High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

RA-MVS		98.44 1	98.74 1	98.10 1	99.26 1	99.39 1	98.48 11	96.83 1	98.40 1	97.46 1	98.73 3	99.54 3	97.64 1	98.00 1	97.75 1	98.94 7	99.35 2

DeepC-MVS_fast	93.32 1	96.48 26	96.42 31	96.56 23	98.70 28	98.31 41	97.97 27	95.76 24	96.31 17	92.01 32	91.43 45	95.42 45	96.46 25	97.65 14	97.69 2	98.49 35	98.12 52
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DELS-MVS		93.71 56	93.47 56	94.00 48	96.82 58	98.39 39	96.80 44	91.07 60	89.51 118	89.94 46	83.80 93	89.29 77	90.95 118	97.32 18	97.65 3	98.42 45	98.32 42
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
MGCNet		96.54 25	97.36 17	95.60 36	98.03 38	99.07 10	98.02 25	92.24 49	95.87 23	92.54 29	96.41 18	96.08 36	94.03 56	97.69 11	97.47 4	98.73 20	98.90 14

SMA-MVS		97.53 10	97.93 10	97.07 13	99.21 2	99.02 12	98.08 23	96.25 15	96.36 15	93.57 19	96.56 17	99.27 8	96.78 19	97.91 5	97.43 5	98.51 30	98.94 13
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
DeepPCF-MVS	92.65 2	95.50 37	96.96 23	93.79 54	96.44 62	98.21 46	93.51 125	94.08 40	96.94 7	89.29 49	93.08 36	96.77 31	93.82 61	97.68 12	97.40 6	95.59 212	98.65 22

MSLP-MVS++		96.05 31	95.63 35	96.55 24	98.33 32	98.17 48	96.94 42	94.61 38	94.70 43	94.37 14	89.20 58	95.96 40	96.81 16	95.57 63	97.33 7	98.24 69	98.47 37

MVSMamba_PlusPlus		94.63 47	95.45 40	93.67 55	94.05 94	98.25 45	95.98 55	90.70 63	95.11 34	87.05 77	91.10 46	90.84 65	95.77 34	97.52 16	97.32 8	98.44 42	98.00 56

DVP-MVS		97.93 6	98.23 5	97.58 6	99.05 9	99.31 2	98.64 7	96.62 7	97.56 4	95.08 9	96.61 16	99.64 1	97.32 2	97.91 5	97.31 9	98.77 17	99.26 3
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MSP-MVS		97.70 9	98.09 8	97.24 9	99.00 14	99.17 6	98.76 5	96.41 13	96.91 8	93.88 18	97.72 8	99.04 10	96.93 14	97.29 21	97.31 9	98.45 41	99.23 5
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
SED-MVS		97.98 4	98.36 4	97.54 7	98.94 19	99.29 3	98.81 4	96.64 5	97.14 5	95.16 8	97.96 5	99.61 2	96.92 15	98.00 1	97.24 11	98.75 19	99.25 4

CNVR-MVS		97.30 13	97.41 14	97.18 11	99.02 13	98.60 25	98.15 20	96.24 17	96.12 20	94.10 15	95.54 29	97.99 15	96.99 10	97.97 4	97.17 12	98.57 28	98.50 35

SteuartSystems-ACMMP		97.10 18	97.49 13	96.65 21	98.97 16	98.95 13	98.43 13	95.96 21	95.12 32	91.46 33	96.85 12	97.60 21	96.37 27	97.76 8	97.16 13	98.68 21	98.97 12
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		98.07 3	98.46 2	97.62 4	99.08 5	99.29 3	98.84 3	96.63 6	97.89 3	95.35 7	97.83 7	99.48 4	96.98 12	97.99 3	97.14 14	98.82 13	99.60 1

DeepC-MVS	92.10 3	95.22 38	94.77 46	95.75 33	97.77 43	98.54 29	97.63 33	95.96 21	95.07 36	88.85 53	85.35 81	91.85 58	95.82 33	96.88 32	97.10 15	98.44 42	98.63 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	90.28 7	94.70 46	94.34 52	95.11 39	98.06 37	98.21 46	96.89 43	91.03 61	94.72 42	91.45 34	82.87 104	93.10 54	94.61 46	96.24 52	97.08 16	98.63 26	98.16 48

MED-MVS		98.16 2	98.41 3	97.87 2	99.09 4	99.15 7	98.72 6	96.75 2	98.03 2	96.62 2	98.77 1	99.31 6	97.16 6	97.77 7	97.07 17	98.89 9	98.79 15

DPE-MVS		97.83 7	98.13 7	97.48 8	98.83 25	99.19 5	98.99 1	96.70 3	96.05 21	94.39 13	98.30 4	99.47 5	97.02 9	97.75 9	97.02 18	98.98 3	99.10 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		97.79 8	97.96 9	97.60 5	99.20 3	99.10 8	98.88 2	96.68 4	96.81 10	94.64 10	97.84 6	98.02 14	97.24 4	97.74 10	97.02 18	98.97 5	99.16 7
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
IS_MVSNet		91.87 79	93.35 58	90.14 133	94.09 91	97.73 66	93.09 135	88.12 126	88.71 130	79.98 155	84.49 86	90.63 70	87.49 165	97.07 26	96.96 20	98.07 88	97.88 66

PHI-MVS		95.86 32	96.93 26	94.61 44	97.60 47	98.65 22	96.49 46	93.13 44	94.07 48	87.91 64	97.12 10	97.17 27	93.90 60	96.46 44	96.93 21	98.64 25	98.10 54

3Dnovator+	90.56 5	95.06 40	94.56 49	95.65 34	98.11 36	98.15 49	97.19 38	91.59 56	95.11 34	93.23 26	81.99 118	94.71 48	95.43 40	96.48 43	96.88 22	98.35 51	98.63 23

APD-MVS		97.12 16	97.05 22	97.19 10	99.04 10	98.63 23	98.45 12	96.54 8	94.81 41	93.50 20	96.10 23	97.40 25	96.81 16	97.05 27	96.82 23	98.80 14	98.56 28
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
aaEdge-Enhanced		97.97 5	98.17 6	97.75 3	99.06 7	99.08 9	98.60 9	96.48 9	97.14 5	96.47 3	98.77 1	99.29 7	97.22 5	97.29 21	96.80 24	98.66 23	98.79 15

CANet		94.85 42	94.92 44	94.78 41	97.25 52	98.52 32	97.20 37	91.81 53	93.25 58	91.06 36	86.29 74	94.46 49	92.99 75	97.02 29	96.68 25	98.34 53	98.20 46

ACMMP_NAP		96.93 19	97.27 19	96.53 26	99.06 7	98.95 13	98.24 17	96.06 19	95.66 25	90.96 37	95.63 28	97.71 19	96.53 23	97.66 13	96.68 25	98.30 60	98.61 26

NCCC		96.75 22	96.67 28	96.85 19	99.03 12	98.44 37	98.15 20	96.28 14	96.32 16	92.39 30	92.16 40	97.55 23	96.68 22	97.32 18	96.65 27	98.55 29	98.26 44

SD-MVS		97.35 11	97.73 11	96.90 17	97.35 49	98.66 18	97.85 30	96.25 15	96.86 9	94.54 12	96.75 14	99.13 9	96.99 10	96.94 31	96.58 28	98.39 49	99.20 6
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
UA-Net		90.81 111	92.58 68	88.74 145	94.87 83	97.44 74	92.61 141	88.22 124	82.35 195	78.93 159	85.20 83	95.61 43	79.56 231	96.52 42	96.57 29	98.23 70	94.37 187

CS-MVS		94.53 49	94.73 47	94.31 46	96.30 64	98.53 30	94.98 69	89.24 101	93.37 57	90.24 44	88.96 60	89.76 76	96.09 31	97.48 17	96.42 30	98.99 2	98.59 27

TSAR-MVS + MP.		97.31 12	97.64 12	96.92 16	97.28 51	98.56 27	98.61 8	95.48 32	96.72 11	94.03 17	96.73 15	98.29 12	97.15 7	97.61 15	96.42 30	98.96 6	99.13 8
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EC-MVSNet		94.19 52	95.05 43	93.18 62	93.56 109	97.65 69	95.34 65	86.37 150	92.05 71	88.71 55	89.91 54	93.32 52	96.14 30	97.29 21	96.42 30	98.98 3	98.70 19

sasdasda		93.08 59	93.09 59	93.07 66	94.24 86	97.86 57	95.45 63	87.86 134	94.00 50	87.47 69	88.32 62	82.37 110	95.13 42	93.96 114	96.41 33	98.27 64	98.73 17

canonicalmvs		93.08 59	93.09 59	93.07 66	94.24 86	97.86 57	95.45 63	87.86 134	94.00 50	87.47 69	88.32 62	82.37 110	95.13 42	93.96 114	96.41 33	98.27 64	98.73 17

TSAR-MVS + ACMM		96.19 27	97.39 16	94.78 41	97.70 45	98.41 38	97.72 32	95.49 31	96.47 14	86.66 83	96.35 19	97.85 16	93.99 57	97.19 25	96.37 35	97.12 162	99.13 8

ETV-MVS		93.80 55	94.57 48	92.91 70	93.98 95	97.50 72	93.62 119	88.70 114	91.95 72	87.57 67	90.21 53	90.79 67	94.56 47	97.20 24	96.35 36	99.02 1	97.98 57

X-MVS		96.07 30	96.33 32	95.77 32	98.94 19	98.66 18	97.94 28	95.41 34	95.12 32	88.03 60	93.00 37	96.06 37	95.85 32	96.65 38	96.35 36	98.47 36	98.48 36

Vis-MVSNet (Re-imp)		90.54 120	92.76 66	87.94 156	93.73 106	96.94 107	92.17 151	87.91 129	88.77 129	76.12 169	83.68 94	90.80 66	79.49 232	96.34 49	96.35 36	98.21 72	96.46 136

ACMMPR		96.92 20	96.96 23	96.87 18	98.99 15	98.78 15	98.38 14	95.52 28	96.57 13	92.81 28	96.06 24	95.90 41	97.07 8	96.60 41	96.34 39	98.46 38	98.42 39

HFP-MVS		97.11 17	97.19 20	97.00 15	98.97 16	98.73 16	98.37 15	95.69 25	96.60 12	93.28 24	96.87 11	96.64 33	97.27 3	96.64 39	96.33 40	98.44 42	98.56 28

MGCFI-Net		92.75 64	92.98 63	92.48 80	94.18 88	97.77 63	95.28 67	87.77 136	93.88 53	85.28 125	88.19 64	82.17 115	94.14 54	93.86 117	96.32 41	98.20 73	98.69 20

CDPH-MVS		94.80 45	95.50 37	93.98 50	98.34 31	98.06 51	97.41 36	93.23 43	92.81 62	82.98 138	92.51 39	94.82 47	93.53 66	96.08 54	96.30 42	98.42 45	97.94 60

HPM-MVS++		97.22 14	97.40 15	97.01 14	99.08 5	98.55 28	98.19 18	96.48 9	96.02 22	93.28 24	96.26 21	98.71 11	96.76 20	97.30 20	96.25 43	98.30 60	98.68 21

MVS_111021_HR		94.84 43	95.91 34	93.60 56	97.35 49	98.46 36	95.08 68	91.19 58	94.18 47	85.97 95	95.38 30	92.56 56	93.61 65	96.61 40	96.25 43	98.40 47	97.92 62

SPE-MVS-test		94.63 47	95.28 41	93.88 53	96.56 61	98.67 17	93.41 128	89.31 98	94.27 46	89.64 47	90.84 49	91.64 61	95.58 37	97.04 28	96.17 45	98.77 17	98.32 42

MCST-MVS		96.83 21	97.06 21	96.57 22	98.88 23	98.47 35	98.02 25	96.16 18	95.58 27	90.96 37	95.78 27	97.84 17	96.46 25	97.00 30	96.17 45	98.94 7	98.55 33

SF-MVS		97.20 15	97.29 18	97.10 12	98.95 18	98.51 33	97.51 34	96.48 9	96.17 19	94.64 10	97.32 9	97.57 22	96.23 29	96.78 33	96.15 47	98.79 16	98.55 33

test1111		90.47 122	89.10 134	92.07 92	94.92 81	98.30 42	94.17 91	90.30 68	89.56 117	83.92 133	73.25 191	73.66 182	90.26 130	96.77 34	96.14 48	98.87 10	96.04 153

DPM-MVS		95.07 39	94.84 45	95.34 38	97.44 48	97.49 73	97.76 31	95.52 28	94.88 39	88.92 52	87.25 67	96.44 34	94.41 48	95.78 60	96.11 49	97.99 107	95.95 157

test2506		90.93 108	89.20 132	92.95 68	94.97 79	98.30 42	94.53 76	90.25 69	89.91 109	88.39 58	83.23 99	64.17 239	90.69 124	96.75 36	96.10 50	98.87 10	95.97 156

ECVR-MVS		90.77 115	89.27 130	92.52 77	94.97 79	98.30 42	94.53 76	90.25 69	89.91 109	85.80 104	73.64 184	74.31 181	90.69 124	96.75 36	96.10 50	98.87 10	95.91 160

PGM-MVS		96.16 28	96.33 32	95.95 29	99.04 10	98.63 23	98.32 16	92.76 46	93.42 56	90.49 42	96.30 20	95.31 46	96.71 21	96.46 44	96.02 52	98.38 50	98.19 47

MP-MVS		96.56 24	96.72 27	96.37 27	98.93 21	98.48 34	98.04 24	95.55 27	94.32 45	90.95 39	95.88 26	97.02 29	96.29 28	96.77 34	96.01 53	98.47 36	98.56 28
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
QAPM		94.13 53	94.33 53	93.90 51	97.82 42	98.37 40	96.47 47	90.89 62	92.73 66	85.63 108	85.35 81	93.87 50	94.17 53	95.71 62	95.90 54	98.40 47	98.42 39

CP-MVS		96.68 23	96.59 30	96.77 20	98.85 24	98.58 26	98.18 19	95.51 30	95.34 29	92.94 27	95.21 32	96.25 35	96.79 18	96.44 46	95.77 55	98.35 51	98.56 28

TSAR-MVS + GP.		95.86 32	96.95 25	94.60 45	94.07 92	98.11 50	96.30 49	91.76 54	95.67 24	91.07 35	96.82 13	97.69 20	95.71 36	95.96 57	95.75 56	98.68 21	98.63 23

Vis-MVSNet		89.36 140	91.49 87	86.88 169	92.10 156	97.60 71	92.16 152	85.89 153	84.21 178	75.20 171	82.58 108	87.13 80	77.40 236	95.90 59	95.63 57	98.51 30	97.36 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
casdiffmvs_mvg		91.94 76	91.25 92	92.75 73	93.41 111	97.19 91	95.48 62	89.77 76	89.86 111	86.41 85	81.02 128	82.23 113	92.93 77	95.44 67	95.61 58	98.51 30	97.40 82
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CSCG		95.68 34	95.46 39	95.93 30	98.71 27	99.07 10	97.13 40	93.55 41	95.48 28	93.35 23	90.61 51	93.82 51	95.16 41	94.60 90	95.57 59	97.70 129	99.08 11

MAR-MVS		92.71 66	92.63 67	92.79 72	97.70 45	97.15 94	93.75 113	87.98 128	90.71 85	85.76 105	86.28 75	86.38 84	94.35 51	94.95 74	95.49 60	97.22 155	97.44 80
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
train_agg		96.15 29	96.64 29	95.58 37	98.44 30	98.03 52	98.14 22	95.40 35	93.90 52	87.72 66	96.26 21	98.10 13	95.75 35	96.25 51	95.45 61	98.01 103	98.47 37

Casviewmamba		92.36 71	91.93 80	92.87 71	93.39 112	97.42 75	94.57 75	89.86 73	93.10 59	87.57 67	82.10 116	82.17 115	93.67 64	95.97 56	95.43 62	98.18 76	97.30 87

EIA-MVS		92.72 65	92.96 64	92.44 83	93.86 102	97.76 64	93.13 134	88.65 117	89.78 114	86.68 81	86.69 71	87.57 78	93.74 62	96.07 55	95.32 63	98.58 27	97.53 77

OpenMVS	88.18 11	92.51 67	91.61 85	93.55 57	97.74 44	98.02 53	95.66 59	90.46 66	89.14 123	86.50 84	75.80 170	90.38 74	92.69 85	94.99 73	95.30 64	98.27 64	97.63 72

PVSNet_BlendedMVS		92.80 62	92.44 71	93.23 59	96.02 66	97.83 61	93.74 114	90.58 64	91.86 74	90.69 40	85.87 79	82.04 117	90.01 131	96.39 47	95.26 65	98.34 53	97.81 67

PVSNet_Blended		92.80 62	92.44 71	93.23 59	96.02 66	97.83 61	93.74 114	90.58 64	91.86 74	90.69 40	85.87 79	82.04 117	90.01 131	96.39 47	95.26 65	98.34 53	97.81 67

casdiffmvs		91.72 84	91.16 94	92.38 85	93.16 125	97.15 94	93.95 103	89.49 95	91.58 80	86.03 94	80.75 130	80.95 132	93.16 71	95.25 69	95.22 67	98.50 33	97.23 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		91.92 77	92.39 73	91.36 118	95.45 76	97.85 59	92.25 148	89.54 93	88.53 133	87.47 69	79.82 138	90.53 71	85.47 191	96.31 50	95.16 68	97.99 107	98.56 28

hybridcas		91.91 78	91.29 90	92.65 75	93.18 122	97.22 88	94.63 73	89.68 83	91.78 77	87.11 75	80.73 133	81.57 123	92.96 76	95.56 64	95.14 69	98.32 56	97.01 102

viewmacassd2359aftdt		90.80 113	89.95 122	91.78 99	93.17 124	97.14 97	93.99 100	89.56 92	87.66 141	83.65 134	78.82 147	80.23 142	92.23 97	93.74 122	95.11 70	98.10 84	96.97 113

viewmanbaseed2359cas		91.57 87	91.09 96	92.12 90	93.36 113	97.26 80	94.02 99	89.62 90	90.50 92	84.95 131	82.00 117	81.36 124	92.69 85	94.47 97	95.04 71	98.09 86	97.00 105

MVS_111021_LR		94.84 43	95.57 36	94.00 48	97.11 54	97.72 68	94.88 72	91.16 59	95.24 31	88.74 54	96.03 25	91.52 63	94.33 52	95.96 57	95.01 72	97.79 119	97.49 79

EPNet		93.92 54	94.40 50	93.36 58	97.89 40	96.55 115	96.08 52	92.14 50	91.65 78	89.16 50	94.07 34	90.17 75	87.78 160	95.24 70	94.97 73	97.09 164	98.15 49
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CANet_DTU		90.74 117	92.93 65	88.19 151	94.36 85	96.61 112	94.34 82	84.66 165	90.66 86	68.75 216	90.41 52	86.89 82	89.78 133	95.46 66	94.87 74	97.25 154	95.62 165

gg-mvs-nofinetune		81.83 229	83.58 196	79.80 241	91.57 162	96.54 116	93.79 110	68.80 263	62.71 266	43.01 274	55.28 259	85.06 93	83.65 209	96.13 53	94.86 75	97.98 110	94.46 184

E4		91.04 104	90.00 121	92.25 89	93.15 127	97.14 97	94.09 96	89.62 90	87.54 144	86.08 92	79.38 141	80.24 141	92.53 89	93.89 116	94.82 76	98.04 93	96.99 107

E5new		91.10 100	90.03 119	92.35 86	93.15 127	97.13 99	94.28 85	89.76 77	87.71 139	86.24 87	79.61 139	80.18 144	92.62 87	93.77 119	94.80 77	98.02 100	97.01 102

E5		91.10 100	90.03 119	92.35 86	93.15 127	97.13 99	94.28 85	89.76 77	87.71 139	86.24 87	79.61 139	80.18 144	92.62 87	93.77 119	94.80 77	98.02 100	97.01 102

baseline1		90.81 111	90.29 112	91.42 114	93.67 107	95.86 136	93.94 106	89.69 82	89.29 120	82.85 139	82.91 103	80.30 140	89.60 136	95.05 72	94.79 79	98.80 14	93.82 195

E6new		90.91 109	89.94 123	92.04 93	93.14 130	97.16 92	93.76 111	88.98 103	87.44 145	85.85 102	79.15 144	79.96 148	92.48 91	94.04 108	94.75 80	98.03 94	97.06 100

E6		90.91 109	89.94 123	92.04 93	93.14 130	97.16 92	93.76 111	88.98 103	87.44 145	85.85 102	79.15 144	79.96 148	92.48 91	94.04 108	94.75 80	98.03 94	97.06 100

E3new		91.52 88	90.67 107	92.51 78	93.24 117	97.23 85	94.16 92	89.65 85	89.19 121	87.26 72	81.25 125	81.00 130	92.71 83	94.26 101	94.75 80	98.03 94	96.99 107

E3		91.50 90	90.67 107	92.48 80	93.24 117	97.23 85	94.16 92	89.65 85	89.18 122	87.08 76	81.24 126	81.04 129	92.71 83	94.26 101	94.75 80	98.03 94	96.99 107

MVS_Test		91.81 81	92.19 75	91.37 117	93.24 117	96.95 105	94.43 78	86.25 151	91.45 81	83.45 136	86.31 73	85.15 92	92.93 77	93.99 110	94.71 84	97.92 113	96.77 120

viewcassd2359sk11		91.81 81	91.13 95	92.61 76	93.28 116	97.26 80	94.16 92	89.64 87	90.27 96	87.79 65	82.51 111	81.72 122	92.78 81	94.43 98	94.69 85	98.01 103	96.99 107

FMVSNet2		89.61 136	89.14 133	90.16 132	88.66 194	93.65 171	94.25 87	85.44 159	88.57 132	84.96 130	73.53 186	83.82 97	89.38 141	94.23 103	94.68 86	98.31 57	95.47 169

E2		92.03 73	91.47 88	92.69 74	93.29 115	97.27 79	94.14 95	89.63 89	91.02 83	88.25 59	83.68 94	82.18 114	92.84 80	94.51 94	94.62 87	98.00 105	97.00 105

viewdifsd2359ckpt13		91.32 93	90.71 106	92.04 93	93.21 121	97.23 85	93.57 123	89.54 93	89.94 107	85.21 126	81.31 124	80.56 138	92.78 81	94.56 91	94.57 88	97.95 112	96.80 118

viewdifsd2359ckpt09		91.65 86	90.91 103	92.51 78	93.35 114	97.36 76	93.95 103	89.64 87	89.83 112	86.67 82	82.25 114	80.77 136	93.37 69	94.71 85	94.48 89	98.07 88	96.99 107

UGNet		91.52 88	93.41 57	89.32 139	94.13 89	97.15 94	91.83 161	89.01 102	90.62 88	85.86 101	86.83 68	91.73 60	77.40 236	94.68 87	94.43 90	97.71 127	98.40 41
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
EPP-MVSNet		92.13 72	93.06 61	91.05 120	93.66 108	97.30 78	92.18 149	87.90 130	90.24 98	83.63 135	86.14 76	90.52 73	90.76 122	94.82 82	94.38 91	98.18 76	97.98 57

FMVSNet3		90.19 127	90.06 118	90.34 125	88.69 193	93.85 163	94.58 74	85.78 155	90.03 103	85.56 110	77.38 153	86.13 85	89.22 147	93.29 135	94.36 92	98.20 73	95.40 173

casdiffseed414692147		89.97 128	88.31 143	91.90 96	93.03 132	96.77 111	93.66 118	88.85 107	86.52 157	85.39 122	74.87 178	75.76 178	92.53 89	93.35 133	94.26 93	97.97 111	96.67 126

LS3D		91.97 75	90.98 99	93.12 64	97.03 56	97.09 101	95.33 66	95.59 26	92.47 67	79.26 158	81.60 121	82.77 105	94.39 50	94.28 99	94.23 94	97.14 161	94.45 185

OMC-MVS		94.49 50	94.36 51	94.64 43	97.17 53	97.73 66	95.49 61	92.25 48	96.18 18	90.34 43	88.51 61	92.88 55	94.90 45	94.92 76	94.17 95	97.69 131	96.15 149

GBi-Net		90.21 125	90.11 116	90.32 126	88.66 194	93.65 171	94.25 87	85.78 155	90.03 103	85.56 110	77.38 153	86.13 85	89.38 141	93.97 111	94.16 96	98.31 57	95.47 169

test1		90.21 125	90.11 116	90.32 126	88.66 194	93.65 171	94.25 87	85.78 155	90.03 103	85.56 110	77.38 153	86.13 85	89.38 141	93.97 111	94.16 96	98.31 57	95.47 169

FMVSNet1		87.33 155	86.00 176	88.89 142	87.13 220	92.83 196	93.08 136	84.46 169	81.35 202	82.20 140	66.33 226	77.96 164	88.96 150	93.97 111	94.16 96	97.54 141	95.38 174

ACMMP		95.54 35	95.49 38	95.61 35	98.27 34	98.53 30	97.16 39	94.86 36	94.88 39	89.34 48	95.36 31	91.74 59	95.50 39	95.51 65	94.16 96	98.50 33	98.22 45
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
DI_MVS_pp		91.05 103	90.15 115	92.11 91	92.67 147	96.61 112	96.03 53	88.44 120	90.25 97	85.92 98	73.73 183	84.89 94	91.92 101	94.17 105	94.07 100	97.68 132	97.31 86

viewdifsd2359ckpt07		90.96 107	90.40 111	91.62 107	93.22 120	96.95 105	93.49 126	89.26 100	88.94 126	85.56 110	80.56 134	80.99 131	91.25 110	94.88 80	94.01 101	96.92 182	96.49 135

CDS-MVSNet		88.34 148	88.71 137	87.90 157	90.70 176	94.54 147	92.38 143	86.02 152	80.37 207	79.42 157	79.30 142	83.43 99	82.04 219	93.39 131	94.01 101	96.86 187	95.93 159
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVSTER		91.73 83	91.61 85	91.86 98	93.18 122	94.56 146	94.37 80	87.90 130	90.16 102	88.69 56	89.23 57	81.28 126	88.92 153	95.75 61	93.95 103	98.12 81	96.37 140

diffmvs_AUTHOR		91.22 97	90.82 105	91.68 106	92.69 146	96.56 114	94.05 97	88.87 106	91.87 73	85.08 129	82.26 113	80.04 147	91.84 103	93.80 118	93.93 104	97.56 139	97.26 88

gm-plane-assit		77.65 246	78.50 244	76.66 248	87.96 203	85.43 261	64.70 270	74.50 246	64.15 264	51.26 268	61.32 249	58.17 261	84.11 207	95.16 71	93.83 105	97.45 147	91.41 223

diffmvs		91.37 92	91.09 96	91.70 104	92.71 144	96.47 120	94.03 98	88.78 110	92.74 64	85.43 117	83.63 96	80.37 139	91.76 106	93.39 131	93.78 106	97.50 144	97.23 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
AdaColmap		95.02 41	93.71 54	96.54 25	98.51 29	97.76 64	96.69 45	95.94 23	93.72 54	93.50 20	89.01 59	90.53 71	96.49 24	94.51 94	93.76 107	98.07 88	96.69 125

Fast-Effi-MVS+		88.56 147	87.99 150	89.22 140	91.56 163	95.21 141	92.29 147	82.69 189	86.82 152	77.73 162	76.24 167	73.39 183	93.36 70	94.22 104	93.64 108	97.65 135	96.43 138

DCV-MVSNet		91.24 96	91.26 91	91.22 119	92.84 139	93.44 175	93.82 109	86.75 146	91.33 82	85.61 109	84.00 91	85.46 91	91.27 109	92.91 138	93.62 109	97.02 169	98.05 55

Effi-MVS+		89.79 132	89.83 125	89.74 135	92.98 133	96.45 122	93.48 127	84.24 170	87.62 143	76.45 167	81.76 119	77.56 169	93.48 67	94.61 89	93.59 110	97.82 118	97.22 92

onestephybrid01		91.32 93	90.98 99	91.72 103	92.81 140	96.53 117	93.37 131	88.92 105	92.09 70	86.86 80	83.06 100	81.79 120	91.09 114	92.66 142	93.52 111	97.26 153	97.22 92

tfpn200view9		89.55 137	87.86 152	91.53 111	93.90 100	97.26 80	94.31 84	89.74 79	85.87 162	81.15 146	76.46 163	70.38 201	91.76 106	94.92 76	93.51 112	98.28 63	96.61 128

thres400		89.40 139	87.58 159	91.53 111	94.06 93	97.21 90	94.19 90	89.83 75	85.69 164	81.08 148	75.50 175	69.76 208	91.80 104	94.79 84	93.51 112	98.20 73	96.60 129

thres200		89.49 138	87.72 154	91.55 110	93.95 97	97.25 83	94.34 82	89.74 79	85.66 165	81.18 145	76.12 169	70.19 207	91.80 104	94.92 76	93.51 112	98.27 64	96.40 139

CPTT-MVS		95.54 35	95.07 42	96.10 28	97.88 41	97.98 54	97.92 29	94.86 36	94.56 44	92.16 31	91.01 47	95.71 42	96.97 13	94.56 91	93.50 115	96.81 189	98.14 50

LGP-MVS_train		91.83 80	92.04 78	91.58 109	95.46 74	96.18 129	95.97 56	89.85 74	90.45 93	77.76 161	91.92 43	80.07 146	92.34 96	94.27 100	93.47 116	98.11 83	97.90 65

ET-MVSNet_ETH3D		89.93 129	90.84 104	88.87 143	79.60 254	96.19 128	94.43 78	86.56 147	90.63 87	80.75 151	90.71 50	77.78 166	93.73 63	91.36 170	93.45 117	98.15 78	95.77 162

FA-MVS(training)		90.79 114	91.33 89	90.17 131	93.76 105	97.22 88	92.74 139	77.79 238	90.60 90	88.03 60	78.80 148	87.41 79	91.00 117	95.40 68	93.43 118	97.70 129	96.46 136

thres100view900		89.36 140	87.61 157	91.39 115	93.90 100	96.86 109	94.35 81	89.66 84	85.87 162	81.15 146	76.46 163	70.38 201	91.17 112	94.09 106	93.43 118	98.13 80	96.16 148

hybridnocas07		91.26 95	90.98 99	91.59 108	92.70 145	96.41 124	93.58 120	88.76 112	92.74 64	85.96 97	84.20 89	80.95 132	91.05 116	92.38 150	93.38 120	97.52 142	96.77 120

Anonymous202405211			88.00 149		93.16 125	96.38 125	93.58 120	89.34 97	87.92 138		65.04 235	83.03 102	92.07 98	92.67 141	93.33 121	96.96 175	97.63 72

CNLPA		93.69 57	92.50 69	95.06 40	97.11 54	97.36 76	93.88 108	93.30 42	95.64 26	93.44 22	80.32 135	90.73 69	94.99 44	93.58 124	93.33 121	97.67 133	96.57 131

PLC	90.69 4	94.32 51	92.99 62	95.87 31	97.91 39	96.49 119	95.95 57	94.12 39	94.94 37	94.09 16	85.90 77	90.77 68	95.58 37	94.52 93	93.32 123	97.55 140	95.00 179
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
viewmamba		91.38 91	91.07 98	91.74 100	92.86 138	96.52 118	93.58 120	88.83 109	94.05 49	85.68 107	83.53 97	81.22 127	92.03 100	92.17 158	93.24 124	97.46 146	96.75 123

dmvs_re		87.31 156	86.10 172	88.74 145	89.84 180	94.28 155	92.66 140	89.41 96	82.61 192	74.69 172	74.69 180	69.47 209	87.78 160	92.38 150	93.23 125	98.03 94	96.02 155

OPM-MVS		91.08 102	89.34 129	93.11 65	96.18 65	96.13 130	96.39 48	92.39 47	82.97 190	81.74 141	82.55 110	80.20 143	93.97 59	94.62 88	93.23 125	98.00 105	95.73 163
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres600view7		89.28 143	87.47 162	91.39 115	94.12 90	97.25 83	93.94 106	89.74 79	85.62 167	80.63 152	75.24 177	69.33 211	91.66 108	94.92 76	93.23 125	98.27 64	96.72 124

GeoE		89.29 142	88.68 138	89.99 134	92.75 143	96.03 134	93.07 137	83.79 177	86.98 150	81.34 144	74.72 179	78.92 154	91.22 111	93.31 134	93.21 128	97.78 121	97.60 76

IterMVS-LS		88.60 145	88.45 141	88.78 144	92.02 157	92.44 208	92.00 157	83.57 181	86.52 157	78.90 160	78.61 150	81.34 125	89.12 148	90.68 185	93.18 129	97.10 163	96.35 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 1792x2688		88.57 146	87.82 153	89.44 138	95.46 74	96.89 108	93.74 114	85.87 154	89.63 115	77.42 164	61.38 248	83.31 100	88.80 155	93.44 130	93.16 130	95.37 220	96.95 115

FC-MVSNet-train		90.55 119	90.19 114	90.97 121	93.78 104	95.16 142	92.11 154	88.85 107	87.64 142	83.38 137	84.36 88	78.41 159	89.53 137	94.69 86	93.15 131	98.15 78	97.92 62

hybrid		91.19 98	90.98 99	91.43 113	92.63 149	96.34 126	93.39 129	88.61 118	92.81 62	85.87 100	83.98 92	81.17 128	90.76 122	92.64 145	93.14 132	97.33 149	96.76 122

TSAR-MVS + COLMAP		92.39 69	92.31 74	92.47 82	95.35 78	96.46 121	96.13 51	92.04 52	95.33 30	80.11 154	94.95 33	77.35 170	94.05 55	94.49 96	93.08 133	97.15 159	94.53 183

CLD-MVS		92.50 68	91.96 79	93.13 63	93.93 99	96.24 127	95.69 58	88.77 111	92.92 60	89.01 51	88.19 64	81.74 121	93.13 72	93.63 123	93.08 133	98.23 70	97.91 64
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous20231211		89.82 131	88.18 147	91.74 100	92.52 151	96.09 132	93.38 130	89.30 99	88.95 125	85.90 99	64.55 240	84.39 95	92.41 95	92.24 155	93.06 135	96.93 180	97.95 59

TAPA-MVS	90.35 6	93.69 57	93.52 55	93.90 51	96.89 57	97.62 70	96.15 50	91.67 55	94.94 37	85.97 95	87.72 66	91.96 57	94.40 49	93.76 121	93.06 135	98.30 60	95.58 167
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0530		91.04 104	91.74 82	90.21 128	92.93 137	97.00 103	92.06 155	87.63 141	90.74 84	81.51 142	86.81 69	82.48 107	89.23 145	94.81 83	93.03 137	97.90 114	97.33 85

tttt0517		91.01 106	91.71 83	90.19 130	92.98 133	97.07 102	91.96 160	87.63 141	90.61 89	81.42 143	86.76 70	82.26 112	89.23 145	94.86 81	93.03 137	97.90 114	97.36 83

dtuplus		90.51 121	89.50 127	91.69 105	92.61 150	96.04 133	93.70 117	88.72 113	88.47 134	86.07 93	79.85 137	80.92 134	92.04 99	91.20 172	92.89 139	96.99 172	97.14 97

IB-MVS	85.10 14	87.98 150	87.97 151	87.99 155	94.55 84	96.86 109	84.52 241	88.21 125	86.48 160	88.54 57	74.41 182	77.74 167	74.10 249	89.65 205	92.85 140	98.06 91	97.80 69
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
viewmambaseed2359dif		90.70 118	89.81 126	91.73 102	92.66 148	96.10 131	93.97 101	88.69 115	89.92 108	86.12 90	80.79 129	80.73 137	91.92 101	91.13 177	92.81 141	97.06 166	97.20 94

HQP-MVS		92.39 69	92.49 70	92.29 88	95.65 70	95.94 135	95.64 60	92.12 51	92.46 68	79.65 156	91.97 42	82.68 106	92.92 79	93.47 129	92.77 142	97.74 125	98.12 52

ACMM	88.76 10	91.70 85	90.43 110	93.19 61	95.56 71	95.14 143	93.35 132	91.48 57	92.26 69	87.12 74	84.02 90	79.34 151	93.99 57	94.07 107	92.68 143	97.62 138	95.50 168
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_ETH3D		84.57 192	81.40 229	88.28 150	89.34 187	94.38 154	90.33 175	86.50 149	74.74 247	77.52 163	59.90 253	62.04 247	88.78 156	88.82 216	92.65 144	97.22 155	97.24 89

baseline		91.19 98	91.89 81	90.38 124	92.76 141	95.04 144	93.55 124	84.54 168	92.92 60	85.71 106	86.68 72	86.96 81	89.28 144	92.00 160	92.62 145	96.46 194	96.99 107

ACMP	89.13 9	92.03 73	91.70 84	92.41 84	94.92 81	96.44 123	93.95 103	89.96 72	91.81 76	85.48 114	90.97 48	79.12 153	92.42 94	93.28 136	92.55 146	97.76 123	97.74 71
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		87.87 151	86.42 168	89.57 136	95.56 71	96.99 104	92.37 144	84.15 172	86.64 154	77.17 165	57.65 255	83.97 96	91.08 115	92.09 159	92.44 147	97.09 164	95.16 176

DU-MVS		86.12 168	84.81 188	87.66 161	87.77 207	93.78 165	90.15 181	87.87 132	84.40 173	73.45 181	70.59 202	64.82 236	88.95 151	90.14 191	92.33 148	97.76 123	97.62 74

TranMVSNet+NR-MVSNet		85.57 177	84.41 191	86.92 168	87.67 210	93.34 178	90.31 177	88.43 121	83.07 189	70.11 207	69.99 208	65.28 231	86.96 171	89.73 202	92.27 149	98.06 91	97.17 96

MIMVSNet		82.97 220	84.00 194	81.77 237	82.23 248	92.25 211	87.40 226	72.73 256	81.48 201	69.55 210	68.79 210	72.42 191	81.82 222	92.23 156	92.25 150	96.89 184	88.61 247

UniMVSNet_NR-MVSNet		86.80 160	85.86 179	87.89 158	88.17 200	94.07 159	90.15 181	88.51 119	84.20 179	73.45 181	72.38 196	70.30 206	88.95 151	90.25 190	92.21 151	98.12 81	97.62 74

PatchMatch-RL		90.30 124	88.93 136	91.89 97	95.41 77	95.68 137	90.94 167	88.67 116	89.80 113	86.95 79	85.90 77	72.51 190	92.46 93	93.56 126	92.18 152	96.93 180	92.89 205

anonymousdsp		84.51 194	85.85 180	82.95 225	86.30 231	93.51 174	85.77 238	80.38 225	78.25 227	63.42 244	73.51 187	72.20 192	84.64 201	93.21 137	92.16 153	97.19 157	98.14 50

CHOSEN 280x420		90.77 115	92.14 76	89.17 141	93.86 102	92.81 197	93.16 133	80.22 226	90.21 99	84.67 132	89.89 55	91.38 64	90.57 128	94.94 75	92.11 154	92.52 247	93.65 197

EPNet_dtu		88.32 149	90.61 109	85.64 184	96.79 59	92.27 210	92.03 156	90.31 67	89.05 124	65.44 237	89.43 56	85.90 89	74.22 247	92.76 139	92.09 155	95.02 233	92.76 212
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSDG		90.42 123	88.25 146	92.94 69	96.67 60	94.41 152	93.96 102	92.91 45	89.59 116	86.26 86	76.74 160	80.92 134	90.43 129	92.60 146	92.08 156	97.44 148	91.41 223

LTVRE_ROB	81.71 16	82.44 226	81.84 222	83.13 216	89.01 189	92.99 190	88.90 206	82.32 198	66.26 262	54.02 265	74.68 181	59.62 259	88.87 154	90.71 184	92.02 157	95.68 209	96.62 127
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
ACMH	85.51 13	87.31 156	86.59 166	88.14 152	93.96 96	94.51 148	89.00 205	87.99 127	81.58 200	70.15 206	78.41 151	71.78 195	90.60 127	91.30 171	91.99 158	97.17 158	96.58 130
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PCF-MVS	90.19 8	92.98 61	92.07 77	94.04 47	96.39 63	97.87 56	96.03 53	95.47 33	87.16 148	85.09 128	84.81 85	93.21 53	93.46 68	91.98 161	91.98 159	97.78 121	97.51 78
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
baseline2		88.97 144	89.50 127	88.36 148	91.14 168	95.30 138	90.13 183	85.17 162	87.24 147	80.80 150	84.46 87	78.44 158	85.60 188	93.54 127	91.87 160	97.31 151	95.66 164

FC-MVSNet-test		86.15 167	89.10 134	82.71 229	89.83 181	93.18 185	87.88 221	84.69 164	86.54 156	62.18 247	82.39 112	83.31 100	74.18 248	92.52 148	91.86 161	97.50 144	93.88 194

UniMVSNet (Re)		86.22 166	85.46 184	87.11 166	88.34 198	94.42 151	89.65 195	87.10 145	84.39 175	74.61 173	70.41 205	68.10 216	85.10 194	91.17 175	91.79 162	97.84 117	97.94 60

NR-MVSNet		85.46 180	84.54 190	86.52 175	88.33 199	93.78 165	90.45 174	87.87 132	84.40 173	71.61 193	70.59 202	62.09 246	82.79 215	91.75 163	91.75 163	98.10 84	97.44 80

Fast-Effi-MVS+-dtu		86.25 164	87.70 155	84.56 199	90.37 179	93.70 168	90.54 173	78.14 235	83.50 185	65.37 238	81.59 122	75.83 177	86.09 183	91.70 165	91.70 164	96.88 185	95.84 161

pm-mvs1		84.55 193	83.46 197	85.82 179	88.16 201	93.39 177	89.05 204	85.36 161	74.03 248	72.43 191	65.08 234	71.11 197	82.30 218	93.48 128	91.70 164	97.64 136	95.43 172

Effi-MVS+-dtu		87.51 154	88.13 148	86.77 172	91.10 169	94.90 145	90.91 169	82.67 190	83.47 186	71.55 194	81.11 127	77.04 171	89.41 140	92.65 144	91.68 166	95.00 234	96.09 151

GA-MVS		85.08 187	85.65 181	84.42 201	89.77 182	94.25 156	89.26 199	84.62 166	81.19 204	62.25 246	75.72 171	68.44 215	84.14 206	93.57 125	91.68 166	96.49 192	94.71 182

tfpnnormal		83.80 207	81.26 231	86.77 172	89.60 184	93.26 183	89.72 194	87.60 143	72.78 249	70.44 204	60.53 252	61.15 252	85.55 189	92.72 140	91.44 168	97.71 127	96.92 116

GG-mvs-BLEND		62.84 259	90.21 113	30.91 268	0.57 283	94.45 150	86.99 228	0.34 278	88.71 130	0.98 283	81.55 123	91.58 62	0.86 280	92.66 142	91.43 169	95.73 206	91.11 227

PMMVS		89.88 130	91.19 93	88.35 149	89.73 183	91.97 220	90.62 172	81.92 211	90.57 91	80.58 153	92.16 40	86.85 83	91.17 112	92.31 152	91.35 170	96.11 200	93.11 204

usedtu_dtu_shiyan1		86.08 171	86.20 171	85.93 178	81.88 251	93.87 162	90.68 170	86.54 148	86.84 151	72.93 186	71.70 197	75.39 179	85.90 184	91.74 164	91.33 171	97.66 134	92.56 215

thisisatest0515		85.70 174	87.00 163	84.19 204	88.16 201	93.67 170	84.20 243	84.14 173	83.39 188	72.91 187	76.79 159	74.75 180	78.82 234	92.57 147	91.26 172	96.94 177	96.56 132

FMVSNet5		84.47 197	84.72 189	84.18 205	83.30 243	88.43 252	88.09 219	79.42 230	84.25 177	74.14 176	73.15 192	78.74 155	83.65 209	91.19 174	91.19 173	96.46 194	86.07 255

viewdifsd2359ckpt11		89.68 133	88.67 139	90.86 122	92.35 152	95.23 139	91.72 163	88.40 122	88.84 127	86.14 89	80.75 130	78.17 162	90.95 118	90.02 197	91.15 174	95.59 212	96.50 133

viewmsd2359difaftdt		89.67 135	88.66 140	90.85 123	92.35 152	95.23 139	91.72 163	88.40 122	88.80 128	86.12 90	80.75 130	78.20 161	90.94 120	90.02 197	91.15 174	95.59 212	96.50 133

ACMH+	85.75 12	87.19 158	86.02 175	88.56 147	93.42 110	94.41 152	89.91 189	87.66 140	83.45 187	72.25 192	76.42 165	71.99 194	90.78 121	89.86 200	90.94 176	97.32 150	95.11 178

Baseline_NR-MVSNet		85.28 183	83.42 201	87.46 165	87.77 207	90.80 236	89.90 191	87.69 138	83.93 183	74.16 175	64.72 238	66.43 226	87.48 166	90.14 191	90.83 177	97.73 126	97.11 98

test0.0.03 1		85.58 176	87.69 156	83.11 217	91.22 166	92.54 204	85.60 240	83.62 179	85.66 165	67.84 223	82.79 106	79.70 150	73.51 252	91.15 176	90.79 178	96.88 185	91.23 226

TAMVS		84.94 190	84.95 186	84.93 194	88.82 190	93.18 185	88.44 216	81.28 219	77.16 233	73.76 178	75.43 176	76.57 174	82.04 219	90.59 186	90.79 178	95.22 222	90.94 229

EG-PatchMatch MVS		81.70 231	81.31 230	82.15 234	88.75 191	93.81 164	87.14 227	78.89 232	71.57 252	64.12 243	61.20 251	68.46 214	76.73 241	91.48 167	90.77 180	97.28 152	91.90 220

CR-MVSNet		85.48 179	86.29 169	84.53 200	91.08 171	92.10 213	89.18 200	73.30 253	84.75 169	71.08 199	73.12 193	77.91 165	86.27 179	91.48 167	90.75 181	96.27 198	93.94 192

PatchT		83.86 205	85.51 183	81.94 235	88.41 197	91.56 226	78.79 258	71.57 258	84.08 181	71.08 199	70.62 201	76.13 176	86.27 179	91.48 167	90.75 181	95.52 218	93.94 192

TransMVSNet (Re)		82.67 223	80.93 234	84.69 197	88.71 192	91.50 227	87.90 220	87.15 144	71.54 254	68.24 220	63.69 242	64.67 238	78.51 235	91.65 166	90.73 183	97.64 136	92.73 214

PEN-MVS		82.49 225	81.58 226	83.56 212	86.93 223	92.05 217	86.71 231	83.84 176	76.94 235	64.68 240	67.24 219	60.11 256	81.17 226	87.78 220	90.70 184	98.02 100	96.21 147

CP-MVSNet		83.11 219	82.15 216	84.23 203	87.20 217	92.70 198	86.42 233	83.53 182	77.83 229	67.67 224	66.89 224	60.53 255	82.47 216	89.23 211	90.65 185	98.08 87	97.20 94

WR-MVS		83.14 217	83.38 203	82.87 226	87.55 211	93.29 180	86.36 234	84.21 171	80.05 211	66.41 231	66.91 222	66.92 223	75.66 245	88.96 214	90.56 186	97.05 167	96.96 114

v2v482		84.51 194	83.05 208	86.20 177	87.25 216	93.28 181	90.22 179	85.40 160	79.94 213	69.78 209	67.74 218	65.15 233	87.57 163	89.12 212	90.55 187	96.97 173	95.60 166

PS-CasMVS		82.53 224	81.54 227	83.68 210	87.08 222	92.54 204	86.20 235	83.46 183	76.46 238	65.73 236	65.71 231	59.41 260	81.61 224	89.06 213	90.55 187	98.03 94	97.07 99

v10		84.18 200	83.17 207	85.37 186	87.34 214	92.68 199	90.32 176	81.33 218	79.93 214	69.23 214	66.33 226	65.74 229	87.03 170	90.84 180	90.38 189	96.97 173	96.29 145

v7n		82.25 227	81.54 227	83.07 219	85.55 236	92.58 202	86.68 232	81.10 222	76.54 236	65.97 234	62.91 244	60.56 254	82.36 217	91.07 178	90.35 190	96.77 190	96.80 118

v1144		84.03 204	82.88 211	85.37 186	87.17 218	93.15 188	90.18 180	83.31 184	78.83 223	67.85 222	65.99 228	64.99 234	86.79 173	90.75 182	90.33 191	96.90 183	96.15 149

V42		84.48 196	83.36 204	85.79 181	87.14 219	93.28 181	90.03 184	83.98 175	80.30 208	71.20 198	66.90 223	67.17 220	85.55 189	89.35 206	90.27 192	96.82 188	96.27 146

v1192		83.56 211	82.35 214	84.98 192	86.84 225	92.84 194	90.01 186	82.70 188	78.54 224	66.48 230	64.88 236	62.91 241	86.91 172	90.72 183	90.25 193	96.94 177	96.32 143

v8		84.45 198	83.30 205	85.80 180	87.53 212	92.95 191	90.31 177	82.46 196	80.46 206	71.43 195	66.99 221	67.16 221	86.14 181	89.26 210	90.22 194	96.94 177	96.06 152

v1240		82.88 221	81.66 225	84.29 202	86.46 230	92.52 207	89.06 203	81.82 213	77.16 233	65.09 239	64.17 241	61.50 250	86.36 176	90.12 193	90.13 195	96.95 176	96.04 153

CVMVSNet		83.83 206	85.53 182	81.85 236	89.60 184	90.92 232	87.81 222	83.21 185	80.11 210	60.16 254	76.47 162	78.57 157	76.79 239	89.76 201	90.13 195	93.51 239	92.75 213

WR-MVS_H		82.86 222	82.66 213	83.10 218	87.44 213	93.33 179	85.71 239	83.20 186	77.36 232	68.20 221	66.37 225	65.23 232	76.05 243	89.35 206	90.13 195	97.99 107	96.89 117

pmmvs5		83.37 213	82.68 212	84.18 205	87.13 220	93.18 185	86.74 230	82.08 207	76.48 237	67.28 227	71.26 199	62.70 243	84.71 200	90.77 181	90.12 198	97.15 159	94.24 188

test-mter		86.09 170	88.38 142	83.43 214	87.89 204	92.61 201	86.89 229	77.11 241	84.30 176	68.62 218	82.57 109	82.45 108	84.34 202	92.40 149	90.11 199	95.74 205	94.21 190

IterMVS-SCA-FT		85.44 181	86.71 164	83.97 208	90.59 177	90.84 234	89.73 193	78.34 234	84.07 182	66.40 232	77.27 158	78.66 156	83.06 211	91.20 172	90.10 200	95.72 207	94.78 180

v1921920		83.30 215	82.09 218	84.70 196	86.59 229	92.67 200	89.82 192	82.23 200	78.32 225	65.76 235	64.64 239	62.35 244	86.78 174	90.34 189	90.02 201	97.02 169	96.31 144

MS-PatchMatch		87.63 152	87.61 157	87.65 162	93.95 97	94.09 158	92.60 142	81.52 216	86.64 154	76.41 168	73.46 188	85.94 88	85.01 199	92.23 156	90.00 202	96.43 196	90.93 230

v144192		83.48 212	82.23 215	84.94 193	86.65 226	92.84 194	89.63 196	82.48 194	77.87 228	67.36 226	65.33 233	63.50 240	86.51 175	89.72 203	89.99 203	97.03 168	96.35 141

DTE-MVSNet		81.76 230	81.04 232	82.60 231	86.63 227	91.48 229	85.97 237	83.70 178	76.45 239	62.44 245	67.16 220	59.98 257	78.98 233	87.15 224	89.93 204	97.88 116	95.12 177

test-LLR		86.88 159	88.28 144	85.24 189	91.22 166	92.07 215	87.41 224	83.62 179	84.58 171	69.33 212	83.00 101	82.79 103	84.24 203	92.26 153	89.81 205	95.64 210	93.44 198

TESTMET0.1,1		86.11 169	88.28 144	83.59 211	87.80 205	92.07 215	87.41 224	77.12 240	84.58 171	69.33 212	83.00 101	82.79 103	84.24 203	92.26 153	89.81 205	95.64 210	93.44 198

USDC		86.73 162	85.96 177	87.63 163	91.64 160	93.97 160	92.76 138	84.58 167	88.19 135	70.67 202	80.10 136	67.86 218	89.43 138	91.81 162	89.77 207	96.69 191	90.05 238

COLMAP_ROB	84.39 15	87.61 153	86.03 174	89.46 137	95.54 73	94.48 149	91.77 162	90.14 71	87.16 148	75.50 170	73.41 189	76.86 173	87.33 167	90.05 196	89.76 208	96.48 193	90.46 233
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
IterMVS		85.25 184	86.49 167	83.80 209	90.42 178	90.77 237	90.02 185	78.04 236	84.10 180	66.27 233	77.28 157	78.41 159	83.01 213	90.88 179	89.72 209	95.04 227	94.24 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testgi		81.94 228	84.09 193	79.43 242	89.53 186	90.83 235	82.49 247	81.75 214	80.59 205	59.46 257	82.82 105	65.75 228	67.97 254	90.10 194	89.52 210	95.39 219	89.03 242

RPMNet		84.82 191	85.90 178	83.56 212	91.10 169	92.10 213	88.73 209	71.11 259	84.75 169	68.79 215	73.56 185	77.62 168	85.33 192	90.08 195	89.43 211	96.32 197	93.77 196

v148		83.61 209	82.10 217	85.37 186	87.34 214	92.94 192	87.48 223	85.72 158	78.92 222	73.87 177	65.71 231	64.69 237	81.78 223	87.82 219	89.35 212	96.01 201	95.26 175

TinyColmap		84.04 203	82.01 220	86.42 176	90.87 172	91.84 221	88.89 207	84.07 174	82.11 197	69.89 208	71.08 200	60.81 253	89.04 149	90.52 187	89.19 213	95.76 204	88.50 248

pmmvs6		80.90 237	78.77 243	83.38 215	85.84 232	91.61 225	86.01 236	82.54 192	64.17 263	70.43 205	54.14 263	67.06 222	80.73 228	90.50 188	89.17 214	94.74 235	94.75 181

TDRefinement		84.97 189	83.39 202	86.81 171	92.97 135	94.12 157	92.18 149	87.77 136	82.78 191	71.31 197	68.43 211	68.07 217	81.10 227	89.70 204	89.03 215	95.55 216	91.62 221

FE-MVSNET2		76.99 249	76.02 252	78.12 246	71.26 267	89.46 248	81.92 249	80.87 223	71.48 255	61.96 248	47.82 267	54.83 264	75.73 244	89.29 209	88.91 216	97.00 171	90.36 235

pmmvs4		86.00 172	84.28 192	88.00 154	87.80 205	92.01 218	89.94 188	84.91 163	86.79 153	80.98 149	73.41 189	66.34 227	88.12 158	89.31 208	88.90 217	96.24 199	93.20 203

dtuonly		85.32 182	85.19 185	85.48 185	89.06 188	91.16 230	91.15 166	82.82 187	83.63 184	70.67 202	72.83 194	79.27 152	87.08 169	89.96 199	88.41 218	92.11 253	91.06 228

Anonymous20231206		78.09 245	78.11 246	78.07 247	85.19 238	89.17 249	80.99 251	81.24 221	75.46 244	58.25 259	54.78 262	59.90 258	66.73 258	88.94 215	88.26 219	96.01 201	90.25 236

SixPastTwentyTwo		83.12 218	83.44 199	82.74 227	87.71 209	93.11 189	82.30 248	82.33 197	79.24 215	64.33 241	78.77 149	62.75 242	84.11 207	88.11 218	87.89 220	95.70 208	94.21 190

MIMVSNet1		73.19 253	73.70 254	72.60 254	65.42 270	86.69 260	75.56 263	79.65 228	67.87 260	55.30 261	45.24 269	56.41 262	63.79 261	86.98 225	87.66 221	95.85 203	85.04 257

FE-MVSNET		73.24 252	74.06 253	72.28 255	64.92 271	85.32 262	76.06 261	79.75 227	67.71 261	50.14 270	49.61 265	54.40 265	67.26 257	85.97 231	87.33 222	95.53 217	88.10 252

test20.03		76.41 250	78.49 245	73.98 251	85.64 234	87.50 255	75.89 262	80.71 224	70.84 256	51.07 269	68.06 214	61.40 251	54.99 265	88.28 217	87.20 223	95.58 215	86.15 254

pmmvs-eth3d		79.78 242	77.58 247	82.34 233	81.57 252	87.46 256	82.92 245	81.28 219	75.33 245	71.34 196	61.88 246	52.41 266	81.59 225	87.56 221	86.90 224	95.36 221	91.48 222

MDTV_nov1_ep13		86.64 163	87.50 161	85.65 183	90.73 174	93.69 169	89.96 187	78.03 237	89.48 119	76.85 166	84.92 84	82.42 109	86.14 181	86.85 227	86.15 225	92.17 250	88.97 244

RPSCF		89.68 133	89.24 131	90.20 129	92.97 135	92.93 193	92.30 146	87.69 138	90.44 94	85.12 127	91.68 44	85.84 90	90.69 124	87.34 223	86.07 226	92.46 248	90.37 234

tpm		83.16 216	83.64 195	82.60 231	90.75 173	91.05 231	88.49 210	73.99 248	82.36 194	67.08 229	78.10 152	68.79 212	84.17 205	85.95 232	85.96 227	91.09 256	93.23 202

PM-MVS		80.29 239	79.30 242	81.45 238	81.91 249	88.23 253	82.61 246	79.01 231	79.99 212	67.15 228	69.07 209	51.39 268	82.92 214	87.55 222	85.59 228	95.08 225	93.28 201

SCA		86.25 164	87.52 160	84.77 195	91.59 161	93.90 161	89.11 202	73.25 255	90.38 95	72.84 188	83.26 98	83.79 98	88.49 157	86.07 230	85.56 229	93.33 240	89.67 240

EU-MVSNet		78.43 243	80.25 240	76.30 249	83.81 241	87.27 258	80.99 251	79.52 229	76.01 240	54.12 264	70.44 204	64.87 235	67.40 256	86.23 229	85.54 230	91.95 254	91.41 223

EPMVS		85.77 173	86.24 170	85.23 190	92.76 141	93.78 165	89.91 189	73.60 251	90.19 100	74.22 174	82.18 115	78.06 163	87.55 164	85.61 233	85.38 231	93.32 241	88.48 249

CostFormer		86.78 161	86.05 173	87.62 164	92.15 155	93.20 184	91.55 165	75.83 243	88.11 137	85.29 124	81.76 119	76.22 175	87.80 159	84.45 236	85.21 232	93.12 242	93.42 200

MVS-HIRNet		78.16 244	77.57 248	78.83 243	85.83 233	87.76 254	76.67 260	70.22 261	75.82 243	67.39 225	55.61 258	70.52 199	81.96 221	86.67 228	85.06 233	90.93 258	81.58 262

ADS-MVSNet		84.08 202	84.95 186	83.05 221	91.53 165	91.75 223	88.16 218	70.70 260	89.96 106	69.51 211	78.83 146	76.97 172	86.29 178	84.08 238	84.60 234	92.13 252	88.48 249

0.4-1-1-0.1		85.56 178	83.44 199	88.04 153	83.51 242	92.54 204	92.35 145	82.48 194	82.48 193	85.45 115	76.70 161	73.34 184	89.71 134	81.68 253	84.56 235	94.73 236	92.79 211

CMPMVS	61.19 17	79.86 241	77.46 249	82.66 230	91.54 164	91.82 222	83.25 244	81.57 215	70.51 257	68.64 217	59.89 254	66.77 224	79.63 230	84.00 239	84.30 236	91.34 255	84.89 258
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PatchmatchNet		85.70 174	86.65 165	84.60 198	91.79 158	93.40 176	89.27 198	73.62 250	90.19 100	72.63 190	82.74 107	81.93 119	87.64 162	84.99 234	84.29 237	92.64 246	89.00 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
0.3-1-1-0.015		85.24 185	82.99 209	87.87 159	83.27 244	92.15 212	92.14 153	82.29 199	81.93 198	85.41 118	76.15 168	73.18 186	89.63 135	81.11 256	84.26 238	94.50 237	92.12 218

0.4-1-1-0.2		85.17 186	82.95 210	87.75 160	83.20 245	92.00 219	91.99 158	82.20 201	81.62 199	85.34 123	76.38 166	73.33 185	89.43 138	81.21 255	84.14 239	94.36 238	92.00 219

dps		85.00 188	83.21 206	87.08 167	90.73 174	92.55 203	89.34 197	75.29 245	84.94 168	87.01 78	79.27 143	67.69 219	87.27 168	84.22 237	83.56 240	92.83 245	90.25 236

MDTV_nov1_ep13_2view		80.43 238	80.94 233	79.84 240	84.82 239	90.87 233	84.23 242	73.80 249	80.28 209	64.33 241	70.05 207	68.77 213	79.67 229	84.83 235	83.50 241	92.17 250	88.25 251

pmmvs3		71.13 256	71.06 258	71.21 256	73.54 265	80.19 266	71.69 268	64.86 265	62.04 267	52.10 266	54.92 261	48.00 273	75.03 246	83.75 240	83.24 242	90.04 264	85.27 256

tpmrst		83.72 208	83.45 198	84.03 207	92.21 154	91.66 224	88.74 208	73.58 252	88.14 136	72.67 189	77.37 156	72.11 193	86.34 177	82.94 241	82.05 243	90.63 260	89.86 239

tpm cat1		84.13 201	81.99 221	86.63 174	91.74 159	91.50 227	90.68 170	75.69 244	86.12 161	85.44 116	72.39 195	70.72 198	85.16 193	80.89 257	81.56 244	91.07 257	90.71 231

MDA-MVSNet-bldmvs		73.81 251	72.56 256	75.28 250	72.52 266	88.87 251	74.95 264	82.67 190	71.57 252	55.02 262	65.96 229	42.84 275	76.11 242	70.61 266	81.47 245	90.38 263	86.59 253

new_pmnet		72.29 255	73.25 255	71.16 257	75.35 256	81.38 265	73.72 266	69.27 262	75.97 241	49.84 271	56.27 256	56.12 263	69.08 253	81.73 252	80.86 246	89.72 265	80.44 264

PatchmatchNet1												61.90 248	74.10 249	82.01 251	80.80 247	90.60 261	84.59 260
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		77.55 247	76.68 250	78.56 244	85.43 237	87.30 257	78.84 257	81.88 212	78.30 226	60.61 251	61.46 247	62.15 245	74.03 251	82.04 250	80.69 248	90.59 262	84.81 259

blended_shiyan6		81.63 233	80.44 236	83.02 222	74.06 258	89.96 239	88.46 215	81.98 210	79.01 217	73.38 183	68.03 215	70.41 200	85.03 198	82.38 245	80.40 249	95.18 224	92.87 206

blended_shiyan8		81.65 232	80.43 237	83.06 220	74.09 257	89.98 238	88.48 211	81.99 209	79.15 216	73.52 180	67.98 216	70.34 205	85.09 195	82.39 244	80.39 250	95.19 223	92.81 210

gbinet_0.2-2-1-0.02		81.58 234	80.59 235	82.73 228	73.97 263	89.77 245	88.25 217	82.49 193	77.59 230	73.56 179	67.87 217	71.56 196	83.06 211	82.77 242	80.22 251	95.04 227	94.38 186

pmnet_mix02		80.14 240	80.21 241	80.06 239	86.61 228	89.66 247	80.40 253	82.20 201	82.29 196	61.35 250	71.52 198	66.67 225	76.75 240	82.55 243	80.18 252	93.05 243	88.62 246

ambc			67.96 260		73.69 264	79.79 267	73.82 265		71.61 251	59.80 256	46.00 268	20.79 280	66.15 259	86.92 226	80.11 253	89.13 266	90.50 232

wanda-best-256-512		81.56 235	80.31 238	83.02 222	74.05 259	89.88 241	88.48 211	82.09 203	78.96 219	73.38 183	68.19 212	70.37 203	85.08 196	82.18 246	80.05 254	95.03 229	92.52 216

FE-blended-shiyan7		81.56 235	80.31 238	83.02 222	74.05 259	89.88 241	88.48 211	82.09 203	78.97 218	73.38 183	68.19 212	70.35 204	85.08 196	82.18 246	80.05 254	95.03 229	92.52 216

usedtu_blend_shiyan5		83.61 209	81.81 224	85.71 182	74.05 259	89.88 241	91.99 158	82.09 203	78.96 219	85.41 118	75.60 172	73.18 186	85.67 185	82.18 246	80.05 254	95.03 229	92.85 208

FE-MVSNET3		83.34 214	81.82 223	85.12 191	74.05 259	89.88 241	88.48 211	82.09 203	78.96 219	85.41 118	75.60 172	73.18 186	85.67 185	82.18 246	80.05 254	95.03 229	92.87 206

blend_shiyan4		84.25 199	82.04 219	86.82 170	82.33 246	89.89 240	90.94 167	81.51 217	81.22 203	85.41 118	75.60 172	73.18 186	85.67 185	81.60 254	79.96 258	95.08 225	92.85 208

Gipuma		58.52 262	56.17 265	61.27 260	67.14 269	58.06 272	52.16 274	68.40 264	69.00 258	45.02 273	22.79 274	20.57 281	55.11 264	76.27 261	79.33 259	79.80 270	67.16 269
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
usedtu_dtu_shiyan2		69.49 258	68.33 259	70.84 258	57.31 275	83.43 264	77.39 259	72.63 257	54.43 268	61.92 249	40.25 271	52.40 267	65.07 260	79.46 259	79.03 260	90.69 259	89.29 241

new-patchmatchnet		72.32 254	71.09 257	73.74 252	81.17 253	84.86 263	72.21 267	77.48 239	68.32 259	54.89 263	55.10 260	49.31 271	63.68 262	79.30 260	76.46 261	93.03 244	84.32 261

dtuonlycased		77.37 248	76.66 251	78.20 245	81.91 249	88.92 250	79.41 254	78.66 233	75.26 246	59.93 255	63.10 243	69.37 210	77.10 238	75.02 263	76.14 262	92.22 249	88.78 245

WB-MVS		60.76 261	66.86 262	53.64 261	82.24 247	72.70 269	48.70 276	82.04 208	63.91 265	12.91 279	64.77 237	49.00 272	22.74 275	75.95 262	75.36 263	73.22 273	66.33 270

PMMVS2		53.68 264	55.72 266	51.30 262	58.84 272	67.02 271	54.23 272	60.97 268	47.50 272	19.42 276	34.81 272	31.97 278	30.88 271	65.84 268	69.99 264	83.47 268	72.92 268

FPMVS		69.87 257	67.10 261	73.10 253	84.09 240	78.35 268	79.40 255	76.41 242	71.92 250	57.71 260	54.06 264	50.04 269	56.72 263	71.19 265	68.70 265	84.25 267	75.43 266

tmp_tt				50.24 264	68.55 268	46.86 275	48.90 275	18.28 272	86.51 159	68.32 219	70.19 206	65.33 230	26.69 273	74.37 264	66.80 266	70.72 274

PMVS	56.77 18	61.27 260	58.64 264	64.35 259	75.66 255	54.60 273	53.62 273	74.23 247	53.69 269	58.37 258	44.27 270	49.38 270	44.16 269	69.51 267	65.35 267	80.07 269	73.66 267
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	39.81 19	39.52 266	41.58 269	37.11 267	33.93 276	49.06 274	26.45 279	54.22 269	29.46 276	24.15 275	20.77 276	10.60 285	34.42 270	51.12 270	65.27 268	49.49 277	64.81 271
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		58.10 263	64.61 263	50.51 263	28.26 277	41.71 276	61.28 271	32.07 271	75.92 242	52.04 267	47.94 266	61.83 249	51.80 266	79.83 258	63.95 269	77.60 271	81.05 263

E-PMN		40.00 265	35.74 270	44.98 265	57.69 274	39.15 278	28.05 277	62.70 266	35.52 274	17.78 277	20.90 275	14.36 283	44.47 268	35.89 273	47.86 270	59.15 275	56.47 274

EMVS		39.04 267	34.32 271	44.54 266	58.25 273	39.35 277	27.61 278	62.55 267	35.99 273	16.40 278	20.04 278	14.77 282	44.80 267	33.12 274	44.10 271	57.61 276	52.89 275

VLMVS_CLIP		29.70 268	43.84 267	13.21 269	11.25 278	21.39 279	16.21 281	1.74 274	47.67 271	3.36 281	62.42 245	35.59 277	23.65 274	41.21 271	37.55 272	23.05 278	61.07 273

MVS_clip		28.15 269	43.14 268	10.65 270	8.94 279	19.20 280	9.65 282	1.75 273	51.68 270	2.21 282	56.15 257	38.39 276	27.36 272	38.12 272	36.05 273	14.00 279	62.41 272

VLMVS		17.69 270	26.31 272	7.64 271	8.91 280	13.24 281	6.52 283	1.39 275	30.98 275	5.28 280	30.66 273	28.26 279	15.43 276	21.16 275	20.12 274	8.28 280	39.73 276

MVS_baseline		8.56 271	14.59 273	1.52 273	0.64 281	1.40 284	0.33 286	0.00 279	16.79 277	0.00 286	20.45 277	13.87 284	8.04 277	10.31 276	9.13 275	0.09 283	30.19 277

testmvs		4.35 272	6.54 274	1.79 272	0.60 282	1.82 282	3.06 284	0.95 276	7.22 278	0.88 284	12.38 279	1.25 286	3.87 279	6.09 277	5.58 276	1.40 281	11.42 279

test123		3.48 273	5.31 275	1.34 274	0.20 284	1.52 283	2.17 285	0.58 277	6.13 279	0.31 285	9.85 280	0.31 287	3.90 278	2.65 278	5.28 277	0.87 282	11.46 278

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

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

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

ACM-MVS					98.26 35	97.95 55	97.46 35		93.48 55	87.20 73	92.59 38	96.71 32	93.07 74			97.52 142	97.79 70

PatchmatchNet2					85.63 235	86.94 259	78.98 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										60.42 252	61.25 250
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							98.60 9	96.48 9		96.36 4						98.66 23

TPM-MVS					98.33 32	97.85 59	97.06 41			89.97 45	93.26 35	97.16 28	93.12 73			97.79 119	95.95 157
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										60.19 253

9.14												97.28 26

SR-MVS					98.93 21			96.00 20				97.75 18

our_test_3					86.93 223	89.77 245	81.61 250

MTAPA										95.36 6		97.46 24

MTMP										95.70 5		96.90 30

Patchmatch-RL test							18.47 280

XVS					95.68 68	98.66 18	94.96 70			88.03 60		96.06 37				98.46 38

X-MVStestdata					95.68 68	98.66 18	94.96 70			88.03 60		96.06 37				98.46 38

mPP-MVS					98.76 26							95.49 44

NP-MVS									91.63 79

Patchmtry						92.39 209	89.18 200	73.30 253		71.08 199

DeepMVS_CX						71.82 270	68.37 269	48.05 270	77.38 231	46.88 272	65.77 230	47.03 274	67.48 255	64.27 269		76.89 272	76.72 265

High-resolution multi-view benchmark