High-res multi-view results

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

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

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

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

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

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

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

MED-MVS		95.58 1	95.75 2	95.39 2	97.71 11	98.49 9	96.09 6	92.87 5	97.56 1	96.23 2	97.24 1	91.38 8	93.67 6	93.97 18	92.54 17	95.77 51	99.03 16

SED-MVS		95.53 2	95.79 1	95.23 3	97.60 12	98.92 1	95.99 7	92.05 10	97.14 2	94.19 4	94.71 8	93.25 3	95.08 1	94.32 12	92.59 16	96.49 20	99.58 3

aaEdge-Enhanced		95.35 3	95.21 6	95.51 1	97.58 14	98.09 15	95.37 14	93.61 1	96.66 6	95.96 3	97.24 1	90.86 12	93.58 8	92.95 28	91.63 34	96.96 9	99.03 16

DPE-MVS		95.10 4	95.53 3	94.60 7	97.77 9	98.64 5	96.60 5	92.45 8	96.34 8	91.41 9	96.70 4	92.26 7	93.56 9	93.68 20	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 13	98.89 2	95.37 14	92.04 11	96.85 4	94.00 5	92.81 16	93.02 4	92.93 10	94.22 15	92.15 23	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 7	98.84 3	95.80 8	91.88 13	96.65 7	93.15 6	93.79 10	90.11 15	95.03 2	94.20 17	92.39 18	96.44 24	99.22 10

MSP-MVS		95.00 7	95.47 4	94.45 8	96.78 22	98.11 13	95.72 10	90.91 17	96.68 5	91.57 8	96.98 3	89.47 18	94.76 3	95.24 3	92.15 23	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 5	98.59 7	95.56 11	92.91 4	94.86 15	88.46 17	91.32 23	90.83 13	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 11	96.86 4	93.46 3	94.87 14	90.26 12	95.96 5	88.42 21	92.76 13	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 15	98.06 16	95.79 9	91.98 12	95.50 11	92.19 7	95.25 6	87.97 24	92.93 10	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 10	95.43 12	92.54 7	94.41 21	83.05 35	91.38 21	90.97 11	92.24 17	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 6	97.71 22	94.65 19	91.01 16	95.91 9	87.43 19	93.52 13	92.63 6	92.29 16	94.22 15	92.34 20	94.47 86	98.37 30

NCCC		93.59 13	94.00 17	93.10 13	97.90 8	97.93 18	95.40 13	92.39 9	94.47 19	84.94 25	91.21 24	89.32 19	92.53 14	93.90 19	92.98 13	95.44 60	98.22 33

SMA-MVS		93.47 14	94.29 13	92.52 16	97.72 10	97.77 21	94.46 22	90.19 20	94.96 13	87.15 20	90.15 28	90.99 10	91.49 21	94.31 13	93.33 11	94.10 95	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 18	97.09 30	95.27 17	91.47 14	95.71 10	89.57 14	93.66 11	86.28 30	92.81 12	92.06 37	90.70 47	94.83 82	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 47	97.89 20	94.56 20	90.89 18	94.80 16	90.04 13	93.53 12	90.14 14	89.78 28	92.74 30	92.17 21	93.35 140	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 50	97.54 24	94.75 18	89.87 21	95.26 12	89.20 16	93.16 14	88.19 23	92.15 19	91.79 42	89.65 74	94.99 76	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 38	97.40 25	97.39 1	92.56 6	92.88 29	81.84 42	81.31 43	92.95 5	91.21 22	96.54 1	97.33 1	96.01 37	93.94 142

MGCNet		92.61 19	94.18 14	90.77 26	95.62 41	98.60 6	93.09 29	83.78 48	94.44 20	85.52 24	87.49 34	89.90 16	90.25 25	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 20	97.36 26	93.95 26	89.44 23	92.62 30	83.20 32	94.34 9	85.55 32	88.95 35	93.07 25	91.90 28	94.51 85	98.30 31
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		92.16 21	92.91 25	91.28 23	96.95 19	97.36 26	93.66 27	89.23 25	93.33 24	83.71 30	90.53 25	86.84 27	90.39 24	93.30 24	91.56 35	93.74 108	97.43 52

HFP-MVS		92.02 22	92.13 27	91.89 21	97.16 17	96.46 43	93.57 28	87.60 28	93.79 23	88.17 18	93.15 15	83.94 42	91.19 23	90.81 52	89.83 67	93.66 114	96.94 70

train_agg		91.99 23	93.71 18	89.98 30	96.42 30	97.03 33	94.31 24	89.05 26	93.33 24	77.75 54	95.06 7	88.27 22	88.38 42	92.02 39	91.41 38	94.00 99	98.84 22

DeepC-MVS_fast	86.59 2	91.69 24	91.39 30	92.05 20	97.43 16	96.92 36	94.05 25	90.23 19	93.31 27	83.19 33	77.91 50	84.23 38	92.42 15	94.62 10	94.83 3	95.00 75	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 95	96.21 49	92.51 37	83.83 47	94.24 22	83.77 29	91.87 20	89.62 17	90.07 26	90.40 57	90.31 53	97.09 6	99.10 14

ACMMPR		91.15 26	91.44 29	90.81 25	96.61 24	96.25 47	93.09 29	87.08 31	93.32 26	84.78 26	92.08 19	82.10 47	89.71 29	90.24 58	89.82 68	93.61 119	96.30 94

DeepPCF-MVS	86.71 1	91.00 27	94.05 16	87.43 47	95.58 42	98.17 12	86.22 97	88.59 27	97.01 3	76.77 68	85.11 39	88.90 20	87.29 50	95.02 9	94.69 4	90.15 227	99.48 6

TSAR-MVS + ACMM		90.98 28	93.18 23	88.42 40	95.69 39	96.73 38	94.52 21	86.97 34	92.99 28	76.32 74	92.31 18	86.64 28	84.40 81	92.97 27	92.02 25	92.62 167	98.59 25

MP-MVS		90.81 29	91.45 28	90.06 29	96.59 25	96.33 46	92.46 38	87.19 30	90.27 44	82.54 38	91.38 21	84.88 35	88.27 43	90.58 55	89.30 80	93.30 142	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 32	95.90 55	92.77 35	86.86 35	92.12 34	84.19 27	89.18 31	82.37 45	89.43 32	89.65 73	88.43 96	93.27 143	97.13 62

MSLP-MVS++		90.33 31	88.82 42	92.10 19	96.52 28	95.93 51	94.35 23	86.26 36	88.37 59	89.24 15	75.94 58	82.60 44	89.71 29	89.45 79	92.17 21	96.51 19	97.24 57

CANet		89.98 32	90.42 37	89.47 34	94.13 51	98.05 17	91.76 43	83.27 51	90.87 41	81.90 41	72.32 66	84.82 36	88.42 40	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 27	95.90 55	93.06 31	82.48 59	90.04 46	80.37 44	92.75 17	80.96 52	88.93 36	89.88 67	89.08 85	93.69 112	95.86 106

PHI-MVS		89.88 34	92.75 26	86.52 56	94.97 44	97.57 23	89.99 55	84.56 43	92.52 32	69.72 127	90.35 27	87.11 26	84.89 71	91.82 41	92.37 19	95.02 74	97.51 48

CSCG		89.81 35	89.69 38	89.96 31	96.55 26	97.90 19	92.89 33	87.06 32	88.74 56	86.17 21	78.24 49	86.53 29	84.75 75	87.82 104	90.59 49	92.32 172	98.01 36

X-MVS		89.73 36	90.65 33	88.66 38	96.44 29	95.93 51	92.26 40	86.98 33	90.73 42	76.32 74	89.56 30	82.05 48	86.51 55	89.98 65	89.60 75	93.43 135	96.72 81

MVSMamba_PlusPlus		89.35 37	90.53 35	87.97 43	88.39 88	97.06 32	90.65 50	82.45 60	94.65 17	77.06 66	79.37 46	77.40 67	92.23 18	95.16 5	94.06 7	97.04 7	96.02 101

EPNet		89.30 38	90.89 31	87.44 46	95.67 40	96.81 37	91.13 46	83.12 53	91.14 38	76.31 78	87.60 33	80.40 56	84.45 78	92.13 36	91.12 43	93.96 100	97.01 66
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 45	96.56 39	92.57 36	89.38 24	89.25 52	79.59 47	70.02 74	77.05 69	88.24 44	92.44 32	92.79 14	93.65 117	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 34	96.53 42	92.95 32	85.95 38	90.36 43	67.93 133	85.80 38	80.69 53	83.82 88	90.81 52	91.85 31	94.18 92	96.99 67

3Dnovator+	81.14 5	88.59 41	87.49 51	89.88 32	95.83 37	96.45 45	91.94 42	82.41 61	87.09 65	85.94 23	62.80 118	85.37 33	89.46 31	91.51 44	91.89 30	93.72 109	97.30 55

ACMMP		88.48 42	88.71 43	88.22 42	94.61 48	95.53 61	90.64 51	85.60 40	90.97 39	78.62 50	89.88 29	74.20 83	86.29 57	88.16 101	86.37 123	93.57 121	95.86 106
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 31	95.35 66	90.71 48	91.08 15	90.22 45	86.17 21	74.33 62	73.67 86	92.00 20	86.31 129	85.82 132	93.52 124	94.53 129

3Dnovator	80.58 8	88.20 44	86.53 57	90.15 28	96.86 21	96.46 43	91.97 41	83.06 54	85.16 70	83.66 31	62.28 126	82.15 46	88.98 34	90.99 49	92.65 15	96.38 26	96.03 99

CPTT-MVS		88.17 45	87.84 49	88.55 39	93.33 53	93.75 109	92.33 39	84.75 42	89.87 48	81.72 43	83.93 40	81.12 51	88.45 39	85.42 141	84.07 153	90.72 217	96.72 81

MVS_111021_HR		87.82 46	88.84 41	86.62 54	94.42 49	97.36 26	88.21 66	83.26 52	83.42 76	72.52 107	82.63 41	76.93 70	84.95 70	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 46	97.34 29	92.78 34	84.50 44	77.87 109	81.94 40	67.17 82	75.49 78	82.84 103	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 93	90.05 154	89.28 59	77.05 117	91.37 35	79.97 45	76.70 54	85.25 34	84.89 71	93.53 21	91.41 38	96.73 13	95.55 113

MVS_111021_LR		87.58 49	88.67 44	86.31 57	92.58 57	95.89 57	86.20 98	82.49 58	89.08 54	77.47 61	86.20 37	74.22 82	85.49 63	90.03 63	88.52 94	93.66 114	96.74 79

QAPM		87.06 50	86.46 58	87.75 44	96.63 23	97.09 30	91.71 44	82.62 57	80.58 93	71.28 113	66.04 91	84.24 37	87.01 51	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 54	96.98 34	86.57 87	81.82 63	89.78 49	82.78 36	71.54 68	66.07 125	80.73 124	93.46 22	91.97 26	96.45 22	99.53 4

PVSNet_Blended		86.98 51	87.05 53	86.90 49	93.03 54	96.98 34	86.57 87	81.82 63	89.78 49	82.78 36	71.54 68	66.07 125	80.73 124	93.46 22	91.97 26	96.45 22	99.53 4

ETV-MVS		86.94 53	89.49 39	83.95 89	87.28 102	95.61 60	83.58 139	76.37 124	92.59 31	73.20 99	80.35 44	76.42 73	87.38 49	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 63	96.03 50	81.71 150	76.71 118	91.19 37	77.12 65	77.64 52	75.63 77	87.59 48	90.82 51	89.11 83	94.06 97	97.99 38

CS-MVS		86.70 55	87.61 50	85.65 60	91.33 67	95.64 59	84.73 126	76.64 120	88.68 57	77.78 53	74.87 59	72.86 90	89.09 33	92.89 29	90.18 57	94.31 90	98.16 34

EC-MVSNet		86.42 56	88.31 46	84.20 84	86.61 124	94.08 98	86.20 98	72.18 161	89.06 55	76.02 79	74.48 61	80.47 55	88.90 37	92.03 38	90.07 60	95.30 62	98.00 37

OMC-MVS		86.38 57	86.21 63	86.57 55	92.30 59	94.35 91	87.60 71	83.51 50	92.32 33	77.37 62	72.27 67	77.83 61	86.59 54	87.62 109	85.95 129	92.08 176	93.11 159

HQP-MVS		86.17 58	87.35 52	84.80 74	91.41 66	92.37 129	91.05 47	84.35 46	88.52 58	64.21 140	87.05 36	68.91 106	84.80 73	89.12 82	88.16 101	92.96 157	97.31 54

sasdasda		85.93 59	86.26 61	85.54 63	88.94 80	95.44 62	89.56 56	76.01 128	87.83 60	77.70 55	76.43 55	68.66 108	87.80 46	87.02 116	91.51 36	93.25 144	96.95 68

canonicalmvs		85.93 59	86.26 61	85.54 63	88.94 80	95.44 62	89.56 56	76.01 128	87.83 60	77.70 55	76.43 55	68.66 108	87.80 46	87.02 116	91.51 36	93.25 144	96.95 68

MAR-MVS		85.65 61	86.30 60	84.88 72	95.51 43	95.89 57	86.50 90	76.71 118	89.23 53	68.59 130	70.93 72	74.49 80	88.55 38	89.40 80	90.30 54	93.42 136	93.88 147
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 65	96.23 48	90.27 52	89.81 22	77.87 109	70.67 123	69.20 76	77.86 59	85.55 62	85.92 135	86.38 122	93.03 154	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 98	93.16 120	90.01 54	82.72 56	87.17 64	79.28 49	71.43 71	65.81 128	86.02 58	87.33 112	86.96 116	95.25 68	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 33	96.55 41	89.36 58	81.59 65	79.19 103	75.20 88	55.84 167	79.04 58	84.45 78	88.47 95	89.35 79	95.48 57	95.48 114

MGCFI-Net		85.07 65	85.99 64	83.99 86	88.81 83	95.23 71	89.06 61	75.74 131	87.40 63	70.72 122	75.99 57	68.44 116	86.51 55	86.83 120	91.24 40	93.11 151	96.78 77

TSAR-MVS + COLMAP		84.93 66	85.79 66	83.92 90	90.90 69	93.57 113	89.25 60	82.00 62	91.29 36	61.66 149	88.25 32	59.46 171	86.71 53	89.79 68	87.09 113	93.01 155	91.09 183

TAPA-MVS	80.99 7	84.83 67	84.42 71	85.31 66	91.89 62	93.73 111	88.53 65	82.80 55	89.99 47	69.78 126	71.53 70	75.03 79	85.47 64	86.26 130	84.54 147	93.39 138	89.90 193
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 52	90.35 147	88.80 63	84.47 45	86.76 66	82.17 39	66.56 87	71.01 98	88.41 41	85.48 138	84.28 150	92.26 174	88.21 213
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	86.88 113	95.36 65	82.84 146	76.39 123	87.61 62	71.03 114	74.33 62	71.12 97	85.16 65	89.69 72	88.70 92	94.40 88	98.23 32

CNLPA		84.72 70	82.14 101	87.73 45	92.85 56	93.83 105	84.70 127	85.07 41	90.90 40	83.16 34	56.28 162	71.53 94	88.14 45	84.19 149	84.00 158	92.48 169	94.26 136

MVS_Test		84.60 71	85.13 70	83.99 86	88.17 91	95.27 70	88.21 66	73.15 152	84.30 73	70.55 124	68.67 80	68.78 107	86.99 52	91.71 43	91.90 28	96.84 12	95.27 119

E2		84.16 72	82.96 85	85.55 61	87.24 106	94.92 74	86.60 86	79.90 74	78.46 107	78.56 51	65.58 96	64.57 135	84.77 74	90.00 64	90.43 52	96.22 30	96.77 78

Casviewmamba		84.10 73	82.75 89	85.67 59	87.27 103	94.54 87	86.53 89	80.07 71	80.60 92	79.92 46	63.36 113	65.36 130	85.98 59	89.75 71	89.72 71	94.25 91	95.93 105

casdiffmvs_mvg		83.97 74	82.62 92	85.54 63	87.71 96	94.38 89	88.93 62	80.11 70	77.34 113	77.57 60	63.01 116	65.95 127	84.96 69	90.69 54	90.23 56	93.95 101	96.74 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs		83.84 75	82.65 91	85.22 68	87.25 105	94.62 83	86.01 104	79.62 79	79.48 100	77.59 59	61.92 129	64.34 139	85.57 61	90.55 56	90.51 50	95.26 66	97.14 61
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	86.65 120	94.59 85	85.79 110	73.78 149	85.83 68	72.94 100	69.28 75	70.80 100	83.45 94	86.80 121	87.59 108	96.47 21	95.77 110

diffmvs		83.69 77	83.17 83	84.31 80	85.45 140	93.92 99	86.89 76	78.62 91	82.71 82	75.95 80	66.78 86	63.90 142	83.84 87	87.90 103	89.16 81	95.10 71	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	87.13 107	94.82 77	86.47 91	79.81 75	76.49 121	77.69 58	64.03 106	63.90 142	84.40 81	89.49 77	90.26 55	96.12 31	96.68 84

hybridcas		83.63 79	81.98 103	85.55 61	87.09 108	94.43 88	86.68 82	79.77 76	78.10 108	79.32 48	61.40 132	64.87 132	84.99 68	89.59 75	89.40 77	95.46 59	96.08 98

hybridnocas07		83.51 80	82.86 87	84.26 82	85.51 139	93.82 106	85.90 109	78.82 90	83.91 74	77.18 64	67.15 83	64.53 137	83.24 99	85.43 140	88.30 98	94.90 78	96.92 72

hybrid		83.39 81	82.89 86	83.97 88	85.35 144	93.76 108	85.67 111	78.58 92	83.51 75	76.87 67	66.86 85	65.10 131	82.60 108	85.71 136	88.11 102	94.73 83	97.17 59

CANet_DTU		83.33 82	86.59 56	79.53 133	88.88 82	94.87 75	86.63 85	68.85 192	85.45 69	50.54 202	77.86 51	69.94 103	85.62 60	92.63 31	90.88 45	96.63 14	94.46 130

DI_MVS_pp		83.32 83	82.53 96	84.25 83	86.26 132	93.66 112	90.23 53	77.16 116	77.05 118	74.06 95	53.74 176	74.33 81	83.61 93	91.40 46	89.82 68	94.17 93	97.73 45

viewmanbaseed2359cas		83.27 84	82.21 100	84.51 78	87.27 103	94.83 76	86.41 92	79.61 80	77.03 119	73.99 96	63.66 109	63.85 144	84.06 84	88.94 85	90.63 48	95.72 53	96.56 87

viewdifsd2359ckpt09		83.21 85	81.85 107	84.79 75	86.60 125	94.61 84	86.12 101	79.22 83	76.41 122	76.76 69	64.54 100	62.66 154	85.00 67	89.79 68	88.69 93	95.03 73	96.29 95

viewmamba		83.12 86	82.57 94	83.76 94	85.45 140	93.77 107	85.29 115	78.87 87	84.43 72	75.48 83	65.83 93	64.57 135	83.33 97	84.73 146	87.97 103	94.16 94	96.68 84

onestephybrid01		83.11 87	82.62 92	83.69 96	85.53 136	93.84 104	85.06 122	78.84 88	82.40 84	77.70 55	65.60 94	65.49 129	81.53 116	85.34 142	87.83 107	93.48 131	97.84 42

diffmvs_AUTHOR		83.09 88	82.28 98	84.04 85	85.22 147	93.85 103	86.75 78	78.41 95	79.81 98	75.32 85	64.61 99	63.57 146	83.62 92	87.60 110	88.86 91	94.93 77	97.68 46

E3new		82.99 89	81.31 113	84.95 70	86.95 111	94.63 81	86.33 94	79.69 77	73.85 141	76.69 70	62.37 124	63.02 150	84.04 85	88.73 91	90.04 62	95.99 38	96.53 89

E3		82.98 90	81.31 113	84.92 71	86.95 111	94.63 81	86.32 95	79.69 77	73.86 140	76.54 72	62.35 125	63.05 149	84.01 86	88.73 91	90.03 63	95.99 38	96.52 90

viewdifsd2359ckpt13		82.93 91	81.75 112	84.30 81	87.00 110	94.76 78	85.59 113	79.57 81	76.32 124	74.15 92	62.74 120	62.67 152	84.44 80	89.49 77	90.15 58	95.06 72	96.13 97

baseline1		82.63 92	82.02 102	83.34 101	88.30 90	91.89 133	88.03 69	80.86 67	75.05 129	65.96 135	64.27 103	72.20 92	80.01 128	91.32 47	89.56 76	96.90 11	89.85 194

PVSNet_Blended_VisFu		82.55 93	83.70 78	81.21 117	89.66 73	95.15 73	82.41 147	77.36 115	72.53 151	73.64 97	61.15 134	77.19 68	70.35 189	91.31 48	89.72 71	93.84 104	98.85 21

ET-MVSNet_ETH3D		82.37 94	85.68 68	78.51 143	62.90 253	94.66 79	87.06 73	73.57 150	83.13 78	61.52 151	78.37 48	76.01 75	89.99 27	84.14 150	89.03 86	96.03 36	94.42 131

PMMVS		82.26 95	85.48 69	78.51 143	85.92 135	91.92 132	78.30 182	70.77 169	86.30 67	61.11 153	82.46 42	70.88 99	84.70 76	88.05 102	84.78 142	90.24 226	93.98 140

E5new		82.25 96	80.16 120	84.68 76	86.67 116	94.33 92	86.64 83	79.95 72	70.44 159	75.30 86	60.18 140	62.15 155	83.73 89	87.82 104	89.87 65	95.80 46	96.32 91

E5		82.25 96	80.16 120	84.68 76	86.67 116	94.33 92	86.64 83	79.95 72	70.44 159	75.30 86	60.18 140	62.15 155	83.73 89	87.82 104	89.87 65	95.80 46	96.32 91

ACMP	79.58 9	82.23 98	81.82 108	82.71 105	88.15 92	90.95 143	85.23 118	78.52 94	81.70 85	72.52 107	78.41 47	60.63 166	80.48 126	82.88 163	83.44 163	91.37 195	94.70 126
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
viewmambaseed2359dif		82.18 99	80.85 116	83.72 95	85.36 143	93.20 119	86.29 96	77.89 104	77.11 117	76.48 73	62.40 122	63.42 147	83.28 98	84.01 152	87.92 104	93.04 153	97.91 39

CHOSEN 280x420		82.15 100	85.87 65	77.80 148	86.54 127	93.42 115	81.74 149	59.96 239	78.99 105	63.99 141	74.50 60	83.95 41	80.99 119	89.53 76	85.01 137	93.56 123	95.71 112

LGP-MVS_train		82.12 101	82.57 94	81.59 111	89.26 77	90.23 150	88.76 64	78.05 96	81.26 88	61.64 150	79.52 45	62.11 159	79.59 132	85.20 143	84.68 144	92.27 173	95.02 123

E4		82.02 102	79.99 128	84.39 79	86.67 116	94.32 94	86.01 104	79.43 82	69.96 166	75.10 89	59.77 143	62.13 157	83.38 95	87.74 108	89.71 73	95.77 51	96.31 93

viewdifsd2359ckpt07		81.95 103	80.38 119	83.79 93	86.81 114	94.23 95	84.62 128	79.22 83	71.88 153	75.48 83	61.13 135	62.70 151	81.05 118	88.84 87	89.15 82	95.57 54	94.70 126

FMVSNet3		81.93 104	81.98 103	81.88 110	79.49 184	87.02 171	88.15 68	72.57 155	83.02 79	72.63 104	56.55 158	73.48 87	82.34 113	91.49 45	91.20 41	96.07 32	91.13 182

test2506		81.91 105	81.78 111	82.06 109	89.09 78	95.32 67	84.61 130	77.54 109	74.61 133	68.77 129	63.80 108	67.53 119	77.09 141	90.19 60	89.01 87	95.27 63	92.00 174

dtuplus		81.70 106	80.04 124	83.63 99	85.25 146	93.26 118	85.98 106	78.03 97	73.89 139	76.64 71	60.83 138	63.39 148	83.12 101	83.91 156	87.41 109	92.77 163	97.63 47

thisisatest0530		81.67 107	84.27 74	78.63 139	85.53 136	93.88 102	81.77 148	73.84 146	81.35 87	63.85 143	68.79 78	77.64 63	73.02 170	88.73 91	85.73 133	93.76 107	93.80 151

viewmacassd2359aftdt		81.60 108	79.90 130	83.58 100	86.67 116	94.36 90	86.02 103	79.17 85	70.40 161	71.64 111	58.95 147	62.12 158	82.55 110	87.08 115	90.14 59	95.41 61	96.24 96

tttt0517		81.51 109	84.12 77	78.47 145	85.33 145	93.74 110	81.42 153	73.84 146	81.21 89	63.59 144	68.73 79	77.46 66	73.02 170	88.47 95	85.73 133	93.63 118	93.49 155

E6new		81.43 110	79.49 133	83.69 96	86.62 122	94.23 95	84.87 123	77.93 102	69.39 171	74.14 93	59.07 145	61.48 160	82.80 105	87.23 113	89.01 87	95.80 46	96.01 102

E6		81.43 110	79.49 133	83.69 96	86.62 122	94.23 95	84.87 123	77.93 102	69.39 171	74.14 93	59.07 145	61.48 160	82.80 105	87.23 113	89.01 87	95.80 46	96.01 102

FA-MVS(training)		81.41 112	81.98 103	80.76 126	87.58 99	94.59 85	83.09 141	61.18 236	79.80 99	74.74 90	58.46 150	69.76 104	82.12 114	88.90 86	87.00 114	95.83 44	95.33 116

OPM-MVS		81.34 113	78.18 142	85.02 69	91.27 68	91.78 134	90.66 49	83.62 49	62.39 192	65.91 136	63.35 114	64.33 140	85.03 66	87.77 107	85.88 131	93.66 114	91.75 178
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	83.22 162	92.71 122	80.32 162	74.25 145	80.39 95	63.94 142	68.89 77	68.44 116	74.67 156	89.61 74	86.68 120	95.83 44	96.81 76

IS_MVSNet		80.92 115	84.14 76	77.16 152	87.43 100	93.90 101	80.44 158	74.64 139	75.05 129	61.10 154	65.59 95	76.89 71	67.39 205	90.88 50	90.05 61	91.95 181	96.62 86

ACMM	78.09 10	80.91 116	78.39 139	83.86 91	89.61 76	87.71 168	85.16 119	80.67 69	79.04 104	74.18 91	63.82 107	60.84 165	82.59 109	84.33 147	83.59 161	90.96 211	89.39 199
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	86.31 131	92.37 129	79.83 165	74.51 140	73.79 143	64.46 139	67.01 84	80.63 54	74.33 159	85.63 137	84.35 149	91.68 188	95.79 109

CostFormer		80.72 118	81.81 109	79.44 135	86.50 128	91.65 135	84.31 132	59.84 240	80.86 90	72.69 102	62.46 121	73.74 84	79.93 129	82.58 168	84.50 148	93.37 139	96.90 74

GBi-Net		80.72 118	80.49 117	81.00 122	78.18 188	86.19 185	86.73 79	72.57 155	83.02 79	72.63 104	56.55 158	73.48 87	80.99 119	86.57 123	86.83 117	94.89 79	90.77 186

test1		80.72 118	80.49 117	81.00 122	78.18 188	86.19 185	86.73 79	72.57 155	83.02 79	72.63 104	56.55 158	73.48 87	80.99 119	86.57 123	86.83 117	94.89 79	90.77 186

UGNet		80.71 121	83.09 84	77.93 147	87.02 109	92.71 122	80.28 163	76.53 121	73.83 142	71.35 112	70.07 73	73.71 85	58.93 226	87.39 111	86.97 115	93.48 131	96.94 70
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	76.03 207	91.03 142	86.78 77	76.11 126	80.64 91	70.88 115	62.86 117	68.56 110	82.79 107	80.60 188	84.02 157	93.67 113	93.30 157

0.4-1-1-0.2		80.56 122	80.09 123	81.10 119	76.02 208	91.04 140	86.90 75	76.23 125	80.57 94	70.87 119	62.39 123	68.47 114	82.82 104	80.69 187	84.19 151	93.72 109	93.32 156

0.4-1-1-0.1		80.27 124	79.82 132	80.80 125	75.96 210	90.95 143	86.41 92	75.70 132	80.30 96	70.74 121	61.89 130	68.45 115	82.38 112	80.37 192	83.53 162	93.60 120	93.22 158

CHOSEN 1792x2688		80.23 125	79.16 136	81.48 113	91.97 60	96.56 39	86.18 100	75.40 135	76.17 125	61.32 152	37.43 246	61.08 164	76.52 147	92.35 33	91.64 33	97.46 3	98.86 20

casdiffseed414692147		79.95 126	77.08 151	83.29 102	86.42 130	93.30 117	85.12 120	77.72 105	69.61 169	73.32 98	52.68 182	56.35 185	83.20 100	84.96 144	87.92 104	93.95 101	94.75 124

thres100view900		79.83 127	77.79 146	82.21 106	88.42 86	93.54 114	87.07 72	81.11 66	70.15 162	61.01 155	56.65 156	51.22 193	81.78 115	89.77 70	85.95 129	93.84 104	97.26 56

Effi-MVS+		79.80 128	80.04 124	79.52 134	85.53 136	93.31 116	85.28 116	70.68 171	74.15 135	58.79 164	62.03 128	60.51 167	83.37 96	88.41 97	86.09 128	93.49 130	95.80 108

ECVR-MVS		79.76 129	78.27 140	81.50 112	89.09 78	95.32 67	84.61 130	77.54 109	74.61 133	65.38 137	50.22 190	56.31 186	77.09 141	90.19 60	89.01 87	95.27 63	92.25 168

DCV-MVSNet		79.76 129	79.17 135	80.44 129	84.65 151	84.51 210	84.20 133	72.36 160	75.17 128	70.81 120	66.21 90	66.56 122	80.99 119	82.89 162	84.56 146	89.65 232	94.30 135

FC-MVSNet-train		79.54 131	78.20 141	81.09 120	86.55 126	88.63 163	79.96 164	78.53 93	70.90 157	68.24 131	65.87 92	56.45 184	80.29 127	86.20 133	84.08 152	92.97 156	95.31 118

test-LLR		79.52 132	83.42 79	74.97 161	81.79 167	91.26 136	76.17 203	70.57 172	77.71 111	52.14 187	66.26 88	77.47 64	73.10 166	87.02 116	87.16 111	96.05 34	97.02 64

FMVSNet2		79.24 133	78.14 143	80.53 128	78.18 188	86.19 185	86.73 79	71.91 162	72.97 146	70.48 125	50.63 188	66.55 123	80.99 119	90.10 62	89.77 70	94.89 79	90.77 186

TESTMET0.1,1		79.15 134	83.42 79	74.18 168	79.81 182	91.26 136	76.17 203	67.83 206	77.71 111	52.14 187	66.26 88	77.47 64	73.10 166	87.02 116	87.16 111	96.05 34	97.02 64

tfpn200view9		79.05 135	77.21 150	81.18 118	88.42 86	92.55 127	85.12 120	77.94 99	70.15 162	61.01 155	56.65 156	51.22 193	81.11 117	88.23 98	84.80 141	93.50 129	96.90 74

test1111		78.99 136	77.77 147	80.42 130	88.64 84	95.31 69	83.39 140	77.67 107	72.76 149	61.91 147	49.58 193	55.59 188	75.67 152	90.23 59	89.09 84	95.23 69	91.83 177

viewdifsd2359ckpt11		78.83 137	76.68 155	81.33 115	84.03 159	90.13 152	80.89 156	77.43 113	70.01 164	75.72 81	60.97 136	59.03 176	79.67 130	79.81 197	81.58 186	90.25 224	95.22 120

viewmsd2359difaftdt		78.82 138	76.68 155	81.33 115	84.03 159	90.13 152	80.89 156	77.43 113	70.00 165	75.68 82	60.97 136	59.01 177	79.67 130	79.82 196	81.58 186	90.25 224	95.22 120

PatchMatch-RL		78.75 139	76.47 160	81.41 114	88.53 85	91.10 138	78.09 183	77.51 112	77.33 114	71.98 109	64.38 102	48.10 211	82.55 110	84.06 151	82.35 173	89.78 229	87.97 215

LS3D		78.72 140	75.79 166	82.15 107	91.91 61	89.39 159	83.66 137	85.88 39	76.81 120	59.22 163	57.67 153	58.53 178	83.72 91	82.07 173	81.63 184	88.50 240	84.39 227

thres200		78.69 141	76.71 154	80.99 124	88.35 89	92.56 125	86.03 102	77.94 99	66.27 177	60.66 157	56.08 163	51.11 195	79.45 133	88.23 98	85.54 136	93.52 124	97.20 58

Anonymous20231211		78.61 142	75.57 169	82.15 107	84.43 155	90.26 148	84.08 135	77.68 106	71.09 155	72.90 101	39.24 240	66.21 124	84.23 83	82.15 171	84.04 154	89.61 233	96.03 99

IB-MVS	74.10 12	78.52 143	78.51 138	78.52 141	90.15 71	95.39 64	71.95 229	77.53 111	74.95 131	77.25 63	58.93 148	55.92 187	58.37 228	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 58	88.74 162	82.98 142	78.83 89	83.28 77	44.64 233	77.40 53	67.73 118	53.98 238	85.44 139	84.91 138	93.71 111	86.22 222
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 94	92.94 121	84.77 125	78.88 86	65.20 185	59.70 161	55.20 170	50.85 196	79.45 133	88.81 88	84.81 140	93.57 121	96.91 73

UA-Net		78.30 146	80.92 115	75.25 160	87.42 101	92.48 128	79.54 168	75.49 134	60.47 196	60.52 158	68.44 81	84.08 40	57.54 230	88.54 94	88.45 95	90.96 211	83.97 229

Vis-MVSNet (Re-imp)		78.28 147	82.68 90	73.16 180	86.64 121	92.68 124	78.07 184	74.48 141	74.05 136	53.47 175	64.22 104	76.52 72	54.28 234	88.96 84	88.29 99	92.03 178	94.00 139

MSDG		78.11 148	73.17 184	83.86 91	91.78 63	86.83 173	85.25 117	86.02 37	72.84 148	69.69 128	51.43 184	54.00 190	77.61 137	81.95 176	82.27 175	92.83 162	82.91 234

HyFIR lowres test		78.08 149	76.81 152	79.56 132	90.77 70	94.64 80	82.97 143	69.85 182	69.81 168	59.53 162	33.52 254	64.66 133	78.97 135	88.77 90	88.38 97	95.27 63	97.86 41

GeoE		78.04 150	77.52 149	78.65 138	84.51 153	90.84 145	80.94 155	69.24 190	72.86 147	66.06 134	53.45 177	60.46 168	77.37 138	84.20 148	84.85 139	93.78 106	96.00 104

test-mter		77.90 151	82.44 97	72.60 186	78.52 186	90.24 149	73.85 222	65.31 222	76.37 123	51.29 193	65.58 96	75.94 76	71.36 180	85.98 134	86.26 124	95.26 66	96.71 83

thres600view7		77.66 152	75.67 167	79.98 131	87.71 96	92.56 125	83.79 136	77.94 99	64.41 187	58.69 165	54.32 175	50.54 198	78.23 136	88.23 98	83.06 166	93.52 124	96.55 88

MS-PatchMatch		77.47 153	76.48 159	78.63 139	89.89 72	90.42 146	85.42 114	69.53 186	70.79 158	60.43 159	50.05 191	70.62 102	70.66 186	86.71 122	82.54 170	95.86 43	84.23 228

Fast-Effi-MVS+		77.37 154	76.68 155	78.17 146	82.84 164	89.94 155	81.47 152	68.01 201	72.99 145	60.26 160	55.07 171	53.20 191	82.99 102	86.47 128	86.12 127	93.46 133	92.98 162

dmvs_re		77.25 155	75.86 164	78.86 136	81.08 173	89.36 160	84.15 134	80.73 68	73.02 144	55.58 171	58.33 151	48.97 207	75.32 154	83.92 155	86.25 125	96.29 29	91.20 181

Vis-MVSNet		77.24 156	79.99 128	74.02 170	84.62 152	93.92 99	80.33 161	72.55 158	62.58 191	55.25 173	64.45 101	69.49 105	57.00 232	88.78 89	88.21 100	94.36 89	92.54 165
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	82.22 165	90.14 151	79.25 172	61.52 234	78.63 106	56.98 166	65.52 98	72.80 91	73.05 168	80.93 184	83.20 164	90.36 221	89.05 202

EPMVS		77.16 158	79.08 137	74.92 162	86.73 115	91.98 131	78.62 177	55.44 248	79.43 101	56.59 168	61.24 133	70.73 101	76.97 144	80.59 189	81.43 192	95.15 70	88.17 214

tpm cat1		76.93 159	76.19 163	77.79 149	85.08 150	88.58 164	82.96 144	59.33 241	75.72 127	72.64 103	51.25 185	64.41 138	75.74 151	77.90 211	80.10 208	90.97 210	95.35 115

PatchmatchNet		76.85 160	80.03 127	73.15 181	84.08 157	91.04 140	77.76 188	55.85 247	79.43 101	52.74 181	62.08 127	76.02 74	74.56 157	79.92 195	81.41 193	93.92 103	90.29 191
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	84.07 158	84.11 211	81.54 151	68.52 194	66.17 178	61.74 148	57.84 152	64.31 141	74.88 155	83.48 159	86.21 126	93.34 141	92.16 170
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	76.42 205	82.48 221	87.78 70	70.39 175	81.47 86	70.88 115	63.45 110	68.56 110	69.59 192	73.85 229	72.21 238	91.32 196	88.93 204

CDS-MVSNet		76.57 163	76.78 153	76.32 155	80.94 175	89.75 156	82.94 145	72.64 154	59.01 202	62.95 146	58.60 149	62.67 152	66.91 207	86.26 130	87.20 110	91.57 190	93.97 141
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	84.26 156	85.24 200	75.57 210	54.56 250	79.95 97	52.72 182	64.22 104	77.84 60	73.73 163	80.48 190	81.37 194	93.25 144	90.20 192

tpmrst		76.27 165	77.65 148	74.66 164	86.13 134	89.53 158	79.31 171	54.91 249	77.19 116	56.27 169	55.87 166	64.58 134	77.25 139	80.85 185	80.21 205	94.07 96	95.32 117

dps		75.76 166	75.02 171	76.63 154	84.51 153	88.12 165	77.51 189	58.33 243	75.91 126	71.98 109	57.37 154	57.85 179	76.81 146	77.89 212	78.40 217	90.63 218	89.63 196

CR-MVSNet		74.84 167	77.91 144	71.26 204	81.77 169	85.52 196	78.32 180	54.14 252	74.05 136	51.09 196	50.00 192	71.38 96	70.77 184	86.48 126	84.03 155	91.46 194	93.92 144

Effi-MVS+-dtu		74.57 168	74.60 175	74.53 165	81.38 171	86.74 175	80.39 160	67.70 207	67.36 176	53.06 177	59.86 142	57.50 180	75.84 150	80.19 193	78.62 215	88.79 239	91.95 176

dtuonly		74.50 169	74.47 177	74.53 165	77.49 194	85.14 202	81.27 154	67.90 204	67.39 175	53.07 176	50.95 187	59.33 172	75.45 153	82.73 165	82.83 168	91.98 180	92.94 163

RPSCF		74.27 170	73.24 183	75.48 159	81.01 174	80.18 241	76.24 202	72.37 159	74.84 132	68.24 131	72.47 65	67.39 120	73.89 160	71.05 245	69.38 254	81.14 262	77.37 249

FMVSNet1		74.26 171	71.95 191	76.95 153	74.28 225	83.94 213	83.61 138	69.99 176	57.08 208	65.08 138	42.39 229	57.41 181	76.98 143	86.57 123	86.83 117	91.77 187	89.42 197

GA-MVS		73.62 172	74.52 176	72.58 187	79.93 180	89.29 161	78.02 185	71.67 165	60.79 195	42.68 238	54.41 174	49.07 206	70.07 190	89.39 81	86.55 121	93.13 150	92.12 171

Fast-Effi-MVS+-dtu		73.56 173	75.32 170	71.50 200	80.35 177	86.83 173	79.72 166	58.07 244	67.64 174	44.83 230	60.28 139	54.07 189	73.59 165	81.90 178	82.30 174	92.46 170	94.18 137

tpm		73.50 174	74.85 172	71.93 194	83.19 163	86.84 172	78.61 178	55.91 246	65.64 180	48.90 209	56.30 161	61.09 163	72.31 172	79.10 202	80.61 204	92.68 165	94.35 134

RPMNet		73.46 175	77.85 145	68.34 218	81.71 170	85.52 196	73.83 223	50.54 260	74.05 136	46.10 224	53.03 180	71.91 93	66.31 209	83.55 157	82.18 177	91.55 192	94.71 125

USDC		73.43 176	72.31 187	74.73 163	80.86 176	86.21 183	80.42 159	71.83 164	71.69 154	46.94 217	59.60 144	42.58 233	76.47 148	82.66 167	81.22 197	91.88 183	82.24 240

pmmvs4		73.38 177	71.53 194	75.55 158	75.95 211	85.24 200	77.25 193	71.59 166	71.03 156	63.10 145	49.09 198	44.22 223	73.73 163	82.04 174	80.18 206	91.68 188	88.89 206

usedtu_dtu_shiyan1		73.19 178	73.51 182	72.82 182	67.62 244	88.00 167	78.54 179	74.77 137	69.96 166	51.51 192	46.24 205	52.09 192	69.99 191	86.25 132	84.58 145	94.46 87	87.44 217

UniMVSNet_NR-MVSNet		73.11 179	72.59 185	73.71 175	76.90 198	86.58 179	77.01 194	75.82 130	65.59 181	48.82 210	50.97 186	48.42 209	71.61 176	79.19 201	83.03 167	92.11 175	94.37 132

usedtu_blend_shiyan5		73.04 180	72.10 189	74.14 169	56.36 255	82.07 223	86.93 74	69.94 177	56.27 211	70.88 115	63.45 110	68.56 110	69.59 192	73.35 231	72.06 240	91.17 201	88.93 204

FMVSNet5		72.83 181	73.89 180	71.59 198	67.42 245	76.28 251	75.88 207	63.74 227	77.27 115	54.59 174	53.32 178	71.48 95	73.85 161	81.95 176	81.69 182	94.06 97	75.20 255

PatchT		72.66 182	76.58 158	68.09 220	79.02 185	86.09 189	59.81 254	51.78 258	72.00 152	51.09 196	46.84 203	66.70 121	70.77 184	86.48 126	84.03 155	96.07 32	93.92 144

ACMH	71.22 14	72.65 183	70.13 199	75.59 157	86.19 133	86.14 188	75.76 208	77.63 108	54.79 222	46.16 223	53.28 179	47.28 213	77.24 140	78.91 204	81.18 198	90.57 219	89.33 200
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	80.34 178	81.17 235	77.44 190	61.00 238	63.57 190	46.82 219	55.88 165	59.09 175	65.03 211	83.15 160	83.83 159	92.67 166	91.65 179
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	85.21 148	84.89 205	76.96 197	76.04 127	59.76 197	51.63 191	50.37 189	48.69 208	76.90 145	76.06 221	78.69 213	88.85 238	86.90 220

DU-MVS		72.19 186	71.35 195	73.17 179	75.95 211	86.02 190	77.01 194	74.42 142	65.39 183	48.82 210	49.10 196	42.81 231	71.61 176	78.67 205	83.10 165	91.22 199	94.37 132

IterMVS-SCA-FT		72.18 187	73.96 179	70.11 210	80.15 179	81.11 236	77.42 191	61.09 237	63.67 189	46.73 220	55.77 168	59.15 174	63.95 215	82.83 164	83.70 160	91.31 197	91.49 180

UniMVSNet (Re)		72.12 188	72.28 188	71.93 194	76.77 199	87.38 170	75.73 209	73.51 151	65.76 179	50.24 204	48.65 199	46.49 214	63.85 216	80.10 194	82.47 171	91.49 193	95.13 122

ADS-MVSNet		72.11 189	73.72 181	70.24 209	81.24 172	86.59 178	74.75 218	50.56 259	72.58 150	49.17 207	55.40 169	61.46 162	73.80 162	76.01 222	78.14 218	91.93 182	85.86 223

FE-MVSNET3		72.10 190	72.04 190	72.18 191	56.36 255	82.07 223	75.15 211	69.94 177	56.27 211	70.88 115	63.45 110	68.56 110	69.59 192	73.35 231	72.06 240	91.17 201	88.50 210

gg-mvs-nofinetune		72.10 190	74.79 173	68.97 213	83.31 161	95.22 72	85.66 112	48.77 261	35.68 263	22.17 272	30.49 258	77.73 62	76.37 149	94.30 14	93.03 12	97.55 2	97.05 63

TAMVS		72.06 192	71.76 193	72.41 189	76.68 200	88.12 165	74.82 215	68.09 199	53.52 227	56.91 167	52.94 181	56.93 183	66.91 207	81.37 181	82.44 172	91.07 207	86.99 219

v2v482		71.73 193	69.80 201	73.99 171	75.88 215	86.66 177	79.58 167	71.90 163	57.58 206	50.41 203	45.35 208	43.24 229	73.05 168	79.69 198	82.18 177	93.08 152	93.87 148

test0.0.03 1		71.70 194	74.68 174	68.23 219	81.79 167	83.81 214	68.64 233	70.57 172	68.81 173	43.47 235	62.77 119	60.09 170	51.77 247	82.48 169	81.67 183	93.16 148	83.13 232

V42		71.58 195	70.11 200	73.30 178	75.66 218	86.68 176	79.17 174	69.92 181	59.29 201	52.80 180	44.36 212	45.66 217	68.83 195	79.48 200	81.49 189	93.44 134	93.82 150

NR-MVSNet		71.47 196	71.11 196	71.90 196	77.73 193	86.02 190	76.88 198	74.42 142	65.39 183	46.09 225	49.10 196	39.87 246	64.27 214	81.40 180	82.24 176	91.99 179	93.75 152

v8		71.42 197	69.69 202	73.43 177	76.45 203	85.12 204	79.53 169	67.47 210	59.34 200	52.90 179	44.60 210	45.82 216	71.05 182	79.56 199	81.45 191	93.17 147	91.96 175

TranMVSNet+NR-MVSNet		71.12 198	70.24 198	72.15 192	76.01 209	84.80 207	76.55 200	75.65 133	61.99 193	45.29 228	48.42 200	43.07 230	67.55 203	78.28 208	82.83 168	91.85 184	92.29 166

v10		70.97 199	69.44 203	72.75 183	75.90 214	84.58 209	79.43 170	66.45 215	58.07 204	49.93 205	43.87 218	43.68 224	71.91 174	82.04 174	81.70 181	92.89 160	92.11 172

v1144		70.93 200	69.42 205	72.70 184	75.48 219	86.26 181	79.22 173	69.39 188	55.61 219	48.05 215	43.47 221	42.55 234	71.51 178	82.11 172	81.74 180	92.56 168	94.17 138

thisisatest0515		70.62 201	71.94 192	69.07 212	76.48 202	85.59 195	68.03 234	68.02 200	59.70 198	52.94 178	52.19 183	50.36 199	58.10 229	83.15 160	81.63 184	90.87 214	90.99 184

Baseline_NR-MVSNet		70.61 202	68.87 209	72.65 185	75.95 211	80.49 239	75.92 206	74.75 138	65.10 186	48.78 212	41.28 235	44.28 222	68.45 196	78.67 205	79.64 209	92.04 177	92.62 164

v148		70.34 203	68.46 212	72.54 188	76.04 206	86.38 180	74.83 214	72.73 153	55.88 218	55.26 172	43.32 224	43.49 225	64.52 213	76.93 219	80.11 207	91.85 184	93.11 159

v1192		70.32 204	68.77 210	72.12 193	74.76 221	85.62 194	78.73 175	68.53 193	55.08 221	46.34 222	42.39 229	40.67 241	71.90 175	82.27 170	81.53 188	92.43 171	93.86 149

v144192		70.10 205	68.55 211	71.90 196	74.55 222	85.67 193	77.81 186	68.22 198	54.65 223	46.91 218	42.76 227	41.27 238	70.95 183	80.48 190	81.11 202	92.96 157	93.90 146

pmmvs5		70.01 206	69.31 207	70.82 207	75.80 217	86.26 181	72.94 224	67.91 202	53.84 226	47.22 216	47.31 202	41.47 237	67.61 202	83.93 154	81.93 179	93.42 136	90.42 190

COLMAP_ROB	66.31 15	69.91 207	66.61 217	73.76 173	86.44 129	82.76 218	76.59 199	76.46 122	63.82 188	50.92 200	45.60 207	49.13 205	65.87 210	74.96 227	74.45 235	86.30 251	75.57 254
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	74.35 223	85.39 198	77.78 187	67.88 205	54.64 224	45.39 227	42.11 232	39.97 245	71.10 181	81.68 179	81.17 200	92.96 157	93.69 154

pm-mvs1		69.62 209	68.07 215	71.44 201	77.21 196	85.32 199	76.11 205	71.05 167	46.55 249	51.17 195	41.83 233	48.20 210	61.81 222	84.00 153	81.14 201	91.28 198	89.42 197

UniMVSNet_ETH3D		69.49 210	65.86 224	73.72 174	76.51 201	85.88 192	78.65 176	70.52 174	48.08 246	55.71 170	37.64 243	40.56 242	71.38 179	75.05 226	81.49 189	89.57 235	92.29 166

tfpnnormal		69.29 211	65.58 225	73.62 176	79.87 181	84.82 206	76.97 196	75.12 136	45.29 250	49.03 208	35.57 250	37.20 254	68.02 200	82.70 166	81.24 196	92.69 164	92.20 169

v1240		69.28 212	67.82 216	71.00 206	74.09 227	85.13 203	76.54 201	67.28 212	53.17 229	44.70 231	41.55 234	39.38 247	70.51 188	81.29 182	81.18 198	92.88 161	93.02 161

CVMVSNet		68.95 213	70.79 197	66.79 227	79.69 183	83.75 215	72.05 228	70.90 168	56.20 214	36.30 253	54.94 173	59.22 173	54.03 237	78.33 207	78.65 214	87.77 246	84.44 226

MIMVSNet		68.66 214	69.43 204	67.76 221	64.92 249	84.68 208	74.16 219	54.10 254	60.85 194	51.27 194	39.47 239	49.48 200	67.48 204	84.86 145	85.57 135	94.63 84	81.10 241

TDRefinement		67.82 215	64.91 231	71.22 205	82.08 166	81.45 230	77.42 191	73.79 148	59.62 199	48.35 214	42.35 231	42.40 235	60.87 224	74.69 228	74.64 234	84.83 256	79.20 246

wanda-best-256-512		67.61 216	66.46 220	68.94 214	56.36 255	82.07 223	75.15 211	69.94 177	56.27 211	52.66 183	43.54 219	49.41 201	68.38 197	73.35 231	72.06 240	91.17 201	88.53 208

FE-blended-shiyan7		67.61 216	66.46 220	68.94 214	56.36 255	82.07 223	75.15 211	69.94 177	56.28 210	52.66 183	43.54 219	49.41 201	68.38 197	73.35 231	72.06 240	91.17 201	88.53 208

anonymousdsp		67.61 216	68.94 208	66.04 228	71.44 239	83.97 212	66.45 238	63.53 229	50.54 238	42.42 239	49.39 194	45.63 218	62.84 219	77.99 210	81.34 195	89.59 234	93.75 152

blended_shiyan8		67.43 219	66.30 223	68.74 216	56.30 260	82.00 227	74.80 216	69.62 184	55.94 215	52.60 185	43.24 225	49.40 203	68.00 201	73.19 237	71.88 245	91.09 206	88.46 212

blended_shiyan6		67.43 219	66.32 222	68.72 217	56.29 261	81.99 228	74.78 217	69.62 184	55.89 217	52.55 186	43.36 222	49.38 204	68.03 199	73.20 236	71.89 244	91.07 207	88.50 210

TinyColmap		67.16 221	63.51 238	71.42 202	77.94 191	79.54 245	72.80 225	69.78 183	56.58 209	45.52 226	44.53 211	33.53 261	74.45 158	76.91 220	77.06 225	88.03 245	76.41 250

FC-MVSNet-test		67.04 222	72.47 186	60.70 246	76.92 197	81.41 231	61.52 250	69.45 187	65.58 182	26.74 267	61.79 131	60.40 169	41.17 257	77.60 215	77.78 221	88.41 241	82.70 236

gbinet_0.2-2-1-0.02		67.03 223	66.53 219	67.63 222	54.59 263	81.34 234	73.95 220	69.35 189	53.34 228	51.93 189	42.82 226	50.76 197	64.78 212	73.34 235	72.07 239	91.16 205	92.01 173

TransMVSNet (Re)		66.87 224	64.30 233	69.88 211	78.32 187	81.35 233	73.88 221	74.34 144	43.19 255	45.20 229	40.12 237	42.37 236	55.97 233	80.85 185	79.15 210	91.56 191	83.06 233

CMPMVS	50.59 17	66.74 225	62.72 242	71.42 202	85.40 142	89.72 157	72.69 226	70.72 170	51.24 234	51.75 190	38.91 241	44.40 220	63.74 217	70.84 247	71.52 247	84.19 257	72.45 259
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
v7n		66.43 226	65.51 226	67.51 223	71.63 238	83.10 216	70.89 232	65.02 223	50.13 241	44.68 232	39.59 238	38.77 248	62.57 220	77.59 216	78.91 211	90.29 223	90.44 189

EG-PatchMatch MVS		66.23 227	65.20 228	67.43 224	77.74 192	86.20 184	72.51 227	63.68 228	43.95 253	43.44 236	36.22 249	45.43 219	54.04 236	81.00 183	80.95 203	93.15 149	82.67 237

WR-MVS		64.98 228	66.59 218	63.09 238	74.34 224	82.68 219	64.98 244	69.17 191	54.42 225	36.18 254	44.32 213	44.35 221	44.65 250	73.60 230	77.83 220	89.21 237	88.96 203

gm-plane-assit		64.86 229	68.15 214	61.02 245	76.44 204	68.29 262	41.60 269	53.37 255	34.68 265	26.19 269	33.22 256	57.09 182	71.97 173	95.12 7	93.97 9	96.54 18	94.66 128

CP-MVSNet		64.84 230	64.97 229	64.69 233	72.09 234	81.04 237	66.66 237	67.53 209	52.45 231	37.40 248	44.00 217	38.37 250	53.54 240	72.26 241	76.93 226	90.94 213	89.75 195

MDTV_nov1_ep13_2view		64.72 231	64.94 230	64.46 234	71.14 240	81.94 229	67.53 235	54.54 251	55.92 216	43.29 237	44.02 216	43.27 228	59.87 225	71.85 243	74.77 233	90.36 221	82.82 235

MVS-HIRNet		64.63 232	64.03 237	65.33 230	75.01 220	82.84 217	58.54 258	52.10 257	55.42 220	49.29 206	29.83 261	43.48 226	66.97 206	78.28 208	78.81 212	90.07 228	79.52 245

pmnet_mix02		64.58 233	64.11 236	65.12 231	74.16 226	80.17 242	63.24 247	67.91 202	57.87 205	41.69 240	45.86 206	40.99 240	53.97 239	69.92 250	71.67 246	89.77 230	82.29 239

LTVRE_ROB	63.07 16	64.49 234	63.16 241	66.04 228	77.47 195	82.64 220	70.98 231	65.02 223	34.01 266	29.61 263	49.12 195	35.58 259	70.57 187	75.10 225	78.45 216	82.60 260	87.24 218
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	72.67 230	79.83 243	66.97 236	68.24 197	51.21 235	35.29 256	44.09 214	38.51 249	52.36 244	71.06 244	77.65 222	90.99 209	87.68 216

pmmvs6		64.24 236	61.77 246	67.12 225	72.39 233	81.39 232	71.33 230	65.95 221	36.05 262	48.48 213	30.55 257	43.45 227	58.75 227	77.88 213	76.36 229	85.83 252	86.70 221

pmmvs-eth3d		64.24 236	61.96 244	66.90 226	66.35 246	76.04 254	66.09 240	66.31 217	52.59 230	50.94 199	37.61 244	32.79 263	62.43 221	75.78 223	75.48 231	89.27 236	83.39 231

PS-CasMVS		64.22 238	64.19 235	64.25 236	71.86 236	80.67 238	66.42 239	67.43 211	50.64 237	36.48 251	42.60 228	37.46 253	52.56 242	71.98 242	76.69 228	90.76 215	89.29 201

WR-MVS_H		64.14 239	65.36 227	62.71 241	72.47 232	82.33 222	65.13 241	66.99 213	51.81 233	36.47 252	43.33 223	42.77 232	43.99 252	72.41 240	75.99 230	91.20 200	88.86 207

SixPastTwentyTwo		63.75 240	63.42 239	64.13 237	72.91 229	80.34 240	61.29 251	63.90 226	49.58 243	40.42 243	54.99 172	37.13 255	60.90 223	68.46 251	70.80 248	85.37 254	82.65 238

PM-MVS		63.52 241	62.51 243	64.70 232	64.79 251	76.08 253	65.07 242	62.08 232	58.13 203	46.56 221	44.98 209	31.31 265	62.89 218	72.58 239	69.93 253	86.81 248	84.55 225

DTE-MVSNet		63.26 242	63.41 240	63.08 239	72.59 231	78.56 246	65.03 243	68.28 196	50.53 239	32.38 260	44.03 215	37.79 252	49.48 248	70.83 248	76.73 227	90.73 216	85.42 224

testgi		63.11 243	64.88 232	61.05 244	75.83 216	78.51 247	60.42 252	66.20 218	48.77 244	34.56 257	56.96 155	40.35 243	40.95 258	77.46 217	77.22 224	88.37 243	74.86 257

GG-mvs-BLEND		62.08 244	88.31 46	31.46 263	0.16 281	98.10 14	91.57 45	0.09 275	85.07 71	0.21 282	73.90 64	83.74 43	0.19 279	88.98 83	89.39 78	96.58 16	99.02 18

Anonymous20231206		62.05 245	61.83 245	62.30 243	72.09 234	77.84 248	63.10 248	67.62 208	50.20 240	36.68 250	29.59 262	37.05 256	43.90 253	77.33 218	77.31 223	90.41 220	83.49 230

N_pmnet		60.52 246	58.83 250	62.50 242	68.97 243	75.61 255	59.72 256	66.47 214	51.90 232	41.26 241	35.42 252	35.63 258	52.25 245	67.07 254	70.08 252	86.35 249	76.10 251

FE-MVSNET2		60.10 247	59.87 248	60.37 247	51.97 266	77.72 249	63.63 246	66.11 219	45.14 251	36.89 249	26.42 266	33.72 260	51.78 246	77.68 214	78.09 219	91.85 184	80.29 242

dtuonlycased		59.74 248	57.09 251	62.83 240	64.59 252	76.76 250	62.72 249	62.48 231	49.65 242	44.54 234	34.46 253	45.96 215	57.26 231	54.43 261	58.78 260	85.36 255	79.58 244

EU-MVSNet		58.73 249	60.92 247	56.17 250	66.17 248	72.39 258	58.85 257	61.24 235	48.47 245	27.91 265	46.70 204	40.06 244	39.07 260	68.27 252	70.34 250	83.77 258	80.23 243

test20.03		57.93 250	59.22 249	56.44 249	71.84 237	73.78 257	53.55 263	65.96 220	43.02 256	28.46 264	37.50 245	38.17 251	30.41 264	75.25 224	74.42 236	88.41 241	72.37 260

MDA-MVSNet-bldmvs		54.99 251	52.66 256	57.71 248	52.74 265	74.87 256	55.61 260	68.41 195	43.65 254	32.54 258	37.93 242	22.11 274	54.11 235	48.85 265	67.34 255	82.85 259	73.88 258

FE-MVSNET		54.54 252	55.85 252	53.01 253	44.64 268	70.42 261	54.91 261	64.61 225	39.64 259	23.66 271	26.69 265	32.48 264	41.99 254	71.03 246	74.94 232	88.27 244	75.74 252

new-patchmatchnet		53.91 253	52.69 255	55.33 252	64.83 250	70.90 259	52.24 264	61.75 233	41.09 257	30.82 261	29.90 260	28.22 268	36.69 261	61.52 258	65.08 256	85.64 253	72.14 261

MIMVSNet1		52.76 254	53.95 254	51.38 255	41.96 270	70.79 260	53.56 262	63.03 230	39.36 260	27.83 266	22.73 269	33.07 262	34.47 263	70.49 249	72.69 237	87.41 247	68.51 262

pmmvs3		52.59 255	52.43 257	52.78 254	54.53 264	64.49 265	50.07 265	46.89 264	35.31 264	30.19 262	27.27 264	26.96 270	53.02 241	67.28 253	70.54 249	81.96 261	75.20 255

new_pmnet		50.32 256	51.36 258	49.11 257	49.19 267	64.89 264	48.66 267	47.99 263	47.55 247	26.27 268	29.51 263	28.66 267	44.89 249	61.12 259	62.74 258	77.66 264	65.03 263

FPMVS		50.25 257	45.67 261	55.58 251	70.48 241	60.12 266	59.78 255	59.33 241	46.66 248	37.94 246	30.22 259	27.51 269	35.94 262	50.98 264	47.90 264	70.02 266	56.31 264

usedtu_dtu_shiyan2		50.22 258	49.72 260	50.80 256	33.02 274	67.71 263	57.83 259	52.96 256	27.83 271	39.36 245	20.55 271	29.77 266	40.68 259	61.53 257	62.06 259	80.93 263	78.57 247

test_method		47.92 259	55.39 253	39.21 260	19.90 275	49.24 269	39.29 270	34.65 269	57.37 207	32.54 258	25.11 267	41.02 239	44.31 251	66.58 256	57.57 262	64.59 269	90.82 185

PMVS	36.83 18	40.62 260	36.39 263	45.56 258	58.40 254	33.20 272	32.62 272	56.02 245	28.25 270	37.92 247	22.29 270	26.15 271	25.29 266	48.49 266	43.82 267	63.13 270	52.53 267
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		39.74 261	42.23 262	36.84 261	66.24 247	50.82 268	26.18 275	66.39 216	31.14 268	4.85 277	37.06 247	24.28 272	7.95 275	54.48 260	54.23 263	49.46 273	43.61 270

Gipuma		35.20 262	33.96 264	36.65 262	43.30 269	32.51 273	26.96 274	48.31 262	38.87 261	20.08 273	8.08 274	7.41 280	26.44 265	53.60 262	58.43 261	54.81 271	38.79 273
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	34.15 273	44.70 271	27.79 273	39.69 268	22.21 272	4.31 278	15.73 272	14.13 278	12.45 272	40.11 267	47.00 265	66.88 267	53.54 265

E-PMN		21.42 264	17.56 270	25.94 265	36.25 272	19.02 276	11.56 276	43.72 266	15.25 274	6.99 275	8.04 275	4.53 283	21.77 268	16.13 273	26.16 269	35.34 274	33.77 274

MVE	25.07 19	21.25 265	23.51 269	18.62 267	15.07 276	29.77 275	10.67 278	34.60 270	12.51 275	9.46 274	7.84 276	3.82 284	14.38 270	27.45 269	42.42 268	27.56 276	40.74 271
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		20.61 266	16.32 271	25.62 266	36.41 271	18.93 277	11.51 277	43.75 265	15.65 273	6.53 276	7.56 277	4.68 282	22.03 267	14.56 274	23.10 270	33.51 275	29.77 275

VLMVS		19.18 267	30.41 266	6.08 269	4.08 278	8.55 279	5.11 281	0.41 274	40.06 258	2.99 279	55.93 164	23.93 273	9.07 274	20.26 272	19.06 272	14.85 277	45.09 269

VLMVS_CLIP		18.77 268	29.38 267	6.40 268	5.19 277	9.75 278	6.18 280	0.73 272	32.15 267	0.96 280	47.91 201	17.70 276	11.68 273	24.94 270	21.30 271	13.63 278	51.95 268

MVS_clip		14.93 269	23.85 268	4.53 270	3.12 279	7.65 280	3.59 282	0.52 273	30.26 269	0.46 281	33.40 255	16.95 277	12.84 271	21.07 271	17.62 273	6.61 279	40.02 272

MVS_baseline		3.69 270	6.36 272	0.57 271	0.17 280	0.30 281	0.08 285	0.00 278	7.51 276	0.00 285	9.54 273	5.03 281	3.12 276	3.94 275	3.76 274	0.03 282	14.47 276

testmvs		0.76 271	1.23 273	0.21 272	0.05 282	0.21 282	0.38 283	0.09 275	0.94 277	0.05 283	2.13 279	0.08 285	0.60 278	0.82 276	0.77 275	0.11 280	3.62 278

test123		0.67 272	1.11 274	0.16 273	0.01 283	0.14 283	0.20 284	0.04 277	0.77 278	0.02 284	2.15 278	0.02 286	0.61 277	0.23 277	0.72 276	0.07 281	3.76 277

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

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

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

ACM-MVS					98.20 4	98.52 8	96.93 2		94.55 18	78.23 52	87.10 35	93.26 2	93.66 7			95.47 58	97.16 60

PatchmatchNet2					69.65 242	76.10 252	60.12 253
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												35.72 257	52.39 243	67.05 255	70.24 251	86.34 250	75.74 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										41.18 242	35.45 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							95.37 14	93.61 1		96.88 1						96.96 9

TPM-MVS					98.35 1	98.66 4	96.92 3			83.78 28	90.39 26	94.36 1	94.48 4			96.58 16	93.94 142
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										39.41 244

9.14												91.16 9

SR-MVS					96.04 34			87.51 29				87.60 25

Anonymous202405211			75.59 168		85.13 149	91.06 139	84.62 128	77.96 98	69.47 170		40.79 236	63.84 145	84.57 77	83.55 157	84.69 143	89.69 231	95.75 111

our_test_3					73.80 228	79.57 244	64.47 245

ambc			50.35 259		55.61 262	59.93 267	48.73 266		44.08 252	35.81 255	24.01 268	10.64 279	41.57 256	72.83 238	63.35 257	74.99 265	77.61 248

MTAPA										91.14 10		85.84 31

MTMP										90.95 11		84.13 39

Patchmatch-RL test							8.17 279

tmp_tt				39.78 259	56.31 259	31.71 274	35.84 271	15.08 271	82.57 83	50.83 201	63.07 115	47.51 212	15.28 269	52.23 263	44.24 266	65.35 268

XVS					89.65 74	95.93 51	85.97 107			76.32 74		82.05 48				93.51 127

X-MVStestdata					89.65 74	95.93 51	85.97 107			76.32 74		82.05 48				93.51 127

mPP-MVS					95.90 36							80.22 57

NP-MVS									89.55 51

Patchmtry						87.41 169	78.32 180	54.14 252		51.09 196

DeepMVS_CX						48.96 270	43.77 268	40.58 267	50.93 236	24.67 270	36.95 248	20.18 275	41.60 255	38.92 268		52.37 272	53.31 266

High-resolution multi-view benchmark