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		97.92 1	98.27 2	97.52 1	98.88 12	99.60 1	98.80 5	95.08 7	98.57 2	95.63 2	96.98 9	99.73 1	97.67 2	97.26 11	95.86 22	99.04 14	99.89 5

MSP-MVS		97.74 2	98.32 1	97.06 7	98.66 15	99.35 8	98.66 8	94.75 13	98.22 5	93.60 6	97.99 1	98.58 8	97.41 5	98.24 2	95.95 18	99.27 4	99.91 1
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		97.71 3	98.01 6	97.37 2	98.98 6	99.58 3	98.79 6	95.06 8	98.24 4	94.66 3	96.35 15	99.20 4	97.63 3	97.20 13	95.68 23	99.08 12	99.84 7

DPE-MVS		97.69 4	98.16 3	97.14 5	99.01 5	99.52 5	99.12 3	95.38 2	98.00 8	93.31 9	97.71 2	99.61 3	96.94 6	96.99 17	95.45 27	99.09 11	99.81 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS		97.61 5	97.87 7	97.30 3	98.94 11	99.60 1	98.21 13	95.11 4	98.39 3	95.83 1	94.40 30	99.70 2	96.79 7	97.16 14	95.95 18	98.92 26	99.90 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
CNVR-MVS		97.60 6	98.08 4	97.03 8	99.14 2	99.55 4	98.67 7	95.32 3	97.91 9	92.55 11	97.11 6	97.23 14	97.49 4	98.16 3	97.05 6	99.04 14	99.55 20

APDe-MVS		97.31 7	97.51 12	97.08 6	98.95 10	99.29 14	98.58 10	95.11 4	97.69 14	94.16 4	96.91 10	96.81 18	96.57 10	96.71 20	95.39 29	99.08 12	99.79 10
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.17 8	97.18 16	97.17 4	99.11 3	99.20 16	99.05 4	95.55 1	97.39 17	93.56 7	97.48 4	96.71 20	96.75 8	95.73 32	94.40 46	98.98 20	99.33 25

NCCC		97.01 9	97.74 8	96.16 11	99.02 4	99.35 8	98.63 9	95.04 9	97.84 11	88.95 24	96.83 12	97.02 17	96.39 15	97.44 7	96.51 9	98.90 28	99.16 41

SMA-MVS		96.96 10	97.65 11	96.15 12	98.98 6	99.31 13	97.91 18	94.68 15	97.52 15	90.59 18	94.54 29	99.20 4	96.54 12	97.29 9	96.48 10	98.22 65	99.19 37
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
MCST-MVS		96.93 11	98.07 5	95.61 18	98.98 6	99.44 6	98.04 14	95.04 9	98.10 6	86.55 31	97.65 3	97.56 11	95.60 23	97.67 6	96.45 11	99.43 1	99.61 19

HPM-MVS++		96.91 12	97.70 9	96.00 13	98.97 9	99.16 18	97.82 20	94.81 12	98.04 7	89.61 21	96.56 14	98.60 7	96.39 15	97.09 15	95.22 31	98.39 59	99.22 33

SD-MVS		96.87 13	97.69 10	95.92 14	96.38 48	99.25 15	97.76 21	94.75 13	97.72 12	92.46 13	95.94 16	99.09 6	96.48 14	96.01 29	96.08 16	97.68 98	99.73 13
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
APD-MVS		96.79 14	96.99 19	96.56 9	98.76 14	98.87 27	98.42 11	94.93 11	97.70 13	91.83 14	95.52 19	95.94 26	96.63 9	95.94 30	95.47 26	98.80 34	99.47 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		96.50 15	97.08 17	95.82 16	96.12 52	98.97 24	98.00 15	94.13 20	97.89 10	91.49 15	95.11 25	97.52 12	96.26 19	96.27 27	94.07 56	98.91 27	99.74 12
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SteuartSystems-ACMMP		96.20 16	97.22 15	95.01 22	98.40 22	99.11 19	97.93 17	93.62 23	96.28 30	87.45 28	97.05 8	96.00 25	94.23 31	96.83 19	95.97 17	98.40 57	99.27 30
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 17	96.41 24	95.72 17	98.58 17	98.84 28	97.95 16	93.08 27	96.96 23	90.24 19	96.60 13	94.40 32	96.52 13	95.13 42	94.33 47	97.93 88	98.59 67

ACMMP_NAP		95.81 18	96.50 23	95.01 22	98.79 13	99.17 17	97.52 26	94.20 19	96.19 31	85.71 36	93.80 33	96.20 24	95.89 20	96.62 22	94.98 37	97.93 88	98.52 71

MVS_0304		95.79 19	97.46 13	93.85 28	96.81 42	99.35 8	97.21 29	87.28 48	97.10 18	88.65 27	95.17 24	96.41 23	94.15 35	97.29 9	97.19 5	99.01 18	99.73 13

train_agg		95.72 20	97.37 14	93.80 29	97.82 31	98.92 25	97.84 19	93.50 24	96.86 25	81.35 55	97.10 7	97.71 9	94.19 32	96.02 28	95.37 30	98.07 74	99.64 17

ACMMPR		95.59 21	95.89 26	95.25 20	98.41 21	98.74 29	97.69 24	92.73 31	96.88 24	88.95 24	95.33 21	92.91 39	95.79 21	94.73 52	94.33 47	97.92 90	98.32 81

DeepC-MVS_fast	91.53 1	95.57 22	95.67 29	95.45 19	98.57 18	99.00 23	97.76 21	94.41 17	97.06 20	86.84 30	86.39 46	92.27 44	96.38 17	97.89 5	98.06 3	98.73 39	99.01 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		95.49 23	94.84 34	96.25 10	98.64 16	98.63 32	98.35 12	92.37 33	95.04 49	92.62 10	87.12 45	93.79 33	96.55 11	93.53 72	96.78 7	98.98 20	98.99 51

CP-MVS		95.43 24	95.67 29	95.14 21	98.24 27	98.60 33	97.45 27	92.80 29	95.98 34	89.21 23	95.22 22	93.60 34	95.43 24	94.37 59	93.22 77	97.68 98	98.72 58

DPM-MVS		95.36 25	95.84 27	94.82 24	96.70 44	98.49 43	99.27 1	95.09 6	96.71 26	83.87 44	86.34 48	96.44 22	95.06 26	98.35 1	98.82 1	98.89 29	95.69 138

MP-MVS		95.24 26	95.96 25	94.40 26	98.32 24	98.38 48	97.12 30	92.87 28	95.17 47	85.50 37	95.68 17	94.91 30	94.58 28	95.11 43	93.76 62	98.05 77	98.68 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 27	97.02 18	92.61 39	97.19 37	98.71 31	97.74 23	93.21 26	96.97 22	79.27 75	94.09 31	97.14 15	90.84 67	96.64 21	95.94 20	97.42 115	99.67 16

X-MVS		94.70 28	95.71 28	93.52 33	98.38 23	98.56 35	96.99 31	92.62 32	95.58 38	81.00 63	94.57 28	93.49 35	94.16 34	94.82 48	94.29 50	97.99 84	98.68 60

PGM-MVS		94.64 29	95.49 31	93.66 31	98.55 19	98.51 41	97.63 25	87.77 46	94.45 53	84.92 40	97.23 5	91.90 46	95.22 25	94.56 55	93.80 61	97.87 94	97.97 93

TSAR-MVS + GP.		94.59 30	96.60 22	92.25 40	90.25 94	98.17 55	96.22 36	86.53 53	97.49 16	87.26 29	95.21 23	97.06 16	94.07 37	94.34 61	94.20 52	99.18 5	99.71 15

PHI-MVS		94.49 31	96.72 21	91.88 42	97.06 38	98.88 26	94.99 47	89.13 41	96.15 32	79.70 70	96.91 10	95.78 27	91.87 58	94.65 53	95.68 23	98.53 49	98.98 53

AdaColmap		94.28 32	92.94 46	95.84 15	98.32 24	98.33 50	96.06 38	94.62 16	96.29 29	91.22 16	89.89 39	85.50 74	96.38 17	91.85 103	90.89 94	98.44 53	97.81 96

DeepPCF-MVS	91.00 2	94.15 33	96.87 20	90.97 50	96.82 41	99.33 12	89.40 106	92.76 30	98.76 1	82.36 51	88.74 40	95.49 29	90.58 74	98.13 4	97.80 4	93.88 196	99.88 6

CPTT-MVS		94.11 34	93.99 39	94.25 27	96.58 45	97.66 63	97.31 28	91.94 34	94.84 50	88.72 26	92.51 34	93.04 38	95.78 22	91.51 106	89.97 111	95.15 185	98.37 78

EPNet		93.69 35	95.34 32	91.76 43	96.98 40	98.47 45	95.40 44	86.79 50	95.47 40	82.84 48	95.66 18	89.17 52	90.47 76	95.25 41	94.69 41	98.10 71	98.68 60
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 36	93.59 42	93.00 37	97.03 39	98.24 51	95.27 45	91.66 37	95.20 45	83.25 46	95.39 20	85.52 72	92.80 49	92.60 92	90.21 107	98.01 81	97.99 91
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CANet		93.23 37	93.72 41	92.65 38	95.48 55	99.09 21	96.55 34	86.74 51	95.28 43	85.22 38	77.30 76	91.25 48	92.60 51	97.06 16	96.63 8	99.31 2	99.45 24

CDPH-MVS		93.22 38	95.08 33	91.04 49	97.57 34	98.49 43	96.74 33	89.35 40	95.19 46	73.57 106	90.26 37	91.59 47	90.68 71	95.09 45	96.15 14	98.31 64	98.81 56

CSCG		93.16 39	92.65 47	93.76 30	98.32 24	99.09 21	96.12 37	89.91 39	93.15 62	89.64 20	83.62 56	88.91 54	92.40 53	91.09 111	93.70 63	96.14 168	98.99 51

MVS_111021_LR		93.05 40	94.53 36	91.32 47	96.43 47	98.38 48	92.81 62	87.20 49	95.94 36	81.45 54	94.75 26	86.08 68	92.12 56	94.83 47	93.34 71	97.89 93	98.42 77

3Dnovator+	86.26 7	92.90 41	92.45 49	93.42 34	97.25 36	98.45 47	95.82 39	85.71 59	93.83 57	89.55 22	72.31 105	92.28 43	94.01 39	95.10 44	95.92 21	98.17 67	99.23 32

MVS_111021_HR		92.73 42	94.83 35	90.28 55	96.27 49	99.10 20	92.77 63	86.15 56	93.41 60	77.11 93	93.82 32	87.39 60	90.61 72	95.60 34	95.15 33	98.79 35	99.32 26

PLC	89.12 3	92.67 43	90.84 59	94.81 25	97.69 32	96.10 95	95.42 43	91.70 35	95.82 37	92.52 12	81.24 62	86.01 69	94.36 29	92.44 96	90.27 104	97.19 124	93.99 166
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 44	91.96 51	93.20 35	97.99 28	98.47 45	95.78 40	85.94 57	93.07 63	86.40 32	73.43 97	89.00 53	94.08 36	94.74 51	96.44 12	99.01 18	98.57 68

DeepC-MVS	88.77 4	92.39 45	91.74 53	93.14 36	96.21 50	98.55 38	96.30 35	93.84 21	93.06 64	81.09 60	74.69 90	85.20 78	93.48 43	95.41 37	96.13 15	97.92 90	99.18 38
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OMC-MVS		92.05 46	91.88 52	92.25 40	96.51 46	97.94 57	93.18 59	88.97 43	96.53 27	84.47 42	80.79 64	87.85 56	93.25 47	92.48 95	91.81 87	97.12 125	95.73 137

MVSTER		91.91 47	93.43 45	90.14 56	89.81 101	92.32 139	94.53 50	81.32 94	96.00 33	84.77 41	85.41 53	92.39 42	91.32 60	96.41 23	94.01 59	99.11 8	97.45 106

SPE-MVS-test		91.76 48	93.47 43	89.76 59	94.64 60	98.22 53	88.13 116	81.58 91	97.02 21	82.47 50	85.49 52	85.41 76	93.28 45	95.33 39	93.61 65	98.45 52	99.22 33

QAPM		91.68 49	91.97 50	91.34 46	97.86 30	98.72 30	95.60 42	85.72 58	90.86 79	77.14 92	76.06 79	90.35 49	92.69 50	94.10 64	94.60 43	99.04 14	99.09 44

CS-MVS		91.55 50	92.49 48	90.45 54	94.00 63	97.91 59	91.17 83	81.40 93	95.22 44	83.51 45	82.37 60	82.29 84	94.07 37	96.36 26	94.03 57	98.56 46	99.22 33

CNLPA		91.53 51	89.74 72	93.63 32	96.75 43	97.63 65	91.16 84	91.70 35	96.38 28	90.82 17	69.66 118	85.52 72	93.76 40	90.44 118	91.14 93	97.55 108	97.40 107

ETV-MVS		91.51 52	94.06 38	88.54 71	89.39 107	97.52 66	89.48 103	80.88 97	97.09 19	79.41 72	87.87 41	86.18 67	92.95 48	95.94 30	94.33 47	99.13 7	99.52 22

EC-MVSNet		91.25 53	93.45 44	88.68 69	88.90 114	96.18 94	91.66 72	76.70 130	95.57 39	82.00 52	84.18 54	89.28 51	94.17 33	95.64 33	94.19 53	98.68 41	99.14 42

DELS-MVS		91.09 54	90.56 67	91.71 44	95.82 53	98.59 34	95.74 41	86.68 52	85.86 109	85.12 39	72.71 100	81.36 87	88.06 100	97.31 8	98.27 2	98.86 32	99.82 8
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
TAPA-MVS	87.40 6	90.98 55	90.71 61	91.30 48	96.14 51	97.66 63	94.80 48	89.00 42	94.74 52	77.42 91	80.22 65	86.70 63	92.27 54	91.65 105	90.17 109	98.15 70	93.83 170
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 56	90.66 63	90.82 52	94.75 58	98.54 39	91.30 80	86.53 53	95.43 41	85.75 34	78.66 71	70.67 126	87.60 101	96.37 24	95.08 35	98.98 20	99.90 2

PVSNet_Blended		90.74 56	90.66 63	90.82 52	94.75 58	98.54 39	91.30 80	86.53 53	95.43 41	85.75 34	78.66 71	70.67 126	87.60 101	96.37 24	95.08 35	98.98 20	99.90 2

CHOSEN 280x420		90.61 58	94.27 37	86.35 95	93.12 68	98.16 56	89.99 99	69.62 185	92.48 68	76.89 97	87.28 44	96.72 19	90.31 78	94.81 49	92.33 83	98.17 67	98.08 88

MAR-MVS		90.44 59	91.17 57	89.59 60	97.48 35	97.92 58	90.96 89	79.80 102	95.07 48	77.03 94	80.83 63	79.10 97	94.68 27	93.16 77	94.46 45	97.59 107	97.63 99
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
PCF-MVS	88.14 5	90.42 60	89.56 78	91.41 45	94.44 61	98.18 54	94.35 51	94.33 18	84.55 123	76.61 98	75.84 82	88.47 55	91.29 61	90.37 121	90.66 100	97.46 111	98.88 55
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
OpenMVS	83.41 11	89.84 61	88.89 84	90.95 51	97.63 33	98.51 41	94.64 49	85.47 62	88.14 94	78.39 85	65.06 136	85.42 75	91.04 65	93.06 80	93.70 63	98.53 49	98.37 78

EIA-MVS		89.82 62	91.48 55	87.89 83	89.16 109	97.31 68	88.99 107	80.92 96	94.29 54	77.65 89	82.16 61	79.77 95	91.90 57	94.61 54	93.03 79	98.70 40	99.21 36

sasdasda		89.62 63	89.87 70	89.33 62	90.47 87	97.02 74	93.46 56	79.67 105	92.45 69	81.05 61	82.84 57	73.00 113	93.71 41	90.38 119	94.85 38	97.65 102	98.54 69

canonicalmvs		89.62 63	89.87 70	89.33 62	90.47 87	97.02 74	93.46 56	79.67 105	92.45 69	81.05 61	82.84 57	73.00 113	93.71 41	90.38 119	94.85 38	97.65 102	98.54 69

TSAR-MVS + COLMAP		89.59 65	89.64 75	89.53 61	93.32 67	96.51 85	95.03 46	88.53 44	95.98 34	69.10 122	91.81 35	64.53 153	93.40 44	93.53 72	91.35 92	97.77 95	93.75 173

HQP-MVS		89.57 66	90.57 66	88.41 73	92.77 69	94.71 113	94.24 52	87.97 45	93.44 59	68.18 125	91.75 36	71.54 125	89.90 83	92.31 99	91.43 90	97.39 116	98.80 57

MGCFI-Net		89.36 67	89.66 74	89.02 66	90.40 91	96.92 77	93.26 58	79.54 109	92.10 71	80.11 68	82.55 59	72.65 116	93.26 46	90.24 123	94.69 41	97.53 109	98.46 75

MVS_Test		89.02 68	90.20 68	87.64 85	89.83 100	97.05 73	92.30 66	77.59 126	92.89 65	75.01 103	77.36 75	76.10 107	92.27 54	95.30 40	95.42 28	98.83 33	97.30 111

CLD-MVS		88.99 69	88.07 87	90.07 57	89.61 103	94.94 110	93.82 55	85.70 60	92.73 67	82.73 49	79.97 66	69.59 130	90.44 77	90.32 122	89.93 113	98.10 71	99.04 47
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
baseline		88.91 70	89.94 69	87.70 84	89.44 106	96.74 82	91.62 74	77.92 123	93.79 58	78.76 79	77.55 74	78.46 100	89.38 90	92.26 100	92.52 82	99.10 9	98.23 82

PMMVS		88.56 71	91.22 56	85.47 104	90.04 96	95.60 106	86.62 131	78.49 118	93.86 56	70.62 117	90.00 38	80.08 93	91.64 59	92.36 97	89.80 117	95.40 180	96.84 121

test2506		88.38 72	88.02 89	88.80 68	91.55 78	97.78 60	90.87 91	83.36 72	84.51 124	83.06 47	74.13 93	76.93 104	85.39 112	94.34 61	93.33 73	98.60 42	95.10 155

baseline1		88.16 73	88.15 86	88.17 77	90.02 97	94.79 112	91.85 71	83.89 65	87.37 100	75.67 101	73.75 95	79.89 94	88.44 99	94.41 56	93.33 73	99.18 5	93.55 175

thisisatest0530		87.99 74	90.76 60	84.75 108	88.36 122	96.82 79	87.65 121	79.67 105	91.77 73	70.93 113	79.94 67	87.65 58	84.21 122	92.98 83	89.07 129	97.66 101	97.13 115

tttt0517		87.93 75	90.71 61	84.68 109	88.33 123	96.76 81	87.42 124	79.67 105	91.74 74	70.83 114	79.91 68	87.61 59	84.21 122	92.88 88	89.07 129	97.62 105	97.03 117

CANet_DTU		87.91 76	91.57 54	83.64 116	90.96 81	97.12 71	91.90 70	75.97 138	92.83 66	53.16 180	86.02 49	79.02 98	90.80 68	95.40 38	94.15 54	99.03 17	96.47 132

diffmvs		87.86 77	87.40 95	88.39 74	88.57 118	96.10 95	91.24 82	83.15 75	90.62 80	79.13 77	72.45 103	67.71 138	90.07 80	92.58 93	93.31 76	98.17 67	99.03 48
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IS_MVSNet		87.83 78	90.66 63	84.53 110	90.08 95	96.79 80	88.16 115	79.89 101	85.44 111	72.20 108	75.50 86	87.14 61	80.21 150	95.53 35	95.22 31	96.65 142	99.02 49

EPP-MVSNet		87.72 79	89.74 72	85.37 105	89.11 110	95.57 107	86.31 133	79.44 110	85.83 110	75.73 100	77.23 77	90.05 50	84.78 118	91.22 109	90.25 105	96.83 132	98.04 89

casdiffmvs_mvg		87.64 80	86.46 104	89.01 67	89.45 105	96.09 97	92.69 64	83.42 71	84.60 122	80.01 69	68.55 121	70.29 128	90.51 75	93.93 67	93.59 67	97.96 85	98.18 83
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ET-MVSNet_ETH3D		87.63 81	91.08 58	83.59 117	67.96 221	96.30 92	92.06 68	78.47 119	91.95 72	69.87 119	87.57 43	84.14 82	94.34 30	88.58 136	92.10 85	98.88 30	96.93 118

DI_MVS_pp		87.63 81	87.13 97	88.22 76	88.61 117	95.92 101	94.09 54	81.41 92	87.00 103	78.38 86	59.70 155	80.52 91	89.08 93	94.37 59	93.34 71	97.73 96	99.05 46

casdiffmvs		87.59 83	86.69 101	88.64 70	89.06 112	96.32 91	90.18 95	83.21 74	87.74 98	80.20 66	67.99 125	68.34 135	90.79 69	93.83 68	94.08 55	98.41 56	98.50 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		87.44 84	88.72 85	85.95 100	92.02 73	97.26 69	86.88 129	82.66 85	83.86 130	79.16 76	66.96 129	84.91 79	77.26 167	94.97 46	93.48 68	97.73 96	99.64 17

viewmanbaseed2359cas		87.26 85	86.56 102	88.07 81	89.09 111	96.64 83	90.52 93	83.44 69	85.33 112	76.94 96	70.09 116	68.98 133	90.04 81	92.85 89	94.02 58	98.40 57	98.03 90

diffmvs_AUTHOR		87.25 86	86.52 103	88.11 80	88.39 121	96.07 99	91.06 85	82.98 81	88.29 93	78.43 84	70.18 115	67.08 144	89.79 87	92.05 102	93.02 80	98.03 79	98.94 54

FMVSNet3		87.19 87	87.32 96	87.04 93	82.82 159	90.21 154	92.88 61	76.53 133	91.69 75	81.31 56	64.81 139	80.64 88	89.79 87	94.80 50	94.76 40	98.88 30	94.32 162

LS3D		87.19 87	85.48 111	89.18 64	94.96 57	95.47 108	92.02 69	93.36 25	88.69 91	67.01 126	70.56 112	72.10 120	92.47 52	89.96 126	89.93 113	95.25 182	91.68 184

ACMP	85.16 9	87.15 89	87.04 98	87.27 89	90.80 83	94.45 116	89.41 105	83.09 79	89.15 87	76.98 95	86.35 47	65.80 147	86.94 105	88.45 137	87.52 148	96.42 157	97.56 104
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UGNet		87.04 90	89.59 77	84.07 112	90.94 82	95.95 100	86.02 135	81.65 90	85.94 108	78.54 83	78.00 73	85.40 77	69.62 187	91.83 104	91.53 89	97.63 104	98.51 72
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
LGP-MVS_train		86.95 91	87.65 92	86.12 98	91.77 76	93.84 122	93.04 60	82.77 83	88.04 95	65.33 131	87.69 42	67.09 143	86.79 106	90.20 124	88.99 132	97.05 127	97.71 98

PatchMatch-RL		86.75 92	85.43 112	88.29 75	94.06 62	96.37 90	86.82 130	82.94 82	88.94 89	79.59 71	79.83 69	59.17 167	89.46 89	91.12 110	88.81 136	96.88 131	93.78 171

FA-MVS(training)		86.74 93	88.01 90	85.26 106	89.86 98	96.99 76	88.54 112	64.26 201	89.04 88	81.30 59	66.74 131	81.52 86	89.11 92	94.04 65	90.37 103	98.47 51	97.37 108

viewmambaseed2359dif		86.69 94	85.42 113	88.17 77	88.54 119	95.67 103	90.98 88	82.71 84	86.36 107	80.14 67	68.41 122	68.31 136	89.91 82	87.78 144	92.27 84	96.75 136	99.13 43

baseline2		86.51 95	89.35 81	83.19 119	85.70 144	94.88 111	85.75 140	77.13 128	89.87 84	70.65 116	79.03 70	79.14 96	81.51 143	93.70 69	90.22 106	98.38 60	98.60 66

thres100view900		86.48 96	85.08 115	88.12 79	90.54 84	96.90 78	92.39 65	84.82 63	84.16 128	71.65 109	70.86 109	60.49 162	91.23 63	93.65 70	90.19 108	98.10 71	99.32 26

ACMM	84.23 10	86.40 97	84.64 118	88.46 72	91.90 74	91.93 145	88.11 117	85.59 61	88.61 92	79.13 77	75.31 87	66.25 145	89.86 86	89.88 127	87.64 145	96.16 167	92.86 180
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		86.16 98	86.00 107	86.35 95	81.81 165	89.52 163	91.40 76	76.53 133	91.69 75	81.31 56	64.81 139	80.64 88	88.72 94	90.54 115	90.72 96	98.34 61	94.08 163

test1		86.16 98	86.00 107	86.35 95	81.81 165	89.52 163	91.40 76	76.53 133	91.69 75	81.31 56	64.81 139	80.64 88	88.72 94	90.54 115	90.72 96	98.34 61	94.08 163

tfpn200view9		86.07 100	84.76 117	87.61 86	90.54 84	96.39 87	91.35 79	83.15 75	84.16 128	71.65 109	70.86 109	60.49 162	90.91 66	92.89 85	89.34 120	98.05 77	99.17 39

DCV-MVSNet		85.90 101	85.88 109	85.93 101	87.86 128	88.37 180	89.45 104	77.46 127	87.33 101	77.51 90	76.06 79	75.76 109	88.48 98	87.40 147	88.89 135	94.80 191	97.37 108

Vis-MVSNet (Re-imp)		85.89 102	89.62 76	81.55 130	89.85 99	96.08 98	87.55 122	79.80 102	84.80 119	66.55 128	73.70 96	86.71 62	68.25 194	94.40 57	94.53 44	97.32 119	97.09 116

MSDG		85.81 103	82.29 143	89.93 58	95.52 54	92.61 134	91.51 75	91.46 38	85.12 116	78.56 81	63.25 145	69.01 132	85.31 115	88.45 137	88.23 139	97.21 123	89.33 195

thres200		85.80 104	84.38 120	87.46 87	90.51 86	96.39 87	91.64 73	83.15 75	81.59 140	71.54 111	70.24 113	60.41 164	89.88 84	92.89 85	89.85 116	98.06 75	99.26 31

ECVR-MVS		85.74 105	83.80 128	88.00 82	91.55 78	97.78 60	90.87 91	83.36 72	84.51 124	78.21 87	58.65 160	62.75 158	85.39 112	94.34 61	93.33 73	98.60 42	95.25 149

viewmacassd2359aftdt		85.71 106	84.41 119	87.22 90	88.63 116	96.25 93	90.16 96	83.07 80	79.77 147	74.57 105	65.34 133	67.22 142	88.71 97	90.93 112	93.61 65	98.20 66	97.77 97

OPM-MVS		85.69 107	82.79 136	89.06 65	93.42 65	94.21 120	94.21 53	87.61 47	72.68 166	70.79 115	71.09 107	67.27 141	90.74 70	91.29 108	89.05 131	97.61 106	93.94 168
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		85.59 108	84.08 123	87.36 88	90.45 89	96.60 84	90.95 90	83.67 68	80.99 143	71.17 112	69.08 120	60.25 165	89.88 84	93.14 78	89.34 120	98.02 80	99.17 39

CostFormer		85.47 109	86.98 99	83.71 115	88.70 115	94.02 121	88.07 118	62.72 203	89.78 85	78.68 80	72.69 101	78.37 101	87.35 103	85.96 160	89.32 124	96.73 139	98.72 58

test1111		85.17 110	83.46 131	87.17 91	91.36 80	97.75 62	90.06 98	83.44 69	83.41 132	75.25 102	58.08 163	62.19 160	84.39 121	94.39 58	93.38 70	98.54 48	95.00 157

thres600view7		85.14 111	83.58 130	86.96 94	90.37 93	96.39 87	90.33 94	83.15 75	80.46 144	70.60 118	67.96 126	60.04 166	89.22 91	92.89 85	88.28 138	98.06 75	99.08 45

test-LLR		85.11 112	89.49 79	80.00 139	85.32 148	94.49 114	82.27 170	74.18 147	87.83 96	56.70 158	75.55 84	86.26 64	82.75 136	93.06 80	90.60 101	98.77 36	98.65 64

FMVSNet2		84.89 113	84.02 125	85.91 102	81.81 165	89.52 163	91.40 76	75.79 139	84.45 126	79.39 73	58.75 158	74.35 111	88.72 94	93.51 74	93.46 69	98.34 61	94.08 163

FC-MVSNet-train		84.88 114	84.08 123	85.82 103	89.21 108	91.74 146	85.87 136	81.20 95	81.71 139	74.66 104	73.38 98	64.99 151	86.60 107	90.75 113	88.08 140	97.36 117	97.90 94

EPNet_dtu		84.87 115	89.01 82	80.05 138	95.25 56	92.88 132	88.84 109	84.11 64	91.69 75	49.28 196	85.69 50	78.95 99	65.39 199	92.22 101	91.66 88	97.43 114	89.95 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 116	85.71 110	83.73 114	87.94 127	95.76 102	90.08 97	73.45 154	85.12 116	62.66 140	72.39 104	64.97 152	90.59 73	92.95 84	90.69 99	97.67 100	98.12 85

UA-Net		84.69 117	87.64 93	81.25 132	90.38 92	95.67 103	87.33 125	79.41 111	72.07 170	66.48 129	75.09 88	92.48 41	66.88 195	94.03 66	94.25 51	97.01 130	89.88 192

TESTMET0.1,1		84.62 118	89.49 79	78.94 148	82.18 162	94.49 114	82.27 170	70.94 174	87.83 96	56.70 158	75.55 84	86.26 64	82.75 136	93.06 80	90.60 101	98.77 36	98.65 64

CHOSEN 1792x2688		84.59 119	84.30 122	84.93 107	93.71 64	98.23 52	89.91 100	77.96 122	84.81 118	65.93 130	45.19 205	71.76 124	83.13 134	95.46 36	95.13 34	98.94 25	99.53 21

Anonymous20231211		84.23 120	81.71 149	87.17 91	87.38 136	93.59 125	88.95 108	82.14 88	83.82 131	78.56 81	48.09 199	73.89 112	91.25 62	86.38 154	88.06 142	94.74 192	98.14 84

MDTV_nov1_ep13		84.17 121	88.03 88	79.66 141	86.00 142	94.41 117	85.05 142	66.01 197	90.36 81	64.34 136	77.13 78	84.56 80	82.71 138	87.12 151	88.92 133	93.84 198	93.69 174

test-mter		84.06 122	89.00 83	78.29 153	81.92 163	94.23 119	81.07 180	70.38 179	87.12 102	56.10 167	74.75 89	85.80 70	81.81 142	92.52 94	90.10 110	98.43 54	98.49 74

viewmsd2359difaftdt		83.97 123	82.19 144	86.04 99	87.69 132	93.13 129	86.43 132	82.37 87	81.93 137	79.33 74	68.06 124	64.40 155	87.12 104	83.73 177	86.86 154	93.31 204	97.22 112

IB-MVS	79.58 12	83.83 124	84.81 116	82.68 122	91.85 75	97.35 67	75.75 199	82.57 86	86.55 105	84.01 43	70.90 108	65.43 149	63.18 205	84.19 174	89.92 115	98.74 38	99.31 28
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
EPMVS		83.71 125	86.76 100	80.16 137	89.72 102	95.64 105	84.68 143	59.73 208	89.61 86	62.67 139	72.65 102	81.80 85	86.22 109	86.23 156	88.03 143	97.96 85	93.35 176

HyFIR lowres test		83.43 126	82.94 134	84.01 113	93.41 66	97.10 72	87.21 126	74.04 149	80.15 146	64.98 132	41.09 213	76.61 106	86.51 108	93.31 75	93.01 81	97.91 92	99.30 29

PatchmatchNet		83.28 127	87.57 94	78.29 153	87.46 134	94.95 109	83.36 152	59.43 211	90.20 83	58.10 153	74.29 92	86.20 66	84.13 124	85.27 166	87.39 149	97.25 122	94.67 160
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 128	87.76 91	78.00 158	87.45 135	92.20 140	82.63 166	58.42 213	90.30 82	58.23 151	75.74 83	87.75 57	83.97 127	86.10 159	87.64 145	97.30 120	94.62 161

GeoE		83.17 129	82.86 135	83.53 118	87.24 137	93.78 123	87.94 119	72.75 159	82.19 136	69.76 120	60.54 152	65.95 146	86.01 110	89.41 131	89.72 118	97.47 110	98.43 76

CDS-MVSNet		83.13 130	83.73 129	82.43 128	84.52 153	92.92 131	88.26 114	77.67 125	72.08 169	69.08 123	66.96 129	74.66 110	78.61 156	90.70 114	91.96 86	96.46 156	96.86 120
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 131	81.86 146	84.13 111	88.25 124	88.32 181	87.67 120	80.86 98	84.78 120	76.57 99	85.56 51	76.00 108	84.61 119	78.20 210	76.52 213	86.81 219	83.63 212

Vis-MVSNet		82.88 132	86.04 106	79.20 146	87.77 131	96.42 86	86.10 134	76.70 130	74.82 160	61.38 143	70.70 111	77.91 102	64.83 201	93.22 76	93.19 78	98.43 54	96.01 135
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 133	82.64 139	82.62 124	87.81 130	92.81 133	84.39 144	61.96 204	86.43 106	81.63 53	69.72 117	67.60 140	84.42 120	82.51 188	83.90 187	95.52 176	95.50 146

IterMVS-LS		82.62 134	82.75 138	82.48 125	87.09 138	87.48 194	87.19 127	72.85 157	79.09 148	66.63 127	65.22 134	72.14 119	84.06 126	88.33 140	91.39 91	97.03 129	95.60 145
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 135	82.51 141	82.72 121	85.49 147	93.06 130	87.17 128	71.39 171	84.18 127	64.59 134	63.03 146	58.89 168	90.22 79	91.39 107	90.83 95	97.44 112	96.21 134

tpm cat1		82.39 136	82.32 142	82.47 126	88.13 125	92.42 138	87.43 123	62.79 202	85.30 113	78.05 88	60.14 153	72.10 120	83.20 133	82.26 191	85.67 166	95.23 183	98.35 80

dmvs_re		82.31 137	81.55 150	83.19 119	83.15 158	93.17 128	88.68 111	83.72 66	82.73 134	61.70 141	67.43 128	55.43 176	83.35 132	87.51 146	89.27 127	98.56 46	95.31 148

MS-PatchMatch		82.16 138	82.18 145	82.12 129	91.65 77	93.50 126	89.51 102	71.95 165	81.48 141	64.45 135	59.58 157	77.54 103	77.23 168	89.88 127	85.62 167	97.94 87	87.68 199

tpmrst		81.71 139	83.87 127	79.20 146	89.01 113	93.67 124	84.22 145	60.14 206	87.45 99	59.49 147	64.97 137	71.86 123	85.30 116	84.72 170	86.30 158	97.04 128	98.09 87

RPMNet		81.47 140	86.24 105	75.90 176	86.72 139	92.12 142	82.82 164	55.76 219	85.21 114	53.73 178	63.45 143	83.16 83	80.13 151	92.34 98	89.52 119	96.23 165	97.90 94

CR-MVSNet		81.44 141	85.29 114	76.94 167	86.53 140	92.12 142	83.86 146	58.37 214	85.21 114	56.28 162	59.60 156	80.39 92	80.50 148	92.77 90	89.32 124	96.12 169	97.59 102

Effi-MVS+-dtu		81.18 142	82.77 137	79.33 144	84.70 152	92.54 136	85.81 137	71.55 169	78.84 149	57.06 157	71.98 106	63.77 156	85.09 117	88.94 133	87.62 147	91.79 212	95.68 140

test0.0.03 1		80.99 143	84.37 121	77.05 165	85.32 148	89.79 159	78.43 190	74.18 147	84.78 120	57.98 156	76.06 79	72.88 115	69.14 191	88.02 142	87.70 144	97.27 121	91.37 185

Fast-Effi-MVS+-dtu		80.57 144	83.44 132	77.22 163	83.98 156	91.52 148	85.78 139	64.54 200	80.38 145	50.28 192	74.06 94	62.89 157	82.00 141	89.10 132	88.91 134	96.75 136	97.21 114

FMVSNet5		80.56 145	82.53 140	78.26 155	73.80 215	81.52 213	82.26 172	68.36 190	88.85 90	64.21 137	69.09 119	84.38 81	83.49 131	87.13 150	86.76 155	97.44 112	79.95 215

ADS-MVSNet		80.25 146	82.96 133	77.08 164	87.86 128	92.60 135	81.82 177	56.19 218	86.95 104	56.16 165	68.19 123	72.42 118	83.70 130	82.05 192	85.45 172	96.75 136	93.08 179

FMVSNet1		80.18 147	78.07 161	82.65 123	78.55 189	87.57 193	88.41 113	73.93 150	70.16 175	73.57 106	49.80 188	64.45 154	85.35 114	90.54 115	90.72 96	96.10 170	93.21 177

USDC		80.10 148	79.33 157	81.00 134	86.36 141	91.71 147	88.74 110	75.77 140	81.90 138	54.90 172	67.67 127	52.05 181	83.94 128	88.44 139	86.25 159	96.31 160	87.28 203

COLMAP_ROB	75.69 15	79.47 149	76.90 168	82.46 127	92.20 70	90.53 150	85.30 141	83.69 67	78.27 152	61.47 142	58.26 161	62.75 158	78.28 159	82.41 189	82.13 200	93.83 200	83.98 211
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs4		79.32 150	77.78 163	81.11 133	80.18 174	88.96 175	83.39 150	76.07 136	81.27 142	69.35 121	58.66 159	51.19 184	82.01 140	87.16 149	84.39 184	95.66 174	92.82 181

PatchT		79.28 151	83.88 126	73.93 185	85.54 146	90.95 149	66.14 216	56.53 217	83.21 133	56.28 162	56.50 165	76.80 105	80.50 148	92.77 90	89.32 124	98.57 45	97.59 102

ACMH	78.51 14	79.27 152	78.08 160	80.65 135	89.52 104	90.40 151	80.45 182	79.77 104	69.54 180	54.85 173	64.83 138	56.16 174	83.94 128	84.58 172	86.01 163	95.41 179	95.03 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 153	78.95 159	79.56 142	81.89 164	92.52 137	82.97 159	73.70 151	67.27 186	64.97 133	61.66 151	65.06 150	78.61 156	87.12 151	88.07 141	95.23 183	90.95 187

ACMH+	79.09 13	79.12 154	77.22 167	81.35 131	88.50 120	90.36 152	82.14 174	79.38 113	72.78 165	58.59 148	62.31 150	56.44 173	84.10 125	82.03 193	84.05 185	95.40 180	92.55 182

UniMVSNet_NR-MVSNet		78.89 155	78.04 162	79.88 140	79.40 180	89.70 160	82.92 161	80.17 99	76.37 158	58.56 149	57.10 164	54.92 177	81.44 144	83.51 180	87.12 151	96.76 135	97.60 100

tpm		78.87 156	81.33 153	76.00 174	85.57 145	90.19 155	82.81 165	59.66 209	78.35 151	51.40 187	66.30 132	67.92 137	80.94 146	83.28 183	85.73 164	95.65 175	97.56 104

GA-MVS		78.86 157	80.42 154	77.05 165	83.27 157	92.17 141	83.24 154	75.73 141	73.75 162	46.27 206	62.43 148	57.12 170	76.94 170	93.14 78	89.34 120	96.83 132	95.00 157

IterMVS		78.85 158	81.36 151	75.93 175	84.27 155	85.74 200	83.83 148	66.35 195	76.82 153	50.48 190	63.48 142	68.82 134	73.99 175	89.68 129	89.34 120	96.63 145	95.67 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 159	81.34 152	75.64 180	84.31 154	85.67 201	83.51 149	66.14 196	76.67 154	50.38 191	63.45 143	69.02 131	73.23 177	89.66 130	89.22 128	96.24 164	95.67 141

UniMVSNet (Re)		78.00 160	77.52 164	78.57 151	79.66 179	90.36 152	82.09 175	77.86 124	76.38 157	60.26 144	54.63 171	52.07 180	75.31 173	84.97 169	86.10 161	96.22 166	98.11 86

DU-MVS		77.98 161	76.71 169	79.46 143	78.68 186	89.26 169	82.92 161	79.06 115	76.52 155	58.56 149	54.89 169	48.35 198	81.44 144	83.16 185	87.21 150	96.08 171	97.60 100

FC-MVSNet-test		77.95 162	81.85 147	73.39 190	82.31 160	88.99 174	79.33 186	74.24 146	78.75 150	47.40 204	70.22 114	72.09 122	60.78 211	86.66 153	85.62 167	96.30 161	90.61 188

NR-MVSNet		77.21 163	76.41 170	78.14 157	80.18 174	89.26 169	83.38 151	79.06 115	76.52 155	56.59 160	54.89 169	45.32 208	72.89 179	85.39 165	86.12 160	96.71 140	97.36 110

thisisatest0515		77.13 164	79.36 156	74.52 182	79.79 178	89.65 161	73.54 204	73.69 152	74.10 161	58.14 152	62.79 147	60.57 161	66.49 197	88.08 141	85.16 177	95.49 178	95.15 153

gg-mvs-nofinetune		77.08 165	79.79 155	73.92 186	85.95 143	97.23 70	92.18 67	52.65 222	46.19 225	27.79 229	38.27 217	85.63 71	85.67 111	96.95 18	95.62 25	99.30 3	98.67 63

TranMVSNet+NR-MVSNet		77.02 166	75.76 172	78.49 152	78.46 192	88.24 182	83.03 158	79.97 100	73.49 164	54.73 174	54.00 174	48.74 193	78.15 161	82.36 190	86.90 153	96.59 147	96.55 126

CVMVSNet		76.86 167	79.09 158	74.26 183	85.29 150	89.44 166	79.91 185	78.47 119	68.94 183	44.45 211	62.35 149	69.70 129	64.50 202	85.82 161	87.03 152	92.94 207	90.33 189

Baseline_NR-MVSNet		76.71 168	74.56 179	79.23 145	78.68 186	84.15 209	82.45 168	78.87 117	75.83 159	60.05 145	47.92 200	50.18 190	79.06 155	83.16 185	83.86 188	96.26 162	96.80 122

v2v482		76.25 169	74.78 176	77.96 159	78.50 191	89.14 172	83.05 157	76.02 137	68.78 184	54.11 175	51.36 180	48.59 195	79.49 153	83.53 179	85.60 170	96.59 147	96.49 131

V42		76.21 170	75.04 175	77.58 160	78.68 186	89.33 168	82.93 160	74.64 144	69.84 177	56.13 166	50.42 185	50.93 185	76.30 172	83.32 181	84.89 181	96.83 132	96.54 127

v8		75.89 171	74.74 177	77.23 162	79.09 182	88.00 185	83.19 155	71.08 173	70.03 176	56.29 161	50.50 183	50.88 186	77.06 169	83.32 181	84.99 179	96.68 141	95.49 147

TinyColmap		75.75 172	73.19 190	78.74 150	84.82 151	87.69 189	81.59 178	74.62 145	71.81 171	54.01 176	55.79 168	44.42 213	82.89 135	84.61 171	83.76 189	94.50 193	84.22 210

MIMVSNet		75.71 173	77.26 165	73.90 187	70.93 217	88.71 178	79.98 184	57.67 216	73.58 163	58.08 155	53.93 175	58.56 169	79.41 154	90.04 125	89.97 111	97.34 118	86.04 204

UniMVSNet_ETH3D		75.63 174	71.59 199	80.35 136	81.03 169	89.90 158	83.25 153	76.58 132	60.08 207	64.19 138	42.89 212	45.01 209	82.14 139	80.20 203	86.75 156	94.90 188	96.29 133

pm-mvs1		75.61 175	74.19 181	77.26 161	80.16 176	88.79 176	81.49 179	75.49 143	59.49 209	58.09 154	48.32 196	55.53 175	72.35 180	88.61 135	85.48 171	95.99 172	93.12 178

v10		75.57 176	74.67 178	76.62 170	78.73 185	87.46 195	83.14 156	69.41 186	69.27 181	53.44 179	49.73 189	49.21 192	78.44 158	86.17 158	85.18 176	96.53 152	95.65 144

v1144		75.54 177	74.55 180	76.69 168	78.33 195	88.77 177	82.89 163	72.76 158	67.18 188	51.73 184	49.34 191	48.37 196	78.10 162	86.22 157	85.24 174	96.35 159	96.74 123

TDRefinement		75.54 177	73.22 188	78.25 156	87.65 133	89.65 161	85.81 137	79.28 114	71.14 173	56.06 168	52.17 178	51.96 182	68.74 193	81.60 194	80.58 202	91.94 210	85.45 205

pmmvs5		75.46 179	75.12 174	75.87 177	79.39 181	89.44 166	78.12 192	72.27 163	65.98 193	51.54 185	55.83 167	46.23 203	76.80 171	88.77 134	85.73 164	97.07 126	93.84 169

tfpnnormal		75.27 180	72.12 196	78.94 148	82.30 161	88.52 179	82.41 169	79.41 111	58.03 210	55.59 170	43.83 211	44.71 210	77.35 165	87.70 145	85.45 172	96.60 146	96.61 125

anonymousdsp		75.14 181	77.25 166	72.69 193	76.68 205	89.26 169	75.26 201	68.44 189	65.53 196	46.65 205	58.16 162	56.67 172	73.96 176	87.84 143	86.05 162	95.13 186	97.22 112

v148		74.98 182	73.52 186	76.69 168	78.84 184	89.02 173	78.78 188	76.82 129	67.22 187	59.61 146	49.18 192	47.94 200	70.57 186	80.76 198	83.99 186	95.52 176	96.52 129

v1192		74.96 183	73.92 182	76.17 171	77.76 198	88.19 184	82.54 167	71.94 166	66.84 189	50.07 194	48.10 198	46.14 204	78.28 159	86.30 155	85.23 175	96.41 158	96.67 124

v144192		74.76 184	73.64 183	76.06 173	77.58 199	88.23 183	81.87 176	71.63 168	66.03 192	51.08 188	48.63 195	46.77 202	77.59 164	84.53 173	84.76 182	96.64 144	96.54 127

v1921920		74.60 185	73.56 185	75.81 178	77.43 201	87.94 186	82.18 173	71.33 172	66.48 191	49.23 198	47.84 201	45.56 206	78.03 163	85.70 163	84.92 180	96.65 142	96.50 130

v1240		74.04 186	73.04 192	75.20 181	77.19 203	87.69 189	80.93 181	70.72 178	65.08 197	48.47 199	47.31 202	44.71 210	77.33 166	85.50 164	85.07 178	96.59 147	95.94 136

testgi		73.22 187	75.84 171	70.16 204	81.67 168	85.50 204	71.45 206	70.81 176	69.56 179	44.74 210	74.52 91	49.25 191	58.45 212	84.10 176	83.37 193	93.86 197	84.56 209

CP-MVSNet		73.19 188	72.37 194	74.15 184	77.54 200	86.77 198	76.34 195	72.05 164	65.66 195	51.47 186	50.49 184	43.66 214	70.90 182	80.93 197	83.40 192	96.59 147	95.66 143

WR-MVS		72.93 189	73.57 184	72.19 196	78.14 196	87.71 188	76.21 197	73.02 156	67.78 185	50.09 193	50.35 186	50.53 188	61.27 210	80.42 201	83.10 196	94.43 194	95.11 154

TransMVSNet (Re)		72.90 190	70.51 203	75.69 179	80.88 170	85.26 206	79.25 187	78.43 121	56.13 216	52.81 181	46.81 203	48.20 199	66.77 196	85.18 168	83.70 190	95.98 173	88.28 198

WR-MVS_H		72.69 191	72.80 193	72.56 195	77.94 197	87.83 187	75.26 201	71.53 170	64.75 198	52.19 183	49.83 187	48.62 194	61.96 208	81.12 196	82.44 198	96.50 153	95.00 157

SixPastTwentyTwo		72.65 192	73.22 188	71.98 199	78.40 193	87.64 191	70.09 209	70.37 180	66.49 190	47.60 202	65.09 135	45.94 205	73.09 178	78.94 205	78.66 208	92.33 208	89.82 193

LTVRE_ROB	71.82 16	72.62 193	71.77 197	73.62 188	80.74 171	87.59 192	80.42 183	70.37 180	49.73 220	37.12 223	59.76 154	42.52 219	80.92 147	83.20 184	85.61 169	92.13 209	93.95 167
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
PS-CasMVS		72.37 194	71.47 201	73.43 189	77.32 202	86.43 199	75.99 198	71.94 166	63.37 201	49.24 197	49.07 193	42.42 220	69.60 188	80.59 200	83.18 195	96.48 155	95.23 151

MVS-HIRNet		72.32 195	73.45 187	71.00 202	80.58 172	89.97 156	68.51 213	55.28 220	70.89 174	52.27 182	39.09 215	57.11 171	75.02 174	85.76 162	86.33 157	94.36 195	85.00 207

PEN-MVS		72.24 196	71.30 202	73.33 191	77.08 204	85.57 202	76.75 193	72.52 161	63.89 200	48.12 200	50.79 181	43.09 217	69.03 192	78.54 207	83.46 191	96.50 153	93.76 172

v7n		72.11 197	71.66 198	72.63 194	75.26 210	86.85 196	76.74 194	68.77 188	62.70 204	49.40 195	45.92 204	43.51 215	70.63 185	84.16 175	83.21 194	94.99 187	95.25 149

EG-PatchMatch MVS		71.81 198	71.54 200	72.12 197	80.53 173	89.94 157	78.51 189	66.56 194	57.38 212	47.46 203	44.28 210	52.22 179	63.10 206	85.22 167	84.42 183	96.56 151	87.35 202

CMPMVS	54.54 17	71.74 199	67.94 208	76.16 172	90.41 90	93.25 127	78.32 191	75.60 142	59.81 208	53.95 177	44.64 208	51.22 183	70.70 183	74.59 216	75.88 214	88.01 216	76.23 218
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 200	73.08 191	69.97 205	75.22 211	86.81 197	73.98 203	59.61 210	69.75 178	48.01 201	54.21 173	53.06 178	69.19 190	78.50 208	80.43 203	93.84 198	88.79 196

pmnet_mix02		71.64 201	72.36 195	70.81 203	78.39 194	85.57 202	68.64 211	73.65 153	72.13 167	45.07 209	56.01 166	50.61 187	65.34 200	76.21 213	76.60 212	93.75 201	89.35 194

gm-plane-assit		71.33 202	75.18 173	66.83 208	79.06 183	75.57 220	48.05 227	60.33 205	48.28 221	34.67 227	44.34 209	67.70 139	79.78 152	97.25 12	96.21 13	99.10 9	96.92 119

DTE-MVSNet		71.19 203	70.45 204	72.06 198	76.61 206	84.59 208	75.61 200	72.32 162	63.12 203	45.70 208	50.72 182	43.02 218	65.89 198	77.53 212	82.23 199	96.26 162	91.93 183

pmmvs6		70.29 204	67.90 209	73.07 192	76.17 207	85.31 205	76.29 196	70.75 177	47.39 223	55.33 171	37.15 221	50.49 189	69.55 189	82.96 187	80.85 201	90.34 215	91.18 186

PM-MVS		70.17 205	69.42 206	71.04 201	70.82 218	81.26 215	71.25 207	67.80 191	69.16 182	51.04 189	53.15 177	34.93 224	72.19 181	80.30 202	76.95 211	93.16 206	90.21 190

pmmvs-eth3d		69.59 206	67.57 211	71.95 200	70.04 219	80.05 216	71.48 205	70.00 184	62.57 205	55.99 169	44.92 206	35.73 223	70.64 184	81.56 195	79.69 204	93.55 202	88.43 197

N_pmnet		68.54 207	67.83 210	69.38 206	75.77 208	81.90 212	66.21 215	72.53 160	65.91 194	46.09 207	44.67 207	45.48 207	63.82 204	74.66 215	77.39 210	91.87 211	84.77 208

Anonymous20231206		68.09 208	68.68 207	67.39 207	75.16 212	82.55 210	69.33 210	70.06 183	63.34 202	42.28 214	37.91 219	43.12 216	52.67 215	83.56 178	82.71 197	94.84 190	87.59 200

EU-MVSNet		68.07 209	70.25 205	65.52 209	74.68 214	81.30 214	68.53 212	70.31 182	62.40 206	37.43 222	54.62 172	48.36 197	51.34 216	78.32 209	79.27 205	90.84 213	87.47 201

GG-mvs-BLEND		65.67 210	93.78 40	32.89 223	0.47 234	99.35 8	96.92 32	0.22 232	93.28 61	0.51 235	84.07 55	92.50 40	0.62 232	93.59 71	93.86 60	98.59 44	99.79 10

test20.03		65.17 211	67.41 212	62.55 211	75.35 209	79.31 217	62.22 217	68.83 187	56.50 215	35.35 226	51.97 179	44.70 212	40.01 221	80.69 199	79.25 206	93.55 202	79.47 217

MDA-MVSNet-bldmvs		62.23 212	61.13 216	63.52 210	58.94 225	82.44 211	60.71 220	73.28 155	57.22 213	38.42 220	49.63 190	27.64 231	62.83 207	54.98 223	74.16 215	86.96 218	81.83 214

new_pmnet		61.60 213	62.68 214	60.35 214	63.02 222	74.93 221	60.97 219	58.86 212	64.21 199	35.38 225	39.51 214	39.89 221	57.37 213	72.78 217	72.56 217	86.49 220	74.85 220

new-patchmatchnet		60.74 214	59.78 218	61.87 212	69.52 220	76.67 219	57.99 223	65.78 198	52.63 218	38.47 219	38.08 218	32.92 227	48.88 218	68.50 218	69.87 218	90.56 214	79.75 216

pmmvs3		60.52 215	60.87 217	60.12 215	61.38 223	71.62 222	57.42 224	53.94 221	48.09 222	35.95 224	38.62 216	32.19 230	64.12 203	75.33 214	77.99 209	87.89 217	82.28 213

MIMVSNet1		60.51 216	61.43 215	59.44 216	48.75 228	77.21 218	60.98 218	66.84 193	52.09 219	38.74 218	29.29 224	39.40 222	48.08 219	77.60 211	78.87 207	93.22 205	75.56 219

test_method		60.40 217	66.30 213	53.52 218	37.48 232	64.10 226	55.56 225	42.45 227	71.79 172	41.87 215	33.74 222	46.80 201	61.71 209	79.18 204	73.33 216	82.01 222	95.17 152

FPMVS		56.54 218	52.82 220	60.87 213	74.90 213	67.58 225	67.69 214	65.38 199	57.86 211	41.51 216	37.83 220	34.19 225	41.21 220	55.88 222	53.09 224	74.55 225	63.31 223

WB-MVS		47.20 219	51.37 221	42.35 221	71.55 216	57.66 228	32.77 231	70.86 175	47.39 223	6.95 234	48.14 197	32.52 228	12.95 229	61.73 221	61.27 221	59.00 229	50.85 227

PMVS	42.57 18	45.71 220	42.61 223	49.32 219	61.35 224	37.82 231	36.96 229	60.10 207	37.20 226	41.50 217	28.53 225	33.11 226	28.82 226	53.45 224	48.70 226	67.22 227	59.42 224
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 221	42.62 222	45.50 220	50.79 227	41.20 230	35.55 230	52.51 223	52.95 217	29.09 228	12.92 227	11.48 234	38.15 222	62.01 220	66.62 220	66.89 228	51.17 225
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 222	42.55 224	39.74 222	43.25 229	55.05 229	38.15 228	47.11 226	31.78 227	11.83 231	21.16 226	19.12 232	20.98 228	49.95 226	56.09 223	77.09 223	64.68 222

E-PMN		27.87 223	24.36 226	31.97 224	41.27 231	25.56 234	16.62 233	49.16 224	22.00 229	9.90 232	11.75 229	7.86 236	29.57 225	22.22 228	34.70 227	45.27 230	46.41 228

MVE	32.98 19	27.61 224	29.89 225	24.94 226	21.97 233	37.22 232	15.56 235	38.83 228	17.49 230	14.72 230	11.64 231	5.62 237	21.26 227	35.20 227	50.95 225	37.29 232	51.13 226
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		26.96 225	22.96 227	31.63 225	41.91 230	25.73 233	16.30 234	49.10 225	22.38 228	9.03 233	11.22 232	8.12 235	29.93 224	20.16 229	31.04 228	43.49 231	42.04 229

testmvs		5.16 226	8.14 228	1.69 227	0.36 235	1.65 235	3.02 236	0.66 230	7.17 231	0.50 236	12.58 228	0.69 238	4.67 230	5.42 230	5.65 229	0.92 233	23.86 231

test123		4.39 227	7.11 229	1.21 228	0.11 236	1.16 236	1.67 237	0.35 231	5.91 232	0.16 237	11.65 230	0.16 239	4.45 231	1.72 231	4.92 230	0.51 234	24.28 230

uanet_test		0.00 228	0.00 230	0.00 229	0.00 237	0.00 237	0.00 238	0.00 233	0.00 233	0.00 238	0.00 233	0.00 240	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

sosnet-low-res		0.00 228	0.00 230	0.00 229	0.00 237	0.00 237	0.00 238	0.00 233	0.00 233	0.00 238	0.00 233	0.00 240	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

sosnet		0.00 228	0.00 230	0.00 229	0.00 237	0.00 237	0.00 238	0.00 233	0.00 233	0.00 238	0.00 233	0.00 240	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

TPM-MVS					99.19 1	99.43 7	99.16 2			85.97 33	94.75 26	97.40 13	97.76 1			98.95 24	95.69 138
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										43.17 212

9.14												97.59 10

SR-MVS					98.52 20			93.70 22				96.63 21

Anonymous202405211			81.72 148		88.09 126	94.27 118	89.62 101	82.14 88	82.27 135		48.83 194	72.58 117	91.08 64	87.40 147	88.70 137	94.90 188	97.99 91

our_test_3					78.55 189	84.98 207	70.12 208

ambc			57.08 219		58.68 226	67.71 224	60.07 221		57.13 214	42.79 213	30.00 223	11.64 233	50.18 217	78.89 206	69.14 219	82.64 221	85.02 206

MTAPA										93.37 8		95.71 28

MTMP										93.84 5		94.86 31

Patchmatch-RL test							19.65 232

tmp_tt				57.89 217	79.94 177	59.29 227	52.84 226	36.65 229	94.77 51	68.22 124	72.96 99	65.62 148	33.65 223	66.20 219	58.02 222	76.06 224

XVS					92.16 71	98.56 35	91.04 86			81.00 63		93.49 35				98.00 82

X-MVStestdata					92.16 71	98.56 35	91.04 86			81.00 63		93.49 35				98.00 82

mPP-MVS					97.95 29							92.24 45

NP-MVS									94.12 55

Patchmtry						92.08 144	83.86 146	58.37 214		56.28 162

DeepMVS_CX						70.68 223	59.61 222	67.36 192	72.12 168	38.41 221	53.88 176	32.44 229	55.15 214	50.88 225		74.35 226	68.42 221

High-resolution multi-view benchmark