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.

MTMP										95.70 1		96.90 26

MTAPA										95.36 2		97.46 20

zzz-MVS		96.98 15	96.68 23	97.33 5	99.09 3	98.71 12	98.43 8	96.01 16	96.11 18	95.19 3	92.89 33	97.32 22	96.84 12	97.20 16	96.09 41	98.44 33	98.46 32

SED-MVS		97.98 1	98.36 1	97.54 3	98.94 17	99.29 2	98.81 3	96.64 3	97.14 2	95.16 4	97.96 2	99.61 2	96.92 11	98.00 1	97.24 8	98.75 13	99.25 2

DVP-MVS		97.93 2	98.23 2	97.58 2	99.05 6	99.31 1	98.64 5	96.62 4	97.56 1	95.08 5	96.61 13	99.64 1	97.32 1	97.91 3	97.31 6	98.77 12	99.26 1
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
xxxxxxxxxxxxxcwj		95.62 31	94.35 47	97.10 9	98.95 15	98.51 27	97.51 29	96.48 6	96.17 15	94.64 6	97.32 5	76.98 137	96.23 26	96.78 28	96.15 38	98.79 10	98.55 25

SF-MVS		97.20 11	97.29 13	97.10 9	98.95 15	98.51 27	97.51 29	96.48 6	96.17 15	94.64 6	97.32 5	97.57 18	96.23 26	96.78 28	96.15 38	98.79 10	98.55 25

APDe-MVS		97.79 4	97.96 5	97.60 1	99.20 2	99.10 5	98.88 2	96.68 2	96.81 6	94.64 6	97.84 3	98.02 10	97.24 3	97.74 7	97.02 13	98.97 3	99.16 5

SD-MVS		97.35 7	97.73 7	96.90 15	97.35 45	98.66 13	97.85 25	96.25 11	96.86 5	94.54 9	96.75 11	99.13 5	96.99 7	96.94 25	96.58 22	98.39 40	99.20 4
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
DPE-MVS		97.83 3	98.13 3	97.48 4	98.83 23	99.19 3	98.99 1	96.70 1	96.05 19	94.39 10	98.30 1	99.47 3	97.02 6	97.75 6	97.02 13	98.98 2	99.10 8
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSLP-MVS++		96.05 27	95.63 31	96.55 22	98.33 30	98.17 40	96.94 37	94.61 35	94.70 39	94.37 11	89.20 52	95.96 35	96.81 13	95.57 55	97.33 5	98.24 58	98.47 30

CNVR-MVS		97.30 9	97.41 10	97.18 8	99.02 10	98.60 20	98.15 16	96.24 13	96.12 17	94.10 12	95.54 25	97.99 11	96.99 7	97.97 2	97.17 9	98.57 20	98.50 28

PLC	90.69 4	94.32 45	92.99 57	95.87 29	97.91 34	96.49 87	95.95 51	94.12 36	94.94 33	94.09 13	85.90 70	90.77 63	95.58 34	94.52 79	93.32 93	97.55 110	95.00 142
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TSAR-MVS + MP.		97.31 8	97.64 8	96.92 14	97.28 47	98.56 22	98.61 6	95.48 29	96.72 7	94.03 14	96.73 12	98.29 8	97.15 4	97.61 11	96.42 26	98.96 4	99.13 6
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSP-MVS		97.70 5	98.09 4	97.24 6	99.00 11	99.17 4	98.76 4	96.41 9	96.91 4	93.88 15	97.72 4	99.04 6	96.93 10	97.29 15	97.31 6	98.45 32	99.23 3
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
SMA-MVS		97.53 6	97.93 6	97.07 11	99.21 1	99.02 7	98.08 19	96.25 11	96.36 11	93.57 16	96.56 14	99.27 4	96.78 16	97.91 3	97.43 3	98.51 22	98.94 11
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
APD-MVS		97.12 12	97.05 17	97.19 7	99.04 7	98.63 18	98.45 7	96.54 5	94.81 37	93.50 17	96.10 19	97.40 21	96.81 13	97.05 22	96.82 18	98.80 8	98.56 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
AdaColmap		95.02 38	93.71 50	96.54 23	98.51 27	97.76 53	96.69 40	95.94 20	93.72 46	93.50 17	89.01 53	90.53 66	96.49 21	94.51 80	93.76 79	98.07 74	96.69 97

CNLPA		93.69 52	92.50 63	95.06 37	97.11 50	97.36 64	93.88 83	93.30 39	95.64 23	93.44 19	80.32 108	90.73 64	94.99 39	93.58 97	93.33 91	97.67 104	96.57 102

CSCG		95.68 30	95.46 35	95.93 28	98.71 25	99.07 6	97.13 36	93.55 38	95.48 25	93.35 20	90.61 45	93.82 46	95.16 37	94.60 77	95.57 49	97.70 101	99.08 9

HFP-MVS		97.11 13	97.19 15	97.00 13	98.97 13	98.73 11	98.37 11	95.69 22	96.60 8	93.28 21	96.87 8	96.64 28	97.27 2	96.64 32	96.33 33	98.44 33	98.56 20

HPM-MVS++		97.22 10	97.40 11	97.01 12	99.08 4	98.55 23	98.19 14	96.48 6	96.02 20	93.28 21	96.26 17	98.71 7	96.76 17	97.30 14	96.25 35	98.30 50	98.68 13

3Dnovator+	90.56 5	95.06 37	94.56 43	95.65 32	98.11 32	98.15 41	97.19 34	91.59 53	95.11 31	93.23 23	81.99 100	94.71 43	95.43 36	96.48 36	96.88 17	98.35 42	98.63 16

CP-MVS		96.68 20	96.59 26	96.77 18	98.85 22	98.58 21	98.18 15	95.51 27	95.34 26	92.94 24	95.21 28	96.25 31	96.79 15	96.44 39	95.77 46	98.35 42	98.56 20

ACMMPR		96.92 17	96.96 18	96.87 16	98.99 12	98.78 10	98.38 10	95.52 25	96.57 9	92.81 25	96.06 20	95.90 36	97.07 5	96.60 34	96.34 32	98.46 29	98.42 33

NCCC		96.75 19	96.67 24	96.85 17	99.03 9	98.44 33	98.15 16	96.28 10	96.32 12	92.39 26	92.16 35	97.55 19	96.68 19	97.32 12	96.65 21	98.55 21	98.26 37

CPTT-MVS		95.54 32	95.07 36	96.10 26	97.88 36	97.98 47	97.92 24	94.86 33	94.56 40	92.16 27	91.01 42	95.71 37	96.97 9	94.56 78	93.50 87	96.81 150	98.14 44

DeepC-MVS_fast	93.32 1	96.48 22	96.42 27	96.56 21	98.70 26	98.31 37	97.97 22	95.76 21	96.31 13	92.01 28	91.43 40	95.42 40	96.46 22	97.65 10	97.69 1	98.49 26	98.12 46
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SteuartSystems-ACMMP		97.10 14	97.49 9	96.65 19	98.97 13	98.95 8	98.43 8	95.96 18	95.12 29	91.46 29	96.85 9	97.60 17	96.37 24	97.76 5	97.16 10	98.68 14	98.97 10
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator	90.28 7	94.70 43	94.34 48	95.11 36	98.06 33	98.21 38	96.89 38	91.03 59	94.72 38	91.45 30	82.87 91	93.10 50	94.61 41	96.24 45	97.08 12	98.63 17	98.16 42

abl_6				94.78 38	97.46 43	97.99 46	95.76 52	91.80 50	93.72 46	91.25 31	91.33 41	96.47 29	94.28 48			98.14 67	97.39 76

TSAR-MVS + GP.		95.86 28	96.95 20	94.60 43	94.07 82	98.11 42	96.30 44	91.76 51	95.67 21	91.07 32	96.82 10	97.69 16	95.71 32	95.96 49	95.75 47	98.68 14	98.63 16

CANet		94.85 39	94.92 37	94.78 38	97.25 48	98.52 26	97.20 33	91.81 49	93.25 49	91.06 33	86.29 66	94.46 44	92.99 66	97.02 23	96.68 19	98.34 44	98.20 40

ACMMP_NAP		96.93 16	97.27 14	96.53 24	99.06 5	98.95 8	98.24 13	96.06 15	95.66 22	90.96 34	95.63 24	97.71 15	96.53 20	97.66 9	96.68 19	98.30 50	98.61 19

MCST-MVS		96.83 18	97.06 16	96.57 20	98.88 21	98.47 31	98.02 21	96.16 14	95.58 24	90.96 34	95.78 23	97.84 13	96.46 22	97.00 24	96.17 37	98.94 5	98.55 25

MP-MVS		96.56 21	96.72 22	96.37 25	98.93 19	98.48 29	98.04 20	95.55 24	94.32 41	90.95 36	95.88 22	97.02 25	96.29 25	96.77 30	96.01 43	98.47 27	98.56 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PVSNet_BlendedMVS		92.80 57	92.44 65	93.23 55	96.02 61	97.83 51	93.74 87	90.58 61	91.86 61	90.69 37	85.87 72	82.04 105	90.01 94	96.39 40	95.26 54	98.34 44	97.81 61

PVSNet_Blended		92.80 57	92.44 65	93.23 55	96.02 61	97.83 51	93.74 87	90.58 61	91.86 61	90.69 37	85.87 72	82.04 105	90.01 94	96.39 40	95.26 54	98.34 44	97.81 61

PGM-MVS		96.16 24	96.33 28	95.95 27	99.04 7	98.63 18	98.32 12	92.76 43	93.42 48	90.49 39	96.30 16	95.31 41	96.71 18	96.46 37	96.02 42	98.38 41	98.19 41

OMC-MVS		94.49 44	94.36 46	94.64 41	97.17 49	97.73 55	95.49 56	92.25 45	96.18 14	90.34 40	88.51 54	92.88 51	94.90 40	94.92 65	94.17 69	97.69 102	96.15 117

DELS-MVS		93.71 51	93.47 52	94.00 45	96.82 54	98.39 35	96.80 39	91.07 58	89.51 94	89.94 41	83.80 84	89.29 71	90.95 87	97.32 12	97.65 2	98.42 36	98.32 36
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
ACMMP		95.54 32	95.49 34	95.61 33	98.27 31	98.53 25	97.16 35	94.86 33	94.88 35	89.34 42	95.36 27	91.74 55	95.50 35	95.51 56	94.16 70	98.50 24	98.22 39
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
DeepPCF-MVS	92.65 2	95.50 34	96.96 18	93.79 51	96.44 57	98.21 38	93.51 93	94.08 37	96.94 3	89.29 43	93.08 31	96.77 27	93.82 55	97.68 8	97.40 4	95.59 173	98.65 15

EPNet		93.92 49	94.40 45	93.36 54	97.89 35	96.55 85	96.08 47	92.14 46	91.65 64	89.16 44	94.07 30	90.17 70	87.78 121	95.24 59	94.97 59	97.09 129	98.15 43
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CLD-MVS		92.50 62	91.96 73	93.13 58	93.93 88	96.24 93	95.69 53	88.77 81	92.92 50	89.01 45	88.19 57	81.74 108	93.13 65	93.63 96	93.08 100	98.23 59	97.91 58
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DPM-MVS		95.07 36	94.84 38	95.34 35	97.44 44	97.49 61	97.76 26	95.52 25	94.88 35	88.92 46	87.25 59	96.44 30	94.41 43	95.78 52	96.11 40	97.99 82	95.95 122

DeepC-MVS	92.10 3	95.22 35	94.77 40	95.75 31	97.77 38	98.54 24	97.63 28	95.96 18	95.07 32	88.85 47	85.35 74	91.85 54	95.82 29	96.88 27	97.10 11	98.44 33	98.63 16
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVS_111021_LR		94.84 40	95.57 32	94.00 45	97.11 50	97.72 57	94.88 63	91.16 57	95.24 28	88.74 48	96.03 21	91.52 58	94.33 47	95.96 49	95.01 58	97.79 92	97.49 73

MVSTER		91.73 72	91.61 78	91.86 74	93.18 100	94.56 109	94.37 67	87.90 94	90.16 85	88.69 49	89.23 51	81.28 110	88.92 114	95.75 53	93.95 76	98.12 69	96.37 108

IB-MVS	85.10 14	87.98 114	87.97 115	87.99 119	94.55 76	96.86 81	84.52 190	88.21 89	86.48 123	88.54 50	74.41 140	77.74 132	74.10 197	89.65 167	92.85 106	98.06 76	97.80 63
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
CS-MVS		94.03 48	94.83 39	93.09 61	93.25 98	97.39 63	95.10 59	87.26 106	91.48 67	88.41 51	89.96 48	93.41 48	95.72 31	97.06 21	96.55 24	98.81 6	98.00 50

XVS					95.68 63	98.66 13	94.96 61			88.03 52		96.06 32				98.46 29

X-MVStestdata					95.68 63	98.66 13	94.96 61			88.03 52		96.06 32				98.46 29

X-MVS		96.07 26	96.33 28	95.77 30	98.94 17	98.66 13	97.94 23	95.41 31	95.12 29	88.03 52	93.00 32	96.06 32	95.85 28	96.65 31	96.35 29	98.47 27	98.48 29

PHI-MVS		95.86 28	96.93 21	94.61 42	97.60 42	98.65 17	96.49 41	93.13 41	94.07 43	87.91 55	97.12 7	97.17 24	93.90 54	96.46 37	96.93 16	98.64 16	98.10 48

train_agg		96.15 25	96.64 25	95.58 34	98.44 28	98.03 44	98.14 18	95.40 32	93.90 45	87.72 56	96.26 17	98.10 9	95.75 30	96.25 44	95.45 51	98.01 80	98.47 30

ETV-MVS		93.80 50	94.57 42	92.91 64	93.98 84	97.50 60	93.62 90	88.70 82	91.95 60	87.57 57	90.21 47	90.79 62	94.56 42	97.20 16	96.35 29	99.02 1	97.98 51

canonicalmvs		93.08 55	93.09 55	93.07 62	94.24 78	97.86 49	95.45 57	87.86 98	94.00 44	87.47 58	88.32 55	82.37 103	95.13 38	93.96 94	96.41 27	98.27 54	98.73 12

PVSNet_Blended_VisFu		91.92 68	92.39 67	91.36 85	95.45 71	97.85 50	92.25 111	89.54 74	88.53 104	87.47 58	79.82 110	90.53 66	85.47 146	96.31 43	95.16 57	97.99 82	98.56 20

test_part1		87.53 118	84.97 147	90.52 89	92.11 118	93.31 141	93.32 97	85.79 117	79.56 172	87.38 60	62.89 192	78.60 123	89.25 105	90.65 150	92.17 118	95.24 180	97.62 67

ACMM	88.76 10	91.70 74	90.43 88	93.19 57	95.56 66	95.14 106	93.35 96	91.48 54	92.26 59	87.12 61	84.02 82	79.34 118	93.99 51	94.07 89	92.68 108	97.62 109	95.50 131
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
dps		85.00 147	83.21 167	87.08 129	90.73 138	92.55 165	89.34 152	75.29 192	84.94 131	87.01 62	79.27 112	67.69 169	87.27 128	84.22 197	83.56 197	92.83 193	90.25 185

MVS_0304		94.30 46	94.68 41	93.86 50	96.33 59	98.48 29	97.41 31	91.20 55	92.75 53	86.96 63	86.03 69	93.81 47	92.64 70	96.89 26	96.54 25	98.61 18	98.24 38

PatchMatch-RL		90.30 90	88.93 102	91.89 73	95.41 72	95.68 101	90.94 124	88.67 83	89.80 90	86.95 64	85.90 70	72.51 147	92.46 71	93.56 99	92.18 117	96.93 142	92.89 167

EIA-MVS		92.72 59	92.96 58	92.44 67	93.86 91	97.76 53	93.13 99	88.65 84	89.78 91	86.68 65	86.69 63	87.57 72	93.74 56	96.07 48	95.32 52	98.58 19	97.53 71

TSAR-MVS + ACMM		96.19 23	97.39 12	94.78 38	97.70 40	98.41 34	97.72 27	95.49 28	96.47 10	86.66 66	96.35 15	97.85 12	93.99 51	97.19 18	96.37 28	97.12 127	99.13 6

OpenMVS	88.18 11	92.51 61	91.61 78	93.55 53	97.74 39	98.02 45	95.66 54	90.46 63	89.14 97	86.50 67	75.80 133	90.38 69	92.69 69	94.99 62	95.30 53	98.27 54	97.63 65

MSDG		90.42 89	88.25 109	92.94 63	96.67 56	94.41 115	93.96 78	92.91 42	89.59 93	86.26 68	76.74 125	80.92 112	90.43 93	92.60 116	92.08 122	97.44 115	91.41 174

casdiffmvs		91.72 73	91.16 83	92.38 69	93.16 101	97.15 71	93.95 79	89.49 75	91.58 66	86.03 69	80.75 107	80.95 111	93.16 64	95.25 58	95.22 56	98.50 24	97.23 82

MVS_111021_HR		94.84 40	95.91 30	93.60 52	97.35 45	98.46 32	95.08 60	91.19 56	94.18 42	85.97 70	95.38 26	92.56 52	93.61 58	96.61 33	96.25 35	98.40 38	97.92 56

TAPA-MVS	90.35 6	93.69 52	93.52 51	93.90 48	96.89 53	97.62 58	96.15 45	91.67 52	94.94 33	85.97 70	87.72 58	91.96 53	94.40 44	93.76 95	93.06 102	98.30 50	95.58 130
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DI_MVS_plusplus_trai		91.05 80	90.15 92	92.11 71	92.67 114	96.61 83	96.03 48	88.44 86	90.25 80	85.92 72	73.73 141	84.89 87	91.92 76	94.17 87	94.07 74	97.68 103	97.31 80

Anonymous20231211		89.82 96	88.18 110	91.74 75	92.52 115	96.09 97	93.38 95	89.30 77	88.95 99	85.90 73	64.55 188	84.39 88	92.41 73	92.24 123	93.06 102	96.93 142	97.95 53

UGNet		91.52 75	93.41 53	89.32 104	94.13 79	97.15 71	91.83 121	89.01 78	90.62 74	85.86 74	86.83 60	91.73 56	77.40 186	94.68 74	94.43 65	97.71 99	98.40 35
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
MAR-MVS		92.71 60	92.63 61	92.79 65	97.70 40	97.15 71	93.75 86	87.98 92	90.71 71	85.76 75	86.28 67	86.38 77	94.35 46	94.95 63	95.49 50	97.22 120	97.44 74
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
baseline		91.19 78	91.89 74	90.38 90	92.76 110	95.04 107	93.55 92	84.54 131	92.92 50	85.71 76	86.68 64	86.96 74	89.28 104	92.00 127	92.62 110	96.46 155	96.99 89

QAPM		94.13 47	94.33 49	93.90 48	97.82 37	98.37 36	96.47 42	90.89 60	92.73 55	85.63 77	85.35 74	93.87 45	94.17 49	95.71 54	95.90 45	98.40 38	98.42 33

DCV-MVSNet		91.24 77	91.26 81	91.22 86	92.84 109	93.44 136	93.82 84	86.75 109	91.33 69	85.61 78	84.00 83	85.46 84	91.27 82	92.91 110	93.62 82	97.02 133	98.05 49

GBi-Net		90.21 91	90.11 93	90.32 92	88.66 156	93.65 132	94.25 72	85.78 118	90.03 86	85.56 79	77.38 118	86.13 78	89.38 101	93.97 91	94.16 70	98.31 47	95.47 132

test1		90.21 91	90.11 93	90.32 92	88.66 156	93.65 132	94.25 72	85.78 118	90.03 86	85.56 79	77.38 118	86.13 78	89.38 101	93.97 91	94.16 70	98.31 47	95.47 132

FMVSNet3		90.19 93	90.06 95	90.34 91	88.69 155	93.85 124	94.58 64	85.78 118	90.03 86	85.56 79	77.38 118	86.13 78	89.22 108	93.29 107	94.36 67	98.20 62	95.40 136

ACMP	89.13 9	92.03 66	91.70 77	92.41 68	94.92 74	96.44 91	93.95 79	89.96 66	91.81 63	85.48 82	90.97 43	79.12 119	92.42 72	93.28 108	92.55 111	97.76 95	97.74 64
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
tpm cat1		84.13 159	81.99 179	86.63 135	91.74 122	91.50 186	90.68 126	75.69 191	86.12 124	85.44 83	72.39 150	70.72 154	85.16 148	80.89 205	81.56 201	91.07 203	90.71 181

diffmvs		91.37 76	91.09 84	91.70 76	92.71 113	96.47 88	94.03 77	88.78 80	92.74 54	85.43 84	83.63 86	80.37 113	91.76 79	93.39 104	93.78 78	97.50 112	97.23 82

CostFormer		86.78 125	86.05 135	87.62 126	92.15 117	93.20 146	91.55 123	75.83 190	88.11 107	85.29 85	81.76 101	76.22 141	87.80 120	84.45 196	85.21 192	93.12 190	93.42 162

RPSCF		89.68 98	89.24 99	90.20 95	92.97 105	92.93 155	92.30 108	87.69 100	90.44 78	85.12 86	91.68 39	85.84 83	90.69 90	87.34 184	86.07 186	92.46 196	90.37 184

PCF-MVS	90.19 8	92.98 56	92.07 71	94.04 44	96.39 58	97.87 48	96.03 48	95.47 30	87.16 112	85.09 87	84.81 78	93.21 49	93.46 61	91.98 128	91.98 125	97.78 93	97.51 72
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
FMVSNet2		89.61 99	89.14 100	90.16 97	88.66 156	93.65 132	94.25 72	85.44 122	88.57 103	84.96 88	73.53 143	83.82 90	89.38 101	94.23 84	94.68 64	98.31 47	95.47 132

CS-MVS-test		93.31 54	94.43 44	92.01 72	92.93 107	97.30 65	94.24 75	85.81 116	92.49 56	84.71 89	88.25 56	91.18 60	95.59 33	97.14 19	95.98 44	98.81 6	98.68 13

CHOSEN 280x420		90.77 85	92.14 70	89.17 107	93.86 91	92.81 159	93.16 98	80.22 176	90.21 82	84.67 90	89.89 49	91.38 59	90.57 92	94.94 64	92.11 120	92.52 195	93.65 159

EPP-MVSNet		92.13 65	93.06 56	91.05 87	93.66 96	97.30 65	92.18 112	87.90 94	90.24 81	83.63 91	86.14 68	90.52 68	90.76 89	94.82 70	94.38 66	98.18 64	97.98 51

MVS_Test		91.81 71	92.19 69	91.37 84	93.24 99	96.95 78	94.43 65	86.25 112	91.45 68	83.45 92	86.31 65	85.15 85	92.93 67	93.99 90	94.71 63	97.92 86	96.77 95

FC-MVSNet-train		90.55 87	90.19 91	90.97 88	93.78 93	95.16 105	92.11 116	88.85 79	87.64 109	83.38 93	84.36 81	78.41 126	89.53 98	94.69 73	93.15 99	98.15 65	97.92 56

CDPH-MVS		94.80 42	95.50 33	93.98 47	98.34 29	98.06 43	97.41 31	93.23 40	92.81 52	82.98 94	92.51 34	94.82 42	93.53 59	96.08 47	96.30 34	98.42 36	97.94 54

baseline1		90.81 83	90.29 89	91.42 81	93.67 95	95.86 100	93.94 81	89.69 72	89.29 96	82.85 95	82.91 90	80.30 114	89.60 97	95.05 61	94.79 62	98.80 8	93.82 157

FMVSNet1		87.33 120	86.00 138	88.89 108	87.13 182	92.83 158	93.08 101	84.46 132	81.35 160	82.20 96	66.33 175	77.96 129	88.96 111	93.97 91	94.16 70	97.54 111	95.38 137

OPM-MVS		91.08 79	89.34 98	93.11 60	96.18 60	96.13 96	96.39 43	92.39 44	82.97 152	81.74 97	82.55 97	80.20 115	93.97 53	94.62 75	93.23 94	98.00 81	95.73 126

thisisatest0530		91.04 81	91.74 75	90.21 94	92.93 107	97.00 76	92.06 117	87.63 103	90.74 70	81.51 98	86.81 61	82.48 100	89.23 106	94.81 71	93.03 104	97.90 87	97.33 79

tttt0517		91.01 82	91.71 76	90.19 96	92.98 103	97.07 75	91.96 120	87.63 103	90.61 75	81.42 99	86.76 62	82.26 104	89.23 106	94.86 69	93.03 104	97.90 87	97.36 77

GeoE		89.29 105	88.68 104	89.99 99	92.75 112	96.03 98	93.07 102	83.79 140	86.98 114	81.34 100	74.72 138	78.92 120	91.22 83	93.31 106	93.21 96	97.78 93	97.60 70

thres200		89.49 101	87.72 118	91.55 78	93.95 86	97.25 68	94.34 69	89.74 69	85.66 128	81.18 101	76.12 132	70.19 159	91.80 77	94.92 65	93.51 84	98.27 54	96.40 107

thres100view900		89.36 103	87.61 121	91.39 82	93.90 89	96.86 81	94.35 68	89.66 73	85.87 125	81.15 102	76.46 127	70.38 156	91.17 84	94.09 88	93.43 90	98.13 68	96.16 116

tfpn200view9		89.55 100	87.86 116	91.53 79	93.90 89	97.26 67	94.31 71	89.74 69	85.87 125	81.15 102	76.46 127	70.38 156	91.76 79	94.92 65	93.51 84	98.28 53	96.61 99

thres400		89.40 102	87.58 123	91.53 79	94.06 83	97.21 70	94.19 76	89.83 68	85.69 127	81.08 104	75.50 135	69.76 160	91.80 77	94.79 72	93.51 84	98.20 62	96.60 100

pmmvs4		86.00 135	84.28 154	88.00 118	87.80 167	92.01 178	89.94 143	84.91 126	86.79 117	80.98 105	73.41 146	66.34 177	88.12 119	89.31 170	88.90 179	96.24 160	93.20 165

baseline2		88.97 107	89.50 97	88.36 113	91.14 132	95.30 102	90.13 138	85.17 125	87.24 111	80.80 106	84.46 80	78.44 125	85.60 143	93.54 100	91.87 126	97.31 117	95.66 127

ET-MVSNet_ETH3D		89.93 94	90.84 86	88.87 109	79.60 208	96.19 94	94.43 65	86.56 110	90.63 73	80.75 107	90.71 44	77.78 131	93.73 57	91.36 136	93.45 89	98.15 65	95.77 125

thres600view7		89.28 106	87.47 126	91.39 82	94.12 80	97.25 68	93.94 81	89.74 69	85.62 130	80.63 108	75.24 137	69.33 161	91.66 81	94.92 65	93.23 94	98.27 54	96.72 96

PMMVS		89.88 95	91.19 82	88.35 114	89.73 146	91.97 179	90.62 127	81.92 163	90.57 76	80.58 109	92.16 35	86.85 76	91.17 84	92.31 120	91.35 136	96.11 161	93.11 166

TSAR-MVS + COLMAP		92.39 63	92.31 68	92.47 66	95.35 73	96.46 89	96.13 46	92.04 48	95.33 27	80.11 110	94.95 29	77.35 135	94.05 50	94.49 81	93.08 100	97.15 124	94.53 146

IS_MVSNet		91.87 69	93.35 54	90.14 98	94.09 81	97.73 55	93.09 100	88.12 90	88.71 101	79.98 111	84.49 79	90.63 65	87.49 125	97.07 20	96.96 15	98.07 74	97.88 60

HQP-MVS		92.39 63	92.49 64	92.29 70	95.65 65	95.94 99	95.64 55	92.12 47	92.46 58	79.65 112	91.97 37	82.68 99	92.92 68	93.47 102	92.77 107	97.74 97	98.12 46

CDS-MVSNet		88.34 112	88.71 103	87.90 121	90.70 140	94.54 110	92.38 106	86.02 113	80.37 164	79.42 113	79.30 111	83.43 92	82.04 169	93.39 104	94.01 75	96.86 148	95.93 123
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LS3D		91.97 67	90.98 85	93.12 59	97.03 52	97.09 74	95.33 58	95.59 23	92.47 57	79.26 114	81.60 103	82.77 98	94.39 45	94.28 82	94.23 68	97.14 126	94.45 148

UA-Net		90.81 83	92.58 62	88.74 111	94.87 75	97.44 62	92.61 104	88.22 88	82.35 155	78.93 115	85.20 76	95.61 38	79.56 181	96.52 35	96.57 23	98.23 59	94.37 149

IterMVS-LS		88.60 108	88.45 105	88.78 110	92.02 120	92.44 169	92.00 119	83.57 144	86.52 121	78.90 116	78.61 115	81.34 109	89.12 109	90.68 149	93.18 97	97.10 128	96.35 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LGP-MVS_train		91.83 70	92.04 72	91.58 77	95.46 69	96.18 95	95.97 50	89.85 67	90.45 77	77.76 117	91.92 38	80.07 116	92.34 74	94.27 83	93.47 88	98.11 71	97.90 59

Fast-Effi-MVS+		88.56 110	87.99 113	89.22 105	91.56 126	95.21 103	92.29 109	82.69 151	86.82 115	77.73 118	76.24 130	73.39 145	93.36 62	94.22 85	93.64 80	97.65 105	96.43 105

DROMVSNet		88.56 110	87.99 113	89.22 105	91.56 126	95.21 103	92.29 109	82.69 151	86.82 115	77.73 118	76.24 130	73.39 145	93.36 62	94.22 85	93.64 80	97.65 105	96.43 105

UniMVSNet_ETH3D		84.57 151	81.40 185	88.28 115	89.34 150	94.38 117	90.33 130	86.50 111	74.74 197	77.52 120	59.90 199	62.04 196	88.78 117	88.82 177	92.65 109	97.22 120	97.24 81

CHOSEN 1792x2688		88.57 109	87.82 117	89.44 103	95.46 69	96.89 80	93.74 87	85.87 115	89.63 92	77.42 121	61.38 195	83.31 93	88.80 116	93.44 103	93.16 98	95.37 178	96.95 91

HyFIR lowres test		87.87 115	86.42 132	89.57 101	95.56 66	96.99 77	92.37 107	84.15 135	86.64 118	77.17 122	57.65 201	83.97 89	91.08 86	92.09 126	92.44 112	97.09 129	95.16 139

MDTV_nov1_ep13		86.64 127	87.50 125	85.65 142	90.73 138	93.69 130	89.96 142	78.03 185	89.48 95	76.85 123	84.92 77	82.42 102	86.14 140	86.85 188	86.15 185	92.17 197	88.97 192

Effi-MVS+		89.79 97	89.83 96	89.74 100	92.98 103	96.45 90	93.48 94	84.24 133	87.62 110	76.45 124	81.76 101	77.56 134	93.48 60	94.61 76	93.59 83	97.82 91	97.22 84

MS-PatchMatch		87.63 116	87.61 121	87.65 124	93.95 86	94.09 120	92.60 105	81.52 168	86.64 118	76.41 125	73.46 145	85.94 81	85.01 150	92.23 124	90.00 165	96.43 157	90.93 180

Vis-MVSNet (Re-imp)		90.54 88	92.76 60	87.94 120	93.73 94	96.94 79	92.17 114	87.91 93	88.77 100	76.12 126	83.68 85	90.80 61	79.49 182	96.34 42	96.35 29	98.21 61	96.46 104

COLMAP_ROB	84.39 15	87.61 117	86.03 136	89.46 102	95.54 68	94.48 112	91.77 122	90.14 65	87.16 112	75.50 127	73.41 146	76.86 139	87.33 127	90.05 161	89.76 171	96.48 154	90.46 183
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Vis-MVSNet		89.36 103	91.49 80	86.88 131	92.10 119	97.60 59	92.16 115	85.89 114	84.21 141	75.20 128	82.58 95	87.13 73	77.40 186	95.90 51	95.63 48	98.51 22	97.36 77
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet (Re)		86.22 130	85.46 146	87.11 128	88.34 160	94.42 114	89.65 150	87.10 108	84.39 138	74.61 129	70.41 159	68.10 166	85.10 149	91.17 140	91.79 128	97.84 90	97.94 54

EPMVS		85.77 136	86.24 134	85.23 148	92.76 110	93.78 126	89.91 144	73.60 198	90.19 83	74.22 130	82.18 99	78.06 128	87.55 124	85.61 193	85.38 191	93.32 189	88.48 196

Baseline_NR-MVSNet		85.28 144	83.42 162	87.46 127	87.77 169	90.80 194	89.90 146	87.69 100	83.93 146	74.16 131	64.72 186	66.43 176	87.48 126	90.14 156	90.83 140	97.73 98	97.11 87

FMVSNet5		84.47 156	84.72 151	84.18 162	83.30 203	88.43 200	88.09 168	79.42 179	84.25 140	74.14 132	73.15 148	78.74 121	83.65 160	91.19 139	91.19 138	96.46 155	86.07 201

v148		83.61 167	82.10 176	85.37 144	87.34 176	92.94 154	87.48 172	85.72 121	78.92 174	73.87 133	65.71 180	64.69 187	81.78 173	87.82 180	89.35 175	96.01 162	95.26 138

TAMVS		84.94 149	84.95 148	84.93 151	88.82 152	93.18 147	88.44 166	81.28 170	77.16 184	73.76 134	75.43 136	76.57 140	82.04 169	90.59 151	90.79 141	95.22 181	90.94 179

UniMVSNet_NR-MVSNet		86.80 124	85.86 141	87.89 122	88.17 162	94.07 121	90.15 136	88.51 85	84.20 142	73.45 135	72.38 151	70.30 158	88.95 112	90.25 155	92.21 116	98.12 69	97.62 67

DU-MVS		86.12 132	84.81 150	87.66 123	87.77 169	93.78 126	90.15 136	87.87 96	84.40 136	73.45 135	70.59 156	64.82 186	88.95 112	90.14 156	92.33 113	97.76 95	97.62 67

thisisatest0515		85.70 137	87.00 127	84.19 161	88.16 163	93.67 131	84.20 192	84.14 136	83.39 150	72.91 137	76.79 124	74.75 144	78.82 184	92.57 117	91.26 137	96.94 139	96.56 103

SCA		86.25 128	87.52 124	84.77 152	91.59 124	93.90 123	89.11 157	73.25 202	90.38 79	72.84 138	83.26 87	83.79 91	88.49 118	86.07 191	85.56 189	93.33 188	89.67 189

tpmrst		83.72 166	83.45 160	84.03 164	92.21 116	91.66 183	88.74 163	73.58 199	88.14 106	72.67 139	77.37 121	72.11 150	86.34 136	82.94 201	82.05 200	90.63 205	89.86 188

PatchmatchNet		85.70 137	86.65 129	84.60 155	91.79 121	93.40 137	89.27 153	73.62 197	90.19 83	72.63 140	82.74 94	81.93 107	87.64 122	84.99 194	84.29 196	92.64 194	89.00 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pm-mvs1		84.55 152	83.46 159	85.82 139	88.16 163	93.39 138	89.05 159	85.36 124	74.03 198	72.43 141	65.08 183	71.11 153	82.30 168	93.48 101	91.70 130	97.64 107	95.43 135

ACMH+	85.75 12	87.19 122	86.02 137	88.56 112	93.42 97	94.41 115	89.91 144	87.66 102	83.45 149	72.25 142	76.42 129	71.99 151	90.78 88	89.86 162	90.94 139	97.32 116	95.11 141

NR-MVSNet		85.46 142	84.54 152	86.52 136	88.33 161	93.78 126	90.45 129	87.87 96	84.40 136	71.61 143	70.59 156	62.09 195	82.79 165	91.75 130	91.75 129	98.10 72	97.44 74

Effi-MVS+-dtu		87.51 119	88.13 111	86.77 133	91.10 133	94.90 108	90.91 125	82.67 153	83.47 148	71.55 144	81.11 106	77.04 136	89.41 100	92.65 115	91.68 132	95.00 185	96.09 119

v8		84.45 157	83.30 166	85.80 140	87.53 174	92.95 153	90.31 132	82.46 157	80.46 163	71.43 145	66.99 170	67.16 171	86.14 140	89.26 171	90.22 157	96.94 139	96.06 120

pmmvs-eth3d		79.78 193	77.58 198	82.34 185	81.57 206	87.46 204	82.92 194	81.28 170	75.33 196	71.34 146	61.88 193	52.41 212	81.59 175	87.56 182	86.90 184	95.36 179	91.48 173

TDRefinement		84.97 148	83.39 163	86.81 132	92.97 105	94.12 119	92.18 112	87.77 99	82.78 153	71.31 147	68.43 165	68.07 167	81.10 177	89.70 166	89.03 178	95.55 175	91.62 172

V42		84.48 155	83.36 165	85.79 141	87.14 181	93.28 143	90.03 139	83.98 138	80.30 165	71.20 148	66.90 172	67.17 170	85.55 144	89.35 168	90.27 155	96.82 149	96.27 114

CR-MVSNet		85.48 141	86.29 133	84.53 157	91.08 135	92.10 173	89.18 155	73.30 200	84.75 132	71.08 149	73.12 149	77.91 130	86.27 138	91.48 133	90.75 144	96.27 159	93.94 154

Patchmtry						92.39 170	89.18 155	73.30 200		71.08 149

PatchT		83.86 163	85.51 145	81.94 187	88.41 159	91.56 185	78.79 204	71.57 204	84.08 144	71.08 149	70.62 155	76.13 142	86.27 138	91.48 133	90.75 144	95.52 176	93.94 154

USDC		86.73 126	85.96 139	87.63 125	91.64 123	93.97 122	92.76 103	84.58 130	88.19 105	70.67 152	80.10 109	67.86 168	89.43 99	91.81 129	89.77 170	96.69 152	90.05 187

tfpnnormal		83.80 165	81.26 187	86.77 133	89.60 147	93.26 145	89.72 149	87.60 105	72.78 199	70.44 153	60.53 198	61.15 200	85.55 144	92.72 112	91.44 134	97.71 99	96.92 92

pmmvs6		80.90 188	78.77 194	83.38 172	85.84 194	91.61 184	86.01 185	82.54 155	64.17 211	70.43 154	54.14 208	67.06 172	80.73 178	90.50 153	89.17 177	94.74 186	94.75 144

ACMH	85.51 13	87.31 121	86.59 130	88.14 117	93.96 85	94.51 111	89.00 160	87.99 91	81.58 158	70.15 155	78.41 116	71.78 152	90.60 91	91.30 137	91.99 124	97.17 123	96.58 101
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TranMVSNet+NR-MVSNet		85.57 140	84.41 153	86.92 130	87.67 172	93.34 139	90.31 132	88.43 87	83.07 151	70.11 156	69.99 162	65.28 181	86.96 130	89.73 164	92.27 114	98.06 76	97.17 86

TinyColmap		84.04 161	82.01 178	86.42 137	90.87 136	91.84 180	88.89 162	84.07 137	82.11 157	69.89 157	71.08 154	60.81 201	89.04 110	90.52 152	89.19 176	95.76 165	88.50 195

v2v482		84.51 153	83.05 169	86.20 138	87.25 178	93.28 143	90.22 134	85.40 123	79.94 170	69.78 158	67.74 167	65.15 183	87.57 123	89.12 173	90.55 150	96.97 135	95.60 129

MIMVSNet		82.97 176	84.00 156	81.77 189	82.23 204	92.25 172	87.40 175	72.73 203	81.48 159	69.55 159	68.79 164	72.42 148	81.82 172	92.23 124	92.25 115	96.89 145	88.61 194

ADS-MVSNet		84.08 160	84.95 148	83.05 177	91.53 129	91.75 182	88.16 167	70.70 206	89.96 89	69.51 160	78.83 113	76.97 138	86.29 137	84.08 198	84.60 194	92.13 199	88.48 196

test-LLR		86.88 123	88.28 107	85.24 147	91.22 130	92.07 175	87.41 173	83.62 142	84.58 134	69.33 161	83.00 88	82.79 96	84.24 154	92.26 121	89.81 168	95.64 171	93.44 160

TESTMET0.1,1		86.11 133	88.28 107	83.59 168	87.80 167	92.07 175	87.41 173	77.12 187	84.58 134	69.33 161	83.00 88	82.79 96	84.24 154	92.26 121	89.81 168	95.64 171	93.44 160

v10		84.18 158	83.17 168	85.37 144	87.34 176	92.68 161	90.32 131	81.33 169	79.93 171	69.23 163	66.33 175	65.74 179	87.03 129	90.84 144	90.38 152	96.97 135	96.29 113

RPMNet		84.82 150	85.90 140	83.56 169	91.10 133	92.10 173	88.73 164	71.11 205	84.75 132	68.79 164	73.56 142	77.62 133	85.33 147	90.08 160	89.43 174	96.32 158	93.77 158

CANet_DTU		90.74 86	92.93 59	88.19 116	94.36 77	96.61 83	94.34 69	84.66 128	90.66 72	68.75 165	90.41 46	86.89 75	89.78 96	95.46 57	94.87 60	97.25 119	95.62 128

CMPMVS	61.19 17	79.86 192	77.46 200	82.66 182	91.54 128	91.82 181	83.25 193	81.57 167	70.51 206	68.64 166	59.89 200	66.77 174	79.63 180	84.00 199	84.30 195	91.34 201	84.89 204
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test-mter		86.09 134	88.38 106	83.43 171	87.89 166	92.61 163	86.89 178	77.11 188	84.30 139	68.62 167	82.57 96	82.45 101	84.34 153	92.40 119	90.11 162	95.74 166	94.21 152

tmp_tt				50.24 211	68.55 214	46.86 219	48.90 219	18.28 218	86.51 122	68.32 168	70.19 160	65.33 180	26.69 217	74.37 209	66.80 211	70.72 217

TransMVSNet (Re)		82.67 179	80.93 190	84.69 154	88.71 154	91.50 186	87.90 169	87.15 107	71.54 204	68.24 169	63.69 190	64.67 188	78.51 185	91.65 132	90.73 146	97.64 107	92.73 170

WR-MVS_H		82.86 178	82.66 172	83.10 175	87.44 175	93.33 140	85.71 188	83.20 149	77.36 183	68.20 170	66.37 174	65.23 182	76.05 192	89.35 168	90.13 158	97.99 82	96.89 93

v1144		84.03 162	82.88 170	85.37 144	87.17 180	93.15 150	90.18 135	83.31 147	78.83 175	67.85 171	65.99 177	64.99 184	86.79 132	90.75 146	90.33 154	96.90 144	96.15 117

test0.0.03 1		85.58 139	87.69 120	83.11 174	91.22 130	92.54 166	85.60 189	83.62 142	85.66 128	67.84 172	82.79 93	79.70 117	73.51 199	91.15 141	90.79 141	96.88 146	91.23 177

CP-MVSNet		83.11 175	82.15 175	84.23 160	87.20 179	92.70 160	86.42 182	83.53 145	77.83 181	67.67 173	66.89 173	60.53 203	82.47 166	89.23 172	90.65 148	98.08 73	97.20 85

MVS-HIRNet		78.16 195	77.57 199	78.83 195	85.83 195	87.76 202	76.67 205	70.22 207	75.82 194	67.39 174	55.61 203	70.52 155	81.96 171	86.67 189	85.06 193	90.93 204	81.58 207

v144192		83.48 169	82.23 174	84.94 150	86.65 188	92.84 156	89.63 151	82.48 156	77.87 180	67.36 175	65.33 182	63.50 189	86.51 134	89.72 165	89.99 166	97.03 132	96.35 109

pmmvs5		83.37 170	82.68 171	84.18 162	87.13 182	93.18 147	86.74 179	82.08 162	76.48 188	67.28 176	71.26 153	62.70 192	84.71 151	90.77 145	90.12 161	97.15 124	94.24 150

PM-MVS		80.29 190	79.30 193	81.45 190	81.91 205	88.23 201	82.61 195	79.01 180	79.99 169	67.15 177	69.07 163	51.39 213	82.92 164	87.55 183	85.59 188	95.08 182	93.28 163

tpm		83.16 172	83.64 157	82.60 183	90.75 137	91.05 189	88.49 165	73.99 195	82.36 154	67.08 178	78.10 117	68.79 162	84.17 156	85.95 192	85.96 187	91.09 202	93.23 164

v1192		83.56 168	82.35 173	84.98 149	86.84 187	92.84 156	90.01 141	82.70 150	78.54 176	66.48 179	64.88 185	62.91 190	86.91 131	90.72 147	90.25 156	96.94 139	96.32 111

WR-MVS		83.14 173	83.38 164	82.87 179	87.55 173	93.29 142	86.36 183	84.21 134	80.05 168	66.41 180	66.91 171	66.92 173	75.66 193	88.96 175	90.56 149	97.05 131	96.96 90

IterMVS-SCA-FT		85.44 143	86.71 128	83.97 165	90.59 141	90.84 192	89.73 148	78.34 182	84.07 145	66.40 181	77.27 123	78.66 122	83.06 162	91.20 138	90.10 163	95.72 168	94.78 143

IterMVS		85.25 145	86.49 131	83.80 166	90.42 142	90.77 195	90.02 140	78.04 184	84.10 143	66.27 182	77.28 122	78.41 126	83.01 163	90.88 143	89.72 172	95.04 183	94.24 150
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v7n		82.25 183	81.54 183	83.07 176	85.55 197	92.58 164	86.68 181	81.10 173	76.54 187	65.97 183	62.91 191	60.56 202	82.36 167	91.07 142	90.35 153	96.77 151	96.80 94

v1921920		83.30 171	82.09 177	84.70 153	86.59 191	92.67 162	89.82 147	82.23 160	78.32 177	65.76 184	64.64 187	62.35 193	86.78 133	90.34 154	90.02 164	97.02 133	96.31 112

PS-CasMVS		82.53 180	81.54 183	83.68 167	87.08 184	92.54 166	86.20 184	83.46 146	76.46 189	65.73 185	65.71 180	59.41 208	81.61 174	89.06 174	90.55 150	98.03 78	97.07 88

EPNet_dtu		88.32 113	90.61 87	85.64 143	96.79 55	92.27 171	92.03 118	90.31 64	89.05 98	65.44 186	89.43 50	85.90 82	74.22 195	92.76 111	92.09 121	95.02 184	92.76 168
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		86.25 128	87.70 119	84.56 156	90.37 143	93.70 129	90.54 128	78.14 183	83.50 147	65.37 187	81.59 104	75.83 143	86.09 142	91.70 131	91.70 130	96.88 146	95.84 124

v1240		82.88 177	81.66 181	84.29 159	86.46 192	92.52 168	89.06 158	81.82 165	77.16 184	65.09 188	64.17 189	61.50 198	86.36 135	90.12 158	90.13 158	96.95 138	96.04 121

PEN-MVS		82.49 181	81.58 182	83.56 169	86.93 185	92.05 177	86.71 180	83.84 139	76.94 186	64.68 189	67.24 168	60.11 204	81.17 176	87.78 181	90.70 147	98.02 79	96.21 115

SixPastTwentyTwo		83.12 174	83.44 161	82.74 180	87.71 171	93.11 151	82.30 197	82.33 158	79.24 173	64.33 190	78.77 114	62.75 191	84.11 158	88.11 179	87.89 181	95.70 169	94.21 152

MDTV_nov1_ep13_2view		80.43 189	80.94 189	79.84 192	84.82 200	90.87 191	84.23 191	73.80 196	80.28 166	64.33 190	70.05 161	68.77 163	79.67 179	84.83 195	83.50 198	92.17 197	88.25 198

EG-PatchMatch MVS		81.70 187	81.31 186	82.15 186	88.75 153	93.81 125	87.14 176	78.89 181	71.57 202	64.12 192	61.20 197	68.46 164	76.73 190	91.48 133	90.77 143	97.28 118	91.90 171

anonymousdsp		84.51 153	85.85 142	82.95 178	86.30 193	93.51 135	85.77 187	80.38 175	78.25 179	63.42 193	73.51 144	72.20 149	84.64 152	93.21 109	92.16 119	97.19 122	98.14 44

DTE-MVSNet		81.76 186	81.04 188	82.60 183	86.63 189	91.48 188	85.97 186	83.70 141	76.45 190	62.44 194	67.16 169	59.98 205	78.98 183	87.15 185	89.93 167	97.88 89	95.12 140

GA-MVS		85.08 146	85.65 143	84.42 158	89.77 145	94.25 118	89.26 154	84.62 129	81.19 161	62.25 195	75.72 134	68.44 165	84.14 157	93.57 98	91.68 132	96.49 153	94.71 145

FC-MVSNet-test		86.15 131	89.10 101	82.71 181	89.83 144	93.18 147	87.88 170	84.69 127	86.54 120	62.18 196	82.39 98	83.31 93	74.18 196	92.52 118	91.86 127	97.50 112	93.88 156

pmnet_mix02		80.14 191	80.21 192	80.06 191	86.61 190	89.66 197	80.40 201	82.20 161	82.29 156	61.35 197	71.52 152	66.67 175	76.75 189	82.55 202	80.18 205	93.05 191	88.62 193

N_pmnet		77.55 198	76.68 201	78.56 196	85.43 198	87.30 205	78.84 203	81.88 164	78.30 178	60.61 198	61.46 194	62.15 194	74.03 198	82.04 203	80.69 204	90.59 206	84.81 205

RE-MVS-def										60.19 199

CVMVSNet		83.83 164	85.53 144	81.85 188	89.60 147	90.92 190	87.81 171	83.21 148	80.11 167	60.16 200	76.47 126	78.57 124	76.79 188	89.76 163	90.13 158	93.51 187	92.75 169

ambc			67.96 207		73.69 211	79.79 212	73.82 209		71.61 201	59.80 201	46.00 211	20.79 221	66.15 205	86.92 187	80.11 206	89.13 210	90.50 182

testgi		81.94 184	84.09 155	79.43 194	89.53 149	90.83 193	82.49 196	81.75 166	80.59 162	59.46 202	82.82 92	65.75 178	67.97 201	90.10 159	89.52 173	95.39 177	89.03 190

PMVS	56.77 18	61.27 207	58.64 210	64.35 207	75.66 209	54.60 217	53.62 217	74.23 194	53.69 215	58.37 203	44.27 213	49.38 215	44.16 214	69.51 212	65.35 212	80.07 213	73.66 212
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Anonymous20231206		78.09 196	78.11 197	78.07 197	85.19 199	89.17 198	80.99 199	81.24 172	75.46 195	58.25 204	54.78 207	59.90 206	66.73 204	88.94 176	88.26 180	96.01 162	90.25 185

FPMVS		69.87 205	67.10 208	73.10 203	84.09 201	78.35 213	79.40 202	76.41 189	71.92 200	57.71 205	54.06 209	50.04 214	56.72 208	71.19 210	68.70 210	84.25 211	75.43 211

MIMVSNet1		73.19 201	73.70 202	72.60 204	65.42 216	86.69 207	75.56 207	79.65 177	67.87 209	55.30 206	45.24 212	56.41 210	63.79 206	86.98 186	87.66 182	95.85 164	85.04 203

MDA-MVSNet-bldmvs		73.81 200	72.56 204	75.28 200	72.52 213	88.87 199	74.95 208	82.67 153	71.57 202	55.02 207	65.96 178	42.84 219	76.11 191	70.61 211	81.47 202	90.38 207	86.59 199

new-patchmatchnet		72.32 202	71.09 205	73.74 202	81.17 207	84.86 209	72.21 211	77.48 186	68.32 208	54.89 208	55.10 205	49.31 216	63.68 207	79.30 207	76.46 208	93.03 192	84.32 206

EU-MVSNet		78.43 194	80.25 191	76.30 199	83.81 202	87.27 206	80.99 199	79.52 178	76.01 191	54.12 209	70.44 158	64.87 185	67.40 203	86.23 190	85.54 190	91.95 200	91.41 174

LTVRE_ROB	81.71 16	82.44 182	81.84 180	83.13 173	89.01 151	92.99 152	88.90 161	82.32 159	66.26 210	54.02 210	74.68 139	59.62 207	88.87 115	90.71 148	92.02 123	95.68 170	96.62 98
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
pmmvs3		71.13 204	71.06 206	71.21 205	73.54 212	80.19 211	71.69 212	64.86 211	62.04 214	52.10 211	54.92 206	48.00 217	75.03 194	83.75 200	83.24 199	90.04 208	85.27 202

test_method		58.10 209	64.61 209	50.51 210	28.26 221	41.71 220	61.28 215	32.07 217	75.92 193	52.04 212	47.94 210	61.83 197	51.80 211	79.83 206	63.95 214	77.60 215	81.05 208

gm-plane-assit		77.65 197	78.50 195	76.66 198	87.96 165	85.43 208	64.70 214	74.50 193	64.15 212	51.26 213	61.32 196	58.17 209	84.11 158	95.16 60	93.83 77	97.45 114	91.41 174

test20.03		76.41 199	78.49 196	73.98 201	85.64 196	87.50 203	75.89 206	80.71 174	70.84 205	51.07 214	68.06 166	61.40 199	54.99 210	88.28 178	87.20 183	95.58 174	86.15 200

new_pmnet		72.29 203	73.25 203	71.16 206	75.35 210	81.38 210	73.72 210	69.27 208	75.97 192	49.84 215	56.27 202	56.12 211	69.08 200	81.73 204	80.86 203	89.72 209	80.44 209

DeepMVS_CX						71.82 214	68.37 213	48.05 216	77.38 182	46.88 216	65.77 179	47.03 218	67.48 202	64.27 214		76.89 216	76.72 210

Gipuma		58.52 208	56.17 211	61.27 208	67.14 215	58.06 216	52.16 218	68.40 210	69.00 207	45.02 217	22.79 215	20.57 222	55.11 209	76.27 208	79.33 207	79.80 214	67.16 214
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
gg-mvs-nofinetune		81.83 185	83.58 158	79.80 193	91.57 125	96.54 86	93.79 85	68.80 209	62.71 213	43.01 218	55.28 204	85.06 86	83.65 160	96.13 46	94.86 61	97.98 85	94.46 147

MVE	39.81 19	39.52 212	41.58 213	37.11 214	33.93 220	49.06 218	26.45 222	54.22 215	29.46 219	24.15 219	20.77 217	10.60 225	34.42 215	51.12 215	65.27 213	49.49 220	64.81 215
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		53.68 210	55.72 212	51.30 209	58.84 217	67.02 215	54.23 216	60.97 214	47.50 216	19.42 220	34.81 214	31.97 220	30.88 216	65.84 213	69.99 209	83.47 212	72.92 213

E-PMN		40.00 211	35.74 214	44.98 212	57.69 219	39.15 222	28.05 220	62.70 212	35.52 218	17.78 221	20.90 216	14.36 224	44.47 213	35.89 216	47.86 215	59.15 218	56.47 216

EMVS		39.04 213	34.32 215	44.54 213	58.25 218	39.35 221	27.61 221	62.55 213	35.99 217	16.40 222	20.04 218	14.77 223	44.80 212	33.12 217	44.10 216	57.61 219	52.89 217

GG-mvs-BLEND		62.84 206	90.21 90	30.91 215	0.57 223	94.45 113	86.99 177	0.34 221	88.71 101	0.98 223	81.55 105	91.58 57	0.86 220	92.66 114	91.43 135	95.73 167	91.11 178

testmvs		4.35 214	6.54 216	1.79 216	0.60 222	1.82 223	3.06 224	0.95 219	7.22 220	0.88 224	12.38 219	1.25 226	3.87 219	6.09 218	5.58 217	1.40 221	11.42 219

test123		3.48 215	5.31 217	1.34 217	0.20 224	1.52 224	2.17 225	0.58 220	6.13 221	0.31 225	9.85 220	0.31 227	3.90 218	2.65 219	5.28 218	0.87 222	11.46 218

uanet_test		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

sosnet-low-res		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

sosnet		0.00 216	0.00 218	0.00 218	0.00 225	0.00 225	0.00 226	0.00 222	0.00 222	0.00 226	0.00 221	0.00 228	0.00 221	0.00 220	0.00 219	0.00 223	0.00 220

9.14												97.28 23

SR-MVS					98.93 19			96.00 17				97.75 14

Anonymous202405211			88.00 112		93.16 101	96.38 92	93.58 91	89.34 76	87.92 108		65.04 184	83.03 95	92.07 75	92.67 113	93.33 91	96.96 137	97.63 65

our_test_3					86.93 185	89.77 196	81.61 198

Patchmatch-RL test							18.47 223

mPP-MVS					98.76 24							95.49 39

NP-MVS									91.63 65

High-resolution multi-view benchmark