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.

MTMP										93.14 1		90.21 34

MTAPA										92.97 2		91.03 27

DVP-MVS++		95.79 1	96.42 1	95.06 1	97.84 2	98.17 2	97.03 4	92.84 4	96.68 1	92.83 3	95.90 7	94.38 4	92.90 7	95.98 2	94.85 6	96.93 3	98.99 1

MED-MVS		95.66 2	96.33 3	94.88 2	96.63 25	97.96 5	96.90 6	92.96 2	96.43 2	92.70 4	97.77 1	94.16 5	93.27 4	95.59 7	94.71 11	96.79 7	97.66 12

aaEdge-Enhanced		95.38 6	95.93 6	94.74 4	96.51 27	97.82 8	96.76 7	92.70 7	95.23 6	92.39 5	97.77 1	94.08 6	93.28 3	94.87 19	94.08 22	96.77 9	97.66 12

TestfortrainingZip							96.76 7	92.70 7		92.16 6						96.77 9

SED-MVS		95.61 3	96.36 2	94.73 5	96.84 19	98.15 3	97.08 3	92.92 3	95.64 4	91.84 7	95.98 6	95.33 1	92.83 9	96.00 1	94.94 4	96.90 4	98.45 3

DVP-MVS		95.56 4	96.26 4	94.73 5	96.93 16	98.19 1	96.62 10	92.81 6	96.15 3	91.73 8	95.01 9	95.31 2	93.41 1	95.95 3	94.77 9	96.90 4	98.46 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
DPE-MVS		95.53 5	96.13 5	94.82 3	96.81 22	98.05 4	97.42 1	93.09 1	94.31 11	91.49 9	97.12 3	95.03 3	93.27 4	95.55 8	94.58 15	96.86 6	98.25 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SD-MVS		94.53 12	95.22 10	93.73 16	95.69 40	97.03 17	95.77 24	91.95 15	94.41 10	91.35 10	94.97 10	93.34 10	91.80 21	94.72 24	93.99 24	95.82 42	98.07 7
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
SF-MVS		94.61 10	94.96 12	94.20 11	96.75 24	97.07 15	95.82 21	92.60 10	93.98 14	91.09 11	95.89 8	92.54 14	91.93 17	94.40 30	93.56 33	97.04 2	97.27 20

APDe-MVS		95.23 7	95.69 8	94.70 7	97.12 10	97.81 9	97.19 2	92.83 5	95.06 8	90.98 12	96.47 4	92.77 12	93.38 2	95.34 11	94.21 19	96.68 12	98.17 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + MP.		94.48 13	94.97 11	93.90 14	95.53 41	97.01 18	96.69 9	90.71 26	94.24 12	90.92 13	94.97 10	92.19 17	93.03 6	94.83 20	93.60 30	96.51 16	97.97 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		94.60 11	94.91 13	94.24 10	97.86 1	96.53 34	96.14 12	92.51 11	93.87 16	90.76 14	93.45 20	93.84 7	92.62 11	95.11 14	94.08 22	95.58 59	97.48 17

MSP-MVS		95.12 8	95.83 7	94.30 8	96.82 21	97.94 6	96.98 5	92.37 14	95.40 5	90.59 15	96.16 5	93.71 8	92.70 10	94.80 21	94.77 9	96.37 17	97.99 8
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
SMA-MVS		94.70 9	95.35 9	93.93 13	97.57 3	97.57 11	95.98 15	91.91 16	94.50 9	90.35 16	93.46 19	92.72 13	91.89 19	95.89 4	95.22 1	95.88 35	98.10 6
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
MSLP-MVS++		92.02 36	91.40 40	92.75 25	96.01 35	95.88 48	93.73 44	89.00 36	89.89 48	90.31 17	81.28 64	88.85 42	91.45 24	92.88 54	94.24 18	96.00 31	96.76 34

HFP-MVS		94.02 17	94.22 21	93.78 15	97.25 7	96.85 23	95.81 22	90.94 25	94.12 13	90.29 18	94.09 16	89.98 35	92.52 13	93.94 36	93.49 36	95.87 37	97.10 26

APD-MVS		94.37 14	94.47 18	94.26 9	97.18 8	96.99 19	96.53 11	92.68 9	92.45 25	89.96 19	94.53 13	91.63 23	92.89 8	94.58 25	93.82 26	96.31 22	97.26 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
3Dnovator+	86.06 4	91.60 38	90.86 45	92.47 28	96.00 36	96.50 37	94.70 37	87.83 46	90.49 41	89.92 20	74.68 116	89.35 39	90.66 33	94.02 34	94.14 20	95.67 51	96.85 32

CNVR-MVS		94.37 14	94.65 14	94.04 12	97.29 6	97.11 14	96.00 14	92.43 13	93.45 17	89.85 21	90.92 28	93.04 11	92.59 12	95.77 5	94.82 7	96.11 29	97.42 19

CSCG		92.76 28	93.16 30	92.29 31	96.30 31	97.74 10	94.67 38	88.98 38	92.46 24	89.73 22	86.67 40	92.15 20	88.69 47	92.26 63	92.92 48	95.40 70	97.89 10

ACMMPR		93.72 20	93.94 23	93.48 19	97.07 11	96.93 20	95.78 23	90.66 28	93.88 15	89.24 23	93.53 18	89.08 41	92.24 14	93.89 38	93.50 34	95.88 35	96.73 35

MGCNet		93.46 22	94.44 19	92.32 30	95.88 37	97.84 7	95.25 30	87.99 43	92.23 27	89.16 24	91.23 27	91.51 25	88.98 42	95.64 6	95.04 3	96.67 14	97.57 16

CP-MVS		93.25 24	93.26 29	93.24 22	96.84 19	96.51 35	95.52 26	90.61 29	92.37 26	88.88 25	90.91 29	89.52 37	91.91 18	93.64 43	92.78 50	95.69 49	97.09 27

AdaColmap		90.29 46	88.38 63	92.53 27	96.10 34	95.19 61	92.98 50	91.40 20	89.08 52	88.65 26	78.35 81	81.44 75	91.30 30	90.81 96	90.21 100	94.72 120	93.59 115

ACMMP_NAP		93.94 18	94.49 17	93.30 21	97.03 13	97.31 13	95.96 16	91.30 21	93.41 19	88.55 27	93.00 21	90.33 32	91.43 27	95.53 9	94.41 17	95.53 63	97.47 18

NCCC		93.69 21	93.66 26	93.72 17	97.37 5	96.66 31	95.93 20	92.50 12	93.40 20	88.35 28	87.36 37	92.33 16	92.18 15	94.89 18	94.09 21	96.00 31	96.91 31

DeepC-MVS_fast	88.76 1	93.10 25	93.02 32	93.19 23	97.13 9	96.51 35	95.35 29	91.19 22	93.14 22	88.14 29	85.26 44	89.49 38	91.45 24	95.17 12	95.07 2	95.85 40	96.48 39
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		93.35 23	93.59 27	93.08 24	97.39 4	96.82 25	95.38 28	90.71 26	90.82 38	88.07 30	92.83 23	90.29 33	91.32 29	94.03 33	93.19 44	95.61 56	97.16 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
3Dnovator	85.17 5	90.48 44	89.90 52	91.16 39	94.88 47	95.74 52	93.82 41	85.36 59	89.28 50	87.81 31	74.34 122	87.40 51	88.56 48	93.07 50	93.74 29	96.53 15	95.71 53

CNLPA		88.40 62	87.00 80	90.03 46	93.73 57	94.28 79	89.56 103	85.81 56	91.87 31	87.55 32	69.53 153	81.49 74	89.23 40	89.45 129	88.59 145	94.31 143	93.82 103

SteuartSystems-ACMMP		94.06 16	94.65 14	93.38 20	96.97 15	97.36 12	96.12 13	91.78 17	92.05 30	87.34 33	94.42 14	90.87 29	91.87 20	95.47 10	94.59 14	96.21 27	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
CANet		91.33 40	91.46 39	91.18 38	95.01 44	96.71 26	93.77 42	87.39 49	87.72 57	87.26 34	81.77 60	89.73 36	87.32 63	94.43 29	93.86 25	96.31 22	96.02 49

MCST-MVS		93.81 19	94.06 22	93.53 18	96.79 23	96.85 23	95.95 17	91.69 19	92.20 28	87.17 35	90.83 30	93.41 9	91.96 16	94.49 28	93.50 34	97.61 1	97.12 25

PLC	83.76 9	88.61 61	86.83 84	90.70 41	94.22 52	92.63 124	91.50 65	87.19 50	89.16 51	86.87 36	75.51 107	80.87 77	89.98 38	90.01 117	89.20 131	94.41 139	90.45 181
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CPTT-MVS		91.39 39	90.95 43	91.91 34	95.06 43	95.24 60	95.02 34	88.98 38	91.02 37	86.71 37	84.89 46	88.58 46	91.60 23	90.82 95	89.67 118	94.08 149	96.45 40

DeepC-MVS	87.86 3	92.26 33	91.86 36	92.73 26	96.18 32	96.87 22	95.19 32	91.76 18	92.17 29	86.58 38	81.79 59	85.85 54	90.88 32	94.57 26	94.61 13	95.80 43	97.18 22
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PGM-MVS		92.76 28	93.03 31	92.45 29	97.03 13	96.67 30	95.73 25	87.92 45	90.15 47	86.53 39	92.97 22	88.33 47	91.69 22	93.62 44	93.03 45	95.83 41	96.41 42

TPM-MVS					96.31 30	96.02 42	94.89 35			86.52 40	87.18 39	92.17 18	86.76 70			95.56 60	93.85 101
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
PVSNet_BlendedMVS		88.19 69	88.00 69	88.42 68	92.71 72	94.82 72	89.08 118	83.81 86	84.91 78	86.38 41	79.14 73	78.11 102	82.66 115	93.05 51	91.10 68	95.86 38	94.86 68

PVSNet_Blended		88.19 69	88.00 69	88.42 68	92.71 72	94.82 72	89.08 118	83.81 86	84.91 78	86.38 41	79.14 73	78.11 102	82.66 115	93.05 51	91.10 68	95.86 38	94.86 68

TSAR-MVS + GP.		92.71 30	93.91 24	91.30 37	91.96 76	96.00 44	93.43 45	87.94 44	92.53 23	86.27 43	93.57 17	91.94 21	91.44 26	93.29 47	92.89 49	96.78 8	97.15 24

DPM-MVS		91.72 37	91.48 38	92.00 33	95.53 41	95.75 51	95.94 18	91.07 23	91.20 36	85.58 44	81.63 62	90.74 30	88.40 50	93.40 45	93.75 28	95.45 69	93.85 101

CS-MVS		90.34 45	90.58 47	90.07 45	93.11 63	95.82 50	90.57 76	83.62 90	87.07 61	85.35 45	82.98 51	83.47 65	91.37 28	94.94 16	93.37 40	96.37 17	96.41 42

ACMMP		92.03 35	92.16 34	91.87 36	95.88 37	96.55 33	94.47 39	89.49 35	91.71 33	85.26 46	91.52 26	84.48 61	90.21 36	92.82 55	91.63 63	95.92 34	96.42 41
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
CLD-MVS		88.66 59	88.52 61	88.82 60	91.37 85	94.22 80	92.82 52	82.08 126	88.27 56	85.14 47	81.86 58	78.53 98	85.93 80	91.17 81	90.61 84	95.55 61	95.00 64
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DELS-MVS		89.71 51	89.68 55	89.74 48	93.75 56	96.22 38	93.76 43	85.84 55	82.53 95	85.05 48	78.96 76	84.24 62	84.25 99	94.91 17	94.91 5	95.78 46	96.02 49
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
OMC-MVS		90.23 48	90.40 48	90.03 46	93.45 59	95.29 57	91.89 60	86.34 53	93.25 21	84.94 49	81.72 61	86.65 53	88.90 43	91.69 72	90.27 99	94.65 124	93.95 93

SPE-MVS-test		90.29 46	90.96 42	89.51 54	93.18 62	95.87 49	89.18 111	83.72 89	88.32 55	84.82 50	84.89 46	85.23 58	90.25 35	94.04 32	92.66 54	95.94 33	95.69 54

DeepPCF-MVS	88.51 2	92.64 31	94.42 20	90.56 42	94.84 48	96.92 21	91.31 68	89.61 34	95.16 7	84.55 51	89.91 32	91.45 26	90.15 37	95.12 13	94.81 8	92.90 188	97.58 15

MVS_111021_LR		90.14 49	90.89 44	89.26 56	93.23 61	94.05 90	90.43 84	84.65 66	90.16 46	84.52 52	90.14 31	83.80 64	87.99 54	92.50 59	90.92 75	94.74 118	94.70 72

XVS					93.11 63	96.70 27	91.91 58			83.95 53		88.82 43				95.79 44

X-MVStestdata					93.11 63	96.70 27	91.91 58			83.95 53		88.82 43				95.79 44

X-MVS		92.36 32	92.75 33	91.90 35	96.89 17	96.70 27	95.25 30	90.48 31	91.50 35	83.95 53	88.20 34	88.82 43	89.11 41	93.75 41	93.43 37	95.75 47	96.83 33

E2		87.53 77	86.95 81	88.20 73	90.10 111	94.13 84	90.50 82	84.09 83	84.43 82	83.82 56	77.92 86	77.84 108	85.37 86	90.43 106	90.08 104	95.32 85	93.79 107

ACM-MVS					96.49 28	96.04 41	95.42 27		89.60 49	83.77 57	86.60 41	91.59 24	86.35 74			94.91 108	96.07 47

train_agg		92.87 27	93.53 28	92.09 32	96.88 18	95.38 56	95.94 18	90.59 30	90.65 40	83.65 58	94.31 15	91.87 22	90.30 34	93.38 46	92.42 55	95.17 95	96.73 35

viewcassd2359sk11		87.35 81	86.67 90	88.14 75	90.08 113	94.12 85	90.51 80	84.13 81	83.71 86	83.42 59	76.99 90	77.46 111	85.33 87	90.40 107	90.21 100	95.34 80	93.81 106

EPNet		89.60 52	89.91 51	89.24 57	96.45 29	93.61 102	92.95 51	88.03 42	85.74 69	83.36 60	87.29 38	83.05 68	80.98 131	92.22 64	91.85 60	93.69 170	95.58 58
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Casviewmamba		88.37 66	88.02 68	88.78 61	90.62 94	94.98 68	91.00 72	85.24 60	86.70 62	83.08 61	76.96 93	78.63 97	87.25 65	92.43 60	91.85 60	95.48 67	94.60 75

EC-MVSNet		89.96 50	90.77 46	89.01 58	90.54 98	95.15 62	91.34 67	81.43 135	85.27 71	83.08 61	82.83 52	87.22 52	90.97 31	94.79 22	93.38 38	96.73 11	96.71 37

TSAR-MVS + ACMM		92.97 26	94.51 16	91.16 39	95.88 37	96.59 32	95.09 33	90.45 32	93.42 18	83.01 63	94.68 12	90.74 30	88.74 46	94.75 23	93.78 27	93.82 164	97.63 14

E3new		87.09 83	86.27 96	88.05 76	90.04 115	94.08 88	90.53 78	84.16 78	82.52 97	82.94 64	75.92 100	76.91 119	85.29 88	90.27 109	90.34 94	95.36 75	93.82 103

E3		87.08 84	86.27 96	88.04 77	90.04 115	94.08 88	90.53 78	84.16 78	82.52 97	82.86 65	75.91 101	76.93 117	85.27 89	90.27 109	90.33 95	95.36 75	93.82 103

ACMM	83.27 10	87.68 74	86.09 100	89.54 53	93.26 60	92.19 131	91.43 66	86.74 51	86.02 66	82.85 66	75.63 105	75.14 134	88.41 49	90.68 102	89.99 107	94.59 127	92.97 129
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
sasdasda		89.36 54	89.92 49	88.70 63	91.38 83	95.92 46	91.81 62	82.61 121	90.37 42	82.73 67	82.09 55	79.28 90	88.30 51	91.17 81	93.59 31	95.36 75	97.04 28

canonicalmvs		89.36 54	89.92 49	88.70 63	91.38 83	95.92 46	91.81 62	82.61 121	90.37 42	82.73 67	82.09 55	79.28 90	88.30 51	91.17 81	93.59 31	95.36 75	97.04 28

MVSMamba_PlusPlus		90.78 42	91.67 37	89.74 48	91.80 79	96.07 40	92.21 54	85.88 54	90.36 44	82.63 69	84.71 48	85.27 57	89.59 39	95.08 15	94.64 12	96.36 19	95.58 58

viewdifsd2359ckpt09		87.46 78	86.79 86	88.25 72	89.99 117	94.91 69	90.57 76	84.20 77	82.83 91	82.29 70	76.85 94	76.34 125	86.99 69	91.42 76	90.96 74	95.48 67	94.22 87

FA-MVS(training)		85.65 108	85.79 105	85.48 114	90.44 103	93.47 104	88.66 129	73.11 222	83.34 88	82.26 71	71.79 138	78.39 100	83.14 109	91.00 89	89.47 124	95.28 89	93.06 127

PVSNet_Blended_VisFu		87.40 80	87.80 71	86.92 94	92.86 68	95.40 55	88.56 133	83.45 101	79.55 139	82.26 71	74.49 118	84.03 63	79.24 164	92.97 53	91.53 65	95.15 97	96.65 38

OpenMVS	82.53 11	87.71 73	86.84 83	88.73 62	94.42 51	95.06 65	91.02 71	83.49 96	82.50 99	82.24 73	67.62 165	85.48 55	85.56 82	91.19 80	91.30 66	95.67 51	94.75 70

E5new		86.71 87	85.64 107	87.96 78	89.95 119	93.99 95	90.75 73	84.39 70	80.71 124	82.22 74	74.36 120	76.30 127	85.12 93	89.86 119	90.30 96	95.33 82	93.93 94

E5		86.71 87	85.64 107	87.96 78	89.95 119	93.99 95	90.75 73	84.39 70	80.71 124	82.22 74	74.36 120	76.30 127	85.12 93	89.86 119	90.30 96	95.33 82	93.93 94

E4		86.66 89	85.61 110	87.87 81	89.94 121	94.00 94	90.47 83	84.16 78	80.46 128	82.16 76	74.11 123	76.35 124	85.14 90	90.04 116	90.45 90	95.37 74	93.86 100

casdiffmvs_mvg		87.97 71	87.63 76	88.37 70	90.55 97	94.42 76	91.82 61	84.69 65	84.05 84	82.08 77	76.57 96	79.00 93	85.49 83	92.35 61	92.29 57	95.55 61	94.70 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
hybridcas		87.61 75	87.14 79	88.16 74	90.27 109	94.38 78	90.69 75	84.23 74	85.22 73	82.04 78	75.47 108	78.20 101	86.12 75	91.78 71	90.99 73	95.61 56	93.93 94

E6new		86.44 94	85.45 113	87.59 86	89.94 121	94.05 90	90.00 91	83.35 105	80.22 129	81.75 79	73.69 128	75.92 130	85.13 91	90.17 112	90.41 91	95.40 70	93.70 111

E6		86.44 94	85.45 113	87.59 86	89.94 121	94.05 90	90.00 91	83.35 105	80.22 129	81.75 79	73.69 128	75.92 130	85.13 91	90.17 112	90.41 91	95.40 70	93.70 111

ETV-MVS		89.22 56	89.76 53	88.60 66	91.60 81	94.61 75	89.48 105	83.46 100	85.20 74	81.58 81	82.75 53	82.59 70	88.80 44	94.57 26	93.28 42	96.68 12	95.31 62

onestephybrid01		86.53 92	86.61 91	86.44 98	88.53 138	92.94 116	89.16 115	82.82 111	84.73 81	81.56 82	77.96 84	78.49 99	82.84 111	88.93 136	89.00 137	93.74 167	94.23 86

MVSTER		86.03 103	86.12 99	85.93 108	88.62 137	89.93 161	89.33 108	79.91 159	81.87 107	81.35 83	81.07 65	74.91 136	80.66 137	92.13 68	90.10 103	95.68 50	92.80 134

MVS_111021_HR		90.56 43	91.29 41	89.70 51	94.71 50	95.63 53	91.81 62	86.38 52	87.53 58	81.29 84	87.96 35	85.43 56	87.69 57	93.90 37	92.93 47	96.33 20	95.69 54

ACMP	83.90 8	88.32 67	88.06 66	88.62 65	92.18 74	93.98 97	91.28 69	85.24 60	86.69 63	81.23 85	85.62 43	75.13 135	87.01 68	89.83 121	89.77 115	94.79 114	95.43 61
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
casdiffmvs		87.45 79	87.15 78	87.79 84	90.15 110	94.22 80	89.96 94	83.93 85	85.08 76	80.91 86	75.81 103	77.88 106	86.08 77	91.86 70	90.86 77	95.74 48	94.37 78
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IB-MVS	79.09 12	82.60 142	82.19 141	83.07 144	91.08 88	93.55 103	80.90 226	81.35 137	76.56 157	80.87 87	64.81 192	69.97 165	68.87 227	85.64 187	90.06 106	95.36 75	94.74 71
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
viewdifsd2359ckpt13		86.88 86	86.35 95	87.50 89	89.91 125	94.19 82	89.89 96	83.43 102	82.94 90	80.82 88	75.76 104	76.45 123	85.95 79	90.72 101	90.49 89	95.00 102	93.88 97

EIA-MVS		87.94 72	88.05 67	87.81 82	91.46 82	95.00 67	88.67 127	82.81 112	82.53 95	80.81 89	80.04 68	80.20 81	87.48 60	92.58 58	91.61 64	95.63 53	94.36 80

hybridnocas07		86.29 99	86.58 93	85.96 107	88.15 146	92.31 128	88.95 123	81.61 133	86.15 64	80.80 90	79.24 72	77.78 109	82.33 119	88.53 142	88.60 144	93.92 157	93.42 118

PHI-MVS		92.05 34	93.74 25	90.08 44	94.96 45	97.06 16	93.11 49	87.71 47	90.71 39	80.78 91	92.40 24	91.03 27	87.68 58	94.32 31	94.48 16	96.21 27	96.16 46

DI_MVS_pp		86.41 97	85.54 112	87.42 91	89.24 131	93.13 110	92.16 56	82.65 118	82.30 101	80.75 92	68.30 161	80.41 79	85.01 96	90.56 104	90.07 105	94.70 122	94.01 91

viewmanbaseed2359cas		87.17 82	86.90 82	87.48 90	90.08 113	94.14 83	90.30 86	83.19 109	84.17 83	80.68 93	76.78 95	77.43 112	85.43 85	90.78 97	90.92 75	95.21 93	94.10 90

hybrid		86.13 101	86.45 94	85.75 109	88.02 149	92.17 132	88.79 126	81.32 138	85.86 67	80.67 94	78.80 77	78.11 102	82.06 122	88.52 143	88.29 149	93.66 172	93.38 119

dtuplus		85.37 112	84.69 120	86.16 103	88.46 139	91.91 135	89.32 109	81.64 131	80.88 120	80.66 95	74.38 119	76.92 118	83.58 103	87.28 157	87.61 156	93.33 182	93.87 98

viewmamba		86.59 90	86.74 88	86.42 99	88.44 141	92.86 118	89.26 110	82.63 120	87.39 60	80.58 96	78.43 80	77.87 107	83.66 101	88.44 146	88.75 142	93.96 155	93.45 117

casdiffseed414692147		85.57 109	83.88 129	87.54 88	89.98 118	93.88 99	90.07 90	83.49 96	79.40 140	80.57 97	68.32 160	71.85 158	86.11 76	89.45 129	90.56 87	95.00 102	93.69 113

viewmambaseed2359dif		85.52 110	85.01 117	86.12 105	88.39 142	91.96 134	89.39 106	81.43 135	82.16 102	80.47 98	75.52 106	76.85 120	83.66 101	87.03 162	87.60 157	93.37 181	93.98 92

diffmvs		86.52 93	86.76 87	86.23 102	88.31 145	92.63 124	89.58 102	81.61 133	86.14 65	80.26 99	79.00 75	77.27 113	83.58 103	88.94 135	89.06 134	94.05 151	94.29 81
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		85.95 105	85.62 109	86.34 100	89.73 127	93.40 107	89.18 111	81.99 128	81.53 110	80.19 100	75.17 110	76.65 121	83.45 106	90.32 108	89.00 137	93.51 176	93.26 121

TAPA-MVS	84.37 7	88.91 58	88.93 59	88.89 59	93.00 67	94.85 71	92.00 57	84.84 64	91.68 34	80.05 101	79.77 70	84.56 60	88.17 53	90.11 115	89.00 137	95.30 86	92.57 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
diffmvs_AUTHOR		86.44 94	86.59 92	86.26 101	88.33 144	92.74 120	89.66 101	81.74 130	85.17 75	80.04 102	77.70 87	77.20 114	83.68 100	89.66 125	89.28 127	94.14 148	94.37 78

QAPM		89.49 53	89.58 56	89.38 55	94.73 49	95.94 45	92.35 53	85.00 63	85.69 70	80.03 103	76.97 92	87.81 49	87.87 55	92.18 67	92.10 58	96.33 20	96.40 44

PCF-MVS	84.60 6	88.66 59	87.75 74	89.73 50	93.06 66	96.02 42	93.22 48	90.00 33	82.44 100	80.02 104	77.96 84	85.16 59	87.36 62	88.54 141	88.54 146	94.72 120	95.61 57
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
viewdifsd2359ckpt11		84.31 129	83.65 132	85.08 117	88.07 147	91.03 142	86.86 163	80.65 143	79.92 133	79.63 105	75.08 112	73.99 142	82.74 112	86.40 178	85.98 188	92.51 193	93.16 123

viewmsd2359difaftdt		84.31 129	83.65 132	85.07 118	88.07 147	91.03 142	86.86 163	80.65 143	79.92 133	79.61 106	75.08 112	73.98 143	82.74 112	86.40 178	85.99 186	92.51 193	93.16 123

viewmacassd2359aftdt		86.41 97	85.73 106	87.21 92	89.86 126	94.03 93	90.30 86	83.22 108	80.76 123	79.59 107	73.51 132	76.32 126	85.06 95	90.24 111	91.13 67	95.23 91	94.11 89

PatchMatch-RL		83.34 136	81.36 148	85.65 110	90.33 106	89.52 174	84.36 193	81.82 129	80.87 122	79.29 108	74.04 124	62.85 207	86.05 78	88.40 147	87.04 166	92.04 206	86.77 215

MSDG		83.87 131	81.02 153	87.19 93	92.17 75	89.80 165	89.15 116	85.72 57	80.61 126	79.24 109	66.66 170	68.75 172	82.69 114	87.95 151	87.44 159	94.19 145	85.92 224

MAR-MVS		88.39 64	88.44 62	88.33 71	94.90 46	95.06 65	90.51 80	83.59 93	85.27 71	79.07 110	77.13 89	82.89 69	87.70 56	92.19 66	92.32 56	94.23 144	94.20 88
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
tpm cat1		77.78 198	75.28 227	80.70 173	87.14 162	85.84 221	85.81 174	70.40 232	77.44 154	78.80 111	63.72 196	64.01 200	76.55 185	75.60 253	75.21 251	85.51 256	85.12 226

baseline		84.89 119	86.06 101	83.52 141	87.25 160	89.67 171	87.76 140	75.68 202	84.92 77	78.40 112	80.10 67	80.98 76	80.20 148	86.69 171	87.05 165	91.86 210	92.99 128

Anonymous20231211		84.42 127	83.02 135	86.05 106	88.85 136	92.70 122	88.92 125	83.40 103	79.99 132	78.31 113	55.83 237	78.92 95	83.33 108	89.06 134	89.76 116	93.50 177	94.90 66

MVS_Test		86.93 85	87.24 77	86.56 96	90.10 111	93.47 104	90.31 85	80.12 154	83.55 87	78.12 114	79.58 71	79.80 85	85.45 84	90.17 112	90.59 85	95.29 87	93.53 116

RPSCF		83.46 135	83.36 134	83.59 139	87.75 152	87.35 202	84.82 190	79.46 164	83.84 85	78.12 114	82.69 54	79.87 83	82.60 117	82.47 220	81.13 224	88.78 238	86.13 222

DCV-MVSNet		85.88 107	86.17 98	85.54 113	89.10 134	89.85 163	89.34 107	80.70 142	83.04 89	78.08 116	76.19 99	79.00 93	82.42 118	89.67 124	90.30 96	93.63 174	95.12 63

UGNet		85.90 106	88.23 64	83.18 143	88.96 135	94.10 86	87.52 143	83.60 92	81.66 109	77.90 117	80.76 66	83.19 67	66.70 237	91.13 87	90.71 82	94.39 140	96.06 48
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
CDPH-MVS		91.14 41	92.01 35	90.11 43	96.18 32	96.18 39	94.89 35	88.80 40	88.76 53	77.88 118	89.18 33	87.71 50	87.29 64	93.13 49	93.31 41	95.62 54	95.84 51

CostFormer		80.94 159	80.21 162	81.79 157	87.69 154	88.58 190	87.47 145	70.66 231	80.02 131	77.88 118	73.03 133	71.40 159	78.24 169	79.96 230	79.63 227	88.82 237	88.84 188

dps		78.02 195	75.94 218	80.44 178	86.06 171	86.62 208	82.58 210	69.98 235	75.14 166	77.76 120	69.08 156	59.93 223	78.47 167	79.47 232	77.96 236	87.78 242	83.40 235

OPM-MVS		87.56 76	85.80 104	89.62 52	93.90 55	94.09 87	94.12 40	88.18 41	75.40 165	77.30 121	76.41 97	77.93 105	88.79 45	92.20 65	90.82 78	95.40 70	93.72 110
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
GeoE		84.62 122	83.98 128	85.35 115	89.34 130	92.83 119	88.34 134	78.95 169	79.29 142	77.16 122	68.10 162	74.56 137	83.40 107	89.31 132	89.23 130	94.92 107	94.57 77

0.4-1-1-0.1		79.43 177	77.51 196	81.66 159	79.11 234	88.57 191	87.37 147	75.16 211	73.57 184	75.70 123	67.26 167	67.91 178	80.67 136	78.11 244	79.88 225	91.94 209	87.30 211

0.3-1-1-0.015		79.02 183	76.98 204	81.41 163	78.71 238	88.07 194	87.16 154	74.71 213	72.89 190	75.60 124	66.54 171	67.75 180	80.60 141	77.49 248	79.58 228	91.66 213	86.56 219

usedtu_blend_shiyan5		77.43 202	75.78 221	79.36 187	69.08 258	86.01 213	86.97 159	75.62 205	68.11 219	75.60 124	65.73 177	67.75 180	76.63 182	78.43 240	76.54 243	92.29 200	87.87 203

blend_shiyan4		78.17 193	76.23 212	80.43 179	77.49 243	85.96 219	85.63 178	74.87 212	72.02 195	75.60 124	65.73 177	67.75 180	76.63 182	77.82 246	76.48 247	92.34 198	87.87 203

FE-MVSNET3		77.14 204	75.80 220	78.71 195	69.08 258	86.01 213	83.06 203	75.62 205	68.11 219	75.60 124	65.73 177	67.75 180	76.63 182	78.43 240	76.54 243	92.29 200	88.01 198

GBi-Net		84.51 124	84.80 118	84.17 130	84.20 196	89.95 158	89.70 98	80.37 148	81.17 113	75.50 128	69.63 149	79.69 87	79.75 156	90.73 98	90.72 79	95.52 64	91.71 160

test1		84.51 124	84.80 118	84.17 130	84.20 196	89.95 158	89.70 98	80.37 148	81.17 113	75.50 128	69.63 149	79.69 87	79.75 156	90.73 98	90.72 79	95.52 64	91.71 160

FMVSNet3		84.44 126	84.64 121	84.21 129	84.32 195	90.13 156	89.85 97	80.37 148	81.17 113	75.50 128	69.63 149	79.69 87	79.62 159	89.72 123	90.52 88	95.59 58	91.58 167

HQP-MVS		89.13 57	89.58 56	88.60 66	93.53 58	93.67 100	93.29 47	87.58 48	88.53 54	75.50 128	87.60 36	80.32 80	87.07 66	90.66 103	89.95 110	94.62 126	96.35 45

0.4-1-1-0.2		78.93 185	76.93 205	81.25 168	78.56 239	87.86 196	86.98 158	74.58 214	72.54 193	75.49 132	66.85 169	67.89 179	80.44 142	77.55 247	79.41 231	91.49 216	86.44 220

test2506		85.20 115	84.11 126	86.47 97	91.84 77	95.28 58	89.18 111	84.49 68	82.59 93	75.34 133	74.66 117	58.07 234	81.68 124	93.76 39	92.71 51	96.28 25	91.71 160

MGCFI-Net		88.38 65	89.72 54	86.83 95	91.21 86	95.59 54	91.14 70	82.37 124	90.25 45	75.33 134	81.89 57	79.13 92	85.69 81	90.98 92	93.23 43	95.23 91	96.94 30

FMVSNet2		83.87 131	83.73 131	84.05 134	84.20 196	89.95 158	89.70 98	80.21 153	79.17 144	74.89 135	65.91 174	77.49 110	79.75 156	90.87 94	91.00 72	95.52 64	91.71 160

pmmvs4		79.99 165	78.08 188	82.22 154	83.04 211	87.16 205	84.95 186	78.80 173	78.64 147	74.53 136	64.61 193	59.41 228	79.45 161	84.13 208	84.54 205	92.53 192	88.08 196

thisisatest0530		85.15 117	85.86 102	84.33 126	89.19 133	92.57 127	87.22 152	80.11 155	82.15 104	74.41 137	78.15 82	73.80 146	79.90 152	90.99 90	89.58 119	95.13 99	93.75 109

FC-MVSNet-train		85.18 116	85.31 115	85.03 119	90.67 93	91.62 138	87.66 142	83.61 91	79.75 137	74.37 138	78.69 78	71.21 160	78.91 165	91.23 77	89.96 109	94.96 105	94.69 74

tttt0517		85.11 118	85.81 103	84.30 127	89.24 131	92.68 123	87.12 157	80.11 155	81.98 105	74.31 139	78.08 83	73.57 148	79.90 152	91.01 88	89.58 119	95.11 101	93.77 108

LGP-MVS_train		88.25 68	88.55 60	87.89 80	92.84 70	93.66 101	93.35 46	85.22 62	85.77 68	74.03 140	86.60 41	76.29 129	86.62 72	91.20 79	90.58 86	95.29 87	95.75 52

TSAR-MVS + COLMAP		88.40 62	89.09 58	87.60 85	92.72 71	93.92 98	92.21 54	85.57 58	91.73 32	73.72 141	91.75 25	73.22 152	87.64 59	91.49 74	89.71 117	93.73 168	91.82 158

EPP-MVSNet		86.55 91	87.76 73	85.15 116	90.52 99	94.41 77	87.24 151	82.32 125	81.79 108	73.60 142	78.57 79	82.41 71	82.07 121	91.23 77	90.39 93	95.14 98	95.48 60

ECVR-MVS		85.25 114	84.47 122	86.16 103	91.84 77	95.28 58	89.18 111	84.49 68	82.59 93	73.49 143	66.12 173	69.28 169	81.68 124	93.76 39	92.71 51	96.28 25	91.58 167

IterMVS-LS		83.28 137	82.95 137	83.65 137	88.39 142	88.63 189	86.80 165	78.64 174	76.56 157	73.43 144	72.52 137	75.35 133	80.81 133	86.43 177	88.51 147	93.84 163	92.66 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UA-Net		86.07 102	87.78 72	84.06 133	92.85 69	95.11 64	87.73 141	84.38 72	73.22 187	73.18 145	79.99 69	89.22 40	71.47 219	93.22 48	93.03 45	94.76 117	90.69 175

baseline2		82.80 139	82.86 138	82.73 148	87.68 155	90.50 149	84.92 188	78.93 170	78.07 151	73.06 146	75.08 112	69.77 166	77.31 176	88.90 138	86.94 167	94.50 132	90.74 174

Fast-Effi-MVS+		83.77 133	82.98 136	84.69 120	87.98 150	91.87 136	88.10 137	77.70 183	78.10 150	73.04 147	69.13 155	68.51 173	86.66 71	90.49 105	89.85 113	94.67 123	92.88 131

ET-MVSNet_ETH3D		84.65 121	85.58 111	83.56 140	74.99 252	92.62 126	90.29 88	80.38 147	82.16 102	73.01 148	83.41 49	71.10 161	87.05 67	87.77 152	90.17 102	95.62 54	91.82 158

LS3D		85.96 104	84.37 124	87.81 82	94.13 53	93.27 109	90.26 89	89.00 36	84.91 78	72.84 149	71.74 139	72.47 154	87.45 61	89.53 128	89.09 133	93.20 184	89.60 184

FMVSNet1		81.64 153	80.61 158	82.84 146	82.36 221	89.20 180	88.67 127	79.58 162	70.79 202	72.63 150	58.95 223	72.26 155	79.34 162	90.73 98	90.72 79	94.47 135	91.62 165

Effi-MVS+		85.33 113	85.08 116	85.63 111	89.69 128	93.42 106	89.90 95	80.31 152	79.32 141	72.48 151	73.52 131	74.03 141	86.55 73	90.99 90	89.98 108	94.83 112	94.27 85

test1111		84.86 120	84.21 125	85.61 112	91.75 80	95.14 63	88.63 130	84.57 67	81.88 106	71.21 152	65.66 183	68.51 173	81.19 128	93.74 42	92.68 53	96.31 22	91.86 157

baseline1		84.54 123	84.43 123	84.67 121	90.62 94	91.16 141	88.63 130	83.75 88	79.78 136	71.16 153	75.14 111	74.10 140	77.84 173	91.56 73	90.67 83	96.04 30	88.58 190

CDS-MVSNet		81.63 154	82.09 142	81.09 170	87.21 161	90.28 152	87.46 146	80.33 151	69.06 211	70.66 154	71.30 140	73.87 144	67.99 230	89.58 126	89.87 112	92.87 189	90.69 175
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CHOSEN 280x420		80.28 163	81.66 144	78.67 196	82.92 214	79.24 257	85.36 183	66.79 250	78.11 149	70.32 155	75.03 115	79.87 83	81.09 130	89.07 133	83.16 212	85.54 255	87.17 212

CHOSEN 1792x2688		82.16 145	80.91 156	83.61 138	91.14 87	92.01 133	89.55 104	79.15 168	79.87 135	70.29 156	52.51 246	72.56 153	81.39 126	88.87 139	88.17 150	90.15 231	92.37 151

IS_MVSNet		86.18 100	88.18 65	83.85 136	91.02 89	94.72 74	87.48 144	82.46 123	81.05 117	70.28 157	76.98 91	82.20 73	76.65 181	93.97 35	93.38 38	95.18 94	94.97 65

HyFIR lowres test		81.62 155	79.45 177	84.14 132	91.00 90	93.38 108	88.27 135	78.19 177	76.28 159	70.18 158	48.78 252	73.69 147	83.52 105	87.05 161	87.83 154	93.68 171	89.15 187

PMMVS		81.65 152	84.05 127	78.86 191	78.56 239	82.63 243	83.10 201	67.22 247	81.39 111	70.11 159	84.91 45	79.74 86	82.12 120	87.31 156	85.70 191	92.03 207	86.67 218

thres100view900		82.55 143	81.01 155	84.34 125	90.30 107	92.27 129	89.04 121	82.77 113	75.14 166	69.56 160	65.72 180	63.13 202	79.62 159	89.97 118	89.26 129	94.73 119	91.61 166

tfpn200view9		82.86 138	81.46 146	84.48 123	90.30 107	93.09 111	89.05 120	82.71 114	75.14 166	69.56 160	65.72 180	63.13 202	80.38 145	91.15 84	89.51 121	94.91 108	92.50 148

thres200		82.77 140	81.25 150	84.54 122	90.38 104	93.05 112	89.13 117	82.67 116	74.40 172	69.53 162	65.69 182	63.03 205	80.63 138	91.15 84	89.42 125	94.88 110	92.04 154

MDTV_nov1_ep13		79.14 181	79.49 176	78.74 194	85.40 180	86.89 206	84.32 195	70.29 233	78.85 145	69.42 163	75.37 109	73.29 151	75.64 194	80.61 226	79.48 230	87.36 244	81.91 241

v148		78.59 190	76.84 207	80.62 175	83.61 204	89.16 181	83.65 199	79.24 167	69.38 209	69.34 164	59.88 217	60.41 220	75.19 197	83.81 210	84.63 203	92.70 191	90.63 177

thres400		82.68 141	81.15 151	84.47 124	90.52 99	92.89 117	88.95 123	82.71 114	74.33 173	69.22 165	65.31 186	62.61 208	80.63 138	90.96 93	89.50 122	94.79 114	92.45 150

MS-PatchMatch		81.79 151	81.44 147	82.19 155	90.35 105	89.29 178	88.08 138	75.36 210	77.60 153	69.00 166	64.37 195	78.87 96	77.14 179	88.03 150	85.70 191	93.19 185	86.24 221

UniMVSNet_ETH3D		79.24 180	76.47 209	82.48 150	85.66 177	90.97 144	86.08 172	81.63 132	64.48 238	68.94 167	54.47 239	57.65 236	78.83 166	85.20 197	88.91 140	93.72 169	93.60 114

thres600view7		82.53 144	81.02 153	84.28 128	90.61 96	93.05 112	88.57 132	82.67 116	74.12 177	68.56 168	65.09 189	62.13 213	80.40 144	91.15 84	89.02 136	94.88 110	92.59 142

Vis-MVSNet		84.38 128	86.68 89	81.70 158	87.65 156	94.89 70	88.14 136	80.90 141	74.48 171	68.23 169	77.53 88	80.72 78	69.98 223	92.68 56	91.90 59	95.33 82	94.58 76
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v8		79.90 167	78.39 185	81.66 159	83.97 200	89.81 164	87.16 154	77.40 185	71.49 197	67.71 170	61.24 206	62.49 209	79.83 155	85.48 191	86.17 181	93.89 160	92.02 156

V42		79.59 173	78.43 184	80.94 171	82.79 217	89.71 169	86.66 166	76.73 192	71.38 198	67.42 171	61.01 208	62.30 211	78.39 168	85.56 189	86.48 175	93.65 173	92.60 141

thisisatest0515		79.76 171	80.59 159	78.80 192	84.40 194	88.91 187	79.48 232	76.94 189	72.29 194	67.33 172	67.82 164	65.99 187	70.80 221	88.50 144	87.84 152	93.86 162	92.75 137

tpmrst		76.55 212	75.99 217	77.20 205	87.32 159	83.05 239	82.86 208	65.62 253	78.61 148	67.22 173	69.19 154	65.71 188	75.87 189	76.75 251	75.33 250	84.31 259	83.28 237

Effi-MVS+-dtu		82.05 146	81.76 143	82.38 152	87.72 153	90.56 148	86.90 162	78.05 179	73.85 180	66.85 174	71.29 141	71.90 157	82.00 123	86.64 172	85.48 193	92.76 190	92.58 143

COLMAP_ROB	76.78 15	80.50 162	78.49 182	82.85 145	90.96 91	89.65 172	86.20 171	83.40 103	77.15 155	66.54 175	62.27 200	65.62 189	77.89 172	85.23 194	84.70 202	92.11 205	84.83 229
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		79.51 175	80.15 164	78.75 193	86.58 167	87.70 198	83.07 202	68.53 241	81.31 112	66.40 176	73.83 125	75.38 132	79.30 163	80.49 228	79.39 232	88.63 240	82.96 239

PatchmatchNet		78.67 189	78.85 180	78.46 199	86.85 165	86.03 212	83.77 198	68.11 245	80.88 120	66.19 177	72.90 135	73.40 150	78.06 170	79.25 234	77.71 237	87.75 243	81.75 242
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
blended_shiyan8		75.62 226	74.39 233	77.05 208	69.20 256	86.13 210	83.05 206	75.65 203	68.14 217	66.18 178	58.73 228	64.21 195	75.71 192	78.65 238	76.92 240	92.50 195	87.96 200

wanda-best-256-512		75.51 228	74.25 234	76.99 211	69.08 258	86.01 213	83.06 203	75.62 205	68.11 219	66.14 179	58.89 224	64.15 196	75.77 190	78.43 240	76.54 243	92.29 200	87.59 207

FE-blended-shiyan7		75.51 228	74.25 234	76.99 211	69.08 258	86.01 213	83.06 203	75.62 205	68.12 218	66.14 179	58.89 224	64.15 196	75.77 190	78.43 240	76.54 243	92.29 200	87.59 207

blended_shiyan6		75.62 226	74.41 232	77.03 209	69.20 256	86.12 211	83.03 207	75.65 203	68.09 222	66.14 179	58.83 227	64.22 194	75.70 193	78.65 238	76.94 239	92.49 196	88.01 198

pmmvs-eth3d		74.32 236	71.96 242	77.08 207	77.33 245	82.71 242	78.41 238	76.02 199	66.65 226	65.98 182	54.23 241	49.02 262	73.14 214	82.37 221	82.69 217	91.61 215	86.05 223

v2v482		79.84 169	78.07 189	81.90 156	83.75 201	90.21 155	87.17 153	79.85 160	70.65 203	65.93 183	61.93 202	60.07 221	80.82 132	85.25 193	86.71 170	93.88 161	91.70 164

ACMH+	79.08 13	81.84 150	80.06 165	83.91 135	89.92 124	90.62 147	86.21 170	83.48 99	73.88 179	65.75 184	66.38 172	65.30 190	84.63 97	85.90 184	87.25 162	93.45 178	91.13 173

gbinet_0.2-2-1-0.02		75.42 231	74.57 231	76.42 217	67.86 262	86.00 217	82.79 209	76.24 194	65.77 233	65.59 185	58.60 230	65.11 191	73.76 208	79.11 236	76.90 241	92.27 204	90.47 180

v10		79.62 172	78.19 187	81.28 167	83.73 202	89.69 170	87.27 150	76.86 190	70.50 205	65.46 186	60.58 213	60.47 219	80.44 142	86.91 163	86.63 173	93.93 156	92.55 145

CMPMVS	56.49 17	73.84 238	71.73 244	76.31 221	85.20 184	85.67 223	75.80 246	73.23 221	62.26 244	65.40 187	53.40 244	59.70 225	71.77 218	80.25 229	79.56 229	86.45 252	81.28 246
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CR-MVSNet		78.71 188	78.86 179	78.55 197	85.85 175	85.15 228	82.30 215	68.23 242	74.71 169	65.37 188	64.39 194	69.59 168	77.18 177	85.10 199	84.87 199	92.34 198	88.21 194

Patchmtry						85.54 226	82.30 215	68.23 242		65.37 188

PatchT		76.42 214	77.81 193	74.80 230	78.46 241	84.30 234	71.82 255	65.03 257	73.89 178	65.37 188	61.58 204	66.70 185	77.18 177	85.10 199	84.87 199	90.94 226	88.21 194

dmvs_re		81.08 158	79.92 168	82.44 151	86.66 166	87.70 198	87.91 139	83.30 107	72.86 191	65.29 191	65.76 176	63.43 201	76.69 180	88.93 136	89.50 122	94.80 113	91.23 172

UniMVSNet (Re)		81.22 156	81.08 152	81.39 164	85.35 181	91.76 137	84.93 187	82.88 110	76.13 160	65.02 192	64.94 190	63.09 204	75.17 198	87.71 154	89.04 135	94.97 104	94.88 67

CANet_DTU		85.43 111	87.72 75	82.76 147	90.95 92	93.01 114	89.99 93	75.46 209	82.67 92	64.91 193	83.14 50	80.09 82	80.68 135	92.03 69	91.03 70	94.57 129	92.08 152

usedtu_dtu_shiyan1		79.85 168	79.89 169	79.80 185	77.40 244	89.77 167	85.31 184	80.48 146	77.76 152	64.71 194	61.69 203	67.04 184	75.92 188	87.76 153	87.67 155	94.96 105	87.52 209

TDRefinement		79.05 182	77.05 202	81.39 164	88.45 140	89.00 185	86.92 160	82.65 118	74.21 175	64.41 195	59.17 220	59.16 230	74.52 204	85.23 194	85.09 197	91.37 219	87.51 210

dtuonly		77.14 204	77.32 198	76.92 213	81.74 226	80.84 250	85.46 182	68.93 240	74.15 176	64.33 196	65.39 185	71.91 156	75.62 195	83.27 214	81.21 223	85.47 257	84.45 232

UniMVSNet_NR-MVSNet		81.87 148	81.33 149	82.50 149	85.31 182	91.30 139	85.70 175	84.25 73	75.89 161	64.21 197	66.95 168	64.65 193	80.22 146	87.07 160	89.18 132	95.27 90	94.29 81

DU-MVS		81.20 157	80.30 161	82.25 153	84.98 189	90.94 145	85.70 175	83.58 94	75.74 162	64.21 197	65.30 187	59.60 227	80.22 146	86.89 164	89.31 126	94.77 116	94.29 81

EPMVS		77.53 200	78.07 189	76.90 214	86.89 164	84.91 232	82.18 218	66.64 251	81.00 118	64.11 199	72.75 136	69.68 167	74.42 206	79.36 233	78.13 235	87.14 246	80.68 250

v1144		79.38 179	77.83 192	81.18 169	83.62 203	90.23 153	87.15 156	78.35 176	69.13 210	64.02 200	60.20 215	59.41 228	80.14 150	86.78 167	86.57 174	93.81 165	92.53 147

tpm		76.30 218	76.05 216	76.59 216	86.97 163	83.01 240	83.83 197	67.06 249	71.83 196	63.87 201	69.56 152	62.88 206	73.41 212	79.79 231	78.59 233	84.41 258	86.68 216

pm-mvs1		78.51 192	77.75 194	79.40 186	84.83 192	89.30 177	83.55 200	79.38 165	62.64 243	63.68 202	58.73 228	64.68 192	70.78 222	89.79 122	87.84 152	94.17 146	91.28 171

USDC		80.69 160	79.89 169	81.62 161	86.48 168	89.11 183	86.53 167	78.86 171	81.15 116	63.48 203	72.98 134	59.12 232	81.16 129	87.10 159	85.01 198	93.23 183	84.77 230

Baseline_NR-MVSNet		79.84 169	78.37 186	81.55 162	84.98 189	86.66 207	85.06 185	83.49 96	75.57 164	63.31 204	58.22 232	60.97 217	78.00 171	86.89 164	87.13 163	94.47 135	93.15 125

v144192		78.81 186	77.22 200	80.67 174	82.95 212	89.79 166	86.40 168	77.42 184	68.26 216	63.13 205	59.50 218	58.13 233	80.08 151	85.93 183	86.08 183	94.06 150	92.83 133

MVS-HIRNet		68.83 247	66.39 252	71.68 240	77.58 242	75.52 261	66.45 263	65.05 256	62.16 245	62.84 206	44.76 259	56.60 243	71.96 217	78.04 245	75.06 252	86.18 254	72.56 261

test-LLR		79.47 176	79.84 171	79.03 190	87.47 157	82.40 246	81.24 223	78.05 179	73.72 181	62.69 207	73.76 126	74.42 138	73.49 210	84.61 204	82.99 215	91.25 221	87.01 213

TESTMET0.1,1		77.78 198	79.84 171	75.38 226	80.86 231	82.40 246	81.24 223	62.72 261	73.72 181	62.69 207	73.76 126	74.42 138	73.49 210	84.61 204	82.99 215	91.25 221	87.01 213

v1192		78.94 184	77.33 197	80.82 172	83.25 207	89.90 162	86.91 161	77.72 182	68.63 214	62.61 209	59.17 220	57.53 237	80.62 140	86.89 164	86.47 176	93.79 166	92.75 137

Vis-MVSNet (Re-imp)		83.65 134	86.81 85	79.96 182	90.46 102	92.71 121	84.84 189	82.00 127	80.93 119	62.44 210	76.29 98	82.32 72	65.54 240	92.29 62	91.66 62	94.49 134	91.47 169

ACMH	78.52 14	81.86 149	80.45 160	83.51 142	90.51 101	91.22 140	85.62 179	84.23 74	70.29 207	62.21 211	69.04 157	64.05 199	84.48 98	87.57 155	88.45 148	94.01 153	92.54 146
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test-mter		77.79 197	80.02 166	75.18 227	81.18 230	82.85 241	80.52 229	62.03 262	73.62 183	62.16 212	73.55 130	73.83 145	73.81 207	84.67 203	83.34 211	91.37 219	88.31 193

TinyColmap		76.73 208	73.95 237	79.96 182	85.16 186	85.64 224	82.34 214	78.19 177	70.63 204	62.06 213	60.69 212	49.61 260	80.81 133	85.12 198	83.69 210	91.22 223	82.27 240

IterMVS-SCA-FT		79.41 178	80.20 163	78.49 198	85.88 172	86.26 209	83.95 196	71.94 226	73.55 185	61.94 214	70.48 146	70.50 162	75.23 196	85.81 186	84.61 204	91.99 208	90.18 182

PM-MVS		74.17 237	73.10 238	75.41 225	76.07 248	82.53 244	77.56 242	71.69 227	71.04 199	61.92 215	61.23 207	47.30 264	74.82 202	81.78 223	79.80 226	90.42 228	88.05 197

pmmvs6		74.83 233	72.89 240	77.09 206	82.11 222	87.50 201	80.88 227	76.97 188	52.79 261	61.91 216	46.66 254	60.49 218	69.28 225	86.74 170	85.46 194	91.39 218	90.56 178

v1921920		78.57 191	76.99 203	80.41 180	82.93 213	89.63 173	86.38 169	77.14 187	68.31 215	61.80 217	58.89 224	56.79 240	80.19 149	86.50 176	86.05 185	94.02 152	92.76 136

tfpnnormal		77.46 201	74.86 229	80.49 177	86.34 170	88.92 186	84.33 194	81.26 139	61.39 247	61.70 218	51.99 247	53.66 253	74.84 201	88.63 140	87.38 161	94.50 132	92.08 152

FMVSNet5		75.50 230	76.07 214	74.83 229	76.16 247	81.19 249	81.34 221	70.21 234	73.20 188	61.59 219	58.97 222	68.33 176	68.50 228	85.87 185	85.85 189	91.18 224	79.11 253

pmmvs5		76.93 207	76.33 211	77.62 203	81.97 223	88.40 193	81.32 222	74.35 218	65.42 236	61.42 220	63.07 198	57.95 235	73.23 213	85.60 188	85.35 196	93.41 179	88.55 191

NR-MVSNet		80.25 164	79.98 167	80.56 176	85.20 184	90.94 145	85.65 177	83.58 94	75.74 162	61.36 221	65.30 187	56.75 241	72.38 215	88.46 145	88.80 141	95.16 96	93.87 98

IterMVS		78.79 187	79.71 174	77.71 202	85.26 183	85.91 220	84.54 192	69.84 237	73.38 186	61.25 222	70.53 145	70.35 163	74.43 205	85.21 196	83.80 209	90.95 225	88.77 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v7n		77.22 203	76.23 212	78.38 200	81.89 224	89.10 184	82.24 217	76.36 193	65.96 231	61.21 223	56.56 235	55.79 245	75.07 200	86.55 173	86.68 171	93.52 175	92.95 130

v1240		78.15 194	76.53 208	80.04 181	82.85 216	89.48 176	85.61 180	76.77 191	67.05 224	61.18 224	58.37 231	56.16 244	79.89 154	86.11 182	86.08 183	93.92 157	92.47 149

TAMVS		76.42 214	77.16 201	75.56 224	83.05 210	85.55 225	80.58 228	71.43 228	65.40 237	61.04 225	67.27 166	69.22 171	67.99 230	84.88 202	84.78 201	89.28 236	83.01 238

TranMVSNet+NR-MVSNet		80.52 161	79.84 171	81.33 166	84.92 191	90.39 150	85.53 181	84.22 76	74.27 174	60.68 226	64.93 191	59.96 222	77.48 175	86.75 169	89.28 127	95.12 100	93.29 120

RPMNet		77.07 206	77.63 195	76.42 217	85.56 179	85.15 228	81.37 220	65.27 255	74.71 169	60.29 227	63.71 197	66.59 186	73.64 209	82.71 218	82.12 220	92.38 197	88.39 192

EPNet_dtu		81.98 147	83.82 130	79.83 184	94.10 54	85.97 218	87.29 149	84.08 84	80.61 126	59.96 228	81.62 63	77.19 115	62.91 245	87.21 158	86.38 178	90.66 227	87.77 206
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ADS-MVSNet		74.53 235	75.69 223	73.17 237	81.57 228	80.71 252	79.27 235	63.03 260	79.27 143	59.94 229	67.86 163	68.32 177	71.08 220	77.33 249	76.83 242	84.12 261	79.53 251

EG-PatchMatch MVS		76.40 216	75.47 225	77.48 204	85.86 174	90.22 154	82.45 212	73.96 220	59.64 253	59.60 230	52.75 245	62.20 212	68.44 229	88.23 148	87.50 158	94.55 130	87.78 205

Fast-Effi-MVS+-dtu		79.95 166	80.69 157	79.08 189	86.36 169	89.14 182	85.85 173	72.28 225	72.85 192	59.32 231	70.43 147	68.42 175	77.57 174	86.14 181	86.44 177	93.11 186	91.39 170

MDTV_nov1_ep13_2view		73.21 239	72.91 239	73.56 236	80.01 232	84.28 235	78.62 237	66.43 252	68.64 213	59.12 232	60.39 214	59.69 226	69.81 224	78.82 237	77.43 238	87.36 244	81.11 248

MIMVSNet		74.69 234	75.60 224	73.62 235	76.02 249	85.31 227	81.21 225	67.43 246	71.02 200	59.07 233	54.48 238	64.07 198	66.14 239	86.52 175	86.64 172	91.83 211	81.17 247

TransMVSNet (Re)		76.57 211	75.16 228	78.22 201	85.60 178	87.24 203	82.46 211	81.23 140	59.80 252	59.05 234	57.07 234	59.14 231	66.60 238	88.09 149	86.82 168	94.37 141	87.95 202

anonymousdsp		77.94 196	79.00 178	76.71 215	79.03 235	87.83 197	79.58 231	72.87 223	65.80 232	58.86 235	65.82 175	62.48 210	75.99 187	86.77 168	88.66 143	93.92 157	95.68 56

GA-MVS		79.52 174	79.71 174	79.30 188	85.68 176	90.36 151	84.55 191	78.44 175	70.47 206	57.87 236	68.52 159	61.38 215	76.21 186	89.40 131	87.89 151	93.04 187	89.96 183

SixPastTwentyTwo		76.02 220	75.72 222	76.36 219	83.38 205	87.54 200	75.50 247	76.22 195	65.50 235	57.05 237	70.64 143	53.97 252	74.54 203	80.96 225	82.12 220	91.44 217	89.35 186

RE-MVS-def										56.08 238

pmnet_mix02		71.95 240	71.83 243	72.10 239	81.40 229	80.63 253	73.78 251	72.85 224	70.90 201	54.89 239	62.17 201	57.42 238	62.92 244	76.80 250	73.98 255	86.74 250	80.87 249

PMVS	50.48 18	55.81 259	51.93 262	60.33 257	72.90 254	49.34 270	48.78 269	69.51 238	43.49 267	54.25 240	36.26 268	41.04 271	39.71 265	65.07 263	60.70 264	76.85 267	67.58 264
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CP-MVSNet		76.36 217	76.41 210	76.32 220	82.73 218	88.64 188	79.39 233	79.62 161	67.21 223	53.70 241	60.72 211	55.22 247	67.91 232	83.52 212	86.34 179	94.55 130	93.19 122

usedtu_dtu_shiyan2		62.45 255	61.54 258	63.50 255	49.14 272	78.26 259	71.51 256	67.18 248	43.16 268	53.22 242	33.68 270	45.76 265	53.15 256	74.24 256	74.13 254	86.83 248	81.56 245

FPMVS		63.63 254	60.08 260	67.78 248	80.01 232	71.50 265	72.88 254	69.41 239	61.82 246	53.11 243	45.12 257	42.11 269	50.86 258	66.69 262	63.84 263	80.41 263	69.46 263

PS-CasMVS		75.90 222	75.86 219	75.96 222	82.59 219	88.46 192	79.23 236	79.56 163	66.00 230	52.77 244	59.48 219	54.35 251	67.14 235	83.37 213	86.23 180	94.47 135	93.10 126

WR-MVS_H		75.84 223	76.93 205	74.57 233	82.86 215	89.50 175	78.34 239	79.36 166	66.90 225	52.51 245	60.20 215	59.71 224	59.73 247	83.61 211	85.77 190	94.65 124	92.84 132

FE-MVSNET2		71.00 242	70.45 247	71.65 241	66.32 263	85.00 231	76.33 244	76.20 196	61.03 248	52.47 246	41.50 264	50.21 258	64.44 242	84.97 201	85.46 194	94.16 147	84.97 227

WR-MVS		76.63 210	78.02 191	75.02 228	84.14 199	89.76 168	78.34 239	80.64 145	69.56 208	52.32 247	61.26 205	61.24 216	60.66 246	84.45 206	87.07 164	93.99 154	92.77 135

ambc			61.92 256		70.98 255	73.54 264	63.64 266		60.06 250	52.23 248	38.44 266	19.17 278	57.12 248	82.33 222	75.03 253	83.21 262	84.89 228

PEN-MVS		76.02 220	76.07 214	75.95 223	83.17 209	87.97 195	79.65 230	80.07 158	66.57 227	51.45 249	60.94 209	55.47 246	66.81 236	82.72 217	86.80 169	94.59 127	92.03 155

tmp_tt				32.73 265	43.96 274	21.15 276	26.71 275	8.99 271	65.67 234	51.39 250	56.01 236	42.64 268	11.76 274	56.60 266	50.81 267	53.55 273

CVMVSNet		76.70 209	78.46 183	74.64 232	83.34 206	84.48 233	81.83 219	74.58 214	68.88 212	51.23 251	69.77 148	70.05 164	67.49 233	84.27 207	83.81 208	89.38 235	87.96 200

test0.0.03 1		76.03 219	78.51 181	73.12 238	87.47 157	85.13 230	76.32 245	78.05 179	73.19 189	50.98 252	70.64 143	69.28 169	55.53 251	85.33 192	84.38 206	90.39 229	81.63 244

dtuonlycased		69.72 246	68.74 249	70.86 243	74.97 253	83.54 237	75.33 248	68.22 244	63.98 241	50.82 253	50.34 250	62.09 214	69.26 226	68.11 261	69.75 261	86.54 251	83.37 236

Anonymous20231206		70.80 243	70.59 246	71.04 242	81.60 227	82.49 245	74.64 250	75.87 200	64.17 239	49.27 254	44.85 258	53.59 254	54.68 254	83.07 215	82.34 219	90.17 230	83.65 234

DTE-MVSNet		75.14 232	75.44 226	74.80 230	83.18 208	87.19 204	78.25 241	80.11 155	66.05 229	48.31 255	60.88 210	54.67 248	64.54 241	82.57 219	86.17 181	94.43 138	90.53 179

MDA-MVSNet-bldmvs		66.22 250	64.49 254	68.24 247	61.67 265	82.11 248	70.07 259	76.16 197	59.14 254	47.94 256	54.35 240	35.82 273	67.33 234	64.94 264	75.68 249	86.30 253	79.36 252

N_pmnet		66.85 249	66.63 251	67.11 250	78.73 237	74.66 262	70.53 257	71.07 229	66.46 228	46.54 257	51.68 249	51.91 257	55.48 252	74.68 254	72.38 257	80.29 265	74.65 259

PatchmatchNet3										46.50 258	51.71 248
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
testgi		71.92 241	74.20 236	69.27 246	84.58 193	83.06 238	73.40 252	74.39 217	64.04 240	46.17 259	68.90 158	57.15 239	48.89 260	84.07 209	83.08 214	88.18 241	79.09 254

LTVRE_ROB	74.41 16	75.78 224	74.72 230	77.02 210	85.88 172	89.22 179	82.44 213	77.17 186	50.57 263	45.45 260	65.44 184	52.29 255	81.25 127	85.50 190	87.42 160	89.94 233	92.62 140
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
pmmvs3		61.89 256	61.74 257	62.06 256	64.30 264	70.83 266	64.22 264	52.14 266	48.78 265	44.47 261	41.67 262	41.70 270	63.03 243	76.06 252	76.02 248	84.18 260	77.14 257

new-patchmatchnet		63.80 253	63.31 255	64.37 253	76.49 246	75.99 260	63.73 265	70.99 230	57.27 256	43.08 262	45.86 256	43.80 266	45.13 262	73.20 257	70.68 260	86.80 249	76.34 258

EU-MVSNet		69.98 245	72.30 241	67.28 249	75.67 250	79.39 256	73.12 253	69.94 236	63.59 242	42.80 263	62.93 199	56.71 242	55.07 253	79.13 235	78.55 234	87.06 247	85.82 225

MIMVSNet1		65.00 252	66.24 253	63.55 254	58.41 269	80.01 254	69.00 261	74.03 219	55.81 258	41.88 264	36.81 267	49.48 261	47.89 261	81.32 224	82.40 218	90.08 232	77.88 255

gm-plane-assit		70.29 244	70.65 245	69.88 245	85.03 187	78.50 258	58.41 268	65.47 254	50.39 264	40.88 265	49.60 251	50.11 259	75.14 199	91.43 75	89.78 114	94.32 142	84.73 231

test20.03		68.31 248	70.05 248	66.28 251	82.41 220	80.84 250	67.35 262	76.11 198	58.44 255	40.80 266	53.77 243	54.54 249	42.28 263	83.07 215	81.96 222	88.73 239	77.76 256

FC-MVSNet-test		76.53 213	81.62 145	70.58 244	84.99 188	85.73 222	74.81 249	78.85 172	77.00 156	39.13 267	75.90 102	73.50 149	54.08 255	86.54 174	85.99 186	91.65 214	86.68 216

test_method		41.78 262	48.10 263	34.42 264	10.74 276	19.78 277	44.64 271	17.73 270	59.83 251	38.67 268	35.82 269	54.41 250	34.94 266	62.87 265	43.13 268	59.81 271	60.82 266

FE-MVSNET		66.05 251	67.24 250	64.66 252	59.88 267	79.66 255	69.18 260	74.46 216	55.47 260	37.02 269	41.66 263	48.62 263	55.72 249	80.54 227	83.09 213	91.68 212	81.66 243

gg-mvs-nofinetune		75.64 225	77.26 199	73.76 234	87.92 151	92.20 130	87.32 148	64.67 258	51.92 262	35.35 270	46.44 255	77.05 116	71.97 216	92.64 57	91.02 71	95.34 80	89.53 185

new_pmnet		59.28 257	61.47 259	56.73 258	61.66 266	68.29 267	59.57 267	54.91 263	60.83 249	34.38 271	44.66 260	43.65 267	49.90 259	71.66 258	71.56 259	79.94 266	69.67 262

Gipuma		49.17 261	47.05 264	51.65 259	59.67 268	48.39 271	41.98 272	63.47 259	55.64 259	33.33 272	14.90 272	13.78 280	41.34 264	69.31 260	72.30 258	70.11 268	55.00 269
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX						48.31 272	48.03 270	26.08 269	56.42 257	25.77 273	47.51 253	31.31 274	51.30 257	48.49 268		53.61 272	61.52 265

MVE	30.17 19	30.88 265	33.52 266	27.80 267	23.78 275	39.16 273	18.69 278	46.90 268	21.88 274	15.39 274	14.37 275	7.31 284	24.41 269	41.63 269	56.22 266	37.64 276	54.07 270
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		31.40 264	26.80 269	36.78 262	51.39 271	29.96 274	20.20 276	54.17 264	25.93 273	12.75 275	14.73 273	8.58 282	34.10 268	27.36 271	37.83 269	48.07 274	43.18 273

EMVS		30.49 266	25.44 270	36.39 263	51.47 270	29.89 275	20.17 277	54.00 265	26.49 272	12.02 276	13.94 276	8.84 281	34.37 267	25.04 273	34.37 270	46.29 275	39.53 274

WB-MVS		52.27 260	57.26 261	46.45 260	75.64 251	65.62 268	40.45 274	75.80 201	47.10 266	9.11 277	53.83 242	38.98 272	14.47 273	69.44 259	68.29 262	63.24 270	57.56 268

PMMVS2		41.68 263	44.74 265	38.10 261	46.97 273	52.32 269	40.63 273	48.08 267	35.51 269	7.36 278	26.86 271	24.64 276	16.72 271	55.24 267	59.03 265	68.85 269	59.59 267

VLMVS		8.89 269	13.44 271	3.59 270	5.08 279	6.17 280	2.76 282	0.68 274	15.76 275	2.37 279	14.73 273	16.29 279	7.11 275	9.48 274	8.48 273	3.54 279	23.17 275

VLMVS_CLIP		20.42 267	30.84 267	8.27 268	9.48 277	14.89 278	7.31 280	1.43 272	31.73 271	1.73 280	42.31 261	24.42 277	16.57 272	29.99 270	25.85 271	13.11 277	46.66 271

MVS_clip		18.62 268	29.48 268	5.95 269	5.46 278	10.98 279	4.66 281	0.97 273	34.09 270	0.72 281	40.29 265	25.13 275	17.18 270	27.33 272	23.64 272	6.69 278	44.89 272

GG-mvs-BLEND		57.56 258	82.61 140	28.34 266	0.22 281	90.10 157	79.37 234	0.14 276	79.56 138	0.40 282	71.25 142	83.40 66	0.30 279	86.27 180	83.87 207	89.59 234	83.83 233

testmvs		1.03 271	1.63 273	0.34 272	0.09 282	0.35 282	0.61 283	0.16 275	1.49 277	0.10 283	3.15 278	0.15 285	0.86 278	1.32 276	1.18 275	0.20 280	3.76 278

test123		0.87 272	1.40 274	0.25 273	0.03 283	0.25 283	0.35 284	0.08 277	1.21 278	0.05 284	2.84 279	0.03 286	0.89 277	0.43 277	1.16 276	0.13 281	3.87 277

MVS_baseline		4.92 270	8.41 272	0.85 271	0.32 280	0.47 281	0.13 285	0.00 278	9.53 276	0.00 285	11.57 277	7.80 283	4.61 276	4.54 275	4.62 274	0.04 282	20.32 276

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

PatchmatchNet2					78.78 236	73.76 263	70.51 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												52.02 256	55.56 250	74.53 255	72.48 256	80.30 264	74.43 260
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
9.14												92.16 19

SR-MVS					96.58 26			90.99 24				92.40 15

Anonymous202405211			82.75 139		89.58 129	92.97 115	89.04 121	84.13 81	78.72 146		57.18 233	76.64 122	83.13 110	89.55 127	89.92 111	93.38 180	94.28 84

our_test_3					81.81 225	83.96 236	76.61 243

Patchmatch-RL test							8.55 279

mPP-MVS					97.06 12							88.08 48

NP-MVS									87.47 59

High-resolution multi-view benchmark