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.

MED-MVS		98.08 1	98.22 3	97.91 1	98.97 9	99.41 8	98.93 5	95.37 5	98.80 1	98.12 2	98.11 1	99.53 4	97.16 6	96.58 24	95.40 31	98.93 29	99.68 16

ME-MVS		98.02 2	98.12 5	97.91 1	98.97 9	99.32 14	98.29 14	95.80 1	98.28 5	98.12 2	98.11 1	99.40 5	97.13 7	96.54 25	95.50 27	99.17 7	99.68 16

SED-MVS		97.92 3	98.27 2	97.52 3	98.88 14	99.60 1	98.80 6	95.08 10	98.57 3	95.63 5	96.98 11	99.73 1	97.67 2	97.26 12	95.86 23	99.04 16	99.89 5

MSP-MVS		97.74 4	98.32 1	97.06 9	98.66 17	99.35 9	98.66 9	94.75 16	98.22 7	93.60 9	97.99 3	98.58 10	97.41 5	98.24 2	95.95 19	99.27 4	99.91 1
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 5	98.01 8	97.37 4	98.98 6	99.58 3	98.79 7	95.06 11	98.24 6	94.66 6	96.35 17	99.20 6	97.63 3	97.20 14	95.68 24	99.08 14	99.84 7

DPE-MVS		97.69 6	98.16 4	97.14 7	99.01 5	99.52 5	99.12 3	95.38 4	98.00 10	93.31 12	97.71 4	99.61 3	96.94 8	96.99 18	95.45 29	99.09 13	99.81 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		97.61 7	97.87 9	97.30 5	98.94 13	99.60 1	98.21 16	95.11 7	98.39 4	95.83 4	94.40 32	99.70 2	96.79 9	97.16 15	95.95 19	98.92 30	99.90 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
CNVR-MVS		97.60 8	98.08 6	97.03 10	99.14 2	99.55 4	98.67 8	95.32 6	97.91 11	92.55 14	97.11 8	97.23 16	97.49 4	98.16 3	97.05 6	99.04 16	99.55 22

APDe-MVS		97.31 9	97.51 14	97.08 8	98.95 12	99.29 16	98.58 11	95.11 7	97.69 16	94.16 7	96.91 12	96.81 20	96.57 12	96.71 21	95.39 32	99.08 14	99.79 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.17 10	97.18 18	97.17 6	99.11 3	99.20 18	99.05 4	95.55 3	97.39 20	93.56 10	97.48 6	96.71 22	96.75 10	95.73 35	94.40 49	98.98 23	99.33 27

NCCC		97.01 11	97.74 10	96.16 13	99.02 4	99.35 9	98.63 10	95.04 12	97.84 13	88.95 27	96.83 14	97.02 19	96.39 17	97.44 7	96.51 10	98.90 32	99.16 44

SMA-MVS		96.96 12	97.65 13	96.15 14	98.98 6	99.31 15	97.91 21	94.68 18	97.52 18	90.59 21	94.54 31	99.20 6	96.54 14	97.29 10	96.48 11	98.22 75	99.19 39
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 13	98.07 7	95.61 20	98.98 6	99.44 6	98.04 17	95.04 12	98.10 8	86.55 34	97.65 5	97.56 13	95.60 26	97.67 6	96.45 12	99.43 1	99.61 21

HPM-MVS++		96.91 14	97.70 11	96.00 15	98.97 9	99.16 20	97.82 23	94.81 15	98.04 9	89.61 24	96.56 16	98.60 9	96.39 17	97.09 16	95.22 34	98.39 65	99.22 35

SD-MVS		96.87 15	97.69 12	95.92 16	96.38 50	99.25 17	97.76 24	94.75 16	97.72 14	92.46 16	95.94 18	99.09 8	96.48 16	96.01 32	96.08 17	97.68 117	99.73 13
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 16	96.99 21	96.56 11	98.76 16	98.87 29	98.42 12	94.93 14	97.70 15	91.83 17	95.52 21	95.94 28	96.63 11	95.94 33	95.47 28	98.80 38	99.47 25
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		96.50 17	97.08 19	95.82 18	96.12 54	98.97 26	98.00 18	94.13 23	97.89 12	91.49 18	95.11 27	97.52 14	96.26 21	96.27 30	94.07 59	98.91 31	99.74 12
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 18	97.22 17	95.01 24	98.40 24	99.11 21	97.93 20	93.62 26	96.28 33	87.45 31	97.05 10	96.00 27	94.23 34	96.83 20	95.97 18	98.40 62	99.27 32
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 19	96.41 26	95.72 19	98.58 19	98.84 30	97.95 19	93.08 30	96.96 26	90.24 22	96.60 15	94.40 34	96.52 15	95.13 45	94.33 50	97.93 107	98.59 72

ACMMP_NAP		95.81 20	96.50 25	95.01 24	98.79 15	99.17 19	97.52 29	94.20 22	96.19 34	85.71 39	93.80 35	96.20 26	95.89 23	96.62 23	94.98 40	97.93 107	98.52 76

MGCNet		95.79 21	97.46 15	93.85 30	96.81 44	99.35 9	97.21 32	87.28 51	97.10 21	88.65 30	95.17 26	96.41 25	94.15 38	97.29 10	97.19 5	99.01 21	99.73 13

train_agg		95.72 22	97.37 16	93.80 31	97.82 33	98.92 27	97.84 22	93.50 27	96.86 28	81.35 61	97.10 9	97.71 11	94.19 35	96.02 31	95.37 33	98.07 91	99.64 19

ACMMPR		95.59 23	95.89 28	95.25 22	98.41 23	98.74 31	97.69 27	92.73 34	96.88 27	88.95 27	95.33 23	92.91 41	95.79 24	94.73 55	94.33 50	97.92 109	98.32 88

DeepC-MVS_fast	91.53 1	95.57 24	95.67 31	95.45 21	98.57 20	99.00 25	97.76 24	94.41 20	97.06 23	86.84 33	86.39 49	92.27 46	96.38 19	97.89 5	98.06 3	98.73 43	99.01 53
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 25	94.84 36	96.25 12	98.64 18	98.63 34	98.35 13	92.37 36	95.04 52	92.62 13	87.12 47	93.79 35	96.55 13	93.53 80	96.78 7	98.98 23	98.99 54

CP-MVS		95.43 26	95.67 31	95.14 23	98.24 29	98.60 35	97.45 30	92.80 32	95.98 37	89.21 26	95.22 24	93.60 36	95.43 27	94.37 62	93.22 89	97.68 117	98.72 62

DPM-MVS		95.36 27	95.84 29	94.82 26	96.70 46	98.49 45	99.27 1	95.09 9	96.71 29	83.87 47	86.34 51	96.44 24	95.06 29	98.35 1	98.82 1	98.89 33	95.69 166

MP-MVS		95.24 28	95.96 27	94.40 28	98.32 26	98.38 50	97.12 33	92.87 31	95.17 50	85.50 40	95.68 19	94.91 32	94.58 31	95.11 46	93.76 67	98.05 94	98.68 64
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 29	97.02 20	92.61 41	97.19 39	98.71 33	97.74 26	93.21 29	96.97 25	79.27 97	94.09 33	97.14 17	90.84 72	96.64 22	95.94 21	97.42 138	99.67 18

X-MVS		94.70 30	95.71 30	93.52 35	98.38 25	98.56 37	96.99 34	92.62 35	95.58 41	81.00 71	94.57 30	93.49 37	94.16 37	94.82 51	94.29 53	97.99 102	98.68 64

PGM-MVS		94.64 31	95.49 33	93.66 33	98.55 21	98.51 43	97.63 28	87.77 49	94.45 56	84.92 43	97.23 7	91.90 48	95.22 28	94.56 58	93.80 66	97.87 113	97.97 106

TSAR-MVS + GP.		94.59 32	96.60 24	92.25 42	90.25 96	98.17 57	96.22 39	86.53 56	97.49 19	87.26 32	95.21 25	97.06 18	94.07 40	94.34 64	94.20 55	99.18 5	99.71 15

PHI-MVS		94.49 33	96.72 23	91.88 44	97.06 40	98.88 28	94.99 51	89.13 44	96.15 35	79.70 84	96.91 12	95.78 29	91.87 61	94.65 56	95.68 24	98.53 53	98.98 56

AdaColmap		94.28 34	92.94 49	95.84 17	98.32 26	98.33 52	96.06 41	94.62 19	96.29 32	91.22 19	89.89 41	85.50 76	96.38 19	91.85 115	90.89 117	98.44 58	97.81 113

DeepPCF-MVS	91.00 2	94.15 35	96.87 22	90.97 53	96.82 43	99.33 13	89.40 134	92.76 33	98.76 2	82.36 54	88.74 42	95.49 31	90.58 80	98.13 4	97.80 4	93.88 234	99.88 6

CPTT-MVS		94.11 36	93.99 42	94.25 29	96.58 47	97.66 66	97.31 31	91.94 37	94.84 53	88.72 29	92.51 36	93.04 40	95.78 25	91.51 121	89.97 134	95.15 215	98.37 85

EPNet		93.69 37	95.34 34	91.76 45	96.98 42	98.47 47	95.40 47	86.79 53	95.47 43	82.84 51	95.66 20	89.17 54	90.47 83	95.25 44	94.69 44	98.10 86	98.68 64
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 38	93.59 45	93.00 39	97.03 41	98.24 53	95.27 49	91.66 40	95.20 48	83.25 49	95.39 22	85.52 74	92.80 52	92.60 104	90.21 130	98.01 99	97.99 102
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 39	93.72 44	92.65 40	95.48 57	99.09 23	96.55 37	86.74 54	95.28 46	85.22 41	77.30 79	91.25 50	92.60 54	97.06 17	96.63 9	99.31 2	99.45 26

CDPH-MVS		93.22 40	95.08 35	91.04 51	97.57 36	98.49 45	96.74 36	89.35 43	95.19 49	73.57 137	90.26 39	91.59 49	90.68 77	95.09 48	96.15 15	98.31 73	98.81 60

CSCG		93.16 41	92.65 50	93.76 32	98.32 26	99.09 23	96.12 40	89.91 42	93.15 65	89.64 23	83.62 59	88.91 56	92.40 56	91.09 128	93.70 68	96.14 196	98.99 54

MVS_111021_LR		93.05 42	94.53 38	91.32 49	96.43 49	98.38 50	92.81 66	87.20 52	95.94 39	81.45 60	94.75 28	86.08 70	92.12 59	94.83 50	93.34 83	97.89 112	98.42 83

3Dnovator+	86.26 7	92.90 43	92.45 52	93.42 36	97.25 38	98.45 49	95.82 42	85.71 62	93.83 60	89.55 25	72.31 116	92.28 45	94.01 42	95.10 47	95.92 22	98.17 82	99.23 34

MVSMamba_PlusPlus		92.73 44	94.19 40	91.03 52	89.86 100	98.16 58	95.33 48	85.38 66	97.56 17	80.47 74	86.68 48	84.99 81	96.11 22	97.37 8	96.77 8	99.04 16	97.76 115

MVS_111021_HR		92.73 44	94.83 37	90.28 58	96.27 51	99.10 22	92.77 67	86.15 59	93.41 63	77.11 124	93.82 34	87.39 62	90.61 78	95.60 37	95.15 36	98.79 39	99.32 28

PLC	89.12 3	92.67 46	90.84 62	94.81 27	97.69 34	96.10 112	95.42 46	91.70 38	95.82 40	92.52 15	81.24 65	86.01 71	94.36 32	92.44 108	90.27 127	97.19 147	93.99 195
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 47	91.96 54	93.20 37	97.99 30	98.47 47	95.78 43	85.94 60	93.07 66	86.40 35	73.43 103	89.00 55	94.08 39	94.74 54	96.44 13	99.01 21	98.57 73

DeepC-MVS	88.77 4	92.39 48	91.74 56	93.14 38	96.21 52	98.55 40	96.30 38	93.84 24	93.06 67	81.09 68	74.69 93	85.20 80	93.48 46	95.41 40	96.13 16	97.92 109	99.18 40
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 49	91.88 55	92.25 42	96.51 48	97.94 60	93.18 63	88.97 46	96.53 30	84.47 45	80.79 67	87.85 58	93.25 50	92.48 107	91.81 110	97.12 149	95.73 165

MVSTER		91.91 50	93.43 48	90.14 59	89.81 104	92.32 166	94.53 54	81.32 119	96.00 36	84.77 44	85.41 56	92.39 44	91.32 64	96.41 26	94.01 62	99.11 10	97.45 127

SPE-MVS-test		91.76 51	93.47 46	89.76 62	94.64 62	98.22 55	88.13 145	81.58 116	97.02 24	82.47 53	85.49 55	85.41 78	93.28 48	95.33 42	93.61 75	98.45 57	99.22 35

QAPM		91.68 52	91.97 53	91.34 48	97.86 32	98.72 32	95.60 45	85.72 61	90.86 85	77.14 123	76.06 82	90.35 51	92.69 53	94.10 68	94.60 46	99.04 16	99.09 47

CS-MVS		91.55 53	92.49 51	90.45 57	94.00 65	97.91 62	91.17 90	81.40 118	95.22 47	83.51 48	82.37 63	82.29 87	94.07 40	96.36 29	94.03 60	98.56 50	99.22 35

CNLPA		91.53 54	89.74 75	93.63 34	96.75 45	97.63 68	91.16 92	91.70 38	96.38 31	90.82 20	69.66 135	85.52 74	93.76 43	90.44 135	91.14 116	97.55 130	97.40 128

ETV-MVS		91.51 55	94.06 41	88.54 79	89.39 110	97.52 69	89.48 129	80.88 124	97.09 22	79.41 92	87.87 43	86.18 69	92.95 51	95.94 33	94.33 50	99.13 9	99.52 24

EC-MVSNet		91.25 56	93.45 47	88.68 76	88.90 120	96.18 109	91.66 76	76.70 159	95.57 42	82.00 57	84.18 57	89.28 53	94.17 36	95.64 36	94.19 56	98.68 45	99.14 45

DELS-MVS		91.09 57	90.56 70	91.71 46	95.82 55	98.59 36	95.74 44	86.68 55	85.86 123	85.12 42	72.71 110	81.36 90	88.06 125	97.31 9	98.27 2	98.86 36	99.82 8
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 58	90.71 64	91.30 50	96.14 53	97.66 66	94.80 52	89.00 45	94.74 55	77.42 120	80.22 68	86.70 65	92.27 57	91.65 120	90.17 132	98.15 85	93.83 199
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 59	90.66 66	90.82 55	94.75 60	98.54 41	91.30 85	86.53 56	95.43 44	85.75 37	78.66 74	70.67 135	87.60 127	96.37 27	95.08 38	98.98 23	99.90 2

PVSNet_Blended		90.74 59	90.66 66	90.82 55	94.75 60	98.54 41	91.30 85	86.53 56	95.43 44	85.75 37	78.66 74	70.67 135	87.60 127	96.37 27	95.08 38	98.98 23	99.90 2

CHOSEN 280x420		90.61 61	94.27 39	86.35 118	93.12 70	98.16 58	89.99 122	69.62 223	92.48 71	76.89 128	87.28 46	96.72 21	90.31 86	94.81 52	92.33 103	98.17 82	98.08 99

MAR-MVS		90.44 62	91.17 60	89.59 63	97.48 37	97.92 61	90.96 99	79.80 130	95.07 51	77.03 125	80.83 66	79.10 100	94.68 30	93.16 87	94.46 48	97.59 128	97.63 120
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 63	89.56 81	91.41 47	94.44 63	98.18 56	94.35 55	94.33 21	84.55 140	76.61 129	75.84 85	88.47 57	91.29 65	90.37 138	90.66 123	97.46 134	98.88 59
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
OpenMVS	83.41 11	89.84 64	88.89 87	90.95 54	97.63 35	98.51 43	94.64 53	85.47 65	88.14 106	78.39 111	65.06 165	85.42 77	91.04 69	93.06 90	93.70 68	98.53 53	98.37 85

EIA-MVS		89.82 65	91.48 58	87.89 102	89.16 112	97.31 71	88.99 136	80.92 123	94.29 57	77.65 118	82.16 64	79.77 98	91.90 60	94.61 57	93.03 94	98.70 44	99.21 38

sasdasda		89.62 66	89.87 73	89.33 65	90.47 89	97.02 77	93.46 60	79.67 133	92.45 72	81.05 69	82.84 60	73.00 122	93.71 44	90.38 136	94.85 41	97.65 122	98.54 74

canonicalmvs		89.62 66	89.87 73	89.33 65	90.47 89	97.02 77	93.46 60	79.67 133	92.45 72	81.05 69	82.84 60	73.00 122	93.71 44	90.38 136	94.85 41	97.65 122	98.54 74

TSAR-MVS + COLMAP		89.59 68	89.64 78	89.53 64	93.32 69	96.51 93	95.03 50	88.53 47	95.98 37	69.10 153	91.81 37	64.53 182	93.40 47	93.53 80	91.35 115	97.77 114	93.75 202

HQP-MVS		89.57 69	90.57 69	88.41 83	92.77 71	94.71 136	94.24 56	87.97 48	93.44 62	68.18 156	91.75 38	71.54 134	89.90 98	92.31 111	91.43 113	97.39 139	98.80 61

MGCFI-Net		89.36 70	89.66 77	89.02 71	90.40 93	96.92 80	93.26 62	79.54 137	92.10 75	80.11 78	82.55 62	72.65 125	93.26 49	90.24 140	94.69 44	97.53 132	98.46 81

MVS_Test		89.02 71	90.20 71	87.64 105	89.83 103	97.05 76	92.30 70	77.59 155	92.89 68	75.01 134	77.36 78	76.10 110	92.27 57	95.30 43	95.42 30	98.83 37	97.30 132

CLD-MVS		88.99 72	88.07 90	90.07 60	89.61 106	94.94 133	93.82 59	85.70 63	92.73 70	82.73 52	79.97 69	69.59 142	90.44 84	90.32 139	89.93 136	98.10 86	99.04 50
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 73	89.94 72	87.70 104	89.44 109	96.74 85	91.62 78	77.92 152	93.79 61	78.76 102	77.55 77	78.46 103	89.38 108	92.26 112	92.52 100	99.10 11	98.23 90

PMMVS		88.56 74	91.22 59	85.47 131	90.04 98	95.60 128	86.62 161	78.49 147	93.86 59	70.62 148	90.00 40	80.08 96	91.64 62	92.36 109	89.80 140	95.40 210	96.84 144

test2506		88.38 75	88.02 92	88.80 75	91.55 80	97.78 63	90.87 102	83.36 78	84.51 141	83.06 50	74.13 96	76.93 107	85.39 139	94.34 64	93.33 85	98.60 46	95.10 184

E2		88.25 76	87.54 98	89.08 69	88.94 118	96.72 86	90.74 104	83.41 76	86.83 118	82.08 56	72.76 109	70.33 137	90.81 73	93.83 74	94.01 62	98.48 55	98.29 89

Casviewmamba		88.16 77	87.37 100	89.09 68	89.09 114	96.34 100	90.93 101	83.41 76	89.70 93	82.13 55	70.03 133	70.14 139	91.34 63	94.28 67	93.39 81	97.66 120	97.68 118

baseline1		88.16 77	88.15 89	88.17 90	90.02 99	94.79 135	91.85 75	83.89 69	87.37 112	75.67 132	73.75 101	79.89 97	88.44 124	94.41 59	93.33 85	99.18 5	93.55 204

thisisatest0530		87.99 79	90.76 63	84.75 135	88.36 144	96.82 82	87.65 150	79.67 133	91.77 77	70.93 144	79.94 70	87.65 60	84.21 150	92.98 93	89.07 153	97.66 120	97.13 137

tttt0517		87.93 80	90.71 64	84.68 136	88.33 145	96.76 84	87.42 154	79.67 133	91.74 78	70.83 145	79.91 71	87.61 61	84.21 150	92.88 98	89.07 153	97.62 126	97.03 139

CANet_DTU		87.91 81	91.57 57	83.64 143	90.96 83	97.12 74	91.90 74	75.97 167	92.83 69	53.16 218	86.02 52	79.02 101	90.80 74	95.40 41	94.15 57	99.03 20	96.47 156

diffmvs		87.86 82	87.40 99	88.39 84	88.57 134	96.10 112	91.24 87	83.15 89	90.62 87	79.13 99	72.45 114	67.71 161	90.07 93	92.58 105	93.31 88	98.17 82	99.03 51
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 83	90.66 66	84.53 137	90.08 97	96.79 83	88.16 144	79.89 129	85.44 125	72.20 139	75.50 89	87.14 63	80.21 178	95.53 38	95.22 34	96.65 166	99.02 52

viewcassd2359sk11		87.73 84	86.79 109	88.83 74	88.87 122	96.64 87	90.66 107	83.33 83	85.05 134	81.22 66	70.85 125	69.54 143	90.50 82	93.40 84	93.86 64	98.40 62	98.21 91

EPP-MVSNet		87.72 85	89.74 75	85.37 132	89.11 113	95.57 129	86.31 164	79.44 138	85.83 124	75.73 131	77.23 80	90.05 52	84.78 146	91.22 126	90.25 128	96.83 156	98.04 100

hybridnocas07		87.67 86	87.10 104	88.33 85	88.75 124	96.06 118	90.46 111	83.08 95	91.52 84	80.08 79	73.23 105	68.53 151	89.58 105	89.30 153	92.59 99	98.05 94	98.47 80

hybridcas		87.66 87	86.50 115	89.01 72	88.92 119	96.24 107	91.23 88	83.30 84	87.20 114	81.96 58	68.06 144	69.31 144	90.34 85	93.95 71	93.10 92	98.33 70	97.67 119

casdiffmvs_mvg		87.64 88	86.46 116	89.01 72	89.45 108	96.09 114	92.69 68	83.42 75	84.60 139	80.01 81	68.55 141	70.29 138	90.51 81	93.93 72	93.59 77	97.96 103	98.18 92
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 89	87.24 102	88.09 94	88.62 132	96.01 119	90.12 118	82.94 100	91.56 83	79.86 83	73.01 107	68.92 148	89.06 116	90.03 144	92.46 101	97.94 105	98.66 68

ET-MVSNet_ETH3D		87.63 89	91.08 61	83.59 144	67.96 252	96.30 102	92.06 72	78.47 148	91.95 76	69.87 150	87.57 45	84.14 85	94.34 33	88.58 160	92.10 106	98.88 34	96.93 140

DI_MVS_pp		87.63 89	87.13 103	88.22 87	88.61 133	95.92 122	94.09 58	81.41 117	87.00 116	78.38 112	59.70 185	80.52 94	89.08 115	94.37 62	93.34 83	97.73 115	99.05 49

casdiffmvs		87.59 92	86.69 111	88.64 77	89.06 116	96.32 101	90.18 116	83.21 88	87.74 110	80.20 76	67.99 147	68.34 157	90.79 75	93.83 74	94.08 58	98.41 61	98.50 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
onestephybrid01		87.50 93	87.03 106	88.04 97	88.72 128	96.07 116	89.49 128	83.05 97	90.81 86	81.13 67	71.59 120	69.71 140	88.69 122	89.50 151	92.40 102	97.16 148	99.17 41

viewmamba		87.49 94	86.97 108	88.09 94	88.73 127	95.97 120	90.04 121	82.85 102	92.44 74	78.95 101	72.17 118	68.85 149	90.31 86	88.68 158	92.23 105	97.65 122	98.42 83

PVSNet_Blended_VisFu		87.44 95	88.72 88	85.95 126	92.02 75	97.26 72	86.88 159	82.66 105	83.86 147	79.16 98	66.96 153	84.91 82	77.26 199	94.97 49	93.48 78	97.73 115	99.64 19

viewdifsd2359ckpt09		87.42 96	86.55 113	88.45 82	88.67 130	96.49 94	90.38 113	83.11 93	85.25 128	79.50 86	70.80 126	68.43 154	90.90 71	93.87 73	93.04 93	98.10 86	97.95 107

viewmanbaseed2359cas		87.26 97	86.56 112	88.07 96	89.09 114	96.64 87	90.52 110	83.44 73	85.33 126	76.94 127	70.09 132	68.98 147	90.04 94	92.85 99	94.02 61	98.40 62	98.03 101

diffmvs_AUTHOR		87.25 98	86.52 114	88.11 93	88.39 142	96.07 116	91.06 94	82.98 99	88.29 105	78.43 108	70.18 131	67.08 171	89.79 102	92.05 114	93.02 95	98.03 97	98.94 57

FMVSNet3		87.19 99	87.32 101	87.04 116	82.82 183	90.21 183	92.88 65	76.53 162	91.69 79	81.31 62	64.81 168	80.64 91	89.79 102	94.80 53	94.76 43	98.88 34	94.32 191

LS3D		87.19 99	85.48 126	89.18 67	94.96 59	95.47 130	92.02 73	93.36 28	88.69 101	67.01 157	70.56 128	72.10 129	92.47 55	89.96 145	89.93 136	95.25 212	91.68 220

ACMP	85.16 9	87.15 101	87.04 105	87.27 111	90.80 85	94.45 139	89.41 133	83.09 94	89.15 95	76.98 126	86.35 50	65.80 176	86.94 132	88.45 161	87.52 176	96.42 182	97.56 125
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E3new		87.11 102	85.87 123	88.55 78	88.74 126	96.52 91	90.53 108	83.25 86	82.75 152	80.24 75	68.90 139	68.41 156	90.19 90	92.76 102	93.68 70	98.32 71	98.10 96

E3		87.08 103	85.87 123	88.49 80	88.75 124	96.52 91	90.53 108	83.25 86	82.74 153	79.93 82	68.88 140	68.46 153	90.18 91	92.76 102	93.66 72	98.32 71	98.10 96

UGNet		87.04 104	89.59 80	84.07 139	90.94 84	95.95 121	86.02 166	81.65 114	85.94 122	78.54 106	78.00 76	85.40 79	69.62 224	91.83 116	91.53 112	97.63 125	98.51 77
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		87.03 105	86.28 117	87.90 101	88.81 123	96.63 89	89.75 124	83.30 84	85.16 131	77.32 121	69.27 136	67.96 159	90.14 92	93.53 80	93.67 71	98.09 90	97.74 116

LGP-MVS_train		86.95 106	87.65 95	86.12 121	91.77 78	93.84 145	93.04 64	82.77 103	88.04 107	65.33 162	87.69 44	67.09 170	86.79 133	90.20 141	88.99 156	97.05 151	97.71 117

PatchMatch-RL		86.75 107	85.43 128	88.29 86	94.06 64	96.37 99	86.82 160	82.94 100	88.94 98	79.59 85	79.83 72	59.17 199	89.46 107	91.12 127	88.81 160	96.88 155	93.78 200

FA-MVS(training)		86.74 108	88.01 93	85.26 133	89.86 100	96.99 79	88.54 141	64.26 242	89.04 96	81.30 65	66.74 155	81.52 89	89.11 114	94.04 69	90.37 126	98.47 56	97.37 129

viewmambaseed2359dif		86.69 109	85.42 129	88.17 90	88.54 135	95.67 124	90.98 98	82.71 104	86.36 121	80.14 77	68.41 142	68.31 158	89.91 97	87.78 168	92.27 104	96.75 160	99.13 46

baseline2		86.51 110	89.35 84	83.19 146	85.70 168	94.88 134	85.75 171	77.13 157	89.87 91	70.65 147	79.03 73	79.14 99	81.51 171	93.70 76	90.22 129	98.38 66	98.60 71

viewdifsd2359ckpt07		86.50 111	85.45 127	87.72 103	88.88 121	96.19 108	89.63 125	83.34 82	81.97 158	78.44 107	67.87 149	68.43 154	87.74 126	93.68 77	93.13 91	98.27 74	96.88 142

thres100view900		86.48 112	85.08 132	88.12 92	90.54 86	96.90 81	92.39 69	84.82 67	84.16 145	71.65 140	70.86 123	60.49 194	91.23 67	93.65 78	90.19 131	98.10 86	99.32 28

ACMM	84.23 10	86.40 113	84.64 140	88.46 81	91.90 76	91.93 172	88.11 146	85.59 64	88.61 102	79.13 99	75.31 90	66.25 174	89.86 101	89.88 146	87.64 173	96.16 195	92.86 209
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
E5new		86.34 114	84.76 136	88.20 88	88.52 136	96.26 103	90.68 105	83.36 78	79.90 170	78.40 109	66.52 156	67.18 168	90.01 95	91.82 117	93.64 73	98.22 75	97.98 104

E5		86.34 114	84.76 136	88.20 88	88.52 136	96.26 103	90.68 105	83.36 78	79.90 170	78.40 109	66.52 156	67.18 168	90.01 95	91.82 117	93.64 73	98.22 75	97.98 104

dtuplus		86.22 116	84.66 139	88.03 98	88.31 146	95.62 127	90.41 112	82.64 106	82.92 151	80.07 80	67.05 152	68.49 152	90.23 88	87.56 170	92.10 106	96.49 179	98.90 58

GBi-Net		86.16 117	86.00 120	86.35 118	81.81 190	89.52 192	91.40 81	76.53 162	91.69 79	81.31 62	64.81 168	80.64 91	88.72 118	90.54 132	90.72 119	98.34 67	94.08 192

test1		86.16 117	86.00 120	86.35 118	81.81 190	89.52 192	91.40 81	76.53 162	91.69 79	81.31 62	64.81 168	80.64 91	88.72 118	90.54 132	90.72 119	98.34 67	94.08 192

E4		86.15 119	84.60 141	87.96 100	88.52 136	96.25 105	90.25 115	83.05 97	79.58 173	78.14 114	66.12 159	67.23 166	89.62 104	91.68 119	93.43 80	98.20 78	97.93 108

tfpn200view9		86.07 120	84.76 136	87.61 106	90.54 86	96.39 96	91.35 84	83.15 89	84.16 145	71.65 140	70.86 123	60.49 194	90.91 70	92.89 95	89.34 144	98.05 94	99.17 41

DCV-MVSNet		85.90 121	85.88 122	85.93 127	87.86 151	88.37 209	89.45 132	77.46 156	87.33 113	77.51 119	76.06 82	75.76 112	88.48 123	87.40 172	88.89 159	94.80 221	97.37 129

Vis-MVSNet (Re-imp)		85.89 122	89.62 79	81.55 158	89.85 102	96.08 115	87.55 151	79.80 130	84.80 136	66.55 159	73.70 102	86.71 64	68.25 231	94.40 60	94.53 47	97.32 142	97.09 138

MSDG		85.81 123	82.29 168	89.93 61	95.52 56	92.61 161	91.51 80	91.46 41	85.12 132	78.56 104	63.25 174	69.01 146	85.31 142	88.45 161	88.23 165	97.21 146	89.33 232

thres200		85.80 124	84.38 143	87.46 109	90.51 88	96.39 96	91.64 77	83.15 89	81.59 162	71.54 142	70.24 129	60.41 196	89.88 99	92.89 95	89.85 139	98.06 92	99.26 33

E6new		85.77 125	84.30 145	87.49 107	88.49 140	96.18 109	89.47 130	81.93 112	79.29 174	77.66 116	65.72 160	66.80 172	89.17 111	91.36 123	92.90 97	98.19 80	97.84 111

E6		85.77 125	84.30 145	87.49 107	88.49 140	96.18 109	89.47 130	81.93 112	79.29 174	77.66 116	65.72 160	66.80 172	89.17 111	91.36 123	92.90 97	98.19 80	97.84 111

ECVR-MVS		85.74 127	83.80 153	88.00 99	91.55 80	97.78 63	90.87 102	83.36 78	84.51 141	78.21 113	58.65 190	62.75 188	85.39 139	94.34 64	93.33 85	98.60 46	95.25 177

viewmacassd2359aftdt		85.71 128	84.41 142	87.22 112	88.63 131	96.25 105	90.16 117	83.07 96	79.77 172	74.57 136	65.34 162	67.22 167	88.71 121	90.93 129	93.61 75	98.20 78	97.77 114

OPM-MVS		85.69 129	82.79 161	89.06 70	93.42 67	94.21 143	94.21 57	87.61 50	72.68 196	70.79 146	71.09 121	67.27 165	90.74 76	91.29 125	89.05 155	97.61 127	93.94 197
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		85.59 130	84.08 148	87.36 110	90.45 91	96.60 90	90.95 100	83.67 72	80.99 166	71.17 143	69.08 138	60.25 197	89.88 99	93.14 88	89.34 144	98.02 98	99.17 41

0.3-1-1-0.015		85.55 131	85.15 131	86.02 124	78.77 211	93.03 156	91.14 93	80.95 122	88.71 100	79.50 86	73.18 106	73.11 116	89.48 106	83.59 205	88.42 163	96.29 188	96.01 161

0.4-1-1-0.2		85.51 132	85.07 133	86.02 124	78.76 212	93.04 155	91.17 90	81.04 121	88.53 103	79.46 91	72.62 113	73.05 120	89.37 109	83.67 204	88.56 162	96.31 185	96.03 160

CostFormer		85.47 133	86.98 107	83.71 142	88.70 129	94.02 144	88.07 147	62.72 244	89.78 92	78.68 103	72.69 111	78.37 104	87.35 129	85.96 185	89.32 148	96.73 163	98.72 62

0.4-1-1-0.1		85.32 134	84.89 134	85.83 129	78.73 213	93.00 157	90.99 97	80.42 126	88.43 104	79.41 92	72.22 117	73.05 120	89.17 111	83.43 209	88.14 166	96.24 191	95.94 163

test1111		85.17 135	83.46 156	87.17 113	91.36 82	97.75 65	90.06 120	83.44 73	83.41 149	75.25 133	58.08 194	62.19 190	84.39 149	94.39 61	93.38 82	98.54 52	95.00 186

thres600view7		85.14 136	83.58 155	86.96 117	90.37 95	96.39 96	90.33 114	83.15 89	80.46 167	70.60 149	67.96 148	60.04 198	89.22 110	92.89 95	88.28 164	98.06 92	99.08 48

test-LLR		85.11 137	89.49 82	80.00 168	85.32 172	94.49 137	82.27 202	74.18 177	87.83 108	56.70 195	75.55 87	86.26 66	82.75 164	93.06 90	90.60 124	98.77 40	98.65 69

FMVSNet2		84.89 138	84.02 150	85.91 128	81.81 190	89.52 192	91.40 81	75.79 168	84.45 143	79.39 94	58.75 188	74.35 114	88.72 118	93.51 83	93.46 79	98.34 67	94.08 192

FC-MVSNet-train		84.88 139	84.08 148	85.82 130	89.21 111	91.74 173	85.87 167	81.20 120	81.71 161	74.66 135	73.38 104	64.99 180	86.60 134	90.75 130	88.08 167	97.36 140	97.90 109

EPNet_dtu		84.87 140	89.01 85	80.05 167	95.25 58	92.88 159	88.84 138	84.11 68	91.69 79	49.28 234	85.69 53	78.95 102	65.39 236	92.22 113	91.66 111	97.43 137	89.95 228
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 141	85.71 125	83.73 141	87.94 150	95.76 123	90.08 119	73.45 192	85.12 132	62.66 171	72.39 115	64.97 181	90.59 79	92.95 94	90.69 122	97.67 119	98.12 94

UA-Net		84.69 142	87.64 96	81.25 160	90.38 94	95.67 124	87.33 155	79.41 139	72.07 200	66.48 160	75.09 91	92.48 43	66.88 232	94.03 70	94.25 54	97.01 154	89.88 229

TESTMET0.1,1		84.62 143	89.49 82	78.94 178	82.18 187	94.49 137	82.27 202	70.94 212	87.83 108	56.70 195	75.55 87	86.26 66	82.75 164	93.06 90	90.60 124	98.77 40	98.65 69

CHOSEN 1792x2688		84.59 144	84.30 145	84.93 134	93.71 66	98.23 54	89.91 123	77.96 151	84.81 135	65.93 161	45.19 243	71.76 133	83.13 162	95.46 39	95.13 37	98.94 28	99.53 23

casdiffseed414692147		84.37 145	81.97 172	87.16 115	88.39 142	95.36 131	89.17 135	81.64 115	78.81 178	77.31 122	60.13 183	61.16 192	88.91 117	89.68 148	91.85 109	97.54 131	96.81 145

Anonymous20231211		84.23 146	81.71 176	87.17 113	87.38 160	93.59 148	88.95 137	82.14 110	83.82 148	78.56 104	48.09 236	73.89 115	91.25 66	86.38 179	88.06 169	94.74 222	98.14 93

MDTV_nov1_ep13		84.17 147	88.03 91	79.66 170	86.00 166	94.41 140	85.05 173	66.01 238	90.36 88	64.34 167	77.13 81	84.56 83	82.71 166	87.12 176	88.92 157	93.84 236	93.69 203

test-mter		84.06 148	89.00 86	78.29 183	81.92 188	94.23 142	81.07 212	70.38 217	87.12 115	56.10 205	74.75 92	85.80 72	81.81 170	92.52 106	90.10 133	98.43 59	98.49 79

viewdifsd2359ckpt11		83.97 149	82.19 169	86.05 122	87.69 155	93.13 152	86.43 162	82.38 108	82.00 157	79.38 95	68.06 144	64.36 185	87.13 130	83.72 203	86.86 182	93.31 242	97.22 133

viewmsd2359difaftdt		83.97 149	82.19 169	86.04 123	87.69 155	93.13 152	86.43 162	82.37 109	81.93 159	79.33 96	68.06 144	64.40 184	87.12 131	83.73 202	86.86 182	93.31 242	97.22 133

IB-MVS	79.58 12	83.83 151	84.81 135	82.68 150	91.85 77	97.35 70	75.75 237	82.57 107	86.55 119	84.01 46	70.90 122	65.43 178	63.18 243	84.19 199	89.92 138	98.74 42	99.31 30
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		83.71 152	86.76 110	80.16 166	89.72 105	95.64 126	84.68 174	59.73 249	89.61 94	62.67 170	72.65 112	81.80 88	86.22 136	86.23 181	88.03 170	97.96 103	93.35 205

HyFIR lowres test		83.43 153	82.94 159	84.01 140	93.41 68	97.10 75	87.21 156	74.04 180	80.15 169	64.98 163	41.09 251	76.61 109	86.51 135	93.31 85	93.01 96	97.91 111	99.30 31

PatchmatchNet		83.28 154	87.57 97	78.29 183	87.46 158	94.95 132	83.36 184	59.43 252	90.20 90	58.10 190	74.29 95	86.20 68	84.13 152	85.27 191	87.39 177	97.25 145	94.67 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 155	87.76 94	78.00 189	87.45 159	92.20 167	82.63 198	58.42 254	90.30 89	58.23 188	75.74 86	87.75 59	83.97 155	86.10 184	87.64 173	97.30 143	94.62 190

GeoE		83.17 156	82.86 160	83.53 145	87.24 161	93.78 146	87.94 148	72.75 197	82.19 156	69.76 151	60.54 181	65.95 175	86.01 137	89.41 152	89.72 141	97.47 133	98.43 82

CDS-MVSNet		83.13 157	83.73 154	82.43 156	84.52 177	92.92 158	88.26 143	77.67 154	72.08 199	69.08 154	66.96 153	74.66 113	78.61 185	90.70 131	91.96 108	96.46 181	96.86 143
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 158	81.86 173	84.13 138	88.25 147	88.32 210	87.67 149	80.86 125	84.78 137	76.57 130	85.56 54	76.00 111	84.61 147	78.20 240	76.52 244	86.81 260	83.63 252

Vis-MVSNet		82.88 159	86.04 119	79.20 176	87.77 154	96.42 95	86.10 165	76.70 159	74.82 190	61.38 174	70.70 127	77.91 105	64.83 238	93.22 86	93.19 90	98.43 59	96.01 161
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 160	82.64 164	82.62 152	87.81 153	92.81 160	84.39 176	61.96 245	86.43 120	81.63 59	69.72 134	67.60 163	84.42 148	82.51 218	83.90 216	95.52 206	95.50 174

IterMVS-LS		82.62 161	82.75 163	82.48 153	87.09 162	87.48 223	87.19 157	72.85 195	79.09 176	66.63 158	65.22 163	72.14 128	84.06 154	88.33 164	91.39 114	97.03 153	95.60 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 162	82.51 166	82.72 149	85.49 171	93.06 154	87.17 158	71.39 209	84.18 144	64.59 165	63.03 175	58.89 200	90.22 89	91.39 122	90.83 118	97.44 135	96.21 158

tpm cat1		82.39 163	82.32 167	82.47 154	88.13 148	92.42 165	87.43 152	62.79 243	85.30 127	78.05 115	60.14 182	72.10 129	83.20 161	82.26 221	85.67 195	95.23 213	98.35 87

dmvs_re		82.31 164	81.55 177	83.19 146	83.15 182	93.17 151	88.68 140	83.72 70	82.73 154	61.70 172	67.43 151	55.43 213	83.35 160	87.51 171	89.27 151	98.56 50	95.31 176

MS-PatchMatch		82.16 165	82.18 171	82.12 157	91.65 79	93.50 149	89.51 127	71.95 203	81.48 163	64.45 166	59.58 187	77.54 106	77.23 200	89.88 146	85.62 196	97.94 105	87.68 236

blend_shiyan4		81.76 166	80.92 182	82.74 148	79.07 208	85.29 235	91.60 79	74.15 179	89.00 97	79.50 86	73.82 98	73.11 116	77.73 193	77.73 242	75.18 247	94.37 225	92.34 212

tpmrst		81.71 167	83.87 152	79.20 176	89.01 117	93.67 147	84.22 177	60.14 247	87.45 111	59.49 178	64.97 166	71.86 132	85.30 143	84.72 195	86.30 187	97.04 152	98.09 98

RPMNet		81.47 168	86.24 118	75.90 208	86.72 163	92.12 169	82.82 196	55.76 261	85.21 129	53.73 216	63.45 172	83.16 86	80.13 179	92.34 110	89.52 142	96.23 193	97.90 109

CR-MVSNet		81.44 169	85.29 130	76.94 199	86.53 164	92.12 169	83.86 178	58.37 255	85.21 129	56.28 200	59.60 186	80.39 95	80.50 176	92.77 100	89.32 148	96.12 197	97.59 123

Effi-MVS+-dtu		81.18 170	82.77 162	79.33 174	84.70 176	92.54 163	85.81 168	71.55 207	78.84 177	57.06 194	71.98 119	63.77 186	85.09 144	88.94 156	87.62 175	91.79 252	95.68 168

test0.0.03 1		80.99 171	84.37 144	77.05 197	85.32 172	89.79 188	78.43 228	74.18 177	84.78 137	57.98 193	76.06 82	72.88 124	69.14 228	88.02 166	87.70 171	97.27 144	91.37 221

dtuonly		80.91 172	81.25 181	80.52 164	82.54 184	91.09 176	87.43 152	75.69 171	77.28 182	56.58 198	58.23 192	67.55 164	85.08 145	89.06 155	89.42 143	95.80 202	96.10 159

Fast-Effi-MVS+-dtu		80.57 173	83.44 157	77.22 195	83.98 180	91.52 175	85.78 170	64.54 241	80.38 168	50.28 230	74.06 97	62.89 187	82.00 169	89.10 154	88.91 158	96.75 160	97.21 136

FMVSNet5		80.56 174	82.53 165	78.26 185	73.80 244	81.52 252	82.26 204	68.36 229	88.85 99	64.21 168	69.09 137	84.38 84	83.49 159	87.13 175	86.76 184	97.44 135	79.95 256

ADS-MVSNet		80.25 175	82.96 158	77.08 196	87.86 151	92.60 162	81.82 209	56.19 260	86.95 117	56.16 203	68.19 143	72.42 127	83.70 158	82.05 222	85.45 201	96.75 160	93.08 208

FMVSNet1		80.18 176	78.07 191	82.65 151	78.55 218	87.57 222	88.41 142	73.93 185	70.16 205	73.57 137	49.80 225	64.45 183	85.35 141	90.54 132	90.72 119	96.10 198	93.21 206

USDC		80.10 177	79.33 187	81.00 162	86.36 165	91.71 174	88.74 139	75.77 169	81.90 160	54.90 210	67.67 150	52.05 219	83.94 156	88.44 163	86.25 188	96.31 185	87.28 240

COLMAP_ROB	75.69 15	79.47 178	76.90 200	82.46 155	92.20 72	90.53 179	85.30 172	83.69 71	78.27 181	61.47 173	58.26 191	62.75 188	78.28 188	82.41 219	82.13 229	93.83 238	83.98 251
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs4		79.32 179	77.78 195	81.11 161	80.18 199	88.96 204	83.39 182	76.07 165	81.27 164	69.35 152	58.66 189	51.19 222	82.01 168	87.16 174	84.39 213	95.66 203	92.82 210

PatchT		79.28 180	83.88 151	73.93 221	85.54 170	90.95 177	66.14 256	56.53 259	83.21 150	56.28 200	56.50 197	76.80 108	80.50 176	92.77 100	89.32 148	98.57 49	97.59 123

ACMH	78.51 14	79.27 181	78.08 190	80.65 163	89.52 107	90.40 180	80.45 219	79.77 132	69.54 210	54.85 211	64.83 167	56.16 211	83.94 156	84.58 197	86.01 192	95.41 209	95.03 185
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 182	78.95 189	79.56 171	81.89 189	92.52 164	82.97 191	73.70 186	67.27 223	64.97 164	61.66 180	65.06 179	78.61 185	87.12 176	88.07 168	95.23 213	90.95 223

ACMH+	79.09 13	79.12 183	77.22 199	81.35 159	88.50 139	90.36 181	82.14 206	79.38 141	72.78 195	58.59 185	62.31 179	56.44 210	84.10 153	82.03 223	84.05 214	95.40 210	92.55 211

usedtu_dtu_shiyan1		79.10 184	79.87 184	78.20 187	71.16 246	90.83 178	84.41 175	78.54 146	81.24 165	58.78 184	56.79 196	61.56 191	78.74 184	90.08 142	87.70 171	97.59 128	90.90 224

UniMVSNet_NR-MVSNet		78.89 185	78.04 192	79.88 169	79.40 205	89.70 189	82.92 193	80.17 127	76.37 188	58.56 186	57.10 195	54.92 214	81.44 172	83.51 208	87.12 179	96.76 159	97.60 121

tpm		78.87 186	81.33 180	76.00 206	85.57 169	90.19 184	82.81 197	59.66 250	78.35 180	51.40 225	66.30 158	67.92 160	80.94 174	83.28 212	85.73 193	95.65 204	97.56 125

GA-MVS		78.86 187	80.42 183	77.05 197	83.27 181	92.17 168	83.24 186	75.73 170	73.75 192	46.27 245	62.43 177	57.12 203	76.94 202	93.14 88	89.34 144	96.83 156	95.00 186

IterMVS		78.85 188	81.36 178	75.93 207	84.27 179	85.74 229	83.83 180	66.35 236	76.82 183	50.48 228	63.48 171	68.82 150	73.99 211	89.68 148	89.34 144	96.63 169	95.67 169
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 189	81.34 179	75.64 212	84.31 178	85.67 230	83.51 181	66.14 237	76.67 184	50.38 229	63.45 172	69.02 145	73.23 214	89.66 150	89.22 152	96.24 191	95.67 169

usedtu_blend_shiyan5		78.69 190	77.98 193	79.53 172	60.42 256	84.96 238	91.21 89	73.97 181	69.27 212	79.50 86	73.82 98	73.11 116	77.73 193	77.31 246	75.07 248	94.33 228	92.34 212

UniMVSNet (Re)		78.00 191	77.52 196	78.57 181	79.66 204	90.36 181	82.09 207	77.86 153	76.38 187	60.26 175	54.63 203	52.07 218	75.31 209	84.97 194	86.10 190	96.22 194	98.11 95

DU-MVS		77.98 192	76.71 201	79.46 173	78.68 215	89.26 198	82.92 193	79.06 143	76.52 185	58.56 186	54.89 201	48.35 236	81.44 172	83.16 214	87.21 178	96.08 199	97.60 121

FC-MVSNet-test		77.95 193	81.85 174	73.39 227	82.31 185	88.99 203	79.33 224	74.24 176	78.75 179	47.40 243	70.22 130	72.09 131	60.78 250	86.66 178	85.62 196	96.30 187	90.61 225

FE-MVSNET3		77.89 194	77.94 194	77.83 191	60.42 256	84.96 238	81.04 213	73.97 181	69.27 212	79.50 86	73.82 98	73.11 116	77.73 193	77.31 246	75.07 248	94.33 228	92.02 216

NR-MVSNet		77.21 195	76.41 202	78.14 188	80.18 199	89.26 198	83.38 183	79.06 143	76.52 185	56.59 197	54.89 201	45.32 246	72.89 216	85.39 190	86.12 189	96.71 164	97.36 131

thisisatest0515		77.13 196	79.36 186	74.52 214	79.79 203	89.65 190	73.54 242	73.69 187	74.10 191	58.14 189	62.79 176	60.57 193	66.49 234	88.08 165	85.16 206	95.49 208	95.15 181

gg-mvs-nofinetune		77.08 197	79.79 185	73.92 222	85.95 167	97.23 73	92.18 71	52.65 264	46.19 265	27.79 271	38.27 255	85.63 73	85.67 138	96.95 19	95.62 26	99.30 3	98.67 67

TranMVSNet+NR-MVSNet		77.02 198	75.76 204	78.49 182	78.46 221	88.24 211	83.03 190	79.97 128	73.49 194	54.73 212	54.00 206	48.74 231	78.15 190	82.36 220	86.90 181	96.59 171	96.55 150

CVMVSNet		76.86 199	79.09 188	74.26 217	85.29 174	89.44 195	79.91 223	78.47 148	68.94 219	44.45 252	62.35 178	69.70 141	64.50 240	85.82 186	87.03 180	92.94 247	90.33 226

Baseline_NR-MVSNet		76.71 200	74.56 211	79.23 175	78.68 215	84.15 246	82.45 200	78.87 145	75.83 189	60.05 176	47.92 237	50.18 228	79.06 183	83.16 214	83.86 217	96.26 189	96.80 146

v2v482		76.25 201	74.78 208	77.96 190	78.50 220	89.14 201	83.05 189	76.02 166	68.78 220	54.11 213	51.36 217	48.59 233	79.49 181	83.53 207	85.60 199	96.59 171	96.49 155

V42		76.21 202	75.04 207	77.58 192	78.68 215	89.33 197	82.93 192	74.64 174	69.84 207	56.13 204	50.42 222	50.93 223	76.30 208	83.32 210	84.89 210	96.83 156	96.54 151

v8		75.89 203	74.74 209	77.23 194	79.09 207	88.00 214	83.19 187	71.08 211	70.03 206	56.29 199	50.50 220	50.88 224	77.06 201	83.32 210	84.99 208	96.68 165	95.49 175

TinyColmap		75.75 204	73.19 222	78.74 180	84.82 175	87.69 218	81.59 210	74.62 175	71.81 201	54.01 214	55.79 200	44.42 251	82.89 163	84.61 196	83.76 218	94.50 223	84.22 250

MIMVSNet		75.71 205	77.26 197	73.90 223	70.93 247	88.71 207	79.98 222	57.67 258	73.58 193	58.08 192	53.93 207	58.56 201	79.41 182	90.04 143	89.97 134	97.34 141	86.04 241

UniMVSNet_ETH3D		75.63 206	71.59 236	80.35 165	81.03 194	89.90 187	83.25 185	76.58 161	60.08 245	64.19 169	42.89 250	45.01 247	82.14 167	80.20 233	86.75 185	94.90 218	96.29 157

pm-mvs1		75.61 207	74.19 213	77.26 193	80.16 201	88.79 205	81.49 211	75.49 173	59.49 247	58.09 191	48.32 233	55.53 212	72.35 217	88.61 159	85.48 200	95.99 200	93.12 207

v10		75.57 208	74.67 210	76.62 202	78.73 213	87.46 224	83.14 188	69.41 224	69.27 212	53.44 217	49.73 226	49.21 230	78.44 187	86.17 183	85.18 205	96.53 176	95.65 172

v1144		75.54 209	74.55 212	76.69 200	78.33 224	88.77 206	82.89 195	72.76 196	67.18 225	51.73 222	49.34 228	48.37 234	78.10 191	86.22 182	85.24 203	96.35 184	96.74 147

TDRefinement		75.54 209	73.22 220	78.25 186	87.65 157	89.65 190	85.81 168	79.28 142	71.14 203	56.06 206	52.17 215	51.96 220	68.74 230	81.60 224	80.58 232	91.94 250	85.45 242

pmmvs5		75.46 211	75.12 206	75.87 209	79.39 206	89.44 195	78.12 230	72.27 201	65.98 230	51.54 223	55.83 199	46.23 241	76.80 205	88.77 157	85.73 193	97.07 150	93.84 198

tfpnnormal		75.27 212	72.12 233	78.94 178	82.30 186	88.52 208	82.41 201	79.41 139	58.03 248	55.59 208	43.83 249	44.71 248	77.35 197	87.70 169	85.45 201	96.60 170	96.61 149

anonymousdsp		75.14 213	77.25 198	72.69 230	76.68 234	89.26 198	75.26 239	68.44 228	65.53 233	46.65 244	58.16 193	56.67 205	73.96 212	87.84 167	86.05 191	95.13 216	97.22 133

v148		74.98 214	73.52 218	76.69 200	78.84 210	89.02 202	78.78 226	76.82 158	67.22 224	59.61 177	49.18 229	47.94 238	70.57 223	80.76 228	83.99 215	95.52 206	96.52 153

v1192		74.96 215	73.92 214	76.17 203	77.76 227	88.19 213	82.54 199	71.94 204	66.84 226	50.07 232	48.10 235	46.14 242	78.28 188	86.30 180	85.23 204	96.41 183	96.67 148

v144192		74.76 216	73.64 215	76.06 205	77.58 228	88.23 212	81.87 208	71.63 206	66.03 229	51.08 226	48.63 232	46.77 240	77.59 196	84.53 198	84.76 211	96.64 168	96.54 151

v1921920		74.60 217	73.56 217	75.81 210	77.43 230	87.94 215	82.18 205	71.33 210	66.48 228	49.23 236	47.84 238	45.56 244	78.03 192	85.70 188	84.92 209	96.65 166	96.50 154

v1240		74.04 218	73.04 224	75.20 213	77.19 232	87.69 218	80.93 216	70.72 216	65.08 234	48.47 238	47.31 239	44.71 248	77.33 198	85.50 189	85.07 207	96.59 171	95.94 163

wanda-best-256-512		73.38 219	72.60 227	74.28 215	60.42 256	84.96 238	81.04 213	73.97 181	69.27 212	59.09 181	52.95 210	56.56 206	76.85 203	77.31 246	75.07 248	94.33 228	92.05 214

FE-blended-shiyan7		73.37 220	72.59 228	74.28 215	60.42 256	84.96 238	81.04 213	73.97 181	69.28 211	59.09 181	52.95 210	56.54 207	76.85 203	77.31 246	75.07 248	94.33 228	92.05 214

blended_shiyan8		73.25 221	72.48 229	74.14 219	60.35 260	84.93 242	80.84 217	73.55 190	69.25 216	59.22 180	52.62 213	56.47 209	76.66 206	77.19 251	74.92 253	94.23 232	91.94 218

blended_shiyan6		73.22 222	72.48 229	74.09 220	60.31 261	84.90 243	80.80 218	73.54 191	69.06 218	59.06 183	52.69 212	56.53 208	76.59 207	77.20 250	74.94 252	94.22 233	92.02 216

testgi		73.22 222	75.84 203	70.16 241	81.67 193	85.50 233	71.45 244	70.81 214	69.56 209	44.74 251	74.52 94	49.25 229	58.45 251	84.10 201	83.37 222	93.86 235	84.56 249

gbinet_0.2-2-1-0.02		73.19 224	72.88 225	73.56 225	60.07 262	84.50 245	80.22 221	73.59 189	67.33 222	59.36 179	52.21 214	58.21 202	73.76 213	77.60 243	75.19 246	94.37 225	95.12 182

CP-MVSNet		73.19 224	72.37 231	74.15 218	77.54 229	86.77 227	76.34 233	72.05 202	65.66 232	51.47 224	50.49 221	43.66 252	70.90 219	80.93 227	83.40 221	96.59 171	95.66 171

WR-MVS		72.93 226	73.57 216	72.19 233	78.14 225	87.71 217	76.21 235	73.02 194	67.78 221	50.09 231	50.35 223	50.53 226	61.27 249	80.42 231	83.10 225	94.43 224	95.11 183

TransMVSNet (Re)		72.90 227	70.51 240	75.69 211	80.88 195	85.26 236	79.25 225	78.43 150	56.13 255	52.81 219	46.81 240	48.20 237	66.77 233	85.18 193	83.70 219	95.98 201	88.28 235

WR-MVS_H		72.69 228	72.80 226	72.56 232	77.94 226	87.83 216	75.26 239	71.53 208	64.75 235	52.19 221	49.83 224	48.62 232	61.96 247	81.12 226	82.44 227	96.50 177	95.00 186

SixPastTwentyTwo		72.65 229	73.22 220	71.98 236	78.40 222	87.64 220	70.09 247	70.37 218	66.49 227	47.60 241	65.09 164	45.94 243	73.09 215	78.94 235	78.66 239	92.33 248	89.82 230

LTVRE_ROB	71.82 16	72.62 230	71.77 234	73.62 224	80.74 196	87.59 221	80.42 220	70.37 218	49.73 260	37.12 264	59.76 184	42.52 257	80.92 175	83.20 213	85.61 198	92.13 249	93.95 196
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		72.37 231	71.47 238	73.43 226	77.32 231	86.43 228	75.99 236	71.94 204	63.37 238	49.24 235	49.07 230	42.42 258	69.60 225	80.59 230	83.18 224	96.48 180	95.23 179

MVS-HIRNet		72.32 232	73.45 219	71.00 239	80.58 197	89.97 185	68.51 252	55.28 262	70.89 204	52.27 220	39.09 253	57.11 204	75.02 210	85.76 187	86.33 186	94.36 227	85.00 246

PEN-MVS		72.24 233	71.30 239	73.33 228	77.08 233	85.57 231	76.75 231	72.52 199	63.89 237	48.12 239	50.79 218	43.09 255	69.03 229	78.54 237	83.46 220	96.50 177	93.76 201

v7n		72.11 234	71.66 235	72.63 231	75.26 239	86.85 225	76.74 232	68.77 227	62.70 241	49.40 233	45.92 242	43.51 253	70.63 222	84.16 200	83.21 223	94.99 217	95.25 177

EG-PatchMatch MVS		71.81 235	71.54 237	72.12 234	80.53 198	89.94 186	78.51 227	66.56 235	57.38 250	47.46 242	44.28 248	52.22 217	63.10 244	85.22 192	84.42 212	96.56 175	87.35 239

CMPMVS	54.54 17	71.74 236	67.94 245	76.16 204	90.41 92	93.25 150	78.32 229	75.60 172	59.81 246	53.95 215	44.64 246	51.22 221	70.70 220	74.59 255	75.88 245	88.01 257	76.23 259
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 237	73.08 223	69.97 242	75.22 240	86.81 226	73.98 241	59.61 251	69.75 208	48.01 240	54.21 205	53.06 216	69.19 227	78.50 238	80.43 233	93.84 236	88.79 233

pmnet_mix02		71.64 238	72.36 232	70.81 240	78.39 223	85.57 231	68.64 250	73.65 188	72.13 197	45.07 250	56.01 198	50.61 225	65.34 237	76.21 252	76.60 243	93.75 239	89.35 231

gm-plane-assit		71.33 239	75.18 205	66.83 246	79.06 209	75.57 260	48.05 269	60.33 246	48.28 261	34.67 268	44.34 247	67.70 162	79.78 180	97.25 13	96.21 14	99.10 11	96.92 141

DTE-MVSNet		71.19 240	70.45 241	72.06 235	76.61 235	84.59 244	75.61 238	72.32 200	63.12 240	45.70 248	50.72 219	43.02 256	65.89 235	77.53 245	82.23 228	96.26 189	91.93 219

pmmvs6		70.29 241	67.90 246	73.07 229	76.17 236	85.31 234	76.29 234	70.75 215	47.39 263	55.33 209	37.15 259	50.49 227	69.55 226	82.96 216	80.85 231	90.34 256	91.18 222

PM-MVS		70.17 242	69.42 243	71.04 238	70.82 248	81.26 254	71.25 245	67.80 231	69.16 217	51.04 227	53.15 209	34.93 265	72.19 218	80.30 232	76.95 242	93.16 246	90.21 227

pmmvs-eth3d		69.59 243	67.57 248	71.95 237	70.04 250	80.05 255	71.48 243	70.00 222	62.57 242	55.99 207	44.92 244	35.73 263	70.64 221	81.56 225	79.69 234	93.55 240	88.43 234

N_pmnet		68.54 244	67.83 247	69.38 243	75.77 237	81.90 251	66.21 255	72.53 198	65.91 231	46.09 246	44.67 245	45.48 245	63.82 242	74.66 254	77.39 241	91.87 251	84.77 248

Anonymous20231206		68.09 245	68.68 244	67.39 245	75.16 241	82.55 247	69.33 249	70.06 221	63.34 239	42.28 255	37.91 257	43.12 254	52.67 254	83.56 206	82.71 226	94.84 220	87.59 237

EU-MVSNet		68.07 246	70.25 242	65.52 248	74.68 243	81.30 253	68.53 251	70.31 220	62.40 244	37.43 263	54.62 204	48.36 235	51.34 256	78.32 239	79.27 236	90.84 253	87.47 238

dtuonlycased		66.81 247	65.49 251	68.34 244	70.60 249	82.21 249	66.95 254	68.30 230	62.57 242	48.64 237	46.62 241	53.65 215	64.78 239	62.62 260	65.70 261	90.79 254	85.07 244

FE-MVSNET2		65.87 248	65.40 252	66.41 247	56.18 265	82.03 250	69.83 248	68.97 225	56.64 253	45.42 249	31.48 262	37.87 261	62.52 246	82.96 216	81.55 230	95.56 205	85.28 243

GG-mvs-BLEND		65.67 249	93.78 43	32.89 264	0.47 275	99.35 9	96.92 35	0.22 274	93.28 64	0.51 277	84.07 58	92.50 42	0.62 273	93.59 79	93.86 64	98.59 48	99.79 10

test20.03		65.17 250	67.41 249	62.55 250	75.35 238	79.31 256	62.22 258	68.83 226	56.50 254	35.35 267	51.97 216	44.70 250	40.01 262	80.69 229	79.25 237	93.55 240	79.47 258

MDA-MVSNet-bldmvs		62.23 251	61.13 256	63.52 249	58.94 263	82.44 248	60.71 262	73.28 193	57.22 251	38.42 261	49.63 227	27.64 272	62.83 245	54.98 264	74.16 254	86.96 259	81.83 255

new_pmnet		61.60 252	62.68 253	60.35 253	63.02 253	74.93 261	60.97 261	58.86 253	64.21 236	35.38 266	39.51 252	39.89 259	57.37 252	72.78 256	72.56 256	86.49 261	74.85 261

FE-MVSNET		61.22 253	62.61 254	59.59 255	48.81 267	75.79 259	61.96 259	67.51 232	52.39 258	34.04 269	33.16 261	37.64 262	52.00 255	77.89 241	79.39 235	93.22 244	82.04 254

new-patchmatchnet		60.74 254	59.78 258	61.87 251	69.52 251	76.67 258	57.99 265	65.78 239	52.63 257	38.47 260	38.08 256	32.92 268	48.88 259	68.50 257	69.87 257	90.56 255	79.75 257

pmmvs3		60.52 255	60.87 257	60.12 254	61.38 254	71.62 263	57.42 266	53.94 263	48.09 262	35.95 265	38.62 254	32.19 271	64.12 241	75.33 253	77.99 240	87.89 258	82.28 253

MIMVSNet1		60.51 256	61.43 255	59.44 256	48.75 268	77.21 257	60.98 260	66.84 234	52.09 259	38.74 259	29.29 264	39.40 260	48.08 260	77.60 243	78.87 238	93.22 244	75.56 260

test_method		60.40 257	66.30 250	53.52 259	37.48 273	64.10 267	55.56 267	42.45 269	71.79 202	41.87 256	33.74 260	46.80 239	61.71 248	79.18 234	73.33 255	82.01 264	95.17 180

FPMVS		56.54 258	52.82 261	60.87 252	74.90 242	67.58 266	67.69 253	65.38 240	57.86 249	41.51 257	37.83 258	34.19 266	41.21 261	55.88 263	53.09 265	74.55 267	63.31 264

usedtu_dtu_shiyan2		56.32 259	55.74 260	57.01 258	40.29 272	72.50 262	63.80 257	57.88 257	37.70 266	45.71 247	25.31 266	35.59 264	49.97 258	67.09 258	67.03 259	84.41 262	84.92 247

WB-MVS		47.20 260	51.37 262	42.35 262	71.55 245	57.66 269	32.77 273	70.86 213	47.39 263	6.95 276	48.14 234	32.52 269	12.95 270	61.73 262	61.27 262	59.00 271	50.85 268

PMVS	42.57 18	45.71 261	42.61 264	49.32 260	61.35 255	37.82 272	36.96 271	60.10 248	37.20 267	41.50 258	28.53 265	33.11 267	28.82 267	53.45 265	48.70 267	67.22 269	59.42 265
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 262	42.62 263	45.50 261	50.79 266	41.20 271	35.55 272	52.51 265	52.95 256	29.09 270	12.92 268	11.48 275	38.15 263	62.01 261	66.62 260	66.89 270	51.17 266
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 263	42.55 265	39.74 263	43.25 269	55.05 270	38.15 270	47.11 268	31.78 268	11.83 273	21.16 267	19.12 273	20.98 269	49.95 267	56.09 264	77.09 265	64.68 263

E-PMN		27.87 264	24.36 267	31.97 265	41.27 271	25.56 275	16.62 275	49.16 266	22.00 270	9.90 274	11.75 270	7.86 277	29.57 266	22.22 269	34.70 268	45.27 272	46.41 269

MVE	32.98 19	27.61 265	29.89 266	24.94 267	21.97 274	37.22 273	15.56 277	38.83 270	17.49 271	14.72 272	11.64 272	5.62 278	21.26 268	35.20 268	50.95 266	37.29 274	51.13 267
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		26.96 266	22.96 268	31.63 266	41.91 270	25.73 274	16.30 276	49.10 267	22.38 269	9.03 275	11.22 273	8.12 276	29.93 265	20.16 270	31.04 269	43.49 273	42.04 270

testmvs		5.16 267	8.14 269	1.69 268	0.36 276	1.65 276	3.02 278	0.66 272	7.17 272	0.50 278	12.58 269	0.69 279	4.67 271	5.42 271	5.65 270	0.92 275	23.86 272

test123		4.39 268	7.11 270	1.21 269	0.11 277	1.16 277	1.67 279	0.35 273	5.91 273	0.16 279	11.65 271	0.16 280	4.45 272	1.72 272	4.92 271	0.51 276	24.28 271

uanet_test		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet-low-res		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

sosnet		0.00 269	0.00 271	0.00 270	0.00 278	0.00 278	0.00 280	0.00 275	0.00 274	0.00 280	0.00 274	0.00 281	0.00 274	0.00 273	0.00 272	0.00 277	0.00 273

TestfortrainingZip							98.29 14	95.80 1		98.47 1						99.17 7

TPM-MVS					99.19 1	99.43 7	99.16 2			85.97 36	94.75 28	97.40 15	97.76 1			98.95 27	95.69 166
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										43.17 253

9.14												97.59 12

SR-MVS					98.52 22			93.70 25				96.63 23

Anonymous202405211			81.72 175		88.09 149	94.27 141	89.62 126	82.14 110	82.27 155		48.83 231	72.58 126	91.08 68	87.40 172	88.70 161	94.90 218	97.99 102

our_test_3					78.55 218	84.98 237	70.12 246

ambc			57.08 259		58.68 264	67.71 265	60.07 263		57.13 252	42.79 254	30.00 263	11.64 274	50.18 257	78.89 236	69.14 258	82.64 263	85.02 245

MTAPA										93.37 11		95.71 30

MTMP										93.84 8		94.86 33

Patchmatch-RL test							19.65 274

tmp_tt				57.89 257	79.94 202	59.29 268	52.84 268	36.65 271	94.77 54	68.22 155	72.96 108	65.62 177	33.65 264	66.20 259	58.02 263	76.06 266

XVS					92.16 73	98.56 37	91.04 95			81.00 71		93.49 37				98.00 100

X-MVStestdata					92.16 73	98.56 37	91.04 95			81.00 71		93.49 37				98.00 100

mPP-MVS					97.95 31							92.24 47

NP-MVS									94.12 58

Patchmtry						92.08 171	83.86 178	58.37 255		56.28 200

DeepMVS_CX						70.68 264	59.61 264	67.36 233	72.12 198	38.41 262	53.88 208	32.44 270	55.15 253	50.88 266		74.35 268	68.42 262

High-resolution multi-view benchmark