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 11	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 14	99.89 5

MSP-MVS		97.74 2	98.32 1	97.06 7	98.66 14	99.35 6	98.66 7	94.75 13	98.22 4	93.60 5	97.99 1	98.58 7	97.41 3	98.24 2	95.95 18	99.27 4	99.91 1

DPE-MVS		97.69 3	98.16 3	97.14 5	99.01 5	99.52 4	99.12 2	95.38 3	98.00 7	93.31 9	97.71 2	99.61 3	96.94 4	96.99 15	95.45 26	99.09 12	99.81 8

DVP-MVS		97.61 4	97.87 6	97.30 2	98.94 10	99.60 1	98.21 12	95.11 5	98.39 3	95.83 1	94.40 28	99.70 2	96.79 5	97.16 12	95.95 18	98.92 26	99.90 2

CNVR-MVS		97.60 5	98.08 4	97.03 8	99.14 1	99.55 3	98.67 6	95.32 4	97.91 8	92.55 12	97.11 7	97.23 12	97.49 2	98.16 3	97.05 5	99.04 14	99.55 18

APDe-MVS		97.31 6	97.51 11	97.08 6	98.95 9	99.29 11	98.58 9	95.11 5	97.69 14	94.16 3	96.91 11	96.81 16	96.57 9	96.71 19	95.39 28	99.08 13	99.79 9

SF-MVS		97.17 7	97.18 14	97.17 3	99.11 2	99.20 13	99.05 3	95.55 1	97.39 17	93.56 6	97.48 4	96.71 18	96.75 6	95.73 31	94.40 43	98.98 19	99.33 24

NCCC		97.01 8	97.74 7	96.16 11	99.02 4	99.35 6	98.63 8	95.04 9	97.84 11	88.95 25	96.83 13	97.02 15	96.39 14	97.44 7	96.51 9	98.90 28	99.16 39

SMA-MVS		96.96 9	97.65 10	96.15 12	98.98 6	99.31 10	97.91 17	94.68 15	97.52 15	90.59 19	94.54 27	99.20 4	96.54 11	97.29 9	96.48 10	98.22 57	99.19 35
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 10	98.07 5	95.61 19	98.98 6	99.44 5	98.04 13	95.04 9	98.10 5	86.55 32	97.65 3	97.56 10	95.60 23	97.67 6	96.45 11	99.43 1	99.61 17

HPM-MVS++		96.91 11	97.70 8	96.00 14	98.97 8	99.16 16	97.82 20	94.81 12	98.04 6	89.61 22	96.56 15	98.60 6	96.39 14	97.09 13	95.22 30	98.39 51	99.22 33

SD-MVS		96.87 12	97.69 9	95.92 15	96.38 48	99.25 12	97.76 21	94.75 13	97.72 12	92.46 14	95.94 16	99.09 5	96.48 13	96.01 27	96.08 16	97.68 88	99.73 12
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 13	96.99 17	96.56 9	98.76 13	98.87 25	98.42 10	94.93 11	97.70 13	91.83 15	95.52 19	95.94 23	96.63 8	95.94 28	95.47 25	98.80 34	99.47 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		96.50 14	97.08 15	95.82 17	96.12 52	98.97 22	98.00 14	94.13 20	97.89 9	91.49 16	95.11 24	97.52 11	96.26 18	96.27 25	94.07 53	98.91 27	99.74 11
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 15	97.22 13	95.01 23	98.40 22	99.11 17	97.93 16	93.62 24	96.28 29	87.45 28	97.05 9	96.00 22	94.23 31	96.83 18	95.97 17	98.40 50	99.27 30
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		96.09 16	96.41 22	95.72 18	98.58 17	98.84 26	97.95 15	93.08 28	96.96 22	90.24 20	96.60 14	94.40 31	96.52 12	95.13 41	94.33 45	97.93 78	98.59 64

zzz-MVS		95.87 17	95.63 29	96.15 12	98.60 16	98.83 27	97.89 18	93.65 23	96.24 30	93.08 10	91.13 35	95.46 28	95.72 22	95.64 33	93.67 61	97.97 75	98.46 71

ACMMP_NAP		95.81 18	96.50 21	95.01 23	98.79 12	99.17 15	97.52 26	94.20 19	96.19 31	85.71 36	93.80 31	96.20 21	95.89 19	96.62 21	94.98 36	97.93 78	98.52 67

train_agg		95.72 19	97.37 12	93.80 29	97.82 31	98.92 23	97.84 19	93.50 25	96.86 24	81.35 51	97.10 8	97.71 8	94.19 32	96.02 26	95.37 29	98.07 65	99.64 15

ACMMPR		95.59 20	95.89 24	95.25 21	98.41 21	98.74 29	97.69 24	92.73 32	96.88 23	88.95 25	95.33 21	92.91 38	95.79 20	94.73 51	94.33 45	97.92 80	98.32 76

DeepC-MVS_fast	91.53 1	95.57 21	95.67 27	95.45 20	98.57 18	99.00 21	97.76 21	94.41 17	97.06 20	86.84 31	86.39 47	92.27 43	96.38 16	97.89 5	98.06 3	98.73 40	99.01 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		95.49 22	94.84 33	96.25 10	98.64 15	98.63 33	98.35 11	92.37 34	95.04 48	92.62 11	87.12 46	93.79 32	96.55 10	93.53 66	96.78 6	98.98 19	98.99 48

CP-MVS		95.43 23	95.67 27	95.14 22	98.24 27	98.60 34	97.45 27	92.80 30	95.98 34	89.21 24	95.22 22	93.60 33	95.43 24	94.37 57	93.22 68	97.68 88	98.72 55

DPM-MVS		95.36 24	95.84 25	94.82 25	96.70 44	98.49 44	99.27 1	95.09 7	96.71 25	83.87 44	86.34 49	96.44 20	95.06 26	98.35 1	98.82 1	98.89 29	95.69 129

MP-MVS		95.24 25	95.96 23	94.40 27	98.32 24	98.38 49	97.12 29	92.87 29	95.17 46	85.50 37	95.68 17	94.91 29	94.58 28	95.11 42	93.76 57	98.05 68	98.68 57
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		94.99 26	97.02 16	92.61 40	97.19 37	98.71 31	97.74 23	93.21 27	96.97 21	79.27 65	94.09 29	97.14 13	90.84 64	96.64 20	95.94 20	97.42 102	99.67 14

X-MVS		94.70 27	95.71 26	93.52 33	98.38 23	98.56 36	96.99 30	92.62 33	95.58 39	81.00 57	94.57 26	93.49 34	94.16 34	94.82 47	94.29 48	97.99 74	98.68 57

PGM-MVS		94.64 28	95.49 30	93.66 31	98.55 19	98.51 42	97.63 25	87.77 48	94.45 52	84.92 40	97.23 6	91.90 45	95.22 25	94.56 54	93.80 56	97.87 84	97.97 86

TSAR-MVS + GP.		94.59 29	96.60 20	92.25 41	90.25 88	98.17 55	96.22 36	86.53 54	97.49 16	87.26 29	95.21 23	97.06 14	94.07 36	94.34 59	94.20 50	99.18 5	99.71 13

xxxxxxxxxxxxxcwj		94.57 30	92.34 48	97.17 3	99.11 2	99.20 13	99.05 3	95.55 1	97.39 17	93.56 6	97.48 4	62.85 146	96.75 6	95.73 31	94.40 43	98.98 19	99.33 24

PHI-MVS		94.49 31	96.72 19	91.88 43	97.06 39	98.88 24	94.99 47	89.13 42	96.15 32	79.70 61	96.91 11	95.78 25	91.87 54	94.65 52	95.68 23	98.53 44	98.98 50

AdaColmap		94.28 32	92.94 44	95.84 16	98.32 24	98.33 51	96.06 38	94.62 16	96.29 28	91.22 17	89.89 39	85.50 74	96.38 16	91.85 95	90.89 83	98.44 46	97.81 89

DeepPCF-MVS	91.00 2	94.15 33	96.87 18	90.97 51	96.82 42	99.33 9	89.40 96	92.76 31	98.76 1	82.36 48	88.74 40	95.49 27	90.58 71	98.13 4	97.80 4	93.88 182	99.88 6

CPTT-MVS		94.11 34	93.99 39	94.25 28	96.58 45	97.66 59	97.31 28	91.94 35	94.84 49	88.72 27	92.51 32	93.04 37	95.78 21	91.51 98	89.97 99	95.15 171	98.37 73

EPNet		93.69 35	95.34 31	91.76 44	96.98 41	98.47 46	95.40 44	86.79 51	95.47 40	82.84 46	95.66 18	89.17 50	90.47 72	95.25 40	94.69 39	98.10 62	98.68 57
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		93.32 36	93.59 42	93.00 38	97.03 40	98.24 52	95.27 45	91.66 38	95.20 44	83.25 45	95.39 20	85.52 72	92.80 44	92.60 85	90.21 95	98.01 71	97.99 84
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CANet		93.23 37	93.72 41	92.65 39	95.48 55	99.09 19	96.55 34	86.74 52	95.28 43	85.22 38	77.30 72	91.25 47	92.60 47	97.06 14	96.63 7	99.31 2	99.45 22

CDPH-MVS		93.22 38	95.08 32	91.04 50	97.57 34	98.49 44	96.74 32	89.35 41	95.19 45	73.57 94	90.26 37	91.59 46	90.68 68	95.09 44	96.15 14	98.31 56	98.81 53

CSCG		93.16 39	92.65 46	93.76 30	98.32 24	99.09 19	96.12 37	89.91 40	93.15 61	89.64 21	83.62 55	88.91 53	92.40 49	91.09 103	93.70 58	96.14 154	98.99 48

MVS_111021_LR		93.05 40	94.53 35	91.32 48	96.43 47	98.38 49	92.81 61	87.20 50	95.94 36	81.45 50	94.75 25	86.08 68	92.12 52	94.83 46	93.34 64	97.89 83	98.42 72

3Dnovator+	86.26 7	92.90 41	92.45 47	93.42 34	97.25 36	98.45 48	95.82 39	85.71 60	93.83 56	89.55 23	72.31 101	92.28 42	94.01 37	95.10 43	95.92 21	98.17 58	99.23 32

MVS_111021_HR		92.73 42	94.83 34	90.28 56	96.27 49	99.10 18	92.77 62	86.15 57	93.41 59	77.11 84	93.82 30	87.39 60	90.61 69	95.60 34	95.15 32	98.79 35	99.32 26

PLC	89.12 3	92.67 43	90.84 58	94.81 26	97.69 32	96.10 86	95.42 43	91.70 36	95.82 38	92.52 13	81.24 58	86.01 69	94.36 29	92.44 89	90.27 92	97.19 111	93.99 151
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
3Dnovator	85.78 8	92.53 44	91.96 50	93.20 36	97.99 28	98.47 46	95.78 40	85.94 58	93.07 63	86.40 33	73.43 93	89.00 52	94.08 35	94.74 50	96.44 12	99.01 18	98.57 65

DeepC-MVS	88.77 4	92.39 45	91.74 52	93.14 37	96.21 50	98.55 39	96.30 35	93.84 21	93.06 64	81.09 55	74.69 87	85.20 77	93.48 40	95.41 37	96.13 15	97.92 80	99.18 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OMC-MVS		92.05 46	91.88 51	92.25 41	96.51 46	97.94 57	93.18 58	88.97 44	96.53 26	84.47 42	80.79 60	87.85 56	93.25 42	92.48 88	91.81 76	97.12 112	95.73 128

MVSTER		91.91 47	93.43 43	90.14 57	89.81 94	92.32 124	94.53 50	81.32 84	96.00 33	84.77 41	85.41 53	92.39 41	91.32 56	96.41 22	94.01 54	99.11 8	97.45 98

MVS_0304		91.90 48	92.93 45	90.69 55	93.66 63	98.78 28	96.73 33	85.43 64	93.13 62	78.11 78	77.02 75	89.09 51	91.10 60	96.98 16	96.54 8	99.11 8	98.96 51

QAPM		91.68 49	91.97 49	91.34 47	97.86 30	98.72 30	95.60 42	85.72 59	90.86 77	77.14 83	76.06 76	90.35 48	92.69 46	94.10 60	94.60 40	99.04 14	99.09 40

CS-MVS		91.55 50	94.12 37	88.55 66	89.68 96	97.47 63	90.90 85	79.76 95	95.94 36	79.26 66	88.32 41	88.42 55	92.80 44	95.93 30	93.70 58	98.93 25	99.07 42

CNLPA		91.53 51	89.74 70	93.63 32	96.75 43	97.63 61	91.16 80	91.70 36	96.38 27	90.82 18	69.66 112	85.52 72	93.76 38	90.44 109	91.14 82	97.55 97	97.40 99

ETV-MVS		91.51 52	94.06 38	88.54 67	89.39 100	97.52 62	89.48 93	80.88 87	97.09 19	79.41 63	87.87 42	86.18 67	92.95 43	95.94 28	94.33 45	99.13 7	99.52 20

DELS-MVS		91.09 53	90.56 66	91.71 45	95.82 53	98.59 35	95.74 41	86.68 53	85.86 104	85.12 39	72.71 96	81.36 84	88.06 91	97.31 8	98.27 2	98.86 32	99.82 7
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 54	90.71 60	91.30 49	96.14 51	97.66 59	94.80 48	89.00 43	94.74 51	77.42 82	80.22 61	86.70 63	92.27 50	91.65 97	90.17 97	98.15 61	93.83 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PVSNet_BlendedMVS		90.74 55	90.66 62	90.82 53	94.75 58	98.54 40	91.30 77	86.53 54	95.43 41	85.75 34	78.66 67	70.67 120	87.60 92	96.37 23	95.08 34	98.98 19	99.90 2

PVSNet_Blended		90.74 55	90.66 62	90.82 53	94.75 58	98.54 40	91.30 77	86.53 54	95.43 41	85.75 34	78.66 67	70.67 120	87.60 92	96.37 23	95.08 34	98.98 19	99.90 2

CHOSEN 280x420		90.61 57	94.27 36	86.35 85	93.12 67	98.16 56	89.99 89	69.62 171	92.48 68	76.89 87	87.28 45	96.72 17	90.31 74	94.81 48	92.33 73	98.17 58	98.08 82

MAR-MVS		90.44 58	91.17 56	89.59 60	97.48 35	97.92 58	90.96 83	79.80 92	95.07 47	77.03 85	80.83 59	79.10 94	94.68 27	93.16 71	94.46 42	97.59 96	97.63 91
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 59	89.56 75	91.41 46	94.44 60	98.18 54	94.35 52	94.33 18	84.55 116	76.61 88	75.84 79	88.47 54	91.29 57	90.37 111	90.66 89	97.46 98	98.88 52
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
OpenMVS	83.41 11	89.84 60	88.89 81	90.95 52	97.63 33	98.51 42	94.64 49	85.47 63	88.14 90	78.39 76	65.06 124	85.42 75	91.04 62	93.06 74	93.70 58	98.53 44	98.37 73

EIA-MVS		89.82 61	91.48 54	87.89 75	89.16 102	97.31 65	88.99 97	80.92 86	94.29 53	77.65 80	82.16 57	79.77 92	91.90 53	94.61 53	93.03 70	98.70 41	99.21 34

canonicalmvs		89.62 62	89.87 69	89.33 62	90.47 83	97.02 71	93.46 57	79.67 96	92.45 69	81.05 56	82.84 56	73.00 109	93.71 39	90.38 110	94.85 37	97.65 92	98.54 66

TSAR-MVS + COLMAP		89.59 63	89.64 72	89.53 61	93.32 66	96.51 78	95.03 46	88.53 45	95.98 34	69.10 109	91.81 33	64.53 142	93.40 41	93.53 66	91.35 81	97.77 85	93.75 158

HQP-MVS		89.57 64	90.57 65	88.41 69	92.77 68	94.71 101	94.24 53	87.97 46	93.44 58	68.18 112	91.75 34	71.54 119	89.90 77	92.31 92	91.43 79	97.39 103	98.80 54

MVS_Test		89.02 65	90.20 67	87.64 77	89.83 93	97.05 70	92.30 64	77.59 115	92.89 65	75.01 92	77.36 71	76.10 103	92.27 50	95.30 39	95.42 27	98.83 33	97.30 102

CLD-MVS		88.99 66	88.07 84	90.07 58	89.61 97	94.94 98	93.82 56	85.70 61	92.73 67	82.73 47	79.97 62	69.59 123	90.44 73	90.32 112	89.93 101	98.10 62	99.04 44
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 67	89.94 68	87.70 76	89.44 99	96.74 76	91.62 71	77.92 112	93.79 57	78.76 71	77.55 70	78.46 97	89.38 83	92.26 93	92.52 72	99.10 10	98.23 77

PMMVS		88.56 68	91.22 55	85.47 93	90.04 90	95.60 94	86.62 118	78.49 107	93.86 55	70.62 105	90.00 38	80.08 90	91.64 55	92.36 90	89.80 105	95.40 166	96.84 111

baseline1		88.16 69	88.15 83	88.17 73	90.02 91	94.79 100	91.85 69	83.89 67	87.37 96	75.67 91	73.75 91	79.89 91	88.44 90	94.41 55	93.33 66	99.18 5	93.55 160

thisisatest0530		87.99 70	90.76 59	84.75 96	88.36 110	96.82 73	87.65 108	79.67 96	91.77 71	70.93 101	79.94 63	87.65 58	84.21 108	92.98 77	89.07 115	97.66 91	97.13 105

tttt0517		87.93 71	90.71 60	84.68 97	88.33 111	96.76 75	87.42 111	79.67 96	91.74 72	70.83 102	79.91 64	87.61 59	84.21 108	92.88 82	89.07 115	97.62 94	97.03 107

CANet_DTU		87.91 72	91.57 53	83.64 105	90.96 77	97.12 68	91.90 68	75.97 126	92.83 66	53.16 166	86.02 50	79.02 95	90.80 65	95.40 38	94.15 51	99.03 17	96.47 122

diffmvs		87.86 73	87.40 90	88.39 70	88.57 108	96.10 86	91.24 79	83.15 71	90.62 78	79.13 68	72.45 99	67.71 129	90.07 76	92.58 86	93.31 67	98.17 58	99.03 45

IS_MVSNet		87.83 74	90.66 62	84.53 98	90.08 89	96.79 74	88.16 103	79.89 91	85.44 106	72.20 96	75.50 83	87.14 61	80.21 136	95.53 35	95.22 30	96.65 128	99.02 46

EPP-MVSNet		87.72 75	89.74 70	85.37 94	89.11 103	95.57 95	86.31 119	79.44 99	85.83 105	75.73 90	77.23 73	90.05 49	84.78 105	91.22 101	90.25 93	96.83 119	98.04 83

ET-MVSNet_ETH3D		87.63 76	91.08 57	83.59 106	67.96 205	96.30 85	92.06 66	78.47 108	91.95 70	69.87 107	87.57 44	84.14 81	94.34 30	88.58 124	92.10 74	98.88 30	96.93 108

DI_MVS_plusplus_trai		87.63 76	87.13 92	88.22 72	88.61 107	95.92 90	94.09 55	81.41 83	87.00 99	78.38 77	59.70 142	80.52 88	89.08 85	94.37 57	93.34 64	97.73 86	99.05 43

casdiffmvs		87.59 78	86.69 96	88.64 65	89.06 104	96.32 84	90.18 87	83.21 70	87.74 94	80.20 60	67.99 116	68.34 127	90.79 66	93.83 62	94.08 52	98.41 49	98.50 69

PVSNet_Blended_VisFu		87.44 79	88.72 82	85.95 89	92.02 72	97.26 66	86.88 116	82.66 78	83.86 121	79.16 67	66.96 119	84.91 78	77.26 153	94.97 45	93.48 62	97.73 86	99.64 15

FMVSNet3		87.19 80	87.32 91	87.04 83	82.82 145	90.21 139	92.88 60	76.53 121	91.69 73	81.31 52	64.81 127	80.64 85	89.79 81	94.80 49	94.76 38	98.88 30	94.32 147

LS3D		87.19 80	85.48 103	89.18 63	94.96 57	95.47 96	92.02 67	93.36 26	88.69 88	67.01 113	70.56 108	72.10 114	92.47 48	89.96 115	89.93 101	95.25 168	91.68 169

ACMP	85.16 9	87.15 82	87.04 93	87.27 81	90.80 79	94.45 104	89.41 95	83.09 75	89.15 85	76.98 86	86.35 48	65.80 135	86.94 95	88.45 125	87.52 134	96.42 143	97.56 96
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
UGNet		87.04 83	89.59 74	84.07 100	90.94 78	95.95 89	86.02 121	81.65 82	85.94 103	78.54 75	78.00 69	85.40 76	69.62 173	91.83 96	91.53 78	97.63 93	98.51 68
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 84	87.65 87	86.12 88	91.77 75	93.84 110	93.04 59	82.77 77	88.04 91	65.33 118	87.69 43	67.09 133	86.79 96	90.20 113	88.99 118	97.05 114	97.71 90

PatchMatch-RL		86.75 85	85.43 104	88.29 71	94.06 61	96.37 83	86.82 117	82.94 76	88.94 86	79.59 62	79.83 65	59.17 154	89.46 82	91.12 102	88.81 122	96.88 118	93.78 156

baseline2		86.51 86	89.35 78	83.19 107	85.70 131	94.88 99	85.75 126	77.13 117	89.87 82	70.65 104	79.03 66	79.14 93	81.51 129	93.70 63	90.22 94	98.38 52	98.60 63

thres100view900		86.48 87	85.08 106	88.12 74	90.54 80	96.90 72	92.39 63	84.82 65	84.16 119	71.65 97	70.86 105	60.49 149	91.23 59	93.65 64	90.19 96	98.10 62	99.32 26

ACMM	84.23 10	86.40 88	84.64 109	88.46 68	91.90 73	91.93 130	88.11 104	85.59 62	88.61 89	79.13 68	75.31 84	66.25 134	89.86 80	89.88 116	87.64 131	96.16 153	92.86 165
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		86.16 89	86.00 99	86.35 85	81.81 151	89.52 148	91.40 73	76.53 121	91.69 73	81.31 52	64.81 127	80.64 85	88.72 86	90.54 106	90.72 85	98.34 53	94.08 148

test1		86.16 89	86.00 99	86.35 85	81.81 151	89.52 148	91.40 73	76.53 121	91.69 73	81.31 52	64.81 127	80.64 85	88.72 86	90.54 106	90.72 85	98.34 53	94.08 148

tfpn200view9		86.07 91	84.76 108	87.61 78	90.54 80	96.39 80	91.35 76	83.15 71	84.16 119	71.65 97	70.86 105	60.49 149	90.91 63	92.89 79	89.34 107	98.05 68	99.17 37

DCV-MVSNet		85.90 92	85.88 101	85.93 90	87.86 116	88.37 165	89.45 94	77.46 116	87.33 97	77.51 81	76.06 76	75.76 105	88.48 89	87.40 133	88.89 121	94.80 177	97.37 100

Vis-MVSNet (Re-imp)		85.89 93	89.62 73	81.55 117	89.85 92	96.08 88	87.55 109	79.80 92	84.80 113	66.55 115	73.70 92	86.71 62	68.25 180	94.40 56	94.53 41	97.32 106	97.09 106

MSDG		85.81 94	82.29 130	89.93 59	95.52 54	92.61 119	91.51 72	91.46 39	85.12 110	78.56 73	63.25 133	69.01 125	85.31 102	88.45 125	88.23 125	97.21 110	89.33 179

thres200		85.80 95	84.38 110	87.46 79	90.51 82	96.39 80	91.64 70	83.15 71	81.59 127	71.54 99	70.24 109	60.41 151	89.88 78	92.89 79	89.85 104	98.06 66	99.26 31

OPM-MVS		85.69 96	82.79 123	89.06 64	93.42 64	94.21 108	94.21 54	87.61 49	72.68 152	70.79 103	71.09 103	67.27 132	90.74 67	91.29 100	89.05 117	97.61 95	93.94 153

thres400		85.59 97	84.08 113	87.36 80	90.45 84	96.60 77	90.95 84	83.67 69	80.99 130	71.17 100	69.08 114	60.25 152	89.88 78	93.14 72	89.34 107	98.02 70	99.17 37

CostFormer		85.47 98	86.98 94	83.71 103	88.70 106	94.02 109	88.07 105	62.72 188	89.78 83	78.68 72	72.69 97	78.37 98	87.35 94	85.96 146	89.32 111	96.73 125	98.72 55

thres600view7		85.14 99	83.58 119	86.96 84	90.37 87	96.39 80	90.33 86	83.15 71	80.46 131	70.60 106	67.96 117	60.04 153	89.22 84	92.89 79	88.28 124	98.06 66	99.08 41

test-LLR		85.11 100	89.49 76	80.00 126	85.32 135	94.49 102	82.27 156	74.18 136	87.83 92	56.70 144	75.55 81	86.26 64	82.75 121	93.06 74	90.60 90	98.77 37	98.65 61

FMVSNet2		84.89 101	84.02 115	85.91 91	81.81 151	89.52 148	91.40 73	75.79 127	84.45 117	79.39 64	58.75 145	74.35 107	88.72 86	93.51 68	93.46 63	98.34 53	94.08 148

FC-MVSNet-train		84.88 102	84.08 113	85.82 92	89.21 101	91.74 131	85.87 122	81.20 85	81.71 126	74.66 93	73.38 94	64.99 139	86.60 97	90.75 104	88.08 126	97.36 104	97.90 87

EPNet_dtu		84.87 103	89.01 79	80.05 125	95.25 56	92.88 117	88.84 99	84.11 66	91.69 73	49.28 182	85.69 51	78.95 96	65.39 185	92.22 94	91.66 77	97.43 101	89.95 176
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		84.80 104	85.71 102	83.73 102	87.94 115	95.76 91	90.08 88	73.45 142	85.12 110	62.66 127	72.39 100	64.97 140	90.59 70	92.95 78	90.69 88	97.67 90	98.12 79

UA-Net		84.69 105	87.64 88	81.25 119	90.38 86	95.67 92	87.33 112	79.41 100	72.07 155	66.48 116	75.09 85	92.48 40	66.88 181	94.03 61	94.25 49	97.01 117	89.88 177

TESTMET0.1,1		84.62 106	89.49 76	78.94 135	82.18 148	94.49 102	82.27 156	70.94 161	87.83 92	56.70 144	75.55 81	86.26 64	82.75 121	93.06 74	90.60 90	98.77 37	98.65 61

CHOSEN 1792x2688		84.59 107	84.30 112	84.93 95	93.71 62	98.23 53	89.91 90	77.96 111	84.81 112	65.93 117	45.19 189	71.76 118	83.13 119	95.46 36	95.13 33	98.94 24	99.53 19

Anonymous20231211		84.23 108	81.71 135	87.17 82	87.38 123	93.59 112	88.95 98	82.14 80	83.82 122	78.56 73	48.09 182	73.89 108	91.25 58	86.38 140	88.06 128	94.74 178	98.14 78

MDTV_nov1_ep13		84.17 109	88.03 85	79.66 128	86.00 129	94.41 105	85.05 128	66.01 183	90.36 79	64.34 123	77.13 74	84.56 79	82.71 123	87.12 137	88.92 119	93.84 184	93.69 159

test-mter		84.06 110	89.00 80	78.29 140	81.92 149	94.23 107	81.07 166	70.38 165	87.12 98	56.10 153	74.75 86	85.80 70	81.81 128	92.52 87	90.10 98	98.43 47	98.49 70

IB-MVS	79.58 12	83.83 111	84.81 107	82.68 109	91.85 74	97.35 64	75.75 185	82.57 79	86.55 101	84.01 43	70.90 104	65.43 137	63.18 190	84.19 160	89.92 103	98.74 39	99.31 28
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
EPMVS		83.71 112	86.76 95	80.16 124	89.72 95	95.64 93	84.68 129	59.73 193	89.61 84	62.67 126	72.65 98	81.80 83	86.22 99	86.23 142	88.03 129	97.96 76	93.35 161

HyFIR lowres test		83.43 113	82.94 122	84.01 101	93.41 65	97.10 69	87.21 113	74.04 138	80.15 133	64.98 119	41.09 197	76.61 102	86.51 98	93.31 69	93.01 71	97.91 82	99.30 29

PatchmatchNet		83.28 114	87.57 89	78.29 140	87.46 121	94.95 97	83.36 138	59.43 196	90.20 81	58.10 139	74.29 89	86.20 66	84.13 110	85.27 152	87.39 135	97.25 109	94.67 145
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		83.26 115	87.76 86	78.00 145	87.45 122	92.20 125	82.63 152	58.42 198	90.30 80	58.23 137	75.74 80	87.75 57	83.97 113	86.10 145	87.64 131	97.30 107	94.62 146

CDS-MVSNet		83.13 116	83.73 118	82.43 115	84.52 140	92.92 116	88.26 102	77.67 114	72.08 154	69.08 110	66.96 119	74.66 106	78.61 142	90.70 105	91.96 75	96.46 142	96.86 110
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
RPSCF		82.91 117	81.86 132	84.13 99	88.25 112	88.32 166	87.67 107	80.86 88	84.78 114	76.57 89	85.56 52	76.00 104	84.61 106	78.20 195	76.52 198	86.81 204	83.63 196

Vis-MVSNet		82.88 118	86.04 98	79.20 133	87.77 119	96.42 79	86.10 120	76.70 119	74.82 146	61.38 129	70.70 107	77.91 99	64.83 186	93.22 70	93.19 69	98.43 47	96.01 125
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dps		82.63 119	82.64 126	82.62 111	87.81 118	92.81 118	84.39 130	61.96 189	86.43 102	81.63 49	69.72 111	67.60 131	84.42 107	82.51 174	83.90 173	95.52 162	95.50 136

IterMVS-LS		82.62 120	82.75 125	82.48 112	87.09 124	87.48 180	87.19 114	72.85 145	79.09 134	66.63 114	65.22 122	72.14 113	84.06 112	88.33 128	91.39 80	97.03 116	95.60 135
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+		82.61 121	82.51 128	82.72 108	85.49 134	93.06 115	87.17 115	71.39 158	84.18 118	64.59 121	63.03 134	58.89 155	90.22 75	91.39 99	90.83 84	97.44 99	96.21 124

tpm cat1		82.39 122	82.32 129	82.47 113	88.13 113	92.42 123	87.43 110	62.79 187	85.30 107	78.05 79	60.14 140	72.10 114	83.20 118	82.26 177	85.67 152	95.23 169	98.35 75

MS-PatchMatch		82.16 123	82.18 131	82.12 116	91.65 76	93.50 113	89.51 92	71.95 152	81.48 128	64.45 122	59.58 144	77.54 100	77.23 154	89.88 116	85.62 153	97.94 77	87.68 183

tpmrst		81.71 124	83.87 117	79.20 133	89.01 105	93.67 111	84.22 131	60.14 191	87.45 95	59.49 133	64.97 125	71.86 117	85.30 103	84.72 156	86.30 143	97.04 115	98.09 81

RPMNet		81.47 125	86.24 97	75.90 163	86.72 125	92.12 127	82.82 150	55.76 204	85.21 108	53.73 164	63.45 131	83.16 82	80.13 137	92.34 91	89.52 106	96.23 151	97.90 87

CR-MVSNet		81.44 126	85.29 105	76.94 154	86.53 126	92.12 127	83.86 132	58.37 199	85.21 108	56.28 148	59.60 143	80.39 89	80.50 134	92.77 83	89.32 111	96.12 155	97.59 94

Effi-MVS+-dtu		81.18 127	82.77 124	79.33 131	84.70 139	92.54 121	85.81 123	71.55 156	78.84 135	57.06 143	71.98 102	63.77 144	85.09 104	88.94 121	87.62 133	91.79 196	95.68 130

test0.0.03 1		80.99 128	84.37 111	77.05 152	85.32 135	89.79 144	78.43 176	74.18 136	84.78 114	57.98 142	76.06 76	72.88 110	69.14 177	88.02 130	87.70 130	97.27 108	91.37 170

Fast-Effi-MVS+-dtu		80.57 129	83.44 120	77.22 150	83.98 143	91.52 133	85.78 125	64.54 186	80.38 132	50.28 178	74.06 90	62.89 145	82.00 127	89.10 120	88.91 120	96.75 123	97.21 104

FMVSNet5		80.56 130	82.53 127	78.26 142	73.80 200	81.52 198	82.26 158	68.36 176	88.85 87	64.21 124	69.09 113	84.38 80	83.49 117	87.13 136	86.76 140	97.44 99	79.95 199

ADS-MVSNet		80.25 131	82.96 121	77.08 151	87.86 116	92.60 120	81.82 163	56.19 203	86.95 100	56.16 151	68.19 115	72.42 112	83.70 116	82.05 178	85.45 158	96.75 123	93.08 164

FMVSNet1		80.18 132	78.07 146	82.65 110	78.55 175	87.57 179	88.41 101	73.93 139	70.16 159	73.57 94	49.80 172	64.45 143	85.35 101	90.54 106	90.72 85	96.10 156	93.21 162

USDC		80.10 133	79.33 142	81.00 121	86.36 127	91.71 132	88.74 100	75.77 128	81.90 125	54.90 158	67.67 118	52.05 167	83.94 114	88.44 127	86.25 144	96.31 146	87.28 187

COLMAP_ROB	75.69 15	79.47 134	76.90 153	82.46 114	92.20 69	90.53 135	85.30 127	83.69 68	78.27 138	61.47 128	58.26 147	62.75 147	78.28 145	82.41 175	82.13 186	93.83 186	83.98 195
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_part1		79.37 135	75.64 158	83.71 103	86.18 128	87.74 173	87.84 106	75.69 130	66.33 176	78.93 70	45.92 187	64.85 141	82.44 124	83.08 172	85.69 151	91.17 197	95.90 127

pmmvs4		79.32 136	77.78 148	81.11 120	80.18 160	88.96 160	83.39 136	76.07 124	81.27 129	69.35 108	58.66 146	51.19 170	82.01 126	87.16 135	84.39 170	95.66 160	92.82 166

PatchT		79.28 137	83.88 116	73.93 172	85.54 133	90.95 134	66.14 201	56.53 202	83.21 123	56.28 148	56.50 150	76.80 101	80.50 134	92.77 83	89.32 111	98.57 43	97.59 94

ACMH	78.51 14	79.27 138	78.08 145	80.65 122	89.52 98	90.40 136	80.45 168	79.77 94	69.54 164	54.85 159	64.83 126	56.16 161	83.94 114	84.58 158	86.01 148	95.41 165	95.03 142
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		79.23 139	78.95 144	79.56 129	81.89 150	92.52 122	82.97 145	73.70 140	67.27 170	64.97 120	61.66 139	65.06 138	78.61 142	87.12 137	88.07 127	95.23 169	90.95 172

ACMH+	79.09 13	79.12 140	77.22 152	81.35 118	88.50 109	90.36 137	82.14 160	79.38 102	72.78 151	58.59 134	62.31 138	56.44 160	84.10 111	82.03 179	84.05 171	95.40 166	92.55 167

UniMVSNet_NR-MVSNet		78.89 141	78.04 147	79.88 127	79.40 166	89.70 145	82.92 147	80.17 89	76.37 144	58.56 135	57.10 149	54.92 163	81.44 130	83.51 165	87.12 137	96.76 122	97.60 92

tpm		78.87 142	81.33 138	76.00 161	85.57 132	90.19 140	82.81 151	59.66 194	78.35 137	51.40 173	66.30 121	67.92 128	80.94 132	83.28 168	85.73 149	95.65 161	97.56 96

GA-MVS		78.86 143	80.42 139	77.05 152	83.27 144	92.17 126	83.24 140	75.73 129	73.75 148	46.27 192	62.43 136	57.12 157	76.94 156	93.14 72	89.34 107	96.83 119	95.00 143

IterMVS		78.85 144	81.36 136	75.93 162	84.27 142	85.74 186	83.83 134	66.35 181	76.82 139	50.48 176	63.48 130	68.82 126	73.99 161	89.68 118	89.34 107	96.63 131	95.67 131
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		78.71 145	81.34 137	75.64 167	84.31 141	85.67 187	83.51 135	66.14 182	76.67 140	50.38 177	63.45 131	69.02 124	73.23 163	89.66 119	89.22 114	96.24 150	95.67 131

UniMVSNet (Re)		78.00 146	77.52 149	78.57 138	79.66 165	90.36 137	82.09 161	77.86 113	76.38 143	60.26 130	54.63 155	52.07 166	75.31 159	84.97 155	86.10 146	96.22 152	98.11 80

DU-MVS		77.98 147	76.71 154	79.46 130	78.68 172	89.26 154	82.92 147	79.06 104	76.52 141	58.56 135	54.89 153	48.35 183	81.44 130	83.16 170	87.21 136	96.08 157	97.60 92

FC-MVSNet-test		77.95 148	81.85 133	73.39 177	82.31 146	88.99 159	79.33 172	74.24 135	78.75 136	47.40 190	70.22 110	72.09 116	60.78 195	86.66 139	85.62 153	96.30 147	90.61 173

NR-MVSNet		77.21 149	76.41 155	78.14 144	80.18 160	89.26 154	83.38 137	79.06 104	76.52 141	56.59 146	54.89 153	45.32 192	72.89 165	85.39 151	86.12 145	96.71 126	97.36 101

thisisatest0515		77.13 150	79.36 141	74.52 169	79.79 164	89.65 146	73.54 190	73.69 141	74.10 147	58.14 138	62.79 135	60.57 148	66.49 183	88.08 129	85.16 163	95.49 164	95.15 140

gg-mvs-nofinetune		77.08 151	79.79 140	73.92 173	85.95 130	97.23 67	92.18 65	52.65 207	46.19 209	27.79 213	38.27 201	85.63 71	85.67 100	96.95 17	95.62 24	99.30 3	98.67 60

TranMVSNet+NR-MVSNet		77.02 152	75.76 157	78.49 139	78.46 178	88.24 167	83.03 144	79.97 90	73.49 150	54.73 160	54.00 158	48.74 178	78.15 147	82.36 176	86.90 139	96.59 133	96.55 116

CVMVSNet		76.86 153	79.09 143	74.26 170	85.29 137	89.44 151	79.91 171	78.47 108	68.94 167	44.45 196	62.35 137	69.70 122	64.50 187	85.82 147	87.03 138	92.94 191	90.33 174

Baseline_NR-MVSNet		76.71 154	74.56 165	79.23 132	78.68 172	84.15 194	82.45 154	78.87 106	75.83 145	60.05 131	47.92 183	50.18 175	79.06 141	83.16 170	83.86 174	96.26 148	96.80 112

v2v482		76.25 155	74.78 162	77.96 146	78.50 177	89.14 157	83.05 143	76.02 125	68.78 168	54.11 161	51.36 164	48.59 180	79.49 139	83.53 164	85.60 156	96.59 133	96.49 121

V42		76.21 156	75.04 161	77.58 147	78.68 172	89.33 153	82.93 146	74.64 133	69.84 161	56.13 152	50.42 169	50.93 171	76.30 158	83.32 166	84.89 167	96.83 119	96.54 117

v8		75.89 157	74.74 163	77.23 149	79.09 168	88.00 170	83.19 141	71.08 160	70.03 160	56.29 147	50.50 167	50.88 172	77.06 155	83.32 166	84.99 165	96.68 127	95.49 137

TinyColmap		75.75 158	73.19 176	78.74 137	84.82 138	87.69 175	81.59 164	74.62 134	71.81 156	54.01 162	55.79 152	44.42 197	82.89 120	84.61 157	83.76 175	94.50 179	84.22 194

MIMVSNet		75.71 159	77.26 150	73.90 174	70.93 201	88.71 163	79.98 170	57.67 201	73.58 149	58.08 141	53.93 159	58.56 156	79.41 140	90.04 114	89.97 99	97.34 105	86.04 188

UniMVSNet_ETH3D		75.63 160	71.59 184	80.35 123	81.03 155	89.90 143	83.25 139	76.58 120	60.08 192	64.19 125	42.89 196	45.01 193	82.14 125	80.20 189	86.75 141	94.90 174	96.29 123

pm-mvs1		75.61 161	74.19 167	77.26 148	80.16 162	88.79 161	81.49 165	75.49 132	59.49 194	58.09 140	48.32 180	55.53 162	72.35 166	88.61 123	85.48 157	95.99 158	93.12 163

v10		75.57 162	74.67 164	76.62 157	78.73 171	87.46 181	83.14 142	69.41 172	69.27 165	53.44 165	49.73 173	49.21 177	78.44 144	86.17 144	85.18 162	96.53 138	95.65 134

v1144		75.54 163	74.55 166	76.69 155	78.33 180	88.77 162	82.89 149	72.76 146	67.18 172	51.73 170	49.34 175	48.37 181	78.10 148	86.22 143	85.24 160	96.35 145	96.74 113

TDRefinement		75.54 163	73.22 174	78.25 143	87.65 120	89.65 146	85.81 123	79.28 103	71.14 157	56.06 154	52.17 162	51.96 168	68.74 179	81.60 180	80.58 188	91.94 194	85.45 189

pmmvs5		75.46 165	75.12 160	75.87 164	79.39 167	89.44 151	78.12 178	72.27 150	65.98 178	51.54 171	55.83 151	46.23 187	76.80 157	88.77 122	85.73 149	97.07 113	93.84 154

tfpnnormal		75.27 166	72.12 181	78.94 135	82.30 147	88.52 164	82.41 155	79.41 100	58.03 195	55.59 156	43.83 195	44.71 194	77.35 151	87.70 132	85.45 158	96.60 132	96.61 115

anonymousdsp		75.14 167	77.25 151	72.69 180	76.68 190	89.26 154	75.26 187	68.44 175	65.53 181	46.65 191	58.16 148	56.67 159	73.96 162	87.84 131	86.05 147	95.13 172	97.22 103

v148		74.98 168	73.52 172	76.69 155	78.84 170	89.02 158	78.78 174	76.82 118	67.22 171	59.61 132	49.18 176	47.94 185	70.57 172	80.76 184	83.99 172	95.52 162	96.52 119

v1192		74.96 169	73.92 168	76.17 158	77.76 183	88.19 169	82.54 153	71.94 153	66.84 173	50.07 180	48.10 181	46.14 188	78.28 145	86.30 141	85.23 161	96.41 144	96.67 114

v144192		74.76 170	73.64 169	76.06 160	77.58 184	88.23 168	81.87 162	71.63 155	66.03 177	51.08 174	48.63 179	46.77 186	77.59 150	84.53 159	84.76 168	96.64 130	96.54 117

v1921920		74.60 171	73.56 171	75.81 165	77.43 186	87.94 171	82.18 159	71.33 159	66.48 175	49.23 184	47.84 184	45.56 190	78.03 149	85.70 149	84.92 166	96.65 128	96.50 120

v1240		74.04 172	73.04 178	75.20 168	77.19 188	87.69 175	80.93 167	70.72 164	65.08 182	48.47 185	47.31 185	44.71 194	77.33 152	85.50 150	85.07 164	96.59 133	95.94 126

testgi		73.22 173	75.84 156	70.16 190	81.67 154	85.50 189	71.45 192	70.81 162	69.56 163	44.74 195	74.52 88	49.25 176	58.45 196	84.10 162	83.37 179	93.86 183	84.56 193

CP-MVSNet		73.19 174	72.37 180	74.15 171	77.54 185	86.77 184	76.34 181	72.05 151	65.66 180	51.47 172	50.49 168	43.66 198	70.90 168	80.93 183	83.40 178	96.59 133	95.66 133

WR-MVS		72.93 175	73.57 170	72.19 183	78.14 181	87.71 174	76.21 183	73.02 144	67.78 169	50.09 179	50.35 170	50.53 173	61.27 194	80.42 187	83.10 182	94.43 180	95.11 141

TransMVSNet (Re)		72.90 176	70.51 188	75.69 166	80.88 156	85.26 191	79.25 173	78.43 110	56.13 201	52.81 167	46.81 186	48.20 184	66.77 182	85.18 154	83.70 176	95.98 159	88.28 182

WR-MVS_H		72.69 177	72.80 179	72.56 182	77.94 182	87.83 172	75.26 187	71.53 157	64.75 183	52.19 169	49.83 171	48.62 179	61.96 193	81.12 182	82.44 184	96.50 139	95.00 143

SixPastTwentyTwo		72.65 178	73.22 174	71.98 186	78.40 179	87.64 177	70.09 195	70.37 166	66.49 174	47.60 188	65.09 123	45.94 189	73.09 164	78.94 190	78.66 194	92.33 192	89.82 178

LTVRE_ROB	71.82 16	72.62 179	71.77 182	73.62 175	80.74 157	87.59 178	80.42 169	70.37 166	49.73 205	37.12 207	59.76 141	42.52 203	80.92 133	83.20 169	85.61 155	92.13 193	93.95 152
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		72.37 180	71.47 186	73.43 176	77.32 187	86.43 185	75.99 184	71.94 153	63.37 186	49.24 183	49.07 177	42.42 204	69.60 174	80.59 186	83.18 181	96.48 141	95.23 139

MVS-HIRNet		72.32 181	73.45 173	71.00 189	80.58 158	89.97 141	68.51 198	55.28 205	70.89 158	52.27 168	39.09 199	57.11 158	75.02 160	85.76 148	86.33 142	94.36 181	85.00 191

PEN-MVS		72.24 182	71.30 187	73.33 178	77.08 189	85.57 188	76.75 179	72.52 148	63.89 185	48.12 186	50.79 165	43.09 201	69.03 178	78.54 192	83.46 177	96.50 139	93.76 157

v7n		72.11 183	71.66 183	72.63 181	75.26 195	86.85 182	76.74 180	68.77 174	62.70 189	49.40 181	45.92 187	43.51 199	70.63 171	84.16 161	83.21 180	94.99 173	95.25 138

EG-PatchMatch MVS		71.81 184	71.54 185	72.12 184	80.53 159	89.94 142	78.51 175	66.56 180	57.38 197	47.46 189	44.28 194	52.22 165	63.10 191	85.22 153	84.42 169	96.56 137	87.35 186

CMPMVS	54.54 17	71.74 185	67.94 193	76.16 159	90.41 85	93.25 114	78.32 177	75.60 131	59.81 193	53.95 163	44.64 192	51.22 169	70.70 169	74.59 200	75.88 199	88.01 201	76.23 202
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13_2view		71.65 186	73.08 177	69.97 191	75.22 196	86.81 183	73.98 189	59.61 195	69.75 162	48.01 187	54.21 157	53.06 164	69.19 176	78.50 193	80.43 189	93.84 184	88.79 180

gm-plane-assit		71.33 187	75.18 159	66.83 194	79.06 169	75.57 205	48.05 211	60.33 190	48.28 206	34.67 211	44.34 193	67.70 130	79.78 138	97.25 11	96.21 13	99.10 10	96.92 109

DTE-MVSNet		71.19 188	70.45 189	72.06 185	76.61 191	84.59 193	75.61 186	72.32 149	63.12 188	45.70 194	50.72 166	43.02 202	65.89 184	77.53 197	82.23 185	96.26 148	91.93 168

pmmvs6		70.29 189	67.90 194	73.07 179	76.17 192	85.31 190	76.29 182	70.75 163	47.39 208	55.33 157	37.15 205	50.49 174	69.55 175	82.96 173	80.85 187	90.34 200	91.18 171

PM-MVS		70.17 190	69.42 191	71.04 188	70.82 202	81.26 200	71.25 193	67.80 177	69.16 166	51.04 175	53.15 161	34.93 208	72.19 167	80.30 188	76.95 197	93.16 190	90.21 175

pmmvs-eth3d		69.59 191	67.57 196	71.95 187	70.04 203	80.05 201	71.48 191	70.00 170	62.57 190	55.99 155	44.92 190	35.73 207	70.64 170	81.56 181	79.69 190	93.55 187	88.43 181

N_pmnet		68.54 192	67.83 195	69.38 192	75.77 193	81.90 197	66.21 200	72.53 147	65.91 179	46.09 193	44.67 191	45.48 191	63.82 189	74.66 199	77.39 196	91.87 195	84.77 192

Anonymous20231206		68.09 193	68.68 192	67.39 193	75.16 197	82.55 195	69.33 196	70.06 169	63.34 187	42.28 199	37.91 203	43.12 200	52.67 199	83.56 163	82.71 183	94.84 176	87.59 184

EU-MVSNet		68.07 194	70.25 190	65.52 195	74.68 199	81.30 199	68.53 197	70.31 168	62.40 191	37.43 206	54.62 156	48.36 182	51.34 200	78.32 194	79.27 191	90.84 198	87.47 185

GG-mvs-BLEND		65.67 195	93.78 40	32.89 207	0.47 217	99.35 6	96.92 31	0.22 216	93.28 60	0.51 218	84.07 54	92.50 39	0.62 215	93.59 65	93.86 55	98.59 42	99.79 9

test20.03		65.17 196	67.41 197	62.55 197	75.35 194	79.31 202	62.22 202	68.83 173	56.50 200	35.35 210	51.97 163	44.70 196	40.01 205	80.69 185	79.25 192	93.55 187	79.47 201

MDA-MVSNet-bldmvs		62.23 197	61.13 200	63.52 196	58.94 209	82.44 196	60.71 205	73.28 143	57.22 198	38.42 204	49.63 174	27.64 214	62.83 192	54.98 206	74.16 200	86.96 203	81.83 198

new_pmnet		61.60 198	62.68 198	60.35 200	63.02 206	74.93 206	60.97 204	58.86 197	64.21 184	35.38 209	39.51 198	39.89 205	57.37 197	72.78 201	72.56 201	86.49 205	74.85 204

new-patchmatchnet		60.74 199	59.78 202	61.87 198	69.52 204	76.67 204	57.99 208	65.78 184	52.63 203	38.47 203	38.08 202	32.92 211	48.88 202	68.50 202	69.87 202	90.56 199	79.75 200

pmmvs3		60.52 200	60.87 201	60.12 201	61.38 207	71.62 207	57.42 209	53.94 206	48.09 207	35.95 208	38.62 200	32.19 213	64.12 188	75.33 198	77.99 195	87.89 202	82.28 197

MIMVSNet1		60.51 201	61.43 199	59.44 202	48.75 212	77.21 203	60.98 203	66.84 179	52.09 204	38.74 202	29.29 207	39.40 206	48.08 203	77.60 196	78.87 193	93.22 189	75.56 203

FPMVS		56.54 202	52.82 204	60.87 199	74.90 198	67.58 210	67.69 199	65.38 185	57.86 196	41.51 200	37.83 204	34.19 209	41.21 204	55.88 205	53.09 207	74.55 209	63.31 207

PMVS	42.57 18	45.71 203	42.61 206	49.32 204	61.35 208	37.82 214	36.96 213	60.10 192	37.20 210	41.50 201	28.53 208	33.11 210	28.82 210	53.45 207	48.70 209	67.22 211	59.42 208
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		43.95 204	42.62 205	45.50 205	50.79 211	41.20 213	35.55 214	52.51 208	52.95 202	29.09 212	12.92 210	11.48 217	38.15 206	62.01 204	66.62 204	66.89 212	51.17 209
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.25 205	42.55 207	39.74 206	43.25 213	55.05 212	38.15 212	47.11 211	31.78 211	11.83 215	21.16 209	19.12 215	20.98 212	49.95 209	56.09 206	77.09 207	64.68 206

E-PMN		27.87 206	24.36 209	31.97 208	41.27 215	25.56 217	16.62 216	49.16 209	22.00 213	9.90 216	11.75 212	7.86 219	29.57 209	22.22 211	34.70 210	45.27 213	46.41 211

MVE	32.98 19	27.61 207	29.89 208	24.94 210	21.97 216	37.22 215	15.56 218	38.83 212	17.49 214	14.72 214	11.64 214	5.62 220	21.26 211	35.20 210	50.95 208	37.29 215	51.13 210
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		26.96 208	22.96 210	31.63 209	41.91 214	25.73 216	16.30 217	49.10 210	22.38 212	9.03 217	11.22 215	8.12 218	29.93 208	20.16 212	31.04 211	43.49 214	42.04 212

testmvs		5.16 209	8.14 211	1.69 211	0.36 218	1.65 218	3.02 219	0.66 214	7.17 215	0.50 219	12.58 211	0.69 221	4.67 213	5.42 213	5.65 212	0.92 216	23.86 214

test123		4.39 210	7.11 212	1.21 212	0.11 219	1.16 219	1.67 220	0.35 215	5.91 216	0.16 220	11.65 213	0.16 222	4.45 214	1.72 214	4.92 213	0.51 217	24.28 213

uanet_test		0.00 211	0.00 213	0.00 213	0.00 220	0.00 220	0.00 221	0.00 217	0.00 217	0.00 221	0.00 216	0.00 223	0.00 216	0.00 215	0.00 214	0.00 218	0.00 215

sosnet-low-res		0.00 211	0.00 213	0.00 213	0.00 220	0.00 220	0.00 221	0.00 217	0.00 217	0.00 221	0.00 216	0.00 223	0.00 216	0.00 215	0.00 214	0.00 218	0.00 215

sosnet		0.00 211	0.00 213	0.00 213	0.00 220	0.00 220	0.00 221	0.00 217	0.00 217	0.00 221	0.00 216	0.00 223	0.00 216	0.00 215	0.00 214	0.00 218	0.00 215

RE-MVS-def										43.17 197

9.14												97.59 9

SR-MVS					98.52 20			93.70 22				96.63 19

Anonymous202405211			81.72 134		88.09 114	94.27 106	89.62 91	82.14 80	82.27 124		48.83 178	72.58 111	91.08 61	87.40 133	88.70 123	94.90 174	97.99 84

our_test_3					78.55 175	84.98 192	70.12 194

ambc			57.08 203		58.68 210	67.71 209	60.07 206		57.13 199	42.79 198	30.00 206	11.64 216	50.18 201	78.89 191	69.14 203	82.64 206	85.02 190

MTAPA										93.37 8		95.71 26

MTMP										93.84 4		94.86 30

Patchmatch-RL test							19.65 215

tmp_tt				57.89 203	79.94 163	59.29 211	52.84 210	36.65 213	94.77 50	68.22 111	72.96 95	65.62 136	33.65 207	66.20 203	58.02 205	76.06 208

XVS					92.16 70	98.56 36	91.04 81			81.00 57		93.49 34				98.00 72

X-MVStestdata					92.16 70	98.56 36	91.04 81			81.00 57		93.49 34				98.00 72

abl_6				93.25 35	97.12 38	98.71 31	94.40 51	87.81 47	97.86 10	87.19 30	91.07 36	95.80 24	94.18 33			98.78 36	99.36 23

mPP-MVS					97.95 29							92.24 44

NP-MVS									94.12 54

Patchmtry						92.08 129	83.86 132	58.37 199		56.28 148

DeepMVS_CX						70.68 208	59.61 207	67.36 178	72.12 153	38.41 205	53.88 160	32.44 212	55.15 198	50.88 208		74.35 210	68.42 205

High-resolution multi-view benchmark