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		98.18 1	98.35 1	97.98 1	99.00 7	99.45 6	98.94 6	95.60 3	98.80 1	98.26 2	98.11 1	99.53 4	97.16 7	97.07 17	95.77 24	98.93 29	99.68 16

aaEdge-Enhanced		98.02 2	98.12 5	97.91 2	98.97 11	99.32 15	98.29 15	95.80 1	98.28 5	98.12 3	98.11 1	99.40 5	97.13 8	96.54 25	95.50 28	99.17 7	99.68 16

SED-MVS		97.92 3	98.27 3	97.52 3	98.88 15	99.60 1	98.80 7	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 2	97.06 9	98.66 18	99.35 10	98.66 10	94.75 16	98.22 7	93.60 9	97.99 3	98.58 10	97.41 6	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 8	99.58 3	98.79 8	95.06 11	98.24 6	94.66 6	96.35 17	99.20 6	97.63 3	97.20 14	95.68 25	99.08 14	99.84 7

DPE-MVS		97.69 6	98.16 4	97.14 7	99.01 6	99.52 5	99.12 3	95.38 5	98.00 10	93.31 12	97.71 4	99.61 3	96.94 9	96.99 19	95.45 30	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 14	99.60 1	98.21 17	95.11 7	98.39 4	95.83 4	94.40 32	99.70 2	96.79 10	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 9	95.32 6	97.91 11	92.55 14	97.11 8	97.23 16	97.49 5	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 13	99.29 17	98.58 12	95.11 7	97.69 17	94.16 7	96.91 12	96.81 20	96.57 13	96.71 22	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 4	99.20 19	99.05 5	95.55 4	97.39 21	93.56 10	97.48 6	96.71 22	96.75 11	95.73 35	94.40 49	98.98 23	99.33 27

NCCC		97.01 11	97.74 10	96.16 13	99.02 5	99.35 10	98.63 11	95.04 12	97.84 13	88.95 27	96.83 14	97.02 19	96.39 18	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 8	99.31 16	97.91 22	94.68 18	97.52 19	90.59 21	94.54 31	99.20 6	96.54 15	97.29 10	96.48 11	98.22 76	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 8	99.44 7	98.04 18	95.04 12	98.10 8	86.55 34	97.65 5	97.56 13	95.60 27	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 11	99.16 21	97.82 24	94.81 15	98.04 9	89.61 24	96.56 16	98.60 9	96.39 18	97.09 16	95.22 34	98.39 66	99.22 35

SD-MVS		96.87 15	97.69 12	95.92 16	96.38 51	99.25 18	97.76 25	94.75 16	97.72 14	92.46 16	95.94 18	99.09 8	96.48 17	96.01 32	96.08 17	97.68 118	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 17	98.87 30	98.42 13	94.93 14	97.70 16	91.83 17	95.52 21	95.94 29	96.63 12	95.94 33	95.47 29	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 55	98.97 27	98.00 19	94.13 23	97.89 12	91.49 18	95.11 27	97.52 14	96.26 22	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 25	99.11 22	97.93 21	93.62 26	96.28 34	87.45 31	97.05 10	96.00 28	94.23 35	96.83 21	95.97 18	98.40 63	99.27 32
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 19	96.41 26	95.72 19	98.58 20	98.84 31	97.95 20	93.08 30	96.96 27	90.24 22	96.60 15	94.40 35	96.52 16	95.13 45	94.33 50	97.93 108	98.59 72

ACMMP_NAP		95.81 20	96.50 25	95.01 24	98.79 16	99.17 20	97.52 30	94.20 22	96.19 35	85.71 39	93.80 35	96.20 27	95.89 24	96.62 24	94.98 40	97.93 108	98.52 76

MGCNet		95.79 21	97.46 15	93.85 30	96.81 45	99.35 10	97.21 33	87.28 51	97.10 22	88.65 30	95.17 26	96.41 25	94.15 39	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 34	98.92 28	97.84 23	93.50 27	96.86 29	81.35 61	97.10 9	97.71 11	94.19 36	96.02 31	95.37 33	98.07 92	99.64 19

ACMMPR		95.59 23	95.89 28	95.25 22	98.41 24	98.74 32	97.69 28	92.73 34	96.88 28	88.95 27	95.33 23	92.91 42	95.79 25	94.73 55	94.33 50	97.92 110	98.32 88

DeepC-MVS_fast	91.53 1	95.57 24	95.67 31	95.45 21	98.57 21	99.00 26	97.76 25	94.41 20	97.06 24	86.84 33	86.39 50	92.27 47	96.38 20	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 19	98.63 35	98.35 14	92.37 36	95.04 53	92.62 13	87.12 48	93.79 36	96.55 14	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 30	98.60 36	97.45 31	92.80 32	95.98 38	89.21 26	95.22 24	93.60 37	95.43 28	94.37 62	93.22 89	97.68 118	98.72 62

DPM-MVS		95.36 27	95.84 29	94.82 26	96.70 47	98.49 46	99.27 1	95.09 9	96.71 30	83.87 47	86.34 52	96.44 24	95.06 30	98.35 1	98.82 1	98.89 33	95.69 167

MP-MVS		95.24 28	95.96 27	94.40 28	98.32 27	98.38 51	97.12 34	92.87 31	95.17 51	85.50 40	95.68 19	94.91 33	94.58 32	95.11 46	93.76 67	98.05 95	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 40	98.71 34	97.74 27	93.21 29	96.97 26	79.27 98	94.09 33	97.14 17	90.84 73	96.64 23	95.94 21	97.42 139	99.67 18

X-MVS		94.70 30	95.71 30	93.52 35	98.38 26	98.56 38	96.99 35	92.62 35	95.58 42	81.00 71	94.57 30	93.49 38	94.16 38	94.82 51	94.29 53	97.99 103	98.68 64

PGM-MVS		94.64 31	95.49 33	93.66 33	98.55 22	98.51 44	97.63 29	87.77 49	94.45 57	84.92 43	97.23 7	91.90 49	95.22 29	94.56 58	93.80 66	97.87 114	97.97 107

TSAR-MVS + GP.		94.59 32	96.60 24	92.25 42	90.25 97	98.17 58	96.22 40	86.53 56	97.49 20	87.26 32	95.21 25	97.06 18	94.07 41	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 41	98.88 29	94.99 52	89.13 44	96.15 36	79.70 85	96.91 12	95.78 30	91.87 62	94.65 56	95.68 25	98.53 53	98.98 56

AdaColmap		94.28 34	92.94 49	95.84 17	98.32 27	98.33 53	96.06 42	94.62 19	96.29 33	91.22 19	89.89 42	85.50 77	96.38 20	91.85 115	90.89 117	98.44 59	97.81 114

DeepPCF-MVS	91.00 2	94.15 35	96.87 22	90.97 53	96.82 44	99.33 14	89.40 135	92.76 33	98.76 2	82.36 54	88.74 43	95.49 32	90.58 81	98.13 4	97.80 4	93.88 235	99.88 6

CPTT-MVS		94.11 36	93.99 42	94.25 29	96.58 48	97.66 67	97.31 32	91.94 37	94.84 54	88.72 29	92.51 36	93.04 41	95.78 26	91.51 121	89.97 134	95.15 216	98.37 85

EPNet		93.69 37	95.34 34	91.76 45	96.98 43	98.47 48	95.40 48	86.79 53	95.47 44	82.84 51	95.66 20	89.17 55	90.47 84	95.25 44	94.69 44	98.10 87	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 42	98.24 54	95.27 50	91.66 40	95.20 49	83.25 49	95.39 22	85.52 75	92.80 53	92.60 104	90.21 130	98.01 100	97.99 103
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 58	99.09 24	96.55 38	86.74 54	95.28 47	85.22 41	77.30 80	91.25 51	92.60 55	97.06 18	96.63 9	99.31 2	99.45 26

CDPH-MVS		93.22 40	95.08 35	91.04 51	97.57 37	98.49 46	96.74 37	89.35 43	95.19 50	73.57 138	90.26 40	91.59 50	90.68 78	95.09 48	96.15 15	98.31 74	98.81 60

CSCG		93.16 41	92.65 50	93.76 32	98.32 27	99.09 24	96.12 41	89.91 42	93.15 66	89.64 23	83.62 60	88.91 57	92.40 57	91.09 128	93.70 68	96.14 197	98.99 54

MVS_111021_LR		93.05 42	94.53 38	91.32 49	96.43 50	98.38 51	92.81 67	87.20 52	95.94 40	81.45 60	94.75 28	86.08 71	92.12 60	94.83 50	93.34 83	97.89 113	98.42 83

3Dnovator+	86.26 7	92.90 43	92.45 52	93.42 36	97.25 39	98.45 50	95.82 43	85.71 62	93.83 61	89.55 25	72.31 118	92.28 46	94.01 43	95.10 47	95.92 22	98.17 83	99.23 34

MVSMamba_PlusPlus		92.73 44	94.19 40	91.03 52	89.86 101	98.16 59	95.33 49	85.38 66	97.56 18	80.47 75	86.68 49	84.99 82	96.11 23	97.37 8	96.77 8	99.04 16	97.76 116

MVS_111021_HR		92.73 44	94.83 37	90.28 58	96.27 52	99.10 23	92.77 68	86.15 59	93.41 64	77.11 125	93.82 34	87.39 63	90.61 79	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 35	96.10 113	95.42 47	91.70 38	95.82 41	92.52 15	81.24 66	86.01 72	94.36 33	92.44 108	90.27 127	97.19 148	93.99 196
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 31	98.47 48	95.78 44	85.94 60	93.07 67	86.40 35	73.43 104	89.00 56	94.08 40	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 53	98.55 41	96.30 39	93.84 24	93.06 68	81.09 68	74.69 94	85.20 81	93.48 47	95.41 40	96.13 16	97.92 110	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 49	97.94 61	93.18 64	88.97 46	96.53 31	84.47 45	80.79 68	87.85 59	93.25 51	92.48 107	91.81 110	97.12 150	95.73 166

MVSTER		91.91 50	93.43 48	90.14 59	89.81 105	92.32 167	94.53 55	81.32 119	96.00 37	84.77 44	85.41 57	92.39 45	91.32 65	96.41 26	94.01 62	99.11 10	97.45 128

SPE-MVS-test		91.76 51	93.47 46	89.76 62	94.64 63	98.22 56	88.13 146	81.58 116	97.02 25	82.47 53	85.49 56	85.41 79	93.28 49	95.33 42	93.61 75	98.45 58	99.22 35

QAPM		91.68 52	91.97 53	91.34 48	97.86 33	98.72 33	95.60 46	85.72 61	90.86 86	77.14 124	76.06 83	90.35 52	92.69 54	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 66	97.91 63	91.17 91	81.40 118	95.22 48	83.51 48	82.37 64	82.29 88	94.07 41	96.36 29	94.03 60	98.56 50	99.22 35

CNLPA		91.53 54	89.74 75	93.63 34	96.75 46	97.63 69	91.16 93	91.70 38	96.38 32	90.82 20	69.66 137	85.52 75	93.76 44	90.44 135	91.14 116	97.55 131	97.40 129

ETV-MVS		91.51 55	94.06 41	88.54 79	89.39 111	97.52 70	89.48 130	80.88 124	97.09 23	79.41 93	87.87 44	86.18 70	92.95 52	95.94 33	94.33 50	99.13 9	99.52 24

EC-MVSNet		91.25 56	93.45 47	88.68 76	88.90 121	96.18 110	91.66 77	76.70 159	95.57 43	82.00 57	84.18 58	89.28 54	94.17 37	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 56	98.59 37	95.74 45	86.68 55	85.86 124	85.12 42	72.71 112	81.36 91	88.06 126	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 54	97.66 67	94.80 53	89.00 45	94.74 56	77.42 121	80.22 69	86.70 66	92.27 58	91.65 120	90.17 132	98.15 86	93.83 200
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 61	98.54 42	91.30 86	86.53 56	95.43 45	85.75 37	78.66 75	70.67 136	87.60 128	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 61	98.54 42	91.30 86	86.53 56	95.43 45	85.75 37	78.66 75	70.67 136	87.60 128	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 71	98.16 59	89.99 123	69.62 223	92.48 72	76.89 129	87.28 47	96.72 21	90.31 87	94.81 52	92.33 103	98.17 83	98.08 100

MAR-MVS		90.44 62	91.17 60	89.59 63	97.48 38	97.92 62	90.96 100	79.80 130	95.07 52	77.03 126	80.83 67	79.10 101	94.68 31	93.16 87	94.46 48	97.59 129	97.63 121
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 64	98.18 57	94.35 56	94.33 21	84.55 141	76.61 130	75.84 86	88.47 58	91.29 66	90.37 138	90.66 123	97.46 135	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 36	98.51 44	94.64 54	85.47 65	88.14 107	78.39 112	65.06 167	85.42 78	91.04 70	93.06 90	93.70 68	98.53 53	98.37 85

EIA-MVS		89.82 65	91.48 58	87.89 102	89.16 113	97.31 72	88.99 137	80.92 123	94.29 58	77.65 119	82.16 65	79.77 99	91.90 61	94.61 57	93.03 94	98.70 44	99.21 38

sasdasda		89.62 66	89.87 73	89.33 65	90.47 90	97.02 78	93.46 61	79.67 133	92.45 73	81.05 69	82.84 61	73.00 123	93.71 45	90.38 136	94.85 41	97.65 123	98.54 74

canonicalmvs		89.62 66	89.87 73	89.33 65	90.47 90	97.02 78	93.46 61	79.67 133	92.45 73	81.05 69	82.84 61	73.00 123	93.71 45	90.38 136	94.85 41	97.65 123	98.54 74

TSAR-MVS + COLMAP		89.59 68	89.64 78	89.53 64	93.32 70	96.51 94	95.03 51	88.53 47	95.98 38	69.10 154	91.81 38	64.53 183	93.40 48	93.53 80	91.35 115	97.77 115	93.75 203

HQP-MVS		89.57 69	90.57 69	88.41 83	92.77 72	94.71 137	94.24 57	87.97 48	93.44 63	68.18 157	91.75 39	71.54 135	89.90 99	92.31 111	91.43 113	97.39 140	98.80 61

MGCFI-Net		89.36 70	89.66 77	89.02 71	90.40 94	96.92 81	93.26 63	79.54 137	92.10 76	80.11 79	82.55 63	72.65 126	93.26 50	90.24 140	94.69 44	97.53 133	98.46 81

MVS_Test		89.02 71	90.20 71	87.64 105	89.83 104	97.05 77	92.30 71	77.59 155	92.89 69	75.01 135	77.36 79	76.10 111	92.27 58	95.30 43	95.42 31	98.83 37	97.30 133

CLD-MVS		88.99 72	88.07 90	90.07 60	89.61 107	94.94 134	93.82 60	85.70 63	92.73 71	82.73 52	79.97 70	69.59 143	90.44 85	90.32 139	89.93 136	98.10 87	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	89.44 110	96.74 86	91.62 79	77.92 152	93.79 62	78.76 103	77.55 78	78.46 104	89.38 109	92.26 112	92.52 100	99.10 11	98.23 91

PMMVS		88.56 74	91.22 59	85.47 131	90.04 99	95.60 129	86.62 162	78.49 147	93.86 60	70.62 149	90.00 41	80.08 97	91.64 63	92.36 109	89.80 140	95.40 211	96.84 145

test2506		88.38 75	88.02 92	88.80 75	91.55 81	97.78 64	90.87 103	83.36 78	84.51 142	83.06 50	74.13 97	76.93 108	85.39 140	94.34 64	93.33 85	98.60 46	95.10 185

E2		88.25 76	87.54 98	89.08 69	88.94 119	96.72 87	90.74 105	83.41 76	86.83 119	82.08 56	72.76 111	70.33 138	90.81 74	93.83 74	94.01 62	98.48 55	98.29 90

Casviewmamba		88.16 77	87.37 100	89.09 68	89.09 115	96.34 101	90.93 102	83.41 76	89.70 94	82.13 55	70.03 135	70.14 140	91.34 64	94.28 67	93.39 81	97.66 121	97.68 119

baseline1		88.16 77	88.15 89	88.17 90	90.02 100	94.79 136	91.85 76	83.89 69	87.37 113	75.67 133	73.75 102	79.89 98	88.44 125	94.41 59	93.33 85	99.18 5	93.55 205

thisisatest0530		87.99 79	90.76 63	84.75 135	88.36 145	96.82 83	87.65 151	79.67 133	91.77 78	70.93 145	79.94 71	87.65 61	84.21 151	92.98 93	89.07 153	97.66 121	97.13 138

tttt0517		87.93 80	90.71 64	84.68 136	88.33 146	96.76 85	87.42 155	79.67 133	91.74 79	70.83 146	79.91 72	87.61 62	84.21 151	92.88 98	89.07 153	97.62 127	97.03 140

CANet_DTU		87.91 81	91.57 57	83.64 143	90.96 84	97.12 75	91.90 75	75.97 167	92.83 70	53.16 219	86.02 53	79.02 102	90.80 75	95.40 41	94.15 57	99.03 20	96.47 157

diffmvs		87.86 82	87.40 99	88.39 84	88.57 135	96.10 113	91.24 88	83.15 89	90.62 88	79.13 100	72.45 116	67.71 162	90.07 94	92.58 105	93.31 88	98.17 83	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 98	96.79 84	88.16 145	79.89 129	85.44 126	72.20 140	75.50 90	87.14 64	80.21 179	95.53 38	95.22 34	96.65 167	99.02 52

viewcassd2359sk11		87.73 84	86.79 109	88.83 74	88.87 123	96.64 88	90.66 108	83.33 83	85.05 135	81.22 66	70.85 127	69.54 144	90.50 83	93.40 84	93.86 64	98.40 63	98.21 92

EPP-MVSNet		87.72 85	89.74 75	85.37 132	89.11 114	95.57 130	86.31 165	79.44 138	85.83 125	75.73 132	77.23 81	90.05 53	84.78 147	91.22 126	90.25 128	96.83 157	98.04 101

hybridnocas07		87.67 86	87.10 104	88.33 85	88.75 125	96.06 119	90.46 112	83.08 95	91.52 85	80.08 80	73.23 107	68.53 152	89.58 106	89.30 153	92.59 99	98.05 95	98.47 80

hybridcas		87.66 87	86.50 115	89.01 72	88.92 120	96.24 108	91.23 89	83.30 84	87.20 115	81.96 58	68.06 146	69.31 145	90.34 86	93.95 71	93.10 92	98.33 71	97.67 120

casdiffmvs_mvg		87.64 88	86.46 116	89.01 72	89.45 109	96.09 115	92.69 69	83.42 75	84.60 140	80.01 82	68.55 143	70.29 139	90.51 82	93.93 72	93.59 77	97.96 104	98.18 93
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	88.62 133	96.01 120	90.12 119	82.94 100	91.56 84	79.86 84	73.01 109	68.92 149	89.06 117	90.03 144	92.46 101	97.94 106	98.66 68

ET-MVSNet_ETH3D		87.63 89	91.08 61	83.59 144	67.96 254	96.30 103	92.06 73	78.47 148	91.95 77	69.87 151	87.57 46	84.14 86	94.34 34	88.58 160	92.10 106	98.88 34	96.93 141

DI_MVS_pp		87.63 89	87.13 103	88.22 87	88.61 134	95.92 123	94.09 59	81.41 117	87.00 117	78.38 113	59.70 188	80.52 95	89.08 116	94.37 62	93.34 83	97.73 116	99.05 49

casdiffmvs		87.59 92	86.69 111	88.64 77	89.06 117	96.32 102	90.18 117	83.21 88	87.74 111	80.20 77	67.99 149	68.34 158	90.79 76	93.83 74	94.08 58	98.41 62	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	88.72 129	96.07 117	89.49 129	83.05 97	90.81 87	81.13 67	71.59 122	69.71 141	88.69 123	89.50 151	92.40 102	97.16 149	99.17 41

viewmamba		87.49 94	86.97 108	88.09 94	88.73 128	95.97 121	90.04 122	82.85 102	92.44 75	78.95 102	72.17 120	68.85 150	90.31 87	88.68 158	92.23 105	97.65 123	98.42 83

PVSNet_Blended_VisFu		87.44 95	88.72 88	85.95 126	92.02 76	97.26 73	86.88 160	82.66 105	83.86 148	79.16 99	66.96 155	84.91 83	77.26 200	94.97 49	93.48 78	97.73 116	99.64 19

viewdifsd2359ckpt09		87.42 96	86.55 113	88.45 82	88.67 131	96.49 95	90.38 114	83.11 93	85.25 129	79.50 87	70.80 128	68.43 155	90.90 72	93.87 73	93.04 93	98.10 87	97.95 108

viewmanbaseed2359cas		87.26 97	86.56 112	88.07 96	89.09 115	96.64 88	90.52 111	83.44 73	85.33 127	76.94 128	70.09 134	68.98 148	90.04 95	92.85 99	94.02 61	98.40 63	98.03 102

diffmvs_AUTHOR		87.25 98	86.52 114	88.11 93	88.39 143	96.07 117	91.06 95	82.98 99	88.29 106	78.43 109	70.18 133	67.08 172	89.79 103	92.05 114	93.02 95	98.03 98	98.94 57

FMVSNet3		87.19 99	87.32 101	87.04 116	82.82 184	90.21 184	92.88 66	76.53 162	91.69 80	81.31 62	64.81 170	80.64 92	89.79 103	94.80 53	94.76 43	98.88 34	94.32 192

LS3D		87.19 99	85.48 126	89.18 67	94.96 60	95.47 131	92.02 74	93.36 28	88.69 102	67.01 158	70.56 130	72.10 130	92.47 56	89.96 145	89.93 136	95.25 213	91.68 221

ACMP	85.16 9	87.15 101	87.04 105	87.27 111	90.80 86	94.45 140	89.41 134	83.09 94	89.15 96	76.98 127	86.35 51	65.80 177	86.94 133	88.45 161	87.52 176	96.42 183	97.56 126
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
E3new		87.11 102	85.87 123	88.55 78	88.74 127	96.52 92	90.53 109	83.25 86	82.75 153	80.24 76	68.90 141	68.41 157	90.19 91	92.76 102	93.68 70	98.32 72	98.10 97

E3		87.08 103	85.87 123	88.49 80	88.75 125	96.52 92	90.53 109	83.25 86	82.74 154	79.93 83	68.88 142	68.46 154	90.18 92	92.76 102	93.66 72	98.32 72	98.10 97

UGNet		87.04 104	89.59 80	84.07 139	90.94 85	95.95 122	86.02 167	81.65 114	85.94 123	78.54 107	78.00 77	85.40 80	69.62 225	91.83 116	91.53 112	97.63 126	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	88.81 124	96.63 90	89.75 125	83.30 84	85.16 132	77.32 122	69.27 138	67.96 160	90.14 93	93.53 80	93.67 71	98.09 91	97.74 117

LGP-MVS_train		86.95 106	87.65 95	86.12 121	91.77 79	93.84 146	93.04 65	82.77 103	88.04 108	65.33 163	87.69 45	67.09 171	86.79 134	90.20 141	88.99 156	97.05 152	97.71 118

PatchMatch-RL		86.75 107	85.43 128	88.29 86	94.06 65	96.37 100	86.82 161	82.94 100	88.94 99	79.59 86	79.83 73	59.17 200	89.46 108	91.12 127	88.81 160	96.88 156	93.78 201

FA-MVS(training)		86.74 108	88.01 93	85.26 133	89.86 101	96.99 80	88.54 142	64.26 242	89.04 97	81.30 65	66.74 157	81.52 90	89.11 115	94.04 69	90.37 126	98.47 56	97.37 130

viewmambaseed2359dif		86.69 109	85.42 129	88.17 90	88.54 136	95.67 125	90.98 99	82.71 104	86.36 122	80.14 78	68.41 144	68.31 159	89.91 98	87.78 168	92.27 104	96.75 161	99.13 46

baseline2		86.51 110	89.35 84	83.19 146	85.70 169	94.88 135	85.75 172	77.13 157	89.87 92	70.65 148	79.03 74	79.14 100	81.51 172	93.70 76	90.22 129	98.38 67	98.60 71

viewdifsd2359ckpt07		86.50 111	85.45 127	87.72 103	88.88 122	96.19 109	89.63 126	83.34 82	81.97 159	78.44 108	67.87 151	68.43 155	87.74 127	93.68 77	93.13 91	98.27 75	96.88 143

thres100view900		86.48 112	85.08 132	88.12 92	90.54 87	96.90 82	92.39 70	84.82 67	84.16 146	71.65 141	70.86 125	60.49 195	91.23 68	93.65 78	90.19 131	98.10 87	99.32 28

ACMM	84.23 10	86.40 113	84.64 140	88.46 81	91.90 77	91.93 173	88.11 147	85.59 64	88.61 103	79.13 100	75.31 91	66.25 175	89.86 102	89.88 146	87.64 173	96.16 196	92.86 210
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	88.52 137	96.26 104	90.68 106	83.36 78	79.90 171	78.40 110	66.52 158	67.18 169	90.01 96	91.82 117	93.64 73	98.22 76	97.98 105

E5		86.34 114	84.76 136	88.20 88	88.52 137	96.26 104	90.68 106	83.36 78	79.90 171	78.40 110	66.52 158	67.18 169	90.01 96	91.82 117	93.64 73	98.22 76	97.98 105

dtuplus		86.22 116	84.66 139	88.03 98	88.31 147	95.62 128	90.41 113	82.64 106	82.92 152	80.07 81	67.05 154	68.49 153	90.23 89	87.56 170	92.10 106	96.49 180	98.90 58

GBi-Net		86.16 117	86.00 120	86.35 118	81.81 191	89.52 193	91.40 82	76.53 162	91.69 80	81.31 62	64.81 170	80.64 92	88.72 119	90.54 132	90.72 119	98.34 68	94.08 193

test1		86.16 117	86.00 120	86.35 118	81.81 191	89.52 193	91.40 82	76.53 162	91.69 80	81.31 62	64.81 170	80.64 92	88.72 119	90.54 132	90.72 119	98.34 68	94.08 193

E4		86.15 119	84.60 141	87.96 100	88.52 137	96.25 106	90.25 116	83.05 97	79.58 174	78.14 115	66.12 161	67.23 167	89.62 105	91.68 119	93.43 80	98.20 79	97.93 109

tfpn200view9		86.07 120	84.76 136	87.61 106	90.54 87	96.39 97	91.35 85	83.15 89	84.16 146	71.65 141	70.86 125	60.49 195	90.91 71	92.89 95	89.34 144	98.05 95	99.17 41

DCV-MVSNet		85.90 121	85.88 122	85.93 127	87.86 152	88.37 210	89.45 133	77.46 156	87.33 114	77.51 120	76.06 83	75.76 113	88.48 124	87.40 172	88.89 159	94.80 222	97.37 130

Vis-MVSNet (Re-imp)		85.89 122	89.62 79	81.55 158	89.85 103	96.08 116	87.55 152	79.80 130	84.80 137	66.55 160	73.70 103	86.71 65	68.25 232	94.40 60	94.53 47	97.32 143	97.09 139

MSDG		85.81 123	82.29 168	89.93 61	95.52 57	92.61 162	91.51 81	91.46 41	85.12 133	78.56 105	63.25 177	69.01 147	85.31 143	88.45 161	88.23 165	97.21 147	89.33 233

thres200		85.80 124	84.38 143	87.46 109	90.51 89	96.39 97	91.64 78	83.15 89	81.59 163	71.54 143	70.24 131	60.41 197	89.88 100	92.89 95	89.85 139	98.06 93	99.26 33

E6new		85.77 125	84.30 145	87.49 107	88.49 141	96.18 110	89.47 131	81.93 112	79.29 175	77.66 117	65.72 162	66.80 173	89.17 112	91.36 123	92.90 97	98.19 81	97.84 112

E6		85.77 125	84.30 145	87.49 107	88.49 141	96.18 110	89.47 131	81.93 112	79.29 175	77.66 117	65.72 162	66.80 173	89.17 112	91.36 123	92.90 97	98.19 81	97.84 112

ECVR-MVS		85.74 127	83.80 153	88.00 99	91.55 81	97.78 64	90.87 103	83.36 78	84.51 142	78.21 114	58.65 193	62.75 189	85.39 140	94.34 64	93.33 85	98.60 46	95.25 178

viewmacassd2359aftdt		85.71 128	84.41 142	87.22 112	88.63 132	96.25 106	90.16 118	83.07 96	79.77 173	74.57 137	65.34 164	67.22 168	88.71 122	90.93 129	93.61 75	98.20 79	97.77 115

OPM-MVS		85.69 129	82.79 161	89.06 70	93.42 68	94.21 144	94.21 58	87.61 50	72.68 197	70.79 147	71.09 123	67.27 166	90.74 77	91.29 125	89.05 155	97.61 128	93.94 198
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 92	96.60 91	90.95 101	83.67 72	80.99 167	71.17 144	69.08 140	60.25 198	89.88 100	93.14 88	89.34 144	98.02 99	99.17 41

0.3-1-1-0.015		85.55 131	85.15 131	86.02 124	78.77 212	93.03 157	91.14 94	80.95 122	88.71 101	79.50 87	73.18 108	73.11 117	89.48 107	83.59 205	88.42 163	96.29 189	96.01 162

0.4-1-1-0.2		85.51 132	85.07 133	86.02 124	78.76 213	93.04 156	91.17 91	81.04 121	88.53 104	79.46 92	72.62 115	73.05 121	89.37 110	83.67 204	88.56 162	96.31 186	96.03 161

CostFormer		85.47 133	86.98 107	83.71 142	88.70 130	94.02 145	88.07 148	62.72 244	89.78 93	78.68 104	72.69 113	78.37 105	87.35 130	85.96 185	89.32 148	96.73 164	98.72 62

0.4-1-1-0.1		85.32 134	84.89 134	85.83 129	78.73 214	93.00 158	90.99 98	80.42 126	88.43 105	79.41 93	72.22 119	73.05 121	89.17 112	83.43 209	88.14 166	96.24 192	95.94 164

test1111		85.17 135	83.46 156	87.17 113	91.36 83	97.75 66	90.06 121	83.44 73	83.41 150	75.25 134	58.08 197	62.19 191	84.39 150	94.39 61	93.38 82	98.54 52	95.00 187

thres600view7		85.14 136	83.58 155	86.96 117	90.37 96	96.39 97	90.33 115	83.15 89	80.46 168	70.60 150	67.96 150	60.04 199	89.22 111	92.89 95	88.28 164	98.06 93	99.08 48

test-LLR		85.11 137	89.49 82	80.00 168	85.32 173	94.49 138	82.27 203	74.18 177	87.83 109	56.70 196	75.55 88	86.26 67	82.75 165	93.06 90	90.60 124	98.77 40	98.65 69

FMVSNet2		84.89 138	84.02 150	85.91 128	81.81 191	89.52 193	91.40 82	75.79 168	84.45 144	79.39 95	58.75 191	74.35 115	88.72 119	93.51 83	93.46 79	98.34 68	94.08 193

FC-MVSNet-train		84.88 139	84.08 148	85.82 130	89.21 112	91.74 174	85.87 168	81.20 120	81.71 162	74.66 136	73.38 105	64.99 181	86.60 135	90.75 130	88.08 167	97.36 141	97.90 110

EPNet_dtu		84.87 140	89.01 85	80.05 167	95.25 59	92.88 160	88.84 139	84.11 68	91.69 80	49.28 235	85.69 54	78.95 103	65.39 237	92.22 113	91.66 111	97.43 138	89.95 229
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	87.94 151	95.76 124	90.08 120	73.45 192	85.12 133	62.66 172	72.39 117	64.97 182	90.59 80	92.95 94	90.69 122	97.67 120	98.12 95

UA-Net		84.69 142	87.64 96	81.25 160	90.38 95	95.67 125	87.33 156	79.41 139	72.07 201	66.48 161	75.09 92	92.48 44	66.88 233	94.03 70	94.25 54	97.01 155	89.88 230

TESTMET0.1,1		84.62 143	89.49 82	78.94 178	82.18 188	94.49 138	82.27 203	70.94 212	87.83 109	56.70 196	75.55 88	86.26 67	82.75 165	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 67	98.23 55	89.91 124	77.96 151	84.81 136	65.93 162	45.19 247	71.76 134	83.13 163	95.46 39	95.13 37	98.94 28	99.53 23

casdiffseed414692147		84.37 145	81.97 172	87.16 115	88.39 143	95.36 132	89.17 136	81.64 115	78.81 179	77.31 123	60.13 186	61.16 193	88.91 118	89.68 148	91.85 109	97.54 132	96.81 146

Anonymous20231211		84.23 146	81.71 176	87.17 113	87.38 161	93.59 149	88.95 138	82.14 110	83.82 149	78.56 105	48.09 239	73.89 116	91.25 67	86.38 179	88.06 169	94.74 223	98.14 94

MDTV_nov1_ep13		84.17 147	88.03 91	79.66 170	86.00 167	94.41 141	85.05 174	66.01 238	90.36 89	64.34 168	77.13 82	84.56 84	82.71 167	87.12 176	88.92 157	93.84 237	93.69 204

test-mter		84.06 148	89.00 86	78.29 183	81.92 189	94.23 143	81.07 213	70.38 217	87.12 116	56.10 206	74.75 93	85.80 73	81.81 171	92.52 106	90.10 133	98.43 60	98.49 79

viewdifsd2359ckpt11		83.97 149	82.19 169	86.05 122	87.69 156	93.13 153	86.43 163	82.38 108	82.00 158	79.38 96	68.06 146	64.36 186	87.13 131	83.72 203	86.86 182	93.31 243	97.22 134

viewmsd2359difaftdt		83.97 149	82.19 169	86.04 123	87.69 156	93.13 153	86.43 163	82.37 109	81.93 160	79.33 97	68.06 146	64.40 185	87.12 132	83.73 202	86.86 182	93.31 243	97.22 134

IB-MVS	79.58 12	83.83 151	84.81 135	82.68 150	91.85 78	97.35 71	75.75 238	82.57 107	86.55 120	84.01 46	70.90 124	65.43 179	63.18 245	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	89.72 106	95.64 127	84.68 175	59.73 249	89.61 95	62.67 171	72.65 114	81.80 89	86.22 137	86.23 181	88.03 170	97.96 104	93.35 206

HyFIR lowres test		83.43 153	82.94 159	84.01 140	93.41 69	97.10 76	87.21 157	74.04 180	80.15 170	64.98 164	41.09 256	76.61 110	86.51 136	93.31 85	93.01 96	97.91 112	99.30 31

PatchmatchNet		83.28 154	87.57 97	78.29 183	87.46 159	94.95 133	83.36 185	59.43 252	90.20 91	58.10 191	74.29 96	86.20 69	84.13 153	85.27 191	87.39 177	97.25 146	94.67 190
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	87.45 160	92.20 168	82.63 199	58.42 254	90.30 90	58.23 189	75.74 87	87.75 60	83.97 156	86.10 184	87.64 173	97.30 144	94.62 191

GeoE		83.17 156	82.86 160	83.53 145	87.24 162	93.78 147	87.94 149	72.75 197	82.19 157	69.76 152	60.54 184	65.95 176	86.01 138	89.41 152	89.72 141	97.47 134	98.43 82

CDS-MVSNet		83.13 157	83.73 154	82.43 156	84.52 178	92.92 159	88.26 144	77.67 154	72.08 200	69.08 155	66.96 155	74.66 114	78.61 186	90.70 131	91.96 108	96.46 182	96.86 144
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	88.25 148	88.32 211	87.67 150	80.86 125	84.78 138	76.57 131	85.56 55	76.00 112	84.61 148	78.20 240	76.52 245	86.81 262	83.63 254

Vis-MVSNet		82.88 159	86.04 119	79.20 176	87.77 155	96.42 96	86.10 166	76.70 159	74.82 191	61.38 175	70.70 129	77.91 106	64.83 239	93.22 86	93.19 90	98.43 60	96.01 162
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	87.81 154	92.81 161	84.39 177	61.96 245	86.43 121	81.63 59	69.72 136	67.60 164	84.42 149	82.51 218	83.90 216	95.52 207	95.50 175

IterMVS-LS		82.62 161	82.75 163	82.48 153	87.09 163	87.48 224	87.19 158	72.85 195	79.09 177	66.63 159	65.22 165	72.14 129	84.06 155	88.33 164	91.39 114	97.03 154	95.60 174
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	85.49 172	93.06 155	87.17 159	71.39 209	84.18 145	64.59 166	63.03 178	58.89 201	90.22 90	91.39 122	90.83 118	97.44 136	96.21 159

tpm cat1		82.39 163	82.32 167	82.47 154	88.13 149	92.42 166	87.43 153	62.79 243	85.30 128	78.05 116	60.14 185	72.10 130	83.20 162	82.26 221	85.67 195	95.23 214	98.35 87

dmvs_re		82.31 164	81.55 177	83.19 146	83.15 183	93.17 152	88.68 141	83.72 70	82.73 155	61.70 173	67.43 153	55.43 214	83.35 161	87.51 171	89.27 151	98.56 50	95.31 177

MS-PatchMatch		82.16 165	82.18 171	82.12 157	91.65 80	93.50 150	89.51 128	71.95 203	81.48 164	64.45 167	59.58 190	77.54 107	77.23 201	89.88 146	85.62 196	97.94 106	87.68 237

blend_shiyan4		81.76 166	80.92 182	82.74 148	79.07 209	85.29 236	91.60 80	74.15 179	89.00 98	79.50 87	73.82 99	73.11 117	77.73 194	77.73 242	75.18 248	94.37 226	92.34 213

tpmrst		81.71 167	83.87 152	79.20 176	89.01 118	93.67 148	84.22 178	60.14 247	87.45 112	59.49 179	64.97 168	71.86 133	85.30 144	84.72 195	86.30 187	97.04 153	98.09 99

RPMNet		81.47 168	86.24 118	75.90 208	86.72 164	92.12 170	82.82 197	55.76 261	85.21 130	53.73 217	63.45 175	83.16 87	80.13 180	92.34 110	89.52 142	96.23 194	97.90 110

CR-MVSNet		81.44 169	85.29 130	76.94 199	86.53 165	92.12 170	83.86 179	58.37 255	85.21 130	56.28 201	59.60 189	80.39 96	80.50 177	92.77 100	89.32 148	96.12 198	97.59 124

Effi-MVS+-dtu		81.18 170	82.77 162	79.33 174	84.70 177	92.54 164	85.81 169	71.55 207	78.84 178	57.06 195	71.98 121	63.77 187	85.09 145	88.94 156	87.62 175	91.79 254	95.68 169

test0.0.03 1		80.99 171	84.37 144	77.05 197	85.32 173	89.79 189	78.43 229	74.18 177	84.78 138	57.98 194	76.06 83	72.88 125	69.14 229	88.02 166	87.70 171	97.27 145	91.37 222

dtuonly		80.91 172	81.25 181	80.52 164	82.54 185	91.09 177	87.43 153	75.69 171	77.28 183	56.58 199	58.23 195	67.55 165	85.08 146	89.06 155	89.42 143	95.80 203	96.10 160

Fast-Effi-MVS+-dtu		80.57 173	83.44 157	77.22 195	83.98 181	91.52 176	85.78 171	64.54 241	80.38 169	50.28 231	74.06 98	62.89 188	82.00 170	89.10 154	88.91 158	96.75 161	97.21 137

FMVSNet5		80.56 174	82.53 165	78.26 185	73.80 246	81.52 254	82.26 205	68.36 229	88.85 100	64.21 169	69.09 139	84.38 85	83.49 160	87.13 175	86.76 184	97.44 136	79.95 258

ADS-MVSNet		80.25 175	82.96 158	77.08 196	87.86 152	92.60 163	81.82 210	56.19 260	86.95 118	56.16 204	68.19 145	72.42 128	83.70 159	82.05 222	85.45 201	96.75 161	93.08 209

FMVSNet1		80.18 176	78.07 191	82.65 151	78.55 219	87.57 223	88.41 143	73.93 185	70.16 206	73.57 138	49.80 228	64.45 184	85.35 142	90.54 132	90.72 119	96.10 199	93.21 207

USDC		80.10 177	79.33 187	81.00 162	86.36 166	91.71 175	88.74 140	75.77 169	81.90 161	54.90 211	67.67 152	52.05 220	83.94 157	88.44 163	86.25 188	96.31 186	87.28 241

COLMAP_ROB	75.69 15	79.47 178	76.90 200	82.46 155	92.20 73	90.53 180	85.30 173	83.69 71	78.27 182	61.47 174	58.26 194	62.75 189	78.28 189	82.41 219	82.13 229	93.83 239	83.98 253
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	80.18 200	88.96 205	83.39 183	76.07 165	81.27 165	69.35 153	58.66 192	51.19 223	82.01 169	87.16 174	84.39 213	95.66 204	92.82 211

PatchT		79.28 180	83.88 151	73.93 221	85.54 171	90.95 178	66.14 258	56.53 259	83.21 151	56.28 201	56.50 200	76.80 109	80.50 177	92.77 100	89.32 148	98.57 49	97.59 124

ACMH	78.51 14	79.27 181	78.08 190	80.65 163	89.52 108	90.40 181	80.45 220	79.77 132	69.54 211	54.85 212	64.83 169	56.16 212	83.94 157	84.58 197	86.01 192	95.41 210	95.03 186
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	81.89 190	92.52 165	82.97 192	73.70 186	67.27 224	64.97 165	61.66 183	65.06 180	78.61 186	87.12 176	88.07 168	95.23 214	90.95 224

ACMH+	79.09 13	79.12 183	77.22 199	81.35 159	88.50 140	90.36 182	82.14 207	79.38 141	72.78 196	58.59 186	62.31 182	56.44 211	84.10 154	82.03 223	84.05 214	95.40 211	92.55 212

usedtu_dtu_shiyan1		79.10 184	79.87 184	78.20 187	71.16 248	90.83 179	84.41 176	78.54 146	81.24 166	58.78 185	56.79 199	61.56 192	78.74 185	90.08 142	87.70 171	97.59 129	90.90 225

UniMVSNet_NR-MVSNet		78.89 185	78.04 192	79.88 169	79.40 206	89.70 190	82.92 194	80.17 127	76.37 189	58.56 187	57.10 198	54.92 215	81.44 173	83.51 208	87.12 179	96.76 160	97.60 122

tpm		78.87 186	81.33 180	76.00 206	85.57 170	90.19 185	82.81 198	59.66 250	78.35 181	51.40 226	66.30 160	67.92 161	80.94 175	83.28 212	85.73 193	95.65 205	97.56 126

GA-MVS		78.86 187	80.42 183	77.05 197	83.27 182	92.17 169	83.24 187	75.73 170	73.75 193	46.27 246	62.43 180	57.12 204	76.94 203	93.14 88	89.34 144	96.83 157	95.00 187

IterMVS		78.85 188	81.36 178	75.93 207	84.27 180	85.74 230	83.83 181	66.35 236	76.82 184	50.48 229	63.48 174	68.82 151	73.99 212	89.68 148	89.34 144	96.63 170	95.67 170
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	84.31 179	85.67 231	83.51 182	66.14 237	76.67 185	50.38 230	63.45 175	69.02 146	73.23 215	89.66 150	89.22 152	96.24 192	95.67 170

usedtu_blend_shiyan5		78.69 190	77.98 193	79.53 172	60.42 258	84.96 239	91.21 90	73.97 181	69.27 213	79.50 87	73.82 99	73.11 117	77.73 194	77.31 246	75.07 249	94.33 229	92.34 213

UniMVSNet (Re)		78.00 191	77.52 196	78.57 181	79.66 205	90.36 182	82.09 208	77.86 153	76.38 188	60.26 176	54.63 206	52.07 219	75.31 210	84.97 194	86.10 190	96.22 195	98.11 96

DU-MVS		77.98 192	76.71 201	79.46 173	78.68 216	89.26 199	82.92 194	79.06 143	76.52 186	58.56 187	54.89 204	48.35 237	81.44 173	83.16 214	87.21 178	96.08 200	97.60 122

FC-MVSNet-test		77.95 193	81.85 174	73.39 227	82.31 186	88.99 204	79.33 225	74.24 176	78.75 180	47.40 244	70.22 132	72.09 132	60.78 252	86.66 178	85.62 196	96.30 188	90.61 226

FE-MVSNET3		77.89 194	77.94 194	77.83 191	60.42 258	84.96 239	81.04 214	73.97 181	69.27 213	79.50 87	73.82 99	73.11 117	77.73 194	77.31 246	75.07 249	94.33 229	92.02 217

NR-MVSNet		77.21 195	76.41 202	78.14 188	80.18 200	89.26 199	83.38 184	79.06 143	76.52 186	56.59 198	54.89 204	45.32 247	72.89 217	85.39 190	86.12 189	96.71 165	97.36 132

thisisatest0515		77.13 196	79.36 186	74.52 214	79.79 204	89.65 191	73.54 243	73.69 187	74.10 192	58.14 190	62.79 179	60.57 194	66.49 235	88.08 165	85.16 206	95.49 209	95.15 182

gg-mvs-nofinetune		77.08 197	79.79 185	73.92 222	85.95 168	97.23 74	92.18 72	52.65 264	46.19 269	27.79 273	38.27 260	85.63 74	85.67 139	96.95 20	95.62 27	99.30 3	98.67 67

TranMVSNet+NR-MVSNet		77.02 198	75.76 204	78.49 182	78.46 222	88.24 212	83.03 191	79.97 128	73.49 195	54.73 213	54.00 209	48.74 232	78.15 191	82.36 220	86.90 181	96.59 172	96.55 151

CVMVSNet		76.86 199	79.09 188	74.26 217	85.29 175	89.44 196	79.91 224	78.47 148	68.94 220	44.45 254	62.35 181	69.70 142	64.50 241	85.82 186	87.03 180	92.94 248	90.33 227

Baseline_NR-MVSNet		76.71 200	74.56 211	79.23 175	78.68 216	84.15 247	82.45 201	78.87 145	75.83 190	60.05 177	47.92 240	50.18 229	79.06 184	83.16 214	83.86 217	96.26 190	96.80 147

v2v482		76.25 201	74.78 208	77.96 190	78.50 221	89.14 202	83.05 190	76.02 166	68.78 221	54.11 214	51.36 220	48.59 234	79.49 182	83.53 207	85.60 199	96.59 172	96.49 156

V42		76.21 202	75.04 207	77.58 192	78.68 216	89.33 198	82.93 193	74.64 174	69.84 208	56.13 205	50.42 225	50.93 224	76.30 209	83.32 210	84.89 210	96.83 157	96.54 152

v8		75.89 203	74.74 209	77.23 194	79.09 208	88.00 215	83.19 188	71.08 211	70.03 207	56.29 200	50.50 223	50.88 225	77.06 202	83.32 210	84.99 208	96.68 166	95.49 176

TinyColmap		75.75 204	73.19 222	78.74 180	84.82 176	87.69 219	81.59 211	74.62 175	71.81 202	54.01 215	55.79 203	44.42 253	82.89 164	84.61 196	83.76 218	94.50 224	84.22 252

MIMVSNet		75.71 205	77.26 197	73.90 223	70.93 249	88.71 208	79.98 223	57.67 258	73.58 194	58.08 193	53.93 210	58.56 202	79.41 183	90.04 143	89.97 134	97.34 142	86.04 242

UniMVSNet_ETH3D		75.63 206	71.59 236	80.35 165	81.03 195	89.90 188	83.25 186	76.58 161	60.08 246	64.19 170	42.89 255	45.01 249	82.14 168	80.20 233	86.75 185	94.90 219	96.29 158

pm-mvs1		75.61 207	74.19 213	77.26 193	80.16 202	88.79 206	81.49 212	75.49 173	59.49 248	58.09 192	48.32 236	55.53 213	72.35 218	88.61 159	85.48 200	95.99 201	93.12 208

v10		75.57 208	74.67 210	76.62 202	78.73 214	87.46 225	83.14 189	69.41 224	69.27 213	53.44 218	49.73 229	49.21 231	78.44 188	86.17 183	85.18 205	96.53 177	95.65 173

v1144		75.54 209	74.55 212	76.69 200	78.33 225	88.77 207	82.89 196	72.76 196	67.18 226	51.73 223	49.34 231	48.37 235	78.10 192	86.22 182	85.24 203	96.35 185	96.74 148

TDRefinement		75.54 209	73.22 220	78.25 186	87.65 158	89.65 191	85.81 169	79.28 142	71.14 204	56.06 207	52.17 218	51.96 221	68.74 231	81.60 224	80.58 232	91.94 251	85.45 243

pmmvs5		75.46 211	75.12 206	75.87 209	79.39 207	89.44 196	78.12 231	72.27 201	65.98 231	51.54 224	55.83 202	46.23 242	76.80 206	88.77 157	85.73 193	97.07 151	93.84 199

tfpnnormal		75.27 212	72.12 233	78.94 178	82.30 187	88.52 209	82.41 202	79.41 139	58.03 250	55.59 209	43.83 254	44.71 250	77.35 198	87.70 169	85.45 201	96.60 171	96.61 150

anonymousdsp		75.14 213	77.25 198	72.69 230	76.68 235	89.26 199	75.26 240	68.44 228	65.53 234	46.65 245	58.16 196	56.67 206	73.96 213	87.84 167	86.05 191	95.13 217	97.22 134

v148		74.98 214	73.52 218	76.69 200	78.84 211	89.02 203	78.78 227	76.82 158	67.22 225	59.61 178	49.18 232	47.94 239	70.57 224	80.76 228	83.99 215	95.52 207	96.52 154

v1192		74.96 215	73.92 214	76.17 203	77.76 228	88.19 214	82.54 200	71.94 204	66.84 227	50.07 233	48.10 238	46.14 243	78.28 189	86.30 180	85.23 204	96.41 184	96.67 149

v144192		74.76 216	73.64 215	76.06 205	77.58 229	88.23 213	81.87 209	71.63 206	66.03 230	51.08 227	48.63 235	46.77 241	77.59 197	84.53 198	84.76 211	96.64 169	96.54 152

v1921920		74.60 217	73.56 217	75.81 210	77.43 231	87.94 216	82.18 206	71.33 210	66.48 229	49.23 237	47.84 241	45.56 245	78.03 193	85.70 188	84.92 209	96.65 167	96.50 155

v1240		74.04 218	73.04 224	75.20 213	77.19 233	87.69 219	80.93 217	70.72 216	65.08 235	48.47 239	47.31 242	44.71 250	77.33 199	85.50 189	85.07 207	96.59 172	95.94 164

wanda-best-256-512		73.38 219	72.60 227	74.28 215	60.42 258	84.96 239	81.04 214	73.97 181	69.27 213	59.09 182	52.95 213	56.56 207	76.85 204	77.31 246	75.07 249	94.33 229	92.05 215

FE-blended-shiyan7		73.37 220	72.59 228	74.28 215	60.42 258	84.96 239	81.04 214	73.97 181	69.28 212	59.09 182	52.95 213	56.54 208	76.85 204	77.31 246	75.07 249	94.33 229	92.05 215

blended_shiyan8		73.25 221	72.48 229	74.14 219	60.35 262	84.93 243	80.84 218	73.55 190	69.25 217	59.22 181	52.62 216	56.47 210	76.66 207	77.19 251	74.92 254	94.23 233	91.94 219

blended_shiyan6		73.22 222	72.48 229	74.09 220	60.31 263	84.90 244	80.80 219	73.54 191	69.06 219	59.06 184	52.69 215	56.53 209	76.59 208	77.20 250	74.94 253	94.22 234	92.02 217

testgi		73.22 222	75.84 203	70.16 241	81.67 194	85.50 234	71.45 245	70.81 214	69.56 210	44.74 253	74.52 95	49.25 230	58.45 253	84.10 201	83.37 222	93.86 236	84.56 250

gbinet_0.2-2-1-0.02		73.19 224	72.88 225	73.56 225	60.07 264	84.50 246	80.22 222	73.59 189	67.33 223	59.36 180	52.21 217	58.21 203	73.76 214	77.60 243	75.19 247	94.37 226	95.12 183

CP-MVSNet		73.19 224	72.37 231	74.15 218	77.54 230	86.77 228	76.34 234	72.05 202	65.66 233	51.47 225	50.49 224	43.66 254	70.90 220	80.93 227	83.40 221	96.59 172	95.66 172

WR-MVS		72.93 226	73.57 216	72.19 233	78.14 226	87.71 218	76.21 236	73.02 194	67.78 222	50.09 232	50.35 226	50.53 227	61.27 251	80.42 231	83.10 225	94.43 225	95.11 184

TransMVSNet (Re)		72.90 227	70.51 240	75.69 211	80.88 196	85.26 237	79.25 226	78.43 150	56.13 257	52.81 220	46.81 244	48.20 238	66.77 234	85.18 193	83.70 219	95.98 202	88.28 236

WR-MVS_H		72.69 228	72.80 226	72.56 232	77.94 227	87.83 217	75.26 240	71.53 208	64.75 236	52.19 222	49.83 227	48.62 233	61.96 249	81.12 226	82.44 227	96.50 178	95.00 187

SixPastTwentyTwo		72.65 229	73.22 220	71.98 236	78.40 223	87.64 221	70.09 248	70.37 218	66.49 228	47.60 242	65.09 166	45.94 244	73.09 216	78.94 235	78.66 239	92.33 249	89.82 231

LTVRE_ROB	71.82 16	72.62 230	71.77 234	73.62 224	80.74 197	87.59 222	80.42 221	70.37 218	49.73 262	37.12 266	59.76 187	42.52 259	80.92 176	83.20 213	85.61 198	92.13 250	93.95 197
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	77.32 232	86.43 229	75.99 237	71.94 204	63.37 239	49.24 236	49.07 233	42.42 260	69.60 226	80.59 230	83.18 224	96.48 181	95.23 180

MVS-HIRNet		72.32 232	73.45 219	71.00 239	80.58 198	89.97 186	68.51 253	55.28 262	70.89 205	52.27 221	39.09 258	57.11 205	75.02 211	85.76 187	86.33 186	94.36 228	85.00 247

PEN-MVS		72.24 233	71.30 239	73.33 228	77.08 234	85.57 232	76.75 232	72.52 199	63.89 238	48.12 240	50.79 221	43.09 257	69.03 230	78.54 237	83.46 220	96.50 178	93.76 202

v7n		72.11 234	71.66 235	72.63 231	75.26 241	86.85 226	76.74 233	68.77 227	62.70 242	49.40 234	45.92 246	43.51 255	70.63 223	84.16 200	83.21 223	94.99 218	95.25 178

EG-PatchMatch MVS		71.81 235	71.54 237	72.12 234	80.53 199	89.94 187	78.51 228	66.56 235	57.38 252	47.46 243	44.28 253	52.22 218	63.10 246	85.22 192	84.42 212	96.56 176	87.35 240

CMPMVS	54.54 17	71.74 236	67.94 245	76.16 204	90.41 93	93.25 151	78.32 230	75.60 172	59.81 247	53.95 216	44.64 250	51.22 222	70.70 221	74.59 256	75.88 246	88.01 259	76.23 261
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	75.22 242	86.81 227	73.98 242	59.61 251	69.75 209	48.01 241	54.21 208	53.06 217	69.19 228	78.50 238	80.43 233	93.84 237	88.79 234

pmnet_mix02		71.64 238	72.36 232	70.81 240	78.39 224	85.57 232	68.64 251	73.65 188	72.13 198	45.07 252	56.01 201	50.61 226	65.34 238	76.21 252	76.60 244	93.75 240	89.35 232

gm-plane-assit		71.33 239	75.18 205	66.83 246	79.06 210	75.57 262	48.05 271	60.33 246	48.28 263	34.67 270	44.34 252	67.70 163	79.78 181	97.25 13	96.21 14	99.10 11	96.92 142

DTE-MVSNet		71.19 240	70.45 241	72.06 235	76.61 236	84.59 245	75.61 239	72.32 200	63.12 241	45.70 250	50.72 222	43.02 258	65.89 236	77.53 245	82.23 228	96.26 190	91.93 220

pmmvs6		70.29 241	67.90 246	73.07 229	76.17 238	85.31 235	76.29 235	70.75 215	47.39 265	55.33 210	37.15 264	50.49 228	69.55 227	82.96 216	80.85 231	90.34 258	91.18 223

PM-MVS		70.17 242	69.42 243	71.04 238	70.82 250	81.26 256	71.25 246	67.80 231	69.16 218	51.04 228	53.15 212	34.93 267	72.19 219	80.30 232	76.95 243	93.16 247	90.21 228

pmmvs-eth3d		69.59 243	67.57 248	71.95 237	70.04 252	80.05 257	71.48 244	70.00 222	62.57 243	55.99 208	44.92 248	35.73 265	70.64 222	81.56 225	79.69 234	93.55 241	88.43 235

N_pmnet		68.54 244	67.83 247	69.38 243	75.77 239	81.90 253	66.21 257	72.53 198	65.91 232	46.09 247	44.67 249	45.48 246	63.82 244	74.66 255	77.39 242	91.87 253	84.77 249

Anonymous20231206		68.09 245	68.68 244	67.39 245	75.16 243	82.55 248	69.33 250	70.06 221	63.34 240	42.28 257	37.91 262	43.12 256	52.67 256	83.56 206	82.71 226	94.84 221	87.59 238

EU-MVSNet		68.07 246	70.25 242	65.52 248	74.68 245	81.30 255	68.53 252	70.31 220	62.40 245	37.43 265	54.62 207	48.36 236	51.34 258	78.32 239	79.27 236	90.84 255	87.47 239

dtuonlycased		66.81 247	65.49 251	68.34 244	70.60 251	82.21 251	66.95 255	68.30 230	62.57 243	48.64 238	46.62 245	53.65 216	64.78 240	62.62 261	65.70 262	90.79 256	85.07 245

FE-MVSNET2		65.87 248	65.40 252	66.41 247	56.18 267	82.03 252	69.83 249	68.97 225	56.64 255	45.42 251	31.48 267	37.87 263	62.52 248	82.96 216	81.55 230	95.56 206	85.28 244

GG-mvs-BLEND		65.67 249	93.78 43	32.89 264	0.47 280	99.35 10	96.92 36	0.22 277	93.28 65	0.51 282	84.07 59	92.50 43	0.62 279	93.59 79	93.86 64	98.59 48	99.79 10

test20.03		65.17 250	67.41 249	62.55 250	75.35 240	79.31 258	62.22 260	68.83 226	56.50 256	35.35 269	51.97 219	44.70 252	40.01 264	80.69 229	79.25 237	93.55 241	79.47 260

MDA-MVSNet-bldmvs		62.23 251	61.13 256	63.52 249	58.94 265	82.44 249	60.71 264	73.28 193	57.22 253	38.42 263	49.63 230	27.64 275	62.83 247	54.98 265	74.16 255	86.96 261	81.83 257

new_pmnet		61.60 252	62.68 253	60.35 253	63.02 255	74.93 263	60.97 263	58.86 253	64.21 237	35.38 268	39.51 257	39.89 261	57.37 254	72.78 257	72.56 257	86.49 263	74.85 263

FE-MVSNET		61.22 253	62.61 254	59.59 255	48.81 269	75.79 261	61.96 261	67.51 232	52.39 260	34.04 271	33.16 266	37.64 264	52.00 257	77.89 241	79.39 235	93.22 245	82.04 256

new-patchmatchnet		60.74 254	59.78 258	61.87 251	69.52 253	76.67 260	57.99 267	65.78 239	52.63 259	38.47 262	38.08 261	32.92 270	48.88 261	68.50 258	69.87 258	90.56 257	79.75 259

pmmvs3		60.52 255	60.87 257	60.12 254	61.38 256	71.62 265	57.42 268	53.94 263	48.09 264	35.95 267	38.62 259	32.19 273	64.12 242	75.33 253	77.99 240	87.89 260	82.28 255

MIMVSNet1		60.51 256	61.43 255	59.44 256	48.75 270	77.21 259	60.98 262	66.84 234	52.09 261	38.74 261	29.29 269	39.40 262	48.08 262	77.60 243	78.87 238	93.22 245	75.56 262

test_method		60.40 257	66.30 250	53.52 259	37.48 275	64.10 269	55.56 269	42.45 269	71.79 203	41.87 258	33.74 265	46.80 240	61.71 250	79.18 234	73.33 256	82.01 266	95.17 181

FPMVS		56.54 258	52.82 261	60.87 252	74.90 244	67.58 268	67.69 254	65.38 240	57.86 251	41.51 259	37.83 263	34.19 268	41.21 263	55.88 264	53.09 266	74.55 269	63.31 267

usedtu_dtu_shiyan2		56.32 259	55.74 260	57.01 258	40.29 274	72.50 264	63.80 259	57.88 257	37.70 270	45.71 249	25.31 271	35.59 266	49.97 260	67.09 259	67.03 260	84.41 264	84.92 248

WB-MVS		47.20 260	51.37 262	42.35 262	71.55 247	57.66 271	32.77 275	70.86 213	47.39 265	6.95 279	48.14 237	32.52 271	12.95 275	61.73 263	61.27 263	59.00 273	50.85 273

PMVS	42.57 18	45.71 261	42.61 264	49.32 260	61.35 257	37.82 274	36.96 273	60.10 248	37.20 271	41.50 260	28.53 270	33.11 269	28.82 269	53.45 266	48.70 268	67.22 271	59.42 268
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 262	42.62 263	45.50 261	50.79 268	41.20 273	35.55 274	52.51 265	52.95 258	29.09 272	12.92 274	11.48 280	38.15 265	62.01 262	66.62 261	66.89 272	51.17 271
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	43.25 271	55.05 272	38.15 272	47.11 268	31.78 272	11.83 275	21.16 272	19.12 278	20.98 271	49.95 268	56.09 265	77.09 267	64.68 265

E-PMN		27.87 264	24.36 270	31.97 265	41.27 273	25.56 277	16.62 277	49.16 266	22.00 274	9.90 276	11.75 276	7.86 283	29.57 268	22.22 273	34.70 269	45.27 274	46.41 274

MVE	32.98 19	27.61 265	29.89 269	24.94 267	21.97 276	37.22 275	15.56 279	38.83 270	17.49 275	14.72 274	11.64 278	5.62 284	21.26 270	35.20 269	50.95 267	37.29 276	51.13 272
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS		27.53 266	41.28 266	11.50 268	6.16 277	13.25 280	11.93 281	0.81 274	58.16 249	7.91 278	73.32 106	31.49 274	15.94 274	29.06 271	26.73 272	26.23 277	56.94 269

EMVS		26.96 267	22.96 271	31.63 266	41.91 272	25.73 276	16.30 278	49.10 267	22.38 273	9.03 277	11.22 279	8.12 282	29.93 267	20.16 274	31.04 270	43.49 275	42.04 275

VLMVS_CLIP		25.63 268	39.16 267	9.86 269	6.13 278	13.35 278	12.42 280	0.89 273	46.24 268	1.87 280	64.55 173	24.38 277	16.52 273	32.19 270	29.70 271	21.31 278	63.70 266

MVS_clip		22.46 269	34.64 268	8.26 270	5.07 279	13.31 279	7.37 282	0.95 272	47.19 267	1.65 281	47.15 243	26.70 276	20.25 272	27.61 272	26.13 273	14.24 279	54.41 270

MVS_baseline		6.53 270	11.27 272	1.00 273	0.34 282	0.92 283	0.21 285	0.00 278	13.24 276	0.00 285	17.44 273	9.02 281	5.33 276	9.00 275	7.38 274	0.10 282	21.89 278

testmvs		5.16 271	8.14 273	1.69 271	0.36 281	1.65 281	3.02 283	0.66 275	7.17 277	0.50 283	12.58 275	0.69 285	4.67 277	5.42 276	5.65 275	0.92 280	23.86 277

test123		4.39 272	7.11 274	1.21 272	0.11 283	1.16 282	1.67 284	0.35 276	5.91 278	0.16 284	11.65 277	0.16 286	4.45 278	1.72 277	4.92 276	0.51 281	24.28 276

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

ACM-MVS					99.13 3	99.41 9	99.12 3		97.72 14	80.64 74	91.95 37	96.34 26	97.61 4			98.47 56	98.31 89

PatchmatchNet2					76.30 237	82.30 250	66.57 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												45.23 248	63.86 243	74.74 254	77.59 241	91.88 252	84.46 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										45.84 248	44.44 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.29 15	95.80 1		98.47 1						99.17 7

TPM-MVS					99.19 1	99.43 8	99.16 2			85.97 36	94.75 28	97.40 15	97.76 1			98.95 27	95.69 167
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										43.17 255

9.14												97.59 12

SR-MVS					98.52 23			93.70 25				96.63 23

Anonymous202405211			81.72 175		88.09 150	94.27 142	89.62 127	82.14 110	82.27 156		48.83 234	72.58 127	91.08 69	87.40 172	88.70 161	94.90 219	97.99 103

our_test_3					78.55 219	84.98 238	70.12 247

ambc			57.08 259		58.68 266	67.71 267	60.07 265		57.13 254	42.79 256	30.00 268	11.64 279	50.18 259	78.89 236	69.14 259	82.64 265	85.02 246

MTAPA										93.37 11		95.71 31

MTMP										93.84 8		94.86 34

Patchmatch-RL test							19.65 276

tmp_tt				57.89 257	79.94 203	59.29 270	52.84 270	36.65 271	94.77 55	68.22 156	72.96 110	65.62 178	33.65 266	66.20 260	58.02 264	76.06 268

XVS					92.16 74	98.56 38	91.04 96			81.00 71		93.49 38				98.00 101

X-MVStestdata					92.16 74	98.56 38	91.04 96			81.00 71		93.49 38				98.00 101

mPP-MVS					97.95 32							92.24 48

NP-MVS									94.12 59

Patchmtry						92.08 172	83.86 179	58.37 255		56.28 201

DeepMVS_CX						70.68 266	59.61 266	67.36 233	72.12 199	38.41 264	53.88 211	32.44 272	55.15 255	50.88 267		74.35 270	68.42 264

High-resolution multi-view benchmark