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 8	98.57 2	95.63 2	96.98 10	99.73 1	97.67 1	97.26 10	95.86 22	99.04 15	99.89 5

MSP-MVS		97.74 2	98.32 1	97.06 8	98.66 15	99.35 7	98.66 8	94.75 14	98.22 5	93.60 6	97.99 1	98.58 8	97.41 4	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 9	98.24 4	94.66 3	96.35 16	99.20 4	97.63 2	97.20 12	95.68 23	99.08 13	99.84 7

DPE-MVS		97.69 4	98.16 3	97.14 6	99.01 5	99.52 5	99.12 2	95.38 3	98.00 8	93.31 10	97.71 2	99.61 3	96.94 5	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 5	98.39 3	95.83 1	94.40 29	99.70 2	96.79 6	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 9	99.14 1	99.55 4	98.67 7	95.32 4	97.91 9	92.55 13	97.11 7	97.23 13	97.49 3	98.16 3	97.05 5	99.04 15	99.55 19

APDe-MVS		97.31 7	97.51 12	97.08 7	98.95 10	99.29 12	98.58 10	95.11 5	97.69 15	94.16 4	96.91 11	96.81 17	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 2	99.20 14	99.05 3	95.55 1	97.39 18	93.56 7	97.48 4	96.71 19	96.75 7	95.73 32	94.40 44	98.98 20	99.33 25

NCCC		97.01 9	97.74 8	96.16 12	99.02 4	99.35 7	98.63 9	95.04 10	97.84 12	88.95 26	96.83 13	97.02 16	96.39 15	97.44 7	96.51 9	98.90 28	99.16 42

SMA-MVS		96.96 10	97.65 11	96.15 13	98.98 6	99.31 11	97.91 18	94.68 16	97.52 16	90.59 20	94.54 28	99.20 4	96.54 12	97.29 9	96.48 10	98.22 64	99.19 38
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 20	98.98 6	99.44 6	98.04 14	95.04 10	98.10 6	86.55 33	97.65 3	97.56 11	95.60 24	97.67 6	96.45 11	99.43 1	99.61 18

HPM-MVS++		96.91 12	97.70 9	96.00 15	98.97 9	99.16 17	97.82 21	94.81 13	98.04 7	89.61 23	96.56 15	98.60 7	96.39 15	97.09 14	95.22 31	98.39 58	99.22 34

SD-MVS		96.87 13	97.69 10	95.92 16	96.38 49	99.25 13	97.76 22	94.75 14	97.72 13	92.46 15	95.94 17	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 10	98.76 14	98.87 26	98.42 11	94.93 12	97.70 14	91.83 16	95.52 20	95.94 24	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 18	96.12 53	98.97 23	98.00 15	94.13 21	97.89 10	91.49 17	95.11 25	97.52 12	96.26 19	96.27 27	94.07 55	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 24	98.40 23	99.11 18	97.93 17	93.62 25	96.28 31	87.45 29	97.05 9	96.00 23	94.23 32	96.83 19	95.97 17	98.40 57	99.27 31
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 17	96.41 23	95.72 19	98.58 18	98.84 27	97.95 16	93.08 29	96.96 24	90.24 21	96.60 14	94.40 32	96.52 13	95.13 44	94.33 46	97.93 85	98.59 67

zzz-MVS		95.87 18	95.63 30	96.15 13	98.60 17	98.83 28	97.89 19	93.65 24	96.24 32	93.08 11	91.13 36	95.46 29	95.72 23	95.64 34	93.67 63	97.97 82	98.46 74

ACMMP_NAP		95.81 19	96.50 22	95.01 24	98.79 13	99.17 16	97.52 27	94.20 20	96.19 33	85.71 37	93.80 32	96.20 22	95.89 20	96.62 22	94.98 37	97.93 85	98.52 70

train_agg		95.72 20	97.37 13	93.80 30	97.82 32	98.92 24	97.84 20	93.50 26	96.86 26	81.35 56	97.10 8	97.71 9	94.19 33	96.02 28	95.37 30	98.07 72	99.64 16

ACMMPR		95.59 21	95.89 25	95.25 22	98.41 22	98.74 30	97.69 25	92.73 33	96.88 25	88.95 26	95.33 22	92.91 39	95.79 21	94.73 54	94.33 46	97.92 87	98.32 80

DeepC-MVS_fast	91.53 1	95.57 22	95.67 28	95.45 21	98.57 19	99.00 22	97.76 22	94.41 18	97.06 21	86.84 32	86.39 47	92.27 44	96.38 17	97.89 5	98.06 3	98.73 40	99.01 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		95.49 23	94.84 34	96.25 11	98.64 16	98.63 34	98.35 12	92.37 35	95.04 51	92.62 12	87.12 46	93.79 33	96.55 11	93.53 73	96.78 6	98.98 20	98.99 51

CP-MVS		95.43 24	95.67 28	95.14 23	98.24 28	98.60 35	97.45 28	92.80 31	95.98 36	89.21 25	95.22 23	93.60 34	95.43 25	94.37 61	93.22 74	97.68 95	98.72 58

DPM-MVS		95.36 25	95.84 26	94.82 26	96.70 45	98.49 45	99.27 1	95.09 7	96.71 27	83.87 45	86.34 49	96.44 21	95.06 27	98.35 1	98.82 1	98.89 29	95.69 134

MP-MVS		95.24 26	95.96 24	94.40 28	98.32 25	98.38 50	97.12 30	92.87 30	95.17 49	85.50 38	95.68 18	94.91 30	94.58 29	95.11 45	93.76 60	98.05 75	98.68 60
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 27	97.02 17	92.61 41	97.19 38	98.71 32	97.74 24	93.21 28	96.97 23	79.27 71	94.09 30	97.14 14	90.84 67	96.64 21	95.94 20	97.42 110	99.67 15

X-MVS		94.70 28	95.71 27	93.52 34	98.38 24	98.56 37	96.99 31	92.62 34	95.58 40	81.00 63	94.57 27	93.49 35	94.16 36	94.82 50	94.29 49	97.99 81	98.68 60

PGM-MVS		94.64 29	95.49 31	93.66 32	98.55 20	98.51 43	97.63 26	87.77 49	94.45 55	84.92 41	97.23 6	91.90 46	95.22 26	94.56 57	93.80 59	97.87 91	97.97 90

TSAR-MVS + GP.		94.59 30	96.60 21	92.25 42	90.25 94	98.17 57	96.22 37	86.53 55	97.49 17	87.26 30	95.21 24	97.06 15	94.07 38	94.34 63	94.20 51	99.18 5	99.71 14

xxxxxxxxxxxxxcwj		94.57 31	92.34 51	97.17 4	99.11 2	99.20 14	99.05 3	95.55 1	97.39 18	93.56 7	97.48 4	62.85 152	96.75 7	95.73 32	94.40 44	98.98 20	99.33 25

PHI-MVS		94.49 32	96.72 20	91.88 44	97.06 40	98.88 25	94.99 48	89.13 43	96.15 34	79.70 67	96.91 11	95.78 26	91.87 57	94.65 55	95.68 23	98.53 49	98.98 53

AdaColmap		94.28 33	92.94 46	95.84 17	98.32 25	98.33 52	96.06 39	94.62 17	96.29 30	91.22 18	89.89 40	85.50 75	96.38 17	91.85 102	90.89 89	98.44 53	97.81 93

DeepPCF-MVS	91.00 2	94.15 34	96.87 19	90.97 52	96.82 43	99.33 10	89.40 101	92.76 32	98.76 1	82.36 52	88.74 41	95.49 28	90.58 74	98.13 4	97.80 4	93.88 190	99.88 6

CPTT-MVS		94.11 35	93.99 39	94.25 29	96.58 46	97.66 65	97.31 29	91.94 36	94.84 52	88.72 28	92.51 33	93.04 38	95.78 22	91.51 105	89.97 106	95.15 179	98.37 77

EPNet		93.69 36	95.34 32	91.76 45	96.98 42	98.47 47	95.40 45	86.79 52	95.47 42	82.84 49	95.66 19	89.17 52	90.47 75	95.25 43	94.69 40	98.10 69	98.68 60
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 37	93.59 42	93.00 39	97.03 41	98.24 53	95.27 46	91.66 39	95.20 47	83.25 47	95.39 21	85.52 73	92.80 48	92.60 92	90.21 102	98.01 78	97.99 88
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 38	93.72 41	92.65 40	95.48 56	99.09 20	96.55 35	86.74 53	95.28 45	85.22 39	77.30 75	91.25 48	92.60 50	97.06 15	96.63 7	99.31 2	99.45 23

CDPH-MVS		93.22 39	95.08 33	91.04 51	97.57 35	98.49 45	96.74 33	89.35 42	95.19 48	73.57 101	90.26 38	91.59 47	90.68 71	95.09 47	96.15 14	98.31 63	98.81 56

CSCG		93.16 40	92.65 48	93.76 31	98.32 25	99.09 20	96.12 38	89.91 41	93.15 64	89.64 22	83.62 57	88.91 55	92.40 52	91.09 110	93.70 61	96.14 162	98.99 51

MVS_111021_LR		93.05 41	94.53 36	91.32 49	96.43 48	98.38 50	92.81 62	87.20 51	95.94 38	81.45 55	94.75 26	86.08 69	92.12 55	94.83 49	93.34 68	97.89 90	98.42 76

3Dnovator+	86.26 7	92.90 42	92.45 50	93.42 35	97.25 37	98.45 49	95.82 40	85.71 61	93.83 59	89.55 24	72.31 105	92.28 43	94.01 40	95.10 46	95.92 21	98.17 65	99.23 33

MVS_111021_HR		92.73 43	94.83 35	90.28 58	96.27 50	99.10 19	92.77 63	86.15 58	93.41 62	77.11 90	93.82 31	87.39 61	90.61 72	95.60 36	95.15 33	98.79 35	99.32 27

PLC	89.12 3	92.67 44	90.84 61	94.81 27	97.69 33	96.10 93	95.42 44	91.70 37	95.82 39	92.52 14	81.24 61	86.01 70	94.36 30	92.44 96	90.27 99	97.19 119	93.99 160
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 45	91.96 53	93.20 37	97.99 29	98.47 47	95.78 41	85.94 59	93.07 66	86.40 34	73.43 97	89.00 54	94.08 37	94.74 53	96.44 12	99.01 19	98.57 68

DeepC-MVS	88.77 4	92.39 46	91.74 55	93.14 38	96.21 51	98.55 40	96.30 36	93.84 22	93.06 67	81.09 61	74.69 90	85.20 79	93.48 43	95.41 39	96.13 15	97.92 87	99.18 39
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 47	91.88 54	92.25 42	96.51 47	97.94 59	93.18 59	88.97 45	96.53 28	84.47 43	80.79 63	87.85 57	93.25 46	92.48 95	91.81 82	97.12 120	95.73 133

MVSTER		91.91 48	93.43 45	90.14 59	89.81 101	92.32 132	94.53 51	81.32 90	96.00 35	84.77 42	85.41 54	92.39 42	91.32 59	96.41 23	94.01 57	99.11 8	97.45 102

MVS_0304		91.90 49	92.93 47	90.69 56	93.66 66	98.78 29	96.73 34	85.43 65	93.13 65	78.11 84	77.02 78	89.09 53	91.10 63	96.98 17	96.54 8	99.11 8	98.96 54

CS-MVS-test		91.76 50	93.47 43	89.76 62	94.64 61	98.22 55	88.13 110	81.58 87	97.02 22	82.47 51	85.49 53	85.41 77	93.28 45	95.33 41	93.61 64	98.45 52	99.22 34

QAPM		91.68 51	91.97 52	91.34 48	97.86 31	98.72 31	95.60 43	85.72 60	90.86 80	77.14 89	76.06 79	90.35 49	92.69 49	94.10 66	94.60 41	99.04 15	99.09 44

CS-MVS		91.55 52	92.49 49	90.45 57	94.00 64	97.91 61	91.17 82	81.40 89	95.22 46	83.51 46	82.37 59	82.29 85	94.07 38	96.36 26	94.03 56	98.56 47	99.22 34

CNLPA		91.53 53	89.74 73	93.63 33	96.75 44	97.63 67	91.16 83	91.70 37	96.38 29	90.82 19	69.66 116	85.52 73	93.76 41	90.44 116	91.14 88	97.55 104	97.40 103

ETV-MVS		91.51 54	94.06 38	88.54 71	89.39 106	97.52 68	89.48 98	80.88 93	97.09 20	79.41 69	87.87 42	86.18 68	92.95 47	95.94 30	94.33 46	99.13 7	99.52 21

DROMVSNet		91.25 55	93.45 44	88.68 69	88.90 112	96.18 92	91.66 71	76.70 124	95.57 41	82.00 53	84.18 55	89.28 51	94.17 35	95.64 34	94.19 52	98.68 42	99.14 43

DELS-MVS		91.09 56	90.56 69	91.71 46	95.82 54	98.59 36	95.74 42	86.68 54	85.86 108	85.12 40	72.71 100	81.36 88	88.06 95	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 57	90.71 63	91.30 50	96.14 52	97.66 65	94.80 49	89.00 44	94.74 54	77.42 88	80.22 64	86.70 64	92.27 53	91.65 104	90.17 104	98.15 68	93.83 164
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 58	90.66 65	90.82 54	94.75 59	98.54 41	91.30 79	86.53 55	95.43 43	85.75 35	78.66 70	70.67 125	87.60 96	96.37 24	95.08 35	98.98 20	99.90 2

PVSNet_Blended		90.74 58	90.66 65	90.82 54	94.75 59	98.54 41	91.30 79	86.53 55	95.43 43	85.75 35	78.66 70	70.67 125	87.60 96	96.37 24	95.08 35	98.98 20	99.90 2

CHOSEN 280x420		90.61 60	94.27 37	86.35 91	93.12 70	98.16 58	89.99 94	69.62 179	92.48 71	76.89 93	87.28 45	96.72 18	90.31 77	94.81 51	92.33 79	98.17 65	98.08 86

MAR-MVS		90.44 61	91.17 59	89.59 63	97.48 36	97.92 60	90.96 86	79.80 98	95.07 50	77.03 91	80.83 62	79.10 98	94.68 28	93.16 78	94.46 43	97.59 103	97.63 95
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 62	89.56 78	91.41 47	94.44 62	98.18 56	94.35 53	94.33 19	84.55 120	76.61 94	75.84 82	88.47 56	91.29 60	90.37 118	90.66 95	97.46 106	98.88 55
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
OpenMVS	83.41 11	89.84 63	88.89 84	90.95 53	97.63 34	98.51 43	94.64 50	85.47 64	88.14 94	78.39 81	65.06 129	85.42 76	91.04 65	93.06 81	93.70 61	98.53 49	98.37 77

EIA-MVS		89.82 64	91.48 57	87.89 80	89.16 108	97.31 70	88.99 102	80.92 92	94.29 56	77.65 86	82.16 60	79.77 96	91.90 56	94.61 56	93.03 76	98.70 41	99.21 37

canonicalmvs		89.62 65	89.87 72	89.33 65	90.47 89	97.02 76	93.46 58	79.67 101	92.45 72	81.05 62	82.84 58	73.00 114	93.71 42	90.38 117	94.85 38	97.65 99	98.54 69

TSAR-MVS + COLMAP		89.59 66	89.64 75	89.53 64	93.32 69	96.51 84	95.03 47	88.53 46	95.98 36	69.10 117	91.81 34	64.53 148	93.40 44	93.53 73	91.35 87	97.77 92	93.75 167

HQP-MVS		89.57 67	90.57 68	88.41 73	92.77 71	94.71 108	94.24 54	87.97 47	93.44 61	68.18 120	91.75 35	71.54 124	89.90 80	92.31 99	91.43 85	97.39 111	98.80 57

MVS_Test		89.02 68	90.20 70	87.64 82	89.83 100	97.05 75	92.30 65	77.59 120	92.89 68	75.01 99	77.36 74	76.10 108	92.27 53	95.30 42	95.42 28	98.83 33	97.30 107

CLD-MVS		88.99 69	88.07 87	90.07 60	89.61 103	94.94 105	93.82 57	85.70 62	92.73 70	82.73 50	79.97 65	69.59 128	90.44 76	90.32 119	89.93 108	98.10 69	99.04 47
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
baseline		88.91 70	89.94 71	87.70 81	89.44 105	96.74 82	91.62 73	77.92 117	93.79 60	78.76 76	77.55 73	78.46 101	89.38 86	92.26 100	92.52 78	99.10 10	98.23 81

PMMVS		88.56 71	91.22 58	85.47 99	90.04 96	95.60 101	86.62 126	78.49 112	93.86 58	70.62 112	90.00 39	80.08 94	91.64 58	92.36 97	89.80 112	95.40 174	96.84 116

test2506		88.38 72	88.02 89	88.80 68	91.55 80	97.78 62	90.87 88	83.36 72	84.51 121	83.06 48	74.13 93	76.93 105	85.39 106	94.34 63	93.33 70	98.60 43	95.10 149

baseline1		88.16 73	88.15 86	88.17 77	90.02 97	94.79 107	91.85 70	83.89 68	87.37 100	75.67 97	73.75 95	79.89 95	88.44 94	94.41 58	93.33 70	99.18 5	93.55 169

thisisatest0530		87.99 74	90.76 62	84.75 103	88.36 117	96.82 79	87.65 116	79.67 101	91.77 74	70.93 108	79.94 66	87.65 59	84.21 116	92.98 84	89.07 123	97.66 98	97.13 110

tttt0517		87.93 75	90.71 63	84.68 104	88.33 118	96.76 81	87.42 119	79.67 101	91.74 75	70.83 109	79.91 67	87.61 60	84.21 116	92.88 89	89.07 123	97.62 101	97.03 112

CANet_DTU		87.91 76	91.57 56	83.64 112	90.96 83	97.12 73	91.90 69	75.97 132	92.83 69	53.16 174	86.02 50	79.02 99	90.80 68	95.40 40	94.15 53	99.03 18	96.47 127

diffmvs		87.86 77	87.40 95	88.39 74	88.57 115	96.10 93	91.24 81	83.15 75	90.62 81	79.13 73	72.45 103	67.71 134	90.07 79	92.58 93	93.31 73	98.17 65	99.03 48

IS_MVSNet		87.83 78	90.66 65	84.53 105	90.08 95	96.79 80	88.16 109	79.89 97	85.44 110	72.20 103	75.50 86	87.14 62	80.21 144	95.53 37	95.22 31	96.65 136	99.02 49

EPP-MVSNet		87.72 79	89.74 73	85.37 100	89.11 109	95.57 102	86.31 127	79.44 104	85.83 109	75.73 96	77.23 76	90.05 50	84.78 112	91.22 108	90.25 100	96.83 127	98.04 87

ET-MVSNet_ETH3D		87.63 80	91.08 60	83.59 113	67.96 214	96.30 91	92.06 67	78.47 113	91.95 73	69.87 114	87.57 44	84.14 83	94.34 31	88.58 132	92.10 80	98.88 30	96.93 113

DI_MVS_plusplus_trai		87.63 80	87.13 97	88.22 76	88.61 114	95.92 97	94.09 56	81.41 88	87.00 103	78.38 82	59.70 148	80.52 92	89.08 89	94.37 61	93.34 68	97.73 93	99.05 46

casdiffmvs		87.59 82	86.69 101	88.64 70	89.06 110	96.32 90	90.18 91	83.21 74	87.74 98	80.20 66	67.99 120	68.34 132	90.79 69	93.83 69	94.08 54	98.41 56	98.50 72

PVSNet_Blended_VisFu		87.44 83	88.72 85	85.95 95	92.02 75	97.26 71	86.88 124	82.66 82	83.86 127	79.16 72	66.96 123	84.91 80	77.26 161	94.97 48	93.48 65	97.73 93	99.64 16

FMVSNet3		87.19 84	87.32 96	87.04 89	82.82 153	90.21 147	92.88 61	76.53 127	91.69 76	81.31 57	64.81 132	80.64 89	89.79 84	94.80 52	94.76 39	98.88 30	94.32 156

LS3D		87.19 84	85.48 108	89.18 66	94.96 58	95.47 103	92.02 68	93.36 27	88.69 92	67.01 121	70.56 112	72.10 119	92.47 51	89.96 122	89.93 108	95.25 176	91.68 178

ACMP	85.16 9	87.15 86	87.04 98	87.27 86	90.80 85	94.45 111	89.41 100	83.09 79	89.15 88	76.98 92	86.35 48	65.80 141	86.94 99	88.45 133	87.52 142	96.42 151	97.56 100
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UGNet		87.04 87	89.59 77	84.07 107	90.94 84	95.95 96	86.02 129	81.65 86	85.94 107	78.54 80	78.00 72	85.40 78	69.62 181	91.83 103	91.53 84	97.63 100	98.51 71
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 88	87.65 92	86.12 94	91.77 78	93.84 117	93.04 60	82.77 81	88.04 95	65.33 126	87.69 43	67.09 138	86.79 100	90.20 120	88.99 126	97.05 122	97.71 94

PatchMatch-RL		86.75 89	85.43 109	88.29 75	94.06 63	96.37 89	86.82 125	82.94 80	88.94 90	79.59 68	79.83 68	59.17 162	89.46 85	91.12 109	88.81 130	96.88 126	93.78 165

FA-MVS(training)		86.74 90	88.01 90	85.26 101	89.86 98	96.99 77	88.54 106	64.26 195	89.04 89	81.30 60	66.74 125	81.52 87	89.11 88	94.04 67	90.37 98	98.47 51	97.37 104

baseline2		86.51 91	89.35 81	83.19 115	85.70 139	94.88 106	85.75 134	77.13 122	89.87 85	70.65 111	79.03 69	79.14 97	81.51 137	93.70 70	90.22 101	98.38 59	98.60 66

thres100view900		86.48 92	85.08 111	88.12 78	90.54 86	96.90 78	92.39 64	84.82 66	84.16 125	71.65 104	70.86 109	60.49 157	91.23 62	93.65 71	90.19 103	98.10 69	99.32 27

ACMM	84.23 10	86.40 93	84.64 114	88.46 72	91.90 76	91.93 138	88.11 111	85.59 63	88.61 93	79.13 73	75.31 87	66.25 139	89.86 83	89.88 123	87.64 139	96.16 161	92.86 174
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		86.16 94	86.00 104	86.35 91	81.81 159	89.52 156	91.40 75	76.53 127	91.69 76	81.31 57	64.81 132	80.64 89	88.72 90	90.54 113	90.72 91	98.34 60	94.08 157

test1		86.16 94	86.00 104	86.35 91	81.81 159	89.52 156	91.40 75	76.53 127	91.69 76	81.31 57	64.81 132	80.64 89	88.72 90	90.54 113	90.72 91	98.34 60	94.08 157

tfpn200view9		86.07 96	84.76 113	87.61 83	90.54 86	96.39 86	91.35 78	83.15 75	84.16 125	71.65 104	70.86 109	60.49 157	90.91 66	92.89 86	89.34 115	98.05 75	99.17 40

DCV-MVSNet		85.90 97	85.88 106	85.93 96	87.86 123	88.37 173	89.45 99	77.46 121	87.33 101	77.51 87	76.06 79	75.76 110	88.48 93	87.40 141	88.89 129	94.80 185	97.37 104

Vis-MVSNet (Re-imp)		85.89 98	89.62 76	81.55 125	89.85 99	96.08 95	87.55 117	79.80 98	84.80 117	66.55 123	73.70 96	86.71 63	68.25 188	94.40 59	94.53 42	97.32 114	97.09 111

MSDG		85.81 99	82.29 138	89.93 61	95.52 55	92.61 127	91.51 74	91.46 40	85.12 114	78.56 78	63.25 138	69.01 130	85.31 109	88.45 133	88.23 133	97.21 118	89.33 189

thres200		85.80 100	84.38 115	87.46 84	90.51 88	96.39 86	91.64 72	83.15 75	81.59 135	71.54 106	70.24 113	60.41 159	89.88 81	92.89 86	89.85 111	98.06 73	99.26 32

ECVR-MVS		85.74 101	83.80 123	88.00 79	91.55 80	97.78 62	90.87 88	83.36 72	84.51 121	78.21 83	58.65 153	62.75 153	85.39 106	94.34 63	93.33 70	98.60 43	95.25 143

OPM-MVS		85.69 102	82.79 131	89.06 67	93.42 67	94.21 115	94.21 55	87.61 50	72.68 160	70.79 110	71.09 107	67.27 137	90.74 70	91.29 107	89.05 125	97.61 102	93.94 162
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres400		85.59 103	84.08 118	87.36 85	90.45 90	96.60 83	90.95 87	83.67 70	80.99 138	71.17 107	69.08 118	60.25 160	89.88 81	93.14 79	89.34 115	98.02 77	99.17 40

CostFormer		85.47 104	86.98 99	83.71 110	88.70 113	94.02 116	88.07 112	62.72 197	89.78 86	78.68 77	72.69 101	78.37 102	87.35 98	85.96 154	89.32 119	96.73 133	98.72 58

test1111		85.17 105	83.46 126	87.17 87	91.36 82	97.75 64	90.06 93	83.44 71	83.41 129	75.25 98	58.08 156	62.19 155	84.39 115	94.39 60	93.38 67	98.54 48	95.00 151

thres600view7		85.14 106	83.58 125	86.96 90	90.37 93	96.39 86	90.33 90	83.15 75	80.46 139	70.60 113	67.96 121	60.04 161	89.22 87	92.89 86	88.28 132	98.06 73	99.08 45

test-LLR		85.11 107	89.49 79	80.00 134	85.32 143	94.49 109	82.27 164	74.18 142	87.83 96	56.70 152	75.55 84	86.26 65	82.75 129	93.06 81	90.60 96	98.77 37	98.65 64

FMVSNet2		84.89 108	84.02 120	85.91 97	81.81 159	89.52 156	91.40 75	75.79 133	84.45 123	79.39 70	58.75 151	74.35 112	88.72 90	93.51 75	93.46 66	98.34 60	94.08 157

FC-MVSNet-train		84.88 109	84.08 118	85.82 98	89.21 107	91.74 139	85.87 130	81.20 91	81.71 134	74.66 100	73.38 98	64.99 145	86.60 101	90.75 111	88.08 134	97.36 112	97.90 91

EPNet_dtu		84.87 110	89.01 82	80.05 133	95.25 57	92.88 125	88.84 104	84.11 67	91.69 76	49.28 190	85.69 51	78.95 100	65.39 193	92.22 101	91.66 83	97.43 109	89.95 185
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 111	85.71 107	83.73 109	87.94 122	95.76 98	90.08 92	73.45 149	85.12 114	62.66 135	72.39 104	64.97 146	90.59 73	92.95 85	90.69 94	97.67 97	98.12 83

UA-Net		84.69 112	87.64 93	81.25 127	90.38 92	95.67 99	87.33 120	79.41 105	72.07 164	66.48 124	75.09 88	92.48 41	66.88 189	94.03 68	94.25 50	97.01 125	89.88 186

TESTMET0.1,1		84.62 113	89.49 79	78.94 143	82.18 156	94.49 109	82.27 164	70.94 169	87.83 96	56.70 152	75.55 84	86.26 65	82.75 129	93.06 81	90.60 96	98.77 37	98.65 64

CHOSEN 1792x2688		84.59 114	84.30 117	84.93 102	93.71 65	98.23 54	89.91 95	77.96 116	84.81 116	65.93 125	45.19 198	71.76 123	83.13 127	95.46 38	95.13 34	98.94 25	99.53 20

Anonymous20231211		84.23 115	81.71 143	87.17 87	87.38 130	93.59 120	88.95 103	82.14 84	83.82 128	78.56 78	48.09 191	73.89 113	91.25 61	86.38 148	88.06 136	94.74 186	98.14 82

MDTV_nov1_ep13		84.17 116	88.03 88	79.66 136	86.00 137	94.41 112	85.05 136	66.01 191	90.36 82	64.34 131	77.13 77	84.56 81	82.71 131	87.12 145	88.92 127	93.84 192	93.69 168

test-mter		84.06 117	89.00 83	78.29 148	81.92 157	94.23 114	81.07 174	70.38 173	87.12 102	56.10 161	74.75 89	85.80 71	81.81 136	92.52 94	90.10 105	98.43 54	98.49 73

IB-MVS	79.58 12	83.83 118	84.81 112	82.68 117	91.85 77	97.35 69	75.75 193	82.57 83	86.55 105	84.01 44	70.90 108	65.43 143	63.18 199	84.19 168	89.92 110	98.74 39	99.31 29
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		83.71 119	86.76 100	80.16 132	89.72 102	95.64 100	84.68 137	59.73 202	89.61 87	62.67 134	72.65 102	81.80 86	86.22 103	86.23 150	88.03 137	97.96 83	93.35 170

HyFIR lowres test		83.43 120	82.94 129	84.01 108	93.41 68	97.10 74	87.21 121	74.04 144	80.15 141	64.98 127	41.09 206	76.61 107	86.51 102	93.31 76	93.01 77	97.91 89	99.30 30

PatchmatchNet		83.28 121	87.57 94	78.29 148	87.46 128	94.95 104	83.36 146	59.43 205	90.20 84	58.10 147	74.29 92	86.20 67	84.13 118	85.27 160	87.39 143	97.25 117	94.67 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 122	87.76 91	78.00 153	87.45 129	92.20 133	82.63 160	58.42 207	90.30 83	58.23 145	75.74 83	87.75 58	83.97 121	86.10 153	87.64 139	97.30 115	94.62 155

GeoE		83.17 123	82.86 130	83.53 114	87.24 131	93.78 118	87.94 113	72.75 154	82.19 132	69.76 115	60.54 145	65.95 140	86.01 104	89.41 127	89.72 113	97.47 105	98.43 75

CDS-MVSNet		83.13 124	83.73 124	82.43 123	84.52 148	92.92 124	88.26 108	77.67 119	72.08 163	69.08 118	66.96 123	74.66 111	78.61 150	90.70 112	91.96 81	96.46 150	96.86 115
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 125	81.86 140	84.13 106	88.25 119	88.32 174	87.67 115	80.86 94	84.78 118	76.57 95	85.56 52	76.00 109	84.61 113	78.20 204	76.52 207	86.81 213	83.63 206

Vis-MVSNet		82.88 126	86.04 103	79.20 141	87.77 126	96.42 85	86.10 128	76.70 124	74.82 154	61.38 137	70.70 111	77.91 103	64.83 195	93.22 77	93.19 75	98.43 54	96.01 130
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 127	82.64 134	82.62 119	87.81 125	92.81 126	84.39 138	61.96 198	86.43 106	81.63 54	69.72 115	67.60 136	84.42 114	82.51 182	83.90 181	95.52 170	95.50 141

IterMVS-LS		82.62 128	82.75 133	82.48 120	87.09 132	87.48 188	87.19 122	72.85 152	79.09 142	66.63 122	65.22 127	72.14 118	84.06 120	88.33 136	91.39 86	97.03 124	95.60 140
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 129	82.51 136	82.72 116	85.49 142	93.06 123	87.17 123	71.39 166	84.18 124	64.59 129	63.03 139	58.89 163	90.22 78	91.39 106	90.83 90	97.44 107	96.21 129

tpm cat1		82.39 130	82.32 137	82.47 121	88.13 120	92.42 131	87.43 118	62.79 196	85.30 111	78.05 85	60.14 146	72.10 119	83.20 126	82.26 185	85.67 160	95.23 177	98.35 79

MS-PatchMatch		82.16 131	82.18 139	82.12 124	91.65 79	93.50 121	89.51 97	71.95 160	81.48 136	64.45 130	59.58 150	77.54 104	77.23 162	89.88 123	85.62 161	97.94 84	87.68 193

tpmrst		81.71 132	83.87 122	79.20 141	89.01 111	93.67 119	84.22 139	60.14 200	87.45 99	59.49 141	64.97 130	71.86 122	85.30 110	84.72 164	86.30 151	97.04 123	98.09 85

RPMNet		81.47 133	86.24 102	75.90 171	86.72 133	92.12 135	82.82 158	55.76 213	85.21 112	53.73 172	63.45 136	83.16 84	80.13 145	92.34 98	89.52 114	96.23 159	97.90 91

CR-MVSNet		81.44 134	85.29 110	76.94 162	86.53 134	92.12 135	83.86 140	58.37 208	85.21 112	56.28 156	59.60 149	80.39 93	80.50 142	92.77 90	89.32 119	96.12 163	97.59 98

Effi-MVS+-dtu		81.18 135	82.77 132	79.33 139	84.70 147	92.54 129	85.81 131	71.55 164	78.84 143	57.06 151	71.98 106	63.77 150	85.09 111	88.94 129	87.62 141	91.79 205	95.68 135

test0.0.03 1		80.99 136	84.37 116	77.05 160	85.32 143	89.79 152	78.43 184	74.18 142	84.78 118	57.98 150	76.06 79	72.88 115	69.14 185	88.02 138	87.70 138	97.27 116	91.37 179

Fast-Effi-MVS+-dtu		80.57 137	83.44 127	77.22 158	83.98 151	91.52 141	85.78 133	64.54 194	80.38 140	50.28 186	74.06 94	62.89 151	82.00 135	89.10 128	88.91 128	96.75 131	97.21 109

FMVSNet5		80.56 138	82.53 135	78.26 150	73.80 209	81.52 207	82.26 166	68.36 184	88.85 91	64.21 132	69.09 117	84.38 82	83.49 125	87.13 144	86.76 148	97.44 107	79.95 209

ADS-MVSNet		80.25 139	82.96 128	77.08 159	87.86 123	92.60 128	81.82 171	56.19 212	86.95 104	56.16 159	68.19 119	72.42 117	83.70 124	82.05 186	85.45 166	96.75 131	93.08 173

FMVSNet1		80.18 140	78.07 154	82.65 118	78.55 183	87.57 187	88.41 107	73.93 145	70.16 169	73.57 101	49.80 181	64.45 149	85.35 108	90.54 113	90.72 91	96.10 164	93.21 171

USDC		80.10 141	79.33 150	81.00 129	86.36 135	91.71 140	88.74 105	75.77 134	81.90 133	54.90 166	67.67 122	52.05 175	83.94 122	88.44 135	86.25 152	96.31 154	87.28 197

COLMAP_ROB	75.69 15	79.47 142	76.90 161	82.46 122	92.20 72	90.53 143	85.30 135	83.69 69	78.27 146	61.47 136	58.26 154	62.75 153	78.28 153	82.41 183	82.13 194	93.83 194	83.98 205
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_part1		79.37 143	75.64 166	83.71 110	86.18 136	87.74 181	87.84 114	75.69 136	66.33 186	78.93 75	45.92 196	64.85 147	82.44 132	83.08 180	85.69 159	91.17 206	95.90 132

pmmvs4		79.32 144	77.78 156	81.11 128	80.18 168	88.96 168	83.39 144	76.07 130	81.27 137	69.35 116	58.66 152	51.19 178	82.01 134	87.16 143	84.39 178	95.66 168	92.82 175

PatchT		79.28 145	83.88 121	73.93 180	85.54 141	90.95 142	66.14 210	56.53 211	83.21 130	56.28 156	56.50 158	76.80 106	80.50 142	92.77 90	89.32 119	98.57 46	97.59 98

ACMH	78.51 14	79.27 146	78.08 153	80.65 130	89.52 104	90.40 144	80.45 176	79.77 100	69.54 174	54.85 167	64.83 131	56.16 169	83.94 122	84.58 166	86.01 156	95.41 173	95.03 150
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 147	78.95 152	79.56 137	81.89 158	92.52 130	82.97 153	73.70 146	67.27 180	64.97 128	61.66 144	65.06 144	78.61 150	87.12 145	88.07 135	95.23 177	90.95 181

ACMH+	79.09 13	79.12 148	77.22 160	81.35 126	88.50 116	90.36 145	82.14 168	79.38 107	72.78 159	58.59 142	62.31 143	56.44 168	84.10 119	82.03 187	84.05 179	95.40 174	92.55 176

UniMVSNet_NR-MVSNet		78.89 149	78.04 155	79.88 135	79.40 174	89.70 153	82.92 155	80.17 95	76.37 152	58.56 143	57.10 157	54.92 171	81.44 138	83.51 173	87.12 145	96.76 130	97.60 96

tpm		78.87 150	81.33 146	76.00 169	85.57 140	90.19 148	82.81 159	59.66 203	78.35 145	51.40 181	66.30 126	67.92 133	80.94 140	83.28 176	85.73 157	95.65 169	97.56 100

GA-MVS		78.86 151	80.42 147	77.05 160	83.27 152	92.17 134	83.24 148	75.73 135	73.75 156	46.27 200	62.43 141	57.12 165	76.94 164	93.14 79	89.34 115	96.83 127	95.00 151

IterMVS		78.85 152	81.36 144	75.93 170	84.27 150	85.74 194	83.83 142	66.35 189	76.82 147	50.48 184	63.48 135	68.82 131	73.99 169	89.68 125	89.34 115	96.63 139	95.67 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 153	81.34 145	75.64 175	84.31 149	85.67 195	83.51 143	66.14 190	76.67 148	50.38 185	63.45 136	69.02 129	73.23 171	89.66 126	89.22 122	96.24 158	95.67 136

UniMVSNet (Re)		78.00 154	77.52 157	78.57 146	79.66 173	90.36 145	82.09 169	77.86 118	76.38 151	60.26 138	54.63 164	52.07 174	75.31 167	84.97 163	86.10 154	96.22 160	98.11 84

DU-MVS		77.98 155	76.71 162	79.46 138	78.68 180	89.26 162	82.92 155	79.06 109	76.52 149	58.56 143	54.89 162	48.35 192	81.44 138	83.16 178	87.21 144	96.08 165	97.60 96

FC-MVSNet-test		77.95 156	81.85 141	73.39 185	82.31 154	88.99 167	79.33 180	74.24 141	78.75 144	47.40 198	70.22 114	72.09 121	60.78 205	86.66 147	85.62 161	96.30 155	90.61 182

NR-MVSNet		77.21 157	76.41 163	78.14 152	80.18 168	89.26 162	83.38 145	79.06 109	76.52 149	56.59 154	54.89 162	45.32 202	72.89 173	85.39 159	86.12 153	96.71 134	97.36 106

thisisatest0515		77.13 158	79.36 149	74.52 177	79.79 172	89.65 154	73.54 198	73.69 147	74.10 155	58.14 146	62.79 140	60.57 156	66.49 191	88.08 137	85.16 171	95.49 172	95.15 147

gg-mvs-nofinetune		77.08 159	79.79 148	73.92 181	85.95 138	97.23 72	92.18 66	52.65 216	46.19 219	27.79 223	38.27 210	85.63 72	85.67 105	96.95 18	95.62 25	99.30 3	98.67 63

TranMVSNet+NR-MVSNet		77.02 160	75.76 165	78.49 147	78.46 186	88.24 175	83.03 152	79.97 96	73.49 158	54.73 168	54.00 167	48.74 187	78.15 155	82.36 184	86.90 147	96.59 141	96.55 121

CVMVSNet		76.86 161	79.09 151	74.26 178	85.29 145	89.44 159	79.91 179	78.47 113	68.94 177	44.45 205	62.35 142	69.70 127	64.50 196	85.82 155	87.03 146	92.94 200	90.33 183

Baseline_NR-MVSNet		76.71 162	74.56 173	79.23 140	78.68 180	84.15 203	82.45 162	78.87 111	75.83 153	60.05 139	47.92 192	50.18 184	79.06 149	83.16 178	83.86 182	96.26 156	96.80 117

v2v482		76.25 163	74.78 170	77.96 154	78.50 185	89.14 165	83.05 151	76.02 131	68.78 178	54.11 169	51.36 173	48.59 189	79.49 147	83.53 172	85.60 164	96.59 141	96.49 126

V42		76.21 164	75.04 169	77.58 155	78.68 180	89.33 161	82.93 154	74.64 139	69.84 171	56.13 160	50.42 178	50.93 179	76.30 166	83.32 174	84.89 175	96.83 127	96.54 122

v8		75.89 165	74.74 171	77.23 157	79.09 176	88.00 178	83.19 149	71.08 168	70.03 170	56.29 155	50.50 176	50.88 180	77.06 163	83.32 174	84.99 173	96.68 135	95.49 142

TinyColmap		75.75 166	73.19 184	78.74 145	84.82 146	87.69 183	81.59 172	74.62 140	71.81 165	54.01 170	55.79 161	44.42 207	82.89 128	84.61 165	83.76 183	94.50 187	84.22 204

MIMVSNet		75.71 167	77.26 158	73.90 182	70.93 210	88.71 171	79.98 178	57.67 210	73.58 157	58.08 149	53.93 168	58.56 164	79.41 148	90.04 121	89.97 106	97.34 113	86.04 198

UniMVSNet_ETH3D		75.63 168	71.59 193	80.35 131	81.03 163	89.90 151	83.25 147	76.58 126	60.08 202	64.19 133	42.89 205	45.01 203	82.14 133	80.20 197	86.75 149	94.90 182	96.29 128

pm-mvs1		75.61 169	74.19 175	77.26 156	80.16 170	88.79 169	81.49 173	75.49 138	59.49 204	58.09 148	48.32 189	55.53 170	72.35 174	88.61 131	85.48 165	95.99 166	93.12 172

v10		75.57 170	74.67 172	76.62 165	78.73 179	87.46 189	83.14 150	69.41 180	69.27 175	53.44 173	49.73 182	49.21 186	78.44 152	86.17 152	85.18 170	96.53 146	95.65 139

v1144		75.54 171	74.55 174	76.69 163	78.33 189	88.77 170	82.89 157	72.76 153	67.18 182	51.73 178	49.34 184	48.37 190	78.10 156	86.22 151	85.24 168	96.35 153	96.74 118

TDRefinement		75.54 171	73.22 182	78.25 151	87.65 127	89.65 154	85.81 131	79.28 108	71.14 167	56.06 162	52.17 171	51.96 176	68.74 187	81.60 188	80.58 196	91.94 203	85.45 199

pmmvs5		75.46 173	75.12 168	75.87 172	79.39 175	89.44 159	78.12 186	72.27 158	65.98 188	51.54 179	55.83 160	46.23 197	76.80 165	88.77 130	85.73 157	97.07 121	93.84 163

tfpnnormal		75.27 174	72.12 190	78.94 143	82.30 155	88.52 172	82.41 163	79.41 105	58.03 205	55.59 164	43.83 204	44.71 204	77.35 159	87.70 140	85.45 166	96.60 140	96.61 120

anonymousdsp		75.14 175	77.25 159	72.69 188	76.68 199	89.26 162	75.26 195	68.44 183	65.53 191	46.65 199	58.16 155	56.67 167	73.96 170	87.84 139	86.05 155	95.13 180	97.22 108

v148		74.98 176	73.52 180	76.69 163	78.84 178	89.02 166	78.78 182	76.82 123	67.22 181	59.61 140	49.18 185	47.94 194	70.57 180	80.76 192	83.99 180	95.52 170	96.52 124

v1192		74.96 177	73.92 176	76.17 166	77.76 192	88.19 177	82.54 161	71.94 161	66.84 183	50.07 188	48.10 190	46.14 198	78.28 153	86.30 149	85.23 169	96.41 152	96.67 119

v144192		74.76 178	73.64 177	76.06 168	77.58 193	88.23 176	81.87 170	71.63 163	66.03 187	51.08 182	48.63 188	46.77 196	77.59 158	84.53 167	84.76 176	96.64 138	96.54 122

v1921920		74.60 179	73.56 179	75.81 173	77.43 195	87.94 179	82.18 167	71.33 167	66.48 185	49.23 192	47.84 193	45.56 200	78.03 157	85.70 157	84.92 174	96.65 136	96.50 125

v1240		74.04 180	73.04 186	75.20 176	77.19 197	87.69 183	80.93 175	70.72 172	65.08 192	48.47 193	47.31 194	44.71 204	77.33 160	85.50 158	85.07 172	96.59 141	95.94 131

testgi		73.22 181	75.84 164	70.16 199	81.67 162	85.50 198	71.45 200	70.81 170	69.56 173	44.74 204	74.52 91	49.25 185	58.45 206	84.10 170	83.37 187	93.86 191	84.56 203

CP-MVSNet		73.19 182	72.37 188	74.15 179	77.54 194	86.77 192	76.34 189	72.05 159	65.66 190	51.47 180	50.49 177	43.66 208	70.90 176	80.93 191	83.40 186	96.59 141	95.66 138

WR-MVS		72.93 183	73.57 178	72.19 191	78.14 190	87.71 182	76.21 191	73.02 151	67.78 179	50.09 187	50.35 179	50.53 182	61.27 204	80.42 195	83.10 190	94.43 188	95.11 148

TransMVSNet (Re)		72.90 184	70.51 197	75.69 174	80.88 164	85.26 200	79.25 181	78.43 115	56.13 211	52.81 175	46.81 195	48.20 193	66.77 190	85.18 162	83.70 184	95.98 167	88.28 192

WR-MVS_H		72.69 185	72.80 187	72.56 190	77.94 191	87.83 180	75.26 195	71.53 165	64.75 193	52.19 177	49.83 180	48.62 188	61.96 202	81.12 190	82.44 192	96.50 147	95.00 151

SixPastTwentyTwo		72.65 186	73.22 182	71.98 194	78.40 187	87.64 185	70.09 203	70.37 174	66.49 184	47.60 196	65.09 128	45.94 199	73.09 172	78.94 199	78.66 202	92.33 201	89.82 187

LTVRE_ROB	71.82 16	72.62 187	71.77 191	73.62 183	80.74 165	87.59 186	80.42 177	70.37 174	49.73 215	37.12 217	59.76 147	42.52 213	80.92 141	83.20 177	85.61 163	92.13 202	93.95 161
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		72.37 188	71.47 195	73.43 184	77.32 196	86.43 193	75.99 192	71.94 161	63.37 196	49.24 191	49.07 186	42.42 214	69.60 182	80.59 194	83.18 189	96.48 149	95.23 145

MVS-HIRNet		72.32 189	73.45 181	71.00 197	80.58 166	89.97 149	68.51 207	55.28 214	70.89 168	52.27 176	39.09 208	57.11 166	75.02 168	85.76 156	86.33 150	94.36 189	85.00 201

PEN-MVS		72.24 190	71.30 196	73.33 186	77.08 198	85.57 196	76.75 187	72.52 156	63.89 195	48.12 194	50.79 174	43.09 211	69.03 186	78.54 201	83.46 185	96.50 147	93.76 166

v7n		72.11 191	71.66 192	72.63 189	75.26 204	86.85 190	76.74 188	68.77 182	62.70 199	49.40 189	45.92 196	43.51 209	70.63 179	84.16 169	83.21 188	94.99 181	95.25 143

EG-PatchMatch MVS		71.81 192	71.54 194	72.12 192	80.53 167	89.94 150	78.51 183	66.56 188	57.38 207	47.46 197	44.28 203	52.22 173	63.10 200	85.22 161	84.42 177	96.56 145	87.35 196

CMPMVS	54.54 17	71.74 193	67.94 202	76.16 167	90.41 91	93.25 122	78.32 185	75.60 137	59.81 203	53.95 171	44.64 201	51.22 177	70.70 177	74.59 210	75.88 208	88.01 210	76.23 212
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 194	73.08 185	69.97 200	75.22 205	86.81 191	73.98 197	59.61 204	69.75 172	48.01 195	54.21 166	53.06 172	69.19 184	78.50 202	80.43 197	93.84 192	88.79 190

pmnet_mix02		71.64 195	72.36 189	70.81 198	78.39 188	85.57 196	68.64 205	73.65 148	72.13 161	45.07 203	56.01 159	50.61 181	65.34 194	76.21 207	76.60 206	93.75 195	89.35 188

gm-plane-assit		71.33 196	75.18 167	66.83 203	79.06 177	75.57 214	48.05 221	60.33 199	48.28 216	34.67 221	44.34 202	67.70 135	79.78 146	97.25 11	96.21 13	99.10 10	96.92 114

DTE-MVSNet		71.19 197	70.45 198	72.06 193	76.61 200	84.59 202	75.61 194	72.32 157	63.12 198	45.70 202	50.72 175	43.02 212	65.89 192	77.53 206	82.23 193	96.26 156	91.93 177

pmmvs6		70.29 198	67.90 203	73.07 187	76.17 201	85.31 199	76.29 190	70.75 171	47.39 218	55.33 165	37.15 214	50.49 183	69.55 183	82.96 181	80.85 195	90.34 209	91.18 180

PM-MVS		70.17 199	69.42 200	71.04 196	70.82 211	81.26 209	71.25 201	67.80 185	69.16 176	51.04 183	53.15 170	34.93 218	72.19 175	80.30 196	76.95 205	93.16 199	90.21 184

pmmvs-eth3d		69.59 200	67.57 205	71.95 195	70.04 212	80.05 210	71.48 199	70.00 178	62.57 200	55.99 163	44.92 199	35.73 217	70.64 178	81.56 189	79.69 198	93.55 196	88.43 191

N_pmnet		68.54 201	67.83 204	69.38 201	75.77 202	81.90 206	66.21 209	72.53 155	65.91 189	46.09 201	44.67 200	45.48 201	63.82 198	74.66 209	77.39 204	91.87 204	84.77 202

Anonymous20231206		68.09 202	68.68 201	67.39 202	75.16 206	82.55 204	69.33 204	70.06 177	63.34 197	42.28 208	37.91 212	43.12 210	52.67 209	83.56 171	82.71 191	94.84 184	87.59 194

EU-MVSNet		68.07 203	70.25 199	65.52 204	74.68 208	81.30 208	68.53 206	70.31 176	62.40 201	37.43 216	54.62 165	48.36 191	51.34 210	78.32 203	79.27 199	90.84 207	87.47 195

GG-mvs-BLEND		65.67 204	93.78 40	32.89 217	0.47 227	99.35 7	96.92 32	0.22 226	93.28 63	0.51 228	84.07 56	92.50 40	0.62 225	93.59 72	93.86 58	98.59 45	99.79 10

test20.03		65.17 205	67.41 206	62.55 206	75.35 203	79.31 211	62.22 211	68.83 181	56.50 210	35.35 220	51.97 172	44.70 206	40.01 215	80.69 193	79.25 200	93.55 196	79.47 211

MDA-MVSNet-bldmvs		62.23 206	61.13 210	63.52 205	58.94 218	82.44 205	60.71 214	73.28 150	57.22 208	38.42 214	49.63 183	27.64 224	62.83 201	54.98 216	74.16 209	86.96 212	81.83 208

new_pmnet		61.60 207	62.68 208	60.35 209	63.02 215	74.93 215	60.97 213	58.86 206	64.21 194	35.38 219	39.51 207	39.89 215	57.37 207	72.78 211	72.56 211	86.49 214	74.85 214

new-patchmatchnet		60.74 208	59.78 212	61.87 207	69.52 213	76.67 213	57.99 217	65.78 192	52.63 213	38.47 213	38.08 211	32.92 221	48.88 212	68.50 212	69.87 212	90.56 208	79.75 210

pmmvs3		60.52 209	60.87 211	60.12 210	61.38 216	71.62 216	57.42 218	53.94 215	48.09 217	35.95 218	38.62 209	32.19 223	64.12 197	75.33 208	77.99 203	87.89 211	82.28 207

MIMVSNet1		60.51 210	61.43 209	59.44 211	48.75 221	77.21 212	60.98 212	66.84 187	52.09 214	38.74 212	29.29 217	39.40 216	48.08 213	77.60 205	78.87 201	93.22 198	75.56 213

test_method		60.40 211	66.30 207	53.52 213	37.48 225	64.10 220	55.56 219	42.45 221	71.79 166	41.87 209	33.74 215	46.80 195	61.71 203	79.18 198	73.33 210	82.01 216	95.17 146

FPMVS		56.54 212	52.82 214	60.87 208	74.90 207	67.58 219	67.69 208	65.38 193	57.86 206	41.51 210	37.83 213	34.19 219	41.21 214	55.88 215	53.09 217	74.55 219	63.31 217

PMVS	42.57 18	45.71 213	42.61 216	49.32 214	61.35 217	37.82 224	36.96 223	60.10 201	37.20 220	41.50 211	28.53 218	33.11 220	28.82 220	53.45 217	48.70 219	67.22 221	59.42 218
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 214	42.62 215	45.50 215	50.79 220	41.20 223	35.55 224	52.51 217	52.95 212	29.09 222	12.92 220	11.48 227	38.15 216	62.01 214	66.62 214	66.89 222	51.17 219
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 215	42.55 217	39.74 216	43.25 222	55.05 222	38.15 222	47.11 220	31.78 221	11.83 225	21.16 219	19.12 225	20.98 222	49.95 219	56.09 216	77.09 217	64.68 216

E-PMN		27.87 216	24.36 219	31.97 218	41.27 224	25.56 227	16.62 226	49.16 218	22.00 223	9.90 226	11.75 222	7.86 229	29.57 219	22.22 221	34.70 220	45.27 223	46.41 221

MVE	32.98 19	27.61 217	29.89 218	24.94 220	21.97 226	37.22 225	15.56 228	38.83 222	17.49 224	14.72 224	11.64 224	5.62 230	21.26 221	35.20 220	50.95 218	37.29 225	51.13 220
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		26.96 218	22.96 220	31.63 219	41.91 223	25.73 226	16.30 227	49.10 219	22.38 222	9.03 227	11.22 225	8.12 228	29.93 218	20.16 222	31.04 221	43.49 224	42.04 222

testmvs		5.16 219	8.14 221	1.69 221	0.36 228	1.65 228	3.02 229	0.66 224	7.17 225	0.50 229	12.58 221	0.69 231	4.67 223	5.42 223	5.65 222	0.92 226	23.86 224

test123		4.39 220	7.11 222	1.21 222	0.11 229	1.16 229	1.67 230	0.35 225	5.91 226	0.16 230	11.65 223	0.16 232	4.45 224	1.72 224	4.92 223	0.51 227	24.28 223

uanet_test		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 223	0.00 230	0.00 230	0.00 231	0.00 227	0.00 227	0.00 231	0.00 226	0.00 233	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										43.17 206

9.14												97.59 10

SR-MVS					98.52 21			93.70 23				96.63 20

Anonymous202405211			81.72 142		88.09 121	94.27 113	89.62 96	82.14 84	82.27 131		48.83 187	72.58 116	91.08 64	87.40 141	88.70 131	94.90 182	97.99 88

our_test_3					78.55 183	84.98 201	70.12 202

ambc			57.08 213		58.68 219	67.71 218	60.07 215		57.13 209	42.79 207	30.00 216	11.64 226	50.18 211	78.89 200	69.14 213	82.64 215	85.02 200

MTAPA										93.37 9		95.71 27

MTMP										93.84 5		94.86 31

Patchmatch-RL test							19.65 225

tmp_tt				57.89 212	79.94 171	59.29 221	52.84 220	36.65 223	94.77 53	68.22 119	72.96 99	65.62 142	33.65 217	66.20 213	58.02 215	76.06 218

XVS					92.16 73	98.56 37	91.04 84			81.00 63		93.49 35				98.00 79

X-MVStestdata					92.16 73	98.56 37	91.04 84			81.00 63		93.49 35				98.00 79

abl_6				93.25 36	97.12 39	98.71 32	94.40 52	87.81 48	97.86 11	87.19 31	91.07 37	95.80 25	94.18 34			98.78 36	99.36 24

mPP-MVS					97.95 30							92.24 45

NP-MVS									94.12 57

Patchmtry						92.08 137	83.86 140	58.37 208		56.28 156

DeepMVS_CX						70.68 217	59.61 216	67.36 186	72.12 162	38.41 215	53.88 169	32.44 222	55.15 208	50.88 218		74.35 220	68.42 215

High-resolution multi-view benchmark