31	87.71 48	87.29 63	93.13 48	93.31 39	95.62 52	95.84 48

MP-MVS		93.35 21	93.59 24	93.08 24	97.39 5	96.82 23	95.38 26	90.71 25	90.82 37	88.07 28	92.83 22	90.29 30	91.32 29	94.03 32	93.19 41	95.61 54	97.16 21
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
FMVSNet3		84.44 98	84.64 94	84.21 101	84.32 164	90.13 126	89.85 76	80.37 117	81.17 93	75.50 93	69.63 119	79.69 84	79.62 126	89.72 103	90.52 78	95.59 55	91.58 137

HPM-MVS++		94.60 9	94.91 11	94.24 8	97.86 1	96.53 33	96.14 9	92.51 9	93.87 16	90.76 13	93.45 19	93.84 5	92.62 9	95.11 12	94.08 19	95.58 56	97.48 14

CLD-MVS		88.66 57	88.52 58	88.82 60	91.37 82	94.22 72	92.82 49	82.08 103	88.27 52	85.14 45	81.86 53	78.53 91	85.93 72	91.17 76	90.61 75	95.55 57	95.00 62
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMMP_NAP		93.94 16	94.49 15	93.30 21	97.03 14	97.31 10	95.96 13	91.30 19	93.41 19	88.55 25	93.00 20	90.33 29	91.43 27	95.53 7	94.41 14	95.53 58	97.47 15

GBi-Net		84.51 96	84.80 92	84.17 102	84.20 165	89.95 128	89.70 77	80.37 117	81.17 93	75.50 93	69.63 119	79.69 84	79.75 123	90.73 90	90.72 70	95.52 59	91.71 130

test1		84.51 96	84.80 92	84.17 102	84.20 165	89.95 128	89.70 77	80.37 117	81.17 93	75.50 93	69.63 119	79.69 84	79.75 123	90.73 90	90.72 70	95.52 59	91.71 130

FMVSNet2		83.87 101	83.73 103	84.05 106	84.20 165	89.95 128	89.70 77	80.21 122	79.17 114	74.89 98	65.91 140	77.49 97	79.75 123	90.87 87	91.00 66	95.52 59	91.71 130

DPM-MVS		91.72 36	91.48 36	92.00 32	95.53 38	95.75 48	95.94 15	91.07 22	91.20 35	85.58 42	81.63 58	90.74 27	88.40 48	93.40 44	93.75 25	95.45 62	93.85 85

OPM-MVS		87.56 70	85.80 86	89.62 52	93.90 54	94.09 75	94.12 37	88.18 40	75.40 134	77.30 91	76.41 82	77.93 95	88.79 43	92.20 62	90.82 69	95.40 63	93.72 89
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
abl_6				90.66 41	94.65 48	96.27 38	92.21 51	86.94 49	90.23 42	86.38 38	85.50 41	92.96 10	88.37 49			95.40 63	95.46 57

CSCG		92.76 27	93.16 28	92.29 30	96.30 29	97.74 7	94.67 34	88.98 37	92.46 24	89.73 21	86.67 38	92.15 18	88.69 45	92.26 60	92.92 45	95.40 63	97.89 10

canonicalmvs		89.36 53	89.92 48	88.70 62	91.38 81	95.92 44	91.81 58	82.61 100	90.37 41	82.73 61	82.09 52	79.28 87	88.30 50	91.17 76	93.59 28	95.36 66	97.04 26

IB-MVS	79.09 12	82.60 113	82.19 111	83.07 116	91.08 84	93.55 82	80.90 181	81.35 109	76.56 126	80.87 70	64.81 153	69.97 134	68.87 182	85.64 156	90.06 86	95.36 66	94.74 69
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
gg-mvs-nofinetune		75.64 187	77.26 166	73.76 192	87.92 121	92.20 104	87.32 117	64.67 210	51.92 216	35.35 220	46.44 208	77.05 100	71.97 172	92.64 56	91.02 65	95.34 68	89.53 153

Vis-MVSNet		84.38 100	86.68 79	81.70 129	87.65 126	94.89 64	88.14 107	80.90 113	74.48 140	68.23 132	77.53 78	80.72 75	69.98 179	92.68 55	91.90 55	95.33 69	94.58 72
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	84.37 7	88.91 56	88.93 56	88.89 59	93.00 66	94.85 65	92.00 54	84.84 62	91.68 33	80.05 75	79.77 66	84.56 57	88.17 51	90.11 98	89.00 116	95.30 70	92.57 114
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_Test		86.93 73	87.24 72	86.56 77	90.10 104	93.47 83	90.31 70	80.12 123	83.55 73	78.12 84	79.58 67	79.80 82	85.45 74	90.17 97	90.59 76	95.29 71	93.53 92

LGP-MVS_train		88.25 64	88.55 57	87.89 69	92.84 69	93.66 80	93.35 43	85.22 60	85.77 61	74.03 103	86.60 39	76.29 102	86.62 68	91.20 74	90.58 77	95.29 71	95.75 49

FA-MVS(training)		85.65 83	85.79 87	85.48 88	90.44 97	93.47 83	88.66 100	73.11 177	83.34 74	82.26 62	71.79 108	78.39 92	83.14 83	91.00 83	89.47 103	95.28 73	93.06 97

UniMVSNet_NR-MVSNet		81.87 119	81.33 119	82.50 121	85.31 151	91.30 110	85.70 139	84.25 68	75.89 130	64.21 152	66.95 136	64.65 154	80.22 113	87.07 132	89.18 111	95.27 74	94.29 76

IS_MVSNet		86.18 77	88.18 62	83.85 108	91.02 85	94.72 68	87.48 114	82.46 101	81.05 97	70.28 120	76.98 80	82.20 70	76.65 147	93.97 34	93.38 36	95.18 75	94.97 63

train_agg		92.87 26	93.53 25	92.09 31	96.88 19	95.38 52	95.94 15	90.59 29	90.65 39	83.65 54	94.31 14	91.87 20	90.30 34	93.38 45	92.42 52	95.17 76	96.73 32

NR-MVSNet		80.25 134	79.98 138	80.56 144	85.20 153	90.94 114	85.65 141	83.58 82	75.74 131	61.36 176	65.30 148	56.75 196	72.38 171	88.46 119	88.80 118	95.16 77	93.87 84

PVSNet_Blended_VisFu		87.40 72	87.80 67	86.92 76	92.86 67	95.40 51	88.56 104	83.45 88	79.55 110	82.26 62	74.49 95	84.03 60	79.24 131	92.97 52	91.53 60	95.15 78	96.65 35

EPP-MVSNet		86.55 74	87.76 69	85.15 90	90.52 93	94.41 70	87.24 120	82.32 102	81.79 89	73.60 105	78.57 73	82.41 68	82.07 92	91.23 72	90.39 79	95.14 79	95.48 56

thisisatest0530		85.15 89	85.86 84	84.33 98	89.19 111	92.57 102	87.22 121	80.11 124	82.15 85	74.41 100	78.15 75	73.80 116	79.90 119	90.99 84	89.58 99	95.13 80	93.75 88

TranMVSNet+NR-MVSNet		80.52 131	79.84 140	81.33 135	84.92 160	90.39 120	85.53 144	84.22 70	74.27 143	60.68 181	64.93 152	59.96 177	77.48 142	86.75 140	89.28 106	95.12 81	93.29 93

tttt0517		85.11 90	85.81 85	84.30 99	89.24 109	92.68 98	87.12 125	80.11 124	81.98 86	74.31 102	78.08 76	73.57 118	79.90 119	91.01 82	89.58 99	95.11 82	93.77 87

UniMVSNet (Re)		81.22 127	81.08 122	81.39 133	85.35 150	91.76 108	84.93 148	82.88 91	76.13 129	65.02 149	64.94 151	63.09 160	75.17 155	87.71 127	89.04 114	94.97 83	94.88 65

FC-MVSNet-train		85.18 88	85.31 90	85.03 91	90.67 89	91.62 109	87.66 112	83.61 79	79.75 108	74.37 101	78.69 72	71.21 128	78.91 132	91.23 72	89.96 89	94.96 84	94.69 71

GeoE		84.62 94	83.98 101	85.35 89	89.34 108	92.83 95	88.34 105	78.95 138	79.29 112	77.16 92	68.10 131	74.56 109	83.40 81	89.31 110	89.23 109	94.92 85	94.57 73

tfpn200view9		82.86 109	81.46 116	84.48 95	90.30 101	93.09 89	89.05 93	82.71 94	75.14 135	69.56 123	65.72 142	63.13 158	80.38 112	91.15 78	89.51 101	94.91 86	92.50 118

thres600view7		82.53 115	81.02 123	84.28 100	90.61 91	93.05 90	88.57 103	82.67 96	74.12 145	68.56 131	65.09 150	62.13 169	80.40 111	91.15 78	89.02 115	94.88 87	92.59 112

thres200		82.77 111	81.25 120	84.54 94	90.38 98	93.05 90	89.13 90	82.67 96	74.40 141	69.53 125	65.69 144	63.03 161	80.63 107	91.15 78	89.42 104	94.88 87	92.04 124

Effi-MVS+		85.33 85	85.08 91	85.63 85	89.69 106	93.42 85	89.90 75	80.31 121	79.32 111	72.48 114	73.52 102	74.03 113	86.55 69	90.99 84	89.98 88	94.83 89	94.27 80

thres400		82.68 112	81.15 121	84.47 96	90.52 93	92.89 94	88.95 96	82.71 94	74.33 142	69.22 128	65.31 147	62.61 164	80.63 107	90.96 86	89.50 102	94.79 90	92.45 120

ACMP	83.90 8	88.32 63	88.06 63	88.62 63	92.18 73	93.98 77	91.28 64	85.24 59	86.69 57	81.23 68	85.62 40	75.13 106	87.01 66	89.83 101	89.77 95	94.79 90	95.43 58
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DU-MVS		81.20 128	80.30 132	82.25 124	84.98 158	90.94 114	85.70 139	83.58 82	75.74 131	64.21 152	65.30 148	59.60 182	80.22 113	86.89 135	89.31 105	94.77 92	94.29 76

UA-Net		86.07 78	87.78 68	84.06 105	92.85 68	95.11 60	87.73 111	84.38 67	73.22 154	73.18 108	79.99 65	89.22 38	71.47 175	93.22 47	93.03 42	94.76 93	90.69 144

MVS_111021_LR		90.14 48	90.89 43	89.26 56	93.23 60	94.05 76	90.43 69	84.65 63	90.16 43	84.52 50	90.14 29	83.80 61	87.99 52	92.50 58	90.92 67	94.74 94	94.70 70

thres100view900		82.55 114	81.01 125	84.34 97	90.30 101	92.27 103	89.04 94	82.77 93	75.14 135	69.56 123	65.72 142	63.13 158	79.62 126	89.97 100	89.26 107	94.73 95	91.61 136

AdaColmap		90.29 45	88.38 60	92.53 27	96.10 32	95.19 57	92.98 47	91.40 18	89.08 48	88.65 24	78.35 74	81.44 72	91.30 30	90.81 89	90.21 82	94.72 96	93.59 91

PCF-MVS	84.60 6	88.66 57	87.75 70	89.73 50	93.06 65	96.02 41	93.22 45	90.00 32	82.44 82	80.02 77	77.96 77	85.16 56	87.36 61	88.54 117	88.54 121	94.72 96	95.61 54
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DI_MVS_plusplus_trai		86.41 76	85.54 89	87.42 74	89.24 109	93.13 88	92.16 53	82.65 98	82.30 83	80.75 73	68.30 130	80.41 76	85.01 75	90.56 95	90.07 85	94.70 98	94.01 82

Fast-Effi-MVS+		83.77 103	82.98 106	84.69 92	87.98 120	91.87 107	88.10 108	77.70 152	78.10 120	73.04 110	69.13 125	68.51 142	86.66 67	90.49 96	89.85 93	94.67 99	92.88 101

WR-MVS_H		75.84 185	76.93 171	74.57 191	82.86 184	89.50 144	78.34 194	79.36 135	66.90 183	52.51 199	60.20 175	59.71 179	59.73 201	83.61 179	85.77 159	94.65 100	92.84 102

OMC-MVS		90.23 47	90.40 47	90.03 47	93.45 58	95.29 53	91.89 57	86.34 53	93.25 21	84.94 47	81.72 56	86.65 51	88.90 41	91.69 68	90.27 81	94.65 100	93.95 83

HQP-MVS		89.13 55	89.58 53	88.60 64	93.53 57	93.67 79	93.29 44	87.58 46	88.53 50	75.50 93	87.60 35	80.32 77	87.07 64	90.66 94	89.95 90	94.62 102	96.35 42

PEN-MVS		76.02 182	76.07 178	75.95 181	83.17 178	87.97 162	79.65 185	80.07 127	66.57 185	51.45 202	60.94 169	55.47 201	66.81 191	82.72 184	86.80 140	94.59 103	92.03 125

ACMM	83.27 10	87.68 69	86.09 82	89.54 53	93.26 59	92.19 105	91.43 61	86.74 50	86.02 60	82.85 59	75.63 87	75.14 105	88.41 47	90.68 93	89.99 87	94.59 103	92.97 99
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CANet_DTU		85.43 84	87.72 71	82.76 119	90.95 88	93.01 92	89.99 73	75.46 169	82.67 76	64.91 150	83.14 47	80.09 79	80.68 105	92.03 66	91.03 64	94.57 105	92.08 122

CP-MVSNet		76.36 179	76.41 175	76.32 178	82.73 187	88.64 157	79.39 188	79.62 130	67.21 181	53.70 196	60.72 171	55.22 202	67.91 187	83.52 180	86.34 150	94.55 106	93.19 94

EG-PatchMatch MVS		76.40 178	75.47 187	77.48 168	85.86 143	90.22 124	82.45 167	73.96 175	59.64 208	59.60 185	52.75 200	62.20 168	68.44 184	88.23 121	87.50 129	94.55 106	87.78 168

tfpnnormal		77.46 166	74.86 191	80.49 145	86.34 139	88.92 155	84.33 155	81.26 110	61.39 203	61.70 173	51.99 202	53.66 208	74.84 158	88.63 116	87.38 132	94.50 108	92.08 122

baseline2		82.80 110	82.86 108	82.73 120	87.68 125	90.50 119	84.92 149	78.93 139	78.07 121	73.06 109	75.08 91	69.77 135	77.31 143	88.90 114	86.94 138	94.50 108	90.74 143

Vis-MVSNet (Re-imp)		83.65 104	86.81 77	79.96 149	90.46 96	92.71 96	84.84 150	82.00 104	80.93 99	62.44 165	76.29 83	82.32 69	65.54 195	92.29 59	91.66 57	94.49 110	91.47 139

PS-CasMVS		75.90 184	75.86 183	75.96 180	82.59 188	88.46 160	79.23 191	79.56 132	66.00 188	52.77 198	59.48 179	54.35 206	67.14 190	83.37 181	86.23 151	94.47 111	93.10 96

Baseline_NR-MVSNet		79.84 138	78.37 155	81.55 132	84.98 158	86.66 172	85.06 146	83.49 84	75.57 133	63.31 159	58.22 187	60.97 172	78.00 138	86.89 135	87.13 134	94.47 111	93.15 95

FMVSNet1		81.64 124	80.61 128	82.84 118	82.36 190	89.20 149	88.67 98	79.58 131	70.79 166	72.63 113	58.95 183	72.26 125	79.34 129	90.73 90	90.72 70	94.47 111	91.62 135

DTE-MVSNet		75.14 189	75.44 188	74.80 188	83.18 177	87.19 169	78.25 196	80.11 124	66.05 187	48.31 207	60.88 170	54.67 203	64.54 196	82.57 186	86.17 152	94.43 114	90.53 148

PLC	83.76 9	88.61 59	86.83 76	90.70 40	94.22 50	92.63 99	91.50 60	87.19 48	89.16 47	86.87 34	75.51 88	80.87 74	89.98 38	90.01 99	89.20 110	94.41 115	90.45 149
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UGNet		85.90 81	88.23 61	83.18 115	88.96 113	94.10 74	87.52 113	83.60 80	81.66 90	77.90 87	80.76 62	83.19 64	66.70 192	91.13 81	90.71 73	94.39 116	96.06 45
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
TransMVSNet (Re)		76.57 173	75.16 190	78.22 165	85.60 147	87.24 168	82.46 166	81.23 111	59.80 207	59.05 189	57.07 189	59.14 186	66.60 193	88.09 122	86.82 139	94.37 117	87.95 167

gm-plane-assit		70.29 200	70.65 202	69.88 201	85.03 156	78.50 211	58.41 218	65.47 206	50.39 218	40.88 216	49.60 204	50.11 212	75.14 156	91.43 71	89.78 94	94.32 118	84.73 187

CNLPA		88.40 60	87.00 74	90.03 47	93.73 56	94.28 71	89.56 81	85.81 55	91.87 30	87.55 30	69.53 123	81.49 71	89.23 39	89.45 108	88.59 120	94.31 119	93.82 86

MAR-MVS		88.39 62	88.44 59	88.33 68	94.90 43	95.06 61	90.51 68	83.59 81	85.27 64	79.07 80	77.13 79	82.89 66	87.70 54	92.19 63	92.32 53	94.23 120	94.20 81
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
MSDG		83.87 101	81.02 123	87.19 75	92.17 74	89.80 135	89.15 89	85.72 56	80.61 102	79.24 79	66.66 137	68.75 141	82.69 85	87.95 124	87.44 130	94.19 121	85.92 181

pm-mvs1		78.51 158	77.75 163	79.40 152	84.83 161	89.30 146	83.55 161	79.38 134	62.64 199	63.68 157	58.73 185	64.68 153	70.78 178	89.79 102	87.84 126	94.17 122	91.28 141

CPTT-MVS		91.39 38	90.95 42	91.91 33	95.06 40	95.24 56	95.02 31	88.98 37	91.02 36	86.71 35	84.89 44	88.58 44	91.60 23	90.82 88	89.67 98	94.08 123	96.45 37

v144192		78.81 152	77.22 167	80.67 142	82.95 181	89.79 136	86.40 132	77.42 153	68.26 180	63.13 160	59.50 178	58.13 188	80.08 118	85.93 152	86.08 154	94.06 124	92.83 103

diffmvs		86.52 75	86.76 78	86.23 80	88.31 119	92.63 99	89.58 80	81.61 107	86.14 59	80.26 74	79.00 70	77.27 98	83.58 79	88.94 113	89.06 113	94.05 125	94.29 76

v1921920		78.57 157	76.99 170	80.41 147	82.93 182	89.63 142	86.38 133	77.14 156	68.31 179	61.80 172	58.89 184	56.79 195	80.19 116	86.50 147	86.05 156	94.02 126	92.76 106

ACMH	78.52 14	81.86 120	80.45 131	83.51 114	90.51 95	91.22 111	85.62 142	84.23 69	70.29 171	62.21 166	69.04 127	64.05 156	84.48 77	87.57 128	88.45 123	94.01 127	92.54 116
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		76.63 172	78.02 160	75.02 186	84.14 168	89.76 137	78.34 194	80.64 115	69.56 172	52.32 200	61.26 165	61.24 171	60.66 200	84.45 174	87.07 135	93.99 128	92.77 105

v10		79.62 141	78.19 156	81.28 136	83.73 171	89.69 139	87.27 119	76.86 159	70.50 169	65.46 144	60.58 173	60.47 174	80.44 110	86.91 134	86.63 144	93.93 129	92.55 115

anonymousdsp		77.94 161	79.00 147	76.71 174	79.03 202	87.83 163	79.58 186	72.87 178	65.80 190	58.86 190	65.82 141	62.48 166	75.99 150	86.77 139	88.66 119	93.92 130	95.68 53

v1240		78.15 159	76.53 173	80.04 148	82.85 185	89.48 145	85.61 143	76.77 160	67.05 182	61.18 179	58.37 186	56.16 199	79.89 121	86.11 151	86.08 154	93.92 130	92.47 119

v8		79.90 137	78.39 154	81.66 130	83.97 169	89.81 134	87.16 123	77.40 154	71.49 160	67.71 133	61.24 166	62.49 165	79.83 122	85.48 160	86.17 152	93.89 132	92.02 126

v2v482		79.84 138	78.07 158	81.90 127	83.75 170	90.21 125	87.17 122	79.85 129	70.65 167	65.93 142	61.93 163	60.07 176	80.82 102	85.25 162	86.71 141	93.88 133	91.70 134

thisisatest0515		79.76 140	80.59 129	78.80 157	84.40 163	88.91 156	79.48 187	76.94 158	72.29 158	67.33 135	67.82 133	65.99 149	70.80 177	88.50 118	87.84 126	93.86 134	92.75 107

IterMVS-LS		83.28 107	82.95 107	83.65 109	88.39 118	88.63 158	86.80 129	78.64 143	76.56 126	73.43 107	72.52 107	75.35 104	80.81 103	86.43 148	88.51 122	93.84 135	92.66 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TSAR-MVS + ACMM		92.97 24	94.51 14	91.16 38	95.88 35	96.59 31	95.09 30	90.45 31	93.42 18	83.01 57	94.68 11	90.74 27	88.74 44	94.75 19	93.78 24	93.82 136	97.63 12

v1144		79.38 147	77.83 161	81.18 137	83.62 172	90.23 123	87.15 124	78.35 145	69.13 174	64.02 155	60.20 175	59.41 183	80.14 117	86.78 138	86.57 145	93.81 137	92.53 117

v1192		78.94 151	77.33 165	80.82 140	83.25 176	89.90 132	86.91 127	77.72 151	68.63 178	62.61 164	59.17 180	57.53 192	80.62 109	86.89 135	86.47 147	93.79 138	92.75 107

TSAR-MVS + COLMAP		88.40 60	89.09 55	87.60 73	92.72 70	93.92 78	92.21 51	85.57 57	91.73 31	73.72 104	91.75 24	73.22 122	87.64 57	91.49 70	89.71 97	93.73 139	91.82 128

UniMVSNet_ETH3D		79.24 148	76.47 174	82.48 122	85.66 146	90.97 113	86.08 136	81.63 106	64.48 195	68.94 130	54.47 195	57.65 191	78.83 133	85.20 166	88.91 117	93.72 140	93.60 90

EPNet		89.60 51	89.91 49	89.24 57	96.45 28	93.61 81	92.95 48	88.03 41	85.74 62	83.36 55	87.29 37	83.05 65	80.98 101	92.22 61	91.85 56	93.69 141	95.58 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		81.62 126	79.45 146	84.14 104	91.00 86	93.38 86	88.27 106	78.19 146	76.28 128	70.18 121	48.78 205	73.69 117	83.52 80	87.05 133	87.83 128	93.68 142	89.15 155

V42		79.59 142	78.43 153	80.94 139	82.79 186	89.71 138	86.66 130	76.73 161	71.38 161	67.42 134	61.01 168	62.30 167	78.39 135	85.56 158	86.48 146	93.65 143	92.60 111

DCV-MVSNet		85.88 82	86.17 80	85.54 87	89.10 112	89.85 133	89.34 84	80.70 114	83.04 75	78.08 86	76.19 84	79.00 88	82.42 89	89.67 104	90.30 80	93.63 144	95.12 60

v7n		77.22 167	76.23 177	78.38 164	81.89 193	89.10 153	82.24 172	76.36 162	65.96 189	61.21 178	56.56 190	55.79 200	75.07 157	86.55 144	86.68 142	93.52 145	92.95 100

Anonymous20231211		84.42 99	83.02 105	86.05 82	88.85 114	92.70 97	88.92 97	83.40 89	79.99 105	78.31 83	55.83 192	78.92 89	83.33 82	89.06 112	89.76 96	93.50 146	94.90 64

ACMH+	79.08 13	81.84 121	80.06 136	83.91 107	89.92 105	90.62 116	86.21 134	83.48 86	73.88 147	65.75 143	66.38 138	65.30 152	84.63 76	85.90 153	87.25 133	93.45 147	91.13 142

pmmvs5		76.93 169	76.33 176	77.62 167	81.97 192	88.40 161	81.32 177	74.35 173	65.42 193	61.42 175	63.07 159	57.95 190	73.23 169	85.60 157	85.35 164	93.41 148	88.55 159

Anonymous202405211			82.75 109		89.58 107	92.97 93	89.04 94	84.13 71	78.72 116		57.18 188	76.64 101	83.13 84	89.55 106	89.92 91	93.38 149	94.28 79

USDC		80.69 130	79.89 139	81.62 131	86.48 137	89.11 152	86.53 131	78.86 140	81.15 96	63.48 158	72.98 104	59.12 187	81.16 99	87.10 131	85.01 166	93.23 150	84.77 186

LS3D		85.96 80	84.37 97	87.81 70	94.13 51	93.27 87	90.26 72	89.00 35	84.91 69	72.84 112	71.74 109	72.47 124	87.45 60	89.53 107	89.09 112	93.20 151	89.60 152

MS-PatchMatch		81.79 122	81.44 117	82.19 126	90.35 99	89.29 147	88.08 109	75.36 170	77.60 122	69.00 129	64.37 156	78.87 90	77.14 146	88.03 123	85.70 160	93.19 152	86.24 178

Fast-Effi-MVS+-dtu		79.95 136	80.69 127	79.08 154	86.36 138	89.14 151	85.85 137	72.28 180	72.85 157	59.32 186	70.43 117	68.42 144	77.57 141	86.14 150	86.44 148	93.11 153	91.39 140

GA-MVS		79.52 143	79.71 143	79.30 153	85.68 145	90.36 121	84.55 152	78.44 144	70.47 170	57.87 191	68.52 129	61.38 170	76.21 149	89.40 109	87.89 125	93.04 154	89.96 151

DeepPCF-MVS	88.51 2	92.64 30	94.42 17	90.56 42	94.84 45	96.92 19	91.31 63	89.61 33	95.16 5	84.55 49	89.91 30	91.45 22	90.15 37	95.12 11	94.81 7	92.90 155	97.58 13

CDS-MVSNet		81.63 125	82.09 112	81.09 138	87.21 131	90.28 122	87.46 116	80.33 120	69.06 175	70.66 117	71.30 110	73.87 114	67.99 185	89.58 105	89.87 92	92.87 156	90.69 144
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		82.05 117	81.76 113	82.38 123	87.72 123	90.56 118	86.90 128	78.05 148	73.85 148	66.85 137	71.29 111	71.90 126	82.00 93	86.64 143	85.48 162	92.76 157	92.58 113

v148		78.59 156	76.84 172	80.62 143	83.61 173	89.16 150	83.65 160	79.24 136	69.38 173	69.34 127	59.88 177	60.41 175	75.19 154	83.81 178	84.63 171	92.70 158	90.63 146

pmmvs4		79.99 135	78.08 157	82.22 125	83.04 180	87.16 170	84.95 147	78.80 142	78.64 117	74.53 99	64.61 154	59.41 183	79.45 128	84.13 176	84.54 173	92.53 159	88.08 164

test_part1		83.23 108	80.55 130	86.35 79	88.60 116	90.61 117	90.78 66	81.13 112	70.89 165	83.01 57	55.72 193	74.60 108	82.19 90	87.79 125	89.26 107	92.39 160	95.01 61

RPMNet		77.07 168	77.63 164	76.42 176	85.56 148	85.15 185	81.37 175	65.27 207	74.71 138	60.29 182	63.71 158	66.59 148	73.64 165	82.71 185	82.12 187	92.38 161	88.39 160

CR-MVSNet		78.71 154	78.86 148	78.55 161	85.85 144	85.15 185	82.30 170	68.23 196	74.71 138	65.37 146	64.39 155	69.59 137	77.18 144	85.10 168	84.87 167	92.34 162	88.21 162

COLMAP_ROB	76.78 15	80.50 132	78.49 151	82.85 117	90.96 87	89.65 141	86.20 135	83.40 89	77.15 124	66.54 138	62.27 161	65.62 151	77.89 139	85.23 163	84.70 170	92.11 163	84.83 185
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchMatch-RL		83.34 106	81.36 118	85.65 84	90.33 100	89.52 143	84.36 154	81.82 105	80.87 101	79.29 78	74.04 97	62.85 163	86.05 71	88.40 120	87.04 137	92.04 164	86.77 174

PMMVS		81.65 123	84.05 100	78.86 156	78.56 204	82.63 198	83.10 162	67.22 200	81.39 91	70.11 122	84.91 43	79.74 83	82.12 91	87.31 129	85.70 160	92.03 165	86.67 177

IterMVS-SCA-FT		79.41 146	80.20 134	78.49 162	85.88 141	86.26 174	83.95 157	71.94 181	73.55 152	61.94 169	70.48 116	70.50 131	75.23 153	85.81 155	84.61 172	91.99 166	90.18 150

baseline		84.89 91	86.06 83	83.52 113	87.25 130	89.67 140	87.76 110	75.68 168	84.92 68	78.40 82	80.10 63	80.98 73	80.20 115	86.69 142	87.05 136	91.86 167	92.99 98

MIMVSNet		74.69 191	75.60 186	73.62 193	76.02 211	85.31 184	81.21 180	67.43 199	71.02 163	59.07 188	54.48 194	64.07 155	66.14 194	86.52 146	86.64 143	91.83 168	81.17 199

FC-MVSNet-test		76.53 175	81.62 115	70.58 200	84.99 157	85.73 179	74.81 202	78.85 141	77.00 125	39.13 218	75.90 85	73.50 119	54.08 207	86.54 145	85.99 157	91.65 169	86.68 175

pmmvs-eth3d		74.32 193	71.96 199	77.08 171	77.33 207	82.71 197	78.41 193	76.02 166	66.65 184	65.98 141	54.23 197	49.02 215	73.14 170	82.37 188	82.69 184	91.61 170	86.05 180

SixPastTwentyTwo		76.02 182	75.72 184	76.36 177	83.38 174	87.54 165	75.50 201	76.22 163	65.50 192	57.05 192	70.64 113	53.97 207	74.54 160	80.96 192	82.12 187	91.44 171	89.35 154

pmmvs6		74.83 190	72.89 197	77.09 170	82.11 191	87.50 166	80.88 182	76.97 157	52.79 215	61.91 171	46.66 207	60.49 173	69.28 181	86.74 141	85.46 163	91.39 172	90.56 147

test-mter		77.79 162	80.02 137	75.18 185	81.18 198	82.85 196	80.52 184	62.03 214	73.62 151	62.16 167	73.55 101	73.83 115	73.81 164	84.67 171	83.34 179	91.37 173	88.31 161

TDRefinement		79.05 150	77.05 169	81.39 133	88.45 117	89.00 154	86.92 126	82.65 98	74.21 144	64.41 151	59.17 180	59.16 185	74.52 161	85.23 163	85.09 165	91.37 173	87.51 170

test-LLR		79.47 145	79.84 140	79.03 155	87.47 127	82.40 201	81.24 178	78.05 148	73.72 149	62.69 162	73.76 99	74.42 110	73.49 166	84.61 172	82.99 182	91.25 175	87.01 172

TESTMET0.1,1		77.78 163	79.84 140	75.38 184	80.86 199	82.40 201	81.24 178	62.72 213	73.72 149	62.69 162	73.76 99	74.42 110	73.49 166	84.61 172	82.99 182	91.25 175	87.01 172

TinyColmap		76.73 170	73.95 194	79.96 149	85.16 155	85.64 181	82.34 169	78.19 146	70.63 168	62.06 168	60.69 172	49.61 213	80.81 103	85.12 167	83.69 178	91.22 177	82.27 194

FMVSNet5		75.50 188	76.07 178	74.83 187	76.16 209	81.19 204	81.34 176	70.21 189	73.20 155	61.59 174	58.97 182	68.33 145	68.50 183	85.87 154	85.85 158	91.18 178	79.11 205

IterMVS		78.79 153	79.71 143	77.71 166	85.26 152	85.91 177	84.54 153	69.84 192	73.38 153	61.25 177	70.53 115	70.35 132	74.43 162	85.21 165	83.80 177	90.95 179	88.77 157
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchT		76.42 176	77.81 162	74.80 188	78.46 205	84.30 190	71.82 208	65.03 209	73.89 146	65.37 146	61.58 164	66.70 147	77.18 144	85.10 168	84.87 167	90.94 180	88.21 162

EPNet_dtu		81.98 118	83.82 102	79.83 151	94.10 52	85.97 176	87.29 118	84.08 72	80.61 102	59.96 183	81.62 59	77.19 99	62.91 199	87.21 130	86.38 149	90.66 181	87.77 169
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PM-MVS		74.17 194	73.10 195	75.41 183	76.07 210	82.53 199	77.56 197	71.69 182	71.04 162	61.92 170	61.23 167	47.30 216	74.82 159	81.78 190	79.80 191	90.42 182	88.05 165

test0.0.03 1		76.03 181	78.51 150	73.12 196	87.47 127	85.13 187	76.32 199	78.05 148	73.19 156	50.98 205	70.64 113	69.28 138	55.53 203	85.33 161	84.38 174	90.39 183	81.63 197

Anonymous20231206		70.80 199	70.59 203	71.04 199	81.60 195	82.49 200	74.64 203	75.87 167	64.17 196	49.27 206	44.85 211	53.59 209	54.68 206	83.07 182	82.34 186	90.17 184	83.65 189

CHOSEN 1792x2688		82.16 116	80.91 126	83.61 110	91.14 83	92.01 106	89.55 82	79.15 137	79.87 106	70.29 119	52.51 201	72.56 123	81.39 96	88.87 115	88.17 124	90.15 185	92.37 121

MIMVSNet1		65.00 206	66.24 207	63.55 209	58.41 220	80.01 208	69.00 211	74.03 174	55.81 213	41.88 215	36.81 216	49.48 214	47.89 212	81.32 191	82.40 185	90.08 186	77.88 207

LTVRE_ROB	74.41 16	75.78 186	74.72 192	77.02 172	85.88 141	89.22 148	82.44 168	77.17 155	50.57 217	45.45 211	65.44 146	52.29 210	81.25 97	85.50 159	87.42 131	89.94 187	92.62 110
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
GG-mvs-BLEND		57.56 211	82.61 110	28.34 219	0.22 227	90.10 127	79.37 189	0.14 225	79.56 109	0.40 228	71.25 112	83.40 63	0.30 225	86.27 149	83.87 175	89.59 188	83.83 188

CVMVSNet		76.70 171	78.46 152	74.64 190	83.34 175	84.48 189	81.83 174	74.58 171	68.88 176	51.23 204	69.77 118	70.05 133	67.49 188	84.27 175	83.81 176	89.38 189	87.96 166

TAMVS		76.42 176	77.16 168	75.56 182	83.05 179	85.55 182	80.58 183	71.43 183	65.40 194	61.04 180	67.27 135	69.22 140	67.99 185	84.88 170	84.78 169	89.28 190	83.01 192

CostFormer		80.94 129	80.21 133	81.79 128	87.69 124	88.58 159	87.47 115	70.66 186	80.02 104	77.88 88	73.03 103	71.40 127	78.24 136	79.96 196	79.63 192	88.82 191	88.84 156

RPSCF		83.46 105	83.36 104	83.59 111	87.75 122	87.35 167	84.82 151	79.46 133	83.84 72	78.12 84	82.69 51	79.87 80	82.60 88	82.47 187	81.13 190	88.78 192	86.13 179

test20.03		68.31 203	70.05 204	66.28 207	82.41 189	80.84 205	67.35 212	76.11 165	58.44 210	40.80 217	53.77 198	54.54 204	42.28 214	83.07 182	81.96 189	88.73 193	77.76 208

SCA		79.51 144	80.15 135	78.75 158	86.58 136	87.70 164	83.07 163	68.53 195	81.31 92	66.40 139	73.83 98	75.38 103	79.30 130	80.49 194	79.39 195	88.63 194	82.96 193

testgi		71.92 198	74.20 193	69.27 202	84.58 162	83.06 193	73.40 205	74.39 172	64.04 197	46.17 210	68.90 128	57.15 194	48.89 211	84.07 177	83.08 181	88.18 195	79.09 206

dps		78.02 160	75.94 182	80.44 146	86.06 140	86.62 173	82.58 165	69.98 190	75.14 135	77.76 90	69.08 126	59.93 178	78.47 134	79.47 198	77.96 199	87.78 196	83.40 190

PatchmatchNet		78.67 155	78.85 149	78.46 163	86.85 135	86.03 175	83.77 159	68.11 198	80.88 100	66.19 140	72.90 105	73.40 120	78.06 137	79.25 200	77.71 200	87.75 197	81.75 196
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13_2view		73.21 196	72.91 196	73.56 194	80.01 200	84.28 191	78.62 192	66.43 204	68.64 177	59.12 187	60.39 174	59.69 181	69.81 180	78.82 202	77.43 201	87.36 198	81.11 200

MDTV_nov1_ep13		79.14 149	79.49 145	78.74 159	85.40 149	86.89 171	84.32 156	70.29 188	78.85 115	69.42 126	75.37 89	73.29 121	75.64 152	80.61 193	79.48 194	87.36 198	81.91 195

EPMVS		77.53 165	78.07 158	76.90 173	86.89 134	84.91 188	82.18 173	66.64 203	81.00 98	64.11 154	72.75 106	69.68 136	74.42 163	79.36 199	78.13 198	87.14 200	80.68 202

EU-MVSNet		69.98 201	72.30 198	67.28 205	75.67 212	79.39 209	73.12 206	69.94 191	63.59 198	42.80 214	62.93 160	56.71 197	55.07 205	79.13 201	78.55 197	87.06 201	85.82 182

new-patchmatchnet		63.80 207	63.31 209	64.37 208	76.49 208	75.99 212	63.73 215	70.99 185	57.27 211	43.08 213	45.86 209	43.80 217	45.13 213	73.20 210	70.68 213	86.80 202	76.34 210

pmnet_mix02		71.95 197	71.83 200	72.10 197	81.40 197	80.63 207	73.78 204	72.85 179	70.90 164	54.89 194	62.17 162	57.42 193	62.92 198	76.80 205	73.98 209	86.74 203	80.87 201

CMPMVS	56.49 17	73.84 195	71.73 201	76.31 179	85.20 153	85.67 180	75.80 200	73.23 176	62.26 200	65.40 145	53.40 199	59.70 180	71.77 174	80.25 195	79.56 193	86.45 204	81.28 198
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDA-MVSNet-bldmvs		66.22 205	64.49 208	68.24 203	61.67 217	82.11 203	70.07 210	76.16 164	59.14 209	47.94 208	54.35 196	35.82 223	67.33 189	64.94 215	75.68 204	86.30 205	79.36 204

MVS-HIRNet		68.83 202	66.39 206	71.68 198	77.58 206	75.52 213	66.45 213	65.05 208	62.16 201	62.84 161	44.76 212	56.60 198	71.96 173	78.04 203	75.06 207	86.18 206	72.56 212

CHOSEN 280x420		80.28 133	81.66 114	78.67 160	82.92 183	79.24 210	85.36 145	66.79 202	78.11 119	70.32 118	75.03 92	79.87 80	81.09 100	89.07 111	83.16 180	85.54 207	87.17 171

tpm cat1		77.78 163	75.28 189	80.70 141	87.14 132	85.84 178	85.81 138	70.40 187	77.44 123	78.80 81	63.72 157	64.01 157	76.55 148	75.60 208	75.21 206	85.51 208	85.12 183

tpm		76.30 180	76.05 180	76.59 175	86.97 133	83.01 195	83.83 158	67.06 201	71.83 159	63.87 156	69.56 122	62.88 162	73.41 168	79.79 197	78.59 196	84.41 209	86.68 175

tpmrst		76.55 174	75.99 181	77.20 169	87.32 129	83.05 194	82.86 164	65.62 205	78.61 118	67.22 136	69.19 124	65.71 150	75.87 151	76.75 206	75.33 205	84.31 210	83.28 191

pmmvs3		61.89 209	61.74 211	62.06 210	64.30 216	70.83 217	64.22 214	52.14 218	48.78 219	44.47 212	41.67 214	41.70 221	63.03 197	76.06 207	76.02 203	84.18 211	77.14 209

ADS-MVSNet		74.53 192	75.69 185	73.17 195	81.57 196	80.71 206	79.27 190	63.03 212	79.27 113	59.94 184	67.86 132	68.32 146	71.08 176	77.33 204	76.83 202	84.12 212	79.53 203

ambc			61.92 210		70.98 215	73.54 215	63.64 216		60.06 205	52.23 201	38.44 215	19.17 226	57.12 202	82.33 189	75.03 208	83.21 213	84.89 184

FPMVS		63.63 208	60.08 213	67.78 204	80.01 200	71.50 216	72.88 207	69.41 194	61.82 202	53.11 197	45.12 210	42.11 220	50.86 209	66.69 213	63.84 214	80.41 214	69.46 214

N_pmnet		66.85 204	66.63 205	67.11 206	78.73 203	74.66 214	70.53 209	71.07 184	66.46 186	46.54 209	51.68 203	51.91 211	55.48 204	74.68 209	72.38 210	80.29 215	74.65 211

new_pmnet		59.28 210	61.47 212	56.73 212	61.66 218	68.29 218	59.57 217	54.91 215	60.83 204	34.38 221	44.66 213	43.65 218	49.90 210	71.66 211	71.56 212	79.94 216	69.67 213

PMVS	50.48 18	55.81 212	51.93 214	60.33 211	72.90 214	49.34 220	48.78 219	69.51 193	43.49 220	54.25 195	36.26 217	41.04 222	39.71 216	65.07 214	60.70 215	76.85 217	67.58 215
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		49.17 213	47.05 216	51.65 213	59.67 219	48.39 221	41.98 222	63.47 211	55.64 214	33.33 222	14.90 220	13.78 227	41.34 215	69.31 212	72.30 211	70.11 218	55.00 219
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.68 215	44.74 217	38.10 214	46.97 223	52.32 219	40.63 223	48.08 219	35.51 221	7.36 227	26.86 219	24.64 225	16.72 221	55.24 218	59.03 216	68.85 219	59.59 218

test_method		41.78 214	48.10 215	34.42 217	10.74 226	19.78 227	44.64 221	17.73 222	59.83 206	38.67 219	35.82 218	54.41 205	34.94 217	62.87 216	43.13 219	59.81 220	60.82 217

DeepMVS_CX						48.31 222	48.03 220	26.08 221	56.42 212	25.77 223	47.51 206	31.31 224	51.30 208	48.49 219		53.61 221	61.52 216

tmp_tt				32.73 218	43.96 224	21.15 226	26.71 224	8.99 223	65.67 191	51.39 203	56.01 191	42.64 219	11.76 222	56.60 217	50.81 218	53.55 222

E-PMN		31.40 216	26.80 219	36.78 215	51.39 222	29.96 224	20.20 225	54.17 216	25.93 223	12.75 225	14.73 221	8.58 229	34.10 219	27.36 221	37.83 220	48.07 223	43.18 221

EMVS		30.49 218	25.44 220	36.39 216	51.47 221	29.89 225	20.17 226	54.00 217	26.49 222	12.02 226	13.94 223	8.84 228	34.37 218	25.04 222	34.37 221	46.29 224	39.53 222

MVE	30.17 19	30.88 217	33.52 218	27.80 220	23.78 225	39.16 223	18.69 227	46.90 220	21.88 224	15.39 224	14.37 222	7.31 230	24.41 220	41.63 220	56.22 217	37.64 225	54.07 220
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		1.03 219	1.63 221	0.34 221	0.09 228	0.35 228	0.61 229	0.16 224	1.49 225	0.10 229	3.15 224	0.15 231	0.86 224	1.32 223	1.18 222	0.20 226	3.76 224

test123		0.87 220	1.40 222	0.25 222	0.03 229	0.25 229	0.35 230	0.08 226	1.21 226	0.05 230	2.84 225	0.03 232	0.89 223	0.43 224	1.16 223	0.13 227	3.87 223

uanet_test		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										56.08 193

9.14												92.16 17

SR-MVS					96.58 27			90.99 23				92.40 14

our_test_3					81.81 194	83.96 192	76.61 198

MTAPA										92.97 2		91.03 23

MTMP										93.14 1		90.21 31

Patchmatch-RL test							8.55 228

mPP-MVS					97.06 13							88.08 46

NP-MVS									87.47 55

Patchmtry						85.54 183	82.30 170	68.23 196		65.37 146

High-resolution multi-view benchmark