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 19	93.53 16	96.79 23	96.85 20	95.95 14	91.69 16	92.20 25	87.17 31	90.83 27	93.41 7	91.96 14	94.49 25	93.50 31	97.61 1	97.12 22

SF-MVS		94.61 8	94.96 10	94.20 9	96.75 24	97.07 12	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 17

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 5	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 3	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 8	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 6	94.58 12	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 27	93.91 21	91.30 34	91.96 73	96.00 40	93.43 41	87.94 40	92.53 21	86.27 39	93.57 15	91.94 19	91.44 24	93.29 44	92.89 46	96.78 7	97.15 21

EC-MVSNet		89.96 47	90.77 43	89.01 55	90.54 93	95.15 58	91.34 62	81.43 109	85.27 63	83.08 54	82.83 47	87.22 49	90.97 29	94.79 18	93.38 35	96.73 8	96.71 34

ETV-MVS		89.22 53	89.76 50	88.60 62	91.60 77	94.61 69	89.48 83	83.46 85	85.20 65	81.58 64	82.75 48	82.59 66	88.80 40	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 6	97.19 2	92.83 4	95.06 6	90.98 9	96.47 2	92.77 10	93.38 2	95.34 9	94.21 16	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		90.88 39	91.35 37	90.34 40	93.91 51	96.79 23	94.49 34	86.54 48	86.57 57	82.85 56	81.68 57	89.70 33	87.57 56	94.64 21	93.93 21	96.67 11	96.15 44

3Dnovator	85.17 5	90.48 41	89.90 49	91.16 36	94.88 43	95.74 48	93.82 37	85.36 55	89.28 45	87.81 27	74.34 97	87.40 48	88.56 44	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 37	97.01 15	96.69 6	90.71 23	94.24 10	90.92 10	94.97 8	92.19 15	93.03 4	94.83 16	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 55	85.35 41	82.98 46	83.47 61	91.37 26	94.94 13	93.37 37	96.37 14	96.41 39

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 17	94.77 8	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 45	95.94 41	92.35 49	85.00 58	85.69 62	80.03 75	76.97 81	87.81 46	87.87 51	92.18 63	92.10 55	96.33 16	96.40 41

MVS_111021_HR		90.56 40	91.29 38	89.70 48	94.71 46	95.63 49	91.81 57	86.38 49	87.53 53	81.29 66	87.96 32	85.43 53	87.69 53	93.90 34	92.93 44	96.33 16	95.69 51

test1111		84.86 93	84.21 99	85.61 85	91.75 76	95.14 59	88.63 101	84.57 62	81.88 87	71.21 115	65.66 147	68.51 142	81.19 98	93.74 39	92.68 50	96.31 18	91.86 127

CANet		91.33 37	91.46 35	91.18 35	95.01 40	96.71 24	93.77 38	87.39 45	87.72 52	87.26 30	81.77 55	89.73 32	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 16	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 18
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test2506		85.20 88	84.11 100	86.47 78	91.84 74	95.28 54	89.18 86	84.49 63	82.59 77	75.34 96	74.66 95	58.07 190	81.68 94	93.76 36	92.71 48	96.28 21	91.71 130

ECVR-MVS		85.25 87	84.47 96	86.16 80	91.84 74	95.28 54	89.18 86	84.49 63	82.59 77	73.49 106	66.12 140	69.28 138	81.68 94	93.76 36	92.71 48	96.28 21	91.58 137

SteuartSystems-ACMMP		94.06 14	94.65 12	93.38 18	96.97 15	97.36 9	96.12 10	91.78 14	92.05 27	87.34 29	94.42 12	90.87 25	91.87 18	95.47 8	94.59 11	96.21 23	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		92.05 31	93.74 22	90.08 42	94.96 41	97.06 13	93.11 45	87.71 43	90.71 36	80.78 71	92.40 22	91.03 23	87.68 54	94.32 28	94.48 13	96.21 23	96.16 43

CNVR-MVS		94.37 12	94.65 12	94.04 10	97.29 6	97.11 11	96.00 11	92.43 10	93.45 15	89.85 18	90.92 25	93.04 9	92.59 10	95.77 5	94.82 6	96.11 25	97.42 16

baseline1		84.54 96	84.43 97	84.67 92	90.62 90	91.16 113	88.63 101	83.75 74	79.78 107	71.16 116	75.14 91	74.10 113	77.84 140	91.56 68	90.67 75	96.04 26	88.58 159

MSLP-MVS++		92.02 33	91.40 36	92.75 23	96.01 32	95.88 44	93.73 40	89.00 33	89.89 44	90.31 14	81.28 60	88.85 39	91.45 22	92.88 51	94.24 15	96.00 27	96.76 31

NCCC		93.69 19	93.66 23	93.72 15	97.37 5	96.66 29	95.93 17	92.50 9	93.40 18	88.35 24	87.36 34	92.33 14	92.18 13	94.89 15	94.09 18	96.00 27	96.91 28

CS-MVS-test		90.29 43	90.96 39	89.51 51	93.18 59	95.87 45	89.18 86	83.72 75	88.32 50	84.82 46	84.89 42	85.23 54	90.25 33	94.04 29	92.66 51	95.94 29	95.69 51

ACMMP		92.03 32	92.16 31	91.87 33	95.88 34	96.55 31	94.47 35	89.49 32	91.71 30	85.26 42	91.52 24	84.48 57	90.21 34	92.82 52	91.63 59	95.92 30	96.42 38
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 8	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 20	93.48 17	97.07 11	96.93 17	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 32

HFP-MVS		94.02 15	94.22 18	93.78 13	97.25 7	96.85 20	95.81 19	90.94 22	94.12 11	90.29 15	94.09 14	89.98 31	92.52 11	93.94 33	93.49 33	95.87 33	97.10 23

PVSNet_BlendedMVS		88.19 65	88.00 65	88.42 64	92.71 69	94.82 66	89.08 91	83.81 72	84.91 68	86.38 37	79.14 68	78.11 95	82.66 87	93.05 48	91.10 63	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 91	83.81 72	84.91 68	86.38 37	79.14 68	78.11 95	82.66 87	93.05 48	91.10 63	95.86 34	94.86 64

DeepC-MVS_fast	88.76 1	93.10 22	93.02 29	93.19 21	97.13 9	96.51 33	95.35 25	91.19 19	93.14 20	88.14 25	85.26 40	89.49 35	91.45 22	95.17 10	95.07 2	95.85 36	96.48 36
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 25	93.03 28	92.45 27	97.03 13	96.67 28	95.73 22	87.92 41	90.15 43	86.53 35	92.97 20	88.33 44	91.69 20	93.62 41	93.03 42	95.83 37	96.41 39

SD-MVS		94.53 10	95.22 8	93.73 14	95.69 36	97.03 14	95.77 21	91.95 12	94.41 8	91.35 7	94.97 8	93.34 8	91.80 19	94.72 20	93.99 20	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 30	91.86 33	92.73 24	96.18 29	96.87 19	95.19 27	91.76 15	92.17 26	86.58 34	81.79 54	85.85 51	90.88 30	94.57 23	94.61 10	95.80 39	97.18 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS					93.11 60	96.70 25	91.91 53			83.95 49		88.82 40				95.79 40

X-MVStestdata					93.11 60	96.70 25	91.91 53			83.95 49		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 79	85.05 44	78.96 71	84.24 58	84.25 79	94.91 14	94.91 4	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 29	92.75 30	91.90 32	96.89 17	96.70 25	95.25 26	90.48 28	91.50 32	83.95 49	88.20 31	88.82 40	89.11 38	93.75 38	93.43 34	95.75 43	96.83 30

casdiffmvs		87.45 72	87.15 74	87.79 71	90.15 104	94.22 73	89.96 74	83.93 71	85.08 66	80.91 68	75.81 87	77.88 98	86.08 69	91.86 66	90.86 69	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 21	93.26 26	93.24 20	96.84 19	96.51 33	95.52 23	90.61 26	92.37 24	88.88 21	90.91 26	89.52 34	91.91 16	93.64 40	92.78 47	95.69 45	97.09 24

MVSTER		86.03 80	86.12 82	85.93 82	88.62 116	89.93 131	89.33 85	79.91 128	81.87 88	81.35 65	81.07 61	74.91 109	80.66 106	92.13 64	90.10 85	95.68 46	92.80 104

3Dnovator+	86.06 4	91.60 35	90.86 42	92.47 26	96.00 33	96.50 35	94.70 32	87.83 42	90.49 38	89.92 17	74.68 94	89.35 36	90.66 31	94.02 31	94.14 17	95.67 47	96.85 29

OpenMVS	82.53 11	87.71 69	86.84 76	88.73 58	94.42 47	95.06 61	91.02 66	83.49 82	82.50 81	82.24 62	67.62 135	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 98	82.81 91	82.53 79	80.81 70	80.04 64	80.20 77	87.48 57	92.58 55	91.61 60	95.63 49	94.36 74

ET-MVSNet_ETH3D		84.65 94	85.58 89	83.56 111	74.99 215	92.62 102	90.29 71	80.38 116	82.16 84	73.01 111	83.41 44	71.10 130	87.05 63	87.77 127	90.17 84	95.62 50	91.82 128

CDPH-MVS		91.14 38	92.01 32	90.11 41	96.18 29	96.18 37	94.89 30	88.80 37	88.76 48	77.88 87	89.18 30	87.71 47	87.29 61	93.13 46	93.31 38	95.62 50	95.84 48

MP-MVS		93.35 20	93.59 24	93.08 22	97.39 4	96.82 22	95.38 24	90.71 23	90.82 35	88.07 26	92.83 21	90.29 29	91.32 27	94.03 30	93.19 41	95.61 52	97.16 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
FMVSNet3		84.44 99	84.64 95	84.21 100	84.32 165	90.13 126	89.85 76	80.37 117	81.17 93	75.50 92	69.63 120	79.69 83	79.62 126	89.72 104	90.52 79	95.59 53	91.58 137

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 12	94.08 19	95.58 54	97.48 14

TPM-MVS					96.31 27	96.02 38	94.89 30			86.52 36	87.18 36	92.17 16	86.76 65			95.56 55	93.85 84
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 71	82.08 63	76.57 82	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	82.08 104	88.27 51	85.14 43	81.86 53	78.53 93	85.93 71	91.17 75	90.61 76	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 10	95.96 13	91.30 18	93.41 17	88.55 23	93.00 19	90.33 28	91.43 25	95.53 7	94.41 14	95.53 58	97.47 15

GBi-Net		84.51 97	84.80 93	84.17 101	84.20 166	89.95 128	89.70 77	80.37 117	81.17 93	75.50 92	69.63 120	79.69 83	79.75 123	90.73 91	90.72 71	95.52 59	91.71 130

test1		84.51 97	84.80 93	84.17 101	84.20 166	89.95 128	89.70 77	80.37 117	81.17 93	75.50 92	69.63 120	79.69 83	79.75 123	90.73 91	90.72 71	95.52 59	91.71 130

FMVSNet2		83.87 102	83.73 104	84.05 105	84.20 166	89.95 128	89.70 77	80.21 122	79.17 114	74.89 98	65.91 141	77.49 99	79.75 123	90.87 88	91.00 67	95.52 59	91.71 130

DPM-MVS		91.72 34	91.48 34	92.00 30	95.53 37	95.75 47	95.94 15	91.07 20	91.20 33	85.58 40	81.63 58	90.74 26	88.40 46	93.40 42	93.75 25	95.45 62	93.85 84

OPM-MVS		87.56 71	85.80 87	89.62 49	93.90 52	94.09 76	94.12 36	88.18 38	75.40 134	77.30 90	76.41 83	77.93 97	88.79 41	92.20 61	90.82 70	95.40 63	93.72 89
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CSCG		92.76 25	93.16 27	92.29 28	96.30 28	97.74 7	94.67 33	88.98 35	92.46 22	89.73 19	86.67 37	92.15 18	88.69 43	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 99	90.37 39	82.73 58	82.09 50	79.28 86	88.30 47	91.17 75	93.59 28	95.36 65	97.04 25

canonicalmvs		89.36 51	89.92 46	88.70 59	91.38 79	95.92 42	91.81 57	82.61 99	90.37 39	82.73 58	82.09 50	79.28 86	88.30 47	91.17 75	93.59 28	95.36 65	97.04 25

IB-MVS	79.09 12	82.60 113	82.19 112	83.07 115	91.08 84	93.55 83	80.90 182	81.35 110	76.56 126	80.87 69	64.81 155	69.97 134	68.87 183	85.64 157	90.06 87	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		75.64 188	77.26 167	73.76 192	87.92 121	92.20 105	87.32 118	64.67 211	51.92 216	35.35 221	46.44 210	77.05 102	71.97 173	92.64 54	91.02 66	95.34 68	89.53 154

Vis-MVSNet		84.38 101	86.68 80	81.70 129	87.65 126	94.89 64	88.14 107	80.90 113	74.48 140	68.23 132	77.53 78	80.72 74	69.98 180	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 31	80.05 74	79.77 66	84.56 56	88.17 49	90.11 99	89.00 117	95.30 70	92.57 114
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_Test		86.93 74	87.24 73	86.56 77	90.10 105	93.47 84	90.31 70	80.12 123	83.55 73	78.12 83	79.58 67	79.80 81	85.45 75	90.17 98	90.59 77	95.29 71	93.53 92

LGP-MVS_train		88.25 64	88.55 57	87.89 68	92.84 67	93.66 81	93.35 42	85.22 57	85.77 60	74.03 103	86.60 38	76.29 104	86.62 67	91.20 73	90.58 78	95.29 71	95.75 49

FA-MVS(training)		85.65 84	85.79 88	85.48 87	90.44 98	93.47 84	88.66 100	73.11 178	83.34 74	82.26 60	71.79 109	78.39 94	83.14 84	91.00 83	89.47 105	95.28 73	93.06 97

UniMVSNet_NR-MVSNet		81.87 119	81.33 120	82.50 120	85.31 152	91.30 111	85.70 140	84.25 66	75.89 130	64.21 153	66.95 137	64.65 154	80.22 113	87.07 133	89.18 112	95.27 74	94.29 75

MGCFI-Net		88.38 62	89.72 51	86.83 76	91.21 82	95.59 50	91.14 65	82.37 102	90.25 41	75.33 97	81.89 52	79.13 88	85.69 72	90.98 86	93.23 40	95.23 75	96.94 27

IS_MVSNet		86.18 78	88.18 62	83.85 107	91.02 85	94.72 68	87.48 115	82.46 101	81.05 97	70.28 120	76.98 80	82.20 69	76.65 148	93.97 32	93.38 35	95.18 76	94.97 61

train_agg		92.87 24	93.53 25	92.09 29	96.88 18	95.38 52	95.94 15	90.59 27	90.65 37	83.65 52	94.31 13	91.87 20	90.30 32	93.38 43	92.42 52	95.17 77	96.73 32

NR-MVSNet		80.25 135	79.98 138	80.56 144	85.20 154	90.94 115	85.65 142	83.58 80	75.74 131	61.36 177	65.30 150	56.75 197	72.38 172	88.46 121	88.80 119	95.16 78	93.87 83

PVSNet_Blended_VisFu		87.40 73	87.80 67	86.92 75	92.86 65	95.40 51	88.56 104	83.45 86	79.55 110	82.26 60	74.49 96	84.03 59	79.24 131	92.97 50	91.53 61	95.15 79	96.65 35

EPP-MVSNet		86.55 75	87.76 69	85.15 89	90.52 94	94.41 71	87.24 121	82.32 103	81.79 89	73.60 105	78.57 73	82.41 67	82.07 92	91.23 71	90.39 80	95.14 80	95.48 56

thisisatest0530		85.15 90	85.86 85	84.33 97	89.19 112	92.57 103	87.22 122	80.11 124	82.15 85	74.41 100	78.15 75	73.80 117	79.90 119	90.99 84	89.58 100	95.13 81	93.75 88

TranMVSNet+NR-MVSNet		80.52 132	79.84 141	81.33 135	84.92 161	90.39 120	85.53 145	84.22 68	74.27 143	60.68 182	64.93 154	59.96 178	77.48 142	86.75 141	89.28 108	95.12 82	93.29 93

tttt0517		85.11 91	85.81 86	84.30 98	89.24 110	92.68 99	87.12 126	80.11 124	81.98 86	74.31 102	78.08 76	73.57 119	79.90 119	91.01 82	89.58 100	95.11 83	93.77 87

UniMVSNet (Re)		81.22 127	81.08 123	81.39 133	85.35 151	91.76 109	84.93 149	82.88 90	76.13 129	65.02 150	64.94 153	63.09 161	75.17 156	87.71 128	89.04 115	94.97 84	94.88 63

FC-MVSNet-train		85.18 89	85.31 91	85.03 90	90.67 89	91.62 110	87.66 113	83.61 77	79.75 108	74.37 101	78.69 72	71.21 129	78.91 132	91.23 71	89.96 90	94.96 85	94.69 70

GeoE		84.62 95	83.98 102	85.35 88	89.34 109	92.83 96	88.34 105	78.95 138	79.29 112	77.16 91	68.10 132	74.56 110	83.40 82	89.31 111	89.23 110	94.92 86	94.57 72

tfpn200view9		82.86 109	81.46 117	84.48 94	90.30 102	93.09 90	89.05 93	82.71 93	75.14 135	69.56 123	65.72 144	63.13 159	80.38 112	91.15 78	89.51 102	94.91 87	92.50 118

thres600view7		82.53 115	81.02 124	84.28 99	90.61 91	93.05 91	88.57 103	82.67 95	74.12 145	68.56 131	65.09 152	62.13 170	80.40 111	91.15 78	89.02 116	94.88 88	92.59 112

thres200		82.77 111	81.25 121	84.54 93	90.38 99	93.05 91	89.13 90	82.67 95	74.40 141	69.53 125	65.69 146	63.03 162	80.63 107	91.15 78	89.42 106	94.88 88	92.04 124

Effi-MVS+		85.33 86	85.08 92	85.63 84	89.69 107	93.42 86	89.90 75	80.31 121	79.32 111	72.48 114	73.52 103	74.03 114	86.55 68	90.99 84	89.98 89	94.83 90	94.27 79

dmvs_re		81.08 129	79.92 139	82.44 122	86.66 136	87.70 164	87.91 110	83.30 89	72.86 157	65.29 149	65.76 143	63.43 158	76.69 147	88.93 115	89.50 103	94.80 91	91.23 142

thres400		82.68 112	81.15 122	84.47 95	90.52 94	92.89 95	88.95 96	82.71 93	74.33 142	69.22 128	65.31 149	62.61 165	80.63 107	90.96 87	89.50 103	94.79 92	92.45 120

ACMP	83.90 8	88.32 63	88.06 63	88.62 61	92.18 71	93.98 78	91.28 64	85.24 56	86.69 56	81.23 67	85.62 39	75.13 108	87.01 64	89.83 102	89.77 96	94.79 92	95.43 57
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DU-MVS		81.20 128	80.30 132	82.25 124	84.98 159	90.94 115	85.70 140	83.58 80	75.74 131	64.21 153	65.30 150	59.60 183	80.22 113	86.89 136	89.31 107	94.77 94	94.29 75

UA-Net		86.07 79	87.78 68	84.06 104	92.85 66	95.11 60	87.73 112	84.38 65	73.22 154	73.18 108	79.99 65	89.22 37	71.47 176	93.22 45	93.03 42	94.76 95	90.69 145

MVS_111021_LR		90.14 46	90.89 41	89.26 53	93.23 58	94.05 77	90.43 69	84.65 61	90.16 42	84.52 48	90.14 28	83.80 60	87.99 50	92.50 56	90.92 68	94.74 96	94.70 68

thres100view900		82.55 114	81.01 126	84.34 96	90.30 102	92.27 104	89.04 94	82.77 92	75.14 135	69.56 123	65.72 144	63.13 159	79.62 126	89.97 101	89.26 109	94.73 97	91.61 136

AdaColmap		90.29 43	88.38 60	92.53 25	96.10 31	95.19 57	92.98 46	91.40 17	89.08 47	88.65 22	78.35 74	81.44 71	91.30 28	90.81 90	90.21 83	94.72 98	93.59 91

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 82	80.02 76	77.96 77	85.16 55	87.36 59	88.54 119	88.54 122	94.72 98	95.61 54
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
DI_MVS_plusplus_trai		86.41 77	85.54 90	87.42 73	89.24 110	93.13 89	92.16 51	82.65 97	82.30 83	80.75 72	68.30 131	80.41 75	85.01 76	90.56 96	90.07 86	94.70 100	94.01 81

Fast-Effi-MVS+		83.77 104	82.98 107	84.69 91	87.98 120	91.87 108	88.10 108	77.70 152	78.10 120	73.04 110	69.13 126	68.51 142	86.66 66	90.49 97	89.85 94	94.67 101	92.88 101

WR-MVS_H		75.84 186	76.93 172	74.57 191	82.86 185	89.50 144	78.34 195	79.36 135	66.90 183	52.51 200	60.20 177	59.71 180	59.73 202	83.61 180	85.77 160	94.65 102	92.84 102

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 45	81.72 56	86.65 50	88.90 39	91.69 67	90.27 82	94.65 102	93.95 82

HQP-MVS		89.13 54	89.58 53	88.60 62	93.53 55	93.67 80	93.29 43	87.58 44	88.53 49	75.50 92	87.60 33	80.32 76	87.07 62	90.66 95	89.95 91	94.62 104	96.35 42

PEN-MVS		76.02 183	76.07 179	75.95 181	83.17 179	87.97 162	79.65 186	80.07 127	66.57 185	51.45 203	60.94 171	55.47 202	66.81 192	82.72 185	86.80 141	94.59 105	92.03 125

ACMM	83.27 10	87.68 70	86.09 83	89.54 50	93.26 57	92.19 106	91.43 61	86.74 47	86.02 59	82.85 56	75.63 88	75.14 107	88.41 45	90.68 94	89.99 88	94.59 105	92.97 99
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CANet_DTU		85.43 85	87.72 71	82.76 118	90.95 88	93.01 93	89.99 73	75.46 170	82.67 76	64.91 151	83.14 45	80.09 78	80.68 105	92.03 65	91.03 65	94.57 107	92.08 122

CP-MVSNet		76.36 180	76.41 176	76.32 178	82.73 188	88.64 157	79.39 189	79.62 130	67.21 181	53.70 197	60.72 173	55.22 203	67.91 188	83.52 181	86.34 151	94.55 108	93.19 94

EG-PatchMatch MVS		76.40 179	75.47 188	77.48 168	85.86 144	90.22 124	82.45 168	73.96 176	59.64 208	59.60 186	52.75 202	62.20 169	68.44 185	88.23 123	87.50 130	94.55 108	87.78 169

tfpnnormal		77.46 167	74.86 192	80.49 145	86.34 140	88.92 155	84.33 156	81.26 111	61.39 203	61.70 174	51.99 204	53.66 209	74.84 159	88.63 118	87.38 133	94.50 110	92.08 122

baseline2		82.80 110	82.86 109	82.73 119	87.68 125	90.50 119	84.92 150	78.93 139	78.07 121	73.06 109	75.08 92	69.77 135	77.31 143	88.90 116	86.94 139	94.50 110	90.74 144

Vis-MVSNet (Re-imp)		83.65 105	86.81 78	79.96 149	90.46 97	92.71 97	84.84 151	82.00 105	80.93 99	62.44 166	76.29 84	82.32 68	65.54 196	92.29 58	91.66 58	94.49 112	91.47 139

PS-CasMVS		75.90 185	75.86 184	75.96 180	82.59 189	88.46 160	79.23 192	79.56 132	66.00 188	52.77 199	59.48 181	54.35 207	67.14 191	83.37 182	86.23 152	94.47 113	93.10 96

Baseline_NR-MVSNet		79.84 139	78.37 156	81.55 132	84.98 159	86.66 173	85.06 147	83.49 82	75.57 133	63.31 160	58.22 189	60.97 173	78.00 138	86.89 136	87.13 135	94.47 113	93.15 95

FMVSNet1		81.64 124	80.61 129	82.84 117	82.36 191	89.20 149	88.67 98	79.58 131	70.79 166	72.63 113	58.95 185	72.26 126	79.34 129	90.73 91	90.72 71	94.47 113	91.62 135

DTE-MVSNet		75.14 190	75.44 189	74.80 188	83.18 178	87.19 170	78.25 197	80.11 124	66.05 187	48.31 208	60.88 172	54.67 204	64.54 197	82.57 187	86.17 153	94.43 116	90.53 149

PLC	83.76 9	88.61 58	86.83 77	90.70 38	94.22 48	92.63 100	91.50 60	87.19 46	89.16 46	86.87 32	75.51 89	80.87 73	89.98 36	90.01 100	89.20 111	94.41 117	90.45 150
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UGNet		85.90 82	88.23 61	83.18 114	88.96 114	94.10 75	87.52 114	83.60 78	81.66 90	77.90 86	80.76 62	83.19 63	66.70 193	91.13 81	90.71 74	94.39 118	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)		76.57 174	75.16 191	78.22 165	85.60 148	87.24 169	82.46 167	81.23 112	59.80 207	59.05 190	57.07 191	59.14 187	66.60 194	88.09 124	86.82 140	94.37 119	87.95 168

gm-plane-assit		70.29 201	70.65 203	69.88 201	85.03 157	78.50 212	58.41 219	65.47 207	50.39 218	40.88 217	49.60 206	50.11 213	75.14 157	91.43 70	89.78 95	94.32 120	84.73 188

CNLPA		88.40 59	87.00 75	90.03 44	93.73 54	94.28 72	89.56 81	85.81 52	91.87 28	87.55 28	69.53 124	81.49 70	89.23 37	89.45 109	88.59 121	94.31 121	93.82 86

MAR-MVS		88.39 61	88.44 59	88.33 67	94.90 42	95.06 61	90.51 68	83.59 79	85.27 63	79.07 79	77.13 79	82.89 65	87.70 52	92.19 62	92.32 53	94.23 122	94.20 80
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		83.87 102	81.02 124	87.19 74	92.17 72	89.80 135	89.15 89	85.72 53	80.61 102	79.24 78	66.66 138	68.75 141	82.69 86	87.95 126	87.44 131	94.19 123	85.92 182

pm-mvs1		78.51 159	77.75 164	79.40 152	84.83 162	89.30 146	83.55 162	79.38 134	62.64 199	63.68 158	58.73 187	64.68 153	70.78 179	89.79 103	87.84 127	94.17 124	91.28 141

CPTT-MVS		91.39 36	90.95 40	91.91 31	95.06 39	95.24 56	95.02 29	88.98 35	91.02 34	86.71 33	84.89 42	88.58 43	91.60 21	90.82 89	89.67 99	94.08 125	96.45 37

v144192		78.81 153	77.22 168	80.67 142	82.95 182	89.79 136	86.40 133	77.42 153	68.26 180	63.13 161	59.50 180	58.13 189	80.08 118	85.93 153	86.08 155	94.06 126	92.83 103

diffmvs		86.52 76	86.76 79	86.23 79	88.31 119	92.63 100	89.58 80	81.61 108	86.14 58	80.26 73	79.00 70	77.27 100	83.58 80	88.94 114	89.06 114	94.05 127	94.29 75
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		78.57 158	76.99 171	80.41 147	82.93 183	89.63 142	86.38 134	77.14 156	68.31 179	61.80 173	58.89 186	56.79 196	80.19 116	86.50 148	86.05 157	94.02 128	92.76 106

ACMH	78.52 14	81.86 120	80.45 131	83.51 113	90.51 96	91.22 112	85.62 143	84.23 67	70.29 171	62.21 167	69.04 128	64.05 156	84.48 78	87.57 129	88.45 124	94.01 129	92.54 116
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		76.63 173	78.02 161	75.02 186	84.14 169	89.76 137	78.34 195	80.64 115	69.56 172	52.32 201	61.26 167	61.24 172	60.66 201	84.45 175	87.07 136	93.99 130	92.77 105

v10		79.62 142	78.19 157	81.28 136	83.73 172	89.69 139	87.27 120	76.86 159	70.50 169	65.46 144	60.58 175	60.47 175	80.44 110	86.91 135	86.63 145	93.93 131	92.55 115

anonymousdsp		77.94 162	79.00 148	76.71 174	79.03 203	87.83 163	79.58 187	72.87 179	65.80 190	58.86 191	65.82 142	62.48 167	75.99 151	86.77 140	88.66 120	93.92 132	95.68 53

v1240		78.15 160	76.53 174	80.04 148	82.85 186	89.48 145	85.61 144	76.77 160	67.05 182	61.18 180	58.37 188	56.16 200	79.89 121	86.11 152	86.08 155	93.92 132	92.47 119

v8		79.90 138	78.39 155	81.66 130	83.97 170	89.81 134	87.16 124	77.40 154	71.49 161	67.71 133	61.24 168	62.49 166	79.83 122	85.48 161	86.17 153	93.89 134	92.02 126

v2v482		79.84 139	78.07 159	81.90 127	83.75 171	90.21 125	87.17 123	79.85 129	70.65 167	65.93 142	61.93 165	60.07 177	80.82 102	85.25 163	86.71 142	93.88 135	91.70 134

thisisatest0515		79.76 141	80.59 130	78.80 157	84.40 164	88.91 156	79.48 188	76.94 158	72.29 159	67.33 135	67.82 134	65.99 149	70.80 178	88.50 120	87.84 127	93.86 136	92.75 107

IterMVS-LS		83.28 108	82.95 108	83.65 108	88.39 118	88.63 158	86.80 130	78.64 143	76.56 126	73.43 107	72.52 108	75.35 106	80.81 103	86.43 149	88.51 123	93.84 137	92.66 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TSAR-MVS + ACMM		92.97 23	94.51 14	91.16 36	95.88 34	96.59 30	95.09 28	90.45 29	93.42 16	83.01 55	94.68 10	90.74 26	88.74 42	94.75 19	93.78 24	93.82 138	97.63 12

v1144		79.38 148	77.83 162	81.18 137	83.62 173	90.23 123	87.15 125	78.35 145	69.13 174	64.02 156	60.20 177	59.41 184	80.14 117	86.78 139	86.57 146	93.81 139	92.53 117

v1192		78.94 152	77.33 166	80.82 140	83.25 177	89.90 132	86.91 128	77.72 151	68.63 178	62.61 165	59.17 182	57.53 193	80.62 109	86.89 136	86.47 148	93.79 140	92.75 107

TSAR-MVS + COLMAP		88.40 59	89.09 55	87.60 72	92.72 68	93.92 79	92.21 50	85.57 54	91.73 29	73.72 104	91.75 23	73.22 123	87.64 55	91.49 69	89.71 98	93.73 141	91.82 128

UniMVSNet_ETH3D		79.24 149	76.47 175	82.48 121	85.66 147	90.97 114	86.08 137	81.63 107	64.48 195	68.94 130	54.47 196	57.65 192	78.83 133	85.20 167	88.91 118	93.72 142	93.60 90

EPNet		89.60 49	89.91 48	89.24 54	96.45 26	93.61 82	92.95 47	88.03 39	85.74 61	83.36 53	87.29 35	83.05 64	80.98 101	92.22 60	91.85 57	93.69 143	95.58 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
HyFIR lowres test		81.62 126	79.45 147	84.14 103	91.00 86	93.38 87	88.27 106	78.19 146	76.28 128	70.18 121	48.78 207	73.69 118	83.52 81	87.05 134	87.83 129	93.68 144	89.15 156

V42		79.59 143	78.43 154	80.94 139	82.79 187	89.71 138	86.66 131	76.73 161	71.38 162	67.42 134	61.01 170	62.30 168	78.39 135	85.56 159	86.48 147	93.65 145	92.60 111

DCV-MVSNet		85.88 83	86.17 81	85.54 86	89.10 113	89.85 133	89.34 84	80.70 114	83.04 75	78.08 85	76.19 85	79.00 89	82.42 90	89.67 105	90.30 81	93.63 146	95.12 59

v7n		77.22 168	76.23 178	78.38 164	81.89 194	89.10 153	82.24 173	76.36 162	65.96 189	61.21 179	56.56 192	55.79 201	75.07 158	86.55 145	86.68 143	93.52 147	92.95 100

Anonymous20231211		84.42 100	83.02 106	86.05 81	88.85 115	92.70 98	88.92 97	83.40 87	79.99 105	78.31 82	55.83 194	78.92 91	83.33 83	89.06 113	89.76 97	93.50 148	94.90 62

ACMH+	79.08 13	81.84 121	80.06 136	83.91 106	89.92 106	90.62 117	86.21 135	83.48 84	73.88 147	65.75 143	66.38 139	65.30 152	84.63 77	85.90 154	87.25 134	93.45 149	91.13 143

pmmvs5		76.93 170	76.33 177	77.62 167	81.97 193	88.40 161	81.32 178	74.35 174	65.42 193	61.42 176	63.07 161	57.95 191	73.23 170	85.60 158	85.35 165	93.41 150	88.55 160

Anonymous202405211			82.75 110		89.58 108	92.97 94	89.04 94	84.13 69	78.72 116		57.18 190	76.64 103	83.13 85	89.55 107	89.92 92	93.38 151	94.28 78

USDC		80.69 131	79.89 140	81.62 131	86.48 138	89.11 152	86.53 132	78.86 140	81.15 96	63.48 159	72.98 105	59.12 188	81.16 99	87.10 132	85.01 167	93.23 152	84.77 187

LS3D		85.96 81	84.37 98	87.81 69	94.13 49	93.27 88	90.26 72	89.00 33	84.91 68	72.84 112	71.74 110	72.47 125	87.45 58	89.53 108	89.09 113	93.20 153	89.60 153

MS-PatchMatch		81.79 122	81.44 118	82.19 126	90.35 100	89.29 147	88.08 109	75.36 171	77.60 122	69.00 129	64.37 158	78.87 92	77.14 146	88.03 125	85.70 161	93.19 154	86.24 179

Fast-Effi-MVS+-dtu		79.95 137	80.69 128	79.08 154	86.36 139	89.14 151	85.85 138	72.28 181	72.85 158	59.32 187	70.43 118	68.42 144	77.57 141	86.14 151	86.44 149	93.11 155	91.39 140

GA-MVS		79.52 144	79.71 144	79.30 153	85.68 146	90.36 121	84.55 153	78.44 144	70.47 170	57.87 192	68.52 130	61.38 171	76.21 150	89.40 110	87.89 126	93.04 156	89.96 152

DeepPCF-MVS	88.51 2	92.64 28	94.42 17	90.56 39	94.84 44	96.92 18	91.31 63	89.61 31	95.16 5	84.55 47	89.91 29	91.45 22	90.15 35	95.12 11	94.81 7	92.90 157	97.58 13

CDS-MVSNet		81.63 125	82.09 113	81.09 138	87.21 131	90.28 122	87.46 117	80.33 120	69.06 175	70.66 117	71.30 111	73.87 115	67.99 186	89.58 106	89.87 93	92.87 158	90.69 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		82.05 117	81.76 114	82.38 123	87.72 123	90.56 118	86.90 129	78.05 148	73.85 148	66.85 137	71.29 112	71.90 127	82.00 93	86.64 144	85.48 163	92.76 159	92.58 113

v148		78.59 157	76.84 173	80.62 143	83.61 174	89.16 150	83.65 161	79.24 136	69.38 173	69.34 127	59.88 179	60.41 176	75.19 155	83.81 179	84.63 172	92.70 160	90.63 147

pmmvs4		79.99 136	78.08 158	82.22 125	83.04 181	87.16 171	84.95 148	78.80 142	78.64 117	74.53 99	64.61 156	59.41 184	79.45 128	84.13 177	84.54 174	92.53 161	88.08 165

RPMNet		77.07 169	77.63 165	76.42 176	85.56 149	85.15 186	81.37 176	65.27 208	74.71 138	60.29 183	63.71 160	66.59 148	73.64 166	82.71 186	82.12 188	92.38 162	88.39 161

CR-MVSNet		78.71 155	78.86 149	78.55 161	85.85 145	85.15 186	82.30 171	68.23 197	74.71 138	65.37 146	64.39 157	69.59 137	77.18 144	85.10 169	84.87 168	92.34 163	88.21 163

COLMAP_ROB	76.78 15	80.50 133	78.49 152	82.85 116	90.96 87	89.65 141	86.20 136	83.40 87	77.15 124	66.54 138	62.27 163	65.62 151	77.89 139	85.23 164	84.70 171	92.11 164	84.83 186
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PatchMatch-RL		83.34 107	81.36 119	85.65 83	90.33 101	89.52 143	84.36 155	81.82 106	80.87 101	79.29 77	74.04 98	62.85 164	86.05 70	88.40 122	87.04 138	92.04 165	86.77 175

PMMVS		81.65 123	84.05 101	78.86 156	78.56 205	82.63 199	83.10 163	67.22 201	81.39 91	70.11 122	84.91 41	79.74 82	82.12 91	87.31 130	85.70 161	92.03 166	86.67 178

IterMVS-SCA-FT		79.41 147	80.20 134	78.49 162	85.88 142	86.26 175	83.95 158	71.94 182	73.55 152	61.94 170	70.48 117	70.50 131	75.23 154	85.81 156	84.61 173	91.99 167	90.18 151

baseline		84.89 92	86.06 84	83.52 112	87.25 130	89.67 140	87.76 111	75.68 169	84.92 67	78.40 81	80.10 63	80.98 72	80.20 115	86.69 143	87.05 137	91.86 168	92.99 98

MIMVSNet		74.69 192	75.60 187	73.62 193	76.02 212	85.31 185	81.21 181	67.43 200	71.02 164	59.07 189	54.48 195	64.07 155	66.14 195	86.52 147	86.64 144	91.83 169	81.17 200

FC-MVSNet-test		76.53 176	81.62 116	70.58 200	84.99 158	85.73 180	74.81 203	78.85 141	77.00 125	39.13 219	75.90 86	73.50 120	54.08 208	86.54 146	85.99 158	91.65 170	86.68 176

pmmvs-eth3d		74.32 194	71.96 200	77.08 171	77.33 208	82.71 198	78.41 194	76.02 166	66.65 184	65.98 141	54.23 198	49.02 216	73.14 171	82.37 189	82.69 185	91.61 171	86.05 181

SixPastTwentyTwo		76.02 183	75.72 185	76.36 177	83.38 175	87.54 166	75.50 202	76.22 163	65.50 192	57.05 193	70.64 114	53.97 208	74.54 161	80.96 193	82.12 188	91.44 172	89.35 155

pmmvs6		74.83 191	72.89 198	77.09 170	82.11 192	87.50 167	80.88 183	76.97 157	52.79 215	61.91 172	46.66 209	60.49 174	69.28 182	86.74 142	85.46 164	91.39 173	90.56 148

test-mter		77.79 163	80.02 137	75.18 185	81.18 199	82.85 197	80.52 185	62.03 215	73.62 151	62.16 168	73.55 102	73.83 116	73.81 165	84.67 172	83.34 180	91.37 174	88.31 162

TDRefinement		79.05 151	77.05 170	81.39 133	88.45 117	89.00 154	86.92 127	82.65 97	74.21 144	64.41 152	59.17 182	59.16 186	74.52 162	85.23 164	85.09 166	91.37 174	87.51 171

test-LLR		79.47 146	79.84 141	79.03 155	87.47 127	82.40 202	81.24 179	78.05 148	73.72 149	62.69 163	73.76 100	74.42 111	73.49 167	84.61 173	82.99 183	91.25 176	87.01 173

TESTMET0.1,1		77.78 164	79.84 141	75.38 184	80.86 200	82.40 202	81.24 179	62.72 214	73.72 149	62.69 163	73.76 100	74.42 111	73.49 167	84.61 173	82.99 183	91.25 176	87.01 173

TinyColmap		76.73 171	73.95 195	79.96 149	85.16 156	85.64 182	82.34 170	78.19 146	70.63 168	62.06 169	60.69 174	49.61 214	80.81 103	85.12 168	83.69 179	91.22 178	82.27 195

FMVSNet5		75.50 189	76.07 179	74.83 187	76.16 210	81.19 205	81.34 177	70.21 190	73.20 155	61.59 175	58.97 184	68.33 145	68.50 184	85.87 155	85.85 159	91.18 179	79.11 206

IterMVS		78.79 154	79.71 144	77.71 166	85.26 153	85.91 178	84.54 154	69.84 193	73.38 153	61.25 178	70.53 116	70.35 132	74.43 163	85.21 166	83.80 178	90.95 180	88.77 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PatchT		76.42 177	77.81 163	74.80 188	78.46 206	84.30 191	71.82 209	65.03 210	73.89 146	65.37 146	61.58 166	66.70 147	77.18 144	85.10 169	84.87 168	90.94 181	88.21 163

EPNet_dtu		81.98 118	83.82 103	79.83 151	94.10 50	85.97 177	87.29 119	84.08 70	80.61 102	59.96 184	81.62 59	77.19 101	62.91 200	87.21 131	86.38 150	90.66 182	87.77 170
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PM-MVS		74.17 195	73.10 196	75.41 183	76.07 211	82.53 200	77.56 198	71.69 183	71.04 163	61.92 171	61.23 169	47.30 217	74.82 160	81.78 191	79.80 192	90.42 183	88.05 166

test0.0.03 1		76.03 182	78.51 151	73.12 196	87.47 127	85.13 188	76.32 200	78.05 148	73.19 156	50.98 206	70.64 114	69.28 138	55.53 204	85.33 162	84.38 175	90.39 184	81.63 198

Anonymous20231206		70.80 200	70.59 204	71.04 199	81.60 196	82.49 201	74.64 204	75.87 167	64.17 196	49.27 207	44.85 213	53.59 210	54.68 207	83.07 183	82.34 187	90.17 185	83.65 190

CHOSEN 1792x2688		82.16 116	80.91 127	83.61 109	91.14 83	92.01 107	89.55 82	79.15 137	79.87 106	70.29 119	52.51 203	72.56 124	81.39 96	88.87 117	88.17 125	90.15 186	92.37 121

MIMVSNet1		65.00 207	66.24 208	63.55 209	58.41 222	80.01 209	69.00 212	74.03 175	55.81 213	41.88 216	36.81 218	49.48 215	47.89 213	81.32 192	82.40 186	90.08 187	77.88 208

LTVRE_ROB	74.41 16	75.78 187	74.72 193	77.02 172	85.88 142	89.22 148	82.44 169	77.17 155	50.57 217	45.45 212	65.44 148	52.29 211	81.25 97	85.50 160	87.42 132	89.94 188	92.62 110
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		57.56 212	82.61 111	28.34 220	0.22 229	90.10 127	79.37 190	0.14 226	79.56 109	0.40 230	71.25 113	83.40 62	0.30 227	86.27 150	83.87 176	89.59 189	83.83 189

CVMVSNet		76.70 172	78.46 153	74.64 190	83.34 176	84.48 190	81.83 175	74.58 172	68.88 176	51.23 205	69.77 119	70.05 133	67.49 189	84.27 176	83.81 177	89.38 190	87.96 167

TAMVS		76.42 177	77.16 169	75.56 182	83.05 180	85.55 183	80.58 184	71.43 184	65.40 194	61.04 181	67.27 136	69.22 140	67.99 186	84.88 171	84.78 170	89.28 191	83.01 193

CostFormer		80.94 130	80.21 133	81.79 128	87.69 124	88.58 159	87.47 116	70.66 187	80.02 104	77.88 87	73.03 104	71.40 128	78.24 136	79.96 197	79.63 193	88.82 192	88.84 157

RPSCF		83.46 106	83.36 105	83.59 110	87.75 122	87.35 168	84.82 152	79.46 133	83.84 72	78.12 83	82.69 49	79.87 79	82.60 89	82.47 188	81.13 191	88.78 193	86.13 180

test20.03		68.31 204	70.05 205	66.28 207	82.41 190	80.84 206	67.35 213	76.11 165	58.44 210	40.80 218	53.77 200	54.54 205	42.28 215	83.07 183	81.96 190	88.73 194	77.76 209

SCA		79.51 145	80.15 135	78.75 158	86.58 137	87.70 164	83.07 164	68.53 196	81.31 92	66.40 139	73.83 99	75.38 105	79.30 130	80.49 195	79.39 196	88.63 195	82.96 194

testgi		71.92 199	74.20 194	69.27 202	84.58 163	83.06 194	73.40 206	74.39 173	64.04 197	46.17 211	68.90 129	57.15 195	48.89 212	84.07 178	83.08 182	88.18 196	79.09 207

dps		78.02 161	75.94 183	80.44 146	86.06 141	86.62 174	82.58 166	69.98 191	75.14 135	77.76 89	69.08 127	59.93 179	78.47 134	79.47 199	77.96 200	87.78 197	83.40 191

PatchmatchNet		78.67 156	78.85 150	78.46 163	86.85 135	86.03 176	83.77 160	68.11 199	80.88 100	66.19 140	72.90 106	73.40 121	78.06 137	79.25 201	77.71 201	87.75 198	81.75 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13_2view		73.21 197	72.91 197	73.56 194	80.01 201	84.28 192	78.62 193	66.43 205	68.64 177	59.12 188	60.39 176	59.69 182	69.81 181	78.82 203	77.43 202	87.36 199	81.11 201

MDTV_nov1_ep13		79.14 150	79.49 146	78.74 159	85.40 150	86.89 172	84.32 157	70.29 189	78.85 115	69.42 126	75.37 90	73.29 122	75.64 153	80.61 194	79.48 195	87.36 199	81.91 196

EPMVS		77.53 166	78.07 159	76.90 173	86.89 134	84.91 189	82.18 174	66.64 204	81.00 98	64.11 155	72.75 107	69.68 136	74.42 164	79.36 200	78.13 199	87.14 201	80.68 203

EU-MVSNet		69.98 202	72.30 199	67.28 205	75.67 213	79.39 210	73.12 207	69.94 192	63.59 198	42.80 215	62.93 162	56.71 198	55.07 206	79.13 202	78.55 198	87.06 202	85.82 183

new-patchmatchnet		63.80 208	63.31 210	64.37 208	76.49 209	75.99 213	63.73 216	70.99 186	57.27 211	43.08 214	45.86 211	43.80 218	45.13 214	73.20 211	70.68 214	86.80 203	76.34 211

pmnet_mix02		71.95 198	71.83 201	72.10 197	81.40 198	80.63 208	73.78 205	72.85 180	70.90 165	54.89 195	62.17 164	57.42 194	62.92 199	76.80 206	73.98 210	86.74 204	80.87 202

CMPMVS	56.49 17	73.84 196	71.73 202	76.31 179	85.20 154	85.67 181	75.80 201	73.23 177	62.26 200	65.40 145	53.40 201	59.70 181	71.77 175	80.25 196	79.56 194	86.45 205	81.28 199
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDA-MVSNet-bldmvs		66.22 206	64.49 209	68.24 203	61.67 219	82.11 204	70.07 211	76.16 164	59.14 209	47.94 209	54.35 197	35.82 225	67.33 190	64.94 217	75.68 205	86.30 206	79.36 205

MVS-HIRNet		68.83 203	66.39 207	71.68 198	77.58 207	75.52 214	66.45 214	65.05 209	62.16 201	62.84 162	44.76 214	56.60 199	71.96 174	78.04 204	75.06 208	86.18 207	72.56 213

CHOSEN 280x420		80.28 134	81.66 115	78.67 160	82.92 184	79.24 211	85.36 146	66.79 203	78.11 119	70.32 118	75.03 93	79.87 79	81.09 100	89.07 112	83.16 181	85.54 208	87.17 172

tpm cat1		77.78 164	75.28 190	80.70 141	87.14 132	85.84 179	85.81 139	70.40 188	77.44 123	78.80 80	63.72 159	64.01 157	76.55 149	75.60 209	75.21 207	85.51 209	85.12 184

tpm		76.30 181	76.05 181	76.59 175	86.97 133	83.01 196	83.83 159	67.06 202	71.83 160	63.87 157	69.56 123	62.88 163	73.41 169	79.79 198	78.59 197	84.41 210	86.68 176

tpmrst		76.55 175	75.99 182	77.20 169	87.32 129	83.05 195	82.86 165	65.62 206	78.61 118	67.22 136	69.19 125	65.71 150	75.87 152	76.75 207	75.33 206	84.31 211	83.28 192

pmmvs3		61.89 210	61.74 212	62.06 210	64.30 218	70.83 218	64.22 215	52.14 219	48.78 219	44.47 213	41.67 216	41.70 222	63.03 198	76.06 208	76.02 204	84.18 212	77.14 210

ADS-MVSNet		74.53 193	75.69 186	73.17 195	81.57 197	80.71 207	79.27 191	63.03 213	79.27 113	59.94 185	67.86 133	68.32 146	71.08 177	77.33 205	76.83 203	84.12 213	79.53 204

ambc			61.92 211		70.98 217	73.54 216	63.64 217		60.06 205	52.23 202	38.44 217	19.17 228	57.12 203	82.33 190	75.03 209	83.21 214	84.89 185

FPMVS		63.63 209	60.08 214	67.78 204	80.01 201	71.50 217	72.88 208	69.41 195	61.82 202	53.11 198	45.12 212	42.11 221	50.86 210	66.69 215	63.84 216	80.41 215	69.46 215

N_pmnet		66.85 205	66.63 206	67.11 206	78.73 204	74.66 215	70.53 210	71.07 185	66.46 186	46.54 210	51.68 205	51.91 212	55.48 205	74.68 210	72.38 211	80.29 216	74.65 212

new_pmnet		59.28 211	61.47 213	56.73 212	61.66 220	68.29 219	59.57 218	54.91 216	60.83 204	34.38 222	44.66 215	43.65 219	49.90 211	71.66 212	71.56 213	79.94 217	69.67 214

PMVS	50.48 18	55.81 213	51.93 216	60.33 211	72.90 216	49.34 222	48.78 220	69.51 194	43.49 221	54.25 196	36.26 219	41.04 223	39.71 217	65.07 216	60.70 217	76.85 218	67.58 216
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		49.17 215	47.05 218	51.65 213	59.67 221	48.39 223	41.98 223	63.47 212	55.64 214	33.33 223	14.90 222	13.78 229	41.34 216	69.31 214	72.30 212	70.11 219	55.00 221
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		41.68 217	44.74 219	38.10 215	46.97 225	52.32 221	40.63 224	48.08 220	35.51 222	7.36 229	26.86 221	24.64 227	16.72 222	55.24 220	59.03 218	68.85 220	59.59 219

WB-MVS		52.27 214	57.26 215	46.45 214	75.64 214	65.62 220	40.45 225	75.80 168	47.10 220	9.11 228	53.83 199	38.98 224	14.47 223	69.44 213	68.29 215	63.24 221	57.56 220

test_method		41.78 216	48.10 217	34.42 218	10.74 228	19.78 229	44.64 222	17.73 223	59.83 206	38.67 220	35.82 220	54.41 206	34.94 218	62.87 218	43.13 221	59.81 222	60.82 218

DeepMVS_CX						48.31 224	48.03 221	26.08 222	56.42 212	25.77 224	47.51 208	31.31 226	51.30 209	48.49 221		53.61 223	61.52 217

tmp_tt				32.73 219	43.96 226	21.15 228	26.71 226	8.99 224	65.67 191	51.39 204	56.01 193	42.64 220	11.76 224	56.60 219	50.81 220	53.55 224

E-PMN		31.40 218	26.80 221	36.78 216	51.39 224	29.96 226	20.20 227	54.17 217	25.93 224	12.75 226	14.73 223	8.58 231	34.10 220	27.36 223	37.83 222	48.07 225	43.18 223

EMVS		30.49 220	25.44 222	36.39 217	51.47 223	29.89 227	20.17 228	54.00 218	26.49 223	12.02 227	13.94 225	8.84 230	34.37 219	25.04 224	34.37 223	46.29 226	39.53 224

MVE	30.17 19	30.88 219	33.52 220	27.80 221	23.78 227	39.16 225	18.69 229	46.90 221	21.88 225	15.39 225	14.37 224	7.31 232	24.41 221	41.63 222	56.22 219	37.64 227	54.07 222
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		1.03 221	1.63 223	0.34 222	0.09 230	0.35 230	0.61 231	0.16 225	1.49 226	0.10 231	3.15 226	0.15 233	0.86 226	1.32 225	1.18 224	0.20 228	3.76 226

test123		0.87 222	1.40 224	0.25 223	0.03 231	0.25 231	0.35 232	0.08 227	1.21 227	0.05 232	2.84 227	0.03 234	0.89 225	0.43 226	1.16 225	0.13 229	3.87 225

uanet_test		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet		0.00 223	0.00 225	0.00 224	0.00 232	0.00 232	0.00 233	0.00 228	0.00 228	0.00 233	0.00 228	0.00 235	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

RE-MVS-def										56.08 194

9.14												92.16 17

SR-MVS					96.58 25			90.99 21				92.40 13

our_test_3					81.81 195	83.96 193	76.61 199

MTAPA										92.97 2		91.03 23

MTMP										93.14 1		90.21 30

Patchmatch-RL test							8.55 230

mPP-MVS					97.06 12							88.08 45

NP-MVS									87.47 54

Patchmtry						85.54 184	82.30 171	68.23 197		65.37 146

High-resolution multi-view benchmark