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.

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
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 39	89.49 34	91.45 22	95.17 10	95.07 2	95.85 36	96.48 34
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
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

DELS-MVS		89.71 48	89.68 50	89.74 46	93.75 52	96.22 36	93.76 38	85.84 51	82.53 77	85.05 43	78.96 68	84.24 57	84.25 76	94.91 14	94.91 4	95.78 42	96.02 44
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
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

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

DeepPCF-MVS	88.51 2	92.64 28	94.42 17	90.56 39	94.84 43	96.92 18	91.31 61	89.61 31	95.16 5	84.55 46	89.91 29	91.45 21	90.15 35	95.12 11	94.81 7	92.90 153	97.58 13

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
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
DeepC-MVS	87.86 3	92.26 30	91.86 33	92.73 24	96.18 28	96.87 19	95.19 27	91.76 15	92.17 26	86.58 34	81.79 51	85.85 50	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
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 24	91.87 18	95.47 8	94.59 11	96.21 23	97.77 11
Skip Steuart: Steuart Systems R&D Blog.
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
PHI-MVS		92.05 31	93.74 22	90.08 42	94.96 40	97.06 13	93.11 44	87.71 43	90.71 36	80.78 69	92.40 22	91.03 22	87.68 53	94.32 28	94.48 13	96.21 23	96.16 41

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 27	91.43 25	95.53 7	94.41 14	95.53 57	97.47 15

MSLP-MVS++		92.02 33	91.40 36	92.75 23	96.01 31	95.88 42	93.73 39	89.00 33	89.89 42	90.31 14	81.28 57	88.85 38	91.45 22	92.88 51	94.24 15	96.00 27	96.76 29

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

3Dnovator+	86.06 4	91.60 35	90.86 42	92.47 26	96.00 32	96.50 35	94.70 31	87.83 42	90.49 38	89.92 17	74.68 91	89.35 35	90.66 31	94.02 31	94.14 17	95.67 47	96.85 27

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 26

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

SD-MVS		94.53 10	95.22 8	93.73 14	95.69 35	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
MVS_0304		90.88 39	91.35 37	90.34 40	93.91 50	96.79 23	94.49 33	86.54 48	86.57 55	82.85 55	81.68 54	89.70 32	87.57 55	94.64 21	93.93 21	96.67 11	96.15 42

CANet		91.33 37	91.46 35	91.18 35	95.01 39	96.71 24	93.77 37	87.39 45	87.72 50	87.26 30	81.77 52	89.73 31	87.32 59	94.43 26	93.86 22	96.31 18	96.02 44

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 20	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
TSAR-MVS + ACMM		92.97 23	94.51 14	91.16 36	95.88 33	96.59 30	95.09 28	90.45 29	93.42 16	83.01 54	94.68 10	90.74 25	88.74 42	94.75 19	93.78 24	93.82 134	97.63 12

DPM-MVS		91.72 34	91.48 34	92.00 30	95.53 36	95.75 45	95.94 15	91.07 20	91.20 33	85.58 39	81.63 55	90.74 25	88.40 46	93.40 42	93.75 25	95.45 61	93.85 82

3Dnovator	85.17 5	90.48 41	89.90 48	91.16 36	94.88 42	95.74 46	93.82 36	85.36 55	89.28 43	87.81 27	74.34 94	87.40 47	88.56 44	93.07 47	93.74 26	96.53 12	95.71 48

TSAR-MVS + MP.		94.48 11	94.97 9	93.90 12	95.53 36	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
canonicalmvs		89.36 51	89.92 46	88.70 59	91.38 78	95.92 41	91.81 56	82.61 98	90.37 39	82.73 57	82.09 49	79.28 85	88.30 47	91.17 75	93.59 28	95.36 64	97.04 25

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 29	97.04 2	97.27 17

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 37	92.24 12	93.89 35	93.50 30	95.88 31	96.73 30

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 30	97.61 1	97.12 22

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 30	92.52 11	93.94 33	93.49 32	95.87 33	97.10 23

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 48	88.20 31	88.82 39	89.11 38	93.75 38	93.43 33	95.75 43	96.83 28

DROMVSNet		89.96 47	90.77 43	89.01 55	90.54 90	95.15 55	91.34 60	81.43 106	85.27 61	83.08 53	82.83 46	87.22 48	90.97 29	94.79 18	93.38 34	96.73 8	96.71 32

IS_MVSNet		86.18 76	88.18 60	83.85 105	91.02 82	94.72 65	87.48 111	82.46 99	81.05 95	70.28 117	76.98 77	82.20 68	76.65 144	93.97 32	93.38 34	95.18 73	94.97 59

CS-MVS		90.34 42	90.58 44	90.07 43	93.11 59	95.82 44	90.57 64	83.62 76	87.07 53	85.35 40	82.98 45	83.47 60	91.37 26	94.94 13	93.37 36	96.37 14	96.41 37

CDPH-MVS		91.14 38	92.01 32	90.11 41	96.18 28	96.18 37	94.89 30	88.80 37	88.76 46	77.88 85	89.18 30	87.71 46	87.29 60	93.13 46	93.31 37	95.62 50	95.84 46

ETV-MVS		89.22 52	89.76 49	88.60 61	91.60 76	94.61 66	89.48 80	83.46 85	85.20 63	81.58 62	82.75 47	82.59 65	88.80 40	94.57 23	93.28 38	96.68 9	95.31 56

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 28	91.32 27	94.03 30	93.19 39	95.61 52	97.16 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
UA-Net		86.07 77	87.78 66	84.06 102	92.85 65	95.11 57	87.73 108	84.38 65	73.22 152	73.18 105	79.99 62	89.22 36	71.47 172	93.22 45	93.03 40	94.76 91	90.69 141

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 41	86.53 35	92.97 20	88.33 43	91.69 20	93.62 41	93.03 40	95.83 37	96.41 37

MVS_111021_HR		90.56 40	91.29 38	89.70 48	94.71 45	95.63 47	91.81 56	86.38 49	87.53 51	81.29 64	87.96 32	85.43 52	87.69 52	93.90 34	92.93 42	96.33 16	95.69 49

CSCG		92.76 25	93.16 27	92.29 28	96.30 27	97.74 7	94.67 32	88.98 35	92.46 22	89.73 19	86.67 36	92.15 17	88.69 43	92.26 59	92.92 43	95.40 62	97.89 10

TSAR-MVS + GP.		92.71 27	93.91 21	91.30 34	91.96 72	96.00 39	93.43 40	87.94 40	92.53 21	86.27 38	93.57 15	91.94 18	91.44 24	93.29 44	92.89 44	96.78 7	97.15 21

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 33	91.91 16	93.64 40	92.78 45	95.69 45	97.09 24

test2506		85.20 86	84.11 98	86.47 76	91.84 73	95.28 51	89.18 83	84.49 63	82.59 75	75.34 94	74.66 92	58.07 186	81.68 91	93.76 36	92.71 46	96.28 21	91.71 127

ECVR-MVS		85.25 85	84.47 94	86.16 78	91.84 73	95.28 51	89.18 83	84.49 63	82.59 75	73.49 103	66.12 137	69.28 135	81.68 91	93.76 36	92.71 46	96.28 21	91.58 134

test1111		84.86 91	84.21 97	85.61 83	91.75 75	95.14 56	88.63 98	84.57 62	81.88 85	71.21 112	65.66 143	68.51 139	81.19 95	93.74 39	92.68 48	96.31 18	91.86 124

CS-MVS-test		90.29 43	90.96 39	89.51 51	93.18 58	95.87 43	89.18 83	83.72 75	88.32 48	84.82 45	84.89 41	85.23 53	90.25 33	94.04 29	92.66 49	95.94 29	95.69 49

train_agg		92.87 24	93.53 25	92.09 29	96.88 18	95.38 49	95.94 15	90.59 27	90.65 37	83.65 51	94.31 13	91.87 19	90.30 32	93.38 43	92.42 50	95.17 74	96.73 30

MAR-MVS		88.39 60	88.44 57	88.33 66	94.90 41	95.06 58	90.51 65	83.59 79	85.27 61	79.07 77	77.13 76	82.89 64	87.70 51	92.19 62	92.32 51	94.23 118	94.20 78
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
casdiffmvs_mvg		87.97 65	87.63 70	88.37 65	90.55 89	94.42 67	91.82 55	84.69 60	84.05 69	82.08 61	76.57 79	79.00 86	85.49 71	92.35 57	92.29 52	95.55 55	94.70 66
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
QAPM		89.49 50	89.58 51	89.38 52	94.73 44	95.94 40	92.35 48	85.00 58	85.69 60	80.03 73	76.97 78	87.81 45	87.87 50	92.18 63	92.10 53	96.33 16	96.40 39

Vis-MVSNet		84.38 99	86.68 78	81.70 126	87.65 123	94.89 61	88.14 104	80.90 110	74.48 138	68.23 129	77.53 75	80.72 73	69.98 176	92.68 53	91.90 54	95.33 67	94.58 69
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPNet		89.60 49	89.91 47	89.24 54	96.45 26	93.61 79	92.95 46	88.03 39	85.74 59	83.36 52	87.29 35	83.05 63	80.98 98	92.22 60	91.85 55	93.69 139	95.58 53
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet (Re-imp)		83.65 103	86.81 76	79.96 146	90.46 94	92.71 94	84.84 147	82.00 102	80.93 97	62.44 162	76.29 81	82.32 67	65.54 192	92.29 58	91.66 56	94.49 108	91.47 136

ACMMP		92.03 32	92.16 31	91.87 33	95.88 33	96.55 31	94.47 34	89.49 32	91.71 30	85.26 41	91.52 24	84.48 56	90.21 34	92.82 52	91.63 57	95.92 30	96.42 36
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
EIA-MVS		87.94 66	88.05 62	87.81 68	91.46 77	95.00 60	88.67 95	82.81 90	82.53 77	80.81 68	80.04 61	80.20 76	87.48 56	92.58 55	91.61 58	95.63 49	94.36 72

PVSNet_Blended_VisFu		87.40 71	87.80 65	86.92 74	92.86 64	95.40 48	88.56 101	83.45 86	79.55 108	82.26 58	74.49 93	84.03 58	79.24 128	92.97 50	91.53 59	95.15 76	96.65 33

OpenMVS	82.53 11	87.71 67	86.84 74	88.73 58	94.42 46	95.06 58	91.02 63	83.49 82	82.50 79	82.24 60	67.62 132	85.48 51	85.56 70	91.19 74	91.30 60	95.67 47	94.75 64

PVSNet_BlendedMVS		88.19 63	88.00 63	88.42 63	92.71 68	94.82 63	89.08 88	83.81 72	84.91 66	86.38 36	79.14 65	78.11 92	82.66 84	93.05 48	91.10 61	95.86 34	94.86 62

PVSNet_Blended		88.19 63	88.00 63	88.42 63	92.71 68	94.82 63	89.08 88	83.81 72	84.91 66	86.38 36	79.14 65	78.11 92	82.66 84	93.05 48	91.10 61	95.86 34	94.86 62

CANet_DTU		85.43 83	87.72 69	82.76 116	90.95 85	93.01 90	89.99 70	75.46 166	82.67 74	64.91 147	83.14 44	80.09 77	80.68 102	92.03 65	91.03 63	94.57 103	92.08 119

gg-mvs-nofinetune		75.64 185	77.26 164	73.76 189	87.92 118	92.20 102	87.32 114	64.67 207	51.92 213	35.35 217	46.44 205	77.05 99	71.97 169	92.64 54	91.02 64	95.34 66	89.53 150

FMVSNet2		83.87 100	83.73 102	84.05 103	84.20 162	89.95 125	89.70 74	80.21 119	79.17 112	74.89 95	65.91 138	77.49 96	79.75 120	90.87 86	91.00 65	95.52 58	91.71 127

MVS_111021_LR		90.14 46	90.89 41	89.26 53	93.23 57	94.05 74	90.43 66	84.65 61	90.16 40	84.52 47	90.14 28	83.80 59	87.99 49	92.50 56	90.92 66	94.74 92	94.70 66

casdiffmvs		87.45 70	87.15 72	87.79 70	90.15 101	94.22 70	89.96 71	83.93 71	85.08 64	80.91 66	75.81 84	77.88 95	86.08 67	91.86 66	90.86 67	95.74 44	94.37 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OPM-MVS		87.56 69	85.80 85	89.62 49	93.90 51	94.09 73	94.12 35	88.18 38	75.40 132	77.30 88	76.41 80	77.93 94	88.79 41	92.20 61	90.82 68	95.40 62	93.72 86
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
GBi-Net		84.51 95	84.80 91	84.17 99	84.20 162	89.95 125	89.70 74	80.37 114	81.17 91	75.50 90	69.63 117	79.69 82	79.75 120	90.73 89	90.72 69	95.52 58	91.71 127

test1		84.51 95	84.80 91	84.17 99	84.20 162	89.95 125	89.70 74	80.37 114	81.17 91	75.50 90	69.63 117	79.69 82	79.75 120	90.73 89	90.72 69	95.52 58	91.71 127

FMVSNet1		81.64 122	80.61 127	82.84 115	82.36 187	89.20 146	88.67 95	79.58 128	70.79 163	72.63 110	58.95 181	72.26 123	79.34 126	90.73 89	90.72 69	94.47 109	91.62 132

UGNet		85.90 80	88.23 59	83.18 112	88.96 111	94.10 72	87.52 110	83.60 78	81.66 88	77.90 84	80.76 59	83.19 62	66.70 189	91.13 80	90.71 72	94.39 114	96.06 43
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
baseline1		84.54 94	84.43 95	84.67 90	90.62 87	91.16 110	88.63 98	83.75 74	79.78 105	71.16 113	75.14 88	74.10 110	77.84 137	91.56 68	90.67 73	96.04 26	88.58 155

CLD-MVS		88.66 55	88.52 56	88.82 57	91.37 79	94.22 70	92.82 47	82.08 101	88.27 49	85.14 42	81.86 50	78.53 90	85.93 69	91.17 75	90.61 74	95.55 55	95.00 58
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_Test		86.93 72	87.24 71	86.56 75	90.10 102	93.47 81	90.31 67	80.12 120	83.55 71	78.12 81	79.58 64	79.80 80	85.45 72	90.17 96	90.59 75	95.29 69	93.53 89

LGP-MVS_train		88.25 62	88.55 55	87.89 67	92.84 66	93.66 78	93.35 41	85.22 57	85.77 58	74.03 100	86.60 37	76.29 101	86.62 65	91.20 73	90.58 76	95.29 69	95.75 47

FMVSNet3		84.44 97	84.64 93	84.21 98	84.32 161	90.13 123	89.85 73	80.37 114	81.17 91	75.50 90	69.63 117	79.69 82	79.62 123	89.72 102	90.52 77	95.59 53	91.58 134

EPP-MVSNet		86.55 73	87.76 67	85.15 87	90.52 91	94.41 68	87.24 117	82.32 100	81.79 87	73.60 102	78.57 70	82.41 66	82.07 89	91.23 71	90.39 78	95.14 77	95.48 54

DCV-MVSNet		85.88 81	86.17 79	85.54 84	89.10 110	89.85 130	89.34 81	80.70 111	83.04 73	78.08 83	76.19 82	79.00 86	82.42 87	89.67 103	90.30 79	93.63 142	95.12 57

OMC-MVS		90.23 45	90.40 45	90.03 44	93.45 55	95.29 50	91.89 54	86.34 50	93.25 19	84.94 44	81.72 53	86.65 49	88.90 39	91.69 67	90.27 80	94.65 98	93.95 80

AdaColmap		90.29 43	88.38 58	92.53 25	96.10 30	95.19 54	92.98 45	91.40 17	89.08 45	88.65 22	78.35 71	81.44 70	91.30 28	90.81 88	90.21 81	94.72 94	93.59 88

ET-MVSNet_ETH3D		84.65 92	85.58 87	83.56 109	74.99 210	92.62 99	90.29 68	80.38 113	82.16 82	73.01 108	83.41 43	71.10 127	87.05 62	87.77 124	90.17 82	95.62 50	91.82 125

MVSTER		86.03 78	86.12 80	85.93 80	88.62 113	89.93 128	89.33 82	79.91 125	81.87 86	81.35 63	81.07 58	74.91 106	80.66 103	92.13 64	90.10 83	95.68 46	92.80 101

DI_MVS_plusplus_trai		86.41 75	85.54 88	87.42 72	89.24 107	93.13 86	92.16 50	82.65 96	82.30 81	80.75 70	68.30 128	80.41 74	85.01 73	90.56 94	90.07 84	94.70 96	94.01 79

IB-MVS	79.09 12	82.60 111	82.19 110	83.07 113	91.08 81	93.55 80	80.90 178	81.35 107	76.56 124	80.87 67	64.81 151	69.97 131	68.87 179	85.64 154	90.06 85	95.36 64	94.74 65
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
ACMM	83.27 10	87.68 68	86.09 81	89.54 50	93.26 56	92.19 103	91.43 59	86.74 47	86.02 57	82.85 55	75.63 85	75.14 104	88.41 45	90.68 92	89.99 86	94.59 101	92.97 96
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Effi-MVS+		85.33 84	85.08 90	85.63 82	89.69 104	93.42 83	89.90 72	80.31 118	79.32 109	72.48 111	73.52 100	74.03 111	86.55 66	90.99 83	89.98 87	94.83 87	94.27 77

FC-MVSNet-train		85.18 87	85.31 89	85.03 88	90.67 86	91.62 107	87.66 109	83.61 77	79.75 106	74.37 98	78.69 69	71.21 126	78.91 129	91.23 71	89.96 88	94.96 82	94.69 68

HQP-MVS		89.13 53	89.58 51	88.60 61	93.53 54	93.67 77	93.29 42	87.58 44	88.53 47	75.50 90	87.60 33	80.32 75	87.07 61	90.66 93	89.95 89	94.62 100	96.35 40

Anonymous202405211			82.75 108		89.58 105	92.97 91	89.04 91	84.13 69	78.72 114		57.18 186	76.64 100	83.13 82	89.55 105	89.92 90	93.38 147	94.28 76

CDS-MVSNet		81.63 123	82.09 111	81.09 135	87.21 128	90.28 119	87.46 113	80.33 117	69.06 172	70.66 114	71.30 108	73.87 112	67.99 182	89.58 104	89.87 91	92.87 154	90.69 141
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		83.77 102	82.98 105	84.69 89	87.98 117	91.87 105	88.10 105	77.70 149	78.10 118	73.04 107	69.13 123	68.51 139	86.66 64	90.49 95	89.85 92	94.67 97	92.88 98

gm-plane-assit		70.29 198	70.65 200	69.88 198	85.03 153	78.50 208	58.41 215	65.47 203	50.39 215	40.88 213	49.60 201	50.11 209	75.14 153	91.43 70	89.78 93	94.32 116	84.73 184

ACMP	83.90 8	88.32 61	88.06 61	88.62 60	92.18 70	93.98 75	91.28 62	85.24 56	86.69 54	81.23 65	85.62 38	75.13 105	87.01 63	89.83 100	89.77 94	94.79 88	95.43 55
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		84.42 98	83.02 104	86.05 79	88.85 112	92.70 95	88.92 94	83.40 87	79.99 103	78.31 80	55.83 190	78.92 88	83.33 80	89.06 111	89.76 95	93.50 144	94.90 60

TSAR-MVS + COLMAP		88.40 58	89.09 53	87.60 71	92.72 67	93.92 76	92.21 49	85.57 54	91.73 29	73.72 101	91.75 23	73.22 120	87.64 54	91.49 69	89.71 96	93.73 137	91.82 125

CPTT-MVS		91.39 36	90.95 40	91.91 31	95.06 38	95.24 53	95.02 29	88.98 35	91.02 34	86.71 33	84.89 41	88.58 42	91.60 21	90.82 87	89.67 97	94.08 121	96.45 35

thisisatest0530		85.15 88	85.86 83	84.33 95	89.19 109	92.57 100	87.22 118	80.11 121	82.15 83	74.41 97	78.15 72	73.80 114	79.90 116	90.99 83	89.58 98	95.13 78	93.75 85

tttt0517		85.11 89	85.81 84	84.30 96	89.24 107	92.68 96	87.12 122	80.11 121	81.98 84	74.31 99	78.08 73	73.57 116	79.90 116	91.01 81	89.58 98	95.11 80	93.77 84

tfpn200view9		82.86 107	81.46 115	84.48 92	90.30 99	93.09 87	89.05 90	82.71 92	75.14 133	69.56 120	65.72 140	63.13 155	80.38 109	91.15 77	89.51 100	94.91 84	92.50 115

thres400		82.68 110	81.15 120	84.47 93	90.52 91	92.89 92	88.95 93	82.71 92	74.33 140	69.22 125	65.31 145	62.61 161	80.63 104	90.96 85	89.50 101	94.79 88	92.45 117

FA-MVS(training)		85.65 82	85.79 86	85.48 85	90.44 95	93.47 81	88.66 97	73.11 174	83.34 72	82.26 58	71.79 106	78.39 91	83.14 81	91.00 82	89.47 102	95.28 71	93.06 94

thres200		82.77 109	81.25 119	84.54 91	90.38 96	93.05 88	89.13 87	82.67 94	74.40 139	69.53 122	65.69 142	63.03 158	80.63 104	91.15 77	89.42 103	94.88 85	92.04 121

DU-MVS		81.20 126	80.30 130	82.25 121	84.98 155	90.94 112	85.70 136	83.58 80	75.74 129	64.21 149	65.30 146	59.60 179	80.22 110	86.89 133	89.31 104	94.77 90	94.29 73

TranMVSNet+NR-MVSNet		80.52 129	79.84 138	81.33 132	84.92 157	90.39 117	85.53 141	84.22 68	74.27 141	60.68 178	64.93 150	59.96 174	77.48 139	86.75 138	89.28 105	95.12 79	93.29 90

thres100view900		82.55 112	81.01 124	84.34 94	90.30 99	92.27 101	89.04 91	82.77 91	75.14 133	69.56 120	65.72 140	63.13 155	79.62 123	89.97 99	89.26 106	94.73 93	91.61 133

GeoE		84.62 93	83.98 100	85.35 86	89.34 106	92.83 93	88.34 102	78.95 135	79.29 110	77.16 89	68.10 129	74.56 107	83.40 79	89.31 109	89.23 107	94.92 83	94.57 70

PLC	83.76 9	88.61 57	86.83 75	90.70 38	94.22 47	92.63 97	91.50 58	87.19 46	89.16 44	86.87 32	75.51 86	80.87 72	89.98 36	90.01 98	89.20 108	94.41 113	90.45 146
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UniMVSNet_NR-MVSNet		81.87 117	81.33 118	82.50 118	85.31 148	91.30 108	85.70 136	84.25 66	75.89 128	64.21 149	66.95 134	64.65 151	80.22 110	87.07 130	89.18 109	95.27 72	94.29 73

LS3D		85.96 79	84.37 96	87.81 68	94.13 48	93.27 85	90.26 69	89.00 33	84.91 66	72.84 109	71.74 107	72.47 122	87.45 57	89.53 106	89.09 110	93.20 149	89.60 149

diffmvs		86.52 74	86.76 77	86.23 77	88.31 116	92.63 97	89.58 77	81.61 105	86.14 56	80.26 71	79.00 67	77.27 97	83.58 77	88.94 112	89.06 111	94.05 123	94.29 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
UniMVSNet (Re)		81.22 125	81.08 121	81.39 130	85.35 147	91.76 106	84.93 145	82.88 89	76.13 127	65.02 146	64.94 149	63.09 157	75.17 152	87.71 125	89.04 112	94.97 81	94.88 61

thres600view7		82.53 113	81.02 122	84.28 97	90.61 88	93.05 88	88.57 100	82.67 94	74.12 143	68.56 128	65.09 148	62.13 166	80.40 108	91.15 77	89.02 113	94.88 85	92.59 109

TAPA-MVS	84.37 7	88.91 54	88.93 54	88.89 56	93.00 63	94.85 62	92.00 51	84.84 59	91.68 31	80.05 72	79.77 63	84.56 55	88.17 48	90.11 97	89.00 114	95.30 68	92.57 111
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UniMVSNet_ETH3D		79.24 146	76.47 172	82.48 119	85.66 143	90.97 111	86.08 133	81.63 104	64.48 192	68.94 127	54.47 192	57.65 188	78.83 130	85.20 164	88.91 115	93.72 138	93.60 87

NR-MVSNet		80.25 132	79.98 136	80.56 141	85.20 150	90.94 112	85.65 138	83.58 80	75.74 129	61.36 173	65.30 146	56.75 193	72.38 168	88.46 118	88.80 116	95.16 75	93.87 81

anonymousdsp		77.94 159	79.00 145	76.71 171	79.03 199	87.83 160	79.58 183	72.87 175	65.80 187	58.86 187	65.82 139	62.48 163	75.99 147	86.77 137	88.66 117	93.92 128	95.68 51

CNLPA		88.40 58	87.00 73	90.03 44	93.73 53	94.28 69	89.56 78	85.81 52	91.87 28	87.55 28	69.53 121	81.49 69	89.23 37	89.45 107	88.59 118	94.31 117	93.82 83

PCF-MVS	84.60 6	88.66 55	87.75 68	89.73 47	93.06 62	96.02 38	93.22 43	90.00 30	82.44 80	80.02 74	77.96 74	85.16 54	87.36 58	88.54 116	88.54 119	94.72 94	95.61 52
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
IterMVS-LS		83.28 106	82.95 106	83.65 106	88.39 115	88.63 155	86.80 126	78.64 140	76.56 124	73.43 104	72.52 105	75.35 103	80.81 100	86.43 146	88.51 120	93.84 133	92.66 106
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	78.52 14	81.86 118	80.45 129	83.51 111	90.51 93	91.22 109	85.62 139	84.23 67	70.29 168	62.21 163	69.04 125	64.05 153	84.48 75	87.57 126	88.45 121	94.01 125	92.54 113
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CHOSEN 1792x2688		82.16 114	80.91 125	83.61 107	91.14 80	92.01 104	89.55 79	79.15 134	79.87 104	70.29 116	52.51 198	72.56 121	81.39 93	88.87 114	88.17 122	90.15 182	92.37 118

GA-MVS		79.52 141	79.71 141	79.30 150	85.68 142	90.36 118	84.55 149	78.44 141	70.47 167	57.87 188	68.52 127	61.38 167	76.21 146	89.40 108	87.89 123	93.04 152	89.96 148

thisisatest0515		79.76 138	80.59 128	78.80 154	84.40 160	88.91 153	79.48 184	76.94 155	72.29 156	67.33 132	67.82 131	65.99 146	70.80 174	88.50 117	87.84 124	93.86 132	92.75 104

pm-mvs1		78.51 156	77.75 161	79.40 149	84.83 158	89.30 143	83.55 158	79.38 131	62.64 196	63.68 154	58.73 183	64.68 150	70.78 175	89.79 101	87.84 124	94.17 120	91.28 138

HyFIR lowres test		81.62 124	79.45 144	84.14 101	91.00 83	93.38 84	88.27 103	78.19 143	76.28 126	70.18 118	48.78 202	73.69 115	83.52 78	87.05 131	87.83 126	93.68 140	89.15 152

EG-PatchMatch MVS		76.40 176	75.47 185	77.48 165	85.86 140	90.22 121	82.45 164	73.96 172	59.64 205	59.60 182	52.75 197	62.20 165	68.44 181	88.23 120	87.50 127	94.55 104	87.78 165

MSDG		83.87 100	81.02 122	87.19 73	92.17 71	89.80 132	89.15 86	85.72 53	80.61 100	79.24 76	66.66 135	68.75 138	82.69 83	87.95 123	87.44 128	94.19 119	85.92 178

LTVRE_ROB	74.41 16	75.78 184	74.72 190	77.02 169	85.88 138	89.22 145	82.44 165	77.17 152	50.57 214	45.45 208	65.44 144	52.29 207	81.25 94	85.50 157	87.42 129	89.94 184	92.62 107
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
tfpnnormal		77.46 164	74.86 189	80.49 142	86.34 136	88.92 152	84.33 152	81.26 108	61.39 200	61.70 170	51.99 199	53.66 205	74.84 155	88.63 115	87.38 130	94.50 106	92.08 119

ACMH+	79.08 13	81.84 119	80.06 134	83.91 104	89.92 103	90.62 114	86.21 131	83.48 84	73.88 145	65.75 140	66.38 136	65.30 149	84.63 74	85.90 151	87.25 131	93.45 145	91.13 139

Baseline_NR-MVSNet		79.84 136	78.37 153	81.55 129	84.98 155	86.66 169	85.06 143	83.49 82	75.57 131	63.31 156	58.22 185	60.97 169	78.00 135	86.89 133	87.13 132	94.47 109	93.15 92

WR-MVS		76.63 170	78.02 158	75.02 183	84.14 165	89.76 134	78.34 191	80.64 112	69.56 169	52.32 197	61.26 163	61.24 168	60.66 197	84.45 172	87.07 133	93.99 126	92.77 102

baseline		84.89 90	86.06 82	83.52 110	87.25 127	89.67 137	87.76 107	75.68 165	84.92 65	78.40 79	80.10 60	80.98 71	80.20 112	86.69 140	87.05 134	91.86 164	92.99 95

PatchMatch-RL		83.34 105	81.36 117	85.65 81	90.33 98	89.52 140	84.36 151	81.82 103	80.87 99	79.29 75	74.04 95	62.85 160	86.05 68	88.40 119	87.04 135	92.04 161	86.77 171

baseline2		82.80 108	82.86 107	82.73 117	87.68 122	90.50 116	84.92 146	78.93 136	78.07 119	73.06 106	75.08 89	69.77 132	77.31 140	88.90 113	86.94 136	94.50 106	90.74 140

TransMVSNet (Re)		76.57 171	75.16 188	78.22 162	85.60 144	87.24 165	82.46 163	81.23 109	59.80 204	59.05 186	57.07 187	59.14 183	66.60 190	88.09 121	86.82 137	94.37 115	87.95 164

PEN-MVS		76.02 180	76.07 176	75.95 178	83.17 175	87.97 159	79.65 182	80.07 124	66.57 182	51.45 199	60.94 167	55.47 198	66.81 188	82.72 182	86.80 138	94.59 101	92.03 122

v2v482		79.84 136	78.07 156	81.90 124	83.75 167	90.21 122	87.17 119	79.85 126	70.65 164	65.93 139	61.93 161	60.07 173	80.82 99	85.25 160	86.71 139	93.88 131	91.70 131

v7n		77.22 165	76.23 175	78.38 161	81.89 190	89.10 150	82.24 169	76.36 159	65.96 186	61.21 175	56.56 188	55.79 197	75.07 154	86.55 142	86.68 140	93.52 143	92.95 97

MIMVSNet		74.69 189	75.60 184	73.62 190	76.02 208	85.31 181	81.21 177	67.43 196	71.02 161	59.07 185	54.48 191	64.07 152	66.14 191	86.52 144	86.64 141	91.83 165	81.17 196

v10		79.62 139	78.19 154	81.28 133	83.73 168	89.69 136	87.27 116	76.86 156	70.50 166	65.46 141	60.58 171	60.47 171	80.44 107	86.91 132	86.63 142	93.93 127	92.55 112

v1144		79.38 145	77.83 159	81.18 134	83.62 169	90.23 120	87.15 121	78.35 142	69.13 171	64.02 152	60.20 173	59.41 180	80.14 114	86.78 136	86.57 143	93.81 135	92.53 114

V42		79.59 140	78.43 151	80.94 136	82.79 183	89.71 135	86.66 127	76.73 158	71.38 159	67.42 131	61.01 166	62.30 164	78.39 132	85.56 156	86.48 144	93.65 141	92.60 108

v1192		78.94 149	77.33 163	80.82 137	83.25 173	89.90 129	86.91 124	77.72 148	68.63 175	62.61 161	59.17 178	57.53 189	80.62 106	86.89 133	86.47 145	93.79 136	92.75 104

Fast-Effi-MVS+-dtu		79.95 134	80.69 126	79.08 151	86.36 135	89.14 148	85.85 134	72.28 177	72.85 155	59.32 183	70.43 115	68.42 141	77.57 138	86.14 148	86.44 146	93.11 151	91.39 137

EPNet_dtu		81.98 116	83.82 101	79.83 148	94.10 49	85.97 173	87.29 115	84.08 70	80.61 100	59.96 180	81.62 56	77.19 98	62.91 196	87.21 128	86.38 147	90.66 178	87.77 166
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CP-MVSNet		76.36 177	76.41 173	76.32 175	82.73 184	88.64 154	79.39 185	79.62 127	67.21 178	53.70 193	60.72 169	55.22 199	67.91 184	83.52 178	86.34 148	94.55 104	93.19 91

PS-CasMVS		75.90 182	75.86 181	75.96 177	82.59 185	88.46 157	79.23 188	79.56 129	66.00 185	52.77 195	59.48 177	54.35 203	67.14 187	83.37 179	86.23 149	94.47 109	93.10 93

v8		79.90 135	78.39 152	81.66 127	83.97 166	89.81 131	87.16 120	77.40 151	71.49 158	67.71 130	61.24 164	62.49 162	79.83 119	85.48 158	86.17 150	93.89 130	92.02 123

DTE-MVSNet		75.14 187	75.44 186	74.80 185	83.18 174	87.19 166	78.25 193	80.11 121	66.05 184	48.31 204	60.88 168	54.67 200	64.54 193	82.57 184	86.17 150	94.43 112	90.53 145

v144192		78.81 150	77.22 165	80.67 139	82.95 178	89.79 133	86.40 129	77.42 150	68.26 177	63.13 157	59.50 176	58.13 185	80.08 115	85.93 150	86.08 152	94.06 122	92.83 100

v1240		78.15 157	76.53 171	80.04 145	82.85 182	89.48 142	85.61 140	76.77 157	67.05 179	61.18 176	58.37 184	56.16 196	79.89 118	86.11 149	86.08 152	93.92 128	92.47 116

v1921920		78.57 155	76.99 168	80.41 144	82.93 179	89.63 139	86.38 130	77.14 153	68.31 176	61.80 169	58.89 182	56.79 192	80.19 113	86.50 145	86.05 154	94.02 124	92.76 103

FC-MVSNet-test		76.53 173	81.62 114	70.58 197	84.99 154	85.73 176	74.81 199	78.85 138	77.00 123	39.13 215	75.90 83	73.50 117	54.08 204	86.54 143	85.99 155	91.65 166	86.68 172

FMVSNet5		75.50 186	76.07 176	74.83 184	76.16 206	81.19 201	81.34 173	70.21 186	73.20 153	61.59 171	58.97 180	68.33 142	68.50 180	85.87 152	85.85 156	91.18 175	79.11 202

WR-MVS_H		75.84 183	76.93 169	74.57 188	82.86 181	89.50 141	78.34 191	79.36 132	66.90 180	52.51 196	60.20 173	59.71 176	59.73 198	83.61 177	85.77 157	94.65 98	92.84 99

MS-PatchMatch		81.79 120	81.44 116	82.19 123	90.35 97	89.29 144	88.08 106	75.36 167	77.60 120	69.00 126	64.37 154	78.87 89	77.14 143	88.03 122	85.70 158	93.19 150	86.24 175

PMMVS		81.65 121	84.05 99	78.86 153	78.56 201	82.63 195	83.10 159	67.22 197	81.39 89	70.11 119	84.91 40	79.74 81	82.12 88	87.31 127	85.70 158	92.03 162	86.67 174

Effi-MVS+-dtu		82.05 115	81.76 112	82.38 120	87.72 120	90.56 115	86.90 125	78.05 145	73.85 146	66.85 134	71.29 109	71.90 124	82.00 90	86.64 141	85.48 160	92.76 155	92.58 110

pmmvs6		74.83 188	72.89 195	77.09 167	82.11 188	87.50 163	80.88 179	76.97 154	52.79 212	61.91 168	46.66 204	60.49 170	69.28 178	86.74 139	85.46 161	91.39 169	90.56 144

pmmvs5		76.93 167	76.33 174	77.62 164	81.97 189	88.40 158	81.32 174	74.35 170	65.42 190	61.42 172	63.07 157	57.95 187	73.23 166	85.60 155	85.35 162	93.41 146	88.55 156

TDRefinement		79.05 148	77.05 167	81.39 130	88.45 114	89.00 151	86.92 123	82.65 96	74.21 142	64.41 148	59.17 178	59.16 182	74.52 158	85.23 161	85.09 163	91.37 170	87.51 167

USDC		80.69 128	79.89 137	81.62 128	86.48 134	89.11 149	86.53 128	78.86 137	81.15 94	63.48 155	72.98 102	59.12 184	81.16 96	87.10 129	85.01 164	93.23 148	84.77 183

CR-MVSNet		78.71 152	78.86 146	78.55 158	85.85 141	85.15 182	82.30 167	68.23 193	74.71 136	65.37 143	64.39 153	69.59 134	77.18 141	85.10 166	84.87 165	92.34 159	88.21 159

PatchT		76.42 174	77.81 160	74.80 185	78.46 202	84.30 187	71.82 205	65.03 206	73.89 144	65.37 143	61.58 162	66.70 144	77.18 141	85.10 166	84.87 165	90.94 177	88.21 159

TAMVS		76.42 174	77.16 166	75.56 179	83.05 176	85.55 179	80.58 180	71.43 180	65.40 191	61.04 177	67.27 133	69.22 137	67.99 182	84.88 168	84.78 167	89.28 187	83.01 189

COLMAP_ROB	76.78 15	80.50 130	78.49 149	82.85 114	90.96 84	89.65 138	86.20 132	83.40 87	77.15 122	66.54 135	62.27 159	65.62 148	77.89 136	85.23 161	84.70 168	92.11 160	84.83 182
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v148		78.59 154	76.84 170	80.62 140	83.61 170	89.16 147	83.65 157	79.24 133	69.38 170	69.34 124	59.88 175	60.41 172	75.19 151	83.81 176	84.63 169	92.70 156	90.63 143

IterMVS-SCA-FT		79.41 144	80.20 132	78.49 159	85.88 138	86.26 171	83.95 154	71.94 178	73.55 150	61.94 166	70.48 114	70.50 128	75.23 150	85.81 153	84.61 170	91.99 163	90.18 147

pmmvs4		79.99 133	78.08 155	82.22 122	83.04 177	87.16 167	84.95 144	78.80 139	78.64 115	74.53 96	64.61 152	59.41 180	79.45 125	84.13 174	84.54 171	92.53 157	88.08 161

test0.0.03 1		76.03 179	78.51 148	73.12 193	87.47 124	85.13 184	76.32 196	78.05 145	73.19 154	50.98 202	70.64 111	69.28 135	55.53 200	85.33 159	84.38 172	90.39 180	81.63 194

GG-mvs-BLEND		57.56 209	82.61 109	28.34 216	0.22 224	90.10 124	79.37 186	0.14 222	79.56 107	0.40 225	71.25 110	83.40 61	0.30 222	86.27 147	83.87 173	89.59 185	83.83 185

CVMVSNet		76.70 169	78.46 150	74.64 187	83.34 172	84.48 186	81.83 171	74.58 168	68.88 173	51.23 201	69.77 116	70.05 130	67.49 185	84.27 173	83.81 174	89.38 186	87.96 163

IterMVS		78.79 151	79.71 141	77.71 163	85.26 149	85.91 174	84.54 150	69.84 189	73.38 151	61.25 174	70.53 113	70.35 129	74.43 159	85.21 163	83.80 175	90.95 176	88.77 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TinyColmap		76.73 168	73.95 192	79.96 146	85.16 152	85.64 178	82.34 166	78.19 143	70.63 165	62.06 165	60.69 170	49.61 210	80.81 100	85.12 165	83.69 176	91.22 174	82.27 191

test-mter		77.79 160	80.02 135	75.18 182	81.18 195	82.85 193	80.52 181	62.03 211	73.62 149	62.16 164	73.55 99	73.83 113	73.81 161	84.67 169	83.34 177	91.37 170	88.31 158

CHOSEN 280x420		80.28 131	81.66 113	78.67 157	82.92 180	79.24 207	85.36 142	66.79 199	78.11 117	70.32 115	75.03 90	79.87 78	81.09 97	89.07 110	83.16 178	85.54 204	87.17 168

testgi		71.92 196	74.20 191	69.27 199	84.58 159	83.06 190	73.40 202	74.39 169	64.04 194	46.17 207	68.90 126	57.15 191	48.89 208	84.07 175	83.08 179	88.18 192	79.09 203

test-LLR		79.47 143	79.84 138	79.03 152	87.47 124	82.40 198	81.24 175	78.05 145	73.72 147	62.69 159	73.76 97	74.42 108	73.49 163	84.61 170	82.99 180	91.25 172	87.01 169

TESTMET0.1,1		77.78 161	79.84 138	75.38 181	80.86 196	82.40 198	81.24 175	62.72 210	73.72 147	62.69 159	73.76 97	74.42 108	73.49 163	84.61 170	82.99 180	91.25 172	87.01 169

pmmvs-eth3d		74.32 191	71.96 197	77.08 168	77.33 204	82.71 194	78.41 190	76.02 163	66.65 181	65.98 138	54.23 194	49.02 212	73.14 167	82.37 186	82.69 182	91.61 167	86.05 177

MIMVSNet1		65.00 204	66.24 205	63.55 206	58.41 217	80.01 205	69.00 208	74.03 171	55.81 210	41.88 212	36.81 213	49.48 211	47.89 209	81.32 189	82.40 183	90.08 183	77.88 204

Anonymous20231206		70.80 197	70.59 201	71.04 196	81.60 192	82.49 197	74.64 200	75.87 164	64.17 193	49.27 203	44.85 208	53.59 206	54.68 203	83.07 180	82.34 184	90.17 181	83.65 186

SixPastTwentyTwo		76.02 180	75.72 182	76.36 174	83.38 171	87.54 162	75.50 198	76.22 160	65.50 189	57.05 189	70.64 111	53.97 204	74.54 157	80.96 190	82.12 185	91.44 168	89.35 151

RPMNet		77.07 166	77.63 162	76.42 173	85.56 145	85.15 182	81.37 172	65.27 204	74.71 136	60.29 179	63.71 156	66.59 145	73.64 162	82.71 183	82.12 185	92.38 158	88.39 157

test20.03		68.31 201	70.05 202	66.28 204	82.41 186	80.84 202	67.35 209	76.11 162	58.44 207	40.80 214	53.77 195	54.54 201	42.28 211	83.07 180	81.96 187	88.73 190	77.76 205

RPSCF		83.46 104	83.36 103	83.59 108	87.75 119	87.35 164	84.82 148	79.46 130	83.84 70	78.12 81	82.69 48	79.87 78	82.60 86	82.47 185	81.13 188	88.78 189	86.13 176

PM-MVS		74.17 192	73.10 193	75.41 180	76.07 207	82.53 196	77.56 194	71.69 179	71.04 160	61.92 167	61.23 165	47.30 213	74.82 156	81.78 188	79.80 189	90.42 179	88.05 162

CostFormer		80.94 127	80.21 131	81.79 125	87.69 121	88.58 156	87.47 112	70.66 183	80.02 102	77.88 85	73.03 101	71.40 125	78.24 133	79.96 194	79.63 190	88.82 188	88.84 153

CMPMVS	56.49 17	73.84 193	71.73 199	76.31 176	85.20 150	85.67 177	75.80 197	73.23 173	62.26 197	65.40 142	53.40 196	59.70 177	71.77 171	80.25 193	79.56 191	86.45 201	81.28 195
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MDTV_nov1_ep13		79.14 147	79.49 143	78.74 156	85.40 146	86.89 168	84.32 153	70.29 185	78.85 113	69.42 123	75.37 87	73.29 119	75.64 149	80.61 191	79.48 192	87.36 195	81.91 192

SCA		79.51 142	80.15 133	78.75 155	86.58 133	87.70 161	83.07 160	68.53 192	81.31 90	66.40 136	73.83 96	75.38 102	79.30 127	80.49 192	79.39 193	88.63 191	82.96 190

tpm		76.30 178	76.05 178	76.59 172	86.97 130	83.01 192	83.83 155	67.06 198	71.83 157	63.87 153	69.56 120	62.88 159	73.41 165	79.79 195	78.59 194	84.41 206	86.68 172

EU-MVSNet		69.98 199	72.30 196	67.28 202	75.67 209	79.39 206	73.12 203	69.94 188	63.59 195	42.80 211	62.93 158	56.71 194	55.07 202	79.13 199	78.55 195	87.06 198	85.82 179

EPMVS		77.53 163	78.07 156	76.90 170	86.89 131	84.91 185	82.18 170	66.64 200	81.00 96	64.11 151	72.75 104	69.68 133	74.42 160	79.36 197	78.13 196	87.14 197	80.68 199

dps		78.02 158	75.94 180	80.44 143	86.06 137	86.62 170	82.58 162	69.98 187	75.14 133	77.76 87	69.08 124	59.93 175	78.47 131	79.47 196	77.96 197	87.78 193	83.40 187

PatchmatchNet		78.67 153	78.85 147	78.46 160	86.85 132	86.03 172	83.77 156	68.11 195	80.88 98	66.19 137	72.90 103	73.40 118	78.06 134	79.25 198	77.71 198	87.75 194	81.75 193
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13_2view		73.21 194	72.91 194	73.56 191	80.01 197	84.28 188	78.62 189	66.43 201	68.64 174	59.12 184	60.39 172	59.69 178	69.81 177	78.82 200	77.43 199	87.36 195	81.11 197

ADS-MVSNet		74.53 190	75.69 183	73.17 192	81.57 193	80.71 203	79.27 187	63.03 209	79.27 111	59.94 181	67.86 130	68.32 143	71.08 173	77.33 202	76.83 200	84.12 209	79.53 200

pmmvs3		61.89 207	61.74 209	62.06 207	64.30 213	70.83 214	64.22 211	52.14 215	48.78 216	44.47 209	41.67 211	41.70 218	63.03 194	76.06 205	76.02 201	84.18 208	77.14 206

MDA-MVSNet-bldmvs		66.22 203	64.49 206	68.24 200	61.67 214	82.11 200	70.07 207	76.16 161	59.14 206	47.94 205	54.35 193	35.82 220	67.33 186	64.94 213	75.68 202	86.30 202	79.36 201

tpmrst		76.55 172	75.99 179	77.20 166	87.32 126	83.05 191	82.86 161	65.62 202	78.61 116	67.22 133	69.19 122	65.71 147	75.87 148	76.75 204	75.33 203	84.31 207	83.28 188

tpm cat1		77.78 161	75.28 187	80.70 138	87.14 129	85.84 175	85.81 135	70.40 184	77.44 121	78.80 78	63.72 155	64.01 154	76.55 145	75.60 206	75.21 204	85.51 205	85.12 180

MVS-HIRNet		68.83 200	66.39 204	71.68 195	77.58 203	75.52 210	66.45 210	65.05 205	62.16 198	62.84 158	44.76 209	56.60 195	71.96 170	78.04 201	75.06 205	86.18 203	72.56 209

ambc			61.92 208		70.98 212	73.54 212	63.64 213		60.06 202	52.23 198	38.44 212	19.17 223	57.12 199	82.33 187	75.03 206	83.21 210	84.89 181

pmnet_mix02		71.95 195	71.83 198	72.10 194	81.40 194	80.63 204	73.78 201	72.85 176	70.90 162	54.89 191	62.17 160	57.42 190	62.92 195	76.80 203	73.98 207	86.74 200	80.87 198

N_pmnet		66.85 202	66.63 203	67.11 203	78.73 200	74.66 211	70.53 206	71.07 181	66.46 183	46.54 206	51.68 200	51.91 208	55.48 201	74.68 207	72.38 208	80.29 212	74.65 208

Gipuma		49.17 211	47.05 214	51.65 210	59.67 216	48.39 218	41.98 219	63.47 208	55.64 211	33.33 219	14.90 217	13.78 224	41.34 212	69.31 210	72.30 209	70.11 215	55.00 216
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
new_pmnet		59.28 208	61.47 210	56.73 209	61.66 215	68.29 215	59.57 214	54.91 212	60.83 201	34.38 218	44.66 210	43.65 215	49.90 207	71.66 209	71.56 210	79.94 213	69.67 210

new-patchmatchnet		63.80 205	63.31 207	64.37 205	76.49 205	75.99 209	63.73 212	70.99 182	57.27 208	43.08 210	45.86 206	43.80 214	45.13 210	73.20 208	70.68 211	86.80 199	76.34 207

FPMVS		63.63 206	60.08 211	67.78 201	80.01 197	71.50 213	72.88 204	69.41 191	61.82 199	53.11 194	45.12 207	42.11 217	50.86 206	66.69 211	63.84 212	80.41 211	69.46 211

PMVS	50.48 18	55.81 210	51.93 212	60.33 208	72.90 211	49.34 217	48.78 216	69.51 190	43.49 217	54.25 192	36.26 214	41.04 219	39.71 213	65.07 212	60.70 213	76.85 214	67.58 212
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		41.68 213	44.74 215	38.10 211	46.97 220	52.32 216	40.63 220	48.08 216	35.51 218	7.36 224	26.86 216	24.64 222	16.72 218	55.24 216	59.03 214	68.85 216	59.59 215

MVE	30.17 19	30.88 215	33.52 216	27.80 217	23.78 222	39.16 220	18.69 224	46.90 217	21.88 221	15.39 221	14.37 219	7.31 227	24.41 217	41.63 218	56.22 215	37.64 222	54.07 217
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				32.73 215	43.96 221	21.15 223	26.71 221	8.99 220	65.67 188	51.39 200	56.01 189	42.64 216	11.76 219	56.60 215	50.81 216	53.55 219

test_method		41.78 212	48.10 213	34.42 214	10.74 223	19.78 224	44.64 218	17.73 219	59.83 203	38.67 216	35.82 215	54.41 202	34.94 214	62.87 214	43.13 217	59.81 217	60.82 214

E-PMN		31.40 214	26.80 217	36.78 212	51.39 219	29.96 221	20.20 222	54.17 213	25.93 220	12.75 222	14.73 218	8.58 226	34.10 216	27.36 219	37.83 218	48.07 220	43.18 218

EMVS		30.49 216	25.44 218	36.39 213	51.47 218	29.89 222	20.17 223	54.00 214	26.49 219	12.02 223	13.94 220	8.84 225	34.37 215	25.04 220	34.37 219	46.29 221	39.53 219

testmvs		1.03 217	1.63 219	0.34 218	0.09 225	0.35 225	0.61 226	0.16 221	1.49 222	0.10 226	3.15 221	0.15 228	0.86 221	1.32 221	1.18 220	0.20 223	3.76 221

test123		0.87 218	1.40 220	0.25 219	0.03 226	0.25 226	0.35 227	0.08 223	1.21 223	0.05 227	2.84 222	0.03 229	0.89 220	0.43 222	1.16 221	0.13 224	3.87 220

uanet_test		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet-low-res		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

sosnet		0.00 219	0.00 221	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 224	0.00 228	0.00 223	0.00 230	0.00 223	0.00 223	0.00 222	0.00 225	0.00 222

RE-MVS-def										56.08 190

9.14												92.16 16

SR-MVS					96.58 25			90.99 21				92.40 13

our_test_3					81.81 191	83.96 189	76.61 195

MTAPA										92.97 2		91.03 22

MTMP										93.14 1		90.21 29

Patchmatch-RL test							8.55 225

XVS					93.11 59	96.70 25	91.91 52			83.95 48		88.82 39				95.79 40

X-MVStestdata					93.11 59	96.70 25	91.91 52			83.95 48		88.82 39				95.79 40

mPP-MVS					97.06 12							88.08 44

NP-MVS									87.47 52

Patchmtry						85.54 180	82.30 167	68.23 193		65.37 143

DeepMVS_CX						48.31 219	48.03 217	26.08 218	56.42 209	25.77 220	47.51 203	31.31 221	51.30 205	48.49 217		53.61 218	61.52 213

High-resolution multi-view benchmark