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.

SMA-MVS		97.53 7	97.93 7	97.07 10	99.21 1	99.02 8	98.08 19	96.25 11	96.36 12	93.57 15	96.56 14	99.27 5	96.78 16	97.91 4	97.43 3	98.51 26	98.94 12
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
APDe-MVS		97.79 5	97.96 6	97.60 2	99.20 2	99.10 6	98.88 2	96.68 2	96.81 7	94.64 6	97.84 3	98.02 11	97.24 3	97.74 8	97.02 14	98.97 5	99.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		98.07 1	98.46 1	97.62 1	99.08 3	99.29 2	98.84 3	96.63 4	97.89 1	95.35 3	97.83 4	99.48 3	96.98 9	97.99 2	97.14 11	98.82 11	99.60 1

HPM-MVS++		97.22 11	97.40 12	97.01 11	99.08 3	98.55 24	98.19 14	96.48 7	96.02 19	93.28 20	96.26 17	98.71 8	96.76 17	97.30 16	96.25 39	98.30 54	98.68 17

ACMMP_NAP		96.93 16	97.27 15	96.53 23	99.06 5	98.95 9	98.24 13	96.06 15	95.66 21	90.96 32	95.63 24	97.71 16	96.53 20	97.66 10	96.68 20	98.30 54	98.61 22

DVP-MVS		97.93 3	98.23 3	97.58 3	99.05 6	99.31 1	98.64 6	96.62 5	97.56 2	95.08 5	96.61 13	99.64 1	97.32 1	97.91 4	97.31 6	98.77 15	99.26 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
PGM-MVS		96.16 24	96.33 28	95.95 26	99.04 7	98.63 19	98.32 12	92.76 42	93.42 49	90.49 37	96.30 16	95.31 41	96.71 18	96.46 40	96.02 48	98.38 45	98.19 44

APD-MVS		97.12 13	97.05 18	97.19 7	99.04 7	98.63 19	98.45 8	96.54 6	94.81 36	93.50 16	96.10 19	97.40 22	96.81 13	97.05 22	96.82 19	98.80 12	98.56 24
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		96.75 19	96.67 24	96.85 16	99.03 9	98.44 34	98.15 16	96.28 10	96.32 13	92.39 25	92.16 35	97.55 20	96.68 19	97.32 14	96.65 22	98.55 25	98.26 40

CNVR-MVS		97.30 10	97.41 11	97.18 8	99.02 10	98.60 21	98.15 16	96.24 13	96.12 17	94.10 11	95.54 25	97.99 12	96.99 7	97.97 3	97.17 9	98.57 24	98.50 31

MSP-MVS		97.70 6	98.09 5	97.24 6	99.00 11	99.17 5	98.76 5	96.41 9	96.91 5	93.88 14	97.72 5	99.04 7	96.93 11	97.29 17	97.31 6	98.45 37	99.23 4
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
ACMMPR		96.92 17	96.96 19	96.87 15	98.99 12	98.78 11	98.38 10	95.52 24	96.57 10	92.81 24	96.06 20	95.90 36	97.07 5	96.60 37	96.34 35	98.46 34	98.42 35

HFP-MVS		97.11 14	97.19 16	97.00 12	98.97 13	98.73 12	98.37 11	95.69 21	96.60 9	93.28 20	96.87 8	96.64 29	97.27 2	96.64 35	96.33 36	98.44 38	98.56 24

SteuartSystems-ACMMP		97.10 15	97.49 10	96.65 18	98.97 13	98.95 9	98.43 9	95.96 17	95.12 28	91.46 28	96.85 9	97.60 18	96.37 24	97.76 6	97.16 10	98.68 18	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		97.20 12	97.29 14	97.10 9	98.95 15	98.51 29	97.51 29	96.48 7	96.17 16	94.64 6	97.32 6	97.57 19	96.23 26	96.78 29	96.15 43	98.79 14	98.55 29

SED-MVS		97.98 2	98.36 2	97.54 4	98.94 16	99.29 2	98.81 4	96.64 3	97.14 3	95.16 4	97.96 2	99.61 2	96.92 12	98.00 1	97.24 8	98.75 17	99.25 3

X-MVS		96.07 26	96.33 28	95.77 29	98.94 16	98.66 14	97.94 23	95.41 30	95.12 28	88.03 54	93.00 33	96.06 32	95.85 29	96.65 34	96.35 32	98.47 32	98.48 32

SR-MVS					98.93 18			96.00 16				97.75 15

MP-MVS		96.56 21	96.72 23	96.37 24	98.93 18	98.48 30	98.04 20	95.55 23	94.32 40	90.95 34	95.88 22	97.02 26	96.29 25	96.77 30	96.01 49	98.47 32	98.56 24
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		96.83 18	97.06 17	96.57 19	98.88 20	98.47 32	98.02 21	96.16 14	95.58 23	90.96 32	95.78 23	97.84 14	96.46 22	97.00 25	96.17 41	98.94 7	98.55 29

CP-MVS		96.68 20	96.59 26	96.77 17	98.85 21	98.58 22	98.18 15	95.51 26	95.34 25	92.94 23	95.21 28	96.25 31	96.79 15	96.44 42	95.77 51	98.35 46	98.56 24

DPE-MVS		97.83 4	98.13 4	97.48 5	98.83 22	99.19 4	98.99 1	96.70 1	96.05 18	94.39 9	98.30 1	99.47 4	97.02 6	97.75 7	97.02 14	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
mPP-MVS					98.76 23							95.49 39

CSCG		95.68 30	95.46 35	95.93 27	98.71 24	99.07 7	97.13 35	93.55 37	95.48 24	93.35 19	90.61 45	93.82 46	95.16 37	94.60 82	95.57 55	97.70 108	99.08 10

DeepC-MVS_fast	93.32 1	96.48 22	96.42 27	96.56 20	98.70 25	98.31 38	97.97 22	95.76 20	96.31 14	92.01 27	91.43 40	95.42 40	96.46 22	97.65 11	97.69 1	98.49 31	98.12 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		95.02 37	93.71 50	96.54 22	98.51 26	97.76 59	96.69 40	95.94 19	93.72 48	93.50 16	89.01 53	90.53 66	96.49 21	94.51 85	93.76 85	98.07 79	96.69 98

train_agg		96.15 25	96.64 25	95.58 33	98.44 27	98.03 48	98.14 18	95.40 31	93.90 46	87.72 59	96.26 17	98.10 10	95.75 31	96.25 47	95.45 57	98.01 86	98.47 33

CDPH-MVS		94.80 41	95.50 33	93.98 46	98.34 28	98.06 47	97.41 30	93.23 39	92.81 54	82.98 100	92.51 34	94.82 42	93.53 60	96.08 50	96.30 38	98.42 40	97.94 56

TPM-MVS					98.33 29	97.85 54	97.06 36			89.97 40	93.26 31	97.16 25	93.12 66			97.79 98	95.95 126
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
MSLP-MVS++		96.05 27	95.63 31	96.55 21	98.33 29	98.17 44	96.94 37	94.61 34	94.70 38	94.37 10	89.20 52	95.96 35	96.81 13	95.57 58	97.33 5	98.24 63	98.47 33

ACMMP		95.54 31	95.49 34	95.61 32	98.27 31	98.53 26	97.16 34	94.86 32	94.88 34	89.34 43	95.36 27	91.74 55	95.50 35	95.51 59	94.16 76	98.50 29	98.22 42
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
3Dnovator+	90.56 5	95.06 36	94.56 45	95.65 31	98.11 32	98.15 45	97.19 33	91.59 51	95.11 30	93.23 22	81.99 103	94.71 43	95.43 36	96.48 39	96.88 18	98.35 46	98.63 19

3Dnovator	90.28 7	94.70 42	94.34 48	95.11 35	98.06 33	98.21 42	96.89 38	91.03 57	94.72 37	91.45 29	82.87 94	93.10 50	94.61 42	96.24 48	97.08 13	98.63 21	98.16 45

PLC	90.69 4	94.32 46	92.99 58	95.87 28	97.91 34	96.49 94	95.95 51	94.12 35	94.94 32	94.09 12	85.90 72	90.77 63	95.58 33	94.52 84	93.32 99	97.55 117	95.00 148
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPNet		93.92 50	94.40 46	93.36 54	97.89 35	96.55 92	96.08 47	92.14 45	91.65 66	89.16 45	94.07 30	90.17 70	87.78 126	95.24 64	94.97 65	97.09 136	98.15 46
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		95.54 31	95.07 37	96.10 25	97.88 36	97.98 50	97.92 24	94.86 32	94.56 39	92.16 26	91.01 41	95.71 37	96.97 10	94.56 83	93.50 92	96.81 157	98.14 47

QAPM		94.13 49	94.33 49	93.90 47	97.82 37	98.37 37	96.47 42	90.89 58	92.73 57	85.63 82	85.35 76	93.87 45	94.17 49	95.71 57	95.90 50	98.40 42	98.42 35

DeepC-MVS	92.10 3	95.22 34	94.77 41	95.75 30	97.77 38	98.54 25	97.63 28	95.96 17	95.07 31	88.85 48	85.35 76	91.85 54	95.82 30	96.88 28	97.10 12	98.44 38	98.63 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OpenMVS	88.18 11	92.51 63	91.61 80	93.55 53	97.74 39	98.02 49	95.66 53	90.46 61	89.14 103	86.50 70	75.80 137	90.38 69	92.69 71	94.99 67	95.30 59	98.27 58	97.63 67

TSAR-MVS + ACMM		96.19 23	97.39 13	94.78 37	97.70 40	98.41 35	97.72 27	95.49 27	96.47 11	86.66 69	96.35 15	97.85 13	93.99 52	97.19 20	96.37 31	97.12 134	99.13 7

MAR-MVS		92.71 62	92.63 63	92.79 67	97.70 40	97.15 78	93.75 91	87.98 97	90.71 72	85.76 80	86.28 69	86.38 79	94.35 47	94.95 68	95.49 56	97.22 127	97.44 75
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
PHI-MVS		95.86 28	96.93 22	94.61 40	97.60 42	98.65 18	96.49 41	93.13 40	94.07 43	87.91 58	97.12 7	97.17 24	93.90 55	96.46 40	96.93 17	98.64 20	98.10 51

DPM-MVS		95.07 35	94.84 40	95.34 34	97.44 43	97.49 68	97.76 26	95.52 24	94.88 34	88.92 47	87.25 61	96.44 30	94.41 44	95.78 55	96.11 45	97.99 88	95.95 126

SD-MVS		97.35 8	97.73 8	96.90 14	97.35 44	98.66 14	97.85 25	96.25 11	96.86 6	94.54 8	96.75 11	99.13 6	96.99 7	96.94 26	96.58 23	98.39 44	99.20 5
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
MVS_111021_HR		94.84 39	95.91 30	93.60 52	97.35 44	98.46 33	95.08 62	91.19 54	94.18 42	85.97 74	95.38 26	92.56 52	93.61 59	96.61 36	96.25 39	98.40 42	97.92 58

TSAR-MVS + MP.		97.31 9	97.64 9	96.92 13	97.28 46	98.56 23	98.61 7	95.48 28	96.72 8	94.03 13	96.73 12	98.29 9	97.15 4	97.61 12	96.42 26	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CANet		94.85 38	94.92 39	94.78 37	97.25 47	98.52 28	97.20 32	91.81 48	93.25 51	91.06 31	86.29 68	94.46 44	92.99 67	97.02 24	96.68 20	98.34 48	98.20 43

OMC-MVS		94.49 45	94.36 47	94.64 39	97.17 48	97.73 61	95.49 55	92.25 44	96.18 15	90.34 38	88.51 55	92.88 51	94.90 41	94.92 70	94.17 75	97.69 110	96.15 118

MVS_111021_LR		94.84 39	95.57 32	94.00 44	97.11 49	97.72 63	94.88 66	91.16 55	95.24 27	88.74 49	96.03 21	91.52 59	94.33 48	95.96 52	95.01 64	97.79 98	97.49 74

CNLPA		93.69 53	92.50 65	95.06 36	97.11 49	97.36 70	93.88 88	93.30 38	95.64 22	93.44 18	80.32 112	90.73 64	94.99 40	93.58 103	93.33 97	97.67 112	96.57 103

LS3D		91.97 69	90.98 89	93.12 60	97.03 51	97.09 81	95.33 60	95.59 22	92.47 58	79.26 120	81.60 106	82.77 100	94.39 46	94.28 87	94.23 74	97.14 133	94.45 154

TAPA-MVS	90.35 6	93.69 53	93.52 51	93.90 47	96.89 52	97.62 65	96.15 45	91.67 50	94.94 32	85.97 74	87.72 60	91.96 53	94.40 45	93.76 101	93.06 109	98.30 54	95.58 136
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DELS-MVS		93.71 52	93.47 52	94.00 44	96.82 53	98.39 36	96.80 39	91.07 56	89.51 100	89.94 41	83.80 86	89.29 72	90.95 90	97.32 14	97.65 2	98.42 40	98.32 38
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
EPNet_dtu		88.32 119	90.61 91	85.64 148	96.79 54	92.27 177	92.03 124	90.31 62	89.05 104	65.44 192	89.43 50	85.90 84	74.22 201	92.76 117	92.09 127	95.02 190	92.76 174
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSDG		90.42 96	88.25 116	92.94 65	96.67 55	94.41 121	93.96 83	92.91 41	89.59 98	86.26 72	76.74 130	80.92 117	90.43 98	92.60 122	92.08 128	97.44 122	91.41 180

CS-MVS-test		94.63 43	95.28 36	93.88 49	96.56 56	98.67 13	93.41 100	89.31 80	94.27 41	89.64 42	90.84 43	91.64 57	95.58 33	97.04 23	96.17 41	98.77 15	98.32 38

DeepPCF-MVS	92.65 2	95.50 33	96.96 19	93.79 51	96.44 57	98.21 42	93.51 98	94.08 36	96.94 4	89.29 44	93.08 32	96.77 28	93.82 56	97.68 9	97.40 4	95.59 180	98.65 18

PCF-MVS	90.19 8	92.98 57	92.07 73	94.04 43	96.39 58	97.87 51	96.03 48	95.47 29	87.16 118	85.09 93	84.81 80	93.21 49	93.46 62	91.98 135	91.98 131	97.78 100	97.51 73
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS_0304		94.30 47	94.68 43	93.86 50	96.33 59	98.48 30	97.41 30	91.20 53	92.75 55	86.96 66	86.03 71	93.81 47	92.64 72	96.89 27	96.54 25	98.61 22	98.24 41

CS-MVS		94.53 44	94.73 42	94.31 42	96.30 60	98.53 26	94.98 63	89.24 82	93.37 50	90.24 39	88.96 54	89.76 71	96.09 28	97.48 13	96.42 26	98.99 2	98.59 23

OPM-MVS		91.08 82	89.34 102	93.11 61	96.18 61	96.13 103	96.39 43	92.39 43	82.97 157	81.74 103	82.55 100	80.20 120	93.97 54	94.62 80	93.23 100	98.00 87	95.73 132
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PVSNet_BlendedMVS		92.80 58	92.44 67	93.23 55	96.02 62	97.83 56	93.74 92	90.58 59	91.86 63	90.69 35	85.87 74	82.04 110	90.01 100	96.39 43	95.26 60	98.34 48	97.81 63

PVSNet_Blended		92.80 58	92.44 67	93.23 55	96.02 62	97.83 56	93.74 92	90.58 59	91.86 63	90.69 35	85.87 74	82.04 110	90.01 100	96.39 43	95.26 60	98.34 48	97.81 63

XVS					95.68 64	98.66 14	94.96 64			88.03 54		96.06 32				98.46 34

X-MVStestdata					95.68 64	98.66 14	94.96 64			88.03 54		96.06 32				98.46 34

HQP-MVS		92.39 65	92.49 66	92.29 75	95.65 66	95.94 106	95.64 54	92.12 46	92.46 59	79.65 118	91.97 37	82.68 101	92.92 70	93.47 108	92.77 114	97.74 104	98.12 49

HyFIR lowres test		87.87 121	86.42 138	89.57 106	95.56 67	96.99 84	92.37 114	84.15 140	86.64 123	77.17 127	57.65 208	83.97 91	91.08 88	92.09 133	92.44 119	97.09 136	95.16 145

ACMM	88.76 10	91.70 77	90.43 92	93.19 57	95.56 67	95.14 112	93.35 102	91.48 52	92.26 60	87.12 64	84.02 84	79.34 123	93.99 52	94.07 93	92.68 115	97.62 116	95.50 137
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
COLMAP_ROB	84.39 15	87.61 123	86.03 143	89.46 107	95.54 69	94.48 118	91.77 128	90.14 66	87.16 118	75.50 132	73.41 152	76.86 142	87.33 133	90.05 167	89.76 177	96.48 161	90.46 189
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
LGP-MVS_train		91.83 73	92.04 74	91.58 82	95.46 70	96.18 102	95.97 50	89.85 68	90.45 79	77.76 123	91.92 38	80.07 121	92.34 76	94.27 88	93.47 93	98.11 76	97.90 61

CHOSEN 1792x2688		88.57 116	87.82 123	89.44 108	95.46 70	96.89 87	93.74 92	85.87 122	89.63 97	77.42 126	61.38 202	83.31 95	88.80 121	93.44 109	93.16 105	95.37 185	96.95 92

PVSNet_Blended_VisFu		91.92 71	92.39 69	91.36 90	95.45 72	97.85 54	92.25 117	89.54 76	88.53 110	87.47 61	79.82 114	90.53 66	85.47 152	96.31 46	95.16 63	97.99 88	98.56 24

PatchMatch-RL		90.30 97	88.93 109	91.89 78	95.41 73	95.68 108	90.94 130	88.67 88	89.80 95	86.95 67	85.90 72	72.51 151	92.46 73	93.56 105	92.18 124	96.93 149	92.89 173

TSAR-MVS + COLMAP		92.39 65	92.31 70	92.47 71	95.35 74	96.46 96	96.13 46	92.04 47	95.33 26	80.11 116	94.95 29	77.35 139	94.05 51	94.49 86	93.08 107	97.15 131	94.53 152

test2506		90.93 86	89.20 105	92.95 64	94.97 75	98.30 39	94.53 68	90.25 64	89.91 92	88.39 53	83.23 90	64.17 194	90.69 93	96.75 32	96.10 46	98.87 8	95.97 125

ECVR-MVS		90.77 90	89.27 103	92.52 69	94.97 75	98.30 39	94.53 68	90.25 64	89.91 92	85.80 79	73.64 147	74.31 148	90.69 93	96.75 32	96.10 46	98.87 8	95.91 129

test1111		90.47 95	89.10 107	92.07 77	94.92 77	98.30 39	94.17 81	90.30 63	89.56 99	83.92 96	73.25 154	73.66 149	90.26 99	96.77 30	96.14 44	98.87 8	96.04 122

ACMP	89.13 9	92.03 68	91.70 79	92.41 73	94.92 77	96.44 98	93.95 84	89.96 67	91.81 65	85.48 87	90.97 42	79.12 124	92.42 74	93.28 114	92.55 118	97.76 102	97.74 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UA-Net		90.81 87	92.58 64	88.74 115	94.87 79	97.44 69	92.61 111	88.22 93	82.35 161	78.93 121	85.20 78	95.61 38	79.56 187	96.52 38	96.57 24	98.23 64	94.37 155

IB-MVS	85.10 14	87.98 120	87.97 121	87.99 124	94.55 80	96.86 88	84.52 196	88.21 94	86.48 128	88.54 52	74.41 145	77.74 136	74.10 203	89.65 173	92.85 113	98.06 81	97.80 65
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
CANet_DTU		90.74 92	92.93 61	88.19 121	94.36 81	96.61 90	94.34 74	84.66 133	90.66 73	68.75 171	90.41 46	86.89 77	89.78 102	95.46 60	94.87 66	97.25 126	95.62 134

sasdasda		93.08 55	93.09 55	93.07 62	94.24 82	97.86 52	95.45 57	87.86 103	94.00 44	87.47 61	88.32 56	82.37 105	95.13 38	93.96 98	96.41 29	98.27 58	98.73 13

canonicalmvs		93.08 55	93.09 55	93.07 62	94.24 82	97.86 52	95.45 57	87.86 103	94.00 44	87.47 61	88.32 56	82.37 105	95.13 38	93.96 98	96.41 29	98.27 58	98.73 13

MGCFI-Net		92.75 60	92.98 59	92.48 70	94.18 84	97.77 58	95.28 61	87.77 105	93.88 47	85.28 91	88.19 58	82.17 109	94.14 50	93.86 100	96.32 37	98.20 67	98.69 16

UGNet		91.52 78	93.41 53	89.32 109	94.13 85	97.15 78	91.83 127	89.01 83	90.62 75	85.86 78	86.83 62	91.73 56	77.40 192	94.68 79	94.43 71	97.71 106	98.40 37
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
thres600view7		89.28 113	87.47 132	91.39 87	94.12 86	97.25 73	93.94 86	89.74 71	85.62 135	80.63 114	75.24 141	69.33 166	91.66 83	94.92 70	93.23 100	98.27 58	96.72 97

IS_MVSNet		91.87 72	93.35 54	90.14 103	94.09 87	97.73 61	93.09 105	88.12 95	88.71 107	79.98 117	84.49 81	90.63 65	87.49 131	97.07 21	96.96 16	98.07 79	97.88 62

TSAR-MVS + GP.		95.86 28	96.95 21	94.60 41	94.07 88	98.11 46	96.30 44	91.76 49	95.67 20	91.07 30	96.82 10	97.69 17	95.71 32	95.96 52	95.75 52	98.68 18	98.63 19

thres400		89.40 109	87.58 129	91.53 84	94.06 89	97.21 76	94.19 80	89.83 69	85.69 132	81.08 110	75.50 139	69.76 164	91.80 79	94.79 77	93.51 89	98.20 67	96.60 101

ETV-MVS		93.80 51	94.57 44	92.91 66	93.98 90	97.50 67	93.62 95	88.70 87	91.95 62	87.57 60	90.21 47	90.79 62	94.56 43	97.20 19	96.35 32	99.02 1	97.98 53

ACMH	85.51 13	87.31 126	86.59 136	88.14 122	93.96 91	94.51 117	89.00 166	87.99 96	81.58 164	70.15 161	78.41 121	71.78 156	90.60 96	91.30 144	91.99 130	97.17 130	96.58 102
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MS-PatchMatch		87.63 122	87.61 127	87.65 129	93.95 92	94.09 127	92.60 112	81.52 173	86.64 123	76.41 130	73.46 151	85.94 83	85.01 156	92.23 131	90.00 171	96.43 164	90.93 186

thres200		89.49 108	87.72 124	91.55 83	93.95 92	97.25 73	94.34 74	89.74 71	85.66 133	81.18 107	76.12 136	70.19 163	91.80 79	94.92 70	93.51 89	98.27 58	96.40 108

CLD-MVS		92.50 64	91.96 75	93.13 59	93.93 94	96.24 100	95.69 52	88.77 86	92.92 52	89.01 46	88.19 58	81.74 113	93.13 65	93.63 102	93.08 107	98.23 64	97.91 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
thres100view900		89.36 110	87.61 127	91.39 87	93.90 95	96.86 88	94.35 73	89.66 75	85.87 130	81.15 108	76.46 132	70.38 160	91.17 86	94.09 92	93.43 95	98.13 73	96.16 117

tfpn200view9		89.55 107	87.86 122	91.53 84	93.90 95	97.26 72	94.31 76	89.74 71	85.87 130	81.15 108	76.46 132	70.38 160	91.76 81	94.92 70	93.51 89	98.28 57	96.61 100

EIA-MVS		92.72 61	92.96 60	92.44 72	93.86 97	97.76 59	93.13 104	88.65 89	89.78 96	86.68 68	86.69 65	87.57 73	93.74 57	96.07 51	95.32 58	98.58 23	97.53 72

CHOSEN 280x420		90.77 90	92.14 72	89.17 111	93.86 97	92.81 165	93.16 103	80.22 181	90.21 84	84.67 95	89.89 49	91.38 60	90.57 97	94.94 69	92.11 126	92.52 201	93.65 165

FC-MVSNet-train		90.55 93	90.19 95	90.97 93	93.78 99	95.16 111	92.11 122	88.85 84	87.64 115	83.38 99	84.36 83	78.41 130	89.53 104	94.69 78	93.15 106	98.15 71	97.92 58

FA-MVS(training)		90.79 89	91.33 83	90.17 101	93.76 100	97.22 75	92.74 109	77.79 191	90.60 77	88.03 54	78.80 118	87.41 74	91.00 89	95.40 62	93.43 95	97.70 108	96.46 105

Vis-MVSNet (Re-imp)		90.54 94	92.76 62	87.94 125	93.73 101	96.94 86	92.17 120	87.91 98	88.77 106	76.12 131	83.68 87	90.80 61	79.49 188	96.34 45	96.35 32	98.21 66	96.46 105

baseline1		90.81 87	90.29 93	91.42 86	93.67 102	95.86 107	93.94 86	89.69 74	89.29 102	82.85 101	82.91 93	80.30 119	89.60 103	95.05 66	94.79 68	98.80 12	93.82 163

EPP-MVSNet		92.13 67	93.06 57	91.05 92	93.66 103	97.30 71	92.18 118	87.90 99	90.24 83	83.63 97	86.14 70	90.52 68	90.76 92	94.82 75	94.38 72	98.18 70	97.98 53

EC-MVSNet		94.19 48	95.05 38	93.18 58	93.56 104	97.65 64	95.34 59	86.37 118	92.05 61	88.71 50	89.91 48	93.32 48	96.14 27	97.29 17	96.42 26	98.98 3	98.70 15

ACMH+	85.75 12	87.19 128	86.02 144	88.56 117	93.42 105	94.41 121	89.91 150	87.66 109	83.45 154	72.25 148	76.42 134	71.99 155	90.78 91	89.86 168	90.94 145	97.32 123	95.11 147

casdiffmvs_mvg		91.94 70	91.25 85	92.75 68	93.41 106	97.19 77	95.48 56	89.77 70	89.86 94	86.41 71	81.02 110	82.23 108	92.93 68	95.44 61	95.61 54	98.51 26	97.40 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		91.81 74	92.19 71	91.37 89	93.24 107	96.95 85	94.43 70	86.25 119	91.45 69	83.45 98	86.31 67	85.15 87	92.93 68	93.99 94	94.71 69	97.92 92	96.77 96

MVSTER		91.73 75	91.61 80	91.86 79	93.18 108	94.56 115	94.37 72	87.90 99	90.16 87	88.69 51	89.23 51	81.28 115	88.92 119	95.75 56	93.95 82	98.12 74	96.37 109

Anonymous202405211			88.00 119		93.16 109	96.38 99	93.58 96	89.34 79	87.92 114		65.04 191	83.03 97	92.07 77	92.67 119	93.33 97	96.96 144	97.63 67

casdiffmvs		91.72 76	91.16 87	92.38 74	93.16 109	97.15 78	93.95 84	89.49 77	91.58 68	86.03 73	80.75 111	80.95 116	93.16 64	95.25 63	95.22 62	98.50 29	97.23 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
tttt0517		91.01 85	91.71 78	90.19 100	92.98 111	97.07 82	91.96 126	87.63 110	90.61 76	81.42 105	86.76 64	82.26 107	89.23 111	94.86 74	93.03 111	97.90 93	97.36 78

Effi-MVS+		89.79 104	89.83 100	89.74 105	92.98 111	96.45 97	93.48 99	84.24 138	87.62 116	76.45 129	81.76 104	77.56 138	93.48 61	94.61 81	93.59 88	97.82 97	97.22 85

RPSCF		89.68 105	89.24 104	90.20 99	92.97 113	92.93 161	92.30 115	87.69 107	90.44 80	85.12 92	91.68 39	85.84 85	90.69 93	87.34 190	86.07 192	92.46 202	90.37 190

TDRefinement		84.97 154	83.39 169	86.81 137	92.97 113	94.12 126	92.18 118	87.77 105	82.78 158	71.31 153	68.43 172	68.07 172	81.10 183	89.70 172	89.03 184	95.55 182	91.62 178

thisisatest0530		91.04 84	91.74 77	90.21 98	92.93 115	97.00 83	92.06 123	87.63 110	90.74 71	81.51 104	86.81 63	82.48 102	89.23 111	94.81 76	93.03 111	97.90 93	97.33 80

DCV-MVSNet		91.24 80	91.26 84	91.22 91	92.84 116	93.44 143	93.82 89	86.75 115	91.33 70	85.61 83	84.00 85	85.46 86	91.27 84	92.91 116	93.62 87	97.02 140	98.05 52

baseline		91.19 81	91.89 76	90.38 94	92.76 117	95.04 113	93.55 97	84.54 136	92.92 52	85.71 81	86.68 66	86.96 76	89.28 110	92.00 134	92.62 117	96.46 162	96.99 90

EPMVS		85.77 142	86.24 140	85.23 153	92.76 117	93.78 133	89.91 150	73.60 204	90.19 85	74.22 136	82.18 102	78.06 132	87.55 130	85.61 199	85.38 197	93.32 195	88.48 202

GeoE		89.29 112	88.68 111	89.99 104	92.75 119	96.03 105	93.07 107	83.79 145	86.98 120	81.34 106	74.72 142	78.92 125	91.22 85	93.31 112	93.21 103	97.78 100	97.60 71

diffmvs		91.37 79	91.09 88	91.70 81	92.71 120	96.47 95	94.03 82	88.78 85	92.74 56	85.43 89	83.63 88	80.37 118	91.76 81	93.39 110	93.78 84	97.50 119	97.23 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
DI_MVS_plusplus_trai		91.05 83	90.15 96	92.11 76	92.67 121	96.61 90	96.03 48	88.44 91	90.25 82	85.92 76	73.73 146	84.89 89	91.92 78	94.17 91	94.07 80	97.68 111	97.31 81

Anonymous20231211		89.82 103	88.18 117	91.74 80	92.52 122	96.09 104	93.38 101	89.30 81	88.95 105	85.90 77	64.55 196	84.39 90	92.41 75	92.24 130	93.06 109	96.93 149	97.95 55

tpmrst		83.72 172	83.45 166	84.03 169	92.21 123	91.66 189	88.74 169	73.58 205	88.14 112	72.67 145	77.37 126	72.11 154	86.34 142	82.94 207	82.05 206	90.63 211	89.86 194

CostFormer		86.78 131	86.05 142	87.62 131	92.15 124	93.20 152	91.55 129	75.83 196	88.11 113	85.29 90	81.76 104	76.22 144	87.80 125	84.45 202	85.21 198	93.12 196	93.42 168

Vis-MVSNet		89.36 110	91.49 82	86.88 136	92.10 125	97.60 66	92.16 121	85.89 121	84.21 146	75.20 133	82.58 98	87.13 75	77.40 192	95.90 54	95.63 53	98.51 26	97.36 78
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IterMVS-LS		88.60 115	88.45 112	88.78 114	92.02 126	92.44 175	92.00 125	83.57 149	86.52 126	78.90 122	78.61 120	81.34 114	89.12 114	90.68 156	93.18 104	97.10 135	96.35 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchmatchNet		85.70 143	86.65 135	84.60 160	91.79 127	93.40 144	89.27 159	73.62 203	90.19 85	72.63 146	82.74 97	81.93 112	87.64 128	84.99 200	84.29 202	92.64 200	89.00 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm cat1		84.13 165	81.99 185	86.63 140	91.74 128	91.50 192	90.68 132	75.69 197	86.12 129	85.44 88	72.39 157	70.72 158	85.16 154	80.89 211	81.56 207	91.07 209	90.71 187

USDC		86.73 132	85.96 146	87.63 130	91.64 129	93.97 129	92.76 108	84.58 135	88.19 111	70.67 158	80.10 113	67.86 173	89.43 105	91.81 136	89.77 176	96.69 159	90.05 193

SCA		86.25 134	87.52 130	84.77 157	91.59 130	93.90 130	89.11 163	73.25 208	90.38 81	72.84 144	83.26 89	83.79 93	88.49 123	86.07 197	85.56 195	93.33 194	89.67 195

gg-mvs-nofinetune		81.83 191	83.58 164	79.80 198	91.57 131	96.54 93	93.79 90	68.80 215	62.71 219	43.01 224	55.28 211	85.06 88	83.65 166	96.13 49	94.86 67	97.98 91	94.46 153

Fast-Effi-MVS+		88.56 117	87.99 120	89.22 110	91.56 132	95.21 110	92.29 116	82.69 156	86.82 121	77.73 124	76.24 135	73.39 150	93.36 63	94.22 90	93.64 86	97.65 113	96.43 107

CMPMVS	61.19 17	79.86 198	77.46 206	82.66 187	91.54 133	91.82 187	83.25 199	81.57 172	70.51 211	68.64 172	59.89 207	66.77 179	79.63 186	84.00 205	84.30 201	91.34 207	84.89 210
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ADS-MVSNet		84.08 166	84.95 154	83.05 182	91.53 134	91.75 188	88.16 173	70.70 212	89.96 91	69.51 166	78.83 117	76.97 141	86.29 143	84.08 204	84.60 200	92.13 205	88.48 202

test-LLR		86.88 129	88.28 114	85.24 152	91.22 135	92.07 181	87.41 179	83.62 147	84.58 139	69.33 167	83.00 91	82.79 98	84.24 160	92.26 128	89.81 174	95.64 178	93.44 166

test0.0.03 1		85.58 145	87.69 126	83.11 179	91.22 135	92.54 172	85.60 195	83.62 147	85.66 133	67.84 178	82.79 96	79.70 122	73.51 205	91.15 148	90.79 147	96.88 153	91.23 183

baseline2		88.97 114	89.50 101	88.36 118	91.14 137	95.30 109	90.13 144	85.17 130	87.24 117	80.80 112	84.46 82	78.44 129	85.60 149	93.54 106	91.87 132	97.31 124	95.66 133

Effi-MVS+-dtu		87.51 124	88.13 118	86.77 138	91.10 138	94.90 114	90.91 131	82.67 157	83.47 153	71.55 150	81.11 109	77.04 140	89.41 106	92.65 121	91.68 138	95.00 191	96.09 120

RPMNet		84.82 156	85.90 147	83.56 174	91.10 138	92.10 179	88.73 170	71.11 211	84.75 137	68.79 170	73.56 148	77.62 137	85.33 153	90.08 166	89.43 180	96.32 165	93.77 164

CR-MVSNet		85.48 147	86.29 139	84.53 162	91.08 140	92.10 179	89.18 161	73.30 206	84.75 137	71.08 155	73.12 156	77.91 134	86.27 144	91.48 140	90.75 150	96.27 166	93.94 160

TinyColmap		84.04 167	82.01 184	86.42 142	90.87 141	91.84 186	88.89 168	84.07 142	82.11 163	69.89 163	71.08 161	60.81 207	89.04 115	90.52 158	89.19 182	95.76 172	88.50 201

tpm		83.16 178	83.64 163	82.60 188	90.75 142	91.05 195	88.49 171	73.99 201	82.36 160	67.08 184	78.10 122	68.79 167	84.17 162	85.95 198	85.96 193	91.09 208	93.23 170

dps		85.00 153	83.21 173	87.08 134	90.73 143	92.55 171	89.34 158	75.29 198	84.94 136	87.01 65	79.27 116	67.69 174	87.27 134	84.22 203	83.56 203	92.83 199	90.25 191

MDTV_nov1_ep13		86.64 133	87.50 131	85.65 147	90.73 143	93.69 137	89.96 148	78.03 190	89.48 101	76.85 128	84.92 79	82.42 104	86.14 146	86.85 194	86.15 191	92.17 203	88.97 198

CDS-MVSNet		88.34 118	88.71 110	87.90 126	90.70 145	94.54 116	92.38 113	86.02 120	80.37 170	79.42 119	79.30 115	83.43 94	82.04 175	93.39 110	94.01 81	96.86 155	95.93 128
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IterMVS-SCA-FT		85.44 149	86.71 134	83.97 170	90.59 146	90.84 198	89.73 154	78.34 187	84.07 150	66.40 187	77.27 128	78.66 127	83.06 168	91.20 145	90.10 169	95.72 175	94.78 149

IterMVS		85.25 151	86.49 137	83.80 171	90.42 147	90.77 201	90.02 146	78.04 189	84.10 148	66.27 188	77.28 127	78.41 130	83.01 169	90.88 150	89.72 178	95.04 189	94.24 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+-dtu		86.25 134	87.70 125	84.56 161	90.37 148	93.70 136	90.54 134	78.14 188	83.50 152	65.37 193	81.59 107	75.83 146	86.09 148	91.70 138	91.70 136	96.88 153	95.84 130

dmvs_re		87.31 126	86.10 141	88.74 115	89.84 149	94.28 124	92.66 110	89.41 78	82.61 159	74.69 134	74.69 143	69.47 165	87.78 126	92.38 126	93.23 100	98.03 83	96.02 124

FC-MVSNet-test		86.15 137	89.10 107	82.71 186	89.83 150	93.18 153	87.88 176	84.69 132	86.54 125	62.18 202	82.39 101	83.31 95	74.18 202	92.52 124	91.86 133	97.50 119	93.88 162

GA-MVS		85.08 152	85.65 150	84.42 163	89.77 151	94.25 125	89.26 160	84.62 134	81.19 167	62.25 201	75.72 138	68.44 170	84.14 163	93.57 104	91.68 138	96.49 160	94.71 151

PMMVS		89.88 102	91.19 86	88.35 119	89.73 152	91.97 185	90.62 133	81.92 168	90.57 78	80.58 115	92.16 35	86.85 78	91.17 86	92.31 127	91.35 142	96.11 168	93.11 172

tfpnnormal		83.80 171	81.26 193	86.77 138	89.60 153	93.26 151	89.72 155	87.60 112	72.78 204	70.44 159	60.53 205	61.15 206	85.55 150	92.72 118	91.44 140	97.71 106	96.92 93

CVMVSNet		83.83 170	85.53 151	81.85 193	89.60 153	90.92 196	87.81 177	83.21 153	80.11 173	60.16 206	76.47 131	78.57 128	76.79 194	89.76 169	90.13 164	93.51 193	92.75 175

testgi		81.94 190	84.09 161	79.43 199	89.53 155	90.83 199	82.49 202	81.75 171	80.59 168	59.46 208	82.82 95	65.75 183	67.97 207	90.10 165	89.52 179	95.39 184	89.03 196

UniMVSNet_ETH3D		84.57 157	81.40 191	88.28 120	89.34 156	94.38 123	90.33 136	86.50 117	74.74 202	77.52 125	59.90 206	62.04 202	88.78 122	88.82 183	92.65 116	97.22 127	97.24 82

LTVRE_ROB	81.71 16	82.44 188	81.84 186	83.13 178	89.01 157	92.99 158	88.90 167	82.32 163	66.26 215	54.02 216	74.68 144	59.62 213	88.87 120	90.71 155	92.02 129	95.68 177	96.62 99
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
TAMVS		84.94 155	84.95 154	84.93 156	88.82 158	93.18 153	88.44 172	81.28 175	77.16 189	73.76 140	75.43 140	76.57 143	82.04 175	90.59 157	90.79 147	95.22 187	90.94 185

EG-PatchMatch MVS		81.70 193	81.31 192	82.15 191	88.75 159	93.81 132	87.14 182	78.89 186	71.57 207	64.12 198	61.20 204	68.46 169	76.73 196	91.48 140	90.77 149	97.28 125	91.90 177

TransMVSNet (Re)		82.67 185	80.93 196	84.69 159	88.71 160	91.50 192	87.90 175	87.15 113	71.54 209	68.24 175	63.69 198	64.67 193	78.51 191	91.65 139	90.73 152	97.64 114	92.73 176

FMVSNet3		90.19 100	90.06 99	90.34 95	88.69 161	93.85 131	94.58 67	85.78 123	90.03 88	85.56 84	77.38 123	86.13 80	89.22 113	93.29 113	94.36 73	98.20 67	95.40 142

GBi-Net		90.21 98	90.11 97	90.32 96	88.66 162	93.65 139	94.25 77	85.78 123	90.03 88	85.56 84	77.38 123	86.13 80	89.38 107	93.97 95	94.16 76	98.31 51	95.47 138

test1		90.21 98	90.11 97	90.32 96	88.66 162	93.65 139	94.25 77	85.78 123	90.03 88	85.56 84	77.38 123	86.13 80	89.38 107	93.97 95	94.16 76	98.31 51	95.47 138

FMVSNet2		89.61 106	89.14 106	90.16 102	88.66 162	93.65 139	94.25 77	85.44 127	88.57 109	84.96 94	73.53 149	83.82 92	89.38 107	94.23 89	94.68 70	98.31 51	95.47 138

PatchT		83.86 169	85.51 152	81.94 192	88.41 165	91.56 191	78.79 210	71.57 210	84.08 149	71.08 155	70.62 162	76.13 145	86.27 144	91.48 140	90.75 150	95.52 183	93.94 160

UniMVSNet (Re)		86.22 136	85.46 153	87.11 133	88.34 166	94.42 120	89.65 156	87.10 114	84.39 143	74.61 135	70.41 166	68.10 171	85.10 155	91.17 147	91.79 134	97.84 96	97.94 56

NR-MVSNet		85.46 148	84.54 158	86.52 141	88.33 167	93.78 133	90.45 135	87.87 101	84.40 141	71.61 149	70.59 163	62.09 201	82.79 171	91.75 137	91.75 135	98.10 77	97.44 75

UniMVSNet_NR-MVSNet		86.80 130	85.86 148	87.89 127	88.17 168	94.07 128	90.15 142	88.51 90	84.20 147	73.45 141	72.38 158	70.30 162	88.95 117	90.25 161	92.21 123	98.12 74	97.62 69

thisisatest0515		85.70 143	87.00 133	84.19 166	88.16 169	93.67 138	84.20 198	84.14 141	83.39 155	72.91 143	76.79 129	74.75 147	78.82 190	92.57 123	91.26 143	96.94 146	96.56 104

pm-mvs1		84.55 158	83.46 165	85.82 144	88.16 169	93.39 145	89.05 165	85.36 129	74.03 203	72.43 147	65.08 190	71.11 157	82.30 174	93.48 107	91.70 136	97.64 114	95.43 141

gm-plane-assit		77.65 203	78.50 201	76.66 203	87.96 171	85.43 214	64.70 220	74.50 199	64.15 217	51.26 219	61.32 203	58.17 215	84.11 164	95.16 65	93.83 83	97.45 121	91.41 180

test-mter		86.09 140	88.38 113	83.43 176	87.89 172	92.61 169	86.89 184	77.11 194	84.30 144	68.62 173	82.57 99	82.45 103	84.34 159	92.40 125	90.11 168	95.74 173	94.21 158

pmmvs4		86.00 141	84.28 160	88.00 123	87.80 173	92.01 184	89.94 149	84.91 131	86.79 122	80.98 111	73.41 152	66.34 182	88.12 124	89.31 176	88.90 185	96.24 167	93.20 171

TESTMET0.1,1		86.11 139	88.28 114	83.59 173	87.80 173	92.07 181	87.41 179	77.12 193	84.58 139	69.33 167	83.00 91	82.79 98	84.24 160	92.26 128	89.81 174	95.64 178	93.44 166

DU-MVS		86.12 138	84.81 156	87.66 128	87.77 175	93.78 133	90.15 142	87.87 101	84.40 141	73.45 141	70.59 163	64.82 191	88.95 117	90.14 162	92.33 120	97.76 102	97.62 69

Baseline_NR-MVSNet		85.28 150	83.42 168	87.46 132	87.77 175	90.80 200	89.90 152	87.69 107	83.93 151	74.16 137	64.72 194	66.43 181	87.48 132	90.14 162	90.83 146	97.73 105	97.11 88

SixPastTwentyTwo		83.12 180	83.44 167	82.74 185	87.71 177	93.11 157	82.30 203	82.33 162	79.24 178	64.33 196	78.77 119	62.75 197	84.11 164	88.11 185	87.89 187	95.70 176	94.21 158

TranMVSNet+NR-MVSNet		85.57 146	84.41 159	86.92 135	87.67 178	93.34 146	90.31 138	88.43 92	83.07 156	70.11 162	69.99 169	65.28 186	86.96 136	89.73 170	92.27 121	98.06 81	97.17 87

WR-MVS		83.14 179	83.38 170	82.87 184	87.55 179	93.29 148	86.36 189	84.21 139	80.05 174	66.41 186	66.91 178	66.92 178	75.66 199	88.96 181	90.56 155	97.05 138	96.96 91

v8		84.45 163	83.30 172	85.80 145	87.53 180	92.95 159	90.31 138	82.46 161	80.46 169	71.43 151	66.99 177	67.16 176	86.14 146	89.26 177	90.22 163	96.94 146	96.06 121

WR-MVS_H		82.86 184	82.66 178	83.10 180	87.44 181	93.33 147	85.71 194	83.20 154	77.36 188	68.20 176	66.37 181	65.23 187	76.05 198	89.35 174	90.13 164	97.99 88	96.89 94

v148		83.61 173	82.10 182	85.37 149	87.34 182	92.94 160	87.48 178	85.72 126	78.92 179	73.87 139	65.71 187	64.69 192	81.78 179	87.82 186	89.35 181	96.01 169	95.26 144

v10		84.18 164	83.17 174	85.37 149	87.34 182	92.68 167	90.32 137	81.33 174	79.93 177	69.23 169	66.33 182	65.74 184	87.03 135	90.84 151	90.38 158	96.97 142	96.29 114

v2v482		84.51 159	83.05 175	86.20 143	87.25 184	93.28 149	90.22 140	85.40 128	79.94 176	69.78 164	67.74 174	65.15 188	87.57 129	89.12 179	90.55 156	96.97 142	95.60 135

CP-MVSNet		83.11 181	82.15 181	84.23 165	87.20 185	92.70 166	86.42 188	83.53 150	77.83 186	67.67 179	66.89 180	60.53 209	82.47 172	89.23 178	90.65 154	98.08 78	97.20 86

v1144		84.03 168	82.88 176	85.37 149	87.17 186	93.15 156	90.18 141	83.31 152	78.83 180	67.85 177	65.99 184	64.99 189	86.79 138	90.75 153	90.33 160	96.90 151	96.15 118

V42		84.48 161	83.36 171	85.79 146	87.14 187	93.28 149	90.03 145	83.98 143	80.30 171	71.20 154	66.90 179	67.17 175	85.55 150	89.35 174	90.27 161	96.82 156	96.27 115

pmmvs5		83.37 176	82.68 177	84.18 167	87.13 188	93.18 153	86.74 185	82.08 166	76.48 193	67.28 182	71.26 160	62.70 198	84.71 157	90.77 152	90.12 167	97.15 131	94.24 156

FMVSNet1		87.33 125	86.00 145	88.89 112	87.13 188	92.83 164	93.08 106	84.46 137	81.35 166	82.20 102	66.33 182	77.96 133	88.96 116	93.97 95	94.16 76	97.54 118	95.38 143

PS-CasMVS		82.53 186	81.54 189	83.68 172	87.08 190	92.54 172	86.20 190	83.46 151	76.46 194	65.73 191	65.71 187	59.41 214	81.61 180	89.06 180	90.55 156	98.03 83	97.07 89

our_test_3					86.93 191	89.77 202	81.61 204

PEN-MVS		82.49 187	81.58 188	83.56 174	86.93 191	92.05 183	86.71 186	83.84 144	76.94 191	64.68 195	67.24 175	60.11 210	81.17 182	87.78 187	90.70 153	98.02 85	96.21 116

v1192		83.56 174	82.35 179	84.98 154	86.84 193	92.84 162	90.01 147	82.70 155	78.54 181	66.48 185	64.88 192	62.91 196	86.91 137	90.72 154	90.25 162	96.94 146	96.32 112

v144192		83.48 175	82.23 180	84.94 155	86.65 194	92.84 162	89.63 157	82.48 160	77.87 185	67.36 181	65.33 189	63.50 195	86.51 140	89.72 171	89.99 172	97.03 139	96.35 110

DTE-MVSNet		81.76 192	81.04 194	82.60 188	86.63 195	91.48 194	85.97 192	83.70 146	76.45 195	62.44 200	67.16 176	59.98 211	78.98 189	87.15 191	89.93 173	97.88 95	95.12 146

pmnet_mix02		80.14 197	80.21 198	80.06 196	86.61 196	89.66 203	80.40 207	82.20 165	82.29 162	61.35 203	71.52 159	66.67 180	76.75 195	82.55 208	80.18 211	93.05 197	88.62 199

v1921920		83.30 177	82.09 183	84.70 158	86.59 197	92.67 168	89.82 153	82.23 164	78.32 182	65.76 190	64.64 195	62.35 199	86.78 139	90.34 160	90.02 170	97.02 140	96.31 113

v1240		82.88 183	81.66 187	84.29 164	86.46 198	92.52 174	89.06 164	81.82 170	77.16 189	65.09 194	64.17 197	61.50 204	86.36 141	90.12 164	90.13 164	96.95 145	96.04 122

anonymousdsp		84.51 159	85.85 149	82.95 183	86.30 199	93.51 142	85.77 193	80.38 180	78.25 184	63.42 199	73.51 150	72.20 153	84.64 158	93.21 115	92.16 125	97.19 129	98.14 47

pmmvs6		80.90 194	78.77 200	83.38 177	85.84 200	91.61 190	86.01 191	82.54 159	64.17 216	70.43 160	54.14 215	67.06 177	80.73 184	90.50 159	89.17 183	94.74 192	94.75 150

MVS-HIRNet		78.16 201	77.57 205	78.83 200	85.83 201	87.76 208	76.67 211	70.22 213	75.82 199	67.39 180	55.61 210	70.52 159	81.96 177	86.67 195	85.06 199	90.93 210	81.58 213

test20.03		76.41 205	78.49 202	73.98 206	85.64 202	87.50 209	75.89 212	80.71 179	70.84 210	51.07 220	68.06 173	61.40 205	54.99 216	88.28 184	87.20 189	95.58 181	86.15 206

v7n		82.25 189	81.54 189	83.07 181	85.55 203	92.58 170	86.68 187	81.10 178	76.54 192	65.97 189	62.91 199	60.56 208	82.36 173	91.07 149	90.35 159	96.77 158	96.80 95

N_pmnet		77.55 204	76.68 207	78.56 201	85.43 204	87.30 211	78.84 209	81.88 169	78.30 183	60.61 204	61.46 201	62.15 200	74.03 204	82.04 209	80.69 210	90.59 212	84.81 211

Anonymous20231206		78.09 202	78.11 203	78.07 202	85.19 205	89.17 204	80.99 205	81.24 177	75.46 200	58.25 210	54.78 214	59.90 212	66.73 210	88.94 182	88.26 186	96.01 169	90.25 191

MDTV_nov1_ep13_2view		80.43 195	80.94 195	79.84 197	84.82 206	90.87 197	84.23 197	73.80 202	80.28 172	64.33 196	70.05 168	68.77 168	79.67 185	84.83 201	83.50 204	92.17 203	88.25 204

FPMVS		69.87 211	67.10 214	73.10 208	84.09 207	78.35 219	79.40 208	76.41 195	71.92 205	57.71 211	54.06 216	50.04 220	56.72 214	71.19 217	68.70 217	84.25 217	75.43 217

EU-MVSNet		78.43 200	80.25 197	76.30 204	83.81 208	87.27 212	80.99 205	79.52 183	76.01 196	54.12 215	70.44 165	64.87 190	67.40 209	86.23 196	85.54 196	91.95 206	91.41 180

FMVSNet5		84.47 162	84.72 157	84.18 167	83.30 209	88.43 206	88.09 174	79.42 184	84.25 145	74.14 138	73.15 155	78.74 126	83.65 166	91.19 146	91.19 144	96.46 162	86.07 207

WB-MVS		60.76 214	66.86 215	53.64 214	82.24 210	72.70 220	48.70 226	82.04 167	63.91 218	12.91 229	64.77 193	49.00 223	22.74 224	75.95 215	75.36 215	73.22 223	66.33 221

MIMVSNet		82.97 182	84.00 162	81.77 194	82.23 211	92.25 178	87.40 181	72.73 209	81.48 165	69.55 165	68.79 171	72.42 152	81.82 178	92.23 131	92.25 122	96.89 152	88.61 200

PM-MVS		80.29 196	79.30 199	81.45 195	81.91 212	88.23 207	82.61 201	79.01 185	79.99 175	67.15 183	69.07 170	51.39 219	82.92 170	87.55 189	85.59 194	95.08 188	93.28 169

pmmvs-eth3d		79.78 199	77.58 204	82.34 190	81.57 213	87.46 210	82.92 200	81.28 175	75.33 201	71.34 152	61.88 200	52.41 218	81.59 181	87.56 188	86.90 190	95.36 186	91.48 179

new-patchmatchnet		72.32 208	71.09 211	73.74 207	81.17 214	84.86 215	72.21 217	77.48 192	68.32 213	54.89 214	55.10 212	49.31 222	63.68 213	79.30 213	76.46 214	93.03 198	84.32 212

ET-MVSNet_ETH3D		89.93 101	90.84 90	88.87 113	79.60 215	96.19 101	94.43 70	86.56 116	90.63 74	80.75 113	90.71 44	77.78 135	93.73 58	91.36 143	93.45 94	98.15 71	95.77 131

PMVS	56.77 18	61.27 213	58.64 217	64.35 212	75.66 216	54.60 224	53.62 223	74.23 200	53.69 221	58.37 209	44.27 220	49.38 221	44.16 220	69.51 219	65.35 219	80.07 219	73.66 218
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		72.29 209	73.25 209	71.16 211	75.35 217	81.38 216	73.72 216	69.27 214	75.97 197	49.84 221	56.27 209	56.12 217	69.08 206	81.73 210	80.86 209	89.72 215	80.44 215

ambc			67.96 213		73.69 218	79.79 218	73.82 215		71.61 206	59.80 207	46.00 218	20.79 228	66.15 211	86.92 193	80.11 212	89.13 216	90.50 188

pmmvs3		71.13 210	71.06 212	71.21 210	73.54 219	80.19 217	71.69 218	64.86 217	62.04 220	52.10 217	54.92 213	48.00 224	75.03 200	83.75 206	83.24 205	90.04 214	85.27 208

MDA-MVSNet-bldmvs		73.81 206	72.56 210	75.28 205	72.52 220	88.87 205	74.95 214	82.67 157	71.57 207	55.02 213	65.96 185	42.84 226	76.11 197	70.61 218	81.47 208	90.38 213	86.59 205

tmp_tt				50.24 217	68.55 221	46.86 226	48.90 225	18.28 224	86.51 127	68.32 174	70.19 167	65.33 185	26.69 223	74.37 216	66.80 218	70.72 224

Gipuma		58.52 215	56.17 218	61.27 213	67.14 222	58.06 223	52.16 224	68.40 216	69.00 212	45.02 223	22.79 222	20.57 229	55.11 215	76.27 214	79.33 213	79.80 220	67.16 220
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MIMVSNet1		73.19 207	73.70 208	72.60 209	65.42 223	86.69 213	75.56 213	79.65 182	67.87 214	55.30 212	45.24 219	56.41 216	63.79 212	86.98 192	87.66 188	95.85 171	85.04 209

PMMVS2		53.68 217	55.72 219	51.30 215	58.84 224	67.02 222	54.23 222	60.97 220	47.50 222	19.42 226	34.81 221	31.97 227	30.88 222	65.84 220	69.99 216	83.47 218	72.92 219

EMVS		39.04 220	34.32 222	44.54 219	58.25 225	39.35 228	27.61 228	62.55 219	35.99 223	16.40 228	20.04 225	14.77 230	44.80 218	33.12 224	44.10 223	57.61 226	52.89 224

E-PMN		40.00 218	35.74 221	44.98 218	57.69 226	39.15 229	28.05 227	62.70 218	35.52 224	17.78 227	20.90 223	14.36 231	44.47 219	35.89 223	47.86 222	59.15 225	56.47 223

MVE	39.81 19	39.52 219	41.58 220	37.11 220	33.93 227	49.06 225	26.45 229	54.22 221	29.46 225	24.15 225	20.77 224	10.60 232	34.42 221	51.12 222	65.27 220	49.49 227	64.81 222
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		58.10 216	64.61 216	50.51 216	28.26 228	41.71 227	61.28 221	32.07 223	75.92 198	52.04 218	47.94 217	61.83 203	51.80 217	79.83 212	63.95 221	77.60 221	81.05 214

testmvs		4.35 221	6.54 223	1.79 222	0.60 229	1.82 230	3.06 231	0.95 225	7.22 226	0.88 231	12.38 226	1.25 233	3.87 226	6.09 225	5.58 224	1.40 228	11.42 226

GG-mvs-BLEND		62.84 212	90.21 94	30.91 221	0.57 230	94.45 119	86.99 183	0.34 227	88.71 107	0.98 230	81.55 108	91.58 58	0.86 227	92.66 120	91.43 141	95.73 174	91.11 184

test123		3.48 222	5.31 224	1.34 223	0.20 231	1.52 231	2.17 232	0.58 226	6.13 227	0.31 232	9.85 227	0.31 234	3.90 225	2.65 226	5.28 225	0.87 229	11.46 225

uanet_test		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

RE-MVS-def										60.19 205

9.14												97.28 23

MTAPA										95.36 2		97.46 21

MTMP										95.70 1		96.90 27

Patchmatch-RL test							18.47 230

NP-MVS									91.63 67

Patchmtry						92.39 176	89.18 161	73.30 206		71.08 155

DeepMVS_CX						71.82 221	68.37 219	48.05 222	77.38 187	46.88 222	65.77 186	47.03 225	67.48 208	64.27 221		76.89 222	76.72 216

High-resolution multi-view benchmark