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.

SED-MVS		95.53 1	95.79 1	95.23 2	97.60 10	98.92 1	95.99 6	92.05 10	97.14 2	94.19 4	94.71 8	93.25 2	95.08 1	94.32 12	92.59 16	96.49 20	99.58 3

MED-MVS		95.36 2	95.50 3	95.21 3	97.58 12	98.38 8	96.05 5	92.19 9	97.56 1	95.96 2	97.24 1	91.38 7	93.67 6	93.08 24	91.80 31	95.77 51	99.03 16

aaEdge-Enhanced		95.35 3	95.21 6	95.51 1	97.58 12	98.09 14	95.37 13	93.61 1	96.66 6	95.96 2	97.24 1	90.86 11	93.58 7	92.95 28	91.63 34	96.96 9	99.03 16

DPE-MVS		95.10 4	95.53 2	94.60 7	97.77 8	98.64 5	96.60 4	92.45 7	96.34 8	91.41 9	96.70 4	92.26 6	93.56 8	93.68 19	91.73 32	95.79 50	99.37 7
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		95.06 5	95.37 5	94.70 5	97.59 11	98.89 2	95.37 13	92.04 11	96.85 4	94.00 5	92.81 16	93.02 3	92.93 9	94.22 15	92.15 22	96.30 28	99.61 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
DVP-MVS++		95.03 6	95.03 7	95.03 4	97.91 6	98.84 3	95.80 7	91.88 13	96.65 7	93.15 6	93.79 10	90.11 14	95.03 2	94.20 17	92.39 17	96.44 24	99.22 10

MSP-MVS		95.00 7	95.47 4	94.45 8	96.78 21	98.11 12	95.72 9	90.91 17	96.68 5	91.57 8	96.98 3	89.47 17	94.76 3	95.24 3	92.15 22	96.98 8	99.64 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
CNVR-MVS		94.53 8	94.85 9	94.15 10	98.03 4	98.59 7	95.56 10	92.91 4	94.86 15	88.46 17	91.32 23	90.83 12	94.03 5	95.20 4	94.16 6	95.89 41	99.01 19

SF-MVS		94.40 9	94.15 15	94.70 5	98.25 3	98.24 10	96.86 3	93.46 3	94.87 14	90.26 12	95.96 5	88.42 20	92.76 12	92.29 34	90.84 46	96.62 15	98.44 29

APDe-MVS		94.31 10	94.30 12	94.33 9	97.57 14	98.06 15	95.79 8	91.98 12	95.50 11	92.19 7	95.25 6	87.97 23	92.93 9	93.01 26	91.02 44	95.52 56	99.29 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MCST-MVS		94.10 11	94.77 10	93.31 12	98.31 2	98.34 9	95.43 11	92.54 6	94.41 20	83.05 35	91.38 21	90.97 10	92.24 16	95.05 8	94.02 8	98.31 1	99.20 11

HPM-MVS++		94.04 12	94.96 8	92.96 14	97.93 5	97.71 21	94.65 18	91.01 16	95.91 9	87.43 19	93.52 13	92.63 5	92.29 15	94.22 15	92.34 19	94.47 85	98.37 30

NCCC		93.59 13	94.00 17	93.10 13	97.90 7	97.93 17	95.40 12	92.39 8	94.47 18	84.94 25	91.21 24	89.32 18	92.53 13	93.90 18	92.98 13	95.44 59	98.22 33

SMA-MVS		93.47 14	94.29 13	92.52 16	97.72 9	97.77 20	94.46 21	90.19 20	94.96 13	87.15 20	90.15 28	90.99 9	91.49 20	94.31 13	93.33 11	94.10 94	98.53 27
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
APD-MVS		93.47 14	93.44 20	93.50 11	97.06 17	97.09 29	95.27 16	91.47 14	95.71 10	89.57 14	93.66 11	86.28 29	92.81 11	92.06 37	90.70 47	94.83 81	98.60 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		93.36 16	94.33 11	92.22 18	94.68 46	97.89 19	94.56 19	90.89 18	94.80 16	90.04 13	93.53 12	90.14 13	89.78 27	92.74 30	92.17 20	93.35 139	99.07 15
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
TSAR-MVS + MP.		93.07 17	93.53 19	92.53 15	94.23 49	97.54 23	94.75 17	89.87 21	95.26 12	89.20 16	93.16 14	88.19 22	92.15 18	91.79 42	89.65 74	94.99 75	99.16 13
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPM-MVS		92.86 18	93.19 22	92.47 17	95.78 37	97.40 24	97.39 1	92.56 5	92.88 28	81.84 42	81.31 42	92.95 4	91.21 21	96.54 1	97.33 1	96.01 37	93.94 141

MGCNet		92.61 19	94.18 14	90.77 26	95.62 40	98.60 6	93.09 28	83.78 48	94.44 19	85.52 24	87.49 34	89.90 15	90.25 24	95.14 6	94.49 5	96.37 27	99.19 12

SteuartSystems-ACMMP		92.31 20	93.31 21	91.15 24	96.88 19	97.36 25	93.95 25	89.44 23	92.62 29	83.20 32	94.34 9	85.55 31	88.95 34	93.07 25	91.90 27	94.51 84	98.30 31
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		92.16 21	92.91 25	91.28 23	96.95 18	97.36 25	93.66 26	89.23 25	93.33 23	83.71 30	90.53 25	86.84 26	90.39 23	93.30 23	91.56 35	93.74 107	97.43 52

HFP-MVS		92.02 22	92.13 27	91.89 21	97.16 16	96.46 42	93.57 27	87.60 28	93.79 22	88.17 18	93.15 15	83.94 41	91.19 22	90.81 52	89.83 67	93.66 113	96.94 69

train_agg		91.99 23	93.71 18	89.98 30	96.42 29	97.03 32	94.31 23	89.05 26	93.33 23	77.75 53	95.06 7	88.27 21	88.38 41	92.02 39	91.41 38	94.00 98	98.84 22

DeepC-MVS_fast	86.59 2	91.69 24	91.39 30	92.05 20	97.43 15	96.92 35	94.05 24	90.23 19	93.31 26	83.19 33	77.91 49	84.23 37	92.42 14	94.62 10	94.83 3	95.00 74	97.88 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TSAR-MVS + GP.		91.29 25	93.11 24	89.18 35	87.81 94	96.21 48	92.51 36	83.83 47	94.24 21	83.77 29	91.87 20	89.62 16	90.07 25	90.40 57	90.31 53	97.09 6	99.10 14

ACMMPR		91.15 26	91.44 29	90.81 25	96.61 23	96.25 46	93.09 28	87.08 31	93.32 25	84.78 26	92.08 19	82.10 46	89.71 28	90.24 58	89.82 68	93.61 118	96.30 93

DeepPCF-MVS	86.71 1	91.00 27	94.05 16	87.43 47	95.58 41	98.17 11	86.22 96	88.59 27	97.01 3	76.77 67	85.11 38	88.90 19	87.29 49	95.02 9	94.69 4	90.15 226	99.48 6

TSAR-MVS + ACMM		90.98 28	93.18 23	88.42 40	95.69 38	96.73 37	94.52 20	86.97 34	92.99 27	76.32 73	92.31 18	86.64 27	84.40 80	92.97 27	92.02 24	92.62 166	98.59 25

MP-MVS		90.81 29	91.45 28	90.06 29	96.59 24	96.33 45	92.46 37	87.19 30	90.27 43	82.54 38	91.38 21	84.88 34	88.27 42	90.58 55	89.30 80	93.30 141	97.44 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		90.57 30	90.68 32	90.44 27	96.13 31	95.90 54	92.77 34	86.86 35	92.12 33	84.19 27	89.18 31	82.37 44	89.43 31	89.65 73	88.43 96	93.27 142	97.13 61

MSLP-MVS++		90.33 31	88.82 42	92.10 19	96.52 27	95.93 50	94.35 22	86.26 36	88.37 58	89.24 15	75.94 57	82.60 43	89.71 28	89.45 79	92.17 20	96.51 19	97.24 57

CANet		89.98 32	90.42 37	89.47 34	94.13 50	98.05 16	91.76 42	83.27 51	90.87 40	81.90 41	72.32 65	84.82 35	88.42 39	94.52 11	93.78 10	97.34 4	98.58 26

PGM-MVS		89.97 33	90.64 34	89.18 35	96.53 26	95.90 54	93.06 30	82.48 59	90.04 45	80.37 44	92.75 17	80.96 51	88.93 35	89.88 67	89.08 85	93.69 111	95.86 105

PHI-MVS		89.88 34	92.75 26	86.52 56	94.97 43	97.57 22	89.99 54	84.56 43	92.52 31	69.72 126	90.35 27	87.11 25	84.89 70	91.82 41	92.37 18	95.02 73	97.51 48

CSCG		89.81 35	89.69 38	89.96 31	96.55 25	97.90 18	92.89 32	87.06 32	88.74 55	86.17 21	78.24 48	86.53 28	84.75 74	87.82 104	90.59 49	92.32 171	98.01 36

X-MVS		89.73 36	90.65 33	88.66 38	96.44 28	95.93 50	92.26 39	86.98 33	90.73 41	76.32 73	89.56 30	82.05 47	86.51 54	89.98 65	89.60 75	93.43 134	96.72 80

MVSMamba_PlusPlus		89.35 37	90.53 35	87.97 43	88.39 87	97.06 31	90.65 49	82.45 60	94.65 17	77.06 65	79.37 45	77.40 66	92.23 17	95.16 5	94.06 7	97.04 7	96.02 100

EPNet		89.30 38	90.89 31	87.44 46	95.67 39	96.81 36	91.13 45	83.12 53	91.14 37	76.31 77	87.60 33	80.40 55	84.45 77	92.13 36	91.12 43	93.96 99	97.01 65
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepC-MVS	84.14 3	88.80 39	88.03 48	89.71 33	94.83 44	96.56 38	92.57 35	89.38 24	89.25 51	79.59 47	70.02 73	77.05 68	88.24 43	92.44 32	92.79 14	93.65 116	98.10 35
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		88.76 40	90.43 36	86.81 52	96.04 33	96.53 41	92.95 31	85.95 38	90.36 42	67.93 132	85.80 37	80.69 52	83.82 87	90.81 52	91.85 30	94.18 91	96.99 66

3Dnovator+	81.14 5	88.59 41	87.49 51	89.88 32	95.83 36	96.45 44	91.94 41	82.41 61	87.09 64	85.94 23	62.80 117	85.37 32	89.46 30	91.51 44	91.89 29	93.72 108	97.30 55

ACMMP		88.48 42	88.71 43	88.22 42	94.61 47	95.53 60	90.64 50	85.60 40	90.97 38	78.62 50	89.88 29	74.20 82	86.29 56	88.16 101	86.37 123	93.57 120	95.86 105
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
AdaColmap		88.46 43	85.75 67	91.62 22	96.25 30	95.35 65	90.71 47	91.08 15	90.22 44	86.17 21	74.33 61	73.67 85	92.00 19	86.31 129	85.82 132	93.52 123	94.53 128

3Dnovator	80.58 8	88.20 44	86.53 57	90.15 28	96.86 20	96.46 42	91.97 40	83.06 54	85.16 69	83.66 31	62.28 125	82.15 45	88.98 33	90.99 49	92.65 15	96.38 26	96.03 98

CPTT-MVS		88.17 45	87.84 49	88.55 39	93.33 52	93.75 108	92.33 38	84.75 42	89.87 47	81.72 43	83.93 39	81.12 50	88.45 38	85.42 141	84.07 153	90.72 216	96.72 80

MVS_111021_HR		87.82 46	88.84 41	86.62 54	94.42 48	97.36 25	88.21 65	83.26 52	83.42 75	72.52 106	82.63 40	76.93 69	84.95 69	91.93 40	91.15 42	96.39 25	98.49 28

DELS-MVS		87.75 47	86.92 55	88.71 37	94.69 45	97.34 28	92.78 33	84.50 44	77.87 108	81.94 40	67.17 81	75.49 77	82.84 102	95.38 2	95.93 2	95.55 55	99.27 9
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
MVSTER		87.68 48	89.12 40	86.01 58	88.11 92	90.05 153	89.28 58	77.05 117	91.37 34	79.97 45	76.70 53	85.25 33	84.89 70	93.53 20	91.41 38	96.73 13	95.55 112

MVS_111021_LR		87.58 49	88.67 44	86.31 57	92.58 56	95.89 56	86.20 97	82.49 58	89.08 53	77.47 60	86.20 36	74.22 81	85.49 62	90.03 63	88.52 94	93.66 113	96.74 78

QAPM		87.06 50	86.46 58	87.75 44	96.63 22	97.09 29	91.71 43	82.62 57	80.58 92	71.28 112	66.04 90	84.24 36	87.01 50	89.93 66	89.91 64	97.26 5	97.44 50

PVSNet_BlendedMVS		86.98 51	87.05 53	86.90 49	93.03 53	96.98 33	86.57 86	81.82 63	89.78 48	82.78 36	71.54 67	66.07 124	80.73 123	93.46 21	91.97 25	96.45 22	99.53 4

PVSNet_Blended		86.98 51	87.05 53	86.90 49	93.03 53	96.98 33	86.57 86	81.82 63	89.78 48	82.78 36	71.54 67	66.07 124	80.73 123	93.46 21	91.97 25	96.45 22	99.53 4

ETV-MVS		86.94 53	89.49 39	83.95 89	87.28 101	95.61 59	83.58 138	76.37 124	92.59 30	73.20 98	80.35 43	76.42 72	87.38 48	92.20 35	90.45 51	95.90 40	98.83 23

SPE-MVS-test		86.72 54	88.35 45	84.83 73	91.78 62	96.03 49	81.71 149	76.71 118	91.19 36	77.12 64	77.64 51	75.63 76	87.59 47	90.82 51	89.11 83	94.06 96	97.99 38

CS-MVS		86.70 55	87.61 50	85.65 60	91.33 66	95.64 58	84.73 125	76.64 120	88.68 56	77.78 52	74.87 58	72.86 89	89.09 32	92.89 29	90.18 57	94.31 89	98.16 34

EC-MVSNet		86.42 56	88.31 46	84.20 84	86.61 123	94.08 97	86.20 97	72.18 161	89.06 54	76.02 78	74.48 60	80.47 54	88.90 36	92.03 38	90.07 60	95.30 61	98.00 37

OMC-MVS		86.38 57	86.21 63	86.57 55	92.30 58	94.35 90	87.60 70	83.51 50	92.32 32	77.37 61	72.27 66	77.83 60	86.59 53	87.62 109	85.95 129	92.08 175	93.11 158

HQP-MVS		86.17 58	87.35 52	84.80 74	91.41 65	92.37 128	91.05 46	84.35 46	88.52 57	64.21 139	87.05 35	68.91 105	84.80 72	89.12 82	88.16 101	92.96 156	97.31 54

sasdasda		85.93 59	86.26 61	85.54 63	88.94 79	95.44 61	89.56 55	76.01 128	87.83 59	77.70 54	76.43 54	68.66 107	87.80 45	87.02 116	91.51 36	93.25 143	96.95 67

canonicalmvs		85.93 59	86.26 61	85.54 63	88.94 79	95.44 61	89.56 55	76.01 128	87.83 59	77.70 54	76.43 54	68.66 107	87.80 45	87.02 116	91.51 36	93.25 143	96.95 67

MAR-MVS		85.65 61	86.30 60	84.88 72	95.51 42	95.89 56	86.50 89	76.71 118	89.23 52	68.59 129	70.93 71	74.49 79	88.55 37	89.40 80	90.30 54	93.42 135	93.88 146
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	82.38 4	85.52 62	84.41 72	86.81 52	91.51 64	96.23 47	90.27 51	89.81 22	77.87 108	70.67 122	69.20 75	77.86 58	85.55 61	85.92 135	86.38 122	93.03 153	97.43 52
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CLD-MVS		85.43 63	84.24 75	86.83 51	87.69 97	93.16 119	90.01 53	82.72 56	87.17 63	79.28 49	71.43 70	65.81 127	86.02 57	87.33 112	86.96 116	95.25 67	97.83 43
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OpenMVS	77.91 11	85.09 64	83.42 79	87.03 48	96.12 32	96.55 40	89.36 57	81.59 65	79.19 102	75.20 87	55.84 165	79.04 57	84.45 77	88.47 95	89.35 79	95.48 57	95.48 113

MGCFI-Net		85.07 65	85.99 64	83.99 86	88.81 82	95.23 70	89.06 60	75.74 131	87.40 62	70.72 121	75.99 56	68.44 115	86.51 54	86.83 120	91.24 40	93.11 150	96.78 76

TSAR-MVS + COLMAP		84.93 66	85.79 66	83.92 90	90.90 68	93.57 112	89.25 59	82.00 62	91.29 35	61.66 148	88.25 32	59.46 170	86.71 52	89.79 68	87.09 113	93.01 154	91.09 182

TAPA-MVS	80.99 7	84.83 67	84.42 71	85.31 66	91.89 61	93.73 110	88.53 64	82.80 55	89.99 46	69.78 125	71.53 69	75.03 78	85.47 63	86.26 130	84.54 147	93.39 137	89.90 192
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	81.02 6	84.81 68	81.81 109	88.31 41	93.77 51	90.35 146	88.80 62	84.47 45	86.76 65	82.17 39	66.56 86	71.01 97	88.41 40	85.48 138	84.28 150	92.26 173	88.21 212
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EIA-MVS		84.75 69	86.43 59	82.79 104	86.88 112	95.36 64	82.84 145	76.39 123	87.61 61	71.03 113	74.33 61	71.12 96	85.16 64	89.69 72	88.70 92	94.40 87	98.23 32

CNLPA		84.72 70	82.14 101	87.73 45	92.85 55	93.83 104	84.70 126	85.07 41	90.90 39	83.16 34	56.28 161	71.53 93	88.14 44	84.19 149	84.00 158	92.48 168	94.26 135

MVS_Test		84.60 71	85.13 70	83.99 86	88.17 90	95.27 69	88.21 65	73.15 152	84.31 72	70.55 123	68.67 79	68.78 106	86.99 51	91.71 43	91.90 27	96.84 12	95.27 118

E2		84.16 72	82.96 85	85.55 61	87.24 105	94.92 73	86.60 85	79.90 74	78.46 106	78.56 51	65.58 95	64.57 134	84.77 73	90.00 64	90.43 52	96.22 30	96.77 77

Casviewmamba		84.10 73	82.75 89	85.67 59	87.27 102	94.54 86	86.53 88	80.07 71	80.60 91	79.92 46	63.36 112	65.36 129	85.98 58	89.75 71	89.72 71	94.25 90	95.93 104

casdiffmvs_mvg		83.97 74	82.62 92	85.54 63	87.71 95	94.38 88	88.93 61	80.11 70	77.34 112	77.57 59	63.01 115	65.95 126	84.96 68	90.69 54	90.23 56	93.95 100	96.74 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
casdiffmvs		83.84 75	82.65 91	85.22 68	87.25 104	94.62 82	86.01 103	79.62 79	79.48 99	77.59 58	61.92 128	64.34 138	85.57 60	90.55 56	90.51 50	95.26 65	97.14 60
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		83.83 76	84.38 73	83.18 103	86.65 119	94.59 84	85.79 109	73.78 149	85.83 67	72.94 99	69.28 74	70.80 99	83.45 93	86.80 121	87.59 108	96.47 21	95.77 109

diffmvs		83.69 77	83.17 83	84.31 80	85.45 139	93.92 98	86.89 75	78.62 91	82.71 81	75.95 79	66.78 85	63.90 141	83.84 86	87.90 103	89.16 81	95.10 70	97.82 44
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		83.64 78	82.24 99	85.27 67	87.13 106	94.82 76	86.47 90	79.81 75	76.49 120	77.69 57	64.03 105	63.90 141	84.40 80	89.49 77	90.26 55	96.12 31	96.68 83

hybridcas		83.63 79	81.98 103	85.55 61	87.09 107	94.43 87	86.68 81	79.77 76	78.10 107	79.32 48	61.40 131	64.87 131	84.99 67	89.59 75	89.40 77	95.46 58	96.08 97

hybridnocas07		83.51 80	82.86 87	84.26 82	85.51 138	93.82 105	85.90 108	78.82 90	83.91 73	77.18 63	67.15 82	64.53 136	83.24 98	85.43 140	88.30 98	94.90 77	96.92 71

hybrid		83.39 81	82.89 86	83.97 88	85.35 143	93.76 107	85.67 110	78.58 92	83.51 74	76.87 66	66.86 84	65.10 130	82.60 107	85.71 136	88.11 102	94.73 82	97.17 59

CANet_DTU		83.33 82	86.59 56	79.53 133	88.88 81	94.87 74	86.63 84	68.85 192	85.45 68	50.54 201	77.86 50	69.94 102	85.62 59	92.63 31	90.88 45	96.63 14	94.46 129

DI_MVS_pp		83.32 83	82.53 96	84.25 83	86.26 131	93.66 111	90.23 52	77.16 116	77.05 117	74.06 94	53.74 174	74.33 80	83.61 92	91.40 46	89.82 68	94.17 92	97.73 45

viewmanbaseed2359cas		83.27 84	82.21 100	84.51 78	87.27 102	94.83 75	86.41 91	79.61 80	77.03 118	73.99 95	63.66 108	63.85 143	84.06 83	88.94 85	90.63 48	95.72 53	96.56 86

viewdifsd2359ckpt09		83.21 85	81.85 107	84.79 75	86.60 124	94.61 83	86.12 100	79.22 83	76.41 121	76.76 68	64.54 99	62.66 153	85.00 66	89.79 68	88.69 93	95.03 72	96.29 94

viewmamba		83.12 86	82.57 94	83.76 94	85.45 139	93.77 106	85.29 114	78.87 87	84.43 71	75.48 82	65.83 92	64.57 134	83.33 96	84.73 146	87.97 103	94.16 93	96.68 83

onestephybrid01		83.11 87	82.62 92	83.69 96	85.53 135	93.84 103	85.06 121	78.84 88	82.40 83	77.70 54	65.60 93	65.49 128	81.53 115	85.34 142	87.83 107	93.48 130	97.84 42

diffmvs_AUTHOR		83.09 88	82.28 98	84.04 85	85.22 146	93.85 102	86.75 77	78.41 95	79.81 97	75.32 84	64.61 98	63.57 145	83.62 91	87.60 110	88.86 91	94.93 76	97.68 46

E3new		82.99 89	81.31 113	84.95 70	86.95 110	94.63 80	86.33 93	79.69 77	73.85 140	76.69 69	62.37 123	63.02 149	84.04 84	88.73 91	90.04 62	95.99 38	96.53 88

E3		82.98 90	81.31 113	84.92 71	86.95 110	94.63 80	86.32 94	79.69 77	73.86 139	76.54 71	62.35 124	63.05 148	84.01 85	88.73 91	90.03 63	95.99 38	96.52 89

viewdifsd2359ckpt13		82.93 91	81.75 112	84.30 81	87.00 109	94.76 77	85.59 112	79.57 81	76.32 123	74.15 91	62.74 119	62.67 151	84.44 79	89.49 77	90.15 58	95.06 71	96.13 96

baseline1		82.63 92	82.02 102	83.34 101	88.30 89	91.89 132	88.03 68	80.86 67	75.05 128	65.96 134	64.27 102	72.20 91	80.01 127	91.32 47	89.56 76	96.90 11	89.85 193

PVSNet_Blended_VisFu		82.55 93	83.70 78	81.21 117	89.66 72	95.15 72	82.41 146	77.36 115	72.53 150	73.64 96	61.15 133	77.19 67	70.35 188	91.31 48	89.72 71	93.84 103	98.85 21

ET-MVSNet_ETH3D		82.37 94	85.68 68	78.51 143	62.90 251	94.66 78	87.06 72	73.57 150	83.13 77	61.52 150	78.37 47	76.01 74	89.99 26	84.14 150	89.03 86	96.03 36	94.42 130

PMMVS		82.26 95	85.48 69	78.51 143	85.92 134	91.92 131	78.30 181	70.77 169	86.30 66	61.11 152	82.46 41	70.88 98	84.70 75	88.05 102	84.78 142	90.24 225	93.98 139

E5new		82.25 96	80.16 120	84.68 76	86.67 115	94.33 91	86.64 82	79.95 72	70.44 158	75.30 85	60.18 139	62.15 154	83.73 88	87.82 104	89.87 65	95.80 46	96.32 90

E5		82.25 96	80.16 120	84.68 76	86.67 115	94.33 91	86.64 82	79.95 72	70.44 158	75.30 85	60.18 139	62.15 154	83.73 88	87.82 104	89.87 65	95.80 46	96.32 90

ACMP	79.58 9	82.23 98	81.82 108	82.71 105	88.15 91	90.95 142	85.23 117	78.52 94	81.70 84	72.52 106	78.41 46	60.63 165	80.48 125	82.88 163	83.44 163	91.37 194	94.70 125
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewmambaseed2359dif		82.18 99	80.85 116	83.72 95	85.36 142	93.20 118	86.29 95	77.89 104	77.11 116	76.48 72	62.40 121	63.42 146	83.28 97	84.01 152	87.92 104	93.04 152	97.91 39

CHOSEN 280x420		82.15 100	85.87 65	77.80 148	86.54 126	93.42 114	81.74 148	59.96 239	78.99 104	63.99 140	74.50 59	83.95 40	80.99 118	89.53 76	85.01 137	93.56 122	95.71 111

LGP-MVS_train		82.12 101	82.57 94	81.59 111	89.26 76	90.23 149	88.76 63	78.05 96	81.26 87	61.64 149	79.52 44	62.11 158	79.59 131	85.20 143	84.68 144	92.27 172	95.02 122

E4		82.02 102	79.99 128	84.39 79	86.67 115	94.32 93	86.01 103	79.43 82	69.96 165	75.10 88	59.77 142	62.13 156	83.38 94	87.74 108	89.71 73	95.77 51	96.31 92

viewdifsd2359ckpt07		81.95 103	80.38 119	83.79 93	86.81 113	94.23 94	84.62 127	79.22 83	71.88 152	75.48 82	61.13 134	62.70 150	81.05 117	88.84 87	89.15 82	95.57 54	94.70 125

FMVSNet3		81.93 104	81.98 103	81.88 110	79.49 183	87.02 170	88.15 67	72.57 155	83.02 78	72.63 103	56.55 157	73.48 86	82.34 112	91.49 45	91.20 41	96.07 32	91.13 181

test2506		81.91 105	81.78 111	82.06 109	89.09 77	95.32 66	84.61 129	77.54 109	74.61 132	68.77 128	63.80 107	67.53 118	77.09 140	90.19 60	89.01 87	95.27 62	92.00 173

dtuplus		81.70 106	80.04 124	83.63 99	85.25 145	93.26 117	85.98 105	78.03 97	73.89 138	76.64 70	60.83 137	63.39 147	83.12 100	83.91 156	87.41 109	92.78 162	97.63 47

thisisatest0530		81.67 107	84.27 74	78.63 139	85.53 135	93.88 101	81.77 147	73.84 146	81.35 86	63.85 142	68.79 77	77.64 62	73.02 169	88.73 91	85.73 133	93.76 106	93.80 150

viewmacassd2359aftdt		81.60 108	79.90 130	83.58 100	86.67 115	94.36 89	86.02 102	79.17 85	70.40 160	71.64 110	58.95 146	62.12 157	82.55 109	87.08 115	90.14 59	95.41 60	96.24 95

tttt0517		81.51 109	84.12 77	78.47 145	85.33 144	93.74 109	81.42 152	73.84 146	81.21 88	63.59 143	68.73 78	77.46 65	73.02 169	88.47 95	85.73 133	93.63 117	93.49 154

E6new		81.43 110	79.49 133	83.69 96	86.62 121	94.23 94	84.87 122	77.93 102	69.39 170	74.14 92	59.07 144	61.48 159	82.80 104	87.23 113	89.01 87	95.80 46	96.01 101

E6		81.43 110	79.49 133	83.69 96	86.62 121	94.23 94	84.87 122	77.93 102	69.39 170	74.14 92	59.07 144	61.48 159	82.80 104	87.23 113	89.01 87	95.80 46	96.01 101

FA-MVS(training)		81.41 112	81.98 103	80.76 126	87.58 98	94.59 84	83.09 140	61.18 236	79.80 98	74.74 89	58.46 149	69.76 103	82.12 113	88.90 86	87.00 114	95.83 44	95.33 115

OPM-MVS		81.34 113	78.18 142	85.02 69	91.27 67	91.78 133	90.66 48	83.62 49	62.39 191	65.91 135	63.35 113	64.33 139	85.03 65	87.77 107	85.88 131	93.66 113	91.75 177
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		81.21 114	83.36 82	78.70 137	83.22 161	92.71 121	80.32 161	74.25 145	80.39 94	63.94 141	68.89 76	68.44 115	74.67 155	89.61 74	86.68 120	95.83 44	96.81 75

IS_MVSNet		80.92 115	84.14 76	77.16 152	87.43 99	93.90 100	80.44 157	74.64 139	75.05 128	61.10 153	65.59 94	76.89 70	67.39 204	90.88 50	90.05 61	91.95 180	96.62 85

ACMM	78.09 10	80.91 116	78.39 139	83.86 91	89.61 75	87.71 167	85.16 118	80.67 69	79.04 103	74.18 90	63.82 106	60.84 164	82.59 108	84.33 147	83.59 161	90.96 210	89.39 198
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		80.82 117	82.79 88	78.52 141	86.31 130	92.37 128	79.83 164	74.51 140	73.79 142	64.46 138	67.01 83	80.63 53	74.33 158	85.63 137	84.35 149	91.68 187	95.79 108

CostFormer		80.72 118	81.81 109	79.44 135	86.50 127	91.65 134	84.31 131	59.84 240	80.86 89	72.69 101	62.46 120	73.74 83	79.93 128	82.58 168	84.50 148	93.37 138	96.90 73

GBi-Net		80.72 118	80.49 117	81.00 122	78.18 187	86.19 184	86.73 78	72.57 155	83.02 78	72.63 103	56.55 157	73.48 86	80.99 118	86.57 123	86.83 117	94.89 78	90.77 185

test1		80.72 118	80.49 117	81.00 122	78.18 187	86.19 184	86.73 78	72.57 155	83.02 78	72.63 103	56.55 157	73.48 86	80.99 118	86.57 123	86.83 117	94.89 78	90.77 185

UGNet		80.71 121	83.09 84	77.93 147	87.02 108	92.71 121	80.28 162	76.53 121	73.83 141	71.35 111	70.07 72	73.71 84	58.93 225	87.39 111	86.97 115	93.48 130	96.94 69
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
0.3-1-1-0.015		80.56 122	80.14 122	81.04 121	76.03 206	91.03 141	86.78 76	76.11 126	80.64 90	70.88 114	62.86 116	68.56 109	82.79 106	80.60 188	84.02 157	93.67 112	93.30 156

0.4-1-1-0.2		80.56 122	80.09 123	81.10 119	76.02 207	91.04 139	86.90 74	76.23 125	80.57 93	70.87 118	62.39 122	68.47 113	82.82 103	80.69 187	84.19 151	93.72 108	93.32 155

0.4-1-1-0.1		80.27 124	79.82 132	80.80 125	75.96 209	90.95 142	86.41 91	75.70 132	80.30 95	70.74 120	61.89 129	68.45 114	82.38 111	80.37 192	83.53 162	93.60 119	93.22 157

CHOSEN 1792x2688		80.23 125	79.16 136	81.48 113	91.97 59	96.56 38	86.18 99	75.40 135	76.17 124	61.32 151	37.43 243	61.08 163	76.52 146	92.35 33	91.64 33	97.46 3	98.86 20

casdiffseed414692147		79.95 126	77.08 151	83.29 102	86.42 129	93.30 116	85.12 119	77.72 105	69.61 168	73.32 97	52.68 180	56.35 184	83.20 99	84.96 144	87.92 104	93.95 100	94.75 123

thres100view900		79.83 127	77.79 146	82.21 106	88.42 85	93.54 113	87.07 71	81.11 66	70.15 161	61.01 154	56.65 155	51.22 192	81.78 114	89.77 70	85.95 129	93.84 103	97.26 56

Effi-MVS+		79.80 128	80.04 124	79.52 134	85.53 135	93.31 115	85.28 115	70.68 171	74.15 134	58.79 163	62.03 127	60.51 166	83.37 95	88.41 97	86.09 128	93.49 129	95.80 107

ECVR-MVS		79.76 129	78.27 140	81.50 112	89.09 77	95.32 66	84.61 129	77.54 109	74.61 132	65.38 136	50.22 188	56.31 185	77.09 140	90.19 60	89.01 87	95.27 62	92.25 167

DCV-MVSNet		79.76 129	79.17 135	80.44 129	84.65 150	84.51 209	84.20 132	72.36 160	75.17 127	70.81 119	66.21 89	66.56 121	80.99 118	82.89 162	84.56 146	89.65 231	94.30 134

FC-MVSNet-train		79.54 131	78.20 141	81.09 120	86.55 125	88.63 162	79.96 163	78.53 93	70.90 156	68.24 130	65.87 91	56.45 183	80.29 126	86.20 133	84.08 152	92.97 155	95.31 117

test-LLR		79.52 132	83.42 79	74.97 161	81.79 166	91.26 135	76.17 202	70.57 172	77.71 110	52.14 186	66.26 87	77.47 63	73.10 165	87.02 116	87.16 111	96.05 34	97.02 63

FMVSNet2		79.24 133	78.14 143	80.53 128	78.18 187	86.19 184	86.73 78	71.91 162	72.97 145	70.48 124	50.63 186	66.56 121	80.99 118	90.10 62	89.77 70	94.89 78	90.77 185

TESTMET0.1,1		79.15 134	83.42 79	74.18 168	79.81 181	91.26 135	76.17 202	67.83 206	77.71 110	52.14 186	66.26 87	77.47 63	73.10 165	87.02 116	87.16 111	96.05 34	97.02 63

tfpn200view9		79.05 135	77.21 150	81.18 118	88.42 85	92.55 126	85.12 119	77.94 99	70.15 161	61.01 154	56.65 155	51.22 192	81.11 116	88.23 98	84.80 141	93.50 128	96.90 73

test1111		78.99 136	77.77 147	80.42 130	88.64 83	95.31 68	83.39 139	77.67 107	72.76 148	61.91 146	49.58 191	55.59 187	75.67 151	90.23 59	89.09 84	95.23 68	91.83 176

viewdifsd2359ckpt11		78.83 137	76.68 155	81.33 115	84.03 158	90.13 151	80.89 155	77.43 113	70.01 163	75.72 80	60.97 135	59.03 175	79.67 129	79.81 197	81.58 186	90.25 223	95.22 119

viewmsd2359difaftdt		78.82 138	76.68 155	81.33 115	84.03 158	90.13 151	80.89 155	77.43 113	70.00 164	75.68 81	60.97 135	59.01 176	79.67 129	79.82 196	81.58 186	90.25 223	95.22 119

PatchMatch-RL		78.75 139	76.47 160	81.41 114	88.53 84	91.10 137	78.09 182	77.51 112	77.33 113	71.98 108	64.38 101	48.10 210	82.55 109	84.06 151	82.35 173	89.78 228	87.97 214

LS3D		78.72 140	75.79 166	82.15 107	91.91 60	89.39 158	83.66 136	85.88 39	76.81 119	59.22 162	57.67 152	58.53 177	83.72 90	82.07 173	81.63 184	88.50 239	84.39 226

thres200		78.69 141	76.71 154	80.99 124	88.35 88	92.56 124	86.03 101	77.94 99	66.27 176	60.66 156	56.08 162	51.11 194	79.45 132	88.23 98	85.54 136	93.52 123	97.20 58

Anonymous20231211		78.61 142	75.57 169	82.15 107	84.43 154	90.26 147	84.08 134	77.68 106	71.09 154	72.90 100	39.24 237	66.21 123	84.23 82	82.15 171	84.04 154	89.61 232	96.03 98

IB-MVS	74.10 12	78.52 143	78.51 138	78.52 141	90.15 70	95.39 63	71.95 228	77.53 111	74.95 130	77.25 62	58.93 147	55.92 186	58.37 227	79.01 203	87.89 106	95.88 42	97.47 49
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
EPNet_dtu		78.49 144	81.96 106	74.45 167	92.57 57	88.74 161	82.98 141	78.83 89	83.28 76	44.64 232	77.40 52	67.73 117	53.98 237	85.44 139	84.91 138	93.71 110	86.22 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thres400		78.39 145	76.39 161	80.73 127	88.02 93	92.94 120	84.77 124	78.88 86	65.20 184	59.70 160	55.20 168	50.85 195	79.45 132	88.81 88	84.81 140	93.57 120	96.91 72

UA-Net		78.30 146	80.92 115	75.25 160	87.42 100	92.48 127	79.54 167	75.49 134	60.47 195	60.52 157	68.44 80	84.08 39	57.54 229	88.54 94	88.45 95	90.96 210	83.97 228

Vis-MVSNet (Re-imp)		78.28 147	82.68 90	73.16 180	86.64 120	92.68 123	78.07 183	74.48 141	74.05 135	53.47 174	64.22 103	76.52 71	54.28 233	88.96 84	88.29 99	92.03 177	94.00 138

MSDG		78.11 148	73.17 184	83.86 91	91.78 62	86.83 172	85.25 116	86.02 37	72.84 147	69.69 127	51.43 182	54.00 189	77.61 136	81.95 176	82.27 175	92.83 161	82.91 233

HyFIR lowres test		78.08 149	76.81 152	79.56 132	90.77 69	94.64 79	82.97 142	69.85 182	69.81 167	59.53 161	33.52 250	64.66 132	78.97 134	88.77 90	88.38 97	95.27 62	97.86 41

GeoE		78.04 150	77.52 149	78.65 138	84.51 152	90.84 144	80.94 154	69.24 190	72.86 146	66.06 133	53.45 175	60.46 167	77.37 137	84.20 148	84.85 139	93.78 105	96.00 103

test-mter		77.90 151	82.44 97	72.60 186	78.52 185	90.24 148	73.85 221	65.31 222	76.37 122	51.29 192	65.58 95	75.94 75	71.36 179	85.98 134	86.26 124	95.26 65	96.71 82

thres600view7		77.66 152	75.67 167	79.98 131	87.71 95	92.56 124	83.79 135	77.94 99	64.41 186	58.69 164	54.32 173	50.54 197	78.23 135	88.23 98	83.06 166	93.52 123	96.55 87

MS-PatchMatch		77.47 153	76.48 159	78.63 139	89.89 71	90.42 145	85.42 113	69.53 186	70.79 157	60.43 158	50.05 189	70.62 101	70.66 185	86.71 122	82.54 170	95.86 43	84.23 227

Fast-Effi-MVS+		77.37 154	76.68 155	78.17 146	82.84 163	89.94 154	81.47 151	68.01 201	72.99 144	60.26 159	55.07 169	53.20 190	82.99 101	86.47 128	86.12 127	93.46 132	92.98 161

dmvs_re		77.25 155	75.86 164	78.86 136	81.08 172	89.36 159	84.15 133	80.73 68	73.02 143	55.58 170	58.33 150	48.97 206	75.32 153	83.92 155	86.25 125	96.29 29	91.20 180

Vis-MVSNet		77.24 156	79.99 128	74.02 170	84.62 151	93.92 98	80.33 160	72.55 158	62.58 190	55.25 172	64.45 100	69.49 104	57.00 231	88.78 89	88.21 100	94.36 88	92.54 164
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MDTV_nov1_ep13		77.20 157	80.04 124	73.90 172	82.22 164	90.14 150	79.25 171	61.52 234	78.63 105	56.98 165	65.52 97	72.80 90	73.05 167	80.93 184	83.20 164	90.36 220	89.05 201

EPMVS		77.16 158	79.08 137	74.92 162	86.73 114	91.98 130	78.62 176	55.44 248	79.43 100	56.59 167	61.24 132	70.73 100	76.97 143	80.59 189	81.43 192	95.15 69	88.17 213

tpm cat1		76.93 159	76.19 163	77.79 149	85.08 149	88.58 163	82.96 143	59.33 241	75.72 126	72.64 102	51.25 183	64.41 137	75.74 150	77.90 211	80.10 208	90.97 209	95.35 114

PatchmatchNet		76.85 160	80.03 127	73.15 181	84.08 156	91.04 139	77.76 187	55.85 247	79.43 100	52.74 180	62.08 126	76.02 73	74.56 156	79.92 195	81.41 193	93.92 102	90.29 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
IterMVS-LS		76.80 161	76.33 162	77.35 151	84.07 157	84.11 210	81.54 150	68.52 194	66.17 177	61.74 147	57.84 151	64.31 140	74.88 154	83.48 159	86.21 126	93.34 140	92.16 169
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
blend_shiyan4		76.72 162	75.85 165	77.73 150	76.42 204	82.48 220	87.78 69	70.39 175	81.47 85	70.88 114	63.45 109	68.56 109	69.59 191	73.85 229	72.21 238	91.32 195	88.93 203

CDS-MVSNet		76.57 163	76.78 153	76.32 155	80.94 174	89.75 155	82.94 144	72.64 154	59.01 201	62.95 145	58.60 148	62.67 151	66.91 206	86.26 130	87.20 110	91.57 189	93.97 140
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SCA		76.41 164	79.90 130	72.35 190	84.26 155	85.24 199	75.57 209	54.56 250	79.95 96	52.72 181	64.22 103	77.84 59	73.73 162	80.48 190	81.37 194	93.25 143	90.20 191

tpmrst		76.27 165	77.65 148	74.66 164	86.13 133	89.53 157	79.31 170	54.91 249	77.19 115	56.27 168	55.87 164	64.58 133	77.25 138	80.85 185	80.21 205	94.07 95	95.32 116

dps		75.76 166	75.02 171	76.63 154	84.51 152	88.12 164	77.51 188	58.33 243	75.91 125	71.98 108	57.37 153	57.85 178	76.81 145	77.89 212	78.40 217	90.63 217	89.63 195

CR-MVSNet		74.84 167	77.91 144	71.26 204	81.77 168	85.52 195	78.32 179	54.14 252	74.05 135	51.09 195	50.00 190	71.38 95	70.77 183	86.48 126	84.03 155	91.46 193	93.92 143

Effi-MVS+-dtu		74.57 168	74.60 175	74.53 165	81.38 170	86.74 174	80.39 159	67.70 207	67.36 175	53.06 176	59.86 141	57.50 179	75.84 149	80.19 193	78.62 215	88.79 238	91.95 175

dtuonly		74.50 169	74.47 177	74.53 165	77.49 193	85.14 201	81.27 153	67.90 204	67.39 174	53.07 175	50.95 185	59.33 171	75.45 152	82.73 165	82.83 168	91.98 179	92.94 162

RPSCF		74.27 170	73.24 183	75.48 159	81.01 173	80.18 240	76.24 201	72.37 159	74.84 131	68.24 130	72.47 64	67.39 119	73.89 159	71.05 245	69.38 253	81.14 260	77.37 248

FMVSNet1		74.26 171	71.95 191	76.95 153	74.28 224	83.94 212	83.61 137	69.99 176	57.08 207	65.08 137	42.39 226	57.41 180	76.98 142	86.57 123	86.83 117	91.77 186	89.42 196

GA-MVS		73.62 172	74.52 176	72.58 187	79.93 179	89.29 160	78.02 184	71.67 165	60.79 194	42.68 237	54.41 172	49.07 205	70.07 189	89.39 81	86.55 121	93.13 149	92.12 170

Fast-Effi-MVS+-dtu		73.56 173	75.32 170	71.50 200	80.35 176	86.83 172	79.72 165	58.07 244	67.64 173	44.83 229	60.28 138	54.07 188	73.59 164	81.90 178	82.30 174	92.46 169	94.18 136

tpm		73.50 174	74.85 172	71.93 194	83.19 162	86.84 171	78.61 177	55.91 246	65.64 179	48.90 208	56.30 160	61.09 162	72.31 171	79.10 202	80.61 204	92.68 164	94.35 133

RPMNet		73.46 175	77.85 145	68.34 218	81.71 169	85.52 195	73.83 222	50.54 260	74.05 135	46.10 223	53.03 178	71.91 92	66.31 208	83.55 157	82.18 177	91.55 191	94.71 124

USDC		73.43 176	72.31 187	74.73 163	80.86 175	86.21 182	80.42 158	71.83 164	71.69 153	46.94 216	59.60 143	42.58 232	76.47 147	82.66 167	81.22 197	91.88 182	82.24 239

pmmvs4		73.38 177	71.53 194	75.55 158	75.95 210	85.24 199	77.25 192	71.59 166	71.03 155	63.10 144	49.09 196	44.22 222	73.73 162	82.04 174	80.18 206	91.68 187	88.89 205

usedtu_dtu_shiyan1		73.19 178	73.51 182	72.82 182	67.62 242	88.00 166	78.54 178	74.77 137	69.96 165	51.51 191	46.24 202	52.09 191	69.99 190	86.25 132	84.58 145	94.46 86	87.44 216

UniMVSNet_NR-MVSNet		73.11 179	72.59 185	73.71 175	76.90 197	86.58 178	77.01 193	75.82 130	65.59 180	48.82 209	50.97 184	48.42 208	71.61 175	79.19 201	83.03 167	92.11 174	94.37 131

usedtu_blend_shiyan5		73.04 180	72.10 189	74.14 169	56.36 253	82.07 222	86.93 73	69.94 177	56.27 210	70.88 114	63.45 109	68.56 109	69.59 191	73.35 231	72.06 240	91.17 200	88.93 203

FMVSNet5		72.83 181	73.89 180	71.59 198	67.42 243	76.28 250	75.88 206	63.74 227	77.27 114	54.59 173	53.32 176	71.48 94	73.85 160	81.95 176	81.69 182	94.06 96	75.20 253

PatchT		72.66 182	76.58 158	68.09 220	79.02 184	86.09 188	59.81 252	51.78 258	72.00 151	51.09 195	46.84 200	66.70 120	70.77 183	86.48 126	84.03 155	96.07 32	93.92 143

ACMH	71.22 14	72.65 183	70.13 199	75.59 157	86.19 132	86.14 187	75.76 207	77.63 108	54.79 221	46.16 222	53.28 177	47.28 212	77.24 139	78.91 204	81.18 198	90.57 218	89.33 199
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS		72.43 184	74.05 178	70.55 208	80.34 177	81.17 234	77.44 189	61.00 238	63.57 189	46.82 218	55.88 163	59.09 174	65.03 210	83.15 160	83.83 159	92.67 165	91.65 178
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH+	72.14 13	72.38 185	69.34 206	75.93 156	85.21 147	84.89 204	76.96 196	76.04 127	59.76 196	51.63 190	50.37 187	48.69 207	76.90 144	76.06 221	78.69 213	88.85 237	86.90 219

DU-MVS		72.19 186	71.35 195	73.17 179	75.95 210	86.02 189	77.01 193	74.42 142	65.39 182	48.82 209	49.10 194	42.81 230	71.61 175	78.67 205	83.10 165	91.22 198	94.37 131

IterMVS-SCA-FT		72.18 187	73.96 179	70.11 210	80.15 178	81.11 235	77.42 190	61.09 237	63.67 188	46.73 219	55.77 166	59.15 173	63.95 214	82.83 164	83.70 160	91.31 196	91.49 179

UniMVSNet (Re)		72.12 188	72.28 188	71.93 194	76.77 198	87.38 169	75.73 208	73.51 151	65.76 178	50.24 203	48.65 197	46.49 213	63.85 215	80.10 194	82.47 171	91.49 192	95.13 121

ADS-MVSNet		72.11 189	73.72 181	70.24 209	81.24 171	86.59 177	74.75 217	50.56 259	72.58 149	49.17 206	55.40 167	61.46 161	73.80 161	76.01 222	78.14 218	91.93 181	85.86 222

FE-MVSNET3		72.10 190	72.04 190	72.18 191	56.36 253	82.07 222	75.15 210	69.94 177	56.27 210	70.88 114	63.45 109	68.56 109	69.59 191	73.35 231	72.06 240	91.17 200	88.50 209

gg-mvs-nofinetune		72.10 190	74.79 173	68.97 213	83.31 160	95.22 71	85.66 111	48.77 261	35.68 261	22.17 270	30.49 253	77.73 61	76.37 148	94.30 14	93.03 12	97.55 2	97.05 62

TAMVS		72.06 192	71.76 193	72.41 189	76.68 199	88.12 164	74.82 214	68.09 199	53.52 226	56.91 166	52.94 179	56.93 182	66.91 206	81.37 181	82.44 172	91.07 206	86.99 218

v2v482		71.73 193	69.80 201	73.99 171	75.88 214	86.66 176	79.58 166	71.90 163	57.58 205	50.41 202	45.35 205	43.24 228	73.05 167	79.69 198	82.18 177	93.08 151	93.87 147

test0.0.03 1		71.70 194	74.68 174	68.23 219	81.79 166	83.81 213	68.64 232	70.57 172	68.81 172	43.47 234	62.77 118	60.09 169	51.77 245	82.48 169	81.67 183	93.16 147	83.13 231

V42		71.58 195	70.11 200	73.30 178	75.66 217	86.68 175	79.17 173	69.92 181	59.29 200	52.80 179	44.36 209	45.66 216	68.83 194	79.48 200	81.49 189	93.44 133	93.82 149

NR-MVSNet		71.47 196	71.11 196	71.90 196	77.73 192	86.02 189	76.88 197	74.42 142	65.39 182	46.09 224	49.10 194	39.87 245	64.27 213	81.40 180	82.24 176	91.99 178	93.75 151

v8		71.42 197	69.69 202	73.43 177	76.45 202	85.12 203	79.53 168	67.47 210	59.34 199	52.90 178	44.60 207	45.82 215	71.05 181	79.56 199	81.45 191	93.17 146	91.96 174

TranMVSNet+NR-MVSNet		71.12 198	70.24 198	72.15 192	76.01 208	84.80 206	76.55 199	75.65 133	61.99 192	45.29 227	48.42 198	43.07 229	67.55 202	78.28 208	82.83 168	91.85 183	92.29 165

v10		70.97 199	69.44 203	72.75 183	75.90 213	84.58 208	79.43 169	66.45 215	58.07 203	49.93 204	43.87 215	43.68 223	71.91 173	82.04 174	81.70 181	92.89 159	92.11 171

v1144		70.93 200	69.42 205	72.70 184	75.48 218	86.26 180	79.22 172	69.39 188	55.61 218	48.05 214	43.47 218	42.55 233	71.51 177	82.11 172	81.74 180	92.56 167	94.17 137

thisisatest0515		70.62 201	71.94 192	69.07 212	76.48 201	85.59 194	68.03 233	68.02 200	59.70 197	52.94 177	52.19 181	50.36 198	58.10 228	83.15 160	81.63 184	90.87 213	90.99 183

Baseline_NR-MVSNet		70.61 202	68.87 209	72.65 185	75.95 210	80.49 238	75.92 205	74.75 138	65.10 185	48.78 211	41.28 232	44.28 221	68.45 195	78.67 205	79.64 209	92.04 176	92.62 163

v148		70.34 203	68.46 212	72.54 188	76.04 205	86.38 179	74.83 213	72.73 153	55.88 217	55.26 171	43.32 221	43.49 224	64.52 212	76.93 219	80.11 207	91.85 183	93.11 158

v1192		70.32 204	68.77 210	72.12 193	74.76 220	85.62 193	78.73 174	68.53 193	55.08 220	46.34 221	42.39 226	40.67 240	71.90 174	82.27 170	81.53 188	92.43 170	93.86 148

v144192		70.10 205	68.55 211	71.90 196	74.55 221	85.67 192	77.81 185	68.22 198	54.65 222	46.91 217	42.76 224	41.27 237	70.95 182	80.48 190	81.11 202	92.96 156	93.90 145

pmmvs5		70.01 206	69.31 207	70.82 207	75.80 216	86.26 180	72.94 223	67.91 202	53.84 225	47.22 215	47.31 199	41.47 236	67.61 201	83.93 154	81.93 179	93.42 135	90.42 189

COLMAP_ROB	66.31 15	69.91 207	66.61 217	73.76 173	86.44 128	82.76 217	76.59 198	76.46 122	63.82 187	50.92 199	45.60 204	49.13 204	65.87 209	74.96 227	74.45 235	86.30 249	75.57 252
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v1921920		69.85 208	68.38 213	71.58 199	74.35 222	85.39 197	77.78 186	67.88 205	54.64 223	45.39 226	42.11 229	39.97 244	71.10 180	81.68 179	81.17 200	92.96 156	93.69 153

pm-mvs1		69.62 209	68.07 215	71.44 201	77.21 195	85.32 198	76.11 204	71.05 167	46.55 248	51.17 194	41.83 230	48.20 209	61.81 221	84.00 153	81.14 201	91.28 197	89.42 196

UniMVSNet_ETH3D		69.49 210	65.86 224	73.72 174	76.51 200	85.88 191	78.65 175	70.52 174	48.08 245	55.71 169	37.64 240	40.56 241	71.38 178	75.05 226	81.49 189	89.57 234	92.29 165

tfpnnormal		69.29 211	65.58 225	73.62 176	79.87 180	84.82 205	76.97 195	75.12 136	45.29 249	49.03 207	35.57 247	37.20 253	68.02 199	82.70 166	81.24 196	92.69 163	92.20 168

v1240		69.28 212	67.82 216	71.00 206	74.09 226	85.13 202	76.54 200	67.28 212	53.17 228	44.70 230	41.55 231	39.38 246	70.51 187	81.29 182	81.18 198	92.88 160	93.02 160

CVMVSNet		68.95 213	70.79 197	66.79 227	79.69 182	83.75 214	72.05 227	70.90 168	56.20 213	36.30 251	54.94 171	59.22 172	54.03 236	78.33 207	78.65 214	87.77 245	84.44 225

MIMVSNet		68.66 214	69.43 204	67.76 221	64.92 247	84.68 207	74.16 218	54.10 254	60.85 193	51.27 193	39.47 236	49.48 199	67.48 203	84.86 145	85.57 135	94.63 83	81.10 240

TDRefinement		67.82 215	64.91 231	71.22 205	82.08 165	81.45 229	77.42 190	73.79 148	59.62 198	48.35 213	42.35 228	42.40 234	60.87 223	74.69 228	74.64 234	84.83 254	79.20 245

wanda-best-256-512		67.61 216	66.46 220	68.94 214	56.36 253	82.07 222	75.15 210	69.94 177	56.27 210	52.66 182	43.54 216	49.41 200	68.38 196	73.35 231	72.06 240	91.17 200	88.53 207

FE-blended-shiyan7		67.61 216	66.46 220	68.94 214	56.36 253	82.07 222	75.15 210	69.94 177	56.28 209	52.66 182	43.54 216	49.41 200	68.38 196	73.35 231	72.06 240	91.17 200	88.53 207

anonymousdsp		67.61 216	68.94 208	66.04 228	71.44 238	83.97 211	66.45 237	63.53 229	50.54 237	42.42 238	49.39 192	45.63 217	62.84 218	77.99 210	81.34 195	89.59 233	93.75 151

blended_shiyan8		67.43 219	66.30 223	68.74 216	56.30 258	82.00 226	74.80 215	69.62 184	55.94 214	52.60 184	43.24 222	49.40 202	68.00 200	73.19 237	71.88 245	91.09 205	88.46 211

blended_shiyan6		67.43 219	66.32 222	68.72 217	56.29 259	81.99 227	74.78 216	69.62 184	55.89 216	52.56 185	43.36 219	49.38 203	68.03 198	73.20 236	71.89 244	91.07 206	88.50 209

TinyColmap		67.16 221	63.51 238	71.42 202	77.94 190	79.54 244	72.80 224	69.78 183	56.58 208	45.52 225	44.53 208	33.53 259	74.45 157	76.91 220	77.06 225	88.03 244	76.41 249

FC-MVSNet-test		67.04 222	72.47 186	60.70 246	76.92 196	81.41 230	61.52 249	69.45 187	65.58 181	26.74 265	61.79 130	60.40 168	41.17 255	77.60 215	77.78 221	88.41 240	82.70 235

gbinet_0.2-2-1-0.02		67.03 223	66.53 219	67.63 222	54.59 261	81.34 233	73.95 219	69.35 189	53.34 227	51.93 188	42.82 223	50.76 196	64.78 211	73.34 235	72.07 239	91.16 204	92.01 172

TransMVSNet (Re)		66.87 224	64.30 233	69.88 211	78.32 186	81.35 232	73.88 220	74.34 144	43.19 254	45.20 228	40.12 234	42.37 235	55.97 232	80.85 185	79.15 210	91.56 190	83.06 232

CMPMVS	50.59 17	66.74 225	62.72 242	71.42 202	85.40 141	89.72 156	72.69 225	70.72 170	51.24 233	51.75 189	38.91 238	44.40 219	63.74 216	70.84 247	71.52 247	84.19 255	72.45 257
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		66.43 226	65.51 226	67.51 223	71.63 237	83.10 215	70.89 231	65.02 223	50.13 240	44.68 231	39.59 235	38.77 247	62.57 219	77.59 216	78.91 211	90.29 222	90.44 188

EG-PatchMatch MVS		66.23 227	65.20 228	67.43 224	77.74 191	86.20 183	72.51 226	63.68 228	43.95 252	43.44 235	36.22 246	45.43 218	54.04 235	81.00 183	80.95 203	93.15 148	82.67 236

WR-MVS		64.98 228	66.59 218	63.09 238	74.34 223	82.68 218	64.98 243	69.17 191	54.42 224	36.18 252	44.32 210	44.35 220	44.65 248	73.60 230	77.83 220	89.21 236	88.96 202

gm-plane-assit		64.86 229	68.15 214	61.02 245	76.44 203	68.29 260	41.60 267	53.37 255	34.68 263	26.19 267	33.22 251	57.09 181	71.97 172	95.12 7	93.97 9	96.54 18	94.66 127

CP-MVSNet		64.84 230	64.97 229	64.69 233	72.09 233	81.04 236	66.66 236	67.53 209	52.45 230	37.40 246	44.00 214	38.37 249	53.54 239	72.26 241	76.93 226	90.94 212	89.75 194

MDTV_nov1_ep13_2view		64.72 231	64.94 230	64.46 234	71.14 239	81.94 228	67.53 234	54.54 251	55.92 215	43.29 236	44.02 213	43.27 227	59.87 224	71.85 243	74.77 233	90.36 220	82.82 234

MVS-HIRNet		64.63 232	64.03 237	65.33 230	75.01 219	82.84 216	58.54 256	52.10 257	55.42 219	49.29 205	29.83 256	43.48 225	66.97 205	78.28 208	78.81 212	90.07 227	79.52 244

pmnet_mix02		64.58 233	64.11 236	65.12 231	74.16 225	80.17 241	63.24 246	67.91 202	57.87 204	41.69 239	45.86 203	40.99 239	53.97 238	69.92 250	71.67 246	89.77 229	82.29 238

LTVRE_ROB	63.07 16	64.49 234	63.16 241	66.04 228	77.47 194	82.64 219	70.98 230	65.02 223	34.01 264	29.61 261	49.12 193	35.58 257	70.57 186	75.10 225	78.45 216	82.60 258	87.24 217
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
PEN-MVS		64.35 235	64.29 234	64.42 235	72.67 229	79.83 242	66.97 235	68.24 197	51.21 234	35.29 254	44.09 211	38.51 248	52.36 242	71.06 244	77.65 222	90.99 208	87.68 215

pmmvs6		64.24 236	61.77 246	67.12 225	72.39 232	81.39 231	71.33 229	65.95 221	36.05 260	48.48 212	30.55 252	43.45 226	58.75 226	77.88 213	76.36 229	85.83 250	86.70 220

pmmvs-eth3d		64.24 236	61.96 244	66.90 226	66.35 244	76.04 252	66.09 239	66.31 217	52.59 229	50.94 198	37.61 241	32.79 261	62.43 220	75.78 223	75.48 231	89.27 235	83.39 230

PS-CasMVS		64.22 238	64.19 235	64.25 236	71.86 235	80.67 237	66.42 238	67.43 211	50.64 236	36.48 249	42.60 225	37.46 252	52.56 241	71.98 242	76.69 228	90.76 214	89.29 200

WR-MVS_H		64.14 239	65.36 227	62.71 241	72.47 231	82.33 221	65.13 240	66.99 213	51.81 232	36.47 250	43.33 220	42.77 231	43.99 250	72.41 240	75.99 230	91.20 199	88.86 206

SixPastTwentyTwo		63.75 240	63.42 239	64.13 237	72.91 228	80.34 239	61.29 250	63.90 226	49.58 242	40.42 241	54.99 170	37.13 254	60.90 222	68.46 251	70.80 248	85.37 252	82.65 237

PM-MVS		63.52 241	62.51 243	64.70 232	64.79 249	76.08 251	65.07 241	62.08 232	58.13 202	46.56 220	44.98 206	31.31 263	62.89 217	72.58 239	69.93 252	86.81 247	84.55 224

DTE-MVSNet		63.26 242	63.41 240	63.08 239	72.59 230	78.56 245	65.03 242	68.28 196	50.53 238	32.38 258	44.03 212	37.79 251	49.48 246	70.83 248	76.73 227	90.73 215	85.42 223

testgi		63.11 243	64.88 232	61.05 244	75.83 215	78.51 246	60.42 251	66.20 218	48.77 243	34.56 255	56.96 154	40.35 242	40.95 256	77.46 217	77.22 224	88.37 242	74.86 255

GG-mvs-BLEND		62.08 244	88.31 46	31.46 263	0.16 275	98.10 13	91.57 44	0.09 272	85.07 70	0.21 277	73.90 63	83.74 42	0.19 273	88.98 83	89.39 78	96.58 16	99.02 18

Anonymous20231206		62.05 245	61.83 245	62.30 243	72.09 233	77.84 247	63.10 247	67.62 208	50.20 239	36.68 248	29.59 257	37.05 255	43.90 251	77.33 218	77.31 223	90.41 219	83.49 229

N_pmnet		60.52 246	58.83 250	62.50 242	68.97 241	75.61 253	59.72 254	66.47 214	51.90 231	41.26 240	35.42 248	35.63 256	52.25 243	67.07 254	70.08 251	86.35 248	76.10 250

FE-MVSNET2		60.10 247	59.87 248	60.37 247	51.97 264	77.72 248	63.63 245	66.11 219	45.14 250	36.89 247	26.42 261	33.72 258	51.78 244	77.68 214	78.09 219	91.85 183	80.29 241

dtuonlycased		59.74 248	57.09 251	62.83 240	64.59 250	76.76 249	62.72 248	62.48 231	49.65 241	44.54 233	34.46 249	45.96 214	57.26 230	54.43 260	58.78 259	85.36 253	79.58 243

EU-MVSNet		58.73 249	60.92 247	56.17 250	66.17 246	72.39 256	58.85 255	61.24 235	48.47 244	27.91 263	46.70 201	40.06 243	39.07 258	68.27 252	70.34 250	83.77 256	80.23 242

test20.03		57.93 250	59.22 249	56.44 249	71.84 236	73.78 255	53.55 261	65.96 220	43.02 255	28.46 262	37.50 242	38.17 250	30.41 262	75.25 224	74.42 236	88.41 240	72.37 258

MDA-MVSNet-bldmvs		54.99 251	52.66 256	57.71 248	52.74 263	74.87 254	55.61 258	68.41 195	43.65 253	32.54 256	37.93 239	22.11 271	54.11 234	48.85 264	67.34 254	82.85 257	73.88 256

FE-MVSNET		54.54 252	55.85 252	53.01 253	44.64 266	70.42 259	54.91 259	64.61 225	39.64 257	23.66 269	26.69 260	32.48 262	41.99 252	71.03 246	74.94 232	88.27 243	75.74 251

new-patchmatchnet		53.91 253	52.69 255	55.33 252	64.83 248	70.90 257	52.24 262	61.75 233	41.09 256	30.82 259	29.90 255	28.22 266	36.69 259	61.52 257	65.08 255	85.64 251	72.14 259

MIMVSNet1		52.76 254	53.95 254	51.38 255	41.96 268	70.79 258	53.56 260	63.03 230	39.36 258	27.83 264	22.73 264	33.07 260	34.47 261	70.49 249	72.69 237	87.41 246	68.51 260

pmmvs3		52.59 255	52.43 257	52.78 254	54.53 262	64.49 263	50.07 263	46.89 264	35.31 262	30.19 260	27.27 259	26.96 268	53.02 240	67.28 253	70.54 249	81.96 259	75.20 253

new_pmnet		50.32 256	51.36 258	49.11 257	49.19 265	64.89 262	48.66 265	47.99 263	47.55 246	26.27 266	29.51 258	28.66 265	44.89 247	61.12 258	62.74 257	77.66 262	65.03 261

FPMVS		50.25 257	45.67 261	55.58 251	70.48 240	60.12 264	59.78 253	59.33 241	46.66 247	37.94 244	30.22 254	27.51 267	35.94 260	50.98 263	47.90 263	70.02 264	56.31 262

usedtu_dtu_shiyan2		50.22 258	49.72 260	50.80 256	33.02 272	67.71 261	57.83 257	52.96 256	27.83 267	39.36 243	20.55 266	29.77 264	40.68 257	61.53 256	62.06 258	80.93 261	78.57 246

test_method		47.92 259	55.39 253	39.21 260	19.90 273	49.24 267	39.29 268	34.65 269	57.37 206	32.54 256	25.11 262	41.02 238	44.31 249	66.58 255	57.57 261	64.59 267	90.82 184

PMVS	36.83 18	40.62 260	36.39 263	45.56 258	58.40 252	33.20 270	32.62 270	56.02 245	28.25 266	37.92 245	22.29 265	26.15 269	25.29 264	48.49 265	43.82 266	63.13 268	52.53 265
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		39.74 261	42.23 262	36.84 261	66.24 245	50.82 266	26.18 273	66.39 216	31.14 265	4.85 275	37.06 244	24.28 270	7.95 270	54.48 259	54.23 262	49.46 271	43.61 266

Gipuma		35.20 262	33.96 264	36.65 262	43.30 267	32.51 271	26.96 272	48.31 262	38.87 259	20.08 271	8.08 268	7.41 275	26.44 263	53.60 261	58.43 260	54.81 269	38.79 268
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		32.52 263	33.92 265	30.88 264	34.15 271	44.70 269	27.79 271	39.69 268	22.21 268	4.31 276	15.73 267	14.13 273	12.45 269	40.11 266	47.00 264	66.88 265	53.54 263

E-PMN		21.42 264	17.56 267	25.94 265	36.25 270	19.02 274	11.56 274	43.72 266	15.25 270	6.99 273	8.04 269	4.53 277	21.77 266	16.13 269	26.16 268	35.34 272	33.77 269

MVE	25.07 19	21.25 265	23.51 266	18.62 267	15.07 274	29.77 273	10.67 276	34.60 270	12.51 271	9.46 272	7.84 270	3.82 278	14.38 268	27.45 268	42.42 267	27.56 274	40.74 267
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		20.61 266	16.32 268	25.62 266	36.41 269	18.93 275	11.51 275	43.75 265	15.65 269	6.53 274	7.56 271	4.68 276	22.03 265	14.56 270	23.10 269	33.51 273	29.77 270

testmvs		0.76 267	1.23 269	0.21 268	0.05 276	0.21 276	0.38 278	0.09 272	0.94 272	0.05 278	2.13 273	0.08 279	0.60 272	0.82 271	0.77 270	0.11 275	3.62 272

test123		0.67 268	1.11 270	0.16 269	0.01 277	0.14 277	0.20 279	0.04 274	0.77 273	0.02 279	2.15 272	0.02 280	0.61 271	0.23 272	0.72 271	0.07 276	3.76 271

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

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

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

TestfortrainingZip							95.37 13	93.61 1		96.88 1						96.96 9

TPM-MVS					98.35 1	98.66 4	96.92 2			83.78 28	90.39 26	94.36 1	94.48 4			96.58 16	93.94 141
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										39.41 242

9.14												91.16 8

SR-MVS					96.04 33			87.51 29				87.60 24

Anonymous202405211			75.59 168		85.13 148	91.06 138	84.62 127	77.96 98	69.47 169		40.79 233	63.84 144	84.57 76	83.55 157	84.69 143	89.69 230	95.75 110

our_test_3					73.80 227	79.57 243	64.47 244

ambc			50.35 259		55.61 260	59.93 265	48.73 264		44.08 251	35.81 253	24.01 263	10.64 274	41.57 254	72.83 238	63.35 256	74.99 263	77.61 247

MTAPA										91.14 10		85.84 30

MTMP										90.95 11		84.13 38

Patchmatch-RL test							8.17 277

tmp_tt				39.78 259	56.31 257	31.71 272	35.84 269	15.08 271	82.57 82	50.83 200	63.07 114	47.51 211	15.28 267	52.23 262	44.24 265	65.35 266

XVS					89.65 73	95.93 50	85.97 106			76.32 73		82.05 47				93.51 126

X-MVStestdata					89.65 73	95.93 50	85.97 106			76.32 73		82.05 47				93.51 126

mPP-MVS					95.90 35							80.22 56

NP-MVS									89.55 50

Patchmtry						87.41 168	78.32 179	54.14 252		51.09 195

DeepMVS_CX						48.96 268	43.77 266	40.58 267	50.93 235	24.67 268	36.95 245	20.18 272	41.60 253	38.92 267		52.37 270	53.31 264

High-resolution multi-view benchmark