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 10	95.86 22	99.04 15	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 12	95.68 23	99.08 13	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 16	95.45 27	99.09 12	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 29	99.70 2	96.79 7	97.16 13	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 5	99.04 15	99.55 19

APDe-MVS		97.31 7	97.51 12	97.08 6	98.95 10	99.29 13	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 13	99.79 10

SF-MVS		97.17 8	97.18 15	97.17 4	99.11 3	99.20 15	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 44	98.98 20	99.33 24

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 40

SMA-MVS		96.96 10	97.65 11	96.15 12	98.98 6	99.31 12	97.91 18	94.68 15	97.52 15	90.59 18	94.54 28	99.20 4	96.54 12	97.29 9	96.48 10	98.22 64	99.19 36
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 30	97.65 3	97.56 11	95.60 23	97.67 6	96.45 11	99.43 1	99.61 18

HPM-MVS++		96.91 12	97.70 9	96.00 13	98.97 9	99.16 17	97.82 20	94.81 12	98.04 7	89.61 21	96.56 14	98.60 7	96.39 15	97.09 14	95.22 31	98.39 58	99.22 32

SD-MVS		96.87 13	97.69 10	95.92 14	96.38 47	99.25 14	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 95	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 18	96.56 9	98.76 14	98.87 26	98.42 11	94.93 11	97.70 13	91.83 14	95.52 19	95.94 25	96.63 9	95.94 30	95.47 26	98.80 34	99.47 22
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		96.50 15	97.08 16	95.82 16	96.12 51	98.97 23	98.00 15	94.13 20	97.89 10	91.49 15	95.11 24	97.52 12	96.26 19	96.27 27	94.07 54	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 14	95.01 22	98.40 22	99.11 18	97.93 17	93.62 23	96.28 29	87.45 27	97.05 8	96.00 24	94.23 31	96.83 19	95.97 17	98.40 57	99.27 29
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 17	96.41 23	95.72 17	98.58 17	98.84 27	97.95 16	93.08 27	96.96 22	90.24 19	96.60 13	94.40 31	96.52 13	95.13 42	94.33 45	97.93 85	98.59 65

ACMMP_NAP		95.81 18	96.50 22	95.01 22	98.79 13	99.17 16	97.52 26	94.20 19	96.19 30	85.71 35	93.80 32	96.20 23	95.89 20	96.62 22	94.98 37	97.93 85	98.52 68

train_agg		95.72 19	97.37 13	93.80 28	97.82 31	98.92 24	97.84 19	93.50 24	96.86 24	81.35 54	97.10 7	97.71 9	94.19 32	96.02 28	95.37 30	98.07 72	99.64 16

ACMMPR		95.59 20	95.89 25	95.25 20	98.41 21	98.74 29	97.69 24	92.73 31	96.88 23	88.95 24	95.33 21	92.91 38	95.79 21	94.73 52	94.33 45	97.92 87	98.32 77

DeepC-MVS_fast	91.53 1	95.57 21	95.67 28	95.45 19	98.57 18	99.00 22	97.76 21	94.41 17	97.06 19	86.84 29	86.39 45	92.27 43	96.38 17	97.89 5	98.06 3	98.73 39	99.01 48
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 22	94.84 33	96.25 10	98.64 16	98.63 32	98.35 12	92.37 33	95.04 48	92.62 10	87.12 44	93.79 32	96.55 11	93.53 72	96.78 6	98.98 20	98.99 49

CP-MVS		95.43 23	95.67 28	95.14 21	98.24 27	98.60 33	97.45 27	92.80 29	95.98 33	89.21 23	95.22 22	93.60 33	95.43 24	94.37 59	93.22 73	97.68 95	98.72 56

DPM-MVS		95.36 24	95.84 26	94.82 24	96.70 43	98.49 43	99.27 1	95.09 6	96.71 25	83.87 43	86.34 47	96.44 22	95.06 26	98.35 1	98.82 1	98.89 29	95.69 131

MP-MVS		95.24 25	95.96 24	94.40 26	98.32 24	98.38 48	97.12 29	92.87 28	95.17 46	85.50 36	95.68 17	94.91 29	94.58 28	95.11 43	93.76 59	98.05 75	98.68 58
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 26	97.02 17	92.61 38	97.19 37	98.71 31	97.74 23	93.21 26	96.97 21	79.27 70	94.09 30	97.14 15	90.84 65	96.64 21	95.94 20	97.42 110	99.67 15

X-MVS		94.70 27	95.71 27	93.52 32	98.38 23	98.56 35	96.99 30	92.62 32	95.58 37	81.00 61	94.57 27	93.49 34	94.16 34	94.82 48	94.29 48	97.99 81	98.68 58

PGM-MVS		94.64 28	95.49 30	93.66 30	98.55 19	98.51 41	97.63 25	87.77 46	94.45 52	84.92 39	97.23 5	91.90 45	95.22 25	94.56 55	93.80 58	97.87 91	97.97 88

TSAR-MVS + GP.		94.59 29	96.60 21	92.25 39	90.25 92	98.17 55	96.22 36	86.53 52	97.49 16	87.26 28	95.21 23	97.06 16	94.07 36	94.34 61	94.20 50	99.18 5	99.71 14

PHI-MVS		94.49 30	96.72 20	91.88 41	97.06 38	98.88 25	94.99 47	89.13 41	96.15 31	79.70 66	96.91 10	95.78 26	91.87 55	94.65 53	95.68 23	98.53 49	98.98 51

AdaColmap		94.28 31	92.94 45	95.84 15	98.32 24	98.33 50	96.06 38	94.62 16	96.29 28	91.22 16	89.89 38	85.50 74	96.38 17	91.85 101	90.89 88	98.44 53	97.81 91

DeepPCF-MVS	91.00 2	94.15 32	96.87 19	90.97 49	96.82 41	99.33 11	89.40 100	92.76 30	98.76 1	82.36 50	88.74 39	95.49 28	90.58 72	98.13 4	97.80 4	93.88 190	99.88 6

CPTT-MVS		94.11 33	93.99 38	94.25 27	96.58 44	97.66 63	97.31 28	91.94 34	94.84 49	88.72 26	92.51 33	93.04 37	95.78 22	91.51 104	89.97 105	95.15 179	98.37 74

EPNet		93.69 34	95.34 31	91.76 42	96.98 40	98.47 45	95.40 44	86.79 49	95.47 39	82.84 47	95.66 18	89.17 51	90.47 74	95.25 41	94.69 40	98.10 69	98.68 58
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 35	93.59 41	93.00 36	97.03 39	98.24 51	95.27 45	91.66 37	95.20 44	83.25 45	95.39 20	85.52 72	92.80 46	92.60 91	90.21 101	98.01 78	97.99 86
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 36	93.72 40	92.65 37	95.48 54	99.09 20	96.55 34	86.74 50	95.28 42	85.22 37	77.30 73	91.25 47	92.60 48	97.06 15	96.63 7	99.31 2	99.45 23

CDPH-MVS		93.22 37	95.08 32	91.04 48	97.57 34	98.49 43	96.74 32	89.35 40	95.19 45	73.57 99	90.26 36	91.59 46	90.68 69	95.09 45	96.15 14	98.31 63	98.81 54

CSCG		93.16 38	92.65 47	93.76 29	98.32 24	99.09 20	96.12 37	89.91 39	93.15 61	89.64 20	83.62 55	88.91 54	92.40 50	91.09 109	93.70 60	96.14 162	98.99 49

MVS_111021_LR		93.05 39	94.53 35	91.32 46	96.43 46	98.38 48	92.81 60	87.20 48	95.94 35	81.45 53	94.75 25	86.08 68	92.12 53	94.83 47	93.34 67	97.89 90	98.42 73

3Dnovator+	86.26 7	92.90 40	92.45 49	93.42 33	97.25 36	98.45 47	95.82 39	85.71 58	93.83 56	89.55 22	72.31 103	92.28 42	94.01 38	95.10 44	95.92 21	98.17 65	99.23 31

MVS_111021_HR		92.73 41	94.83 34	90.28 55	96.27 48	99.10 19	92.77 61	86.15 55	93.41 59	77.11 88	93.82 31	87.39 60	90.61 70	95.60 34	95.15 33	98.79 35	99.32 25

PLC	89.12 3	92.67 42	90.84 59	94.81 25	97.69 32	96.10 91	95.42 43	91.70 35	95.82 36	92.52 12	81.24 59	86.01 69	94.36 29	92.44 95	90.27 98	97.19 119	93.99 159
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 43	91.96 51	93.20 34	97.99 28	98.47 45	95.78 40	85.94 56	93.07 63	86.40 31	73.43 95	89.00 53	94.08 35	94.74 51	96.44 12	99.01 19	98.57 66

DeepC-MVS	88.77 4	92.39 44	91.74 53	93.14 35	96.21 49	98.55 38	96.30 35	93.84 21	93.06 64	81.09 59	74.69 88	85.20 78	93.48 41	95.41 37	96.13 15	97.92 87	99.18 37
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 45	91.88 52	92.25 39	96.51 45	97.94 57	93.18 57	88.97 43	96.53 26	84.47 41	80.79 61	87.85 56	93.25 44	92.48 94	91.81 81	97.12 120	95.73 130

MVSTER		91.91 46	93.43 44	90.14 56	89.81 99	92.32 132	94.53 50	81.32 89	96.00 32	84.77 40	85.41 52	92.39 41	91.32 57	96.41 23	94.01 56	99.11 8	97.45 100

MVS_0304		91.90 47	92.93 46	90.69 53	93.66 64	98.78 28	96.73 33	85.43 62	93.13 62	78.11 82	77.02 76	89.09 52	91.10 61	96.98 17	96.54 8	99.11 8	98.96 52

CS-MVS-test		91.76 48	93.47 42	89.76 59	94.64 59	98.22 53	88.13 110	81.58 86	97.02 20	82.47 49	85.49 51	85.41 76	93.28 43	95.33 39	93.61 62	98.45 52	99.22 32

QAPM		91.68 49	91.97 50	91.34 45	97.86 30	98.72 30	95.60 42	85.72 57	90.86 77	77.14 87	76.06 77	90.35 48	92.69 47	94.10 64	94.60 41	99.04 15	99.09 42

CS-MVS		91.55 50	92.49 48	90.45 54	94.00 62	97.91 59	91.17 81	81.40 88	95.22 43	83.51 44	82.37 57	82.29 84	94.07 36	96.36 26	94.03 55	98.56 46	99.22 32

CNLPA		91.53 51	89.74 71	93.63 31	96.75 42	97.63 65	91.16 82	91.70 35	96.38 27	90.82 17	69.66 114	85.52 72	93.76 39	90.44 115	91.14 87	97.55 104	97.40 101

ETV-MVS		91.51 52	94.06 37	88.54 69	89.39 105	97.52 66	89.48 97	80.88 92	97.09 18	79.41 68	87.87 40	86.18 67	92.95 45	95.94 30	94.33 45	99.13 7	99.52 21

EC-MVSNet		91.25 53	93.45 43	88.68 67	88.90 111	96.18 90	91.66 70	76.70 123	95.57 38	82.00 51	84.18 53	89.28 50	94.17 33	95.64 33	94.19 51	98.68 41	99.14 41

DELS-MVS		91.09 54	90.56 67	91.71 43	95.82 52	98.59 34	95.74 41	86.68 51	85.86 105	85.12 38	72.71 98	81.36 87	88.06 94	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 47	96.14 50	97.66 63	94.80 48	89.00 42	94.74 51	77.42 86	80.22 62	86.70 63	92.27 51	91.65 103	90.17 103	98.15 68	93.83 163
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 56	90.66 63	90.82 51	94.75 57	98.54 39	91.30 78	86.53 52	95.43 40	85.75 33	78.66 68	70.67 124	87.60 95	96.37 24	95.08 35	98.98 20	99.90 2

PVSNet_Blended		90.74 56	90.66 63	90.82 51	94.75 57	98.54 39	91.30 78	86.53 52	95.43 40	85.75 33	78.66 68	70.67 124	87.60 95	96.37 24	95.08 35	98.98 20	99.90 2

CHOSEN 280x420		90.61 58	94.27 36	86.35 89	93.12 68	98.16 56	89.99 93	69.62 177	92.48 68	76.89 91	87.28 43	96.72 19	90.31 76	94.81 49	92.33 78	98.17 65	98.08 84

MAR-MVS		90.44 59	91.17 57	89.59 60	97.48 35	97.92 58	90.96 85	79.80 97	95.07 47	77.03 89	80.83 60	79.10 97	94.68 27	93.16 77	94.46 43	97.59 103	97.63 93
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 76	91.41 44	94.44 60	98.18 54	94.35 51	94.33 18	84.55 118	76.61 92	75.84 80	88.47 55	91.29 58	90.37 117	90.66 94	97.46 106	98.88 53
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 82	90.95 50	97.63 33	98.51 41	94.64 49	85.47 61	88.14 91	78.39 79	65.06 129	85.42 75	91.04 63	93.06 80	93.70 60	98.53 49	98.37 74

EIA-MVS		89.82 62	91.48 55	87.89 78	89.16 107	97.31 68	88.99 101	80.92 91	94.29 53	77.65 84	82.16 58	79.77 95	91.90 54	94.61 54	93.03 75	98.70 40	99.21 35

canonicalmvs		89.62 63	89.87 70	89.33 62	90.47 87	97.02 74	93.46 56	79.67 100	92.45 69	81.05 60	82.84 56	73.00 113	93.71 40	90.38 116	94.85 38	97.65 99	98.54 67

TSAR-MVS + COLMAP		89.59 64	89.64 73	89.53 61	93.32 67	96.51 82	95.03 46	88.53 44	95.98 33	69.10 115	91.81 34	64.53 147	93.40 42	93.53 72	91.35 86	97.77 92	93.75 166

HQP-MVS		89.57 65	90.57 66	88.41 71	92.77 69	94.71 107	94.24 52	87.97 45	93.44 58	68.18 118	91.75 35	71.54 123	89.90 79	92.31 98	91.43 84	97.39 111	98.80 55

MVS_Test		89.02 66	90.20 68	87.64 80	89.83 98	97.05 73	92.30 64	77.59 119	92.89 65	75.01 97	77.36 72	76.10 107	92.27 51	95.30 40	95.42 28	98.83 33	97.30 105

CLD-MVS		88.99 67	88.07 85	90.07 57	89.61 101	94.94 104	93.82 55	85.70 59	92.73 67	82.73 48	79.97 63	69.59 128	90.44 75	90.32 118	89.93 107	98.10 69	99.04 45
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 68	89.94 69	87.70 79	89.44 104	96.74 80	91.62 72	77.92 116	93.79 57	78.76 74	77.55 71	78.46 100	89.38 85	92.26 99	92.52 77	99.10 10	98.23 78

PMMVS		88.56 69	91.22 56	85.47 97	90.04 94	95.60 100	86.62 125	78.49 111	93.86 55	70.62 110	90.00 37	80.08 93	91.64 56	92.36 96	89.80 111	95.40 174	96.84 114

test2506		88.38 70	88.02 87	88.80 66	91.55 78	97.78 60	90.87 87	83.36 71	84.51 119	83.06 46	74.13 91	76.93 104	85.39 105	94.34 61	93.33 69	98.60 42	95.10 148

baseline1		88.16 71	88.15 84	88.17 75	90.02 95	94.79 106	91.85 69	83.89 65	87.37 97	75.67 95	73.75 93	79.89 94	88.44 93	94.41 56	93.33 69	99.18 5	93.55 168

thisisatest0530		87.99 72	90.76 60	84.75 101	88.36 116	96.82 77	87.65 115	79.67 100	91.77 71	70.93 106	79.94 64	87.65 58	84.21 115	92.98 83	89.07 123	97.66 98	97.13 108

tttt0517		87.93 73	90.71 61	84.68 102	88.33 117	96.76 79	87.42 118	79.67 100	91.74 72	70.83 107	79.91 65	87.61 59	84.21 115	92.88 88	89.07 123	97.62 101	97.03 110

CANet_DTU		87.91 74	91.57 54	83.64 109	90.96 81	97.12 71	91.90 68	75.97 131	92.83 66	53.16 173	86.02 48	79.02 98	90.80 66	95.40 38	94.15 52	99.03 18	96.47 125

diffmvs		87.86 75	87.40 93	88.39 72	88.57 114	96.10 91	91.24 80	83.15 74	90.62 78	79.13 72	72.45 101	67.71 134	90.07 78	92.58 92	93.31 72	98.17 65	99.03 46
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 76	90.66 63	84.53 103	90.08 93	96.79 78	88.16 109	79.89 96	85.44 107	72.20 101	75.50 84	87.14 61	80.21 143	95.53 35	95.22 31	96.65 136	99.02 47

EPP-MVSNet		87.72 77	89.74 71	85.37 98	89.11 108	95.57 101	86.31 126	79.44 103	85.83 106	75.73 94	77.23 74	90.05 49	84.78 111	91.22 107	90.25 99	96.83 127	98.04 85

casdiffmvs_mvg		87.64 78	86.46 100	89.01 65	89.45 103	96.09 93	92.69 62	83.42 70	84.60 117	80.01 65	68.55 117	70.29 126	90.51 73	93.93 67	93.59 63	97.96 82	98.18 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
ET-MVSNet_ETH3D		87.63 79	91.08 58	83.59 110	67.96 213	96.30 89	92.06 66	78.47 112	91.95 70	69.87 112	87.57 42	84.14 82	94.34 30	88.58 131	92.10 79	98.88 30	96.93 111

DI_MVS_plusplus_trai		87.63 79	87.13 95	88.22 74	88.61 113	95.92 96	94.09 54	81.41 87	87.00 100	78.38 80	59.70 148	80.52 91	89.08 88	94.37 59	93.34 67	97.73 93	99.05 44

casdiffmvs		87.59 81	86.69 99	88.64 68	89.06 109	96.32 88	90.18 90	83.21 73	87.74 95	80.20 64	67.99 119	68.34 132	90.79 67	93.83 68	94.08 53	98.41 56	98.50 70
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 82	88.72 83	85.95 93	92.02 73	97.26 69	86.88 123	82.66 81	83.86 125	79.16 71	66.96 123	84.91 79	77.26 160	94.97 46	93.48 64	97.73 93	99.64 16

FMVSNet3		87.19 83	87.32 94	87.04 87	82.82 152	90.21 147	92.88 59	76.53 126	91.69 73	81.31 55	64.81 132	80.64 88	89.79 83	94.80 50	94.76 39	98.88 30	94.32 155

LS3D		87.19 83	85.48 107	89.18 63	94.96 56	95.47 102	92.02 67	93.36 25	88.69 89	67.01 119	70.56 110	72.10 118	92.47 49	89.96 121	89.93 107	95.25 176	91.68 177

ACMP	85.16 9	87.15 85	87.04 96	87.27 84	90.80 83	94.45 110	89.41 99	83.09 78	89.15 85	76.98 90	86.35 46	65.80 141	86.94 98	88.45 132	87.52 142	96.42 151	97.56 98
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UGNet		87.04 86	89.59 75	84.07 105	90.94 82	95.95 95	86.02 128	81.65 85	85.94 104	78.54 78	78.00 70	85.40 77	69.62 180	91.83 102	91.53 83	97.63 100	98.51 69
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
LGP-MVS_train		86.95 87	87.65 90	86.12 92	91.77 76	93.84 116	93.04 58	82.77 80	88.04 92	65.33 124	87.69 41	67.09 138	86.79 99	90.20 119	88.99 126	97.05 122	97.71 92

PatchMatch-RL		86.75 88	85.43 108	88.29 73	94.06 61	96.37 87	86.82 124	82.94 79	88.94 87	79.59 67	79.83 66	59.17 160	89.46 84	91.12 108	88.81 130	96.88 126	93.78 164

FA-MVS(training)		86.74 89	88.01 88	85.26 99	89.86 96	96.99 75	88.54 106	64.26 193	89.04 86	81.30 58	66.74 125	81.52 86	89.11 87	94.04 65	90.37 97	98.47 51	97.37 102

baseline2		86.51 90	89.35 79	83.19 112	85.70 137	94.88 105	85.75 133	77.13 121	89.87 82	70.65 109	79.03 67	79.14 96	81.51 136	93.70 69	90.22 100	98.38 59	98.60 64

thres100view900		86.48 91	85.08 110	88.12 76	90.54 84	96.90 76	92.39 63	84.82 63	84.16 123	71.65 102	70.86 107	60.49 155	91.23 60	93.65 70	90.19 102	98.10 69	99.32 25

ACMM	84.23 10	86.40 92	84.64 113	88.46 70	91.90 74	91.93 138	88.11 111	85.59 60	88.61 90	79.13 72	75.31 85	66.25 139	89.86 82	89.88 122	87.64 139	96.16 161	92.86 173
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		86.16 93	86.00 103	86.35 89	81.81 158	89.52 156	91.40 74	76.53 126	91.69 73	81.31 55	64.81 132	80.64 88	88.72 89	90.54 112	90.72 90	98.34 60	94.08 156

test1		86.16 93	86.00 103	86.35 89	81.81 158	89.52 156	91.40 74	76.53 126	91.69 73	81.31 55	64.81 132	80.64 88	88.72 89	90.54 112	90.72 90	98.34 60	94.08 156

tfpn200view9		86.07 95	84.76 112	87.61 81	90.54 84	96.39 84	91.35 77	83.15 74	84.16 123	71.65 102	70.86 107	60.49 155	90.91 64	92.89 85	89.34 114	98.05 75	99.17 38

DCV-MVSNet		85.90 96	85.88 105	85.93 94	87.86 122	88.37 173	89.45 98	77.46 120	87.33 98	77.51 85	76.06 77	75.76 109	88.48 92	87.40 141	88.89 129	94.80 185	97.37 102

Vis-MVSNet (Re-imp)		85.89 97	89.62 74	81.55 123	89.85 97	96.08 94	87.55 116	79.80 97	84.80 114	66.55 121	73.70 94	86.71 62	68.25 187	94.40 57	94.53 42	97.32 114	97.09 109

MSDG		85.81 98	82.29 137	89.93 58	95.52 53	92.61 127	91.51 73	91.46 38	85.12 111	78.56 76	63.25 138	69.01 130	85.31 108	88.45 132	88.23 133	97.21 118	89.33 188

thres200		85.80 99	84.38 114	87.46 82	90.51 86	96.39 84	91.64 71	83.15 74	81.59 134	71.54 104	70.24 111	60.41 157	89.88 80	92.89 85	89.85 110	98.06 73	99.26 30

ECVR-MVS		85.74 100	83.80 122	88.00 77	91.55 78	97.78 60	90.87 87	83.36 71	84.51 119	78.21 81	58.65 153	62.75 151	85.39 105	94.34 61	93.33 69	98.60 42	95.25 142

OPM-MVS		85.69 101	82.79 130	89.06 64	93.42 65	94.21 114	94.21 53	87.61 47	72.68 159	70.79 108	71.09 105	67.27 137	90.74 68	91.29 106	89.05 125	97.61 102	93.94 161
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		85.59 102	84.08 117	87.36 83	90.45 88	96.60 81	90.95 86	83.67 68	80.99 137	71.17 105	69.08 116	60.25 158	89.88 80	93.14 78	89.34 114	98.02 77	99.17 38

CostFormer		85.47 103	86.98 97	83.71 108	88.70 112	94.02 115	88.07 112	62.72 195	89.78 83	78.68 75	72.69 99	78.37 101	87.35 97	85.96 154	89.32 118	96.73 133	98.72 56

test1111		85.17 104	83.46 125	87.17 85	91.36 80	97.75 62	90.06 92	83.44 69	83.41 127	75.25 96	58.08 156	62.19 153	84.39 114	94.39 58	93.38 66	98.54 48	95.00 150

thres600view7		85.14 105	83.58 124	86.96 88	90.37 91	96.39 84	90.33 89	83.15 74	80.46 138	70.60 111	67.96 120	60.04 159	89.22 86	92.89 85	88.28 132	98.06 73	99.08 43

test-LLR		85.11 106	89.49 77	80.00 132	85.32 141	94.49 108	82.27 163	74.18 140	87.83 93	56.70 151	75.55 82	86.26 64	82.75 129	93.06 80	90.60 95	98.77 36	98.65 62

FMVSNet2		84.89 107	84.02 119	85.91 95	81.81 158	89.52 156	91.40 74	75.79 132	84.45 121	79.39 69	58.75 151	74.35 111	88.72 89	93.51 74	93.46 65	98.34 60	94.08 156

FC-MVSNet-train		84.88 108	84.08 117	85.82 96	89.21 106	91.74 139	85.87 129	81.20 90	81.71 133	74.66 98	73.38 96	64.99 145	86.60 100	90.75 110	88.08 134	97.36 112	97.90 89

EPNet_dtu		84.87 109	89.01 80	80.05 131	95.25 55	92.88 125	88.84 103	84.11 64	91.69 73	49.28 189	85.69 49	78.95 99	65.39 192	92.22 100	91.66 82	97.43 109	89.95 184
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 110	85.71 106	83.73 107	87.94 121	95.76 97	90.08 91	73.45 147	85.12 111	62.66 133	72.39 102	64.97 146	90.59 71	92.95 84	90.69 93	97.67 97	98.12 81

UA-Net		84.69 111	87.64 91	81.25 125	90.38 90	95.67 98	87.33 119	79.41 104	72.07 163	66.48 122	75.09 86	92.48 40	66.88 188	94.03 66	94.25 49	97.01 125	89.88 185

TESTMET0.1,1		84.62 112	89.49 77	78.94 141	82.18 155	94.49 108	82.27 163	70.94 167	87.83 93	56.70 151	75.55 82	86.26 64	82.75 129	93.06 80	90.60 95	98.77 36	98.65 62

CHOSEN 1792x2688		84.59 113	84.30 116	84.93 100	93.71 63	98.23 52	89.91 94	77.96 115	84.81 113	65.93 123	45.19 197	71.76 122	83.13 127	95.46 36	95.13 34	98.94 25	99.53 20

Anonymous20231211		84.23 114	81.71 142	87.17 85	87.38 129	93.59 119	88.95 102	82.14 83	83.82 126	78.56 76	48.09 191	73.89 112	91.25 59	86.38 148	88.06 136	94.74 186	98.14 80

MDTV_nov1_ep13		84.17 115	88.03 86	79.66 134	86.00 135	94.41 111	85.05 135	66.01 189	90.36 79	64.34 129	77.13 75	84.56 80	82.71 131	87.12 145	88.92 127	93.84 192	93.69 167

test-mter		84.06 116	89.00 81	78.29 146	81.92 156	94.23 113	81.07 173	70.38 171	87.12 99	56.10 160	74.75 87	85.80 70	81.81 135	92.52 93	90.10 104	98.43 54	98.49 71

IB-MVS	79.58 12	83.83 117	84.81 111	82.68 115	91.85 75	97.35 67	75.75 192	82.57 82	86.55 102	84.01 42	70.90 106	65.43 143	63.18 198	84.19 168	89.92 109	98.74 38	99.31 27
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		83.71 118	86.76 98	80.16 130	89.72 100	95.64 99	84.68 136	59.73 200	89.61 84	62.67 132	72.65 100	81.80 85	86.22 102	86.23 150	88.03 137	97.96 82	93.35 169

HyFIR lowres test		83.43 119	82.94 128	84.01 106	93.41 66	97.10 72	87.21 120	74.04 142	80.15 140	64.98 125	41.09 205	76.61 106	86.51 101	93.31 75	93.01 76	97.91 89	99.30 28

PatchmatchNet		83.28 120	87.57 92	78.29 146	87.46 127	94.95 103	83.36 145	59.43 203	90.20 81	58.10 146	74.29 90	86.20 66	84.13 117	85.27 160	87.39 143	97.25 117	94.67 153
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 121	87.76 89	78.00 151	87.45 128	92.20 133	82.63 159	58.42 205	90.30 80	58.23 144	75.74 81	87.75 57	83.97 120	86.10 153	87.64 139	97.30 115	94.62 154

GeoE		83.17 122	82.86 129	83.53 111	87.24 130	93.78 117	87.94 113	72.75 152	82.19 131	69.76 113	60.54 145	65.95 140	86.01 103	89.41 126	89.72 112	97.47 105	98.43 72

CDS-MVSNet		83.13 123	83.73 123	82.43 121	84.52 146	92.92 124	88.26 108	77.67 118	72.08 162	69.08 116	66.96 123	74.66 110	78.61 149	90.70 111	91.96 80	96.46 150	96.86 113
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 124	81.86 139	84.13 104	88.25 118	88.32 174	87.67 114	80.86 93	84.78 115	76.57 93	85.56 50	76.00 108	84.61 112	78.20 203	76.52 206	86.81 212	83.63 205

Vis-MVSNet		82.88 125	86.04 102	79.20 139	87.77 125	96.42 83	86.10 127	76.70 123	74.82 153	61.38 136	70.70 109	77.91 102	64.83 194	93.22 76	93.19 74	98.43 54	96.01 128
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 126	82.64 133	82.62 117	87.81 124	92.81 126	84.39 137	61.96 196	86.43 103	81.63 52	69.72 113	67.60 136	84.42 113	82.51 181	83.90 180	95.52 170	95.50 139

IterMVS-LS		82.62 127	82.75 132	82.48 118	87.09 131	87.48 187	87.19 121	72.85 150	79.09 141	66.63 120	65.22 127	72.14 117	84.06 119	88.33 135	91.39 85	97.03 124	95.60 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 128	82.51 135	82.72 114	85.49 140	93.06 123	87.17 122	71.39 164	84.18 122	64.59 127	63.03 139	58.89 161	90.22 77	91.39 105	90.83 89	97.44 107	96.21 127

tpm cat1		82.39 129	82.32 136	82.47 119	88.13 119	92.42 131	87.43 117	62.79 194	85.30 108	78.05 83	60.14 146	72.10 118	83.20 126	82.26 184	85.67 159	95.23 177	98.35 76

dmvs_re		82.31 130	81.55 143	83.19 112	83.15 151	93.17 122	88.68 105	83.72 66	82.73 129	61.70 134	67.43 122	55.43 169	83.35 125	87.51 140	89.27 121	98.56 46	95.31 141

MS-PatchMatch		82.16 131	82.18 138	82.12 122	91.65 77	93.50 120	89.51 96	71.95 158	81.48 135	64.45 128	59.58 150	77.54 103	77.23 161	89.88 122	85.62 160	97.94 84	87.68 192

tpmrst		81.71 132	83.87 121	79.20 139	89.01 110	93.67 118	84.22 138	60.14 198	87.45 96	59.49 140	64.97 130	71.86 121	85.30 109	84.72 164	86.30 151	97.04 123	98.09 83

RPMNet		81.47 133	86.24 101	75.90 169	86.72 132	92.12 135	82.82 157	55.76 211	85.21 109	53.73 171	63.45 136	83.16 83	80.13 144	92.34 97	89.52 113	96.23 159	97.90 89

CR-MVSNet		81.44 134	85.29 109	76.94 160	86.53 133	92.12 135	83.86 139	58.37 206	85.21 109	56.28 155	59.60 149	80.39 92	80.50 141	92.77 89	89.32 118	96.12 163	97.59 96

Effi-MVS+-dtu		81.18 135	82.77 131	79.33 137	84.70 145	92.54 129	85.81 130	71.55 162	78.84 142	57.06 150	71.98 104	63.77 149	85.09 110	88.94 128	87.62 141	91.79 205	95.68 133

test0.0.03 1		80.99 136	84.37 115	77.05 158	85.32 141	89.79 152	78.43 183	74.18 140	84.78 115	57.98 149	76.06 77	72.88 114	69.14 184	88.02 137	87.70 138	97.27 116	91.37 178

Fast-Effi-MVS+-dtu		80.57 137	83.44 126	77.22 156	83.98 149	91.52 141	85.78 132	64.54 192	80.38 139	50.28 185	74.06 92	62.89 150	82.00 134	89.10 127	88.91 128	96.75 131	97.21 107

FMVSNet5		80.56 138	82.53 134	78.26 148	73.80 208	81.52 206	82.26 165	68.36 182	88.85 88	64.21 130	69.09 115	84.38 81	83.49 124	87.13 144	86.76 148	97.44 107	79.95 208

ADS-MVSNet		80.25 139	82.96 127	77.08 157	87.86 122	92.60 128	81.82 170	56.19 210	86.95 101	56.16 158	68.19 118	72.42 116	83.70 123	82.05 185	85.45 165	96.75 131	93.08 172

FMVSNet1		80.18 140	78.07 154	82.65 116	78.55 182	87.57 186	88.41 107	73.93 143	70.16 168	73.57 99	49.80 181	64.45 148	85.35 107	90.54 112	90.72 90	96.10 164	93.21 170

USDC		80.10 141	79.33 150	81.00 127	86.36 134	91.71 140	88.74 104	75.77 133	81.90 132	54.90 165	67.67 121	52.05 174	83.94 121	88.44 134	86.25 152	96.31 154	87.28 196

COLMAP_ROB	75.69 15	79.47 142	76.90 161	82.46 120	92.20 70	90.53 143	85.30 134	83.69 67	78.27 145	61.47 135	58.26 154	62.75 151	78.28 152	82.41 182	82.13 193	93.83 194	83.98 204
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmmvs4		79.32 143	77.78 156	81.11 126	80.18 167	88.96 168	83.39 143	76.07 129	81.27 136	69.35 114	58.66 152	51.19 177	82.01 133	87.16 143	84.39 177	95.66 168	92.82 174

PatchT		79.28 144	83.88 120	73.93 178	85.54 139	90.95 142	66.14 209	56.53 209	83.21 128	56.28 155	56.50 158	76.80 105	80.50 141	92.77 89	89.32 118	98.57 45	97.59 96

ACMH	78.51 14	79.27 145	78.08 153	80.65 128	89.52 102	90.40 144	80.45 175	79.77 99	69.54 173	54.85 166	64.83 131	56.16 167	83.94 121	84.58 166	86.01 156	95.41 173	95.03 149
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 146	78.95 152	79.56 135	81.89 157	92.52 130	82.97 152	73.70 144	67.27 179	64.97 126	61.66 144	65.06 144	78.61 149	87.12 145	88.07 135	95.23 177	90.95 180

ACMH+	79.09 13	79.12 147	77.22 160	81.35 124	88.50 115	90.36 145	82.14 167	79.38 106	72.78 158	58.59 141	62.31 143	56.44 166	84.10 118	82.03 186	84.05 178	95.40 174	92.55 175

UniMVSNet_NR-MVSNet		78.89 148	78.04 155	79.88 133	79.40 173	89.70 153	82.92 154	80.17 94	76.37 151	58.56 142	57.10 157	54.92 170	81.44 137	83.51 173	87.12 145	96.76 130	97.60 94

tpm		78.87 149	81.33 146	76.00 167	85.57 138	90.19 148	82.81 158	59.66 201	78.35 144	51.40 180	66.30 126	67.92 133	80.94 139	83.28 176	85.73 157	95.65 169	97.56 98

GA-MVS		78.86 150	80.42 147	77.05 158	83.27 150	92.17 134	83.24 147	75.73 134	73.75 155	46.27 199	62.43 141	57.12 163	76.94 163	93.14 78	89.34 114	96.83 127	95.00 150

IterMVS		78.85 151	81.36 144	75.93 168	84.27 148	85.74 193	83.83 141	66.35 187	76.82 146	50.48 183	63.48 135	68.82 131	73.99 168	89.68 124	89.34 114	96.63 139	95.67 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 152	81.34 145	75.64 173	84.31 147	85.67 194	83.51 142	66.14 188	76.67 147	50.38 184	63.45 136	69.02 129	73.23 170	89.66 125	89.22 122	96.24 158	95.67 134

UniMVSNet (Re)		78.00 153	77.52 157	78.57 144	79.66 172	90.36 145	82.09 168	77.86 117	76.38 150	60.26 137	54.63 164	52.07 173	75.31 166	84.97 163	86.10 154	96.22 160	98.11 82

DU-MVS		77.98 154	76.71 162	79.46 136	78.68 179	89.26 162	82.92 154	79.06 108	76.52 148	58.56 142	54.89 162	48.35 191	81.44 137	83.16 178	87.21 144	96.08 165	97.60 94

FC-MVSNet-test		77.95 155	81.85 140	73.39 183	82.31 153	88.99 167	79.33 179	74.24 139	78.75 143	47.40 197	70.22 112	72.09 120	60.78 204	86.66 147	85.62 160	96.30 155	90.61 181

NR-MVSNet		77.21 156	76.41 163	78.14 150	80.18 167	89.26 162	83.38 144	79.06 108	76.52 148	56.59 153	54.89 162	45.32 201	72.89 172	85.39 159	86.12 153	96.71 134	97.36 104

thisisatest0515		77.13 157	79.36 149	74.52 175	79.79 171	89.65 154	73.54 197	73.69 145	74.10 154	58.14 145	62.79 140	60.57 154	66.49 190	88.08 136	85.16 170	95.49 172	95.15 146

gg-mvs-nofinetune		77.08 158	79.79 148	73.92 179	85.95 136	97.23 70	92.18 65	52.65 214	46.19 217	27.79 222	38.27 209	85.63 71	85.67 104	96.95 18	95.62 25	99.30 3	98.67 61

TranMVSNet+NR-MVSNet		77.02 159	75.76 165	78.49 145	78.46 185	88.24 175	83.03 151	79.97 95	73.49 157	54.73 167	54.00 167	48.74 186	78.15 154	82.36 183	86.90 147	96.59 141	96.55 119

CVMVSNet		76.86 160	79.09 151	74.26 176	85.29 143	89.44 159	79.91 178	78.47 112	68.94 176	44.45 204	62.35 142	69.70 127	64.50 195	85.82 155	87.03 146	92.94 200	90.33 182

Baseline_NR-MVSNet		76.71 161	74.56 172	79.23 138	78.68 179	84.15 202	82.45 161	78.87 110	75.83 152	60.05 138	47.92 192	50.18 183	79.06 148	83.16 178	83.86 181	96.26 156	96.80 115

v2v482		76.25 162	74.78 169	77.96 152	78.50 184	89.14 165	83.05 150	76.02 130	68.78 177	54.11 168	51.36 173	48.59 188	79.49 146	83.53 172	85.60 163	96.59 141	96.49 124

V42		76.21 163	75.04 168	77.58 153	78.68 179	89.33 161	82.93 153	74.64 137	69.84 170	56.13 159	50.42 178	50.93 178	76.30 165	83.32 174	84.89 174	96.83 127	96.54 120

v8		75.89 164	74.74 170	77.23 155	79.09 175	88.00 178	83.19 148	71.08 166	70.03 169	56.29 154	50.50 176	50.88 179	77.06 162	83.32 174	84.99 172	96.68 135	95.49 140

TinyColmap		75.75 165	73.19 183	78.74 143	84.82 144	87.69 182	81.59 171	74.62 138	71.81 164	54.01 169	55.79 161	44.42 206	82.89 128	84.61 165	83.76 182	94.50 187	84.22 203

MIMVSNet		75.71 166	77.26 158	73.90 180	70.93 209	88.71 171	79.98 177	57.67 208	73.58 156	58.08 148	53.93 168	58.56 162	79.41 147	90.04 120	89.97 105	97.34 113	86.04 197

UniMVSNet_ETH3D		75.63 167	71.59 192	80.35 129	81.03 162	89.90 151	83.25 146	76.58 125	60.08 200	64.19 131	42.89 204	45.01 202	82.14 132	80.20 196	86.75 149	94.90 182	96.29 126

pm-mvs1		75.61 168	74.19 174	77.26 154	80.16 169	88.79 169	81.49 172	75.49 136	59.49 202	58.09 147	48.32 189	55.53 168	72.35 173	88.61 130	85.48 164	95.99 166	93.12 171

v10		75.57 169	74.67 171	76.62 163	78.73 178	87.46 188	83.14 149	69.41 178	69.27 174	53.44 172	49.73 182	49.21 185	78.44 151	86.17 152	85.18 169	96.53 146	95.65 137

v1144		75.54 170	74.55 173	76.69 161	78.33 188	88.77 170	82.89 156	72.76 151	67.18 181	51.73 177	49.34 184	48.37 189	78.10 155	86.22 151	85.24 167	96.35 153	96.74 116

TDRefinement		75.54 170	73.22 181	78.25 149	87.65 126	89.65 154	85.81 130	79.28 107	71.14 166	56.06 161	52.17 171	51.96 175	68.74 186	81.60 187	80.58 195	91.94 203	85.45 198

pmmvs5		75.46 172	75.12 167	75.87 170	79.39 174	89.44 159	78.12 185	72.27 156	65.98 186	51.54 178	55.83 160	46.23 196	76.80 164	88.77 129	85.73 157	97.07 121	93.84 162

tfpnnormal		75.27 173	72.12 189	78.94 141	82.30 154	88.52 172	82.41 162	79.41 104	58.03 203	55.59 163	43.83 203	44.71 203	77.35 158	87.70 139	85.45 165	96.60 140	96.61 118

anonymousdsp		75.14 174	77.25 159	72.69 186	76.68 198	89.26 162	75.26 194	68.44 181	65.53 189	46.65 198	58.16 155	56.67 165	73.96 169	87.84 138	86.05 155	95.13 180	97.22 106

v148		74.98 175	73.52 179	76.69 161	78.84 177	89.02 166	78.78 181	76.82 122	67.22 180	59.61 139	49.18 185	47.94 193	70.57 179	80.76 191	83.99 179	95.52 170	96.52 122

v1192		74.96 176	73.92 175	76.17 164	77.76 191	88.19 177	82.54 160	71.94 159	66.84 182	50.07 187	48.10 190	46.14 197	78.28 152	86.30 149	85.23 168	96.41 152	96.67 117

v144192		74.76 177	73.64 176	76.06 166	77.58 192	88.23 176	81.87 169	71.63 161	66.03 185	51.08 181	48.63 188	46.77 195	77.59 157	84.53 167	84.76 175	96.64 138	96.54 120

v1921920		74.60 178	73.56 178	75.81 171	77.43 194	87.94 179	82.18 166	71.33 165	66.48 184	49.23 191	47.84 193	45.56 199	78.03 156	85.70 157	84.92 173	96.65 136	96.50 123

v1240		74.04 179	73.04 185	75.20 174	77.19 196	87.69 182	80.93 174	70.72 170	65.08 190	48.47 192	47.31 194	44.71 203	77.33 159	85.50 158	85.07 171	96.59 141	95.94 129

testgi		73.22 180	75.84 164	70.16 197	81.67 161	85.50 197	71.45 199	70.81 168	69.56 172	44.74 203	74.52 89	49.25 184	58.45 205	84.10 170	83.37 186	93.86 191	84.56 202

CP-MVSNet		73.19 181	72.37 187	74.15 177	77.54 193	86.77 191	76.34 188	72.05 157	65.66 188	51.47 179	50.49 177	43.66 207	70.90 175	80.93 190	83.40 185	96.59 141	95.66 136

WR-MVS		72.93 182	73.57 177	72.19 189	78.14 189	87.71 181	76.21 190	73.02 149	67.78 178	50.09 186	50.35 179	50.53 181	61.27 203	80.42 194	83.10 189	94.43 188	95.11 147

TransMVSNet (Re)		72.90 183	70.51 196	75.69 172	80.88 163	85.26 199	79.25 180	78.43 114	56.13 209	52.81 174	46.81 195	48.20 192	66.77 189	85.18 162	83.70 183	95.98 167	88.28 191

WR-MVS_H		72.69 184	72.80 186	72.56 188	77.94 190	87.83 180	75.26 194	71.53 163	64.75 191	52.19 176	49.83 180	48.62 187	61.96 201	81.12 189	82.44 191	96.50 147	95.00 150

SixPastTwentyTwo		72.65 185	73.22 181	71.98 192	78.40 186	87.64 184	70.09 202	70.37 172	66.49 183	47.60 195	65.09 128	45.94 198	73.09 171	78.94 198	78.66 201	92.33 201	89.82 186

LTVRE_ROB	71.82 16	72.62 186	71.77 190	73.62 181	80.74 164	87.59 185	80.42 176	70.37 172	49.73 213	37.12 216	59.76 147	42.52 212	80.92 140	83.20 177	85.61 162	92.13 202	93.95 160
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		72.37 187	71.47 194	73.43 182	77.32 195	86.43 192	75.99 191	71.94 159	63.37 194	49.24 190	49.07 186	42.42 213	69.60 181	80.59 193	83.18 188	96.48 149	95.23 144

MVS-HIRNet		72.32 188	73.45 180	71.00 195	80.58 165	89.97 149	68.51 206	55.28 212	70.89 167	52.27 175	39.09 207	57.11 164	75.02 167	85.76 156	86.33 150	94.36 189	85.00 200

PEN-MVS		72.24 189	71.30 195	73.33 184	77.08 197	85.57 195	76.75 186	72.52 154	63.89 193	48.12 193	50.79 174	43.09 210	69.03 185	78.54 200	83.46 184	96.50 147	93.76 165

v7n		72.11 190	71.66 191	72.63 187	75.26 203	86.85 189	76.74 187	68.77 180	62.70 197	49.40 188	45.92 196	43.51 208	70.63 178	84.16 169	83.21 187	94.99 181	95.25 142

EG-PatchMatch MVS		71.81 191	71.54 193	72.12 190	80.53 166	89.94 150	78.51 182	66.56 186	57.38 205	47.46 196	44.28 202	52.22 172	63.10 199	85.22 161	84.42 176	96.56 145	87.35 195

CMPMVS	54.54 17	71.74 192	67.94 201	76.16 165	90.41 89	93.25 121	78.32 184	75.60 135	59.81 201	53.95 170	44.64 200	51.22 176	70.70 176	74.59 209	75.88 207	88.01 209	76.23 211
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 193	73.08 184	69.97 198	75.22 204	86.81 190	73.98 196	59.61 202	69.75 171	48.01 194	54.21 166	53.06 171	69.19 183	78.50 201	80.43 196	93.84 192	88.79 189

pmnet_mix02		71.64 194	72.36 188	70.81 196	78.39 187	85.57 195	68.64 204	73.65 146	72.13 160	45.07 202	56.01 159	50.61 180	65.34 193	76.21 206	76.60 205	93.75 195	89.35 187

gm-plane-assit		71.33 195	75.18 166	66.83 201	79.06 176	75.57 213	48.05 220	60.33 197	48.28 214	34.67 220	44.34 201	67.70 135	79.78 145	97.25 11	96.21 13	99.10 10	96.92 112

DTE-MVSNet		71.19 196	70.45 197	72.06 191	76.61 199	84.59 201	75.61 193	72.32 155	63.12 196	45.70 201	50.72 175	43.02 211	65.89 191	77.53 205	82.23 192	96.26 156	91.93 176

pmmvs6		70.29 197	67.90 202	73.07 185	76.17 200	85.31 198	76.29 189	70.75 169	47.39 216	55.33 164	37.15 213	50.49 182	69.55 182	82.96 180	80.85 194	90.34 208	91.18 179

PM-MVS		70.17 198	69.42 199	71.04 194	70.82 210	81.26 208	71.25 200	67.80 183	69.16 175	51.04 182	53.15 170	34.93 217	72.19 174	80.30 195	76.95 204	93.16 199	90.21 183

pmmvs-eth3d		69.59 199	67.57 204	71.95 193	70.04 211	80.05 209	71.48 198	70.00 176	62.57 198	55.99 162	44.92 198	35.73 216	70.64 177	81.56 188	79.69 197	93.55 196	88.43 190

N_pmnet		68.54 200	67.83 203	69.38 199	75.77 201	81.90 205	66.21 208	72.53 153	65.91 187	46.09 200	44.67 199	45.48 200	63.82 197	74.66 208	77.39 203	91.87 204	84.77 201

Anonymous20231206		68.09 201	68.68 200	67.39 200	75.16 205	82.55 203	69.33 203	70.06 175	63.34 195	42.28 207	37.91 211	43.12 209	52.67 208	83.56 171	82.71 190	94.84 184	87.59 193

EU-MVSNet		68.07 202	70.25 198	65.52 202	74.68 207	81.30 207	68.53 205	70.31 174	62.40 199	37.43 215	54.62 165	48.36 190	51.34 209	78.32 202	79.27 198	90.84 206	87.47 194

GG-mvs-BLEND		65.67 203	93.78 39	32.89 215	0.47 226	99.35 8	96.92 31	0.22 224	93.28 60	0.51 227	84.07 54	92.50 39	0.62 224	93.59 71	93.86 57	98.59 44	99.79 10

test20.03		65.17 204	67.41 205	62.55 204	75.35 202	79.31 210	62.22 210	68.83 179	56.50 208	35.35 219	51.97 172	44.70 205	40.01 214	80.69 192	79.25 199	93.55 196	79.47 210

MDA-MVSNet-bldmvs		62.23 205	61.13 209	63.52 203	58.94 217	82.44 204	60.71 213	73.28 148	57.22 206	38.42 213	49.63 183	27.64 223	62.83 200	54.98 215	74.16 208	86.96 211	81.83 207

new_pmnet		61.60 206	62.68 207	60.35 207	63.02 214	74.93 214	60.97 212	58.86 204	64.21 192	35.38 218	39.51 206	39.89 214	57.37 206	72.78 210	72.56 210	86.49 213	74.85 213

new-patchmatchnet		60.74 207	59.78 211	61.87 205	69.52 212	76.67 212	57.99 216	65.78 190	52.63 211	38.47 212	38.08 210	32.92 220	48.88 211	68.50 211	69.87 211	90.56 207	79.75 209

pmmvs3		60.52 208	60.87 210	60.12 208	61.38 215	71.62 215	57.42 217	53.94 213	48.09 215	35.95 217	38.62 208	32.19 222	64.12 196	75.33 207	77.99 202	87.89 210	82.28 206

MIMVSNet1		60.51 209	61.43 208	59.44 209	48.75 220	77.21 211	60.98 211	66.84 185	52.09 212	38.74 211	29.29 216	39.40 215	48.08 212	77.60 204	78.87 200	93.22 198	75.56 212

test_method		60.40 210	66.30 206	53.52 211	37.48 224	64.10 219	55.56 218	42.45 219	71.79 165	41.87 208	33.74 214	46.80 194	61.71 202	79.18 197	73.33 209	82.01 215	95.17 145

FPMVS		56.54 211	52.82 213	60.87 206	74.90 206	67.58 218	67.69 207	65.38 191	57.86 204	41.51 209	37.83 212	34.19 218	41.21 213	55.88 214	53.09 216	74.55 218	63.31 216

PMVS	42.57 18	45.71 212	42.61 215	49.32 212	61.35 216	37.82 223	36.96 222	60.10 199	37.20 218	41.50 210	28.53 217	33.11 219	28.82 219	53.45 216	48.70 218	67.22 220	59.42 217
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 213	42.62 214	45.50 213	50.79 219	41.20 222	35.55 223	52.51 215	52.95 210	29.09 221	12.92 219	11.48 226	38.15 215	62.01 213	66.62 213	66.89 221	51.17 218
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 214	42.55 216	39.74 214	43.25 221	55.05 221	38.15 221	47.11 218	31.78 219	11.83 224	21.16 218	19.12 224	20.98 221	49.95 218	56.09 215	77.09 216	64.68 215

E-PMN		27.87 215	24.36 218	31.97 216	41.27 223	25.56 226	16.62 225	49.16 216	22.00 221	9.90 225	11.75 221	7.86 228	29.57 218	22.22 220	34.70 219	45.27 222	46.41 220

MVE	32.98 19	27.61 216	29.89 217	24.94 218	21.97 225	37.22 224	15.56 227	38.83 220	17.49 222	14.72 223	11.64 223	5.62 229	21.26 220	35.20 219	50.95 217	37.29 224	51.13 219
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		26.96 217	22.96 219	31.63 217	41.91 222	25.73 225	16.30 226	49.10 217	22.38 220	9.03 226	11.22 224	8.12 227	29.93 217	20.16 221	31.04 220	43.49 223	42.04 221

testmvs		5.16 218	8.14 220	1.69 219	0.36 227	1.65 227	3.02 228	0.66 222	7.17 223	0.50 228	12.58 220	0.69 230	4.67 222	5.42 222	5.65 221	0.92 225	23.86 223

test123		4.39 219	7.11 221	1.21 220	0.11 228	1.16 228	1.67 229	0.35 223	5.91 224	0.16 229	11.65 222	0.16 231	4.45 223	1.72 223	4.92 222	0.51 226	24.28 222

uanet_test		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

sosnet		0.00 220	0.00 222	0.00 221	0.00 229	0.00 229	0.00 230	0.00 225	0.00 225	0.00 230	0.00 225	0.00 232	0.00 225	0.00 224	0.00 223	0.00 227	0.00 224

TPM-MVS					99.19 1	99.43 7	99.16 2			85.97 32	94.75 25	97.40 13	97.76 1			98.95 24	95.69 131

RE-MVS-def										43.17 205

9.14												97.59 10

SR-MVS					98.52 20			93.70 22				96.63 21

Anonymous202405211			81.72 141		88.09 120	94.27 112	89.62 95	82.14 83	82.27 130		48.83 187	72.58 115	91.08 62	87.40 141	88.70 131	94.90 182	97.99 86

our_test_3					78.55 182	84.98 200	70.12 201

ambc			57.08 212		58.68 218	67.71 217	60.07 214		57.13 207	42.79 206	30.00 215	11.64 225	50.18 210	78.89 199	69.14 212	82.64 214	85.02 199

MTAPA										93.37 8		95.71 27

MTMP										93.84 5		94.86 30

Patchmatch-RL test							19.65 224

tmp_tt				57.89 210	79.94 170	59.29 220	52.84 219	36.65 221	94.77 50	68.22 117	72.96 97	65.62 142	33.65 216	66.20 212	58.02 214	76.06 217

XVS					92.16 71	98.56 35	91.04 83			81.00 61		93.49 34				98.00 79

X-MVStestdata					92.16 71	98.56 35	91.04 83			81.00 61		93.49 34				98.00 79

mPP-MVS					97.95 29							92.24 44

NP-MVS									94.12 54

Patchmtry						92.08 137	83.86 139	58.37 206		56.28 155

DeepMVS_CX						70.68 216	59.61 215	67.36 184	72.12 161	38.41 214	53.88 169	32.44 221	55.15 207	50.88 217		74.35 219	68.42 214

High-resolution multi-view benchmark