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.

MCST-MVS		93.81 17	94.06 20	93.53 16	96.79 23	96.85 21	95.95 14	91.69 16	92.20 26	87.17 32	90.83 28	93.41 7	91.96 14	94.49 25	93.50 31	97.61 1	97.12 23

SF-MVS		94.61 8	94.96 10	94.20 9	96.75 24	97.07 13	95.82 18	92.60 7	93.98 12	91.09 8	95.89 6	92.54 12	91.93 15	94.40 27	93.56 30	97.04 2	97.27 18

DVP-MVS++		95.79 1	96.42 1	95.06 1	97.84 2	98.17 2	97.03 4	92.84 3	96.68 1	92.83 3	95.90 5	94.38 4	92.90 5	95.98 2	94.85 6	96.93 3	98.99 1

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

DVP-MVS		95.56 3	96.26 3	94.73 3	96.93 16	98.19 1	96.62 7	92.81 5	96.15 2	91.73 5	95.01 7	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 4	96.13 4	94.82 2	96.81 22	98.05 4	97.42 1	93.09 1	94.31 9	91.49 6	97.12 1	95.03 3	93.27 3	95.55 7	94.58 13	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
TSAR-MVS + GP.		92.71 28	93.91 22	91.30 35	91.96 73	96.00 40	93.43 41	87.94 41	92.53 21	86.27 40	93.57 15	91.94 19	91.44 24	93.29 44	92.89 46	96.78 7	97.15 22

EC-MVSNet		89.96 47	90.77 43	89.01 55	90.54 93	95.15 58	91.34 62	81.43 112	85.27 63	83.08 55	82.83 48	87.22 49	90.97 29	94.79 19	93.38 35	96.73 8	96.71 35

ETV-MVS		89.22 53	89.76 50	88.60 62	91.60 77	94.61 69	89.48 86	83.46 85	85.20 65	81.58 64	82.75 49	82.59 66	88.80 41	94.57 23	93.28 39	96.68 9	95.31 58

APDe-MVS		95.23 5	95.69 6	94.70 5	97.12 10	97.81 7	97.19 2	92.83 4	95.06 6	90.98 9	96.47 2	92.77 10	93.38 2	95.34 10	94.21 17	96.68 9	98.17 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVS_0304		93.46 20	94.44 17	92.32 28	95.88 34	97.84 6	95.25 26	87.99 40	92.23 25	89.16 21	91.23 25	91.51 22	88.98 39	95.64 6	95.04 3	96.67 11	97.57 14

3Dnovator	85.17 5	90.48 41	89.90 49	91.16 37	94.88 44	95.74 48	93.82 37	85.36 55	89.28 46	87.81 28	74.34 101	87.40 48	88.56 45	93.07 47	93.74 26	96.53 12	95.71 50

TSAR-MVS + MP.		94.48 11	94.97 9	93.90 12	95.53 38	97.01 16	96.69 6	90.71 23	94.24 10	90.92 10	94.97 8	92.19 15	93.03 4	94.83 17	93.60 27	96.51 13	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
CS-MVS		90.34 42	90.58 44	90.07 43	93.11 60	95.82 46	90.57 67	83.62 76	87.07 56	85.35 42	82.98 47	83.47 61	91.37 26	94.94 14	93.37 37	96.37 14	96.41 40

MSP-MVS		95.12 6	95.83 5	94.30 6	96.82 21	97.94 5	96.98 5	92.37 11	95.40 4	90.59 12	96.16 3	93.71 6	92.70 8	94.80 18	94.77 9	96.37 14	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
QAPM		89.49 50	89.58 53	89.38 52	94.73 46	95.94 41	92.35 49	85.00 58	85.69 62	80.03 78	76.97 82	87.81 46	87.87 52	92.18 63	92.10 55	96.33 16	96.40 42

MVS_111021_HR		90.56 40	91.29 38	89.70 48	94.71 47	95.63 49	91.81 57	86.38 49	87.53 54	81.29 66	87.96 33	85.43 53	87.69 54	93.90 34	92.93 44	96.33 16	95.69 51

test1111		84.86 97	84.21 103	85.61 89	91.75 76	95.14 59	88.63 105	84.57 62	81.88 90	71.21 120	65.66 152	68.51 147	81.19 103	93.74 39	92.68 50	96.31 18	91.86 132

CANet		91.33 38	91.46 36	91.18 36	95.01 41	96.71 24	93.77 38	87.39 46	87.72 53	87.26 31	81.77 56	89.73 33	87.32 60	94.43 26	93.86 22	96.31 18	96.02 46

APD-MVS		94.37 12	94.47 16	94.26 7	97.18 8	96.99 17	96.53 8	92.68 6	92.45 23	89.96 16	94.53 11	91.63 21	92.89 6	94.58 22	93.82 23	96.31 18	97.26 19
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test2506		85.20 92	84.11 104	86.47 80	91.84 74	95.28 54	89.18 90	84.49 63	82.59 79	75.34 101	74.66 99	58.07 195	81.68 99	93.76 36	92.71 48	96.28 21	91.71 135

ECVR-MVS		85.25 91	84.47 100	86.16 83	91.84 74	95.28 54	89.18 90	84.49 63	82.59 79	73.49 111	66.12 145	69.28 143	81.68 99	93.76 36	92.71 48	96.28 21	91.58 142

SteuartSystems-ACMMP		94.06 14	94.65 12	93.38 18	96.97 15	97.36 10	96.12 10	91.78 14	92.05 28	87.34 30	94.42 12	90.87 26	91.87 18	95.47 9	94.59 12	96.21 23	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		92.05 32	93.74 23	90.08 42	94.96 42	97.06 14	93.11 45	87.71 44	90.71 37	80.78 71	92.40 22	91.03 24	87.68 55	94.32 28	94.48 14	96.21 23	96.16 44

CNVR-MVS		94.37 12	94.65 12	94.04 10	97.29 6	97.11 12	96.00 11	92.43 10	93.45 15	89.85 18	90.92 26	93.04 9	92.59 10	95.77 5	94.82 7	96.11 25	97.42 17

baseline1		84.54 100	84.43 101	84.67 97	90.62 90	91.16 117	88.63 105	83.75 74	79.78 112	71.16 121	75.14 94	74.10 117	77.84 145	91.56 68	90.67 77	96.04 26	88.58 164

MSLP-MVS++		92.02 34	91.40 37	92.75 23	96.01 32	95.88 44	93.73 40	89.00 33	89.89 45	90.31 14	81.28 60	88.85 39	91.45 22	92.88 51	94.24 16	96.00 27	96.76 32

NCCC		93.69 19	93.66 24	93.72 15	97.37 5	96.66 29	95.93 17	92.50 9	93.40 18	88.35 25	87.36 35	92.33 14	92.18 13	94.89 16	94.09 19	96.00 27	96.91 29

SPE-MVS-test		90.29 43	90.96 39	89.51 51	93.18 59	95.87 45	89.18 90	83.72 75	88.32 51	84.82 47	84.89 43	85.23 54	90.25 33	94.04 29	92.66 51	95.94 29	95.69 51

ACMMP		92.03 33	92.16 32	91.87 34	95.88 34	96.55 31	94.47 35	89.49 32	91.71 31	85.26 43	91.52 24	84.48 57	90.21 34	92.82 52	91.63 59	95.92 30	96.42 39
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
SMA-MVS		94.70 7	95.35 7	93.93 11	97.57 3	97.57 9	95.98 12	91.91 13	94.50 7	90.35 13	93.46 17	92.72 11	91.89 17	95.89 4	95.22 1	95.88 31	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
ACMMPR		93.72 18	93.94 21	93.48 17	97.07 11	96.93 18	95.78 20	90.66 25	93.88 13	89.24 20	93.53 16	89.08 38	92.24 12	93.89 35	93.50 31	95.88 31	96.73 33

HFP-MVS		94.02 15	94.22 19	93.78 13	97.25 7	96.85 21	95.81 19	90.94 22	94.12 11	90.29 15	94.09 14	89.98 32	92.52 11	93.94 33	93.49 33	95.87 33	97.10 24

PVSNet_BlendedMVS		88.19 65	88.00 65	88.42 64	92.71 69	94.82 66	89.08 95	83.81 72	84.91 69	86.38 38	79.14 68	78.11 95	82.66 92	93.05 48	91.10 64	95.86 34	94.86 64

PVSNet_Blended		88.19 65	88.00 65	88.42 64	92.71 69	94.82 66	89.08 95	83.81 72	84.91 69	86.38 38	79.14 68	78.11 95	82.66 92	93.05 48	91.10 64	95.86 34	94.86 64

DeepC-MVS_fast	88.76 1	93.10 23	93.02 30	93.19 21	97.13 9	96.51 33	95.35 25	91.19 19	93.14 20	88.14 26	85.26 41	89.49 35	91.45 22	95.17 11	95.07 2	95.85 36	96.48 37
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 26	93.03 29	92.45 27	97.03 13	96.67 28	95.73 22	87.92 42	90.15 44	86.53 36	92.97 20	88.33 44	91.69 20	93.62 41	93.03 42	95.83 37	96.41 40

SD-MVS		94.53 10	95.22 8	93.73 14	95.69 37	97.03 15	95.77 21	91.95 12	94.41 8	91.35 7	94.97 8	93.34 8	91.80 19	94.72 21	93.99 21	95.82 38	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
DeepC-MVS	87.86 3	92.26 31	91.86 34	92.73 24	96.18 29	96.87 20	95.19 28	91.76 15	92.17 27	86.58 35	81.79 55	85.85 51	90.88 30	94.57 23	94.61 11	95.80 39	97.18 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS					93.11 60	96.70 25	91.91 53			83.95 50		88.82 40				95.79 40

X-MVStestdata					93.11 60	96.70 25	91.91 53			83.95 50		88.82 40				95.79 40

DELS-MVS		89.71 48	89.68 52	89.74 46	93.75 53	96.22 36	93.76 39	85.84 51	82.53 81	85.05 45	78.96 71	84.24 58	84.25 81	94.91 15	94.91 5	95.78 42	96.02 46
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
X-MVS		92.36 30	92.75 31	91.90 33	96.89 17	96.70 25	95.25 26	90.48 28	91.50 33	83.95 50	88.20 32	88.82 40	89.11 38	93.75 38	93.43 34	95.75 43	96.83 31

casdiffmvs		87.45 72	87.15 74	87.79 71	90.15 104	94.22 73	89.96 76	83.93 71	85.08 67	80.91 68	75.81 89	77.88 98	86.08 69	91.86 66	90.86 71	95.74 44	94.37 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CP-MVS		93.25 22	93.26 27	93.24 20	96.84 19	96.51 33	95.52 23	90.61 26	92.37 24	88.88 22	90.91 27	89.52 34	91.91 16	93.64 40	92.78 47	95.69 45	97.09 25

MVSTER		86.03 83	86.12 84	85.93 86	88.62 118	89.93 136	89.33 89	79.91 133	81.87 91	81.35 65	81.07 61	74.91 113	80.66 111	92.13 64	90.10 87	95.68 46	92.80 109

3Dnovator+	86.06 4	91.60 36	90.86 42	92.47 26	96.00 33	96.50 35	94.70 33	87.83 43	90.49 39	89.92 17	74.68 98	89.35 36	90.66 31	94.02 31	94.14 18	95.67 47	96.85 30

OpenMVS	82.53 11	87.71 69	86.84 77	88.73 58	94.42 48	95.06 61	91.02 66	83.49 82	82.50 83	82.24 62	67.62 140	85.48 52	85.56 73	91.19 74	91.30 62	95.67 47	94.75 66

EIA-MVS		87.94 68	88.05 64	87.81 69	91.46 78	95.00 63	88.67 102	82.81 93	82.53 81	80.81 70	80.04 64	80.20 77	87.48 57	92.58 55	91.61 60	95.63 49	94.36 75

ET-MVSNet_ETH3D		84.65 98	85.58 92	83.56 116	74.99 220	92.62 105	90.29 73	80.38 121	82.16 86	73.01 116	83.41 45	71.10 135	87.05 63	87.77 130	90.17 86	95.62 50	91.82 133

CDPH-MVS		91.14 39	92.01 33	90.11 41	96.18 29	96.18 37	94.89 31	88.80 37	88.76 49	77.88 92	89.18 31	87.71 47	87.29 61	93.13 46	93.31 38	95.62 50	95.84 48

MP-MVS		93.35 21	93.59 25	93.08 22	97.39 4	96.82 23	95.38 24	90.71 23	90.82 36	88.07 27	92.83 21	90.29 30	91.32 27	94.03 30	93.19 41	95.61 52	97.16 21
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
FMVSNet3		84.44 103	84.64 99	84.21 105	84.32 170	90.13 131	89.85 78	80.37 122	81.17 96	75.50 97	69.63 125	79.69 83	79.62 131	89.72 106	90.52 81	95.59 53	91.58 142

HPM-MVS++		94.60 9	94.91 11	94.24 8	97.86 1	96.53 32	96.14 9	92.51 8	93.87 14	90.76 11	93.45 18	93.84 5	92.62 9	95.11 13	94.08 20	95.58 54	97.48 15

TPM-MVS					96.31 27	96.02 38	94.89 31			86.52 37	87.18 37	92.17 16	86.76 65			95.56 55	93.85 88
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
casdiffmvs_mvg		87.97 67	87.63 72	88.37 66	90.55 92	94.42 70	91.82 56	84.69 60	84.05 73	82.08 63	76.57 84	79.00 89	85.49 74	92.35 57	92.29 54	95.55 56	94.70 68
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CLD-MVS		88.66 56	88.52 58	88.82 57	91.37 81	94.22 73	92.82 48	82.08 106	88.27 52	85.14 44	81.86 54	78.53 93	85.93 71	91.17 75	90.61 78	95.55 56	95.00 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ACMMP_NAP		93.94 16	94.49 15	93.30 19	97.03 13	97.31 11	95.96 13	91.30 18	93.41 17	88.55 24	93.00 19	90.33 29	91.43 25	95.53 8	94.41 15	95.53 58	97.47 16

GBi-Net		84.51 101	84.80 97	84.17 106	84.20 171	89.95 133	89.70 79	80.37 122	81.17 96	75.50 97	69.63 125	79.69 83	79.75 128	90.73 92	90.72 73	95.52 59	91.71 135

test1		84.51 101	84.80 97	84.17 106	84.20 171	89.95 133	89.70 79	80.37 122	81.17 96	75.50 97	69.63 125	79.69 83	79.75 128	90.73 92	90.72 73	95.52 59	91.71 135

FMVSNet2		83.87 107	83.73 108	84.05 110	84.20 171	89.95 133	89.70 79	80.21 127	79.17 119	74.89 103	65.91 146	77.49 99	79.75 128	90.87 88	91.00 68	95.52 59	91.71 135

DPM-MVS		91.72 35	91.48 35	92.00 31	95.53 38	95.75 47	95.94 15	91.07 20	91.20 34	85.58 41	81.63 58	90.74 27	88.40 47	93.40 42	93.75 25	95.45 62	93.85 88

OPM-MVS		87.56 71	85.80 89	89.62 49	93.90 52	94.09 77	94.12 36	88.18 38	75.40 139	77.30 95	76.41 85	77.93 97	88.79 42	92.20 61	90.82 72	95.40 63	93.72 93
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CSCG		92.76 26	93.16 28	92.29 29	96.30 28	97.74 8	94.67 34	88.98 35	92.46 22	89.73 19	86.67 38	92.15 18	88.69 44	92.26 59	92.92 45	95.40 63	97.89 10

sasdasda		89.36 51	89.92 46	88.70 59	91.38 79	95.92 42	91.81 57	82.61 101	90.37 40	82.73 58	82.09 51	79.28 86	88.30 48	91.17 75	93.59 28	95.36 65	97.04 26

canonicalmvs		89.36 51	89.92 46	88.70 59	91.38 79	95.92 42	91.81 57	82.61 101	90.37 40	82.73 58	82.09 51	79.28 86	88.30 48	91.17 75	93.59 28	95.36 65	97.04 26

IB-MVS	79.09 12	82.60 118	82.19 117	83.07 120	91.08 84	93.55 85	80.90 187	81.35 114	76.56 131	80.87 69	64.81 160	69.97 139	68.87 188	85.64 162	90.06 89	95.36 65	94.74 67
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
gg-mvs-nofinetune		75.64 193	77.26 172	73.76 197	87.92 126	92.20 108	87.32 122	64.67 216	51.92 221	35.35 226	46.44 215	77.05 104	71.97 178	92.64 54	91.02 67	95.34 68	89.53 159

Vis-MVSNet		84.38 105	86.68 81	81.70 134	87.65 131	94.89 64	88.14 111	80.90 117	74.48 145	68.23 137	77.53 79	80.72 74	69.98 185	92.68 53	91.90 56	95.33 69	94.58 71
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	84.37 7	88.91 55	88.93 56	88.89 56	93.00 64	94.85 65	92.00 52	84.84 59	91.68 32	80.05 76	79.77 66	84.56 56	88.17 50	90.11 101	89.00 120	95.30 70	92.57 119
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_Test		86.93 75	87.24 73	86.56 79	90.10 105	93.47 86	90.31 70	80.12 128	83.55 75	78.12 88	79.58 67	79.80 81	85.45 75	90.17 100	90.59 79	95.29 71	93.53 96

LGP-MVS_train		88.25 64	88.55 57	87.89 68	92.84 67	93.66 83	93.35 42	85.22 57	85.77 60	74.03 108	86.60 39	76.29 108	86.62 67	91.20 73	90.58 80	95.29 71	95.75 49

FA-MVS(training)		85.65 87	85.79 90	85.48 91	90.44 98	93.47 86	88.66 104	73.11 183	83.34 76	82.26 60	71.79 114	78.39 94	83.14 88	91.00 83	89.47 107	95.28 73	93.06 102

UniMVSNet_NR-MVSNet		81.87 124	81.33 125	82.50 125	85.31 157	91.30 115	85.70 145	84.25 66	75.89 135	64.21 158	66.95 142	64.65 159	80.22 118	87.07 136	89.18 115	95.27 74	94.29 76

viewmacassd2359aftdt		86.41 79	85.73 91	87.21 75	89.86 108	94.03 79	90.30 71	83.22 90	80.76 105	79.59 81	73.51 108	76.32 107	85.06 77	90.24 99	91.13 63	95.23 75	94.11 82

MGCFI-Net		88.38 62	89.72 51	86.83 78	91.21 82	95.59 50	91.14 65	82.37 104	90.25 42	75.33 102	81.89 53	79.13 88	85.69 72	90.98 86	93.23 40	95.23 75	96.94 28

viewmanbaseed2359cas		87.17 74	86.90 76	87.48 73	90.08 106	94.14 75	90.30 71	83.19 91	84.17 72	80.68 73	76.78 83	77.43 100	85.43 76	90.78 91	90.92 69	95.21 77	94.10 83

IS_MVSNet		86.18 81	88.18 62	83.85 112	91.02 85	94.72 68	87.48 119	82.46 103	81.05 100	70.28 125	76.98 81	82.20 69	76.65 153	93.97 32	93.38 35	95.18 78	94.97 61

train_agg		92.87 25	93.53 26	92.09 30	96.88 18	95.38 52	95.94 15	90.59 27	90.65 38	83.65 53	94.31 13	91.87 20	90.30 32	93.38 43	92.42 52	95.17 79	96.73 33

NR-MVSNet		80.25 140	79.98 143	80.56 149	85.20 159	90.94 120	85.65 147	83.58 80	75.74 136	61.36 182	65.30 155	56.75 202	72.38 177	88.46 124	88.80 122	95.16 80	93.87 87

PVSNet_Blended_VisFu		87.40 73	87.80 67	86.92 77	92.86 65	95.40 51	88.56 108	83.45 86	79.55 115	82.26 60	74.49 100	84.03 59	79.24 136	92.97 50	91.53 61	95.15 81	96.65 36

EPP-MVSNet		86.55 76	87.76 69	85.15 93	90.52 94	94.41 71	87.24 125	82.32 105	81.79 92	73.60 110	78.57 73	82.41 67	82.07 97	91.23 71	90.39 82	95.14 82	95.48 56

thisisatest0530		85.15 94	85.86 87	84.33 102	89.19 114	92.57 106	87.22 126	80.11 129	82.15 88	74.41 105	78.15 75	73.80 122	79.90 124	90.99 84	89.58 102	95.13 83	93.75 92

TranMVSNet+NR-MVSNet		80.52 137	79.84 146	81.33 140	84.92 166	90.39 125	85.53 150	84.22 68	74.27 148	60.68 187	64.93 159	59.96 183	77.48 147	86.75 145	89.28 110	95.12 84	93.29 97

tttt0517		85.11 95	85.81 88	84.30 103	89.24 112	92.68 102	87.12 130	80.11 129	81.98 89	74.31 107	78.08 76	73.57 124	79.90 124	91.01 82	89.58 102	95.11 85	93.77 91

UniMVSNet (Re)		81.22 132	81.08 128	81.39 138	85.35 156	91.76 113	84.93 154	82.88 92	76.13 134	65.02 155	64.94 158	63.09 166	75.17 161	87.71 131	89.04 118	94.97 86	94.88 63

FC-MVSNet-train		85.18 93	85.31 94	85.03 95	90.67 89	91.62 114	87.66 117	83.61 77	79.75 113	74.37 106	78.69 72	71.21 134	78.91 137	91.23 71	89.96 92	94.96 87	94.69 70

GeoE		84.62 99	83.98 106	85.35 92	89.34 111	92.83 98	88.34 109	78.95 143	79.29 117	77.16 96	68.10 137	74.56 114	83.40 86	89.31 114	89.23 113	94.92 88	94.57 72

tfpn200view9		82.86 114	81.46 122	84.48 99	90.30 102	93.09 92	89.05 97	82.71 95	75.14 140	69.56 128	65.72 149	63.13 164	80.38 117	91.15 78	89.51 104	94.91 89	92.50 123

thres600view7		82.53 120	81.02 129	84.28 104	90.61 91	93.05 93	88.57 107	82.67 97	74.12 150	68.56 136	65.09 157	62.13 175	80.40 116	91.15 78	89.02 119	94.88 90	92.59 117

thres200		82.77 116	81.25 126	84.54 98	90.38 99	93.05 93	89.13 94	82.67 97	74.40 146	69.53 130	65.69 151	63.03 167	80.63 112	91.15 78	89.42 108	94.88 90	92.04 129

Effi-MVS+		85.33 90	85.08 95	85.63 88	89.69 109	93.42 88	89.90 77	80.31 126	79.32 116	72.48 119	73.52 107	74.03 118	86.55 68	90.99 84	89.98 91	94.83 92	94.27 80

dmvs_re		81.08 134	79.92 144	82.44 127	86.66 141	87.70 169	87.91 114	83.30 89	72.86 162	65.29 154	65.76 148	63.43 163	76.69 152	88.93 118	89.50 105	94.80 93	91.23 147

thres400		82.68 117	81.15 127	84.47 100	90.52 94	92.89 97	88.95 100	82.71 95	74.33 147	69.22 133	65.31 154	62.61 170	80.63 112	90.96 87	89.50 105	94.79 94	92.45 125

ACMP	83.90 8	88.32 63	88.06 63	88.62 61	92.18 71	93.98 80	91.28 64	85.24 56	86.69 57	81.23 67	85.62 40	75.13 112	87.01 64	89.83 104	89.77 98	94.79 94	95.43 57
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DU-MVS		81.20 133	80.30 137	82.25 129	84.98 164	90.94 120	85.70 145	83.58 80	75.74 136	64.21 158	65.30 155	59.60 188	80.22 118	86.89 140	89.31 109	94.77 96	94.29 76

UA-Net		86.07 82	87.78 68	84.06 109	92.85 66	95.11 60	87.73 116	84.38 65	73.22 159	73.18 113	79.99 65	89.22 37	71.47 181	93.22 45	93.03 42	94.76 97	90.69 150

MVS_111021_LR		90.14 46	90.89 41	89.26 53	93.23 58	94.05 78	90.43 69	84.65 61	90.16 43	84.52 49	90.14 29	83.80 60	87.99 51	92.50 56	90.92 69	94.74 98	94.70 68

thres100view900		82.55 119	81.01 131	84.34 101	90.30 102	92.27 107	89.04 98	82.77 94	75.14 140	69.56 128	65.72 149	63.13 164	79.62 131	89.97 103	89.26 112	94.73 99	91.61 141

AdaColmap		90.29 43	88.38 60	92.53 25	96.10 31	95.19 57	92.98 46	91.40 17	89.08 48	88.65 23	78.35 74	81.44 71	91.30 28	90.81 90	90.21 85	94.72 100	93.59 95

PCF-MVS	84.60 6	88.66 56	87.75 70	89.73 47	93.06 63	96.02 38	93.22 44	90.00 30	82.44 84	80.02 79	77.96 77	85.16 55	87.36 59	88.54 122	88.54 125	94.72 100	95.61 54
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DI_MVS_pp		86.41 79	85.54 93	87.42 74	89.24 112	93.13 91	92.16 51	82.65 99	82.30 85	80.75 72	68.30 136	80.41 75	85.01 78	90.56 97	90.07 88	94.70 102	94.01 84

Fast-Effi-MVS+		83.77 109	82.98 112	84.69 96	87.98 125	91.87 112	88.10 112	77.70 157	78.10 125	73.04 115	69.13 131	68.51 147	86.66 66	90.49 98	89.85 96	94.67 103	92.88 106

WR-MVS_H		75.84 191	76.93 177	74.57 196	82.86 190	89.50 149	78.34 200	79.36 140	66.90 188	52.51 205	60.20 182	59.71 185	59.73 207	83.61 185	85.77 165	94.65 104	92.84 107

OMC-MVS		90.23 45	90.40 45	90.03 44	93.45 56	95.29 53	91.89 55	86.34 50	93.25 19	84.94 46	81.72 57	86.65 50	88.90 40	91.69 67	90.27 84	94.65 104	93.95 86

HQP-MVS		89.13 54	89.58 53	88.60 62	93.53 55	93.67 82	93.29 43	87.58 45	88.53 50	75.50 97	87.60 34	80.32 76	87.07 62	90.66 96	89.95 93	94.62 106	96.35 43

PEN-MVS		76.02 188	76.07 184	75.95 186	83.17 184	87.97 167	79.65 191	80.07 132	66.57 190	51.45 208	60.94 176	55.47 207	66.81 197	82.72 190	86.80 145	94.59 107	92.03 130

ACMM	83.27 10	87.68 70	86.09 85	89.54 50	93.26 57	92.19 109	91.43 61	86.74 48	86.02 59	82.85 57	75.63 90	75.14 111	88.41 46	90.68 95	89.99 90	94.59 107	92.97 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CANet_DTU		85.43 89	87.72 71	82.76 123	90.95 88	93.01 95	89.99 75	75.46 175	82.67 78	64.91 156	83.14 46	80.09 78	80.68 110	92.03 65	91.03 66	94.57 109	92.08 127

CP-MVSNet		76.36 185	76.41 181	76.32 183	82.73 193	88.64 162	79.39 194	79.62 135	67.21 186	53.70 202	60.72 178	55.22 208	67.91 193	83.52 186	86.34 155	94.55 110	93.19 98

EG-PatchMatch MVS		76.40 184	75.47 193	77.48 173	85.86 149	90.22 129	82.45 173	73.96 181	59.64 213	59.60 191	52.75 207	62.20 174	68.44 190	88.23 126	87.50 134	94.55 110	87.78 174

tfpnnormal		77.46 172	74.86 197	80.49 150	86.34 145	88.92 160	84.33 161	81.26 115	61.39 208	61.70 179	51.99 209	53.66 214	74.84 164	88.63 121	87.38 137	94.50 112	92.08 127

baseline2		82.80 115	82.86 114	82.73 124	87.68 130	90.50 124	84.92 155	78.93 144	78.07 126	73.06 114	75.08 95	69.77 140	77.31 148	88.90 119	86.94 143	94.50 112	90.74 149

Vis-MVSNet (Re-imp)		83.65 110	86.81 79	79.96 154	90.46 97	92.71 100	84.84 156	82.00 107	80.93 102	62.44 171	76.29 86	82.32 68	65.54 201	92.29 58	91.66 58	94.49 114	91.47 144

PS-CasMVS		75.90 190	75.86 189	75.96 185	82.59 194	88.46 165	79.23 197	79.56 137	66.00 193	52.77 204	59.48 186	54.35 212	67.14 196	83.37 187	86.23 156	94.47 115	93.10 101

Baseline_NR-MVSNet		79.84 144	78.37 161	81.55 137	84.98 164	86.66 178	85.06 152	83.49 82	75.57 138	63.31 165	58.22 194	60.97 178	78.00 143	86.89 140	87.13 139	94.47 115	93.15 100

FMVSNet1		81.64 129	80.61 134	82.84 122	82.36 196	89.20 154	88.67 102	79.58 136	70.79 171	72.63 118	58.95 190	72.26 131	79.34 134	90.73 92	90.72 73	94.47 115	91.62 140

DTE-MVSNet		75.14 195	75.44 194	74.80 193	83.18 183	87.19 175	78.25 202	80.11 129	66.05 192	48.31 213	60.88 177	54.67 209	64.54 202	82.57 192	86.17 157	94.43 118	90.53 154

PLC	83.76 9	88.61 58	86.83 78	90.70 39	94.22 49	92.63 103	91.50 60	87.19 47	89.16 47	86.87 33	75.51 92	80.87 73	89.98 36	90.01 102	89.20 114	94.41 119	90.45 155
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UGNet		85.90 85	88.23 61	83.18 119	88.96 116	94.10 76	87.52 118	83.60 78	81.66 93	77.90 91	80.76 62	83.19 63	66.70 198	91.13 81	90.71 76	94.39 120	96.06 45
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
TransMVSNet (Re)		76.57 179	75.16 196	78.22 170	85.60 153	87.24 174	82.46 172	81.23 116	59.80 212	59.05 195	57.07 196	59.14 192	66.60 199	88.09 127	86.82 144	94.37 121	87.95 173

gm-plane-assit		70.29 206	70.65 208	69.88 206	85.03 162	78.50 217	58.41 224	65.47 212	50.39 223	40.88 222	49.60 211	50.11 218	75.14 162	91.43 70	89.78 97	94.32 122	84.73 193

CNLPA		88.40 59	87.00 75	90.03 44	93.73 54	94.28 72	89.56 84	85.81 52	91.87 29	87.55 29	69.53 129	81.49 70	89.23 37	89.45 112	88.59 124	94.31 123	93.82 90

MAR-MVS		88.39 61	88.44 59	88.33 67	94.90 43	95.06 61	90.51 68	83.59 79	85.27 63	79.07 84	77.13 80	82.89 65	87.70 53	92.19 62	92.32 53	94.23 124	94.20 81
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
MSDG		83.87 107	81.02 129	87.19 76	92.17 72	89.80 140	89.15 93	85.72 53	80.61 106	79.24 83	66.66 143	68.75 146	82.69 91	87.95 129	87.44 135	94.19 125	85.92 187

pm-mvs1		78.51 164	77.75 169	79.40 157	84.83 167	89.30 151	83.55 167	79.38 139	62.64 204	63.68 163	58.73 192	64.68 158	70.78 184	89.79 105	87.84 130	94.17 126	91.28 146

diffmvs_AUTHOR		86.44 78	86.59 82	86.26 81	88.33 122	92.74 99	89.66 82	81.74 109	85.17 66	80.04 77	77.70 78	77.20 102	83.68 82	89.66 108	89.28 110	94.14 127	94.37 73

CPTT-MVS		91.39 37	90.95 40	91.91 32	95.06 40	95.24 56	95.02 30	88.98 35	91.02 35	86.71 34	84.89 43	88.58 43	91.60 21	90.82 89	89.67 101	94.08 128	96.45 38

v144192		78.81 158	77.22 173	80.67 147	82.95 187	89.79 141	86.40 138	77.42 158	68.26 185	63.13 166	59.50 185	58.13 194	80.08 123	85.93 158	86.08 159	94.06 129	92.83 108

diffmvs		86.52 77	86.76 80	86.23 82	88.31 123	92.63 103	89.58 83	81.61 111	86.14 58	80.26 75	79.00 70	77.27 101	83.58 84	88.94 117	89.06 117	94.05 130	94.29 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v1921920		78.57 163	76.99 176	80.41 152	82.93 188	89.63 147	86.38 139	77.14 161	68.31 184	61.80 178	58.89 191	56.79 201	80.19 121	86.50 152	86.05 161	94.02 131	92.76 111

ACMH	78.52 14	81.86 125	80.45 136	83.51 118	90.51 96	91.22 116	85.62 148	84.23 67	70.29 176	62.21 172	69.04 133	64.05 161	84.48 80	87.57 132	88.45 127	94.01 132	92.54 121
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		76.63 178	78.02 166	75.02 191	84.14 174	89.76 142	78.34 200	80.64 120	69.56 177	52.32 206	61.26 172	61.24 177	60.66 206	84.45 180	87.07 140	93.99 133	92.77 110

v10		79.62 147	78.19 162	81.28 141	83.73 177	89.69 144	87.27 124	76.86 164	70.50 174	65.46 149	60.58 180	60.47 180	80.44 115	86.91 139	86.63 149	93.93 134	92.55 120

anonymousdsp		77.94 167	79.00 153	76.71 179	79.03 208	87.83 168	79.58 192	72.87 184	65.80 195	58.86 196	65.82 147	62.48 172	75.99 156	86.77 144	88.66 123	93.92 135	95.68 53

v1240		78.15 165	76.53 179	80.04 153	82.85 191	89.48 150	85.61 149	76.77 165	67.05 187	61.18 185	58.37 193	56.16 205	79.89 126	86.11 157	86.08 159	93.92 135	92.47 124

v8		79.90 143	78.39 160	81.66 135	83.97 175	89.81 139	87.16 128	77.40 159	71.49 166	67.71 138	61.24 173	62.49 171	79.83 127	85.48 166	86.17 157	93.89 137	92.02 131

v2v482		79.84 144	78.07 164	81.90 132	83.75 176	90.21 130	87.17 127	79.85 134	70.65 172	65.93 147	61.93 170	60.07 182	80.82 107	85.25 168	86.71 146	93.88 138	91.70 139

thisisatest0515		79.76 146	80.59 135	78.80 162	84.40 169	88.91 161	79.48 193	76.94 163	72.29 164	67.33 140	67.82 139	65.99 154	70.80 183	88.50 123	87.84 130	93.86 139	92.75 112

IterMVS-LS		83.28 113	82.95 113	83.65 113	88.39 120	88.63 163	86.80 135	78.64 148	76.56 131	73.43 112	72.52 113	75.35 110	80.81 108	86.43 153	88.51 126	93.84 140	92.66 114
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TSAR-MVS + ACMM		92.97 24	94.51 14	91.16 37	95.88 34	96.59 30	95.09 29	90.45 29	93.42 16	83.01 56	94.68 10	90.74 27	88.74 43	94.75 20	93.78 24	93.82 141	97.63 12

v1144		79.38 153	77.83 167	81.18 142	83.62 178	90.23 128	87.15 129	78.35 150	69.13 179	64.02 161	60.20 182	59.41 189	80.14 122	86.78 143	86.57 150	93.81 142	92.53 122

v1192		78.94 157	77.33 171	80.82 145	83.25 182	89.90 137	86.91 132	77.72 156	68.63 183	62.61 170	59.17 187	57.53 198	80.62 114	86.89 140	86.47 152	93.79 143	92.75 112

TSAR-MVS + COLMAP		88.40 59	89.09 55	87.60 72	92.72 68	93.92 81	92.21 50	85.57 54	91.73 30	73.72 109	91.75 23	73.22 128	87.64 56	91.49 69	89.71 100	93.73 144	91.82 133

UniMVSNet_ETH3D		79.24 154	76.47 180	82.48 126	85.66 152	90.97 119	86.08 142	81.63 110	64.48 200	68.94 135	54.47 201	57.65 197	78.83 138	85.20 172	88.91 121	93.72 145	93.60 94

EPNet		89.60 49	89.91 48	89.24 54	96.45 26	93.61 84	92.95 47	88.03 39	85.74 61	83.36 54	87.29 36	83.05 64	80.98 106	92.22 60	91.85 57	93.69 146	95.58 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		81.62 131	79.45 152	84.14 108	91.00 86	93.38 89	88.27 110	78.19 151	76.28 133	70.18 126	48.78 212	73.69 123	83.52 85	87.05 137	87.83 132	93.68 147	89.15 161

V42		79.59 148	78.43 159	80.94 144	82.79 192	89.71 143	86.66 136	76.73 166	71.38 167	67.42 139	61.01 175	62.30 173	78.39 140	85.56 164	86.48 151	93.65 148	92.60 116

DCV-MVSNet		85.88 86	86.17 83	85.54 90	89.10 115	89.85 138	89.34 88	80.70 118	83.04 77	78.08 90	76.19 87	79.00 89	82.42 95	89.67 107	90.30 83	93.63 149	95.12 59

v7n		77.22 173	76.23 183	78.38 169	81.89 199	89.10 158	82.24 178	76.36 167	65.96 194	61.21 184	56.56 197	55.79 206	75.07 163	86.55 149	86.68 147	93.52 150	92.95 105

Anonymous20231211		84.42 104	83.02 111	86.05 85	88.85 117	92.70 101	88.92 101	83.40 87	79.99 109	78.31 87	55.83 199	78.92 91	83.33 87	89.06 116	89.76 99	93.50 151	94.90 62

ACMH+	79.08 13	81.84 126	80.06 141	83.91 111	89.92 107	90.62 122	86.21 140	83.48 84	73.88 152	65.75 148	66.38 144	65.30 157	84.63 79	85.90 159	87.25 138	93.45 152	91.13 148

pmmvs5		76.93 175	76.33 182	77.62 172	81.97 198	88.40 166	81.32 183	74.35 179	65.42 198	61.42 181	63.07 166	57.95 196	73.23 175	85.60 163	85.35 170	93.41 153	88.55 165

Anonymous202405211			82.75 115		89.58 110	92.97 96	89.04 98	84.13 69	78.72 121		57.18 195	76.64 106	83.13 89	89.55 110	89.92 94	93.38 154	94.28 79

viewmambaseed2359dif		85.52 88	85.01 96	86.12 84	88.39 120	91.96 111	89.39 87	81.43 112	82.16 86	80.47 74	75.52 91	76.85 105	83.66 83	87.03 138	87.60 133	93.37 155	93.98 85

USDC		80.69 136	79.89 145	81.62 136	86.48 143	89.11 157	86.53 137	78.86 145	81.15 99	63.48 164	72.98 110	59.12 193	81.16 104	87.10 135	85.01 172	93.23 156	84.77 192

LS3D		85.96 84	84.37 102	87.81 69	94.13 50	93.27 90	90.26 74	89.00 33	84.91 69	72.84 117	71.74 115	72.47 130	87.45 58	89.53 111	89.09 116	93.20 157	89.60 158

MS-PatchMatch		81.79 127	81.44 123	82.19 131	90.35 100	89.29 152	88.08 113	75.36 176	77.60 127	69.00 134	64.37 163	78.87 92	77.14 151	88.03 128	85.70 166	93.19 158	86.24 184

Fast-Effi-MVS+-dtu		79.95 142	80.69 133	79.08 159	86.36 144	89.14 156	85.85 143	72.28 186	72.85 163	59.32 192	70.43 123	68.42 149	77.57 146	86.14 156	86.44 153	93.11 159	91.39 145

GA-MVS		79.52 149	79.71 149	79.30 158	85.68 151	90.36 126	84.55 158	78.44 149	70.47 175	57.87 197	68.52 135	61.38 176	76.21 155	89.40 113	87.89 129	93.04 160	89.96 157

DeepPCF-MVS	88.51 2	92.64 29	94.42 18	90.56 40	94.84 45	96.92 19	91.31 63	89.61 31	95.16 5	84.55 48	89.91 30	91.45 23	90.15 35	95.12 12	94.81 8	92.90 161	97.58 13

CDS-MVSNet		81.63 130	82.09 118	81.09 143	87.21 136	90.28 127	87.46 121	80.33 125	69.06 180	70.66 122	71.30 116	73.87 120	67.99 191	89.58 109	89.87 95	92.87 162	90.69 150
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		82.05 122	81.76 119	82.38 128	87.72 128	90.56 123	86.90 133	78.05 153	73.85 153	66.85 142	71.29 117	71.90 132	82.00 98	86.64 148	85.48 168	92.76 163	92.58 118

v148		78.59 162	76.84 178	80.62 148	83.61 179	89.16 155	83.65 166	79.24 141	69.38 178	69.34 132	59.88 184	60.41 181	75.19 160	83.81 184	84.63 177	92.70 164	90.63 152

pmmvs4		79.99 141	78.08 163	82.22 130	83.04 186	87.16 176	84.95 153	78.80 147	78.64 122	74.53 104	64.61 161	59.41 189	79.45 133	84.13 182	84.54 179	92.53 165	88.08 170

viewmsd2359difaftdt		84.31 106	83.65 109	85.07 94	88.07 124	91.03 118	86.86 134	80.65 119	79.92 110	79.61 80	75.08 95	73.98 119	82.74 90	86.40 154	85.99 162	92.51 166	93.16 99

RPMNet		77.07 174	77.63 170	76.42 181	85.56 154	85.15 191	81.37 181	65.27 213	74.71 143	60.29 188	63.71 165	66.59 153	73.64 171	82.71 191	82.12 193	92.38 167	88.39 166

CR-MVSNet		78.71 160	78.86 154	78.55 166	85.85 150	85.15 191	82.30 176	68.23 202	74.71 143	65.37 151	64.39 162	69.59 142	77.18 149	85.10 174	84.87 173	92.34 168	88.21 168

COLMAP_ROB	76.78 15	80.50 138	78.49 157	82.85 121	90.96 87	89.65 146	86.20 141	83.40 87	77.15 129	66.54 143	62.27 168	65.62 156	77.89 144	85.23 169	84.70 176	92.11 169	84.83 191
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchMatch-RL		83.34 112	81.36 124	85.65 87	90.33 101	89.52 148	84.36 160	81.82 108	80.87 104	79.29 82	74.04 102	62.85 169	86.05 70	88.40 125	87.04 142	92.04 170	86.77 180

PMMVS		81.65 128	84.05 105	78.86 161	78.56 210	82.63 204	83.10 168	67.22 206	81.39 94	70.11 127	84.91 42	79.74 82	82.12 96	87.31 133	85.70 166	92.03 171	86.67 183

IterMVS-SCA-FT		79.41 152	80.20 139	78.49 167	85.88 147	86.26 180	83.95 163	71.94 187	73.55 157	61.94 175	70.48 122	70.50 136	75.23 159	85.81 161	84.61 178	91.99 172	90.18 156

baseline		84.89 96	86.06 86	83.52 117	87.25 135	89.67 145	87.76 115	75.68 174	84.92 68	78.40 86	80.10 63	80.98 72	80.20 120	86.69 147	87.05 141	91.86 173	92.99 103

MIMVSNet		74.69 197	75.60 192	73.62 198	76.02 217	85.31 190	81.21 186	67.43 205	71.02 169	59.07 194	54.48 200	64.07 160	66.14 200	86.52 151	86.64 148	91.83 174	81.17 205

FC-MVSNet-test		76.53 181	81.62 121	70.58 205	84.99 163	85.73 185	74.81 208	78.85 146	77.00 130	39.13 224	75.90 88	73.50 125	54.08 213	86.54 150	85.99 162	91.65 175	86.68 181

pmmvs-eth3d		74.32 199	71.96 205	77.08 176	77.33 213	82.71 203	78.41 199	76.02 171	66.65 189	65.98 146	54.23 203	49.02 221	73.14 176	82.37 194	82.69 190	91.61 176	86.05 186

SixPastTwentyTwo		76.02 188	75.72 190	76.36 182	83.38 180	87.54 171	75.50 207	76.22 168	65.50 197	57.05 198	70.64 119	53.97 213	74.54 166	80.96 198	82.12 193	91.44 177	89.35 160

pmmvs6		74.83 196	72.89 203	77.09 175	82.11 197	87.50 172	80.88 188	76.97 162	52.79 220	61.91 177	46.66 214	60.49 179	69.28 187	86.74 146	85.46 169	91.39 178	90.56 153

test-mter		77.79 168	80.02 142	75.18 190	81.18 204	82.85 202	80.52 190	62.03 220	73.62 156	62.16 173	73.55 106	73.83 121	73.81 170	84.67 177	83.34 185	91.37 179	88.31 167

TDRefinement		79.05 156	77.05 175	81.39 138	88.45 119	89.00 159	86.92 131	82.65 99	74.21 149	64.41 157	59.17 187	59.16 191	74.52 167	85.23 169	85.09 171	91.37 179	87.51 176

test-LLR		79.47 151	79.84 146	79.03 160	87.47 132	82.40 207	81.24 184	78.05 153	73.72 154	62.69 168	73.76 104	74.42 115	73.49 172	84.61 178	82.99 188	91.25 181	87.01 178

TESTMET0.1,1		77.78 169	79.84 146	75.38 189	80.86 205	82.40 207	81.24 184	62.72 219	73.72 154	62.69 168	73.76 104	74.42 115	73.49 172	84.61 178	82.99 188	91.25 181	87.01 178

TinyColmap		76.73 176	73.95 200	79.96 154	85.16 161	85.64 187	82.34 175	78.19 151	70.63 173	62.06 174	60.69 179	49.61 219	80.81 108	85.12 173	83.69 184	91.22 183	82.27 200

FMVSNet5		75.50 194	76.07 184	74.83 192	76.16 215	81.19 210	81.34 182	70.21 195	73.20 160	61.59 180	58.97 189	68.33 150	68.50 189	85.87 160	85.85 164	91.18 184	79.11 211

IterMVS		78.79 159	79.71 149	77.71 171	85.26 158	85.91 183	84.54 159	69.84 198	73.38 158	61.25 183	70.53 121	70.35 137	74.43 168	85.21 171	83.80 183	90.95 185	88.77 163
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchT		76.42 182	77.81 168	74.80 193	78.46 211	84.30 196	71.82 214	65.03 215	73.89 151	65.37 151	61.58 171	66.70 152	77.18 149	85.10 174	84.87 173	90.94 186	88.21 168

EPNet_dtu		81.98 123	83.82 107	79.83 156	94.10 51	85.97 182	87.29 123	84.08 70	80.61 106	59.96 189	81.62 59	77.19 103	62.91 205	87.21 134	86.38 154	90.66 187	87.77 175
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PM-MVS		74.17 200	73.10 201	75.41 188	76.07 216	82.53 205	77.56 203	71.69 188	71.04 168	61.92 176	61.23 174	47.30 222	74.82 165	81.78 196	79.80 197	90.42 188	88.05 171

test0.0.03 1		76.03 187	78.51 156	73.12 201	87.47 132	85.13 193	76.32 205	78.05 153	73.19 161	50.98 211	70.64 119	69.28 143	55.53 209	85.33 167	84.38 180	90.39 189	81.63 203

Anonymous20231206		70.80 205	70.59 209	71.04 204	81.60 201	82.49 206	74.64 209	75.87 172	64.17 201	49.27 212	44.85 218	53.59 215	54.68 212	83.07 188	82.34 192	90.17 190	83.65 195

CHOSEN 1792x2688		82.16 121	80.91 132	83.61 114	91.14 83	92.01 110	89.55 85	79.15 142	79.87 111	70.29 124	52.51 208	72.56 129	81.39 101	88.87 120	88.17 128	90.15 191	92.37 126

MIMVSNet1		65.00 212	66.24 213	63.55 214	58.41 227	80.01 214	69.00 217	74.03 180	55.81 218	41.88 221	36.81 223	49.48 220	47.89 218	81.32 197	82.40 191	90.08 192	77.88 213

LTVRE_ROB	74.41 16	75.78 192	74.72 198	77.02 177	85.88 147	89.22 153	82.44 174	77.17 160	50.57 222	45.45 217	65.44 153	52.29 216	81.25 102	85.50 165	87.42 136	89.94 193	92.62 115
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
GG-mvs-BLEND		57.56 217	82.61 116	28.34 225	0.22 234	90.10 132	79.37 195	0.14 231	79.56 114	0.40 235	71.25 118	83.40 62	0.30 232	86.27 155	83.87 181	89.59 194	83.83 194

CVMVSNet		76.70 177	78.46 158	74.64 195	83.34 181	84.48 195	81.83 180	74.58 177	68.88 181	51.23 210	69.77 124	70.05 138	67.49 194	84.27 181	83.81 182	89.38 195	87.96 172

TAMVS		76.42 182	77.16 174	75.56 187	83.05 185	85.55 188	80.58 189	71.43 189	65.40 199	61.04 186	67.27 141	69.22 145	67.99 191	84.88 176	84.78 175	89.28 196	83.01 198

CostFormer		80.94 135	80.21 138	81.79 133	87.69 129	88.58 164	87.47 120	70.66 192	80.02 108	77.88 92	73.03 109	71.40 133	78.24 141	79.96 202	79.63 198	88.82 197	88.84 162

RPSCF		83.46 111	83.36 110	83.59 115	87.75 127	87.35 173	84.82 157	79.46 138	83.84 74	78.12 88	82.69 50	79.87 79	82.60 94	82.47 193	81.13 196	88.78 198	86.13 185

test20.03		68.31 209	70.05 210	66.28 212	82.41 195	80.84 211	67.35 218	76.11 170	58.44 215	40.80 223	53.77 205	54.54 210	42.28 220	83.07 188	81.96 195	88.73 199	77.76 214

SCA		79.51 150	80.15 140	78.75 163	86.58 142	87.70 169	83.07 169	68.53 201	81.31 95	66.40 144	73.83 103	75.38 109	79.30 135	80.49 200	79.39 201	88.63 200	82.96 199

testgi		71.92 204	74.20 199	69.27 207	84.58 168	83.06 199	73.40 211	74.39 178	64.04 202	46.17 216	68.90 134	57.15 200	48.89 217	84.07 183	83.08 187	88.18 201	79.09 212

dps		78.02 166	75.94 188	80.44 151	86.06 146	86.62 179	82.58 171	69.98 196	75.14 140	77.76 94	69.08 132	59.93 184	78.47 139	79.47 204	77.96 205	87.78 202	83.40 196

PatchmatchNet		78.67 161	78.85 155	78.46 168	86.85 140	86.03 181	83.77 165	68.11 204	80.88 103	66.19 145	72.90 111	73.40 126	78.06 142	79.25 206	77.71 206	87.75 203	81.75 202
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13_2view		73.21 202	72.91 202	73.56 199	80.01 206	84.28 197	78.62 198	66.43 210	68.64 182	59.12 193	60.39 181	59.69 187	69.81 186	78.82 208	77.43 207	87.36 204	81.11 206

MDTV_nov1_ep13		79.14 155	79.49 151	78.74 164	85.40 155	86.89 177	84.32 162	70.29 194	78.85 120	69.42 131	75.37 93	73.29 127	75.64 158	80.61 199	79.48 200	87.36 204	81.91 201

EPMVS		77.53 171	78.07 164	76.90 178	86.89 139	84.91 194	82.18 179	66.64 209	81.00 101	64.11 160	72.75 112	69.68 141	74.42 169	79.36 205	78.13 204	87.14 206	80.68 208

EU-MVSNet		69.98 207	72.30 204	67.28 210	75.67 218	79.39 215	73.12 212	69.94 197	63.59 203	42.80 220	62.93 167	56.71 203	55.07 211	79.13 207	78.55 203	87.06 207	85.82 188

new-patchmatchnet		63.80 213	63.31 215	64.37 213	76.49 214	75.99 218	63.73 221	70.99 191	57.27 216	43.08 219	45.86 216	43.80 223	45.13 219	73.20 216	70.68 219	86.80 208	76.34 216

pmnet_mix02		71.95 203	71.83 206	72.10 202	81.40 203	80.63 213	73.78 210	72.85 185	70.90 170	54.89 200	62.17 169	57.42 199	62.92 204	76.80 211	73.98 215	86.74 209	80.87 207

CMPMVS	56.49 17	73.84 201	71.73 207	76.31 184	85.20 159	85.67 186	75.80 206	73.23 182	62.26 205	65.40 150	53.40 206	59.70 186	71.77 180	80.25 201	79.56 199	86.45 210	81.28 204
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDA-MVSNet-bldmvs		66.22 211	64.49 214	68.24 208	61.67 224	82.11 209	70.07 216	76.16 169	59.14 214	47.94 214	54.35 202	35.82 230	67.33 195	64.94 222	75.68 210	86.30 211	79.36 210

MVS-HIRNet		68.83 208	66.39 212	71.68 203	77.58 212	75.52 219	66.45 219	65.05 214	62.16 206	62.84 167	44.76 219	56.60 204	71.96 179	78.04 209	75.06 213	86.18 212	72.56 218

CHOSEN 280x420		80.28 139	81.66 120	78.67 165	82.92 189	79.24 216	85.36 151	66.79 208	78.11 124	70.32 123	75.03 97	79.87 79	81.09 105	89.07 115	83.16 186	85.54 213	87.17 177

tpm cat1		77.78 169	75.28 195	80.70 146	87.14 137	85.84 184	85.81 144	70.40 193	77.44 128	78.80 85	63.72 164	64.01 162	76.55 154	75.60 214	75.21 212	85.51 214	85.12 189

tpm		76.30 186	76.05 186	76.59 180	86.97 138	83.01 201	83.83 164	67.06 207	71.83 165	63.87 162	69.56 128	62.88 168	73.41 174	79.79 203	78.59 202	84.41 215	86.68 181

tpmrst		76.55 180	75.99 187	77.20 174	87.32 134	83.05 200	82.86 170	65.62 211	78.61 123	67.22 141	69.19 130	65.71 155	75.87 157	76.75 212	75.33 211	84.31 216	83.28 197

pmmvs3		61.89 215	61.74 217	62.06 215	64.30 223	70.83 223	64.22 220	52.14 224	48.78 224	44.47 218	41.67 221	41.70 227	63.03 203	76.06 213	76.02 209	84.18 217	77.14 215

ADS-MVSNet		74.53 198	75.69 191	73.17 200	81.57 202	80.71 212	79.27 196	63.03 218	79.27 118	59.94 190	67.86 138	68.32 151	71.08 182	77.33 210	76.83 208	84.12 218	79.53 209

ambc			61.92 216		70.98 222	73.54 221	63.64 222		60.06 210	52.23 207	38.44 222	19.17 233	57.12 208	82.33 195	75.03 214	83.21 219	84.89 190

FPMVS		63.63 214	60.08 219	67.78 209	80.01 206	71.50 222	72.88 213	69.41 200	61.82 207	53.11 203	45.12 217	42.11 226	50.86 215	66.69 220	63.84 221	80.41 220	69.46 220

N_pmnet		66.85 210	66.63 211	67.11 211	78.73 209	74.66 220	70.53 215	71.07 190	66.46 191	46.54 215	51.68 210	51.91 217	55.48 210	74.68 215	72.38 216	80.29 221	74.65 217

new_pmnet		59.28 216	61.47 218	56.73 217	61.66 225	68.29 224	59.57 223	54.91 221	60.83 209	34.38 227	44.66 220	43.65 224	49.90 216	71.66 217	71.56 218	79.94 222	69.67 219

PMVS	50.48 18	55.81 218	51.93 221	60.33 216	72.90 221	49.34 227	48.78 225	69.51 199	43.49 226	54.25 201	36.26 224	41.04 228	39.71 222	65.07 221	60.70 222	76.85 223	67.58 221
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		49.17 220	47.05 223	51.65 218	59.67 226	48.39 228	41.98 228	63.47 217	55.64 219	33.33 228	14.90 227	13.78 234	41.34 221	69.31 219	72.30 217	70.11 224	55.00 226
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.68 222	44.74 224	38.10 220	46.97 230	52.32 226	40.63 229	48.08 225	35.51 227	7.36 234	26.86 226	24.64 232	16.72 227	55.24 225	59.03 223	68.85 225	59.59 224

WB-MVS		52.27 219	57.26 220	46.45 219	75.64 219	65.62 225	40.45 230	75.80 173	47.10 225	9.11 233	53.83 204	38.98 229	14.47 228	69.44 218	68.29 220	63.24 226	57.56 225

test_method		41.78 221	48.10 222	34.42 223	10.74 233	19.78 234	44.64 227	17.73 228	59.83 211	38.67 225	35.82 225	54.41 211	34.94 223	62.87 223	43.13 226	59.81 227	60.82 223

DeepMVS_CX						48.31 229	48.03 226	26.08 227	56.42 217	25.77 229	47.51 213	31.31 231	51.30 214	48.49 226		53.61 228	61.52 222

tmp_tt				32.73 224	43.96 231	21.15 233	26.71 231	8.99 229	65.67 196	51.39 209	56.01 198	42.64 225	11.76 229	56.60 224	50.81 225	53.55 229

E-PMN		31.40 223	26.80 226	36.78 221	51.39 229	29.96 231	20.20 232	54.17 222	25.93 229	12.75 231	14.73 228	8.58 236	34.10 225	27.36 228	37.83 227	48.07 230	43.18 228

EMVS		30.49 225	25.44 227	36.39 222	51.47 228	29.89 232	20.17 233	54.00 223	26.49 228	12.02 232	13.94 230	8.84 235	34.37 224	25.04 229	34.37 228	46.29 231	39.53 229

MVE	30.17 19	30.88 224	33.52 225	27.80 226	23.78 232	39.16 230	18.69 234	46.90 226	21.88 230	15.39 230	14.37 229	7.31 237	24.41 226	41.63 227	56.22 224	37.64 232	54.07 227
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		1.03 226	1.63 228	0.34 227	0.09 235	0.35 235	0.61 236	0.16 230	1.49 231	0.10 236	3.15 231	0.15 238	0.86 231	1.32 230	1.18 229	0.20 233	3.76 231

test123		0.87 227	1.40 229	0.25 228	0.03 236	0.25 236	0.35 237	0.08 232	1.21 232	0.05 237	2.84 232	0.03 239	0.89 230	0.43 231	1.16 230	0.13 234	3.87 230

uanet_test		0.00 228	0.00 230	0.00 229	0.00 237	0.00 237	0.00 238	0.00 233	0.00 233	0.00 238	0.00 233	0.00 240	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

sosnet-low-res		0.00 228	0.00 230	0.00 229	0.00 237	0.00 237	0.00 238	0.00 233	0.00 233	0.00 238	0.00 233	0.00 240	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

sosnet		0.00 228	0.00 230	0.00 229	0.00 237	0.00 237	0.00 238	0.00 233	0.00 233	0.00 238	0.00 233	0.00 240	0.00 233	0.00 232	0.00 231	0.00 235	0.00 232

RE-MVS-def										56.08 199

9.14												92.16 17

SR-MVS					96.58 25			90.99 21				92.40 13

our_test_3					81.81 200	83.96 198	76.61 204

MTAPA										92.97 2		91.03 24

MTMP										93.14 1		90.21 31

Patchmatch-RL test							8.55 235

mPP-MVS					97.06 12							88.08 45

NP-MVS									87.47 55

Patchmtry						85.54 189	82.30 176	68.23 202		65.37 151

High-resolution multi-view benchmark