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.

RA-MVS		98.33 1	98.50 1	98.13 1	98.89 15	99.58 3	98.97 6	95.56 4	99.01 1	98.28 2	98.23 1	99.36 6	97.97 1	97.03 19	96.38 14	99.10 11	99.95 1

MED-MVS		98.18 2	98.35 2	97.98 2	99.00 7	99.45 7	98.94 7	95.60 3	98.80 2	98.26 3	98.11 2	99.53 4	97.16 8	97.07 17	95.77 25	98.93 30	99.68 17

aaEdge-Enhanced		98.02 3	98.12 6	97.91 3	98.97 11	99.32 16	98.29 16	95.80 1	98.28 6	98.12 4	98.11 2	99.40 5	97.13 9	96.54 26	95.50 29	99.17 7	99.68 17

SED-MVS		97.92 4	98.27 4	97.52 4	98.88 16	99.60 1	98.80 8	95.08 11	98.57 4	95.63 6	96.98 12	99.73 1	97.67 3	97.26 12	95.86 24	99.04 17	99.89 6

MSP-MVS		97.74 5	98.32 3	97.06 10	98.66 19	99.35 11	98.66 11	94.75 17	98.22 8	93.60 10	97.99 4	98.58 11	97.41 7	98.24 2	95.95 20	99.27 4	99.91 2
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
DVP-MVS++		97.71 6	98.01 9	97.37 5	98.98 8	99.58 3	98.79 9	95.06 12	98.24 7	94.66 7	96.35 18	99.20 7	97.63 4	97.20 14	95.68 26	99.08 15	99.84 8

DPE-MVS		97.69 7	98.16 5	97.14 8	99.01 6	99.52 6	99.12 3	95.38 6	98.00 11	93.31 13	97.71 5	99.61 3	96.94 10	96.99 20	95.45 31	99.09 14	99.81 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		97.61 8	97.87 10	97.30 6	98.94 14	99.60 1	98.21 18	95.11 8	98.39 5	95.83 5	94.40 33	99.70 2	96.79 11	97.16 15	95.95 20	98.92 31	99.90 3
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
CNVR-MVS		97.60 9	98.08 7	97.03 11	99.14 2	99.55 5	98.67 10	95.32 7	97.91 12	92.55 15	97.11 9	97.23 17	97.49 6	98.16 3	97.05 6	99.04 17	99.55 23

APDe-MVS		97.31 10	97.51 15	97.08 9	98.95 13	99.29 18	98.58 13	95.11 8	97.69 18	94.16 8	96.91 13	96.81 21	96.57 14	96.71 23	95.39 33	99.08 15	99.79 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.17 11	97.18 19	97.17 7	99.11 4	99.20 20	99.05 5	95.55 5	97.39 22	93.56 11	97.48 7	96.71 23	96.75 12	95.73 36	94.40 50	98.98 24	99.33 28

NCCC		97.01 12	97.74 11	96.16 14	99.02 5	99.35 11	98.63 12	95.04 13	97.84 14	88.95 28	96.83 15	97.02 20	96.39 19	97.44 7	96.51 10	98.90 33	99.16 45

SMA-MVS		96.96 13	97.65 14	96.15 15	98.98 8	99.31 17	97.91 23	94.68 19	97.52 20	90.59 22	94.54 32	99.20 7	96.54 16	97.29 10	96.48 11	98.22 77	99.19 40
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
MCST-MVS		96.93 14	98.07 8	95.61 21	98.98 8	99.44 8	98.04 19	95.04 13	98.10 9	86.55 35	97.65 6	97.56 14	95.60 28	97.67 6	96.45 12	99.43 1	99.61 22

HPM-MVS++		96.91 15	97.70 12	96.00 16	98.97 11	99.16 22	97.82 25	94.81 16	98.04 10	89.61 25	96.56 17	98.60 10	96.39 19	97.09 16	95.22 35	98.39 67	99.22 36

SD-MVS		96.87 16	97.69 13	95.92 17	96.38 52	99.25 19	97.76 26	94.75 17	97.72 15	92.46 17	95.94 19	99.09 9	96.48 18	96.01 33	96.08 18	97.68 119	99.73 14
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
APD-MVS		96.79 17	96.99 22	96.56 12	98.76 18	98.87 31	98.42 14	94.93 15	97.70 17	91.83 18	95.52 22	95.94 30	96.63 13	95.94 34	95.47 30	98.80 39	99.47 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		96.50 18	97.08 20	95.82 19	96.12 56	98.97 28	98.00 20	94.13 24	97.89 13	91.49 19	95.11 28	97.52 15	96.26 23	96.27 31	94.07 60	98.91 32	99.74 13
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		96.20 19	97.22 18	95.01 25	98.40 26	99.11 23	97.93 22	93.62 27	96.28 35	87.45 32	97.05 11	96.00 29	94.23 36	96.83 22	95.97 19	98.40 64	99.27 33
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 20	96.41 27	95.72 20	98.58 21	98.84 32	97.95 21	93.08 31	96.96 28	90.24 23	96.60 16	94.40 36	96.52 17	95.13 46	94.33 51	97.93 109	98.59 73

ACMMP_NAP		95.81 21	96.50 26	95.01 25	98.79 17	99.17 21	97.52 31	94.20 23	96.19 36	85.71 40	93.80 36	96.20 28	95.89 25	96.62 25	94.98 41	97.93 109	98.52 77

MGCNet		95.79 22	97.46 16	93.85 31	96.81 46	99.35 11	97.21 34	87.28 52	97.10 23	88.65 31	95.17 27	96.41 26	94.15 40	97.29 10	97.19 5	99.01 22	99.73 14

train_agg		95.72 23	97.37 17	93.80 32	97.82 35	98.92 29	97.84 24	93.50 28	96.86 30	81.35 62	97.10 10	97.71 12	94.19 37	96.02 32	95.37 34	98.07 93	99.64 20

ACMMPR		95.59 24	95.89 29	95.25 23	98.41 25	98.74 33	97.69 29	92.73 35	96.88 29	88.95 28	95.33 24	92.91 43	95.79 26	94.73 56	94.33 51	97.92 111	98.32 89

DeepC-MVS_fast	91.53 1	95.57 25	95.67 32	95.45 22	98.57 22	99.00 27	97.76 26	94.41 21	97.06 25	86.84 34	86.39 51	92.27 48	96.38 21	97.89 5	98.06 3	98.73 44	99.01 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		95.49 26	94.84 37	96.25 13	98.64 20	98.63 36	98.35 15	92.37 37	95.04 54	92.62 14	87.12 49	93.79 37	96.55 15	93.53 81	96.78 7	98.98 24	98.99 55

CP-MVS		95.43 27	95.67 32	95.14 24	98.24 31	98.60 37	97.45 32	92.80 33	95.98 39	89.21 27	95.22 25	93.60 38	95.43 29	94.37 63	93.22 90	97.68 119	98.72 63

DPM-MVS		95.36 28	95.84 30	94.82 27	96.70 48	98.49 47	99.27 1	95.09 10	96.71 31	83.87 48	86.34 53	96.44 25	95.06 31	98.35 1	98.82 1	98.89 34	95.69 168

MP-MVS		95.24 29	95.96 28	94.40 29	98.32 28	98.38 52	97.12 35	92.87 32	95.17 52	85.50 41	95.68 20	94.91 34	94.58 33	95.11 47	93.76 68	98.05 96	98.68 65
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 30	97.02 21	92.61 42	97.19 41	98.71 35	97.74 28	93.21 30	96.97 27	79.27 99	94.09 34	97.14 18	90.84 74	96.64 24	95.94 22	97.42 140	99.67 19

X-MVS		94.70 31	95.71 31	93.52 36	98.38 27	98.56 39	96.99 36	92.62 36	95.58 43	81.00 72	94.57 31	93.49 39	94.16 39	94.82 52	94.29 54	97.99 104	98.68 65

PGM-MVS		94.64 32	95.49 34	93.66 34	98.55 23	98.51 45	97.63 30	87.77 50	94.45 58	84.92 44	97.23 8	91.90 50	95.22 30	94.56 59	93.80 67	97.87 115	97.97 108

TSAR-MVS + GP.		94.59 33	96.60 25	92.25 43	90.25 98	98.17 59	96.22 41	86.53 57	97.49 21	87.26 33	95.21 26	97.06 19	94.07 42	94.34 65	94.20 56	99.18 5	99.71 16

PHI-MVS		94.49 34	96.72 24	91.88 45	97.06 42	98.88 30	94.99 53	89.13 45	96.15 37	79.70 86	96.91 13	95.78 31	91.87 63	94.65 57	95.68 26	98.53 54	98.98 57

AdaColmap		94.28 35	92.94 50	95.84 18	98.32 28	98.33 54	96.06 43	94.62 20	96.29 34	91.22 20	89.89 43	85.50 78	96.38 21	91.85 116	90.89 118	98.44 60	97.81 115

DeepPCF-MVS	91.00 2	94.15 36	96.87 23	90.97 54	96.82 45	99.33 15	89.40 136	92.76 34	98.76 3	82.36 55	88.74 44	95.49 33	90.58 82	98.13 4	97.80 4	93.88 236	99.88 7

CPTT-MVS		94.11 37	93.99 43	94.25 30	96.58 49	97.66 68	97.31 33	91.94 38	94.84 55	88.72 30	92.51 37	93.04 42	95.78 27	91.51 122	89.97 135	95.15 217	98.37 86

EPNet		93.69 38	95.34 35	91.76 46	96.98 44	98.47 49	95.40 49	86.79 54	95.47 45	82.84 52	95.66 21	89.17 56	90.47 85	95.25 45	94.69 45	98.10 88	98.68 65
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 39	93.59 46	93.00 40	97.03 43	98.24 55	95.27 51	91.66 41	95.20 50	83.25 50	95.39 23	85.52 76	92.80 54	92.60 105	90.21 131	98.01 101	97.99 104
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
CANet		93.23 40	93.72 45	92.65 41	95.48 59	99.09 25	96.55 39	86.74 55	95.28 48	85.22 42	77.30 81	91.25 52	92.60 56	97.06 18	96.63 9	99.31 2	99.45 27

CDPH-MVS		93.22 41	95.08 36	91.04 52	97.57 38	98.49 47	96.74 38	89.35 44	95.19 51	73.57 139	90.26 41	91.59 51	90.68 79	95.09 49	96.15 16	98.31 75	98.81 61

CSCG		93.16 42	92.65 51	93.76 33	98.32 28	99.09 25	96.12 42	89.91 43	93.15 67	89.64 24	83.62 61	88.91 58	92.40 58	91.09 129	93.70 69	96.14 198	98.99 55

MVS_111021_LR		93.05 43	94.53 39	91.32 50	96.43 51	98.38 52	92.81 68	87.20 53	95.94 41	81.45 61	94.75 29	86.08 72	92.12 61	94.83 51	93.34 84	97.89 114	98.42 84

3Dnovator+	86.26 7	92.90 44	92.45 53	93.42 37	97.25 40	98.45 51	95.82 44	85.71 63	93.83 62	89.55 26	72.31 119	92.28 47	94.01 44	95.10 48	95.92 23	98.17 84	99.23 35

MVSMamba_PlusPlus		92.73 45	94.19 41	91.03 53	89.86 102	98.16 60	95.33 50	85.38 67	97.56 19	80.47 76	86.68 50	84.99 83	96.11 24	97.37 8	96.77 8	99.04 17	97.76 117

MVS_111021_HR		92.73 45	94.83 38	90.28 59	96.27 53	99.10 24	92.77 69	86.15 60	93.41 65	77.11 126	93.82 35	87.39 64	90.61 80	95.60 38	95.15 37	98.79 40	99.32 29

PLC	89.12 3	92.67 47	90.84 63	94.81 28	97.69 36	96.10 114	95.42 48	91.70 39	95.82 42	92.52 16	81.24 67	86.01 73	94.36 34	92.44 109	90.27 128	97.19 149	93.99 197
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 48	91.96 55	93.20 38	97.99 32	98.47 49	95.78 45	85.94 61	93.07 68	86.40 36	73.43 105	89.00 57	94.08 41	94.74 55	96.44 13	99.01 22	98.57 74

DeepC-MVS	88.77 4	92.39 49	91.74 57	93.14 39	96.21 54	98.55 42	96.30 40	93.84 25	93.06 69	81.09 69	74.69 95	85.20 82	93.48 48	95.41 41	96.13 17	97.92 111	99.18 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OMC-MVS		92.05 50	91.88 56	92.25 43	96.51 50	97.94 62	93.18 65	88.97 47	96.53 32	84.47 46	80.79 69	87.85 60	93.25 52	92.48 108	91.81 111	97.12 151	95.73 167

MVSTER		91.91 51	93.43 49	90.14 60	89.81 106	92.32 168	94.53 56	81.32 120	96.00 38	84.77 45	85.41 58	92.39 46	91.32 66	96.41 27	94.01 63	99.11 10	97.45 129

SPE-MVS-test		91.76 52	93.47 47	89.76 63	94.64 64	98.22 57	88.13 147	81.58 117	97.02 26	82.47 54	85.49 57	85.41 80	93.28 50	95.33 43	93.61 76	98.45 59	99.22 36

QAPM		91.68 53	91.97 54	91.34 49	97.86 34	98.72 34	95.60 47	85.72 62	90.86 87	77.14 125	76.06 84	90.35 53	92.69 55	94.10 69	94.60 47	99.04 17	99.09 48

CS-MVS		91.55 54	92.49 52	90.45 58	94.00 67	97.91 64	91.17 92	81.40 119	95.22 49	83.51 49	82.37 65	82.29 89	94.07 42	96.36 30	94.03 61	98.56 51	99.22 36

CNLPA		91.53 55	89.74 76	93.63 35	96.75 47	97.63 70	91.16 94	91.70 39	96.38 33	90.82 21	69.66 138	85.52 76	93.76 45	90.44 136	91.14 117	97.55 132	97.40 130

ETV-MVS		91.51 56	94.06 42	88.54 80	89.39 112	97.52 71	89.48 131	80.88 125	97.09 24	79.41 94	87.87 45	86.18 71	92.95 53	95.94 34	94.33 51	99.13 9	99.52 25

EC-MVSNet		91.25 57	93.45 48	88.68 77	88.90 122	96.18 111	91.66 78	76.70 160	95.57 44	82.00 58	84.18 59	89.28 55	94.17 38	95.64 37	94.19 57	98.68 46	99.14 46

DELS-MVS		91.09 58	90.56 71	91.71 47	95.82 57	98.59 38	95.74 46	86.68 56	85.86 125	85.12 43	72.71 113	81.36 92	88.06 127	97.31 9	98.27 2	98.86 37	99.82 9
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
TAPA-MVS	87.40 6	90.98 59	90.71 65	91.30 51	96.14 55	97.66 68	94.80 54	89.00 46	94.74 57	77.42 122	80.22 70	86.70 67	92.27 59	91.65 121	90.17 133	98.15 87	93.83 201
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 60	90.66 67	90.82 56	94.75 62	98.54 43	91.30 87	86.53 57	95.43 46	85.75 38	78.66 76	70.67 137	87.60 129	96.37 28	95.08 39	98.98 24	99.90 3

PVSNet_Blended		90.74 60	90.66 67	90.82 56	94.75 62	98.54 43	91.30 87	86.53 57	95.43 46	85.75 38	78.66 76	70.67 137	87.60 129	96.37 28	95.08 39	98.98 24	99.90 3

CHOSEN 280x420		90.61 62	94.27 40	86.35 119	93.12 72	98.16 60	89.99 124	69.62 224	92.48 73	76.89 130	87.28 48	96.72 22	90.31 88	94.81 53	92.33 104	98.17 84	98.08 101

MAR-MVS		90.44 63	91.17 61	89.59 64	97.48 39	97.92 63	90.96 101	79.80 131	95.07 53	77.03 127	80.83 68	79.10 102	94.68 32	93.16 88	94.46 49	97.59 130	97.63 122
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
PCF-MVS	88.14 5	90.42 64	89.56 82	91.41 48	94.44 65	98.18 58	94.35 57	94.33 22	84.55 142	76.61 131	75.84 87	88.47 59	91.29 67	90.37 139	90.66 124	97.46 136	98.88 60
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
OpenMVS	83.41 11	89.84 65	88.89 88	90.95 55	97.63 37	98.51 45	94.64 55	85.47 66	88.14 108	78.39 113	65.06 168	85.42 79	91.04 71	93.06 91	93.70 69	98.53 54	98.37 86

EIA-MVS		89.82 66	91.48 59	87.89 103	89.16 114	97.31 73	88.99 138	80.92 124	94.29 59	77.65 120	82.16 66	79.77 100	91.90 62	94.61 58	93.03 95	98.70 45	99.21 39

sasdasda		89.62 67	89.87 74	89.33 66	90.47 91	97.02 79	93.46 62	79.67 134	92.45 74	81.05 70	82.84 62	73.00 124	93.71 46	90.38 137	94.85 42	97.65 124	98.54 75

canonicalmvs		89.62 67	89.87 74	89.33 66	90.47 91	97.02 79	93.46 62	79.67 134	92.45 74	81.05 70	82.84 62	73.00 124	93.71 46	90.38 137	94.85 42	97.65 124	98.54 75

TSAR-MVS + COLMAP		89.59 69	89.64 79	89.53 65	93.32 71	96.51 95	95.03 52	88.53 48	95.98 39	69.10 155	91.81 39	64.53 184	93.40 49	93.53 81	91.35 116	97.77 116	93.75 204

HQP-MVS		89.57 70	90.57 70	88.41 84	92.77 73	94.71 138	94.24 58	87.97 49	93.44 64	68.18 158	91.75 40	71.54 136	89.90 100	92.31 112	91.43 114	97.39 141	98.80 62

MGCFI-Net		89.36 71	89.66 78	89.02 72	90.40 95	96.92 82	93.26 64	79.54 138	92.10 77	80.11 80	82.55 64	72.65 127	93.26 51	90.24 141	94.69 45	97.53 134	98.46 82

MVS_Test		89.02 72	90.20 72	87.64 106	89.83 105	97.05 78	92.30 72	77.59 156	92.89 70	75.01 136	77.36 80	76.10 112	92.27 59	95.30 44	95.42 32	98.83 38	97.30 134

CLD-MVS		88.99 73	88.07 91	90.07 61	89.61 108	94.94 135	93.82 61	85.70 64	92.73 72	82.73 53	79.97 71	69.59 144	90.44 86	90.32 140	89.93 137	98.10 88	99.04 51
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
baseline		88.91 74	89.94 73	87.70 105	89.44 111	96.74 87	91.62 80	77.92 153	93.79 63	78.76 104	77.55 79	78.46 105	89.38 110	92.26 113	92.52 101	99.10 11	98.23 92

PMMVS		88.56 75	91.22 60	85.47 132	90.04 100	95.60 130	86.62 163	78.49 148	93.86 61	70.62 150	90.00 42	80.08 98	91.64 64	92.36 110	89.80 141	95.40 212	96.84 146

test2506		88.38 76	88.02 93	88.80 76	91.55 82	97.78 65	90.87 104	83.36 79	84.51 143	83.06 51	74.13 98	76.93 109	85.39 141	94.34 65	93.33 86	98.60 47	95.10 186

E2		88.25 77	87.54 99	89.08 70	88.94 120	96.72 88	90.74 106	83.41 77	86.83 120	82.08 57	72.76 112	70.33 139	90.81 75	93.83 75	94.01 63	98.48 56	98.29 91

Casviewmamba		88.16 78	87.37 101	89.09 69	89.09 116	96.34 102	90.93 103	83.41 77	89.70 95	82.13 56	70.03 136	70.14 141	91.34 65	94.28 68	93.39 82	97.66 122	97.68 120

baseline1		88.16 78	88.15 90	88.17 91	90.02 101	94.79 137	91.85 77	83.89 70	87.37 114	75.67 134	73.75 103	79.89 99	88.44 126	94.41 60	93.33 86	99.18 5	93.55 206

thisisatest0530		87.99 80	90.76 64	84.75 136	88.36 146	96.82 84	87.65 152	79.67 134	91.77 79	70.93 146	79.94 72	87.65 62	84.21 152	92.98 94	89.07 154	97.66 122	97.13 139

tttt0517		87.93 81	90.71 65	84.68 137	88.33 147	96.76 86	87.42 156	79.67 134	91.74 80	70.83 147	79.91 73	87.61 63	84.21 152	92.88 99	89.07 154	97.62 128	97.03 141

CANet_DTU		87.91 82	91.57 58	83.64 144	90.96 85	97.12 76	91.90 76	75.97 168	92.83 71	53.16 220	86.02 54	79.02 103	90.80 76	95.40 42	94.15 58	99.03 21	96.47 158

diffmvs		87.86 83	87.40 100	88.39 85	88.57 136	96.10 114	91.24 89	83.15 90	90.62 89	79.13 101	72.45 117	67.71 163	90.07 95	92.58 106	93.31 89	98.17 84	99.03 52
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IS_MVSNet		87.83 84	90.66 67	84.53 138	90.08 99	96.79 85	88.16 146	79.89 130	85.44 127	72.20 141	75.50 91	87.14 65	80.21 180	95.53 39	95.22 35	96.65 168	99.02 53

viewcassd2359sk11		87.73 85	86.79 110	88.83 75	88.87 124	96.64 89	90.66 109	83.33 84	85.05 136	81.22 67	70.85 128	69.54 145	90.50 84	93.40 85	93.86 65	98.40 64	98.21 93

EPP-MVSNet		87.72 86	89.74 76	85.37 133	89.11 115	95.57 131	86.31 166	79.44 139	85.83 126	75.73 133	77.23 82	90.05 54	84.78 148	91.22 127	90.25 129	96.83 158	98.04 102

hybridnocas07		87.67 87	87.10 105	88.33 86	88.75 126	96.06 120	90.46 113	83.08 96	91.52 86	80.08 81	73.23 108	68.53 153	89.58 107	89.30 154	92.59 100	98.05 96	98.47 81

hybridcas		87.66 88	86.50 116	89.01 73	88.92 121	96.24 109	91.23 90	83.30 85	87.20 116	81.96 59	68.06 147	69.31 146	90.34 87	93.95 72	93.10 93	98.33 72	97.67 121

casdiffmvs_mvg		87.64 89	86.46 117	89.01 73	89.45 110	96.09 116	92.69 70	83.42 76	84.60 141	80.01 83	68.55 144	70.29 140	90.51 83	93.93 73	93.59 78	97.96 105	98.18 94
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybrid		87.63 90	87.24 103	88.09 95	88.62 134	96.01 121	90.12 120	82.94 101	91.56 85	79.86 85	73.01 110	68.92 150	89.06 118	90.03 145	92.46 102	97.94 107	98.66 69

ET-MVSNet_ETH3D		87.63 90	91.08 62	83.59 145	67.96 255	96.30 104	92.06 74	78.47 149	91.95 78	69.87 152	87.57 47	84.14 87	94.34 35	88.58 161	92.10 107	98.88 35	96.93 142

DI_MVS_pp		87.63 90	87.13 104	88.22 88	88.61 135	95.92 124	94.09 60	81.41 118	87.00 118	78.38 114	59.70 189	80.52 96	89.08 117	94.37 63	93.34 84	97.73 117	99.05 50

casdiffmvs		87.59 93	86.69 112	88.64 78	89.06 118	96.32 103	90.18 118	83.21 89	87.74 112	80.20 78	67.99 150	68.34 159	90.79 77	93.83 75	94.08 59	98.41 63	98.50 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
onestephybrid01		87.50 94	87.03 107	88.04 98	88.72 130	96.07 118	89.49 130	83.05 98	90.81 88	81.13 68	71.59 123	69.71 142	88.69 124	89.50 152	92.40 103	97.16 150	99.17 42

viewmamba		87.49 95	86.97 109	88.09 95	88.73 129	95.97 122	90.04 123	82.85 103	92.44 76	78.95 103	72.17 121	68.85 151	90.31 88	88.68 159	92.23 106	97.65 124	98.42 84

PVSNet_Blended_VisFu		87.44 96	88.72 89	85.95 127	92.02 77	97.26 74	86.88 161	82.66 106	83.86 149	79.16 100	66.96 156	84.91 84	77.26 201	94.97 50	93.48 79	97.73 117	99.64 20

viewdifsd2359ckpt09		87.42 97	86.55 114	88.45 83	88.67 132	96.49 96	90.38 115	83.11 94	85.25 130	79.50 88	70.80 129	68.43 156	90.90 73	93.87 74	93.04 94	98.10 88	97.95 109

viewmanbaseed2359cas		87.26 98	86.56 113	88.07 97	89.09 116	96.64 89	90.52 112	83.44 74	85.33 128	76.94 129	70.09 135	68.98 149	90.04 96	92.85 100	94.02 62	98.40 64	98.03 103

diffmvs_AUTHOR		87.25 99	86.52 115	88.11 94	88.39 144	96.07 118	91.06 96	82.98 100	88.29 107	78.43 110	70.18 134	67.08 173	89.79 104	92.05 115	93.02 96	98.03 99	98.94 58

FMVSNet3		87.19 100	87.32 102	87.04 117	82.82 185	90.21 185	92.88 67	76.53 163	91.69 81	81.31 63	64.81 171	80.64 93	89.79 104	94.80 54	94.76 44	98.88 35	94.32 193

LS3D		87.19 100	85.48 127	89.18 68	94.96 61	95.47 132	92.02 75	93.36 29	88.69 103	67.01 159	70.56 131	72.10 131	92.47 57	89.96 146	89.93 137	95.25 214	91.68 222

ACMP	85.16 9	87.15 102	87.04 106	87.27 112	90.80 87	94.45 141	89.41 135	83.09 95	89.15 97	76.98 128	86.35 52	65.80 178	86.94 134	88.45 162	87.52 177	96.42 184	97.56 127
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E3new		87.11 103	85.87 124	88.55 79	88.74 127	96.52 93	90.53 110	83.25 87	82.75 154	80.24 77	68.90 142	68.41 158	90.19 92	92.76 103	93.68 71	98.32 73	98.10 98

E3		87.08 104	85.87 124	88.49 81	88.74 127	96.52 93	90.53 110	83.25 87	82.74 155	79.93 84	68.88 143	68.46 155	90.18 93	92.76 103	93.66 73	98.32 73	98.10 98

UGNet		87.04 105	89.59 81	84.07 140	90.94 86	95.95 123	86.02 168	81.65 115	85.94 124	78.54 108	78.00 78	85.40 81	69.62 226	91.83 117	91.53 113	97.63 127	98.51 78
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
viewdifsd2359ckpt13		87.03 106	86.28 118	87.90 102	88.81 125	96.63 91	89.75 126	83.30 85	85.16 133	77.32 123	69.27 139	67.96 161	90.14 94	93.53 81	93.67 72	98.09 92	97.74 118

LGP-MVS_train		86.95 107	87.65 96	86.12 122	91.77 80	93.84 147	93.04 66	82.77 104	88.04 109	65.33 164	87.69 46	67.09 172	86.79 135	90.20 142	88.99 157	97.05 153	97.71 119

PatchMatch-RL		86.75 108	85.43 129	88.29 87	94.06 66	96.37 101	86.82 162	82.94 101	88.94 100	79.59 87	79.83 74	59.17 201	89.46 109	91.12 128	88.81 161	96.88 157	93.78 202

FA-MVS(training)		86.74 109	88.01 94	85.26 134	89.86 102	96.99 81	88.54 143	64.26 243	89.04 98	81.30 66	66.74 158	81.52 91	89.11 116	94.04 70	90.37 127	98.47 57	97.37 131

viewmambaseed2359dif		86.69 110	85.42 130	88.17 91	88.54 137	95.67 126	90.98 100	82.71 105	86.36 123	80.14 79	68.41 145	68.31 160	89.91 99	87.78 169	92.27 105	96.75 162	99.13 47

baseline2		86.51 111	89.35 85	83.19 147	85.70 170	94.88 136	85.75 173	77.13 158	89.87 93	70.65 149	79.03 75	79.14 101	81.51 173	93.70 77	90.22 130	98.38 68	98.60 72

viewdifsd2359ckpt07		86.50 112	85.45 128	87.72 104	88.88 123	96.19 110	89.63 127	83.34 83	81.97 160	78.44 109	67.87 152	68.43 156	87.74 128	93.68 78	93.13 92	98.27 76	96.88 144

thres100view900		86.48 113	85.08 133	88.12 93	90.54 88	96.90 83	92.39 71	84.82 68	84.16 147	71.65 142	70.86 126	60.49 196	91.23 69	93.65 79	90.19 132	98.10 88	99.32 29

ACMM	84.23 10	86.40 114	84.64 141	88.46 82	91.90 78	91.93 174	88.11 148	85.59 65	88.61 104	79.13 101	75.31 92	66.25 176	89.86 103	89.88 147	87.64 174	96.16 197	92.86 211
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E5new		86.34 115	84.76 137	88.20 89	88.52 138	96.26 105	90.68 107	83.36 79	79.90 172	78.40 111	66.52 159	67.18 170	90.01 97	91.82 118	93.64 74	98.22 77	97.98 106

E5		86.34 115	84.76 137	88.20 89	88.52 138	96.26 105	90.68 107	83.36 79	79.90 172	78.40 111	66.52 159	67.18 170	90.01 97	91.82 118	93.64 74	98.22 77	97.98 106

dtuplus		86.22 117	84.66 140	88.03 99	88.31 148	95.62 129	90.41 114	82.64 107	82.92 153	80.07 82	67.05 155	68.49 154	90.23 90	87.56 171	92.10 107	96.49 181	98.90 59

GBi-Net		86.16 118	86.00 121	86.35 119	81.81 192	89.52 194	91.40 83	76.53 163	91.69 81	81.31 63	64.81 171	80.64 93	88.72 120	90.54 133	90.72 120	98.34 69	94.08 194

test1		86.16 118	86.00 121	86.35 119	81.81 192	89.52 194	91.40 83	76.53 163	91.69 81	81.31 63	64.81 171	80.64 93	88.72 120	90.54 133	90.72 120	98.34 69	94.08 194

E4		86.15 120	84.60 142	87.96 101	88.52 138	96.25 107	90.25 117	83.05 98	79.58 175	78.14 116	66.12 162	67.23 168	89.62 106	91.68 120	93.43 81	98.20 80	97.93 110

tfpn200view9		86.07 121	84.76 137	87.61 107	90.54 88	96.39 98	91.35 86	83.15 90	84.16 147	71.65 142	70.86 126	60.49 196	90.91 72	92.89 96	89.34 145	98.05 96	99.17 42

DCV-MVSNet		85.90 122	85.88 123	85.93 128	87.86 153	88.37 211	89.45 134	77.46 157	87.33 115	77.51 121	76.06 84	75.76 114	88.48 125	87.40 173	88.89 160	94.80 223	97.37 131

Vis-MVSNet (Re-imp)		85.89 123	89.62 80	81.55 159	89.85 104	96.08 117	87.55 153	79.80 131	84.80 138	66.55 161	73.70 104	86.71 66	68.25 233	94.40 61	94.53 48	97.32 144	97.09 140

MSDG		85.81 124	82.29 169	89.93 62	95.52 58	92.61 163	91.51 82	91.46 42	85.12 134	78.56 106	63.25 178	69.01 148	85.30 144	88.45 162	88.23 166	97.21 148	89.33 234

thres200		85.80 125	84.38 144	87.46 110	90.51 90	96.39 98	91.64 79	83.15 90	81.59 164	71.54 144	70.24 132	60.41 198	89.88 101	92.89 96	89.85 140	98.06 94	99.26 34

E6new		85.77 126	84.30 146	87.49 108	88.49 142	96.18 111	89.47 132	81.93 113	79.29 176	77.66 118	65.72 163	66.80 174	89.17 113	91.36 124	92.90 98	98.19 82	97.84 113

E6		85.77 126	84.30 146	87.49 108	88.49 142	96.18 111	89.47 132	81.93 113	79.29 176	77.66 118	65.72 163	66.80 174	89.17 113	91.36 124	92.90 98	98.19 82	97.84 113

ECVR-MVS		85.74 128	83.80 154	88.00 100	91.55 82	97.78 65	90.87 104	83.36 79	84.51 143	78.21 115	58.65 194	62.75 190	85.39 141	94.34 65	93.33 86	98.60 47	95.25 179

viewmacassd2359aftdt		85.71 129	84.41 143	87.22 113	88.63 133	96.25 107	90.16 119	83.07 97	79.77 174	74.57 138	65.34 165	67.22 169	88.71 123	90.93 130	93.61 76	98.20 80	97.77 116

OPM-MVS		85.69 130	82.79 162	89.06 71	93.42 69	94.21 145	94.21 59	87.61 51	72.68 198	70.79 148	71.09 124	67.27 167	90.74 78	91.29 126	89.05 156	97.61 129	93.94 199
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		85.59 131	84.08 149	87.36 111	90.45 93	96.60 92	90.95 102	83.67 73	80.99 168	71.17 145	69.08 141	60.25 199	89.88 101	93.14 89	89.34 145	98.02 100	99.17 42

0.3-1-1-0.015		85.55 132	85.15 132	86.02 125	78.77 213	93.03 158	91.14 95	80.95 123	88.71 102	79.50 88	73.18 109	73.11 118	89.48 108	83.59 206	88.42 164	96.29 190	96.01 163

0.4-1-1-0.2		85.51 133	85.07 134	86.02 125	78.76 214	93.04 157	91.17 92	81.04 122	88.53 105	79.46 93	72.62 116	73.05 122	89.37 111	83.67 205	88.56 163	96.31 187	96.03 162

CostFormer		85.47 134	86.98 108	83.71 143	88.70 131	94.02 146	88.07 149	62.72 245	89.78 94	78.68 105	72.69 114	78.37 106	87.35 131	85.96 186	89.32 149	96.73 165	98.72 63

0.4-1-1-0.1		85.32 135	84.89 135	85.83 130	78.73 215	93.00 159	90.99 99	80.42 127	88.43 106	79.41 94	72.22 120	73.05 122	89.17 113	83.43 210	88.14 167	96.24 193	95.94 165

test1111		85.17 136	83.46 157	87.17 114	91.36 84	97.75 67	90.06 122	83.44 74	83.41 151	75.25 135	58.08 198	62.19 192	84.39 151	94.39 62	93.38 83	98.54 53	95.00 188

thres600view7		85.14 137	83.58 156	86.96 118	90.37 97	96.39 98	90.33 116	83.15 90	80.46 169	70.60 151	67.96 151	60.04 200	89.22 112	92.89 96	88.28 165	98.06 94	99.08 49

test-LLR		85.11 138	89.49 83	80.00 169	85.32 174	94.49 139	82.27 204	74.18 178	87.83 110	56.70 197	75.55 89	86.26 68	82.75 166	93.06 91	90.60 125	98.77 41	98.65 70

FMVSNet2		84.89 139	84.02 151	85.91 129	81.81 192	89.52 194	91.40 83	75.79 169	84.45 145	79.39 96	58.75 192	74.35 116	88.72 120	93.51 84	93.46 80	98.34 69	94.08 194

FC-MVSNet-train		84.88 140	84.08 149	85.82 131	89.21 113	91.74 175	85.87 169	81.20 121	81.71 163	74.66 137	73.38 106	64.99 182	86.60 136	90.75 131	88.08 168	97.36 142	97.90 111

EPNet_dtu		84.87 141	89.01 86	80.05 168	95.25 60	92.88 161	88.84 140	84.11 69	91.69 81	49.28 236	85.69 55	78.95 104	65.39 238	92.22 114	91.66 112	97.43 139	89.95 230
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 142	85.71 126	83.73 142	87.94 152	95.76 125	90.08 121	73.45 193	85.12 134	62.66 173	72.39 118	64.97 183	90.59 81	92.95 95	90.69 123	97.67 121	98.12 96

UA-Net		84.69 143	87.64 97	81.25 161	90.38 96	95.67 126	87.33 157	79.41 140	72.07 202	66.48 162	75.09 93	92.48 45	66.88 234	94.03 71	94.25 55	97.01 156	89.88 231

TESTMET0.1,1		84.62 144	89.49 83	78.94 179	82.18 189	94.49 139	82.27 204	70.94 213	87.83 110	56.70 197	75.55 89	86.26 68	82.75 166	93.06 91	90.60 125	98.77 41	98.65 70

CHOSEN 1792x2688		84.59 145	84.30 146	84.93 135	93.71 68	98.23 56	89.91 125	77.96 152	84.81 137	65.93 163	45.19 248	71.76 135	83.13 164	95.46 40	95.13 38	98.94 29	99.53 24

casdiffseed414692147		84.37 146	81.97 173	87.16 116	88.39 144	95.36 133	89.17 137	81.64 116	78.81 180	77.31 124	60.13 187	61.16 194	88.91 119	89.68 149	91.85 110	97.54 133	96.81 147

Anonymous20231211		84.23 147	81.71 177	87.17 114	87.38 162	93.59 150	88.95 139	82.14 111	83.82 150	78.56 106	48.09 240	73.89 117	91.25 68	86.38 180	88.06 170	94.74 224	98.14 95

MDTV_nov1_ep13		84.17 148	88.03 92	79.66 171	86.00 168	94.41 142	85.05 175	66.01 239	90.36 90	64.34 169	77.13 83	84.56 85	82.71 168	87.12 177	88.92 158	93.84 238	93.69 205

test-mter		84.06 149	89.00 87	78.29 184	81.92 190	94.23 144	81.07 214	70.38 218	87.12 117	56.10 207	74.75 94	85.80 74	81.81 172	92.52 107	90.10 134	98.43 61	98.49 80

viewdifsd2359ckpt11		83.97 150	82.19 170	86.05 123	87.69 157	93.13 154	86.43 164	82.38 109	82.00 159	79.38 97	68.06 147	64.36 187	87.13 132	83.72 204	86.86 183	93.31 244	97.22 135

viewmsd2359difaftdt		83.97 150	82.19 170	86.04 124	87.69 157	93.13 154	86.43 164	82.37 110	81.93 161	79.33 98	68.06 147	64.40 186	87.12 133	83.73 203	86.86 183	93.31 244	97.22 135

IB-MVS	79.58 12	83.83 152	84.81 136	82.68 151	91.85 79	97.35 72	75.75 239	82.57 108	86.55 121	84.01 47	70.90 125	65.43 180	63.18 246	84.19 200	89.92 139	98.74 43	99.31 31
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
EPMVS		83.71 153	86.76 111	80.16 167	89.72 107	95.64 128	84.68 176	59.73 250	89.61 96	62.67 172	72.65 115	81.80 90	86.22 138	86.23 182	88.03 171	97.96 105	93.35 207

HyFIR lowres test		83.43 154	82.94 160	84.01 141	93.41 70	97.10 77	87.21 158	74.04 181	80.15 171	64.98 165	41.09 257	76.61 111	86.51 137	93.31 86	93.01 97	97.91 113	99.30 32

PatchmatchNet		83.28 155	87.57 98	78.29 184	87.46 160	94.95 134	83.36 186	59.43 253	90.20 92	58.10 192	74.29 97	86.20 70	84.13 154	85.27 192	87.39 178	97.25 147	94.67 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 156	87.76 95	78.00 190	87.45 161	92.20 169	82.63 200	58.42 255	90.30 91	58.23 190	75.74 88	87.75 61	83.97 157	86.10 185	87.64 174	97.30 145	94.62 192

GeoE		83.17 157	82.86 161	83.53 146	87.24 163	93.78 148	87.94 150	72.75 198	82.19 158	69.76 153	60.54 185	65.95 177	86.01 139	89.41 153	89.72 142	97.47 135	98.43 83

CDS-MVSNet		83.13 158	83.73 155	82.43 157	84.52 179	92.92 160	88.26 145	77.67 155	72.08 201	69.08 156	66.96 156	74.66 115	78.61 187	90.70 132	91.96 109	96.46 183	96.86 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 159	81.86 174	84.13 139	88.25 149	88.32 212	87.67 151	80.86 126	84.78 139	76.57 132	85.56 56	76.00 113	84.61 149	78.20 241	76.52 246	86.81 263	83.63 255

Vis-MVSNet		82.88 160	86.04 120	79.20 177	87.77 156	96.42 97	86.10 167	76.70 160	74.82 192	61.38 176	70.70 130	77.91 107	64.83 240	93.22 87	93.19 91	98.43 61	96.01 163
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 161	82.64 165	82.62 153	87.81 155	92.81 162	84.39 178	61.96 246	86.43 122	81.63 60	69.72 137	67.60 165	84.42 150	82.51 219	83.90 217	95.52 208	95.50 176

IterMVS-LS		82.62 162	82.75 164	82.48 154	87.09 164	87.48 225	87.19 159	72.85 196	79.09 178	66.63 160	65.22 166	72.14 130	84.06 156	88.33 165	91.39 115	97.03 155	95.60 175
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 163	82.51 167	82.72 150	85.49 173	93.06 156	87.17 160	71.39 210	84.18 146	64.59 167	63.03 179	58.89 202	90.22 91	91.39 123	90.83 119	97.44 137	96.21 160

tpm cat1		82.39 164	82.32 168	82.47 155	88.13 150	92.42 167	87.43 154	62.79 244	85.30 129	78.05 117	60.14 186	72.10 131	83.20 163	82.26 222	85.67 196	95.23 215	98.35 88

dmvs_re		82.31 165	81.55 178	83.19 147	83.15 184	93.17 153	88.68 142	83.72 71	82.73 156	61.70 174	67.43 154	55.43 215	83.35 162	87.51 172	89.27 152	98.56 51	95.31 178

MS-PatchMatch		82.16 166	82.18 172	82.12 158	91.65 81	93.50 151	89.51 129	71.95 204	81.48 165	64.45 168	59.58 191	77.54 108	77.23 202	89.88 147	85.62 197	97.94 107	87.68 238

blend_shiyan4		81.76 167	80.92 183	82.74 149	79.07 210	85.29 237	91.60 81	74.15 180	89.00 99	79.50 88	73.82 100	73.11 118	77.73 195	77.73 243	75.18 249	94.37 227	92.34 214

tpmrst		81.71 168	83.87 153	79.20 177	89.01 119	93.67 149	84.22 179	60.14 248	87.45 113	59.49 180	64.97 169	71.86 134	85.30 144	84.72 196	86.30 188	97.04 154	98.09 100

RPMNet		81.47 169	86.24 119	75.90 209	86.72 165	92.12 171	82.82 198	55.76 262	85.21 131	53.73 218	63.45 176	83.16 88	80.13 181	92.34 111	89.52 143	96.23 195	97.90 111

CR-MVSNet		81.44 170	85.29 131	76.94 200	86.53 166	92.12 171	83.86 180	58.37 256	85.21 131	56.28 202	59.60 190	80.39 97	80.50 178	92.77 101	89.32 149	96.12 199	97.59 125

Effi-MVS+-dtu		81.18 171	82.77 163	79.33 175	84.70 178	92.54 165	85.81 170	71.55 208	78.84 179	57.06 196	71.98 122	63.77 188	85.09 146	88.94 157	87.62 176	91.79 255	95.68 170

test0.0.03 1		80.99 172	84.37 145	77.05 198	85.32 174	89.79 190	78.43 230	74.18 178	84.78 139	57.98 195	76.06 84	72.88 126	69.14 230	88.02 167	87.70 172	97.27 146	91.37 223

dtuonly		80.91 173	81.25 182	80.52 165	82.54 186	91.09 178	87.43 154	75.69 172	77.28 184	56.58 200	58.23 196	67.55 166	85.08 147	89.06 156	89.42 144	95.80 204	96.10 161

Fast-Effi-MVS+-dtu		80.57 174	83.44 158	77.22 196	83.98 182	91.52 177	85.78 172	64.54 242	80.38 170	50.28 232	74.06 99	62.89 189	82.00 171	89.10 155	88.91 159	96.75 162	97.21 138

FMVSNet5		80.56 175	82.53 166	78.26 186	73.80 247	81.52 255	82.26 206	68.36 230	88.85 101	64.21 170	69.09 140	84.38 86	83.49 161	87.13 176	86.76 185	97.44 137	79.95 259

ADS-MVSNet		80.25 176	82.96 159	77.08 197	87.86 153	92.60 164	81.82 211	56.19 261	86.95 119	56.16 205	68.19 146	72.42 129	83.70 160	82.05 223	85.45 202	96.75 162	93.08 210

FMVSNet1		80.18 177	78.07 192	82.65 152	78.55 220	87.57 224	88.41 144	73.93 186	70.16 207	73.57 139	49.80 229	64.45 185	85.35 143	90.54 133	90.72 120	96.10 200	93.21 208

USDC		80.10 178	79.33 188	81.00 163	86.36 167	91.71 176	88.74 141	75.77 170	81.90 162	54.90 212	67.67 153	52.05 221	83.94 158	88.44 164	86.25 189	96.31 187	87.28 242

COLMAP_ROB	75.69 15	79.47 179	76.90 201	82.46 156	92.20 74	90.53 181	85.30 174	83.69 72	78.27 183	61.47 175	58.26 195	62.75 190	78.28 190	82.41 220	82.13 230	93.83 240	83.98 254
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs4		79.32 180	77.78 196	81.11 162	80.18 201	88.96 206	83.39 184	76.07 166	81.27 166	69.35 154	58.66 193	51.19 224	82.01 170	87.16 175	84.39 214	95.66 205	92.82 212

PatchT		79.28 181	83.88 152	73.93 222	85.54 172	90.95 179	66.14 259	56.53 260	83.21 152	56.28 202	56.50 201	76.80 110	80.50 178	92.77 101	89.32 149	98.57 50	97.59 125

ACMH	78.51 14	79.27 182	78.08 191	80.65 164	89.52 109	90.40 182	80.45 221	79.77 133	69.54 212	54.85 213	64.83 170	56.16 213	83.94 158	84.58 198	86.01 193	95.41 211	95.03 187
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 183	78.95 190	79.56 172	81.89 191	92.52 166	82.97 193	73.70 187	67.27 225	64.97 166	61.66 184	65.06 181	78.61 187	87.12 177	88.07 169	95.23 215	90.95 225

ACMH+	79.09 13	79.12 184	77.22 200	81.35 160	88.50 141	90.36 183	82.14 208	79.38 142	72.78 197	58.59 187	62.31 183	56.44 212	84.10 155	82.03 224	84.05 215	95.40 212	92.55 213

usedtu_dtu_shiyan1		79.10 185	79.87 185	78.20 188	71.16 249	90.83 180	84.41 177	78.54 147	81.24 167	58.78 186	56.79 200	61.56 193	78.74 186	90.08 143	87.70 172	97.59 130	90.90 226

UniMVSNet_NR-MVSNet		78.89 186	78.04 193	79.88 170	79.40 207	89.70 191	82.92 195	80.17 128	76.37 190	58.56 188	57.10 199	54.92 216	81.44 174	83.51 209	87.12 180	96.76 161	97.60 123

tpm		78.87 187	81.33 181	76.00 207	85.57 171	90.19 186	82.81 199	59.66 251	78.35 182	51.40 227	66.30 161	67.92 162	80.94 176	83.28 213	85.73 194	95.65 206	97.56 127

GA-MVS		78.86 188	80.42 184	77.05 198	83.27 183	92.17 170	83.24 188	75.73 171	73.75 194	46.27 247	62.43 181	57.12 205	76.94 204	93.14 89	89.34 145	96.83 158	95.00 188

IterMVS		78.85 189	81.36 179	75.93 208	84.27 181	85.74 231	83.83 182	66.35 237	76.82 185	50.48 230	63.48 175	68.82 152	73.99 213	89.68 149	89.34 145	96.63 171	95.67 171
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 190	81.34 180	75.64 213	84.31 180	85.67 232	83.51 183	66.14 238	76.67 186	50.38 231	63.45 176	69.02 147	73.23 216	89.66 151	89.22 153	96.24 193	95.67 171

usedtu_blend_shiyan5		78.69 191	77.98 194	79.53 173	60.42 259	84.96 240	91.21 91	73.97 182	69.27 214	79.50 88	73.82 100	73.11 118	77.73 195	77.31 247	75.07 250	94.33 230	92.34 214

UniMVSNet (Re)		78.00 192	77.52 197	78.57 182	79.66 206	90.36 183	82.09 209	77.86 154	76.38 189	60.26 177	54.63 207	52.07 220	75.31 211	84.97 195	86.10 191	96.22 196	98.11 97

DU-MVS		77.98 193	76.71 202	79.46 174	78.68 217	89.26 200	82.92 195	79.06 144	76.52 187	58.56 188	54.89 205	48.35 238	81.44 174	83.16 215	87.21 179	96.08 201	97.60 123

FC-MVSNet-test		77.95 194	81.85 175	73.39 228	82.31 187	88.99 205	79.33 226	74.24 177	78.75 181	47.40 245	70.22 133	72.09 133	60.78 253	86.66 179	85.62 197	96.30 189	90.61 227

FE-MVSNET3		77.89 195	77.94 195	77.83 192	60.42 259	84.96 240	81.04 215	73.97 182	69.27 214	79.50 88	73.82 100	73.11 118	77.73 195	77.31 247	75.07 250	94.33 230	92.02 218

NR-MVSNet		77.21 196	76.41 203	78.14 189	80.18 201	89.26 200	83.38 185	79.06 144	76.52 187	56.59 199	54.89 205	45.32 248	72.89 218	85.39 191	86.12 190	96.71 166	97.36 133

thisisatest0515		77.13 197	79.36 187	74.52 215	79.79 205	89.65 192	73.54 244	73.69 188	74.10 193	58.14 191	62.79 180	60.57 195	66.49 236	88.08 166	85.16 207	95.49 210	95.15 183

gg-mvs-nofinetune		77.08 198	79.79 186	73.92 223	85.95 169	97.23 75	92.18 73	52.65 265	46.19 270	27.79 274	38.27 261	85.63 75	85.67 140	96.95 21	95.62 28	99.30 3	98.67 68

TranMVSNet+NR-MVSNet		77.02 199	75.76 205	78.49 183	78.46 223	88.24 213	83.03 192	79.97 129	73.49 196	54.73 214	54.00 210	48.74 233	78.15 192	82.36 221	86.90 182	96.59 173	96.55 152

CVMVSNet		76.86 200	79.09 189	74.26 218	85.29 176	89.44 197	79.91 225	78.47 149	68.94 221	44.45 255	62.35 182	69.70 143	64.50 242	85.82 187	87.03 181	92.94 249	90.33 228

Baseline_NR-MVSNet		76.71 201	74.56 212	79.23 176	78.68 217	84.15 248	82.45 202	78.87 146	75.83 191	60.05 178	47.92 241	50.18 230	79.06 185	83.16 215	83.86 218	96.26 191	96.80 148

v2v482		76.25 202	74.78 209	77.96 191	78.50 222	89.14 203	83.05 191	76.02 167	68.78 222	54.11 215	51.36 221	48.59 235	79.49 183	83.53 208	85.60 200	96.59 173	96.49 157

V42		76.21 203	75.04 208	77.58 193	78.68 217	89.33 199	82.93 194	74.64 175	69.84 209	56.13 206	50.42 226	50.93 225	76.30 210	83.32 211	84.89 211	96.83 158	96.54 153

v8		75.89 204	74.74 210	77.23 195	79.09 209	88.00 216	83.19 189	71.08 212	70.03 208	56.29 201	50.50 224	50.88 226	77.06 203	83.32 211	84.99 209	96.68 167	95.49 177

TinyColmap		75.75 205	73.19 223	78.74 181	84.82 177	87.69 220	81.59 212	74.62 176	71.81 203	54.01 216	55.79 204	44.42 254	82.89 165	84.61 197	83.76 219	94.50 225	84.22 253

MIMVSNet		75.71 206	77.26 198	73.90 224	70.93 250	88.71 209	79.98 224	57.67 259	73.58 195	58.08 194	53.93 211	58.56 203	79.41 184	90.04 144	89.97 135	97.34 143	86.04 243

UniMVSNet_ETH3D		75.63 207	71.59 237	80.35 166	81.03 196	89.90 189	83.25 187	76.58 162	60.08 247	64.19 171	42.89 256	45.01 250	82.14 169	80.20 234	86.75 186	94.90 220	96.29 159

pm-mvs1		75.61 208	74.19 214	77.26 194	80.16 203	88.79 207	81.49 213	75.49 174	59.49 249	58.09 193	48.32 237	55.53 214	72.35 219	88.61 160	85.48 201	95.99 202	93.12 209

v10		75.57 209	74.67 211	76.62 203	78.73 215	87.46 226	83.14 190	69.41 225	69.27 214	53.44 219	49.73 230	49.21 232	78.44 189	86.17 184	85.18 206	96.53 178	95.65 174

v1144		75.54 210	74.55 213	76.69 201	78.33 226	88.77 208	82.89 197	72.76 197	67.18 227	51.73 224	49.34 232	48.37 236	78.10 193	86.22 183	85.24 204	96.35 186	96.74 149

TDRefinement		75.54 210	73.22 221	78.25 187	87.65 159	89.65 192	85.81 170	79.28 143	71.14 205	56.06 208	52.17 219	51.96 222	68.74 232	81.60 225	80.58 233	91.94 252	85.45 244

pmmvs5		75.46 212	75.12 207	75.87 210	79.39 208	89.44 197	78.12 232	72.27 202	65.98 232	51.54 225	55.83 203	46.23 243	76.80 207	88.77 158	85.73 194	97.07 152	93.84 200

tfpnnormal		75.27 213	72.12 234	78.94 179	82.30 188	88.52 210	82.41 203	79.41 140	58.03 251	55.59 210	43.83 255	44.71 251	77.35 199	87.70 170	85.45 202	96.60 172	96.61 151

anonymousdsp		75.14 214	77.25 199	72.69 231	76.68 236	89.26 200	75.26 241	68.44 229	65.53 235	46.65 246	58.16 197	56.67 207	73.96 214	87.84 168	86.05 192	95.13 218	97.22 135

v148		74.98 215	73.52 219	76.69 201	78.84 212	89.02 204	78.78 228	76.82 159	67.22 226	59.61 179	49.18 233	47.94 240	70.57 225	80.76 229	83.99 216	95.52 208	96.52 155

v1192		74.96 216	73.92 215	76.17 204	77.76 229	88.19 215	82.54 201	71.94 205	66.84 228	50.07 234	48.10 239	46.14 244	78.28 190	86.30 181	85.23 205	96.41 185	96.67 150

v144192		74.76 217	73.64 216	76.06 206	77.58 230	88.23 214	81.87 210	71.63 207	66.03 231	51.08 228	48.63 236	46.77 242	77.59 198	84.53 199	84.76 212	96.64 170	96.54 153

v1921920		74.60 218	73.56 218	75.81 211	77.43 232	87.94 217	82.18 207	71.33 211	66.48 230	49.23 238	47.84 242	45.56 246	78.03 194	85.70 189	84.92 210	96.65 168	96.50 156

v1240		74.04 219	73.04 225	75.20 214	77.19 234	87.69 220	80.93 218	70.72 217	65.08 236	48.47 240	47.31 243	44.71 251	77.33 200	85.50 190	85.07 208	96.59 173	95.94 165

wanda-best-256-512		73.38 220	72.60 228	74.28 216	60.42 259	84.96 240	81.04 215	73.97 182	69.27 214	59.09 183	52.95 214	56.56 208	76.85 205	77.31 247	75.07 250	94.33 230	92.05 216

FE-blended-shiyan7		73.37 221	72.59 229	74.28 216	60.42 259	84.96 240	81.04 215	73.97 182	69.28 213	59.09 183	52.95 214	56.54 209	76.85 205	77.31 247	75.07 250	94.33 230	92.05 216

blended_shiyan8		73.25 222	72.48 230	74.14 220	60.35 263	84.93 244	80.84 219	73.55 191	69.25 218	59.22 182	52.62 217	56.47 211	76.66 208	77.19 252	74.92 255	94.23 234	91.94 220

blended_shiyan6		73.22 223	72.48 230	74.09 221	60.31 264	84.90 245	80.80 220	73.54 192	69.06 220	59.06 185	52.69 216	56.53 210	76.59 209	77.20 251	74.94 254	94.22 235	92.02 218

testgi		73.22 223	75.84 204	70.16 242	81.67 195	85.50 235	71.45 246	70.81 215	69.56 211	44.74 254	74.52 96	49.25 231	58.45 254	84.10 202	83.37 223	93.86 237	84.56 251

gbinet_0.2-2-1-0.02		73.19 225	72.88 226	73.56 226	60.07 265	84.50 247	80.22 223	73.59 190	67.33 224	59.36 181	52.21 218	58.21 204	73.76 215	77.60 244	75.19 248	94.37 227	95.12 184

CP-MVSNet		73.19 225	72.37 232	74.15 219	77.54 231	86.77 229	76.34 235	72.05 203	65.66 234	51.47 226	50.49 225	43.66 255	70.90 221	80.93 228	83.40 222	96.59 173	95.66 173

WR-MVS		72.93 227	73.57 217	72.19 234	78.14 227	87.71 219	76.21 237	73.02 195	67.78 223	50.09 233	50.35 227	50.53 228	61.27 252	80.42 232	83.10 226	94.43 226	95.11 185

TransMVSNet (Re)		72.90 228	70.51 241	75.69 212	80.88 197	85.26 238	79.25 227	78.43 151	56.13 258	52.81 221	46.81 245	48.20 239	66.77 235	85.18 194	83.70 220	95.98 203	88.28 237

WR-MVS_H		72.69 229	72.80 227	72.56 233	77.94 228	87.83 218	75.26 241	71.53 209	64.75 237	52.19 223	49.83 228	48.62 234	61.96 250	81.12 227	82.44 228	96.50 179	95.00 188

SixPastTwentyTwo		72.65 230	73.22 221	71.98 237	78.40 224	87.64 222	70.09 249	70.37 219	66.49 229	47.60 243	65.09 167	45.94 245	73.09 217	78.94 236	78.66 240	92.33 250	89.82 232

LTVRE_ROB	71.82 16	72.62 231	71.77 235	73.62 225	80.74 198	87.59 223	80.42 222	70.37 219	49.73 263	37.12 267	59.76 188	42.52 260	80.92 177	83.20 214	85.61 199	92.13 251	93.95 198
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
PS-CasMVS		72.37 232	71.47 239	73.43 227	77.32 233	86.43 230	75.99 238	71.94 205	63.37 240	49.24 237	49.07 234	42.42 261	69.60 227	80.59 231	83.18 225	96.48 182	95.23 181

MVS-HIRNet		72.32 233	73.45 220	71.00 240	80.58 199	89.97 187	68.51 254	55.28 263	70.89 206	52.27 222	39.09 259	57.11 206	75.02 212	85.76 188	86.33 187	94.36 229	85.00 248

PEN-MVS		72.24 234	71.30 240	73.33 229	77.08 235	85.57 233	76.75 233	72.52 200	63.89 239	48.12 241	50.79 222	43.09 258	69.03 231	78.54 238	83.46 221	96.50 179	93.76 203

v7n		72.11 235	71.66 236	72.63 232	75.26 242	86.85 227	76.74 234	68.77 228	62.70 243	49.40 235	45.92 247	43.51 256	70.63 224	84.16 201	83.21 224	94.99 219	95.25 179

EG-PatchMatch MVS		71.81 236	71.54 238	72.12 235	80.53 200	89.94 188	78.51 229	66.56 236	57.38 253	47.46 244	44.28 254	52.22 219	63.10 247	85.22 193	84.42 213	96.56 177	87.35 241

CMPMVS	54.54 17	71.74 237	67.94 246	76.16 205	90.41 94	93.25 152	78.32 231	75.60 173	59.81 248	53.95 217	44.64 251	51.22 223	70.70 222	74.59 257	75.88 247	88.01 260	76.23 262
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 238	73.08 224	69.97 243	75.22 243	86.81 228	73.98 243	59.61 252	69.75 210	48.01 242	54.21 209	53.06 218	69.19 229	78.50 239	80.43 234	93.84 238	88.79 235

pmnet_mix02		71.64 239	72.36 233	70.81 241	78.39 225	85.57 233	68.64 252	73.65 189	72.13 199	45.07 253	56.01 202	50.61 227	65.34 239	76.21 253	76.60 245	93.75 241	89.35 233

gm-plane-assit		71.33 240	75.18 206	66.83 247	79.06 211	75.57 263	48.05 272	60.33 247	48.28 264	34.67 271	44.34 253	67.70 164	79.78 182	97.25 13	96.21 15	99.10 11	96.92 143

DTE-MVSNet		71.19 241	70.45 242	72.06 236	76.61 237	84.59 246	75.61 240	72.32 201	63.12 242	45.70 251	50.72 223	43.02 259	65.89 237	77.53 246	82.23 229	96.26 191	91.93 221

pmmvs6		70.29 242	67.90 247	73.07 230	76.17 239	85.31 236	76.29 236	70.75 216	47.39 266	55.33 211	37.15 265	50.49 229	69.55 228	82.96 217	80.85 232	90.34 259	91.18 224

PM-MVS		70.17 243	69.42 244	71.04 239	70.82 251	81.26 257	71.25 247	67.80 232	69.16 219	51.04 229	53.15 213	34.93 268	72.19 220	80.30 233	76.95 244	93.16 248	90.21 229

pmmvs-eth3d		69.59 244	67.57 249	71.95 238	70.04 253	80.05 258	71.48 245	70.00 223	62.57 244	55.99 209	44.92 249	35.73 266	70.64 223	81.56 226	79.69 235	93.55 242	88.43 236

N_pmnet		68.54 245	67.83 248	69.38 244	75.77 240	81.90 254	66.21 258	72.53 199	65.91 233	46.09 248	44.67 250	45.48 247	63.82 245	74.66 256	77.39 243	91.87 254	84.77 250

Anonymous20231206		68.09 246	68.68 245	67.39 246	75.16 244	82.55 249	69.33 251	70.06 222	63.34 241	42.28 258	37.91 263	43.12 257	52.67 257	83.56 207	82.71 227	94.84 222	87.59 239

EU-MVSNet		68.07 247	70.25 243	65.52 249	74.68 246	81.30 256	68.53 253	70.31 221	62.40 246	37.43 266	54.62 208	48.36 237	51.34 259	78.32 240	79.27 237	90.84 256	87.47 240

dtuonlycased		66.81 248	65.49 252	68.34 245	70.60 252	82.21 252	66.95 256	68.30 231	62.57 244	48.64 239	46.62 246	53.65 217	64.78 241	62.62 262	65.70 263	90.79 257	85.07 246

FE-MVSNET2		65.87 249	65.40 253	66.41 248	56.18 268	82.03 253	69.83 250	68.97 226	56.64 256	45.42 252	31.48 268	37.87 264	62.52 249	82.96 217	81.55 231	95.56 207	85.28 245

GG-mvs-BLEND		65.67 250	93.78 44	32.89 265	0.47 281	99.35 11	96.92 37	0.22 278	93.28 66	0.51 283	84.07 60	92.50 44	0.62 280	93.59 80	93.86 65	98.59 49	99.79 11

test20.03		65.17 251	67.41 250	62.55 251	75.35 241	79.31 259	62.22 261	68.83 227	56.50 257	35.35 270	51.97 220	44.70 253	40.01 265	80.69 230	79.25 238	93.55 242	79.47 261

MDA-MVSNet-bldmvs		62.23 252	61.13 257	63.52 250	58.94 266	82.44 250	60.71 265	73.28 194	57.22 254	38.42 264	49.63 231	27.64 276	62.83 248	54.98 266	74.16 256	86.96 262	81.83 258

new_pmnet		61.60 253	62.68 254	60.35 254	63.02 256	74.93 264	60.97 264	58.86 254	64.21 238	35.38 269	39.51 258	39.89 262	57.37 255	72.78 258	72.56 258	86.49 264	74.85 264

FE-MVSNET		61.22 254	62.61 255	59.59 256	48.81 270	75.79 262	61.96 262	67.51 233	52.39 261	34.04 272	33.16 267	37.64 265	52.00 258	77.89 242	79.39 236	93.22 246	82.04 257

new-patchmatchnet		60.74 255	59.78 259	61.87 252	69.52 254	76.67 261	57.99 268	65.78 240	52.63 260	38.47 263	38.08 262	32.92 271	48.88 262	68.50 259	69.87 259	90.56 258	79.75 260

pmmvs3		60.52 256	60.87 258	60.12 255	61.38 257	71.62 266	57.42 269	53.94 264	48.09 265	35.95 268	38.62 260	32.19 274	64.12 243	75.33 254	77.99 241	87.89 261	82.28 256

MIMVSNet1		60.51 257	61.43 256	59.44 257	48.75 271	77.21 260	60.98 263	66.84 235	52.09 262	38.74 262	29.29 270	39.40 263	48.08 263	77.60 244	78.87 239	93.22 246	75.56 263

test_method		60.40 258	66.30 251	53.52 260	37.48 276	64.10 270	55.56 270	42.45 270	71.79 204	41.87 259	33.74 266	46.80 241	61.71 251	79.18 235	73.33 257	82.01 267	95.17 182

FPMVS		56.54 259	52.82 262	60.87 253	74.90 245	67.58 269	67.69 255	65.38 241	57.86 252	41.51 260	37.83 264	34.19 269	41.21 264	55.88 265	53.09 267	74.55 270	63.31 268

usedtu_dtu_shiyan2		56.32 260	55.74 261	57.01 259	40.29 275	72.50 265	63.80 260	57.88 258	37.70 271	45.71 250	25.31 272	35.59 267	49.97 261	67.09 260	67.03 261	84.41 265	84.92 249

WB-MVS		47.20 261	51.37 263	42.35 263	71.55 248	57.66 272	32.77 276	70.86 214	47.39 266	6.95 280	48.14 238	32.52 272	12.95 276	61.73 264	61.27 264	59.00 274	50.85 274

PMVS	42.57 18	45.71 262	42.61 265	49.32 261	61.35 258	37.82 275	36.96 274	60.10 249	37.20 272	41.50 261	28.53 271	33.11 270	28.82 270	53.45 267	48.70 269	67.22 272	59.42 269
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 263	42.62 264	45.50 262	50.79 269	41.20 274	35.55 275	52.51 266	52.95 259	29.09 273	12.92 275	11.48 281	38.15 266	62.01 263	66.62 262	66.89 273	51.17 272
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 264	42.55 266	39.74 264	43.25 272	55.05 273	38.15 273	47.11 269	31.78 273	11.83 276	21.16 273	19.12 279	20.98 272	49.95 269	56.09 266	77.09 268	64.68 266

E-PMN		27.87 265	24.36 271	31.97 266	41.27 274	25.56 278	16.62 278	49.16 267	22.00 275	9.90 277	11.75 277	7.86 284	29.57 269	22.22 274	34.70 270	45.27 275	46.41 275

MVE	32.98 19	27.61 266	29.89 270	24.94 268	21.97 277	37.22 276	15.56 280	38.83 271	17.49 276	14.72 275	11.64 279	5.62 285	21.26 271	35.20 270	50.95 268	37.29 277	51.13 273
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS		27.53 267	41.28 267	11.50 269	6.16 278	13.25 281	11.93 282	0.81 275	58.16 250	7.91 279	73.32 107	31.49 275	15.94 275	29.06 272	26.73 273	26.23 278	56.94 270

EMVS		26.96 268	22.96 272	31.63 267	41.91 273	25.73 277	16.30 279	49.10 268	22.38 274	9.03 278	11.22 280	8.12 283	29.93 268	20.16 275	31.04 271	43.49 276	42.04 276

VLMVS_CLIP		25.63 269	39.16 268	9.86 270	6.13 279	13.35 279	12.42 281	0.89 274	46.24 269	1.87 281	64.55 174	24.38 278	16.52 274	32.19 271	29.70 272	21.31 279	63.70 267

MVS_clip		22.46 270	34.64 269	8.26 271	5.07 280	13.31 280	7.37 283	0.95 273	47.19 268	1.65 282	47.15 244	26.70 277	20.25 273	27.61 273	26.13 274	14.24 280	54.41 271

MVS_baseline		6.53 271	11.27 273	1.00 274	0.34 283	0.92 284	0.21 286	0.00 279	13.24 277	0.00 286	17.44 274	9.02 282	5.33 277	9.00 276	7.38 275	0.10 283	21.89 279

testmvs		5.16 272	8.14 274	1.69 272	0.36 282	1.65 282	3.02 284	0.66 276	7.17 278	0.50 284	12.58 276	0.69 286	4.67 278	5.42 277	5.65 276	0.92 281	23.86 278

test123		4.39 273	7.11 275	1.21 273	0.11 284	1.16 283	1.67 285	0.35 277	5.91 279	0.16 285	11.65 278	0.16 287	4.45 279	1.72 278	4.92 277	0.51 282	24.28 277

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

ACM-MVS					99.13 3	99.41 10	99.12 3		97.72 15	80.64 75	91.95 38	96.34 27	97.61 5			98.47 57	98.31 90

PatchmatchNet2					76.30 238	82.30 251	66.57 257
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												45.23 249	63.86 244	74.74 255	77.59 242	91.88 253	84.46 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										45.84 249	44.44 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.29 16	95.80 1		98.47 1						99.17 7

TPM-MVS					99.19 1	99.43 9	99.16 2			85.97 37	94.75 29	97.40 16	97.76 2			98.95 28	95.69 168
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										43.17 256

9.14												97.59 13

SR-MVS					98.52 24			93.70 26				96.63 24

Anonymous202405211			81.72 176		88.09 151	94.27 143	89.62 128	82.14 111	82.27 157		48.83 235	72.58 128	91.08 70	87.40 173	88.70 162	94.90 220	97.99 104

our_test_3					78.55 220	84.98 239	70.12 248

ambc			57.08 260		58.68 267	67.71 268	60.07 266		57.13 255	42.79 257	30.00 269	11.64 280	50.18 260	78.89 237	69.14 260	82.64 266	85.02 247

MTAPA										93.37 12		95.71 32

MTMP										93.84 9		94.86 35

Patchmatch-RL test							19.65 277

tmp_tt				57.89 258	79.94 204	59.29 271	52.84 271	36.65 272	94.77 56	68.22 157	72.96 111	65.62 179	33.65 267	66.20 261	58.02 265	76.06 269

XVS					92.16 75	98.56 39	91.04 97			81.00 72		93.49 39				98.00 102

X-MVStestdata					92.16 75	98.56 39	91.04 97			81.00 72		93.49 39				98.00 102

mPP-MVS					97.95 33							92.24 49

NP-MVS									94.12 60

Patchmtry						92.08 173	83.86 180	58.37 256		56.28 202

DeepMVS_CX						70.68 267	59.61 267	67.36 234	72.12 200	38.41 265	53.88 212	32.44 273	55.15 256	50.88 268		74.35 271	68.42 265

High-resolution multi-view benchmark