High-res multi-view results

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

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

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

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

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

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

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

SED-MVS		95.61 1	96.36 1	94.73 2	96.84 19	98.15 2	97.08 3	92.92 2	95.64 2	91.84 4	95.98 4	95.33 1	92.83 6	96.00 1	94.94 3	96.90 4	98.45 2

DVP-MVS		95.56 2	96.26 2	94.73 2	96.93 16	98.19 1	96.62 6	92.81 4	96.15 1	91.73 5	95.01 7	95.31 2	93.41 1	95.95 2	94.77 7	96.90 4	98.46 1
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
DPE-MVS		95.53 3	96.13 3	94.82 1	96.81 22	98.05 3	97.42 1	93.09 1	94.31 8	91.49 6	97.12 1	95.03 3	93.27 3	95.55 5	94.58 11	96.86 6	98.25 3

HPM-MVS++		94.60 8	94.91 10	94.24 7	97.86 1	96.53 32	96.14 8	92.51 8	93.87 15	90.76 12	93.45 18	93.84 4	92.62 8	95.11 11	94.08 18	95.58 50	97.48 13

MSP-MVS		95.12 5	95.83 4	94.30 5	96.82 21	97.94 4	96.98 4	92.37 11	95.40 3	90.59 13	96.16 3	93.71 5	92.70 7	94.80 15	94.77 7	96.37 14	97.99 7
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
MCST-MVS		93.81 16	94.06 18	93.53 17	96.79 23	96.85 20	95.95 13	91.69 16	92.20 26	87.17 32	90.83 27	93.41 6	91.96 14	94.49 23	93.50 31	97.61 1	97.12 22

SD-MVS		94.53 9	95.22 7	93.73 15	95.69 36	97.03 14	95.77 22	91.95 12	94.41 7	91.35 7	94.97 8	93.34 7	91.80 20	94.72 18	93.99 19	95.82 34	98.07 6
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
CNVR-MVS		94.37 11	94.65 11	94.04 11	97.29 6	97.11 10	96.00 10	92.43 10	93.45 16	89.85 19	90.92 25	93.04 8	92.59 9	95.77 4	94.82 5	96.11 21	97.42 15

abl_6				90.66 40	94.65 47	96.27 37	92.21 50	86.94 48	90.23 41	86.38 37	85.50 40	92.96 9	88.37 46			95.40 57	95.46 53

APDe-MVS		95.23 4	95.69 5	94.70 4	97.12 10	97.81 5	97.19 2	92.83 3	95.06 5	90.98 10	96.47 2	92.77 10	93.38 2	95.34 8	94.21 15	96.68 8	98.17 4

SMA-MVS		94.70 6	95.35 6	93.93 12	97.57 2	97.57 7	95.98 11	91.91 13	94.50 6	90.35 14	93.46 17	92.72 11	91.89 18	95.89 3	95.22 1	95.88 27	98.10 5
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
SF-MVS		94.61 7	94.96 9	94.20 8	96.75 24	97.07 11	95.82 18	92.60 6	93.98 12	91.09 8	95.89 5	92.54 12	91.93 15	94.40 25	93.56 28	97.04 2	97.27 16

SR-MVS					96.58 26			90.99 22				92.40 13

NCCC		93.69 19	93.66 22	93.72 16	97.37 5	96.66 29	95.93 16	92.50 9	93.40 19	88.35 25	87.36 35	92.33 14	92.18 12	94.89 13	94.09 17	96.00 23	96.91 26

TSAR-MVS + MP.		94.48 10	94.97 8	93.90 13	95.53 37	97.01 15	96.69 5	90.71 24	94.24 9	90.92 11	94.97 8	92.19 15	93.03 4	94.83 14	93.60 26	96.51 13	97.97 8
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
9.14												92.16 16

CSCG		92.76 26	93.16 27	92.29 29	96.30 28	97.74 6	94.67 33	88.98 36	92.46 23	89.73 20	86.67 37	92.15 17	88.69 42	92.26 54	92.92 42	95.40 57	97.89 9

TSAR-MVS + GP.		92.71 28	93.91 20	91.30 35	91.96 72	96.00 41	93.43 41	87.94 41	92.53 22	86.27 40	93.57 15	91.94 18	91.44 25	93.29 40	92.89 43	96.78 7	97.15 21

train_agg		92.87 25	93.53 24	92.09 30	96.88 18	95.38 49	95.94 14	90.59 28	90.65 38	83.65 51	94.31 13	91.87 19	90.30 31	93.38 39	92.42 46	95.17 69	96.73 31

APD-MVS		94.37 11	94.47 15	94.26 6	97.18 8	96.99 16	96.53 7	92.68 5	92.45 24	89.96 17	94.53 11	91.63 20	92.89 5	94.58 20	93.82 22	96.31 17	97.26 18
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepPCF-MVS	88.51 2	92.64 29	94.42 16	90.56 41	94.84 44	96.92 18	91.31 61	89.61 32	95.16 4	84.55 46	89.91 29	91.45 21	90.15 33	95.12 10	94.81 6	92.90 147	97.58 12

MTAPA										92.97 2		91.03 22

PHI-MVS		92.05 32	93.74 21	90.08 44	94.96 41	97.06 13	93.11 45	87.71 44	90.71 37	80.78 68	92.40 22	91.03 22	87.68 53	94.32 27	94.48 12	96.21 19	96.16 40

SteuartSystems-ACMMP		94.06 13	94.65 11	93.38 19	96.97 15	97.36 8	96.12 9	91.78 14	92.05 28	87.34 30	94.42 12	90.87 24	91.87 19	95.47 7	94.59 10	96.21 19	97.77 10
Skip Steuart: Steuart Systems R&D Blog.
zzz-MVS		93.80 17	93.45 25	94.20 8	97.53 3	96.43 36	95.88 17	91.12 20	94.09 11	92.74 3	87.68 33	90.77 25	92.04 13	94.74 17	93.56 28	95.91 26	96.85 27

DPM-MVS		91.72 35	91.48 35	92.00 31	95.53 37	95.75 45	95.94 14	91.07 21	91.20 34	85.58 41	81.63 54	90.74 26	88.40 45	93.40 38	93.75 24	95.45 56	93.85 81

TSAR-MVS + ACMM		92.97 23	94.51 13	91.16 37	95.88 34	96.59 30	95.09 29	90.45 30	93.42 17	83.01 53	94.68 10	90.74 26	88.74 40	94.75 16	93.78 23	93.82 128	97.63 11

ACMMP_NAP		93.94 15	94.49 14	93.30 20	97.03 13	97.31 9	95.96 12	91.30 18	93.41 18	88.55 24	93.00 19	90.33 28	91.43 26	95.53 6	94.41 13	95.53 52	97.47 14

MP-MVS		93.35 20	93.59 23	93.08 23	97.39 4	96.82 22	95.38 25	90.71 24	90.82 36	88.07 27	92.83 21	90.29 29	91.32 27	94.03 29	93.19 38	95.61 48	97.16 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTMP										93.14 1		90.21 30

HFP-MVS		94.02 14	94.22 17	93.78 14	97.25 7	96.85 20	95.81 20	90.94 23	94.12 10	90.29 16	94.09 14	89.98 31	92.52 10	93.94 32	93.49 33	95.87 29	97.10 23

CANet		91.33 38	91.46 36	91.18 36	95.01 40	96.71 24	93.77 38	87.39 46	87.72 51	87.26 31	81.77 51	89.73 32	87.32 59	94.43 24	93.86 21	96.31 17	96.02 43

MVS_0304		90.88 40	91.35 38	90.34 42	93.91 52	96.79 23	94.49 34	86.54 50	86.57 55	82.85 55	81.68 53	89.70 33	87.57 55	94.64 19	93.93 20	96.67 10	96.15 41

CP-MVS		93.25 21	93.26 26	93.24 21	96.84 19	96.51 33	95.52 24	90.61 27	92.37 25	88.88 22	90.91 26	89.52 34	91.91 17	93.64 36	92.78 44	95.69 41	97.09 24

DeepC-MVS_fast	88.76 1	93.10 22	93.02 29	93.19 22	97.13 9	96.51 33	95.35 26	91.19 19	93.14 21	88.14 26	85.26 41	89.49 35	91.45 23	95.17 9	95.07 2	95.85 32	96.48 34
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator+	86.06 4	91.60 36	90.86 42	92.47 27	96.00 33	96.50 35	94.70 32	87.83 43	90.49 39	89.92 18	74.68 90	89.35 36	90.66 30	94.02 30	94.14 16	95.67 43	96.85 27

UA-Net		86.07 75	87.78 65	84.06 97	92.85 65	95.11 54	87.73 103	84.38 63	73.22 146	73.18 101	79.99 62	89.22 37	71.47 167	93.22 41	93.03 39	94.76 85	90.69 136

ACMMPR		93.72 18	93.94 19	93.48 18	97.07 11	96.93 17	95.78 21	90.66 26	93.88 14	89.24 21	93.53 16	89.08 38	92.24 11	93.89 34	93.50 31	95.88 27	96.73 31

MSLP-MVS++		92.02 34	91.40 37	92.75 24	96.01 32	95.88 44	93.73 40	89.00 34	89.89 44	90.31 15	81.28 56	88.85 39	91.45 23	92.88 47	94.24 14	96.00 23	96.76 30

XVS					93.11 60	96.70 25	91.91 54			83.95 48		88.82 40				95.79 36

X-MVStestdata					93.11 60	96.70 25	91.91 54			83.95 48		88.82 40				95.79 36

X-MVS		92.36 30	92.75 30	91.90 33	96.89 17	96.70 25	95.25 27	90.48 29	91.50 33	83.95 48	88.20 31	88.82 40	89.11 36	93.75 35	93.43 34	95.75 39	96.83 29

CPTT-MVS		91.39 37	90.95 40	91.91 32	95.06 39	95.24 51	95.02 30	88.98 36	91.02 35	86.71 34	84.89 43	88.58 43	91.60 22	90.82 81	89.67 92	94.08 115	96.45 35

PGM-MVS		92.76 26	93.03 28	92.45 28	97.03 13	96.67 28	95.73 23	87.92 42	90.15 43	86.53 36	92.97 20	88.33 44	91.69 21	93.62 37	93.03 39	95.83 33	96.41 37

mPP-MVS					97.06 12							88.08 45

QAPM		89.49 48	89.58 49	89.38 52	94.73 45	95.94 42	92.35 49	85.00 60	85.69 60	80.03 72	76.97 78	87.81 46	87.87 50	92.18 58	92.10 48	96.33 15	96.40 38

CDPH-MVS		91.14 39	92.01 32	90.11 43	96.18 29	96.18 39	94.89 31	88.80 38	88.76 48	77.88 84	89.18 30	87.71 47	87.29 60	93.13 42	93.31 36	95.62 46	95.84 45

3Dnovator	85.17 5	90.48 42	89.90 46	91.16 37	94.88 43	95.74 46	93.82 37	85.36 57	89.28 45	87.81 28	74.34 92	87.40 48	88.56 43	93.07 43	93.74 25	96.53 12	95.71 47

OMC-MVS		90.23 44	90.40 43	90.03 45	93.45 57	95.29 50	91.89 56	86.34 52	93.25 20	84.94 45	81.72 52	86.65 49	88.90 37	91.69 62	90.27 75	94.65 92	93.95 79

DeepC-MVS	87.86 3	92.26 31	91.86 34	92.73 25	96.18 29	96.87 19	95.19 28	91.76 15	92.17 27	86.58 35	81.79 50	85.85 50	90.88 29	94.57 21	94.61 9	95.80 35	97.18 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OpenMVS	82.53 11	87.71 65	86.84 72	88.73 57	94.42 48	95.06 55	91.02 63	83.49 78	82.50 75	82.24 59	67.62 128	85.48 51	85.56 70	91.19 69	91.30 55	95.67 43	94.75 65

MVS_111021_HR		90.56 41	91.29 39	89.70 49	94.71 46	95.63 47	91.81 57	86.38 51	87.53 52	81.29 62	87.96 32	85.43 52	87.69 52	93.90 33	92.93 41	96.33 15	95.69 48

PCF-MVS	84.60 6	88.66 54	87.75 67	89.73 48	93.06 62	96.02 40	93.22 44	90.00 31	82.44 76	80.02 73	77.96 74	85.16 53	87.36 58	88.54 109	88.54 113	94.72 88	95.61 50
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TAPA-MVS	84.37 7	88.91 53	88.93 53	88.89 55	93.00 63	94.85 59	92.00 53	84.84 61	91.68 32	80.05 71	79.77 63	84.56 54	88.17 48	90.11 91	89.00 108	95.30 64	92.57 109
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMMP		92.03 33	92.16 31	91.87 34	95.88 34	96.55 31	94.47 35	89.49 33	91.71 31	85.26 42	91.52 24	84.48 55	90.21 32	92.82 48	91.63 52	95.92 25	96.42 36
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
DELS-MVS		89.71 46	89.68 48	89.74 47	93.75 54	96.22 38	93.76 39	85.84 53	82.53 73	85.05 44	78.96 68	84.24 56	84.25 75	94.91 12	94.91 4	95.78 38	96.02 43
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
PVSNet_Blended_VisFu		87.40 69	87.80 64	86.92 73	92.86 64	95.40 48	88.56 97	83.45 82	79.55 103	82.26 58	74.49 91	84.03 57	79.24 123	92.97 46	91.53 54	95.15 71	96.65 33

CS-MVS		88.97 52	89.44 51	88.41 64	91.45 75	95.24 51	90.03 70	82.43 96	84.08 68	81.16 64	81.02 58	83.83 58	88.74 40	94.25 28	92.73 45	96.67 10	94.95 60

MVS_111021_LR		90.14 45	90.89 41	89.26 53	93.23 59	94.05 70	90.43 66	84.65 62	90.16 42	84.52 47	90.14 28	83.80 59	87.99 49	92.50 52	90.92 61	94.74 86	94.70 67

GG-mvs-BLEND		57.56 203	82.61 102	28.34 210	0.22 218	90.10 119	79.37 181	0.14 216	79.56 102	0.40 219	71.25 107	83.40 60	0.30 216	86.27 141	83.87 167	89.59 180	83.83 180

UGNet		85.90 78	88.23 58	83.18 107	88.96 105	94.10 68	87.52 105	83.60 74	81.66 83	77.90 83	80.76 59	83.19 61	66.70 184	91.13 75	90.71 67	94.39 108	96.06 42
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
EPNet		89.60 47	89.91 45	89.24 54	96.45 27	93.61 75	92.95 47	88.03 40	85.74 59	83.36 52	87.29 36	83.05 62	80.98 93	92.22 55	91.85 50	93.69 133	95.58 51
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MAR-MVS		88.39 59	88.44 56	88.33 65	94.90 42	95.06 55	90.51 65	83.59 75	85.27 61	79.07 76	77.13 76	82.89 63	87.70 51	92.19 57	92.32 47	94.23 112	94.20 77
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
ETV-MVS		89.22 50	89.76 47	88.60 60	91.60 73	94.61 63	89.48 81	83.46 81	85.20 62	81.58 60	82.75 46	82.59 64	88.80 38	94.57 21	93.28 37	96.68 8	95.31 55

EPP-MVSNet		86.55 71	87.76 66	85.15 82	90.52 87	94.41 64	87.24 112	82.32 97	81.79 82	73.60 99	78.57 70	82.41 65	82.07 87	91.23 66	90.39 73	95.14 72	95.48 52

Vis-MVSNet (Re-imp)		83.65 96	86.81 74	79.96 141	90.46 90	92.71 88	84.84 142	82.00 99	80.93 92	62.44 157	76.29 80	82.32 66	65.54 187	92.29 53	91.66 51	94.49 102	91.47 131

IS_MVSNet		86.18 74	88.18 59	83.85 100	91.02 80	94.72 62	87.48 106	82.46 95	81.05 90	70.28 112	76.98 77	82.20 67	76.65 139	93.97 31	93.38 35	95.18 68	94.97 59

CNLPA		88.40 57	87.00 71	90.03 45	93.73 55	94.28 65	89.56 79	85.81 54	91.87 29	87.55 29	69.53 118	81.49 68	89.23 35	89.45 101	88.59 112	94.31 111	93.82 82

AdaColmap		90.29 43	88.38 57	92.53 26	96.10 31	95.19 53	92.98 46	91.40 17	89.08 47	88.65 23	78.35 71	81.44 69	91.30 28	90.81 82	90.21 76	94.72 88	93.59 87

baseline		84.89 85	86.06 80	83.52 105	87.25 122	89.67 132	87.76 102	75.68 161	84.92 64	78.40 78	80.10 60	80.98 70	80.20 107	86.69 134	87.05 128	91.86 159	92.99 93

PLC	83.76 9	88.61 56	86.83 73	90.70 39	94.22 49	92.63 91	91.50 59	87.19 47	89.16 46	86.87 33	75.51 85	80.87 71	89.98 34	90.01 92	89.20 102	94.41 107	90.45 141
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
Vis-MVSNet		84.38 92	86.68 76	81.70 121	87.65 118	94.89 58	88.14 99	80.90 107	74.48 132	68.23 124	77.53 75	80.72 72	69.98 171	92.68 49	91.90 49	95.33 63	94.58 69
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DI_MVS_plusplus_trai		86.41 73	85.54 85	87.42 71	89.24 101	93.13 81	92.16 52	82.65 92	82.30 77	80.75 69	68.30 125	80.41 73	85.01 72	90.56 88	90.07 79	94.70 90	94.01 78

HQP-MVS		89.13 51	89.58 49	88.60 60	93.53 56	93.67 73	93.29 43	87.58 45	88.53 49	75.50 88	87.60 34	80.32 74	87.07 61	90.66 87	89.95 84	94.62 94	96.35 39

EIA-MVS		87.94 64	88.05 61	87.81 67	91.46 74	95.00 57	88.67 93	82.81 86	82.53 73	80.81 67	80.04 61	80.20 75	87.48 56	92.58 51	91.61 53	95.63 45	94.36 71

CANet_DTU		85.43 80	87.72 68	82.76 111	90.95 83	93.01 85	89.99 71	75.46 162	82.67 72	64.91 142	83.14 45	80.09 76	80.68 97	92.03 60	91.03 58	94.57 97	92.08 117

CHOSEN 280x420		80.28 125	81.66 106	78.67 152	82.92 175	79.24 202	85.36 137	66.79 194	78.11 111	70.32 110	75.03 89	79.87 77	81.09 92	89.07 103	83.16 172	85.54 199	87.17 163

RPSCF		83.46 97	83.36 96	83.59 103	87.75 114	87.35 159	84.82 143	79.46 127	83.84 69	78.12 80	82.69 47	79.87 77	82.60 83	82.47 179	81.13 182	88.78 184	86.13 171

MVS_Test		86.93 70	87.24 69	86.56 74	90.10 97	93.47 77	90.31 67	80.12 117	83.55 70	78.12 80	79.58 64	79.80 79	85.45 71	90.17 90	90.59 70	95.29 65	93.53 88

PMMVS		81.65 115	84.05 93	78.86 148	78.56 196	82.63 190	83.10 154	67.22 192	81.39 84	70.11 114	84.91 42	79.74 80	82.12 86	87.31 121	85.70 152	92.03 157	86.67 169

GBi-Net		84.51 88	84.80 88	84.17 94	84.20 157	89.95 120	89.70 75	80.37 111	81.17 86	75.50 88	69.63 114	79.69 81	79.75 115	90.73 83	90.72 64	95.52 53	91.71 124

test1		84.51 88	84.80 88	84.17 94	84.20 157	89.95 120	89.70 75	80.37 111	81.17 86	75.50 88	69.63 114	79.69 81	79.75 115	90.73 83	90.72 64	95.52 53	91.71 124

FMVSNet3		84.44 90	84.64 90	84.21 93	84.32 156	90.13 118	89.85 74	80.37 111	81.17 86	75.50 88	69.63 114	79.69 81	79.62 118	89.72 96	90.52 72	95.59 49	91.58 130

canonicalmvs		89.36 49	89.92 44	88.70 58	91.38 76	95.92 43	91.81 57	82.61 94	90.37 40	82.73 57	82.09 48	79.28 84	88.30 47	91.17 70	93.59 27	95.36 60	97.04 25

DCV-MVSNet		85.88 79	86.17 77	85.54 81	89.10 104	89.85 125	89.34 82	80.70 108	83.04 71	78.08 82	76.19 81	79.00 85	82.42 84	89.67 97	90.30 74	93.63 136	95.12 56

Anonymous20231211		84.42 91	83.02 97	86.05 77	88.85 106	92.70 89	88.92 92	83.40 83	79.99 98	78.31 79	55.83 184	78.92 86	83.33 78	89.06 104	89.76 90	93.50 138	94.90 61

MS-PatchMatch		81.79 114	81.44 109	82.19 118	90.35 92	89.29 139	88.08 101	75.36 163	77.60 114	69.00 121	64.37 148	78.87 87	77.14 138	88.03 115	85.70 152	93.19 144	86.24 170

CLD-MVS		88.66 54	88.52 55	88.82 56	91.37 77	94.22 66	92.82 48	82.08 98	88.27 50	85.14 43	81.86 49	78.53 88	85.93 69	91.17 70	90.61 69	95.55 51	95.00 58
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PVSNet_BlendedMVS		88.19 62	88.00 62	88.42 62	92.71 68	94.82 60	89.08 86	83.81 70	84.91 65	86.38 37	79.14 65	78.11 89	82.66 81	93.05 44	91.10 56	95.86 30	94.86 63

PVSNet_Blended		88.19 62	88.00 62	88.42 62	92.71 68	94.82 60	89.08 86	83.81 70	84.91 65	86.38 37	79.14 65	78.11 89	82.66 81	93.05 44	91.10 56	95.86 30	94.86 63

OPM-MVS		87.56 67	85.80 83	89.62 50	93.90 53	94.09 69	94.12 36	88.18 39	75.40 126	77.30 87	76.41 79	77.93 91	88.79 39	92.20 56	90.82 63	95.40 57	93.72 85

casdiffmvs		87.45 68	87.15 70	87.79 69	90.15 96	94.22 66	89.96 72	83.93 69	85.08 63	80.91 65	75.81 83	77.88 92	86.08 67	91.86 61	90.86 62	95.74 40	94.37 70

FMVSNet2		83.87 93	83.73 95	84.05 98	84.20 157	89.95 120	89.70 75	80.21 116	79.17 106	74.89 92	65.91 133	77.49 93	79.75 115	90.87 80	91.00 60	95.52 53	91.71 124

diffmvs		86.52 72	86.76 75	86.23 76	88.31 111	92.63 91	89.58 78	81.61 102	86.14 56	80.26 70	79.00 67	77.27 94	83.58 76	88.94 105	89.06 105	94.05 117	94.29 72

EPNet_dtu		81.98 110	83.82 94	79.83 143	94.10 51	85.97 168	87.29 110	84.08 68	80.61 95	59.96 175	81.62 55	77.19 95	62.91 191	87.21 122	86.38 141	90.66 173	87.77 161
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		75.64 179	77.26 158	73.76 184	87.92 113	92.20 96	87.32 109	64.67 202	51.92 207	35.35 211	46.44 200	77.05 96	71.97 164	92.64 50	91.02 59	95.34 62	89.53 145

Anonymous202405211			82.75 101		89.58 100	92.97 86	89.04 89	84.13 67	78.72 108		57.18 180	76.64 97	83.13 79	89.55 99	89.92 85	93.38 141	94.28 75

LGP-MVS_train		88.25 61	88.55 54	87.89 66	92.84 66	93.66 74	93.35 42	85.22 59	85.77 58	74.03 97	86.60 38	76.29 98	86.62 65	91.20 68	90.58 71	95.29 65	95.75 46

SCA		79.51 136	80.15 127	78.75 150	86.58 128	87.70 156	83.07 155	68.53 187	81.31 85	66.40 131	73.83 94	75.38 99	79.30 122	80.49 186	79.39 187	88.63 186	82.96 185

IterMVS-LS		83.28 99	82.95 99	83.65 101	88.39 110	88.63 150	86.80 121	78.64 136	76.56 118	73.43 100	72.52 103	75.35 100	80.81 95	86.43 140	88.51 114	93.84 127	92.66 104
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMM	83.27 10	87.68 66	86.09 79	89.54 51	93.26 58	92.19 97	91.43 60	86.74 49	86.02 57	82.85 55	75.63 84	75.14 101	88.41 44	90.68 86	89.99 81	94.59 95	92.97 94
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	83.90 8	88.32 60	88.06 60	88.62 59	92.18 70	93.98 71	91.28 62	85.24 58	86.69 54	81.23 63	85.62 39	75.13 102	87.01 63	89.83 94	89.77 89	94.79 82	95.43 54
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVSTER		86.03 76	86.12 78	85.93 78	88.62 107	89.93 123	89.33 83	79.91 122	81.87 81	81.35 61	81.07 57	74.91 103	80.66 98	92.13 59	90.10 78	95.68 42	92.80 99

test_part1		83.23 100	80.55 122	86.35 75	88.60 108	90.61 109	90.78 64	81.13 106	70.89 157	83.01 53	55.72 185	74.60 104	82.19 85	87.79 117	89.26 100	92.39 152	95.01 57

test-LLR		79.47 137	79.84 132	79.03 147	87.47 119	82.40 193	81.24 170	78.05 141	73.72 141	62.69 154	73.76 95	74.42 105	73.49 158	84.61 164	82.99 174	91.25 167	87.01 164

TESTMET0.1,1		77.78 155	79.84 132	75.38 176	80.86 191	82.40 193	81.24 170	62.72 205	73.72 141	62.69 154	73.76 95	74.42 105	73.49 158	84.61 164	82.99 174	91.25 167	87.01 164

baseline1		84.54 87	84.43 91	84.67 85	90.62 85	91.16 104	88.63 95	83.75 72	79.78 100	71.16 108	75.14 87	74.10 107	77.84 132	91.56 63	90.67 68	96.04 22	88.58 150

Effi-MVS+		85.33 81	85.08 87	85.63 80	89.69 99	93.42 78	89.90 73	80.31 115	79.32 104	72.48 107	73.52 98	74.03 108	86.55 66	90.99 77	89.98 82	94.83 81	94.27 76

CDS-MVSNet		81.63 117	82.09 104	81.09 130	87.21 123	90.28 114	87.46 108	80.33 114	69.06 167	70.66 109	71.30 105	73.87 109	67.99 177	89.58 98	89.87 86	92.87 148	90.69 136
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test-mter		77.79 154	80.02 129	75.18 177	81.18 190	82.85 188	80.52 176	62.03 206	73.62 143	62.16 159	73.55 97	73.83 110	73.81 156	84.67 163	83.34 171	91.37 165	88.31 153

thisisatest0530		85.15 83	85.86 81	84.33 90	89.19 103	92.57 94	87.22 113	80.11 118	82.15 79	74.41 94	78.15 72	73.80 111	79.90 111	90.99 77	89.58 93	95.13 73	93.75 84

HyFIR lowres test		81.62 118	79.45 138	84.14 96	91.00 81	93.38 79	88.27 98	78.19 139	76.28 120	70.18 113	48.78 197	73.69 112	83.52 77	87.05 125	87.83 120	93.68 134	89.15 147

tttt0517		85.11 84	85.81 82	84.30 91	89.24 101	92.68 90	87.12 117	80.11 118	81.98 80	74.31 96	78.08 73	73.57 113	79.90 111	91.01 76	89.58 93	95.11 75	93.77 83

FC-MVSNet-test		76.53 167	81.62 107	70.58 192	84.99 149	85.73 171	74.81 194	78.85 134	77.00 117	39.13 210	75.90 82	73.50 114	54.08 199	86.54 137	85.99 149	91.65 161	86.68 167

PatchmatchNet		78.67 147	78.85 141	78.46 155	86.85 127	86.03 167	83.77 151	68.11 190	80.88 93	66.19 132	72.90 101	73.40 115	78.06 129	79.25 192	77.71 192	87.75 189	81.75 188
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		79.14 141	79.49 137	78.74 151	85.40 141	86.89 163	84.32 148	70.29 180	78.85 107	69.42 118	75.37 86	73.29 116	75.64 144	80.61 185	79.48 186	87.36 190	81.91 187

TSAR-MVS + COLMAP		88.40 57	89.09 52	87.60 70	92.72 67	93.92 72	92.21 50	85.57 56	91.73 30	73.72 98	91.75 23	73.22 117	87.64 54	91.49 64	89.71 91	93.73 131	91.82 122

CHOSEN 1792x2688		82.16 108	80.91 118	83.61 102	91.14 78	92.01 98	89.55 80	79.15 131	79.87 99	70.29 111	52.51 193	72.56 118	81.39 89	88.87 107	88.17 116	90.15 177	92.37 116

LS3D		85.96 77	84.37 92	87.81 67	94.13 50	93.27 80	90.26 69	89.00 34	84.91 65	72.84 105	71.74 104	72.47 119	87.45 57	89.53 100	89.09 104	93.20 143	89.60 144

FMVSNet1		81.64 116	80.61 120	82.84 110	82.36 182	89.20 141	88.67 93	79.58 125	70.79 158	72.63 106	58.95 175	72.26 120	79.34 121	90.73 83	90.72 64	94.47 103	91.62 128

Effi-MVS+-dtu		82.05 109	81.76 105	82.38 115	87.72 115	90.56 110	86.90 120	78.05 141	73.85 140	66.85 129	71.29 106	71.90 121	82.00 88	86.64 135	85.48 154	92.76 149	92.58 108

CostFormer		80.94 121	80.21 125	81.79 120	87.69 116	88.58 151	87.47 107	70.66 178	80.02 97	77.88 84	73.03 99	71.40 122	78.24 128	79.96 188	79.63 184	88.82 183	88.84 148

FC-MVSNet-train		85.18 82	85.31 86	85.03 83	90.67 84	91.62 101	87.66 104	83.61 73	79.75 101	74.37 95	78.69 69	71.21 123	78.91 124	91.23 66	89.96 83	94.96 77	94.69 68

ET-MVSNet_ETH3D		84.65 86	85.58 84	83.56 104	74.99 205	92.62 93	90.29 68	80.38 110	82.16 78	73.01 104	83.41 44	71.10 124	87.05 62	87.77 118	90.17 77	95.62 46	91.82 122

xxxxxxxxxxxxxcwj		92.95 24	91.88 33	94.20 8	96.75 24	97.07 11	95.82 18	92.60 6	93.98 12	91.09 8	95.89 5	71.01 125	91.93 15	94.40 25	93.56 28	97.04 2	97.27 16

IterMVS-SCA-FT		79.41 138	80.20 126	78.49 154	85.88 133	86.26 166	83.95 149	71.94 173	73.55 144	61.94 161	70.48 111	70.50 126	75.23 145	85.81 147	84.61 164	91.99 158	90.18 142

IterMVS		78.79 145	79.71 135	77.71 158	85.26 144	85.91 169	84.54 145	69.84 184	73.38 145	61.25 169	70.53 110	70.35 127	74.43 154	85.21 157	83.80 169	90.95 171	88.77 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CVMVSNet		76.70 163	78.46 144	74.64 182	83.34 167	84.48 181	81.83 166	74.58 164	68.88 168	51.23 196	69.77 113	70.05 128	67.49 180	84.27 167	83.81 168	89.38 181	87.96 158

IB-MVS	79.09 12	82.60 105	82.19 103	83.07 108	91.08 79	93.55 76	80.90 173	81.35 103	76.56 118	80.87 66	64.81 145	69.97 129	68.87 174	85.64 148	90.06 80	95.36 60	94.74 66
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
baseline2		82.80 102	82.86 100	82.73 112	87.68 117	90.50 111	84.92 141	78.93 132	78.07 113	73.06 102	75.08 88	69.77 130	77.31 135	88.90 106	86.94 130	94.50 100	90.74 135

EPMVS		77.53 157	78.07 150	76.90 165	86.89 126	84.91 180	82.18 165	66.64 195	81.00 91	64.11 146	72.75 102	69.68 131	74.42 155	79.36 191	78.13 190	87.14 192	80.68 194

CR-MVSNet		78.71 146	78.86 140	78.55 153	85.85 136	85.15 177	82.30 162	68.23 188	74.71 130	65.37 138	64.39 147	69.59 132	77.18 136	85.10 160	84.87 159	92.34 154	88.21 154

test0.0.03 1		76.03 173	78.51 142	73.12 188	87.47 119	85.13 179	76.32 191	78.05 141	73.19 148	50.98 197	70.64 108	69.28 133	55.53 195	85.33 153	84.38 166	90.39 175	81.63 189

TAMVS		76.42 168	77.16 160	75.56 174	83.05 171	85.55 174	80.58 175	71.43 175	65.40 186	61.04 172	67.27 129	69.22 134	67.99 177	84.88 162	84.78 161	89.28 182	83.01 184

MSDG		83.87 93	81.02 115	87.19 72	92.17 71	89.80 127	89.15 84	85.72 55	80.61 95	79.24 75	66.66 131	68.75 135	82.69 80	87.95 116	87.44 122	94.19 113	85.92 173

Fast-Effi-MVS+		83.77 95	82.98 98	84.69 84	87.98 112	91.87 99	88.10 100	77.70 145	78.10 112	73.04 103	69.13 120	68.51 136	86.66 64	90.49 89	89.85 87	94.67 91	92.88 96

Fast-Effi-MVS+-dtu		79.95 128	80.69 119	79.08 146	86.36 130	89.14 143	85.85 129	72.28 172	72.85 149	59.32 178	70.43 112	68.42 137	77.57 133	86.14 142	86.44 140	93.11 145	91.39 132

FMVSNet5		75.50 180	76.07 170	74.83 179	76.16 201	81.19 196	81.34 168	70.21 181	73.20 147	61.59 166	58.97 174	68.33 138	68.50 175	85.87 146	85.85 150	91.18 170	79.11 197

ADS-MVSNet		74.53 184	75.69 177	73.17 187	81.57 188	80.71 198	79.27 182	63.03 204	79.27 105	59.94 176	67.86 126	68.32 139	71.08 168	77.33 196	76.83 194	84.12 204	79.53 195

PatchT		76.42 168	77.81 154	74.80 180	78.46 197	84.30 182	71.82 200	65.03 201	73.89 138	65.37 138	61.58 156	66.70 140	77.18 136	85.10 160	84.87 159	90.94 172	88.21 154

RPMNet		77.07 160	77.63 156	76.42 168	85.56 140	85.15 177	81.37 167	65.27 199	74.71 130	60.29 174	63.71 150	66.59 141	73.64 157	82.71 177	82.12 179	92.38 153	88.39 152

thisisatest0515		79.76 132	80.59 121	78.80 149	84.40 155	88.91 148	79.48 179	76.94 151	72.29 150	67.33 127	67.82 127	65.99 142	70.80 169	88.50 110	87.84 118	93.86 126	92.75 102

tpmrst		76.55 166	75.99 173	77.20 161	87.32 121	83.05 186	82.86 156	65.62 197	78.61 110	67.22 128	69.19 119	65.71 143	75.87 143	76.75 198	75.33 197	84.31 202	83.28 183

COLMAP_ROB	76.78 15	80.50 124	78.49 143	82.85 109	90.96 82	89.65 133	86.20 127	83.40 83	77.15 116	66.54 130	62.27 153	65.62 144	77.89 131	85.23 155	84.70 162	92.11 155	84.83 177
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	79.08 13	81.84 113	80.06 128	83.91 99	89.92 98	90.62 108	86.21 126	83.48 80	73.88 139	65.75 135	66.38 132	65.30 145	84.63 73	85.90 145	87.25 125	93.45 139	91.13 134

pm-mvs1		78.51 150	77.75 155	79.40 144	84.83 153	89.30 138	83.55 153	79.38 128	62.64 191	63.68 149	58.73 177	64.68 146	70.78 170	89.79 95	87.84 118	94.17 114	91.28 133

UniMVSNet_NR-MVSNet		81.87 111	81.33 111	82.50 113	85.31 143	91.30 102	85.70 131	84.25 64	75.89 122	64.21 144	66.95 130	64.65 147	80.22 105	87.07 124	89.18 103	95.27 67	94.29 72

MIMVSNet		74.69 183	75.60 178	73.62 185	76.02 203	85.31 176	81.21 172	67.43 191	71.02 155	59.07 180	54.48 186	64.07 148	66.14 186	86.52 138	86.64 135	91.83 160	81.17 191

ACMH	78.52 14	81.86 112	80.45 123	83.51 106	90.51 89	91.22 103	85.62 134	84.23 65	70.29 163	62.21 158	69.04 122	64.05 149	84.48 74	87.57 120	88.45 115	94.01 119	92.54 111
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpm cat1		77.78 155	75.28 181	80.70 133	87.14 124	85.84 170	85.81 130	70.40 179	77.44 115	78.80 77	63.72 149	64.01 150	76.55 140	75.60 200	75.21 198	85.51 200	85.12 175

thres100view900		82.55 106	81.01 117	84.34 89	90.30 94	92.27 95	89.04 89	82.77 87	75.14 127	69.56 115	65.72 135	63.13 151	79.62 118	89.97 93	89.26 100	94.73 87	91.61 129

tfpn200view9		82.86 101	81.46 108	84.48 87	90.30 94	93.09 82	89.05 88	82.71 88	75.14 127	69.56 115	65.72 135	63.13 151	80.38 104	91.15 72	89.51 95	94.91 78	92.50 113

UniMVSNet (Re)		81.22 119	81.08 114	81.39 125	85.35 142	91.76 100	84.93 140	82.88 85	76.13 121	65.02 141	64.94 143	63.09 153	75.17 147	87.71 119	89.04 106	94.97 76	94.88 62

thres200		82.77 103	81.25 112	84.54 86	90.38 91	93.05 83	89.13 85	82.67 90	74.40 133	69.53 117	65.69 137	63.03 154	80.63 99	91.15 72	89.42 97	94.88 79	92.04 119

tpm		76.30 172	76.05 172	76.59 167	86.97 125	83.01 187	83.83 150	67.06 193	71.83 151	63.87 148	69.56 117	62.88 155	73.41 160	79.79 189	78.59 188	84.41 201	86.68 167

PatchMatch-RL		83.34 98	81.36 110	85.65 79	90.33 93	89.52 135	84.36 146	81.82 100	80.87 94	79.29 74	74.04 93	62.85 156	86.05 68	88.40 112	87.04 129	92.04 156	86.77 166

thres400		82.68 104	81.15 113	84.47 88	90.52 87	92.89 87	88.95 91	82.71 88	74.33 134	69.22 120	65.31 139	62.61 157	80.63 99	90.96 79	89.50 96	94.79 82	92.45 115

v8		79.90 129	78.39 146	81.66 122	83.97 161	89.81 126	87.16 115	77.40 147	71.49 152	67.71 125	61.24 158	62.49 158	79.83 114	85.48 152	86.17 144	93.89 124	92.02 121

anonymousdsp		77.94 153	79.00 139	76.71 166	79.03 194	87.83 155	79.58 178	72.87 170	65.80 182	58.86 182	65.82 134	62.48 159	75.99 142	86.77 131	88.66 111	93.92 122	95.68 49

V42		79.59 134	78.43 145	80.94 131	82.79 178	89.71 130	86.66 122	76.73 154	71.38 153	67.42 126	61.01 160	62.30 160	78.39 127	85.56 150	86.48 138	93.65 135	92.60 106

EG-PatchMatch MVS		76.40 170	75.47 179	77.48 160	85.86 135	90.22 116	82.45 159	73.96 168	59.64 199	59.60 177	52.75 192	62.20 161	68.44 176	88.23 113	87.50 121	94.55 98	87.78 160

thres600view7		82.53 107	81.02 115	84.28 92	90.61 86	93.05 83	88.57 96	82.67 90	74.12 137	68.56 123	65.09 142	62.13 162	80.40 103	91.15 72	89.02 107	94.88 79	92.59 107

GA-MVS		79.52 135	79.71 135	79.30 145	85.68 137	90.36 113	84.55 144	78.44 137	70.47 162	57.87 183	68.52 124	61.38 163	76.21 141	89.40 102	87.89 117	93.04 146	89.96 143

WR-MVS		76.63 164	78.02 152	75.02 178	84.14 160	89.76 129	78.34 186	80.64 109	69.56 164	52.32 192	61.26 157	61.24 164	60.66 192	84.45 166	87.07 127	93.99 120	92.77 100

Baseline_NR-MVSNet		79.84 130	78.37 147	81.55 124	84.98 150	86.66 164	85.06 138	83.49 78	75.57 125	63.31 151	58.22 179	60.97 165	78.00 130	86.89 127	87.13 126	94.47 103	93.15 91

pmmvs6		74.83 182	72.89 189	77.09 162	82.11 183	87.50 158	80.88 174	76.97 150	52.79 206	61.91 163	46.66 199	60.49 166	69.28 173	86.74 133	85.46 155	91.39 164	90.56 139

v10		79.62 133	78.19 148	81.28 128	83.73 163	89.69 131	87.27 111	76.86 152	70.50 161	65.46 136	60.58 165	60.47 167	80.44 102	86.91 126	86.63 136	93.93 121	92.55 110

v148		78.59 148	76.84 164	80.62 135	83.61 165	89.16 142	83.65 152	79.24 130	69.38 165	69.34 119	59.88 169	60.41 168	75.19 146	83.81 170	84.63 163	92.70 150	90.63 138

v2v482		79.84 130	78.07 150	81.90 119	83.75 162	90.21 117	87.17 114	79.85 123	70.65 159	65.93 134	61.93 155	60.07 169	80.82 94	85.25 154	86.71 133	93.88 125	91.70 127

TranMVSNet+NR-MVSNet		80.52 123	79.84 132	81.33 127	84.92 152	90.39 112	85.53 136	84.22 66	74.27 135	60.68 173	64.93 144	59.96 170	77.48 134	86.75 132	89.28 99	95.12 74	93.29 89

dps		78.02 152	75.94 174	80.44 138	86.06 132	86.62 165	82.58 157	69.98 182	75.14 127	77.76 86	69.08 121	59.93 171	78.47 126	79.47 190	77.96 191	87.78 188	83.40 182

WR-MVS_H		75.84 177	76.93 163	74.57 183	82.86 176	89.50 136	78.34 186	79.36 129	66.90 175	52.51 191	60.20 167	59.71 172	59.73 193	83.61 171	85.77 151	94.65 92	92.84 97

CMPMVS	56.49 17	73.84 187	71.73 193	76.31 171	85.20 145	85.67 172	75.80 192	73.23 169	62.26 192	65.40 137	53.40 191	59.70 173	71.77 166	80.25 187	79.56 185	86.45 196	81.28 190
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		73.21 188	72.91 188	73.56 186	80.01 192	84.28 183	78.62 184	66.43 196	68.64 169	59.12 179	60.39 166	59.69 174	69.81 172	78.82 194	77.43 193	87.36 190	81.11 192

DU-MVS		81.20 120	80.30 124	82.25 116	84.98 150	90.94 106	85.70 131	83.58 76	75.74 123	64.21 144	65.30 140	59.60 175	80.22 105	86.89 127	89.31 98	94.77 84	94.29 72

v1144		79.38 139	77.83 153	81.18 129	83.62 164	90.23 115	87.15 116	78.35 138	69.13 166	64.02 147	60.20 167	59.41 176	80.14 109	86.78 130	86.57 137	93.81 129	92.53 112

pmmvs4		79.99 127	78.08 149	82.22 117	83.04 172	87.16 162	84.95 139	78.80 135	78.64 109	74.53 93	64.61 146	59.41 176	79.45 120	84.13 168	84.54 165	92.53 151	88.08 156

TDRefinement		79.05 142	77.05 161	81.39 125	88.45 109	89.00 146	86.92 118	82.65 92	74.21 136	64.41 143	59.17 172	59.16 178	74.52 153	85.23 155	85.09 157	91.37 165	87.51 162

TransMVSNet (Re)		76.57 165	75.16 182	78.22 157	85.60 139	87.24 160	82.46 158	81.23 105	59.80 198	59.05 181	57.07 181	59.14 179	66.60 185	88.09 114	86.82 131	94.37 109	87.95 159

USDC		80.69 122	79.89 131	81.62 123	86.48 129	89.11 144	86.53 123	78.86 133	81.15 89	63.48 150	72.98 100	59.12 180	81.16 91	87.10 123	85.01 158	93.23 142	84.77 178

v144192		78.81 144	77.22 159	80.67 134	82.95 173	89.79 128	86.40 124	77.42 146	68.26 172	63.13 152	59.50 170	58.13 181	80.08 110	85.93 144	86.08 146	94.06 116	92.83 98

pmmvs5		76.93 161	76.33 168	77.62 159	81.97 184	88.40 153	81.32 169	74.35 166	65.42 185	61.42 167	63.07 151	57.95 182	73.23 161	85.60 149	85.35 156	93.41 140	88.55 151

UniMVSNet_ETH3D		79.24 140	76.47 166	82.48 114	85.66 138	90.97 105	86.08 128	81.63 101	64.48 187	68.94 122	54.47 187	57.65 183	78.83 125	85.20 158	88.91 109	93.72 132	93.60 86

v1192		78.94 143	77.33 157	80.82 132	83.25 168	89.90 124	86.91 119	77.72 144	68.63 170	62.61 156	59.17 172	57.53 184	80.62 101	86.89 127	86.47 139	93.79 130	92.75 102

pmnet_mix02		71.95 189	71.83 192	72.10 189	81.40 189	80.63 199	73.78 196	72.85 171	70.90 156	54.89 186	62.17 154	57.42 185	62.92 190	76.80 197	73.98 201	86.74 195	80.87 193

testgi		71.92 190	74.20 185	69.27 194	84.58 154	83.06 185	73.40 197	74.39 165	64.04 189	46.17 202	68.90 123	57.15 186	48.89 203	84.07 169	83.08 173	88.18 187	79.09 198

v1921920		78.57 149	76.99 162	80.41 139	82.93 174	89.63 134	86.38 125	77.14 149	68.31 171	61.80 164	58.89 176	56.79 187	80.19 108	86.50 139	86.05 148	94.02 118	92.76 101

NR-MVSNet		80.25 126	79.98 130	80.56 136	85.20 145	90.94 106	85.65 133	83.58 76	75.74 123	61.36 168	65.30 140	56.75 188	72.38 163	88.46 111	88.80 110	95.16 70	93.87 80

EU-MVSNet		69.98 193	72.30 190	67.28 197	75.67 204	79.39 201	73.12 198	69.94 183	63.59 190	42.80 206	62.93 152	56.71 189	55.07 197	79.13 193	78.55 189	87.06 193	85.82 174

MVS-HIRNet		68.83 194	66.39 198	71.68 190	77.58 198	75.52 205	66.45 205	65.05 200	62.16 193	62.84 153	44.76 204	56.60 190	71.96 165	78.04 195	75.06 199	86.18 198	72.56 204

v1240		78.15 151	76.53 165	80.04 140	82.85 177	89.48 137	85.61 135	76.77 153	67.05 174	61.18 171	58.37 178	56.16 191	79.89 113	86.11 143	86.08 146	93.92 122	92.47 114

v7n		77.22 159	76.23 169	78.38 156	81.89 185	89.10 145	82.24 164	76.36 155	65.96 181	61.21 170	56.56 182	55.79 192	75.07 149	86.55 136	86.68 134	93.52 137	92.95 95

PEN-MVS		76.02 174	76.07 170	75.95 173	83.17 170	87.97 154	79.65 177	80.07 121	66.57 177	51.45 194	60.94 161	55.47 193	66.81 183	82.72 176	86.80 132	94.59 95	92.03 120

CP-MVSNet		76.36 171	76.41 167	76.32 170	82.73 179	88.64 149	79.39 180	79.62 124	67.21 173	53.70 188	60.72 163	55.22 194	67.91 179	83.52 172	86.34 142	94.55 98	93.19 90

DTE-MVSNet		75.14 181	75.44 180	74.80 180	83.18 169	87.19 161	78.25 188	80.11 118	66.05 179	48.31 199	60.88 162	54.67 195	64.54 188	82.57 178	86.17 144	94.43 106	90.53 140

test20.03		68.31 195	70.05 196	66.28 199	82.41 181	80.84 197	67.35 204	76.11 158	58.44 201	40.80 209	53.77 190	54.54 196	42.28 206	83.07 174	81.96 181	88.73 185	77.76 200

PS-CasMVS		75.90 176	75.86 175	75.96 172	82.59 180	88.46 152	79.23 183	79.56 126	66.00 180	52.77 190	59.48 171	54.35 197	67.14 182	83.37 173	86.23 143	94.47 103	93.10 92

SixPastTwentyTwo		76.02 174	75.72 176	76.36 169	83.38 166	87.54 157	75.50 193	76.22 156	65.50 184	57.05 184	70.64 108	53.97 198	74.54 152	80.96 184	82.12 179	91.44 163	89.35 146

tfpnnormal		77.46 158	74.86 183	80.49 137	86.34 131	88.92 147	84.33 147	81.26 104	61.39 195	61.70 165	51.99 194	53.66 199	74.84 150	88.63 108	87.38 124	94.50 100	92.08 117

Anonymous20231206		70.80 191	70.59 195	71.04 191	81.60 187	82.49 192	74.64 195	75.87 160	64.17 188	49.27 198	44.85 203	53.59 200	54.68 198	83.07 174	82.34 178	90.17 176	83.65 181

LTVRE_ROB	74.41 16	75.78 178	74.72 184	77.02 164	85.88 133	89.22 140	82.44 160	77.17 148	50.57 208	45.45 203	65.44 138	52.29 201	81.25 90	85.50 151	87.42 123	89.94 179	92.62 105
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
N_pmnet		66.85 196	66.63 197	67.11 198	78.73 195	74.66 206	70.53 201	71.07 176	66.46 178	46.54 201	51.68 195	51.91 202	55.48 196	74.68 201	72.38 202	80.29 207	74.65 203

gm-plane-assit		70.29 192	70.65 194	69.88 193	85.03 148	78.50 203	58.41 210	65.47 198	50.39 209	40.88 208	49.60 196	50.11 203	75.14 148	91.43 65	89.78 88	94.32 110	84.73 179

TinyColmap		76.73 162	73.95 186	79.96 141	85.16 147	85.64 173	82.34 161	78.19 139	70.63 160	62.06 160	60.69 164	49.61 204	80.81 95	85.12 159	83.69 170	91.22 169	82.27 186

MIMVSNet1		65.00 198	66.24 199	63.55 201	58.41 212	80.01 200	69.00 203	74.03 167	55.81 204	41.88 207	36.81 208	49.48 205	47.89 204	81.32 183	82.40 177	90.08 178	77.88 199

pmmvs-eth3d		74.32 185	71.96 191	77.08 163	77.33 199	82.71 189	78.41 185	76.02 159	66.65 176	65.98 133	54.23 189	49.02 206	73.14 162	82.37 180	82.69 176	91.61 162	86.05 172

PM-MVS		74.17 186	73.10 187	75.41 175	76.07 202	82.53 191	77.56 189	71.69 174	71.04 154	61.92 162	61.23 159	47.30 207	74.82 151	81.78 182	79.80 183	90.42 174	88.05 157

new-patchmatchnet		63.80 199	63.31 201	64.37 200	76.49 200	75.99 204	63.73 207	70.99 177	57.27 202	43.08 205	45.86 201	43.80 208	45.13 205	73.20 202	70.68 205	86.80 194	76.34 202

new_pmnet		59.28 202	61.47 204	56.73 204	61.66 210	68.29 210	59.57 209	54.91 207	60.83 196	34.38 212	44.66 205	43.65 209	49.90 202	71.66 203	71.56 204	79.94 208	69.67 205

tmp_tt				32.73 209	43.96 216	21.15 218	26.71 215	8.99 214	65.67 183	51.39 195	56.01 183	42.64 210	11.76 213	56.60 208	50.81 210	53.55 213

FPMVS		63.63 200	60.08 205	67.78 196	80.01 192	71.50 208	72.88 199	69.41 186	61.82 194	53.11 189	45.12 202	42.11 211	50.86 201	66.69 205	63.84 206	80.41 206	69.46 206

pmmvs3		61.89 201	61.74 203	62.06 202	64.30 208	70.83 209	64.22 206	52.14 210	48.78 210	44.47 204	41.67 206	41.70 212	63.03 189	76.06 199	76.02 195	84.18 203	77.14 201

PMVS	50.48 18	55.81 204	51.93 206	60.33 203	72.90 206	49.34 212	48.78 211	69.51 185	43.49 211	54.25 187	36.26 209	41.04 213	39.71 208	65.07 206	60.70 207	76.85 209	67.58 207
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MDA-MVSNet-bldmvs		66.22 197	64.49 200	68.24 195	61.67 209	82.11 195	70.07 202	76.16 157	59.14 200	47.94 200	54.35 188	35.82 214	67.33 181	64.94 207	75.68 196	86.30 197	79.36 196

DeepMVS_CX						48.31 214	48.03 212	26.08 213	56.42 203	25.77 214	47.51 198	31.31 215	51.30 200	48.49 210		53.61 212	61.52 208

PMMVS2		41.68 206	44.74 208	38.10 206	46.97 215	52.32 211	40.63 214	48.08 211	35.51 212	7.36 218	26.86 210	24.64 216	16.72 212	55.24 209	59.03 208	68.85 211	59.59 209

ambc			61.92 202		70.98 207	73.54 207	63.64 208		60.06 197	52.23 193	38.44 207	19.17 217	57.12 194	82.33 181	75.03 200	83.21 205	84.89 176

Gipuma		49.17 205	47.05 207	51.65 205	59.67 211	48.39 213	41.98 213	63.47 203	55.64 205	33.33 213	14.90 211	13.78 218	41.34 207	69.31 204	72.30 203	70.11 210	55.00 210
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		30.49 209	25.44 211	36.39 208	51.47 213	29.89 217	20.17 217	54.00 209	26.49 213	12.02 217	13.94 214	8.84 219	34.37 209	25.04 213	34.37 212	46.29 215	39.53 213

E-PMN		31.40 207	26.80 210	36.78 207	51.39 214	29.96 216	20.20 216	54.17 208	25.93 214	12.75 216	14.73 212	8.58 220	34.10 210	27.36 212	37.83 211	48.07 214	43.18 212

MVE	30.17 19	30.88 208	33.52 209	27.80 211	23.78 217	39.16 215	18.69 218	46.90 212	21.88 215	15.39 215	14.37 213	7.31 221	24.41 211	41.63 211	56.22 209	37.64 216	54.07 211
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		1.03 210	1.63 212	0.34 212	0.09 219	0.35 219	0.61 220	0.16 215	1.49 216	0.10 220	3.15 215	0.15 222	0.86 215	1.32 214	1.18 213	0.20 217	3.76 215

test123		0.87 211	1.40 213	0.25 213	0.03 220	0.25 220	0.35 221	0.08 217	1.21 217	0.05 221	2.84 216	0.03 223	0.89 214	0.43 215	1.16 214	0.13 218	3.87 214

uanet_test		0.00 212	0.00 214	0.00 214	0.00 221	0.00 221	0.00 222	0.00 218	0.00 218	0.00 222	0.00 217	0.00 224	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

sosnet-low-res		0.00 212	0.00 214	0.00 214	0.00 221	0.00 221	0.00 222	0.00 218	0.00 218	0.00 222	0.00 217	0.00 224	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

sosnet		0.00 212	0.00 214	0.00 214	0.00 221	0.00 221	0.00 222	0.00 218	0.00 218	0.00 222	0.00 217	0.00 224	0.00 217	0.00 216	0.00 215	0.00 219	0.00 216

RE-MVS-def										56.08 185

our_test_3					81.81 186	83.96 184	76.61 190

Patchmatch-RL test							8.55 219

NP-MVS									87.47 53

Patchmtry						85.54 175	82.30 162	68.23 188		65.37 138

High-resolution multi-view benchmark