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.

SMA-MVS		97.53 8	97.93 8	97.07 11	99.21 1	99.02 10	98.08 20	96.25 12	96.36 13	93.57 16	96.56 15	99.27 6	96.78 17	97.91 4	97.43 4	98.51 27	98.94 12
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
APDe-MVS		97.79 6	97.96 7	97.60 2	99.20 2	99.10 6	98.88 2	96.68 2	96.81 8	94.64 7	97.84 4	98.02 12	97.24 3	97.74 8	97.02 15	98.97 5	99.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		98.07 1	98.46 1	97.62 1	99.08 3	99.29 2	98.84 3	96.63 4	97.89 1	95.35 3	97.83 5	99.48 3	96.98 10	97.99 2	97.14 12	98.82 12	99.60 1

HPM-MVS++		97.22 12	97.40 13	97.01 12	99.08 3	98.55 26	98.19 15	96.48 8	96.02 20	93.28 21	96.26 19	98.71 9	96.76 18	97.30 17	96.25 40	98.30 55	98.68 19

ME-MVS		97.86 4	98.17 4	97.50 5	99.06 5	99.08 7	98.46 8	96.63 4	97.14 3	94.77 6	98.77 1	99.29 5	97.22 4	97.29 18	96.80 21	98.87 8	98.79 14

ACMMP_NAP		96.93 17	97.27 17	96.53 24	99.06 5	98.95 11	98.24 14	96.06 16	95.66 23	90.96 34	95.63 26	97.71 17	96.53 21	97.66 11	96.68 22	98.30 55	98.61 24

DVP-MVS		97.93 3	98.23 3	97.58 3	99.05 7	99.31 1	98.64 6	96.62 6	97.56 2	95.08 5	96.61 14	99.64 1	97.32 1	97.91 4	97.31 7	98.77 16	99.26 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
PGM-MVS		96.16 26	96.33 30	95.95 27	99.04 8	98.63 21	98.32 13	92.76 43	93.42 51	90.49 39	96.30 18	95.31 43	96.71 19	96.46 41	96.02 49	98.38 46	98.19 45

APD-MVS		97.12 14	97.05 20	97.19 8	99.04 8	98.63 21	98.45 9	96.54 7	94.81 38	93.50 17	96.10 21	97.40 23	96.81 14	97.05 24	96.82 20	98.80 13	98.56 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		96.75 20	96.67 26	96.85 17	99.03 10	98.44 35	98.15 17	96.28 11	96.32 14	92.39 27	92.16 37	97.55 21	96.68 20	97.32 15	96.65 24	98.55 26	98.26 42

CNVR-MVS		97.30 11	97.41 12	97.18 9	99.02 11	98.60 23	98.15 17	96.24 14	96.12 18	94.10 12	95.54 27	97.99 13	96.99 8	97.97 3	97.17 10	98.57 25	98.50 33

MSP-MVS		97.70 7	98.09 6	97.24 7	99.00 12	99.17 5	98.76 5	96.41 10	96.91 6	93.88 15	97.72 6	99.04 8	96.93 12	97.29 18	97.31 7	98.45 38	99.23 4
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
ACMMPR		96.92 18	96.96 21	96.87 16	98.99 13	98.78 13	98.38 11	95.52 25	96.57 11	92.81 25	96.06 22	95.90 38	97.07 6	96.60 38	96.34 36	98.46 35	98.42 37

HFP-MVS		97.11 15	97.19 18	97.00 13	98.97 14	98.73 14	98.37 12	95.69 22	96.60 10	93.28 21	96.87 9	96.64 30	97.27 2	96.64 36	96.33 37	98.44 39	98.56 26

SteuartSystems-ACMMP		97.10 16	97.49 11	96.65 19	98.97 14	98.95 11	98.43 10	95.96 18	95.12 30	91.46 30	96.85 10	97.60 19	96.37 25	97.76 6	97.16 11	98.68 20	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		97.20 13	97.29 16	97.10 10	98.95 16	98.51 31	97.51 31	96.48 8	96.17 17	94.64 7	97.32 7	97.57 20	96.23 27	96.78 30	96.15 44	98.79 15	98.55 31

SED-MVS		97.98 2	98.36 2	97.54 4	98.94 17	99.29 2	98.81 4	96.64 3	97.14 3	95.16 4	97.96 3	99.61 2	96.92 13	98.00 1	97.24 9	98.75 18	99.25 3

X-MVS		96.07 28	96.33 30	95.77 30	98.94 17	98.66 16	97.94 25	95.41 31	95.12 30	88.03 57	93.00 35	96.06 34	95.85 30	96.65 35	96.35 33	98.47 33	98.48 34

SR-MVS					98.93 19			96.00 17				97.75 16

MP-MVS		96.56 22	96.72 25	96.37 25	98.93 19	98.48 32	98.04 21	95.55 24	94.32 42	90.95 36	95.88 24	97.02 27	96.29 26	96.77 31	96.01 50	98.47 33	98.56 26
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		96.83 19	97.06 19	96.57 20	98.88 21	98.47 33	98.02 22	96.16 15	95.58 25	90.96 34	95.78 25	97.84 15	96.46 23	97.00 27	96.17 42	98.94 7	98.55 31

CP-MVS		96.68 21	96.59 28	96.77 18	98.85 22	98.58 24	98.18 16	95.51 27	95.34 27	92.94 24	95.21 30	96.25 32	96.79 16	96.44 43	95.77 52	98.35 47	98.56 26

DPE-MVS		97.83 5	98.13 5	97.48 6	98.83 23	99.19 4	98.99 1	96.70 1	96.05 19	94.39 10	98.30 2	99.47 4	97.02 7	97.75 7	97.02 15	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
mPP-MVS					98.76 24							95.49 41

CSCG		95.68 32	95.46 37	95.93 28	98.71 25	99.07 8	97.13 36	93.55 38	95.48 26	93.35 20	90.61 47	93.82 48	95.16 38	94.60 85	95.57 56	97.70 119	99.08 10

DeepC-MVS_fast	93.32 1	96.48 24	96.42 29	96.56 21	98.70 26	98.31 39	97.97 24	95.76 21	96.31 15	92.01 29	91.43 42	95.42 42	96.46 23	97.65 12	97.69 1	98.49 32	98.12 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		95.02 39	93.71 51	96.54 23	98.51 27	97.76 60	96.69 41	95.94 20	93.72 50	93.50 17	89.01 55	90.53 67	96.49 22	94.51 89	93.76 98	98.07 82	96.69 111

train_agg		96.15 27	96.64 27	95.58 35	98.44 28	98.03 49	98.14 19	95.40 32	93.90 48	87.72 63	96.26 19	98.10 11	95.75 32	96.25 48	95.45 58	98.01 94	98.47 35

CDPH-MVS		94.80 43	95.50 35	93.98 48	98.34 29	98.06 48	97.41 32	93.23 40	92.81 56	82.98 117	92.51 36	94.82 44	93.53 62	96.08 51	96.30 39	98.42 41	97.94 57

TPM-MVS					98.33 30	97.85 55	97.06 37			89.97 42	93.26 33	97.16 26	93.12 69			97.79 109	95.95 142
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
MSLP-MVS++		96.05 29	95.63 33	96.55 22	98.33 30	98.17 45	96.94 38	94.61 35	94.70 40	94.37 11	89.20 54	95.96 37	96.81 14	95.57 59	97.33 6	98.24 64	98.47 35

ACMMP		95.54 33	95.49 36	95.61 33	98.27 32	98.53 28	97.16 35	94.86 33	94.88 36	89.34 45	95.36 29	91.74 56	95.50 36	95.51 60	94.16 87	98.50 30	98.22 43
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
3Dnovator+	90.56 5	95.06 38	94.56 46	95.65 32	98.11 33	98.15 46	97.19 34	91.59 53	95.11 32	93.23 23	81.99 109	94.71 45	95.43 37	96.48 40	96.88 19	98.35 47	98.63 21

3Dnovator	90.28 7	94.70 44	94.34 49	95.11 37	98.06 34	98.21 43	96.89 39	91.03 58	94.72 39	91.45 31	82.87 96	93.10 51	94.61 43	96.24 49	97.08 14	98.63 23	98.16 46

MGCNet		96.54 23	97.36 15	95.60 34	98.03 35	99.07 8	98.02 22	92.24 46	95.87 21	92.54 26	96.41 16	96.08 33	94.03 53	97.69 9	97.47 3	98.73 19	98.90 13

PLC	90.69 4	94.32 48	92.99 59	95.87 29	97.91 36	96.49 107	95.95 52	94.12 36	94.94 34	94.09 13	85.90 73	90.77 64	95.58 34	94.52 88	93.32 112	97.55 130	95.00 164
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPNet		93.92 51	94.40 47	93.36 55	97.89 37	96.55 105	96.08 48	92.14 47	91.65 68	89.16 47	94.07 32	90.17 71	87.78 142	95.24 65	94.97 68	97.09 149	98.15 47
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		95.54 33	95.07 39	96.10 26	97.88 38	97.98 51	97.92 26	94.86 33	94.56 41	92.16 28	91.01 43	95.71 39	96.97 11	94.56 86	93.50 105	96.81 173	98.14 48

QAPM		94.13 50	94.33 50	93.90 49	97.82 39	98.37 38	96.47 43	90.89 59	92.73 58	85.63 93	85.35 77	93.87 47	94.17 50	95.71 58	95.90 51	98.40 43	98.42 37

DeepC-MVS	92.10 3	95.22 36	94.77 43	95.75 31	97.77 40	98.54 27	97.63 30	95.96 18	95.07 33	88.85 50	85.35 77	91.85 55	95.82 31	96.88 29	97.10 13	98.44 39	98.63 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OpenMVS	88.18 11	92.51 64	91.61 81	93.55 54	97.74 41	98.02 50	95.66 54	90.46 62	89.14 113	86.50 76	75.80 153	90.38 70	92.69 79	94.99 68	95.30 60	98.27 59	97.63 68

TSAR-MVS + ACMM		96.19 25	97.39 14	94.78 39	97.70 42	98.41 36	97.72 29	95.49 28	96.47 12	86.66 75	96.35 17	97.85 14	93.99 54	97.19 22	96.37 32	97.12 147	99.13 7

MAR-MVS		92.71 63	92.63 64	92.79 68	97.70 42	97.15 87	93.75 103	87.98 113	90.71 75	85.76 91	86.28 71	86.38 80	94.35 48	94.95 69	95.49 57	97.22 140	97.44 76
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
PHI-MVS		95.86 30	96.93 24	94.61 42	97.60 44	98.65 20	96.49 42	93.13 41	94.07 45	87.91 61	97.12 8	97.17 25	93.90 57	96.46 41	96.93 18	98.64 22	98.10 52

DPM-MVS		95.07 37	94.84 42	95.34 36	97.44 45	97.49 69	97.76 28	95.52 25	94.88 36	88.92 49	87.25 63	96.44 31	94.41 45	95.78 56	96.11 46	97.99 98	95.95 142

SD-MVS		97.35 9	97.73 9	96.90 15	97.35 46	98.66 16	97.85 27	96.25 12	96.86 7	94.54 9	96.75 12	99.13 7	96.99 8	96.94 28	96.58 25	98.39 45	99.20 5
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
MVS_111021_HR		94.84 41	95.91 32	93.60 53	97.35 46	98.46 34	95.08 63	91.19 55	94.18 44	85.97 84	95.38 28	92.56 53	93.61 61	96.61 37	96.25 40	98.40 43	97.92 59

TSAR-MVS + MP.		97.31 10	97.64 10	96.92 14	97.28 48	98.56 25	98.61 7	95.48 29	96.72 9	94.03 14	96.73 13	98.29 10	97.15 5	97.61 13	96.42 27	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CANet		94.85 40	94.92 41	94.78 39	97.25 49	98.52 30	97.20 33	91.81 50	93.25 53	91.06 33	86.29 70	94.46 46	92.99 70	97.02 26	96.68 22	98.34 49	98.20 44

OMC-MVS		94.49 47	94.36 48	94.64 41	97.17 50	97.73 62	95.49 56	92.25 45	96.18 16	90.34 40	88.51 57	92.88 52	94.90 42	94.92 71	94.17 86	97.69 121	96.15 134

MVS_111021_LR		94.84 41	95.57 34	94.00 46	97.11 51	97.72 64	94.88 67	91.16 56	95.24 29	88.74 51	96.03 23	91.52 60	94.33 49	95.96 53	95.01 67	97.79 109	97.49 75

CNLPA		93.69 54	92.50 66	95.06 38	97.11 51	97.36 71	93.88 99	93.30 39	95.64 24	93.44 19	80.32 125	90.73 65	94.99 41	93.58 116	93.33 110	97.67 123	96.57 116

LS3D		91.97 71	90.98 93	93.12 61	97.03 53	97.09 92	95.33 61	95.59 23	92.47 59	79.26 137	81.60 112	82.77 101	94.39 47	94.28 94	94.23 85	97.14 146	94.45 170

TAPA-MVS	90.35 6	93.69 54	93.52 52	93.90 49	96.89 54	97.62 66	96.15 46	91.67 52	94.94 34	85.97 84	87.72 62	91.96 54	94.40 46	93.76 113	93.06 122	98.30 55	95.58 152
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DELS-MVS		93.71 53	93.47 53	94.00 46	96.82 55	98.39 37	96.80 40	91.07 57	89.51 108	89.94 43	83.80 87	89.29 73	90.95 104	97.32 15	97.65 2	98.42 41	98.32 40
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
EPNet_dtu		88.32 135	90.61 100	85.64 166	96.79 56	92.27 194	92.03 138	90.31 63	89.05 114	65.44 210	89.43 52	85.90 85	74.22 220	92.76 130	92.09 141	95.02 210	92.76 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSDG		90.42 110	88.25 132	92.94 66	96.67 57	94.41 137	93.96 93	92.91 42	89.59 106	86.26 78	76.74 146	80.92 124	90.43 114	92.60 135	92.08 142	97.44 135	91.41 198

SPE-MVS-test		94.63 45	95.28 38	93.88 51	96.56 58	98.67 15	93.41 114	89.31 90	94.27 43	89.64 44	90.84 45	91.64 58	95.58 34	97.04 25	96.17 42	98.77 16	98.32 40

DeepPCF-MVS	92.65 2	95.50 35	96.96 21	93.79 52	96.44 59	98.21 43	93.51 111	94.08 37	96.94 5	89.29 46	93.08 34	96.77 29	93.82 58	97.68 10	97.40 5	95.59 196	98.65 20

PCF-MVS	90.19 8	92.98 58	92.07 74	94.04 45	96.39 60	97.87 52	96.03 49	95.47 30	87.16 134	85.09 107	84.81 81	93.21 50	93.46 64	91.98 148	91.98 145	97.78 111	97.51 74
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CS-MVS		94.53 46	94.73 44	94.31 44	96.30 61	98.53 28	94.98 64	89.24 93	93.37 52	90.24 41	88.96 56	89.76 72	96.09 29	97.48 14	96.42 27	98.99 2	98.59 25

OPM-MVS		91.08 91	89.34 116	93.11 62	96.18 62	96.13 116	96.39 44	92.39 44	82.97 174	81.74 120	82.55 102	80.20 132	93.97 56	94.62 83	93.23 113	98.00 96	95.73 148
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PVSNet_BlendedMVS		92.80 59	92.44 68	93.23 56	96.02 63	97.83 57	93.74 104	90.58 60	91.86 65	90.69 37	85.87 75	82.04 112	90.01 116	96.39 44	95.26 61	98.34 49	97.81 64

PVSNet_Blended		92.80 59	92.44 68	93.23 56	96.02 63	97.83 57	93.74 104	90.58 60	91.86 65	90.69 37	85.87 75	82.04 112	90.01 116	96.39 44	95.26 61	98.34 49	97.81 64

XVS					95.68 65	98.66 16	94.96 65			88.03 57		96.06 34				98.46 35

X-MVStestdata					95.68 65	98.66 16	94.96 65			88.03 57		96.06 34				98.46 35

HQP-MVS		92.39 66	92.49 67	92.29 81	95.65 67	95.94 120	95.64 55	92.12 48	92.46 60	79.65 135	91.97 39	82.68 102	92.92 73	93.47 121	92.77 128	97.74 115	98.12 50

HyFIR lowres test		87.87 137	86.42 154	89.57 122	95.56 68	96.99 95	92.37 128	84.15 157	86.64 140	77.17 144	57.65 226	83.97 92	91.08 102	92.09 146	92.44 133	97.09 149	95.16 161

ACMM	88.76 10	91.70 80	90.43 101	93.19 58	95.56 68	95.14 128	93.35 116	91.48 54	92.26 61	87.12 69	84.02 85	79.34 137	93.99 54	94.07 102	92.68 129	97.62 128	95.50 153
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	84.39 15	87.61 139	86.03 160	89.46 123	95.54 70	94.48 134	91.77 142	90.14 67	87.16 134	75.50 149	73.41 169	76.86 158	87.33 149	90.05 182	89.76 194	96.48 177	90.46 207
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
LGP-MVS_train		91.83 75	92.04 75	91.58 96	95.46 71	96.18 115	95.97 51	89.85 69	90.45 83	77.76 140	91.92 40	80.07 133	92.34 86	94.27 95	93.47 106	98.11 77	97.90 62

CHOSEN 1792x2688		88.57 132	87.82 139	89.44 124	95.46 71	96.89 99	93.74 104	85.87 139	89.63 105	77.42 143	61.38 220	83.31 96	88.80 137	93.44 122	93.16 118	95.37 204	96.95 104

PVSNet_Blended_VisFu		91.92 73	92.39 70	91.36 104	95.45 73	97.85 55	92.25 131	89.54 85	88.53 123	87.47 65	79.82 127	90.53 67	85.47 170	96.31 47	95.16 64	97.99 98	98.56 26

PatchMatch-RL		90.30 111	88.93 123	91.89 88	95.41 74	95.68 122	90.94 146	88.67 102	89.80 103	86.95 72	85.90 73	72.51 169	92.46 83	93.56 118	92.18 138	96.93 164	92.89 189

TSAR-MVS + COLMAP		92.39 66	92.31 71	92.47 77	95.35 75	96.46 109	96.13 47	92.04 49	95.33 28	80.11 133	94.95 31	77.35 155	94.05 52	94.49 91	93.08 120	97.15 144	94.53 168

test2506		90.93 97	89.20 119	92.95 65	94.97 76	98.30 40	94.53 69	90.25 65	89.91 99	88.39 55	83.23 92	64.17 212	90.69 109	96.75 33	96.10 47	98.87 8	95.97 141

ECVR-MVS		90.77 103	89.27 117	92.52 72	94.97 76	98.30 40	94.53 69	90.25 65	89.91 99	85.80 90	73.64 164	74.31 165	90.69 109	96.75 33	96.10 47	98.87 8	95.91 145

test1111		90.47 109	89.10 121	92.07 85	94.92 78	98.30 40	94.17 82	90.30 64	89.56 107	83.92 112	73.25 171	73.66 166	90.26 115	96.77 31	96.14 45	98.87 8	96.04 138

ACMP	89.13 9	92.03 69	91.70 80	92.41 79	94.92 78	96.44 111	93.95 94	89.96 68	91.81 67	85.48 99	90.97 44	79.12 138	92.42 84	93.28 127	92.55 132	97.76 113	97.74 67
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		90.81 99	92.58 65	88.74 131	94.87 80	97.44 70	92.61 125	88.22 109	82.35 178	78.93 138	85.20 79	95.61 40	79.56 205	96.52 39	96.57 26	98.23 65	94.37 171

IB-MVS	85.10 14	87.98 136	87.97 137	87.99 140	94.55 81	96.86 100	84.52 214	88.21 110	86.48 145	88.54 54	74.41 162	77.74 152	74.10 222	89.65 190	92.85 126	98.06 85	97.80 66
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
CANet_DTU		90.74 105	92.93 62	88.19 137	94.36 82	96.61 102	94.34 75	84.66 150	90.66 76	68.75 189	90.41 48	86.89 78	89.78 118	95.46 61	94.87 69	97.25 139	95.62 150

sasdasda		93.08 56	93.09 56	93.07 63	94.24 83	97.86 53	95.45 58	87.86 119	94.00 46	87.47 65	88.32 58	82.37 106	95.13 39	93.96 108	96.41 30	98.27 59	98.73 15

canonicalmvs		93.08 56	93.09 56	93.07 63	94.24 83	97.86 53	95.45 58	87.86 119	94.00 46	87.47 65	88.32 58	82.37 106	95.13 39	93.96 108	96.41 30	98.27 59	98.73 15

MGCFI-Net		92.75 61	92.98 60	92.48 75	94.18 85	97.77 59	95.28 62	87.77 121	93.88 49	85.28 104	88.19 60	82.17 111	94.14 51	93.86 111	96.32 38	98.20 68	98.69 18

UGNet		91.52 83	93.41 54	89.32 125	94.13 86	97.15 87	91.83 141	89.01 94	90.62 78	85.86 88	86.83 64	91.73 57	77.40 210	94.68 82	94.43 82	97.71 117	98.40 39
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
thres600view7		89.28 129	87.47 148	91.39 101	94.12 87	97.25 78	93.94 97	89.74 72	85.62 152	80.63 131	75.24 158	69.33 184	91.66 96	94.92 71	93.23 113	98.27 59	96.72 110

IS_MVSNet		91.87 74	93.35 55	90.14 119	94.09 88	97.73 62	93.09 119	88.12 111	88.71 120	79.98 134	84.49 82	90.63 66	87.49 147	97.07 23	96.96 17	98.07 82	97.88 63

TSAR-MVS + GP.		95.86 30	96.95 23	94.60 43	94.07 89	98.11 47	96.30 45	91.76 51	95.67 22	91.07 32	96.82 11	97.69 18	95.71 33	95.96 53	95.75 53	98.68 20	98.63 21

thres400		89.40 125	87.58 145	91.53 98	94.06 90	97.21 84	94.19 81	89.83 70	85.69 149	81.08 127	75.50 156	69.76 182	91.80 92	94.79 79	93.51 102	98.20 68	96.60 114

ETV-MVS		93.80 52	94.57 45	92.91 67	93.98 91	97.50 68	93.62 107	88.70 100	91.95 63	87.57 64	90.21 49	90.79 63	94.56 44	97.20 21	96.35 33	99.02 1	97.98 54

ACMH	85.51 13	87.31 142	86.59 152	88.14 138	93.96 92	94.51 133	89.00 184	87.99 112	81.58 181	70.15 179	78.41 137	71.78 174	90.60 112	91.30 158	91.99 144	97.17 143	96.58 115
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		87.63 138	87.61 143	87.65 145	93.95 93	94.09 143	92.60 126	81.52 190	86.64 140	76.41 147	73.46 168	85.94 84	85.01 174	92.23 144	90.00 188	96.43 180	90.93 204

thres200		89.49 124	87.72 140	91.55 97	93.95 93	97.25 78	94.34 75	89.74 72	85.66 150	81.18 124	76.12 152	70.19 181	91.80 92	94.92 71	93.51 102	98.27 59	96.40 124

CLD-MVS		92.50 65	91.96 76	93.13 60	93.93 95	96.24 113	95.69 53	88.77 99	92.92 54	89.01 48	88.19 60	81.74 115	93.13 68	93.63 115	93.08 120	98.23 65	97.91 61
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thres100view900		89.36 126	87.61 143	91.39 101	93.90 96	96.86 100	94.35 74	89.66 76	85.87 147	81.15 125	76.46 148	70.38 178	91.17 100	94.09 101	93.43 108	98.13 74	96.16 133

tfpn200view9		89.55 123	87.86 138	91.53 98	93.90 96	97.26 75	94.31 77	89.74 72	85.87 147	81.15 125	76.46 148	70.38 178	91.76 94	94.92 71	93.51 102	98.28 58	96.61 113

EIA-MVS		92.72 62	92.96 61	92.44 78	93.86 98	97.76 60	93.13 118	88.65 103	89.78 104	86.68 73	86.69 67	87.57 74	93.74 59	96.07 52	95.32 59	98.58 24	97.53 73

CHOSEN 280x420		90.77 103	92.14 73	89.17 127	93.86 98	92.81 182	93.16 117	80.22 200	90.21 89	84.67 111	89.89 51	91.38 61	90.57 113	94.94 70	92.11 140	92.52 221	93.65 181

FC-MVSNet-train		90.55 107	90.19 105	90.97 107	93.78 100	95.16 127	92.11 136	88.85 97	87.64 129	83.38 116	84.36 84	78.41 144	89.53 120	94.69 81	93.15 119	98.15 72	97.92 59

FA-MVS(training)		90.79 102	91.33 85	90.17 117	93.76 101	97.22 83	92.74 123	77.79 211	90.60 80	88.03 57	78.80 134	87.41 75	91.00 103	95.40 63	93.43 108	97.70 119	96.46 121

Vis-MVSNet (Re-imp)		90.54 108	92.76 63	87.94 141	93.73 102	96.94 98	92.17 134	87.91 114	88.77 119	76.12 148	83.68 88	90.80 62	79.49 206	96.34 46	96.35 33	98.21 67	96.46 121

baseline1		90.81 99	90.29 103	91.42 100	93.67 103	95.86 121	93.94 97	89.69 75	89.29 110	82.85 118	82.91 95	80.30 129	89.60 119	95.05 67	94.79 72	98.80 13	93.82 179

EPP-MVSNet		92.13 68	93.06 58	91.05 106	93.66 104	97.30 73	92.18 132	87.90 115	90.24 88	83.63 114	86.14 72	90.52 69	90.76 108	94.82 77	94.38 83	98.18 71	97.98 54

EC-MVSNet		94.19 49	95.05 40	93.18 59	93.56 105	97.65 65	95.34 60	86.37 135	92.05 62	88.71 52	89.91 50	93.32 49	96.14 28	97.29 18	96.42 27	98.98 3	98.70 17

ACMH+	85.75 12	87.19 144	86.02 161	88.56 133	93.42 106	94.41 137	89.91 168	87.66 125	83.45 171	72.25 166	76.42 150	71.99 173	90.78 107	89.86 185	90.94 162	97.32 136	95.11 163

casdiffmvs_mvg		91.94 72	91.25 87	92.75 69	93.41 107	97.19 85	95.48 57	89.77 71	89.86 101	86.41 77	81.02 119	82.23 109	92.93 71	95.44 62	95.61 55	98.51 27	97.40 78
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmanbaseed2359cas		91.57 82	91.09 91	92.12 83	93.36 108	97.26 75	94.02 90	89.62 82	90.50 82	84.95 110	82.00 108	81.36 117	92.69 79	94.47 92	95.04 66	98.09 80	97.00 94

viewdifsd2359ckpt09		91.65 81	90.91 94	92.51 73	93.35 109	97.36 71	93.95 94	89.64 79	89.83 102	86.67 74	82.25 106	80.77 125	93.37 65	94.71 80	94.48 81	98.07 82	96.99 96

E2		92.03 69	91.47 84	92.69 70	93.29 110	97.27 74	94.14 86	89.63 81	91.02 73	88.25 56	83.68 88	82.18 110	92.84 74	94.51 89	94.62 79	98.00 96	97.00 94

viewcassd2359sk11		91.81 76	91.13 90	92.61 71	93.28 111	97.26 75	94.16 83	89.64 79	90.27 86	87.79 62	82.51 103	81.72 116	92.78 75	94.43 93	94.69 77	98.01 94	96.99 96

E3new		91.52 83	90.67 98	92.51 73	93.24 112	97.23 80	94.16 83	89.65 77	89.19 111	87.26 68	81.25 116	81.00 121	92.71 77	94.26 96	94.75 73	98.03 88	96.99 96

E3		91.50 85	90.67 98	92.48 75	93.24 112	97.23 80	94.16 83	89.65 77	89.18 112	87.08 70	81.24 117	81.04 120	92.71 77	94.26 96	94.75 73	98.03 88	96.99 96

MVS_Test		91.81 76	92.19 72	91.37 103	93.24 112	96.95 96	94.43 71	86.25 136	91.45 71	83.45 115	86.31 69	85.15 88	92.93 71	93.99 104	94.71 76	97.92 103	96.77 109

viewdifsd2359ckpt07		90.96 96	90.40 102	91.62 95	93.22 115	96.95 96	93.49 112	89.26 92	88.94 116	85.56 95	80.56 124	80.99 122	91.25 98	94.88 75	94.01 92	96.92 166	96.49 120

viewdifsd2359ckpt13		91.32 87	90.71 97	92.04 86	93.21 116	97.23 80	93.57 109	89.54 85	89.94 97	85.21 105	81.31 115	80.56 127	92.78 75	94.56 86	94.57 80	97.95 102	96.80 107

MVSTER		91.73 78	91.61 81	91.86 89	93.18 117	94.56 131	94.37 73	87.90 115	90.16 92	88.69 53	89.23 53	81.28 119	88.92 135	95.75 57	93.95 94	98.12 75	96.37 125

viewmacassd2359aftdt		90.80 101	89.95 111	91.78 90	93.17 118	97.14 90	93.99 91	89.56 84	87.66 128	83.65 113	78.82 133	80.23 131	92.23 87	93.74 114	95.11 65	98.10 78	96.97 102

Anonymous202405211			88.00 135		93.16 119	96.38 112	93.58 108	89.34 89	87.92 127		65.04 209	83.03 98	92.07 88	92.67 132	93.33 110	96.96 159	97.63 68

casdiffmvs		91.72 79	91.16 89	92.38 80	93.16 119	97.15 87	93.95 94	89.49 87	91.58 70	86.03 83	80.75 121	80.95 123	93.16 67	95.25 64	95.22 63	98.50 30	97.23 85
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E4		91.04 93	90.00 110	92.25 82	93.15 121	97.14 90	94.09 87	89.62 82	87.54 131	86.08 82	79.38 128	80.24 130	92.53 81	93.89 110	94.82 71	98.04 87	96.99 96

E6		90.91 98	89.94 112	92.04 86	93.14 122	97.16 86	93.76 102	88.98 95	87.44 132	85.85 89	79.15 131	79.96 135	92.48 82	94.04 103	94.75 73	98.03 88	97.06 93

tttt0517		91.01 95	91.71 79	90.19 116	92.98 123	97.07 93	91.96 140	87.63 126	90.61 79	81.42 122	86.76 66	82.26 108	89.23 127	94.86 76	93.03 124	97.90 104	97.36 79

Effi-MVS+		89.79 118	89.83 113	89.74 121	92.98 123	96.45 110	93.48 113	84.24 155	87.62 130	76.45 146	81.76 110	77.56 154	93.48 63	94.61 84	93.59 101	97.82 108	97.22 87

RPSCF		89.68 119	89.24 118	90.20 115	92.97 125	92.93 178	92.30 129	87.69 123	90.44 84	85.12 106	91.68 41	85.84 86	90.69 109	87.34 208	86.07 211	92.46 222	90.37 208

TDRefinement		84.97 171	83.39 186	86.81 154	92.97 125	94.12 142	92.18 132	87.77 121	82.78 175	71.31 171	68.43 190	68.07 190	81.10 201	89.70 189	89.03 201	95.55 200	91.62 196

thisisatest0530		91.04 93	91.74 78	90.21 114	92.93 127	97.00 94	92.06 137	87.63 126	90.74 74	81.51 121	86.81 65	82.48 103	89.23 127	94.81 78	93.03 124	97.90 104	97.33 81

DCV-MVSNet		91.24 88	91.26 86	91.22 105	92.84 128	93.44 160	93.82 100	86.75 131	91.33 72	85.61 94	84.00 86	85.46 87	91.27 97	92.91 129	93.62 100	97.02 154	98.05 53

baseline		91.19 90	91.89 77	90.38 110	92.76 129	95.04 129	93.55 110	84.54 153	92.92 54	85.71 92	86.68 68	86.96 77	89.28 126	92.00 147	92.62 131	96.46 178	96.99 96

EPMVS		85.77 159	86.24 156	85.23 171	92.76 129	93.78 150	89.91 168	73.60 224	90.19 90	74.22 153	82.18 107	78.06 148	87.55 146	85.61 218	85.38 216	93.32 215	88.48 221

GeoE		89.29 128	88.68 125	89.99 120	92.75 131	96.03 119	93.07 121	83.79 162	86.98 136	81.34 123	74.72 159	78.92 139	91.22 99	93.31 125	93.21 116	97.78 111	97.60 72

diffmvs		91.37 86	91.09 91	91.70 93	92.71 132	96.47 108	94.03 89	88.78 98	92.74 57	85.43 101	83.63 90	80.37 128	91.76 94	93.39 123	93.78 97	97.50 132	97.23 85
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs_AUTHOR		91.22 89	90.82 96	91.68 94	92.69 133	96.56 104	94.05 88	88.87 96	91.87 64	85.08 108	82.26 105	80.04 134	91.84 91	93.80 112	93.93 95	97.56 129	97.26 83

DI_MVS_pp		91.05 92	90.15 106	92.11 84	92.67 134	96.61 102	96.03 49	88.44 105	90.25 87	85.92 86	73.73 163	84.89 90	91.92 89	94.17 100	94.07 91	97.68 122	97.31 82

viewmambaseed2359dif		90.70 106	89.81 114	91.73 92	92.66 135	96.10 117	93.97 92	88.69 101	89.92 98	86.12 80	80.79 120	80.73 126	91.92 89	91.13 163	92.81 127	97.06 151	97.20 88

Anonymous20231211		89.82 117	88.18 133	91.74 91	92.52 136	96.09 118	93.38 115	89.30 91	88.95 115	85.90 87	64.55 214	84.39 91	92.41 85	92.24 143	93.06 122	96.93 164	97.95 56

viewdifsd2359ckpt11		89.68 119	88.67 126	90.86 108	92.35 137	95.23 124	91.72 143	88.40 107	88.84 117	86.14 79	80.75 121	78.17 147	90.95 104	90.02 183	91.15 160	95.59 196	96.50 118

viewmsd2359difaftdt		89.67 121	88.66 127	90.85 109	92.35 137	95.23 124	91.72 143	88.40 107	88.80 118	86.12 80	80.75 121	78.20 146	90.94 106	90.02 183	91.15 160	95.59 196	96.50 118

tpmrst		83.72 190	83.45 183	84.03 187	92.21 139	91.66 206	88.74 187	73.58 225	88.14 125	72.67 163	77.37 142	72.11 172	86.34 158	82.94 226	82.05 225	90.63 231	89.86 213

CostFormer		86.78 147	86.05 159	87.62 147	92.15 140	93.20 169	91.55 145	75.83 216	88.11 126	85.29 103	81.76 110	76.22 160	87.80 141	84.45 221	85.21 217	93.12 216	93.42 184

Vis-MVSNet		89.36 126	91.49 83	86.88 152	92.10 141	97.60 67	92.16 135	85.89 138	84.21 163	75.20 150	82.58 100	87.13 76	77.40 210	95.90 55	95.63 54	98.51 27	97.36 79
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IterMVS-LS		88.60 131	88.45 128	88.78 130	92.02 142	92.44 192	92.00 139	83.57 166	86.52 143	78.90 139	78.61 136	81.34 118	89.12 130	90.68 171	93.18 117	97.10 148	96.35 126
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchmatchNet		85.70 160	86.65 151	84.60 178	91.79 143	93.40 161	89.27 177	73.62 223	90.19 90	72.63 164	82.74 99	81.93 114	87.64 144	84.99 219	84.29 221	92.64 220	89.00 216
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm cat1		84.13 183	81.99 203	86.63 157	91.74 144	91.50 209	90.68 149	75.69 217	86.12 146	85.44 100	72.39 174	70.72 176	85.16 172	80.89 231	81.56 226	91.07 229	90.71 205

USDC		86.73 148	85.96 163	87.63 146	91.64 145	93.97 145	92.76 122	84.58 152	88.19 124	70.67 176	80.10 126	67.86 191	89.43 121	91.81 149	89.77 193	96.69 175	90.05 212

SCA		86.25 150	87.52 146	84.77 175	91.59 146	93.90 146	89.11 181	73.25 228	90.38 85	72.84 162	83.26 91	83.79 94	88.49 139	86.07 215	85.56 214	93.33 214	89.67 214

gg-mvs-nofinetune		81.83 209	83.58 181	79.80 216	91.57 147	96.54 106	93.79 101	68.80 235	62.71 239	43.01 244	55.28 229	85.06 89	83.65 184	96.13 50	94.86 70	97.98 101	94.46 169

Fast-Effi-MVS+		88.56 133	87.99 136	89.22 126	91.56 148	95.21 126	92.29 130	82.69 173	86.82 138	77.73 141	76.24 151	73.39 167	93.36 66	94.22 99	93.64 99	97.65 125	96.43 123

CMPMVS	61.19 17	79.86 216	77.46 224	82.66 205	91.54 149	91.82 204	83.25 217	81.57 189	70.51 230	68.64 190	59.89 225	66.77 197	79.63 204	84.00 224	84.30 220	91.34 227	84.89 230
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ADS-MVSNet		84.08 184	84.95 171	83.05 200	91.53 150	91.75 205	88.16 191	70.70 232	89.96 96	69.51 184	78.83 132	76.97 157	86.29 159	84.08 223	84.60 219	92.13 225	88.48 221

test-LLR		86.88 145	88.28 130	85.24 170	91.22 151	92.07 198	87.41 197	83.62 164	84.58 156	69.33 185	83.00 93	82.79 99	84.24 178	92.26 141	89.81 191	95.64 194	93.44 182

test0.0.03 1		85.58 162	87.69 142	83.11 197	91.22 151	92.54 189	85.60 213	83.62 164	85.66 150	67.84 196	82.79 98	79.70 136	73.51 224	91.15 162	90.79 164	96.88 169	91.23 201

baseline2		88.97 130	89.50 115	88.36 134	91.14 153	95.30 123	90.13 162	85.17 147	87.24 133	80.80 129	84.46 83	78.44 143	85.60 167	93.54 119	91.87 146	97.31 137	95.66 149

Effi-MVS+-dtu		87.51 140	88.13 134	86.77 155	91.10 154	94.90 130	90.91 148	82.67 174	83.47 170	71.55 168	81.11 118	77.04 156	89.41 122	92.65 134	91.68 152	95.00 211	96.09 136

RPMNet		84.82 173	85.90 164	83.56 192	91.10 154	92.10 196	88.73 188	71.11 231	84.75 154	68.79 188	73.56 165	77.62 153	85.33 171	90.08 181	89.43 197	96.32 181	93.77 180

CR-MVSNet		85.48 164	86.29 155	84.53 180	91.08 156	92.10 196	89.18 179	73.30 226	84.75 154	71.08 173	73.12 173	77.91 150	86.27 160	91.48 154	90.75 167	96.27 182	93.94 176

TinyColmap		84.04 185	82.01 202	86.42 159	90.87 157	91.84 203	88.89 186	84.07 159	82.11 180	69.89 181	71.08 179	60.81 225	89.04 131	90.52 173	89.19 199	95.76 188	88.50 220

tpm		83.16 196	83.64 180	82.60 206	90.75 158	91.05 212	88.49 189	73.99 221	82.36 177	67.08 202	78.10 138	68.79 185	84.17 180	85.95 217	85.96 212	91.09 228	93.23 186

dps		85.00 170	83.21 190	87.08 150	90.73 159	92.55 188	89.34 176	75.29 218	84.94 153	87.01 71	79.27 130	67.69 192	87.27 150	84.22 222	83.56 222	92.83 219	90.25 210

MDTV_nov1_ep13		86.64 149	87.50 147	85.65 165	90.73 159	93.69 154	89.96 166	78.03 210	89.48 109	76.85 145	84.92 80	82.42 105	86.14 162	86.85 212	86.15 210	92.17 223	88.97 217

CDS-MVSNet		88.34 134	88.71 124	87.90 142	90.70 161	94.54 132	92.38 127	86.02 137	80.37 188	79.42 136	79.30 129	83.43 95	82.04 193	93.39 123	94.01 92	96.86 171	95.93 144
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		85.44 166	86.71 150	83.97 188	90.59 162	90.84 215	89.73 172	78.34 207	84.07 167	66.40 205	77.27 144	78.66 141	83.06 186	91.20 159	90.10 186	95.72 191	94.78 165

IterMVS		85.25 168	86.49 153	83.80 189	90.42 163	90.77 218	90.02 164	78.04 209	84.10 165	66.27 206	77.28 143	78.41 144	83.01 187	90.88 165	89.72 195	95.04 209	94.24 172
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+-dtu		86.25 150	87.70 141	84.56 179	90.37 164	93.70 153	90.54 152	78.14 208	83.50 169	65.37 211	81.59 113	75.83 162	86.09 164	91.70 152	91.70 150	96.88 169	95.84 146

dmvs_re		87.31 142	86.10 158	88.74 131	89.84 165	94.28 140	92.66 124	89.41 88	82.61 176	74.69 151	74.69 160	69.47 183	87.78 142	92.38 139	93.23 113	98.03 88	96.02 140

FC-MVSNet-test		86.15 153	89.10 121	82.71 204	89.83 166	93.18 170	87.88 194	84.69 149	86.54 142	62.18 220	82.39 104	83.31 96	74.18 221	92.52 137	91.86 147	97.50 132	93.88 178

GA-MVS		85.08 169	85.65 167	84.42 181	89.77 167	94.25 141	89.26 178	84.62 151	81.19 185	62.25 219	75.72 154	68.44 188	84.14 181	93.57 117	91.68 152	96.49 176	94.71 167

PMMVS		89.88 116	91.19 88	88.35 135	89.73 168	91.97 202	90.62 151	81.92 185	90.57 81	80.58 132	92.16 37	86.85 79	91.17 100	92.31 140	91.35 156	96.11 184	93.11 188

tfpnnormal		83.80 189	81.26 211	86.77 155	89.60 169	93.26 168	89.72 173	87.60 128	72.78 222	70.44 177	60.53 223	61.15 224	85.55 168	92.72 131	91.44 154	97.71 117	96.92 105

CVMVSNet		83.83 188	85.53 168	81.85 211	89.60 169	90.92 213	87.81 195	83.21 170	80.11 191	60.16 225	76.47 147	78.57 142	76.79 212	89.76 186	90.13 181	93.51 213	92.75 192

testgi		81.94 208	84.09 178	79.43 217	89.53 171	90.83 216	82.49 220	81.75 188	80.59 186	59.46 227	82.82 97	65.75 201	67.97 226	90.10 180	89.52 196	95.39 203	89.03 215

UniMVSNet_ETH3D		84.57 174	81.40 209	88.28 136	89.34 172	94.38 139	90.33 154	86.50 134	74.74 220	77.52 142	59.90 224	62.04 220	88.78 138	88.82 201	92.65 130	97.22 140	97.24 84

LTVRE_ROB	81.71 16	82.44 206	81.84 204	83.13 196	89.01 173	92.99 175	88.90 185	82.32 180	66.26 235	54.02 235	74.68 161	59.62 231	88.87 136	90.71 170	92.02 143	95.68 193	96.62 112
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
TAMVS		84.94 172	84.95 171	84.93 174	88.82 174	93.18 170	88.44 190	81.28 193	77.16 207	73.76 157	75.43 157	76.57 159	82.04 193	90.59 172	90.79 164	95.22 206	90.94 203

EG-PatchMatch MVS		81.70 211	81.31 210	82.15 209	88.75 175	93.81 149	87.14 200	78.89 206	71.57 225	64.12 216	61.20 222	68.46 187	76.73 214	91.48 154	90.77 166	97.28 138	91.90 195

TransMVSNet (Re)		82.67 203	80.93 214	84.69 177	88.71 176	91.50 209	87.90 193	87.15 129	71.54 227	68.24 193	63.69 216	64.67 211	78.51 209	91.65 153	90.73 169	97.64 126	92.73 193

FMVSNet3		90.19 114	90.06 109	90.34 111	88.69 177	93.85 148	94.58 68	85.78 140	90.03 93	85.56 95	77.38 139	86.13 81	89.22 129	93.29 126	94.36 84	98.20 68	95.40 158

GBi-Net		90.21 112	90.11 107	90.32 112	88.66 178	93.65 156	94.25 78	85.78 140	90.03 93	85.56 95	77.38 139	86.13 81	89.38 123	93.97 105	94.16 87	98.31 52	95.47 154

test1		90.21 112	90.11 107	90.32 112	88.66 178	93.65 156	94.25 78	85.78 140	90.03 93	85.56 95	77.38 139	86.13 81	89.38 123	93.97 105	94.16 87	98.31 52	95.47 154

FMVSNet2		89.61 122	89.14 120	90.16 118	88.66 178	93.65 156	94.25 78	85.44 144	88.57 122	84.96 109	73.53 166	83.82 93	89.38 123	94.23 98	94.68 78	98.31 52	95.47 154

PatchT		83.86 187	85.51 169	81.94 210	88.41 181	91.56 208	78.79 229	71.57 230	84.08 166	71.08 173	70.62 180	76.13 161	86.27 160	91.48 154	90.75 167	95.52 202	93.94 176

UniMVSNet (Re)		86.22 152	85.46 170	87.11 149	88.34 182	94.42 136	89.65 174	87.10 130	84.39 160	74.61 152	70.41 184	68.10 189	85.10 173	91.17 161	91.79 148	97.84 107	97.94 57

NR-MVSNet		85.46 165	84.54 175	86.52 158	88.33 183	93.78 150	90.45 153	87.87 117	84.40 158	71.61 167	70.59 181	62.09 219	82.79 189	91.75 150	91.75 149	98.10 78	97.44 76

UniMVSNet_NR-MVSNet		86.80 146	85.86 165	87.89 143	88.17 184	94.07 144	90.15 160	88.51 104	84.20 164	73.45 158	72.38 175	70.30 180	88.95 133	90.25 176	92.21 137	98.12 75	97.62 70

thisisatest0515		85.70 160	87.00 149	84.19 184	88.16 185	93.67 155	84.20 216	84.14 158	83.39 172	72.91 161	76.79 145	74.75 164	78.82 208	92.57 136	91.26 158	96.94 161	96.56 117

pm-mvs1		84.55 175	83.46 182	85.82 162	88.16 185	93.39 162	89.05 183	85.36 146	74.03 221	72.43 165	65.08 208	71.11 175	82.30 192	93.48 120	91.70 150	97.64 126	95.43 157

gm-plane-assit		77.65 221	78.50 219	76.66 222	87.96 187	85.43 233	64.70 240	74.50 219	64.15 237	51.26 238	61.32 221	58.17 233	84.11 182	95.16 66	93.83 96	97.45 134	91.41 198

test-mter		86.09 156	88.38 129	83.43 194	87.89 188	92.61 186	86.89 202	77.11 214	84.30 161	68.62 191	82.57 101	82.45 104	84.34 177	92.40 138	90.11 185	95.74 189	94.21 174

pmmvs4		86.00 158	84.28 177	88.00 139	87.80 189	92.01 201	89.94 167	84.91 148	86.79 139	80.98 128	73.41 169	66.34 200	88.12 140	89.31 193	88.90 203	96.24 183	93.20 187

TESTMET0.1,1		86.11 155	88.28 130	83.59 191	87.80 189	92.07 198	87.41 197	77.12 213	84.58 156	69.33 185	83.00 93	82.79 99	84.24 178	92.26 141	89.81 191	95.64 194	93.44 182

DU-MVS		86.12 154	84.81 173	87.66 144	87.77 191	93.78 150	90.15 160	87.87 117	84.40 158	73.45 158	70.59 181	64.82 209	88.95 133	90.14 177	92.33 134	97.76 113	97.62 70

Baseline_NR-MVSNet		85.28 167	83.42 185	87.46 148	87.77 191	90.80 217	89.90 170	87.69 123	83.93 168	74.16 154	64.72 212	66.43 199	87.48 148	90.14 177	90.83 163	97.73 116	97.11 91

SixPastTwentyTwo		83.12 198	83.44 184	82.74 203	87.71 193	93.11 174	82.30 221	82.33 179	79.24 196	64.33 214	78.77 135	62.75 215	84.11 182	88.11 203	87.89 205	95.70 192	94.21 174

TranMVSNet+NR-MVSNet		85.57 163	84.41 176	86.92 151	87.67 194	93.34 163	90.31 156	88.43 106	83.07 173	70.11 180	69.99 187	65.28 204	86.96 152	89.73 187	92.27 135	98.06 85	97.17 90

WR-MVS		83.14 197	83.38 187	82.87 202	87.55 195	93.29 165	86.36 207	84.21 156	80.05 192	66.41 204	66.91 196	66.92 196	75.66 218	88.96 199	90.56 172	97.05 152	96.96 103

v8		84.45 180	83.30 189	85.80 163	87.53 196	92.95 176	90.31 156	82.46 178	80.46 187	71.43 169	66.99 195	67.16 194	86.14 162	89.26 195	90.22 180	96.94 161	96.06 137

WR-MVS_H		82.86 202	82.66 195	83.10 198	87.44 197	93.33 164	85.71 212	83.20 171	77.36 206	68.20 194	66.37 199	65.23 205	76.05 216	89.35 191	90.13 181	97.99 98	96.89 106

v148		83.61 191	82.10 199	85.37 167	87.34 198	92.94 177	87.48 196	85.72 143	78.92 197	73.87 156	65.71 205	64.69 210	81.78 197	87.82 204	89.35 198	96.01 185	95.26 160

v10		84.18 182	83.17 191	85.37 167	87.34 198	92.68 184	90.32 155	81.33 192	79.93 195	69.23 187	66.33 200	65.74 202	87.03 151	90.84 166	90.38 175	96.97 157	96.29 130

v2v482		84.51 176	83.05 192	86.20 160	87.25 200	93.28 166	90.22 158	85.40 145	79.94 194	69.78 182	67.74 192	65.15 206	87.57 145	89.12 197	90.55 173	96.97 157	95.60 151

CP-MVSNet		83.11 199	82.15 198	84.23 183	87.20 201	92.70 183	86.42 206	83.53 167	77.83 204	67.67 197	66.89 198	60.53 227	82.47 190	89.23 196	90.65 171	98.08 81	97.20 88

v1144		84.03 186	82.88 193	85.37 167	87.17 202	93.15 173	90.18 159	83.31 169	78.83 198	67.85 195	65.99 202	64.99 207	86.79 154	90.75 168	90.33 177	96.90 167	96.15 134

V42		84.48 178	83.36 188	85.79 164	87.14 203	93.28 166	90.03 163	83.98 160	80.30 189	71.20 172	66.90 197	67.17 193	85.55 168	89.35 191	90.27 178	96.82 172	96.27 131

pmmvs5		83.37 194	82.68 194	84.18 185	87.13 204	93.18 170	86.74 203	82.08 183	76.48 211	67.28 200	71.26 178	62.70 216	84.71 175	90.77 167	90.12 184	97.15 144	94.24 172

FMVSNet1		87.33 141	86.00 162	88.89 128	87.13 204	92.83 181	93.08 120	84.46 154	81.35 183	82.20 119	66.33 200	77.96 149	88.96 132	93.97 105	94.16 87	97.54 131	95.38 159

PS-CasMVS		82.53 204	81.54 207	83.68 190	87.08 206	92.54 189	86.20 208	83.46 168	76.46 212	65.73 209	65.71 205	59.41 232	81.61 198	89.06 198	90.55 173	98.03 88	97.07 92

our_test_3					86.93 207	89.77 220	81.61 223

PEN-MVS		82.49 205	81.58 206	83.56 192	86.93 207	92.05 200	86.71 204	83.84 161	76.94 209	64.68 213	67.24 193	60.11 228	81.17 200	87.78 205	90.70 170	98.02 93	96.21 132

v1192		83.56 192	82.35 196	84.98 172	86.84 209	92.84 179	90.01 165	82.70 172	78.54 199	66.48 203	64.88 210	62.91 214	86.91 153	90.72 169	90.25 179	96.94 161	96.32 128

v144192		83.48 193	82.23 197	84.94 173	86.65 210	92.84 179	89.63 175	82.48 177	77.87 203	67.36 199	65.33 207	63.50 213	86.51 156	89.72 188	89.99 189	97.03 153	96.35 126

DTE-MVSNet		81.76 210	81.04 212	82.60 206	86.63 211	91.48 211	85.97 210	83.70 163	76.45 213	62.44 218	67.16 194	59.98 229	78.98 207	87.15 209	89.93 190	97.88 106	95.12 162

pmnet_mix02		80.14 215	80.21 216	80.06 214	86.61 212	89.66 221	80.40 226	82.20 182	82.29 179	61.35 222	71.52 177	66.67 198	76.75 213	82.55 227	80.18 230	93.05 217	88.62 218

v1921920		83.30 195	82.09 200	84.70 176	86.59 213	92.67 185	89.82 171	82.23 181	78.32 200	65.76 208	64.64 213	62.35 217	86.78 155	90.34 175	90.02 187	97.02 154	96.31 129

v1240		82.88 201	81.66 205	84.29 182	86.46 214	92.52 191	89.06 182	81.82 187	77.16 207	65.09 212	64.17 215	61.50 222	86.36 157	90.12 179	90.13 181	96.95 160	96.04 138

anonymousdsp		84.51 176	85.85 166	82.95 201	86.30 215	93.51 159	85.77 211	80.38 199	78.25 202	63.42 217	73.51 167	72.20 171	84.64 176	93.21 128	92.16 139	97.19 142	98.14 48

pmmvs6		80.90 212	78.77 218	83.38 195	85.84 216	91.61 207	86.01 209	82.54 176	64.17 236	70.43 178	54.14 233	67.06 195	80.73 202	90.50 174	89.17 200	94.74 212	94.75 166

MVS-HIRNet		78.16 219	77.57 223	78.83 218	85.83 217	87.76 227	76.67 230	70.22 233	75.82 217	67.39 198	55.61 228	70.52 177	81.96 195	86.67 213	85.06 218	90.93 230	81.58 233

test20.03		76.41 224	78.49 220	73.98 225	85.64 218	87.50 228	75.89 232	80.71 198	70.84 229	51.07 239	68.06 191	61.40 223	54.99 236	88.28 202	87.20 208	95.58 199	86.15 226

v7n		82.25 207	81.54 207	83.07 199	85.55 219	92.58 187	86.68 205	81.10 196	76.54 210	65.97 207	62.91 217	60.56 226	82.36 191	91.07 164	90.35 176	96.77 174	96.80 107

N_pmnet		77.55 222	76.68 225	78.56 219	85.43 220	87.30 230	78.84 228	81.88 186	78.30 201	60.61 223	61.46 219	62.15 218	74.03 223	82.04 228	80.69 229	90.59 232	84.81 231

Anonymous20231206		78.09 220	78.11 221	78.07 221	85.19 221	89.17 223	80.99 224	81.24 195	75.46 218	58.25 229	54.78 232	59.90 230	66.73 230	88.94 200	88.26 204	96.01 185	90.25 210

MDTV_nov1_ep13_2view		80.43 213	80.94 213	79.84 215	84.82 222	90.87 214	84.23 215	73.80 222	80.28 190	64.33 214	70.05 186	68.77 186	79.67 203	84.83 220	83.50 223	92.17 223	88.25 223

FPMVS		69.87 231	67.10 234	73.10 227	84.09 223	78.35 239	79.40 227	76.41 215	71.92 223	57.71 230	54.06 234	50.04 240	56.72 234	71.19 237	68.70 237	84.25 237	75.43 237

EU-MVSNet		78.43 218	80.25 215	76.30 223	83.81 224	87.27 231	80.99 224	79.52 203	76.01 214	54.12 234	70.44 183	64.87 208	67.40 228	86.23 214	85.54 215	91.95 226	91.41 198

FMVSNet5		84.47 179	84.72 174	84.18 185	83.30 225	88.43 225	88.09 192	79.42 204	84.25 162	74.14 155	73.15 172	78.74 140	83.65 184	91.19 160	91.19 159	96.46 178	86.07 227

blend_shiyan4		84.25 181	82.04 201	86.82 153	82.33 226	89.89 219	90.94 146	81.51 191	81.22 184	85.41 102	75.60 155	73.18 168	85.67 166	81.60 230	79.96 232	95.08 207	92.85 190

WB-MVS		60.76 234	66.86 235	53.64 234	82.24 227	72.70 240	48.70 246	82.04 184	63.91 238	12.91 249	64.77 211	49.00 243	22.74 244	75.95 235	75.36 235	73.22 243	66.33 241

MIMVSNet		82.97 200	84.00 179	81.77 212	82.23 228	92.25 195	87.40 199	72.73 229	81.48 182	69.55 183	68.79 189	72.42 170	81.82 196	92.23 144	92.25 136	96.89 168	88.61 219

PM-MVS		80.29 214	79.30 217	81.45 213	81.91 229	88.23 226	82.61 219	79.01 205	79.99 193	67.15 201	69.07 188	51.39 239	82.92 188	87.55 207	85.59 213	95.08 207	93.28 185

FE-MVSNET3		86.08 157	86.20 157	85.93 161	81.88 230	93.87 147	90.68 149	86.54 133	86.84 137	72.94 160	71.70 176	75.39 163	85.90 165	91.74 151	91.33 157	97.66 124	92.56 194

pmmvs-eth3d		79.78 217	77.58 222	82.34 208	81.57 231	87.46 229	82.92 218	81.28 193	75.33 219	71.34 170	61.88 218	52.41 238	81.59 199	87.56 206	86.90 209	95.36 205	91.48 197

new-patchmatchnet		72.32 228	71.09 231	73.74 226	81.17 232	84.86 235	72.21 237	77.48 212	68.32 232	54.89 233	55.10 230	49.31 242	63.68 233	79.30 233	76.46 234	93.03 218	84.32 232

ET-MVSNet_ETH3D		89.93 115	90.84 95	88.87 129	79.60 233	96.19 114	94.43 71	86.56 132	90.63 77	80.75 130	90.71 46	77.78 151	93.73 60	91.36 157	93.45 107	98.15 72	95.77 147

PMVS	56.77 18	61.27 233	58.64 237	64.35 232	75.66 234	54.60 244	53.62 243	74.23 220	53.69 241	58.37 228	44.27 240	49.38 241	44.16 240	69.51 239	65.35 239	80.07 239	73.66 238
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		72.29 229	73.25 229	71.16 231	75.35 235	81.38 236	73.72 236	69.27 234	75.97 215	49.84 241	56.27 227	56.12 235	69.08 225	81.73 229	80.86 228	89.72 235	80.44 235

ambc			67.96 233		73.69 236	79.79 238	73.82 235		71.61 224	59.80 226	46.00 238	20.79 248	66.15 231	86.92 211	80.11 231	89.13 236	90.50 206

pmmvs3		71.13 230	71.06 232	71.21 230	73.54 237	80.19 237	71.69 238	64.86 237	62.04 240	52.10 236	54.92 231	48.00 244	75.03 219	83.75 225	83.24 224	90.04 234	85.27 228

MDA-MVSNet-bldmvs		73.81 225	72.56 230	75.28 224	72.52 238	88.87 224	74.95 234	82.67 174	71.57 225	55.02 232	65.96 203	42.84 246	76.11 215	70.61 238	81.47 227	90.38 233	86.59 225

FE-MVSNET2		76.99 223	76.02 226	78.12 220	71.26 239	89.46 222	81.92 222	80.87 197	71.48 228	61.96 221	47.82 237	54.83 236	75.73 217	89.29 194	88.91 202	97.00 156	90.36 209

tmp_tt				50.24 237	68.55 240	46.86 246	48.90 245	18.28 244	86.51 144	68.32 192	70.19 185	65.33 203	26.69 243	74.37 236	66.80 238	70.72 244

Gipuma		58.52 235	56.17 238	61.27 233	67.14 241	58.06 243	52.16 244	68.40 236	69.00 231	45.02 243	22.79 242	20.57 249	55.11 235	76.27 234	79.33 233	79.80 240	67.16 240
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MIMVSNet1		73.19 227	73.70 228	72.60 228	65.42 242	86.69 232	75.56 233	79.65 202	67.87 233	55.30 231	45.24 239	56.41 234	63.79 232	86.98 210	87.66 206	95.85 187	85.04 229

FE-MVSNET		73.24 226	74.06 227	72.28 229	64.92 243	85.32 234	76.06 231	79.75 201	67.71 234	50.14 240	49.61 235	54.40 237	67.26 229	85.97 216	87.33 207	95.53 201	88.10 224

PMMVS2		53.68 237	55.72 239	51.30 235	58.84 244	67.02 242	54.23 242	60.97 240	47.50 242	19.42 246	34.81 241	31.97 247	30.88 242	65.84 240	69.99 236	83.47 238	72.92 239

EMVS		39.04 240	34.32 242	44.54 239	58.25 245	39.35 248	27.61 248	62.55 239	35.99 243	16.40 248	20.04 245	14.77 250	44.80 238	33.12 244	44.10 243	57.61 246	52.89 244

E-PMN		40.00 238	35.74 241	44.98 238	57.69 246	39.15 249	28.05 247	62.70 238	35.52 244	17.78 247	20.90 243	14.36 251	44.47 239	35.89 243	47.86 242	59.15 245	56.47 243

MVE	39.81 19	39.52 239	41.58 240	37.11 240	33.93 247	49.06 245	26.45 249	54.22 241	29.46 245	24.15 245	20.77 244	10.60 252	34.42 241	51.12 242	65.27 240	49.49 247	64.81 242
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		58.10 236	64.61 236	50.51 236	28.26 248	41.71 247	61.28 241	32.07 243	75.92 216	52.04 237	47.94 236	61.83 221	51.80 237	79.83 232	63.95 241	77.60 241	81.05 234

testmvs		4.35 241	6.54 243	1.79 242	0.60 249	1.82 250	3.06 251	0.95 245	7.22 246	0.88 251	12.38 246	1.25 253	3.87 246	6.09 245	5.58 244	1.40 248	11.42 246

GG-mvs-BLEND		62.84 232	90.21 104	30.91 241	0.57 250	94.45 135	86.99 201	0.34 247	88.71 120	0.98 250	81.55 114	91.58 59	0.86 247	92.66 133	91.43 155	95.73 190	91.11 202

test123		3.48 242	5.31 244	1.34 243	0.20 251	1.52 251	2.17 252	0.58 246	6.13 247	0.31 252	9.85 247	0.31 254	3.90 245	2.65 246	5.28 245	0.87 249	11.46 245

uanet_test		0.00 243	0.00 245	0.00 244	0.00 252	0.00 252	0.00 253	0.00 248	0.00 248	0.00 253	0.00 248	0.00 255	0.00 248	0.00 247	0.00 246	0.00 250	0.00 247

sosnet-low-res		0.00 243	0.00 245	0.00 244	0.00 252	0.00 252	0.00 253	0.00 248	0.00 248	0.00 253	0.00 248	0.00 255	0.00 248	0.00 247	0.00 246	0.00 250	0.00 247

sosnet		0.00 243	0.00 245	0.00 244	0.00 252	0.00 252	0.00 253	0.00 248	0.00 248	0.00 253	0.00 248	0.00 255	0.00 248	0.00 247	0.00 246	0.00 250	0.00 247

RE-MVS-def										60.19 224

9.14												97.28 24

MTAPA										95.36 2		97.46 22

MTMP										95.70 1		96.90 28

Patchmatch-RL test							18.47 250

NP-MVS									91.63 69

Patchmtry						92.39 193	89.18 179	73.30 226		71.08 173

DeepMVS_CX						71.82 241	68.37 239	48.05 242	77.38 205	46.88 242	65.77 204	47.03 245	67.48 227	64.27 241		76.89 242	76.72 236

High-resolution multi-view benchmark