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.

DVP-MVS++		98.07 1	98.46 1	97.62 1	99.08 3	99.29 2	98.84 3	96.63 4	97.89 1	95.35 3	97.83 4	99.48 3	96.98 9	97.99 2	97.14 12	98.82 11	99.60 1

DVP-MVS		97.93 3	98.23 3	97.58 3	99.05 6	99.31 1	98.64 6	96.62 5	97.56 2	95.08 5	96.61 13	99.64 1	97.32 1	97.91 4	97.31 7	98.77 15	99.26 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
SED-MVS		97.98 2	98.36 2	97.54 4	98.94 16	99.29 2	98.81 4	96.64 3	97.14 3	95.16 4	97.96 2	99.61 2	96.92 12	98.00 1	97.24 9	98.75 17	99.25 3

MSP-MVS		97.70 6	98.09 5	97.24 6	99.00 11	99.17 5	98.76 5	96.41 9	96.91 5	93.88 14	97.72 5	99.04 7	96.93 11	97.29 18	97.31 7	98.45 37	99.23 4
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
SD-MVS		97.35 8	97.73 8	96.90 14	97.35 45	98.66 15	97.85 26	96.25 11	96.86 6	94.54 8	96.75 11	99.13 6	96.99 7	96.94 27	96.58 24	98.39 44	99.20 5
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
APDe-MVS		97.79 5	97.96 6	97.60 2	99.20 2	99.10 6	98.88 2	96.68 2	96.81 7	94.64 6	97.84 3	98.02 11	97.24 3	97.74 8	97.02 15	98.97 5	99.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + MP.		97.31 9	97.64 9	96.92 13	97.28 47	98.56 24	98.61 7	95.48 28	96.72 8	94.03 13	96.73 12	98.29 9	97.15 4	97.61 13	96.42 26	98.96 6	99.13 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
TSAR-MVS + ACMM		96.19 24	97.39 13	94.78 38	97.70 41	98.41 35	97.72 28	95.49 27	96.47 11	86.66 69	96.35 16	97.85 13	93.99 53	97.19 21	96.37 31	97.12 137	99.13 7

DPE-MVS		97.83 4	98.13 4	97.48 5	98.83 22	99.19 4	98.99 1	96.70 1	96.05 18	94.39 9	98.30 1	99.47 4	97.02 6	97.75 7	97.02 15	98.98 3	99.10 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CSCG		95.68 31	95.46 36	95.93 27	98.71 24	99.07 7	97.13 35	93.55 37	95.48 25	93.35 19	90.61 46	93.82 47	95.16 37	94.60 82	95.57 55	97.70 110	99.08 10

SteuartSystems-ACMMP		97.10 15	97.49 10	96.65 18	98.97 13	98.95 10	98.43 9	95.96 17	95.12 29	91.46 29	96.85 9	97.60 18	96.37 24	97.76 6	97.16 11	98.68 19	98.97 11
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		97.53 7	97.93 7	97.07 10	99.21 1	99.02 9	98.08 19	96.25 11	96.36 12	93.57 15	96.56 14	99.27 5	96.78 16	97.91 4	97.43 4	98.51 26	98.94 12
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
MVS_0304		96.54 22	97.36 14	95.60 33	98.03 34	99.07 7	98.02 21	92.24 45	95.87 20	92.54 25	96.41 15	96.08 32	94.03 52	97.69 9	97.47 3	98.73 18	98.90 13

sasdasda		93.08 55	93.09 55	93.07 62	94.24 82	97.86 52	95.45 57	87.86 108	94.00 45	87.47 62	88.32 57	82.37 105	95.13 38	93.96 99	96.41 29	98.27 58	98.73 14

canonicalmvs		93.08 55	93.09 55	93.07 62	94.24 82	97.86 52	95.45 57	87.86 108	94.00 45	87.47 62	88.32 57	82.37 105	95.13 38	93.96 99	96.41 29	98.27 58	98.73 14

EC-MVSNet		94.19 48	95.05 39	93.18 58	93.56 104	97.65 64	95.34 59	86.37 123	92.05 61	88.71 51	89.91 49	93.32 48	96.14 27	97.29 18	96.42 26	98.98 3	98.70 16

MGCFI-Net		92.75 60	92.98 59	92.48 70	94.18 84	97.77 58	95.28 61	87.77 110	93.88 48	85.28 93	88.19 59	82.17 109	94.14 50	93.86 101	96.32 37	98.20 67	98.69 17

HPM-MVS++		97.22 11	97.40 12	97.01 11	99.08 3	98.55 25	98.19 14	96.48 7	96.02 19	93.28 20	96.26 18	98.71 8	96.76 17	97.30 17	96.25 39	98.30 54	98.68 18

DeepPCF-MVS	92.65 2	95.50 34	96.96 20	93.79 51	96.44 58	98.21 42	93.51 102	94.08 36	96.94 4	89.29 45	93.08 33	96.77 28	93.82 57	97.68 10	97.40 5	95.59 184	98.65 19

TSAR-MVS + GP.		95.86 29	96.95 22	94.60 42	94.07 88	98.11 46	96.30 44	91.76 50	95.67 21	91.07 31	96.82 10	97.69 17	95.71 32	95.96 52	95.75 52	98.68 19	98.63 20

DeepC-MVS	92.10 3	95.22 35	94.77 42	95.75 30	97.77 39	98.54 26	97.63 29	95.96 17	95.07 32	88.85 49	85.35 76	91.85 54	95.82 30	96.88 28	97.10 13	98.44 38	98.63 20
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator+	90.56 5	95.06 37	94.56 45	95.65 31	98.11 32	98.15 45	97.19 33	91.59 52	95.11 31	93.23 22	81.99 105	94.71 44	95.43 36	96.48 39	96.88 19	98.35 46	98.63 20

ACMMP_NAP		96.93 16	97.27 16	96.53 23	99.06 5	98.95 10	98.24 13	96.06 15	95.66 22	90.96 33	95.63 25	97.71 16	96.53 20	97.66 11	96.68 21	98.30 54	98.61 23

CS-MVS		94.53 45	94.73 43	94.31 43	96.30 60	98.53 27	94.98 63	89.24 84	93.37 51	90.24 40	88.96 55	89.76 71	96.09 28	97.48 14	96.42 26	98.99 2	98.59 24

HFP-MVS		97.11 14	97.19 17	97.00 12	98.97 13	98.73 13	98.37 11	95.69 21	96.60 9	93.28 20	96.87 8	96.64 29	97.27 2	96.64 35	96.33 36	98.44 38	98.56 25

MP-MVS		96.56 21	96.72 24	96.37 24	98.93 18	98.48 31	98.04 20	95.55 23	94.32 41	90.95 35	95.88 23	97.02 26	96.29 25	96.77 30	96.01 49	98.47 32	98.56 25
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		97.12 13	97.05 19	97.19 7	99.04 7	98.63 20	98.45 8	96.54 6	94.81 37	93.50 16	96.10 20	97.40 22	96.81 13	97.05 23	96.82 20	98.80 12	98.56 25
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		96.68 20	96.59 27	96.77 17	98.85 21	98.58 23	98.18 15	95.51 26	95.34 26	92.94 23	95.21 29	96.25 31	96.79 15	96.44 42	95.77 51	98.35 46	98.56 25

PVSNet_Blended_VisFu		91.92 71	92.39 69	91.36 94	95.45 72	97.85 54	92.25 121	89.54 78	88.53 114	87.47 62	79.82 118	90.53 66	85.47 157	96.31 46	95.16 63	97.99 90	98.56 25

SF-MVS		97.20 12	97.29 15	97.10 9	98.95 15	98.51 30	97.51 30	96.48 7	96.17 16	94.64 6	97.32 6	97.57 19	96.23 26	96.78 29	96.15 43	98.79 14	98.55 30

MCST-MVS		96.83 18	97.06 18	96.57 19	98.88 20	98.47 32	98.02 21	96.16 14	95.58 24	90.96 33	95.78 24	97.84 14	96.46 22	97.00 26	96.17 41	98.94 7	98.55 30

CNVR-MVS		97.30 10	97.41 11	97.18 8	99.02 10	98.60 22	98.15 16	96.24 13	96.12 17	94.10 11	95.54 26	97.99 12	96.99 7	97.97 3	97.17 10	98.57 24	98.50 32

X-MVS		96.07 27	96.33 29	95.77 29	98.94 16	98.66 15	97.94 24	95.41 30	95.12 29	88.03 55	93.00 34	96.06 33	95.85 29	96.65 34	96.35 32	98.47 32	98.48 33

train_agg		96.15 26	96.64 26	95.58 34	98.44 27	98.03 48	98.14 18	95.40 31	93.90 47	87.72 60	96.26 18	98.10 10	95.75 31	96.25 47	95.45 57	98.01 88	98.47 34

MSLP-MVS++		96.05 28	95.63 32	96.55 21	98.33 29	98.17 44	96.94 37	94.61 34	94.70 39	94.37 10	89.20 53	95.96 36	96.81 13	95.57 58	97.33 6	98.24 63	98.47 34

ACMMPR		96.92 17	96.96 20	96.87 15	98.99 12	98.78 12	98.38 10	95.52 24	96.57 10	92.81 24	96.06 21	95.90 37	97.07 5	96.60 37	96.34 35	98.46 34	98.42 36

QAPM		94.13 49	94.33 49	93.90 48	97.82 38	98.37 37	96.47 42	90.89 58	92.73 57	85.63 84	85.35 76	93.87 46	94.17 49	95.71 57	95.90 50	98.40 42	98.42 36

UGNet		91.52 79	93.41 53	89.32 114	94.13 85	97.15 79	91.83 131	89.01 85	90.62 76	85.86 80	86.83 63	91.73 56	77.40 197	94.68 79	94.43 73	97.71 108	98.40 38
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
SPE-MVS-test		94.63 44	95.28 37	93.88 50	96.56 57	98.67 14	93.41 104	89.31 82	94.27 42	89.64 43	90.84 44	91.64 57	95.58 33	97.04 24	96.17 41	98.77 15	98.32 39

DELS-MVS		93.71 52	93.47 52	94.00 45	96.82 54	98.39 36	96.80 39	91.07 56	89.51 103	89.94 42	83.80 86	89.29 72	90.95 94	97.32 15	97.65 2	98.42 40	98.32 39
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
NCCC		96.75 19	96.67 25	96.85 16	99.03 9	98.44 34	98.15 16	96.28 10	96.32 13	92.39 26	92.16 36	97.55 20	96.68 19	97.32 15	96.65 23	98.55 25	98.26 41

ACMMP		95.54 32	95.49 35	95.61 32	98.27 31	98.53 27	97.16 34	94.86 32	94.88 35	89.34 44	95.36 28	91.74 55	95.50 35	95.51 59	94.16 78	98.50 29	98.22 42
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CANet		94.85 39	94.92 40	94.78 38	97.25 48	98.52 29	97.20 32	91.81 49	93.25 52	91.06 32	86.29 69	94.46 45	92.99 68	97.02 25	96.68 21	98.34 48	98.20 43

PGM-MVS		96.16 25	96.33 29	95.95 26	99.04 7	98.63 20	98.32 12	92.76 42	93.42 50	90.49 38	96.30 17	95.31 42	96.71 18	96.46 40	96.02 48	98.38 45	98.19 44

3Dnovator	90.28 7	94.70 43	94.34 48	95.11 36	98.06 33	98.21 42	96.89 38	91.03 57	94.72 38	91.45 30	82.87 94	93.10 50	94.61 42	96.24 48	97.08 14	98.63 22	98.16 45

EPNet		93.92 50	94.40 46	93.36 54	97.89 36	96.55 95	96.08 47	92.14 46	91.65 67	89.16 46	94.07 31	90.17 70	87.78 131	95.24 64	94.97 67	97.09 139	98.15 46
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
anonymousdsp		84.51 164	85.85 154	82.95 188	86.30 204	93.51 147	85.77 198	80.38 185	78.25 189	63.42 204	73.51 155	72.20 158	84.64 163	93.21 118	92.16 129	97.19 132	98.14 47

CPTT-MVS		95.54 32	95.07 38	96.10 25	97.88 37	97.98 50	97.92 25	94.86 32	94.56 40	92.16 27	91.01 42	95.71 38	96.97 10	94.56 83	93.50 95	96.81 161	98.14 47

HQP-MVS		92.39 65	92.49 66	92.29 75	95.65 66	95.94 110	95.64 54	92.12 47	92.46 59	79.65 123	91.97 38	82.68 101	92.92 71	93.47 111	92.77 118	97.74 106	98.12 49

DeepC-MVS_fast	93.32 1	96.48 23	96.42 28	96.56 20	98.70 25	98.31 38	97.97 23	95.76 20	96.31 14	92.01 28	91.43 41	95.42 41	96.46 22	97.65 12	97.69 1	98.49 31	98.12 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PHI-MVS		95.86 29	96.93 23	94.61 41	97.60 43	98.65 19	96.49 41	93.13 40	94.07 44	87.91 59	97.12 7	97.17 24	93.90 56	96.46 40	96.93 18	98.64 21	98.10 51

DCV-MVSNet		91.24 81	91.26 84	91.22 95	92.84 118	93.44 148	93.82 93	86.75 120	91.33 71	85.61 85	84.00 85	85.46 86	91.27 88	92.91 119	93.62 90	97.02 144	98.05 52

ETV-MVS		93.80 51	94.57 44	92.91 66	93.98 90	97.50 67	93.62 99	88.70 90	91.95 62	87.57 61	90.21 48	90.79 62	94.56 43	97.20 20	96.35 32	99.02 1	97.98 53

EPP-MVSNet		92.13 67	93.06 57	91.05 96	93.66 103	97.30 71	92.18 122	87.90 104	90.24 85	83.63 102	86.14 71	90.52 68	90.76 97	94.82 75	94.38 74	98.18 70	97.98 53

Anonymous20231211		89.82 107	88.18 122	91.74 82	92.52 126	96.09 108	93.38 105	89.30 83	88.95 108	85.90 79	64.55 201	84.39 90	92.41 76	92.24 133	93.06 112	96.93 153	97.95 55

CDPH-MVS		94.80 42	95.50 34	93.98 47	98.34 28	98.06 47	97.41 31	93.23 39	92.81 55	82.98 105	92.51 35	94.82 43	93.53 61	96.08 50	96.30 38	98.42 40	97.94 56

UniMVSNet (Re)		86.22 141	85.46 158	87.11 138	88.34 171	94.42 125	89.65 161	87.10 119	84.39 148	74.61 140	70.41 171	68.10 176	85.10 160	91.17 150	91.79 138	97.84 98	97.94 56

FC-MVSNet-train		90.55 97	90.19 97	90.97 97	93.78 99	95.16 116	92.11 126	88.85 87	87.64 120	83.38 104	84.36 83	78.41 134	89.53 109	94.69 78	93.15 109	98.15 71	97.92 58

MVS_111021_HR		94.84 40	95.91 31	93.60 52	97.35 45	98.46 33	95.08 62	91.19 54	94.18 43	85.97 76	95.38 27	92.56 52	93.61 60	96.61 36	96.25 39	98.40 42	97.92 58

CLD-MVS		92.50 64	91.96 75	93.13 59	93.93 94	96.24 103	95.69 52	88.77 89	92.92 53	89.01 47	88.19 59	81.74 113	93.13 66	93.63 105	93.08 110	98.23 64	97.91 60
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LGP-MVS_train		91.83 73	92.04 74	91.58 86	95.46 70	96.18 105	95.97 50	89.85 68	90.45 81	77.76 128	91.92 39	80.07 124	92.34 77	94.27 89	93.47 96	98.11 76	97.90 61

IS_MVSNet		91.87 72	93.35 54	90.14 108	94.09 87	97.73 61	93.09 109	88.12 100	88.71 111	79.98 122	84.49 81	90.63 65	87.49 136	97.07 22	96.96 17	98.07 81	97.88 62

PVSNet_BlendedMVS		92.80 58	92.44 67	93.23 55	96.02 62	97.83 56	93.74 96	90.58 59	91.86 64	90.69 36	85.87 74	82.04 110	90.01 105	96.39 43	95.26 60	98.34 48	97.81 63

PVSNet_Blended		92.80 58	92.44 67	93.23 55	96.02 62	97.83 56	93.74 96	90.58 59	91.86 64	90.69 36	85.87 74	82.04 110	90.01 105	96.39 43	95.26 60	98.34 48	97.81 63

IB-MVS	85.10 14	87.98 125	87.97 126	87.99 129	94.55 80	96.86 90	84.52 201	88.21 99	86.48 133	88.54 53	74.41 150	77.74 141	74.10 208	89.65 178	92.85 116	98.06 83	97.80 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
ACMP	89.13 9	92.03 68	91.70 79	92.41 73	94.92 77	96.44 101	93.95 88	89.96 67	91.81 66	85.48 89	90.97 43	79.12 128	92.42 75	93.28 117	92.55 122	97.76 104	97.74 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211			88.00 124		93.16 111	96.38 102	93.58 100	89.34 81	87.92 118		65.04 196	83.03 97	92.07 79	92.67 122	93.33 100	96.96 148	97.63 67

OpenMVS	88.18 11	92.51 63	91.61 80	93.55 53	97.74 40	98.02 49	95.66 53	90.46 61	89.14 106	86.50 70	75.80 142	90.38 69	92.69 72	94.99 67	95.30 59	98.27 58	97.63 67

UniMVSNet_NR-MVSNet		86.80 135	85.86 153	87.89 132	88.17 173	94.07 133	90.15 147	88.51 94	84.20 152	73.45 146	72.38 163	70.30 167	88.95 122	90.25 165	92.21 127	98.12 74	97.62 69

DU-MVS		86.12 143	84.81 161	87.66 133	87.77 180	93.78 138	90.15 147	87.87 106	84.40 146	73.45 146	70.59 168	64.82 196	88.95 122	90.14 166	92.33 124	97.76 104	97.62 69

GeoE		89.29 117	88.68 115	89.99 109	92.75 121	96.03 109	93.07 111	83.79 150	86.98 125	81.34 111	74.72 147	78.92 129	91.22 89	93.31 115	93.21 106	97.78 102	97.60 71

EIA-MVS		92.72 61	92.96 60	92.44 72	93.86 97	97.76 59	93.13 108	88.65 93	89.78 99	86.68 68	86.69 66	87.57 73	93.74 58	96.07 51	95.32 58	98.58 23	97.53 72

PCF-MVS	90.19 8	92.98 57	92.07 73	94.04 44	96.39 59	97.87 51	96.03 48	95.47 29	87.16 123	85.09 95	84.81 80	93.21 49	93.46 63	91.98 138	91.98 135	97.78 102	97.51 73
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS_111021_LR		94.84 40	95.57 33	94.00 45	97.11 50	97.72 63	94.88 66	91.16 55	95.24 28	88.74 50	96.03 22	91.52 59	94.33 48	95.96 52	95.01 66	97.79 100	97.49 74

NR-MVSNet		85.46 153	84.54 163	86.52 146	88.33 172	93.78 138	90.45 140	87.87 106	84.40 146	71.61 154	70.59 168	62.09 206	82.79 176	91.75 140	91.75 139	98.10 77	97.44 75

MAR-MVS		92.71 62	92.63 63	92.79 67	97.70 41	97.15 79	93.75 95	87.98 102	90.71 73	85.76 82	86.28 70	86.38 79	94.35 47	94.95 68	95.49 56	97.22 130	97.44 75
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		91.94 70	91.25 85	92.75 68	93.41 106	97.19 78	95.48 56	89.77 70	89.86 97	86.41 71	81.02 112	82.23 108	92.93 69	95.44 61	95.61 54	98.51 26	97.40 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tttt0517		91.01 87	91.71 78	90.19 105	92.98 113	97.07 84	91.96 130	87.63 115	90.61 77	81.42 110	86.76 65	82.26 107	89.23 116	94.86 74	93.03 114	97.90 95	97.36 78

Vis-MVSNet		89.36 115	91.49 82	86.88 141	92.10 130	97.60 66	92.16 125	85.89 126	84.21 151	75.20 138	82.58 98	87.13 75	77.40 197	95.90 54	95.63 53	98.51 26	97.36 78
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		91.04 86	91.74 77	90.21 103	92.93 117	97.00 85	92.06 127	87.63 115	90.74 72	81.51 109	86.81 64	82.48 102	89.23 116	94.81 76	93.03 114	97.90 95	97.33 80

DI_MVS_pp		91.05 85	90.15 98	92.11 77	92.67 124	96.61 92	96.03 48	88.44 95	90.25 84	85.92 78	73.73 151	84.89 89	91.92 80	94.17 92	94.07 82	97.68 113	97.31 81

diffmvs_AUTHOR		91.22 82	90.82 92	91.68 85	92.69 123	96.56 94	94.05 82	88.87 86	91.87 63	85.08 96	82.26 102	80.04 125	91.84 82	93.80 102	93.93 85	97.56 119	97.26 82

UniMVSNet_ETH3D		84.57 162	81.40 196	88.28 125	89.34 161	94.38 128	90.33 141	86.50 122	74.74 207	77.52 130	59.90 211	62.04 207	88.78 127	88.82 188	92.65 120	97.22 130	97.24 83

casdiffmvs		91.72 76	91.16 87	92.38 74	93.16 111	97.15 79	93.95 88	89.49 79	91.58 69	86.03 75	80.75 114	80.95 117	93.16 65	95.25 63	95.22 62	98.50 29	97.23 84
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs		91.37 80	91.09 88	91.70 84	92.71 122	96.47 98	94.03 83	88.78 88	92.74 56	85.43 91	83.63 88	80.37 120	91.76 85	93.39 113	93.78 87	97.50 122	97.23 84
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Effi-MVS+		89.79 108	89.83 103	89.74 110	92.98 113	96.45 100	93.48 103	84.24 143	87.62 121	76.45 134	81.76 106	77.56 143	93.48 62	94.61 81	93.59 91	97.82 99	97.22 86

viewmambaseed2359dif		90.70 96	89.81 104	91.73 83	92.66 125	96.10 107	93.97 86	88.69 91	89.92 94	86.12 73	80.79 113	80.73 119	91.92 80	91.13 152	92.81 117	97.06 141	97.20 87

CP-MVSNet		83.11 186	82.15 186	84.23 170	87.20 190	92.70 171	86.42 193	83.53 155	77.83 191	67.67 184	66.89 185	60.53 214	82.47 177	89.23 183	90.65 159	98.08 80	97.20 87

TranMVSNet+NR-MVSNet		85.57 151	84.41 164	86.92 140	87.67 183	93.34 151	90.31 143	88.43 96	83.07 161	70.11 167	69.99 174	65.28 191	86.96 141	89.73 175	92.27 125	98.06 83	97.17 89

Baseline_NR-MVSNet		85.28 155	83.42 173	87.46 137	87.77 180	90.80 205	89.90 157	87.69 112	83.93 156	74.16 142	64.72 199	66.43 186	87.48 137	90.14 166	90.83 151	97.73 107	97.11 90

PS-CasMVS		82.53 191	81.54 194	83.68 177	87.08 195	92.54 177	86.20 195	83.46 156	76.46 199	65.73 196	65.71 192	59.41 219	81.61 185	89.06 185	90.55 161	98.03 85	97.07 91

viewmanbaseed2359cas		91.57 78	91.09 88	92.12 76	93.36 107	97.26 72	94.02 84	89.62 76	90.50 80	84.95 98	82.00 104	81.36 114	92.69 72	94.47 87	95.04 65	98.09 79	97.00 92

baseline		91.19 83	91.89 76	90.38 99	92.76 119	95.04 118	93.55 101	84.54 141	92.92 53	85.71 83	86.68 67	86.96 76	89.28 115	92.00 137	92.62 121	96.46 166	96.99 93

viewmacassd2359aftdt		90.80 91	89.95 102	91.78 81	93.17 110	97.14 82	93.99 85	89.56 77	87.66 119	83.65 101	78.82 122	80.23 122	92.23 78	93.74 104	95.11 64	98.10 77	96.97 94

WR-MVS		83.14 184	83.38 175	82.87 189	87.55 184	93.29 153	86.36 194	84.21 144	80.05 179	66.41 191	66.91 183	66.92 183	75.66 204	88.96 186	90.56 160	97.05 142	96.96 95

CHOSEN 1792x2688		88.57 121	87.82 128	89.44 113	95.46 70	96.89 89	93.74 96	85.87 127	89.63 100	77.42 131	61.38 207	83.31 95	88.80 126	93.44 112	93.16 108	95.37 190	96.95 96

tfpnnormal		83.80 176	81.26 198	86.77 143	89.60 158	93.26 156	89.72 160	87.60 117	72.78 209	70.44 164	60.53 210	61.15 211	85.55 155	92.72 121	91.44 144	97.71 108	96.92 97

WR-MVS_H		82.86 189	82.66 183	83.10 185	87.44 186	93.33 152	85.71 199	83.20 159	77.36 193	68.20 181	66.37 186	65.23 192	76.05 203	89.35 179	90.13 169	97.99 90	96.89 98

v7n		82.25 194	81.54 194	83.07 186	85.55 208	92.58 175	86.68 192	81.10 183	76.54 197	65.97 194	62.91 204	60.56 213	82.36 178	91.07 153	90.35 164	96.77 162	96.80 99

MVS_Test		91.81 74	92.19 71	91.37 93	93.24 108	96.95 87	94.43 70	86.25 124	91.45 70	83.45 103	86.31 68	85.15 87	92.93 69	93.99 95	94.71 71	97.92 94	96.77 100

thres600view7		89.28 118	87.47 137	91.39 91	94.12 86	97.25 74	93.94 90	89.74 71	85.62 140	80.63 119	75.24 146	69.33 171	91.66 87	94.92 70	93.23 103	98.27 58	96.72 101

AdaColmap		95.02 38	93.71 50	96.54 22	98.51 26	97.76 59	96.69 40	95.94 19	93.72 49	93.50 16	89.01 54	90.53 66	96.49 21	94.51 85	93.76 88	98.07 81	96.69 102

LTVRE_ROB	81.71 16	82.44 193	81.84 191	83.13 183	89.01 162	92.99 163	88.90 172	82.32 168	66.26 220	54.02 221	74.68 149	59.62 218	88.87 125	90.71 159	92.02 133	95.68 181	96.62 103
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
tfpn200view9		89.55 112	87.86 127	91.53 88	93.90 95	97.26 72	94.31 76	89.74 71	85.87 135	81.15 113	76.46 137	70.38 165	91.76 85	94.92 70	93.51 92	98.28 57	96.61 104

thres400		89.40 114	87.58 134	91.53 88	94.06 89	97.21 77	94.19 80	89.83 69	85.69 137	81.08 115	75.50 144	69.76 169	91.80 83	94.79 77	93.51 92	98.20 67	96.60 105

ACMH	85.51 13	87.31 131	86.59 141	88.14 127	93.96 91	94.51 122	89.00 171	87.99 101	81.58 169	70.15 166	78.41 126	71.78 161	90.60 101	91.30 147	91.99 134	97.17 133	96.58 106
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		93.69 53	92.50 65	95.06 37	97.11 50	97.36 70	93.88 92	93.30 38	95.64 23	93.44 18	80.32 116	90.73 64	94.99 40	93.58 106	93.33 100	97.67 114	96.57 107

thisisatest0515		85.70 148	87.00 138	84.19 171	88.16 174	93.67 143	84.20 203	84.14 146	83.39 160	72.91 148	76.79 134	74.75 152	78.82 195	92.57 126	91.26 147	96.94 150	96.56 108

viewmsd2359difaftdt		89.67 110	88.66 116	90.85 98	92.35 127	95.23 114	91.72 133	88.40 97	88.80 109	86.12 73	80.75 114	78.20 136	90.94 95	90.02 172	91.15 149	95.59 184	96.50 109

FA-MVS(training)		90.79 92	91.33 83	90.17 106	93.76 100	97.22 76	92.74 113	77.79 196	90.60 78	88.03 55	78.80 123	87.41 74	91.00 93	95.40 62	93.43 98	97.70 110	96.46 110

Vis-MVSNet (Re-imp)		90.54 98	92.76 62	87.94 130	93.73 101	96.94 88	92.17 124	87.91 103	88.77 110	76.12 136	83.68 87	90.80 61	79.49 193	96.34 45	96.35 32	98.21 66	96.46 110

Fast-Effi-MVS+		88.56 122	87.99 125	89.22 115	91.56 137	95.21 115	92.29 120	82.69 161	86.82 126	77.73 129	76.24 140	73.39 155	93.36 64	94.22 91	93.64 89	97.65 115	96.43 112

thres200		89.49 113	87.72 129	91.55 87	93.95 92	97.25 74	94.34 74	89.74 71	85.66 138	81.18 112	76.12 141	70.19 168	91.80 83	94.92 70	93.51 92	98.27 58	96.40 113

MVSTER		91.73 75	91.61 80	91.86 80	93.18 109	94.56 120	94.37 72	87.90 104	90.16 89	88.69 52	89.23 52	81.28 116	88.92 124	95.75 56	93.95 84	98.12 74	96.37 114

v144192		83.48 180	82.23 185	84.94 160	86.65 199	92.84 167	89.63 162	82.48 165	77.87 190	67.36 186	65.33 194	63.50 200	86.51 145	89.72 176	89.99 177	97.03 143	96.35 115

IterMVS-LS		88.60 120	88.45 117	88.78 119	92.02 131	92.44 180	92.00 129	83.57 154	86.52 131	78.90 127	78.61 125	81.34 115	89.12 119	90.68 160	93.18 107	97.10 138	96.35 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1192		83.56 179	82.35 184	84.98 159	86.84 198	92.84 167	90.01 152	82.70 160	78.54 186	66.48 190	64.88 197	62.91 201	86.91 142	90.72 158	90.25 167	96.94 150	96.32 117

v1921920		83.30 182	82.09 188	84.70 163	86.59 202	92.67 173	89.82 158	82.23 169	78.32 187	65.76 195	64.64 200	62.35 204	86.78 144	90.34 164	90.02 175	97.02 144	96.31 118

v10		84.18 169	83.17 179	85.37 154	87.34 187	92.68 172	90.32 142	81.33 179	79.93 182	69.23 174	66.33 187	65.74 189	87.03 140	90.84 155	90.38 163	96.97 146	96.29 119

V42		84.48 166	83.36 176	85.79 151	87.14 192	93.28 154	90.03 150	83.98 148	80.30 176	71.20 159	66.90 184	67.17 180	85.55 155	89.35 179	90.27 166	96.82 160	96.27 120

PEN-MVS		82.49 192	81.58 193	83.56 179	86.93 196	92.05 188	86.71 191	83.84 149	76.94 196	64.68 200	67.24 180	60.11 215	81.17 187	87.78 192	90.70 158	98.02 87	96.21 121

thres100view900		89.36 115	87.61 132	91.39 91	93.90 95	96.86 90	94.35 73	89.66 75	85.87 135	81.15 113	76.46 137	70.38 165	91.17 90	94.09 93	93.43 98	98.13 73	96.16 122

v1144		84.03 173	82.88 181	85.37 154	87.17 191	93.15 161	90.18 146	83.31 157	78.83 185	67.85 182	65.99 189	64.99 194	86.79 143	90.75 157	90.33 165	96.90 155	96.15 123

OMC-MVS		94.49 46	94.36 47	94.64 40	97.17 49	97.73 61	95.49 55	92.25 44	96.18 15	90.34 39	88.51 56	92.88 51	94.90 41	94.92 70	94.17 77	97.69 112	96.15 123

Effi-MVS+-dtu		87.51 129	88.13 123	86.77 143	91.10 143	94.90 119	90.91 136	82.67 162	83.47 158	71.55 155	81.11 111	77.04 145	89.41 111	92.65 124	91.68 142	95.00 196	96.09 125

v8		84.45 168	83.30 177	85.80 150	87.53 185	92.95 164	90.31 143	82.46 166	80.46 174	71.43 156	66.99 182	67.16 181	86.14 151	89.26 182	90.22 168	96.94 150	96.06 126

test1111		90.47 99	89.10 111	92.07 78	94.92 77	98.30 39	94.17 81	90.30 63	89.56 102	83.92 100	73.25 159	73.66 154	90.26 104	96.77 30	96.14 44	98.87 8	96.04 127

v1240		82.88 188	81.66 192	84.29 169	86.46 203	92.52 179	89.06 169	81.82 175	77.16 194	65.09 199	64.17 202	61.50 209	86.36 146	90.12 168	90.13 169	96.95 149	96.04 127

dmvs_re		87.31 131	86.10 146	88.74 120	89.84 154	94.28 129	92.66 114	89.41 80	82.61 164	74.69 139	74.69 148	69.47 170	87.78 131	92.38 129	93.23 103	98.03 85	96.02 129

test2506		90.93 88	89.20 109	92.95 64	94.97 75	98.30 39	94.53 68	90.25 64	89.91 95	88.39 54	83.23 90	64.17 199	90.69 98	96.75 32	96.10 46	98.87 8	95.97 130

TPM-MVS					98.33 29	97.85 54	97.06 36			89.97 41	93.26 32	97.16 25	93.12 67			97.79 100	95.95 131
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
DPM-MVS		95.07 36	94.84 41	95.34 35	97.44 44	97.49 68	97.76 27	95.52 24	94.88 35	88.92 48	87.25 62	96.44 30	94.41 44	95.78 55	96.11 45	97.99 90	95.95 131

CDS-MVSNet		88.34 123	88.71 114	87.90 131	90.70 150	94.54 121	92.38 117	86.02 125	80.37 175	79.42 124	79.30 119	83.43 94	82.04 180	93.39 113	94.01 83	96.86 159	95.93 133
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ECVR-MVS		90.77 93	89.27 107	92.52 69	94.97 75	98.30 39	94.53 68	90.25 64	89.91 95	85.80 81	73.64 152	74.31 153	90.69 98	96.75 32	96.10 46	98.87 8	95.91 134

Fast-Effi-MVS+-dtu		86.25 139	87.70 130	84.56 166	90.37 153	93.70 141	90.54 139	78.14 193	83.50 157	65.37 198	81.59 109	75.83 151	86.09 153	91.70 141	91.70 140	96.88 157	95.84 135

ET-MVSNet_ETH3D		89.93 105	90.84 91	88.87 118	79.60 220	96.19 104	94.43 70	86.56 121	90.63 75	80.75 118	90.71 45	77.78 140	93.73 59	91.36 146	93.45 97	98.15 71	95.77 136

OPM-MVS		91.08 84	89.34 106	93.11 61	96.18 61	96.13 106	96.39 43	92.39 43	82.97 162	81.74 108	82.55 100	80.20 123	93.97 55	94.62 80	93.23 103	98.00 89	95.73 137
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline2		88.97 119	89.50 105	88.36 123	91.14 142	95.30 113	90.13 149	85.17 135	87.24 122	80.80 117	84.46 82	78.44 133	85.60 154	93.54 109	91.87 136	97.31 127	95.66 138

CANet_DTU		90.74 95	92.93 61	88.19 126	94.36 81	96.61 92	94.34 74	84.66 138	90.66 74	68.75 176	90.41 47	86.89 77	89.78 107	95.46 60	94.87 68	97.25 129	95.62 139

v2v482		84.51 164	83.05 180	86.20 148	87.25 189	93.28 154	90.22 145	85.40 133	79.94 181	69.78 169	67.74 179	65.15 193	87.57 134	89.12 184	90.55 161	96.97 146	95.60 140

TAPA-MVS	90.35 6	93.69 53	93.52 51	93.90 48	96.89 53	97.62 65	96.15 45	91.67 51	94.94 33	85.97 76	87.72 61	91.96 53	94.40 45	93.76 103	93.06 112	98.30 54	95.58 141
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMM	88.76 10	91.70 77	90.43 94	93.19 57	95.56 67	95.14 117	93.35 106	91.48 53	92.26 60	87.12 65	84.02 84	79.34 127	93.99 53	94.07 94	92.68 119	97.62 118	95.50 142
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		90.21 102	90.11 99	90.32 101	88.66 167	93.65 144	94.25 77	85.78 128	90.03 90	85.56 86	77.38 128	86.13 80	89.38 112	93.97 96	94.16 78	98.31 51	95.47 143

test1		90.21 102	90.11 99	90.32 101	88.66 167	93.65 144	94.25 77	85.78 128	90.03 90	85.56 86	77.38 128	86.13 80	89.38 112	93.97 96	94.16 78	98.31 51	95.47 143

FMVSNet2		89.61 111	89.14 110	90.16 107	88.66 167	93.65 144	94.25 77	85.44 132	88.57 113	84.96 97	73.53 154	83.82 92	89.38 112	94.23 90	94.68 72	98.31 51	95.47 143

pm-mvs1		84.55 163	83.46 170	85.82 149	88.16 174	93.39 150	89.05 170	85.36 134	74.03 208	72.43 152	65.08 195	71.11 162	82.30 179	93.48 110	91.70 140	97.64 116	95.43 146

FMVSNet3		90.19 104	90.06 101	90.34 100	88.69 166	93.85 136	94.58 67	85.78 128	90.03 90	85.56 86	77.38 128	86.13 80	89.22 118	93.29 116	94.36 75	98.20 67	95.40 147

FMVSNet1		87.33 130	86.00 150	88.89 117	87.13 193	92.83 169	93.08 110	84.46 142	81.35 171	82.20 107	66.33 187	77.96 138	88.96 121	93.97 96	94.16 78	97.54 121	95.38 148

v148		83.61 178	82.10 187	85.37 154	87.34 187	92.94 165	87.48 183	85.72 131	78.92 184	73.87 144	65.71 192	64.69 197	81.78 184	87.82 191	89.35 186	96.01 173	95.26 149

HyFIR lowres test		87.87 126	86.42 143	89.57 111	95.56 67	96.99 86	92.37 118	84.15 145	86.64 128	77.17 132	57.65 213	83.97 91	91.08 92	92.09 136	92.44 123	97.09 139	95.16 150

DTE-MVSNet		81.76 197	81.04 199	82.60 193	86.63 200	91.48 199	85.97 197	83.70 151	76.45 200	62.44 205	67.16 181	59.98 216	78.98 194	87.15 196	89.93 178	97.88 97	95.12 151

ACMH+	85.75 12	87.19 133	86.02 149	88.56 122	93.42 105	94.41 126	89.91 155	87.66 114	83.45 159	72.25 153	76.42 139	71.99 160	90.78 96	89.86 173	90.94 150	97.32 126	95.11 152

PLC	90.69 4	94.32 47	92.99 58	95.87 28	97.91 35	96.49 97	95.95 51	94.12 35	94.94 33	94.09 12	85.90 72	90.77 63	95.58 33	94.52 84	93.32 102	97.55 120	95.00 153
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
IterMVS-SCA-FT		85.44 154	86.71 139	83.97 175	90.59 151	90.84 203	89.73 159	78.34 192	84.07 155	66.40 192	77.27 133	78.66 131	83.06 173	91.20 148	90.10 174	95.72 179	94.78 154

pmmvs6		80.90 199	78.77 205	83.38 182	85.84 205	91.61 195	86.01 196	82.54 164	64.17 221	70.43 165	54.14 220	67.06 182	80.73 189	90.50 163	89.17 188	94.74 197	94.75 155

GA-MVS		85.08 157	85.65 155	84.42 168	89.77 156	94.25 130	89.26 165	84.62 139	81.19 172	62.25 206	75.72 143	68.44 175	84.14 168	93.57 107	91.68 142	96.49 164	94.71 156

TSAR-MVS + COLMAP		92.39 65	92.31 70	92.47 71	95.35 74	96.46 99	96.13 46	92.04 48	95.33 27	80.11 121	94.95 30	77.35 144	94.05 51	94.49 86	93.08 110	97.15 134	94.53 157

gg-mvs-nofinetune		81.83 196	83.58 169	79.80 203	91.57 136	96.54 96	93.79 94	68.80 220	62.71 224	43.01 229	55.28 216	85.06 88	83.65 171	96.13 49	94.86 69	97.98 93	94.46 158

LS3D		91.97 69	90.98 90	93.12 60	97.03 52	97.09 83	95.33 60	95.59 22	92.47 58	79.26 125	81.60 108	82.77 100	94.39 46	94.28 88	94.23 76	97.14 136	94.45 159

UA-Net		90.81 89	92.58 64	88.74 120	94.87 79	97.44 69	92.61 115	88.22 98	82.35 166	78.93 126	85.20 78	95.61 39	79.56 192	96.52 38	96.57 25	98.23 64	94.37 160

pmmvs5		83.37 181	82.68 182	84.18 172	87.13 193	93.18 158	86.74 190	82.08 171	76.48 198	67.28 187	71.26 165	62.70 203	84.71 162	90.77 156	90.12 172	97.15 134	94.24 161

IterMVS		85.25 156	86.49 142	83.80 176	90.42 152	90.77 206	90.02 151	78.04 194	84.10 153	66.27 193	77.28 132	78.41 134	83.01 174	90.88 154	89.72 183	95.04 194	94.24 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test-mter		86.09 145	88.38 118	83.43 181	87.89 177	92.61 174	86.89 189	77.11 199	84.30 149	68.62 178	82.57 99	82.45 103	84.34 164	92.40 128	90.11 173	95.74 177	94.21 163

SixPastTwentyTwo		83.12 185	83.44 172	82.74 190	87.71 182	93.11 162	82.30 208	82.33 167	79.24 183	64.33 201	78.77 124	62.75 202	84.11 169	88.11 190	87.89 192	95.70 180	94.21 163

CR-MVSNet		85.48 152	86.29 144	84.53 167	91.08 145	92.10 184	89.18 166	73.30 211	84.75 142	71.08 160	73.12 161	77.91 139	86.27 149	91.48 143	90.75 155	96.27 170	93.94 165

PatchT		83.86 174	85.51 157	81.94 197	88.41 170	91.56 196	78.79 215	71.57 215	84.08 154	71.08 160	70.62 167	76.13 150	86.27 149	91.48 143	90.75 155	95.52 188	93.94 165

FC-MVSNet-test		86.15 142	89.10 111	82.71 191	89.83 155	93.18 158	87.88 181	84.69 137	86.54 130	62.18 207	82.39 101	83.31 95	74.18 207	92.52 127	91.86 137	97.50 122	93.88 167

baseline1		90.81 89	90.29 95	91.42 90	93.67 102	95.86 111	93.94 90	89.69 74	89.29 105	82.85 106	82.91 93	80.30 121	89.60 108	95.05 66	94.79 70	98.80 12	93.82 168

RPMNet		84.82 161	85.90 152	83.56 179	91.10 143	92.10 184	88.73 175	71.11 216	84.75 142	68.79 175	73.56 153	77.62 142	85.33 158	90.08 170	89.43 185	96.32 169	93.77 169

CHOSEN 280x420		90.77 93	92.14 72	89.17 116	93.86 97	92.81 170	93.16 107	80.22 186	90.21 86	84.67 99	89.89 50	91.38 60	90.57 102	94.94 69	92.11 130	92.52 206	93.65 170

test-LLR		86.88 134	88.28 119	85.24 157	91.22 140	92.07 186	87.41 184	83.62 152	84.58 144	69.33 172	83.00 91	82.79 98	84.24 165	92.26 131	89.81 179	95.64 182	93.44 171

TESTMET0.1,1		86.11 144	88.28 119	83.59 178	87.80 178	92.07 186	87.41 184	77.12 198	84.58 144	69.33 172	83.00 91	82.79 98	84.24 165	92.26 131	89.81 179	95.64 182	93.44 171

CostFormer		86.78 136	86.05 147	87.62 136	92.15 129	93.20 157	91.55 134	75.83 201	88.11 117	85.29 92	81.76 106	76.22 149	87.80 130	84.45 207	85.21 203	93.12 201	93.42 173

PM-MVS		80.29 201	79.30 204	81.45 200	81.91 217	88.23 212	82.61 206	79.01 190	79.99 180	67.15 188	69.07 175	51.39 224	82.92 175	87.55 194	85.59 199	95.08 193	93.28 174

tpm		83.16 183	83.64 168	82.60 193	90.75 147	91.05 200	88.49 176	73.99 206	82.36 165	67.08 189	78.10 127	68.79 172	84.17 167	85.95 203	85.96 198	91.09 213	93.23 175

pmmvs4		86.00 146	84.28 165	88.00 128	87.80 178	92.01 189	89.94 154	84.91 136	86.79 127	80.98 116	73.41 157	66.34 187	88.12 129	89.31 181	88.90 190	96.24 171	93.20 176

PMMVS		89.88 106	91.19 86	88.35 124	89.73 157	91.97 190	90.62 138	81.92 173	90.57 79	80.58 120	92.16 36	86.85 78	91.17 90	92.31 130	91.35 146	96.11 172	93.11 177

PatchMatch-RL		90.30 101	88.93 113	91.89 79	95.41 73	95.68 112	90.94 135	88.67 92	89.80 98	86.95 67	85.90 72	72.51 156	92.46 74	93.56 108	92.18 128	96.93 153	92.89 178

EPNet_dtu		88.32 124	90.61 93	85.64 153	96.79 55	92.27 182	92.03 128	90.31 62	89.05 107	65.44 197	89.43 51	85.90 84	74.22 206	92.76 120	92.09 131	95.02 195	92.76 179
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CVMVSNet		83.83 175	85.53 156	81.85 198	89.60 158	90.92 201	87.81 182	83.21 158	80.11 178	60.16 211	76.47 136	78.57 132	76.79 199	89.76 174	90.13 169	93.51 198	92.75 180

TransMVSNet (Re)		82.67 190	80.93 201	84.69 164	88.71 165	91.50 197	87.90 180	87.15 118	71.54 214	68.24 180	63.69 203	64.67 198	78.51 196	91.65 142	90.73 157	97.64 116	92.73 181

EG-PatchMatch MVS		81.70 198	81.31 197	82.15 196	88.75 164	93.81 137	87.14 187	78.89 191	71.57 212	64.12 203	61.20 209	68.46 174	76.73 201	91.48 143	90.77 154	97.28 128	91.90 182

TDRefinement		84.97 159	83.39 174	86.81 142	92.97 115	94.12 131	92.18 122	87.77 110	82.78 163	71.31 158	68.43 177	68.07 177	81.10 188	89.70 177	89.03 189	95.55 187	91.62 183

pmmvs-eth3d		79.78 204	77.58 209	82.34 195	81.57 218	87.46 215	82.92 205	81.28 180	75.33 206	71.34 157	61.88 205	52.41 223	81.59 186	87.56 193	86.90 195	95.36 191	91.48 184

gm-plane-assit		77.65 208	78.50 206	76.66 208	87.96 176	85.43 219	64.70 225	74.50 204	64.15 222	51.26 224	61.32 208	58.17 220	84.11 169	95.16 65	93.83 86	97.45 124	91.41 185

EU-MVSNet		78.43 205	80.25 202	76.30 209	83.81 213	87.27 217	80.99 210	79.52 188	76.01 201	54.12 220	70.44 170	64.87 195	67.40 214	86.23 201	85.54 201	91.95 211	91.41 185

MSDG		90.42 100	88.25 121	92.94 65	96.67 56	94.41 126	93.96 87	92.91 41	89.59 101	86.26 72	76.74 135	80.92 118	90.43 103	92.60 125	92.08 132	97.44 125	91.41 185

test0.0.03 1		85.58 150	87.69 131	83.11 184	91.22 140	92.54 177	85.60 200	83.62 152	85.66 138	67.84 183	82.79 96	79.70 126	73.51 210	91.15 151	90.79 152	96.88 157	91.23 188

GG-mvs-BLEND		62.84 217	90.21 96	30.91 226	0.57 235	94.45 124	86.99 188	0.34 232	88.71 111	0.98 235	81.55 110	91.58 58	0.86 232	92.66 123	91.43 145	95.73 178	91.11 189

TAMVS		84.94 160	84.95 159	84.93 161	88.82 163	93.18 158	88.44 177	81.28 180	77.16 194	73.76 145	75.43 145	76.57 148	82.04 180	90.59 161	90.79 152	95.22 192	90.94 190

MS-PatchMatch		87.63 127	87.61 132	87.65 134	93.95 92	94.09 132	92.60 116	81.52 178	86.64 128	76.41 135	73.46 156	85.94 83	85.01 161	92.23 134	90.00 176	96.43 168	90.93 191

tpm cat1		84.13 170	81.99 190	86.63 145	91.74 133	91.50 197	90.68 137	75.69 202	86.12 134	85.44 90	72.39 162	70.72 163	85.16 159	80.89 216	81.56 212	91.07 214	90.71 192

ambc			67.96 218		73.69 223	79.79 223	73.82 220		71.61 211	59.80 212	46.00 223	20.79 233	66.15 216	86.92 198	80.11 217	89.13 221	90.50 193

COLMAP_ROB	84.39 15	87.61 128	86.03 148	89.46 112	95.54 69	94.48 123	91.77 132	90.14 66	87.16 123	75.50 137	73.41 157	76.86 147	87.33 138	90.05 171	89.76 182	96.48 165	90.46 194
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPSCF		89.68 109	89.24 108	90.20 104	92.97 115	92.93 166	92.30 119	87.69 112	90.44 82	85.12 94	91.68 40	85.84 85	90.69 98	87.34 195	86.07 197	92.46 207	90.37 195

Anonymous20231206		78.09 207	78.11 208	78.07 207	85.19 210	89.17 209	80.99 210	81.24 182	75.46 205	58.25 215	54.78 219	59.90 217	66.73 215	88.94 187	88.26 191	96.01 173	90.25 196

dps		85.00 158	83.21 178	87.08 139	90.73 148	92.55 176	89.34 163	75.29 203	84.94 141	87.01 66	79.27 120	67.69 179	87.27 139	84.22 208	83.56 208	92.83 204	90.25 196

USDC		86.73 137	85.96 151	87.63 135	91.64 134	93.97 134	92.76 112	84.58 140	88.19 115	70.67 163	80.10 117	67.86 178	89.43 110	91.81 139	89.77 181	96.69 163	90.05 198

tpmrst		83.72 177	83.45 171	84.03 174	92.21 128	91.66 194	88.74 174	73.58 210	88.14 116	72.67 150	77.37 131	72.11 159	86.34 147	82.94 212	82.05 211	90.63 216	89.86 199

SCA		86.25 139	87.52 135	84.77 162	91.59 135	93.90 135	89.11 168	73.25 213	90.38 83	72.84 149	83.26 89	83.79 93	88.49 128	86.07 202	85.56 200	93.33 199	89.67 200

testgi		81.94 195	84.09 166	79.43 204	89.53 160	90.83 204	82.49 207	81.75 176	80.59 173	59.46 213	82.82 95	65.75 188	67.97 212	90.10 169	89.52 184	95.39 189	89.03 201

PatchmatchNet		85.70 148	86.65 140	84.60 165	91.79 132	93.40 149	89.27 164	73.62 208	90.19 87	72.63 151	82.74 97	81.93 112	87.64 133	84.99 205	84.29 207	92.64 205	89.00 202
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13		86.64 138	87.50 136	85.65 152	90.73 148	93.69 142	89.96 153	78.03 195	89.48 104	76.85 133	84.92 79	82.42 104	86.14 151	86.85 199	86.15 196	92.17 208	88.97 203

pmnet_mix02		80.14 202	80.21 203	80.06 201	86.61 201	89.66 208	80.40 212	82.20 170	82.29 167	61.35 208	71.52 164	66.67 185	76.75 200	82.55 213	80.18 216	93.05 202	88.62 204

MIMVSNet		82.97 187	84.00 167	81.77 199	82.23 216	92.25 183	87.40 186	72.73 214	81.48 170	69.55 170	68.79 176	72.42 157	81.82 183	92.23 134	92.25 126	96.89 156	88.61 205

TinyColmap		84.04 172	82.01 189	86.42 147	90.87 146	91.84 191	88.89 173	84.07 147	82.11 168	69.89 168	71.08 166	60.81 212	89.04 120	90.52 162	89.19 187	95.76 176	88.50 206

ADS-MVSNet		84.08 171	84.95 159	83.05 187	91.53 139	91.75 193	88.16 178	70.70 217	89.96 93	69.51 171	78.83 121	76.97 146	86.29 148	84.08 209	84.60 205	92.13 210	88.48 207

EPMVS		85.77 147	86.24 145	85.23 158	92.76 119	93.78 138	89.91 155	73.60 209	90.19 87	74.22 141	82.18 103	78.06 137	87.55 135	85.61 204	85.38 202	93.32 200	88.48 207

MDTV_nov1_ep13_2view		80.43 200	80.94 200	79.84 202	84.82 211	90.87 202	84.23 202	73.80 207	80.28 177	64.33 201	70.05 173	68.77 173	79.67 190	84.83 206	83.50 209	92.17 208	88.25 209

MDA-MVSNet-bldmvs		73.81 211	72.56 215	75.28 210	72.52 225	88.87 210	74.95 219	82.67 162	71.57 212	55.02 218	65.96 190	42.84 231	76.11 202	70.61 223	81.47 213	90.38 218	86.59 210

test20.03		76.41 210	78.49 207	73.98 211	85.64 207	87.50 214	75.89 217	80.71 184	70.84 215	51.07 225	68.06 178	61.40 210	54.99 221	88.28 189	87.20 194	95.58 186	86.15 211

FMVSNet5		84.47 167	84.72 162	84.18 172	83.30 214	88.43 211	88.09 179	79.42 189	84.25 150	74.14 143	73.15 160	78.74 130	83.65 171	91.19 149	91.19 148	96.46 166	86.07 212

pmmvs3		71.13 215	71.06 217	71.21 215	73.54 224	80.19 222	71.69 223	64.86 222	62.04 225	52.10 222	54.92 218	48.00 229	75.03 205	83.75 211	83.24 210	90.04 219	85.27 213

MIMVSNet1		73.19 212	73.70 213	72.60 214	65.42 228	86.69 218	75.56 218	79.65 187	67.87 219	55.30 217	45.24 224	56.41 221	63.79 217	86.98 197	87.66 193	95.85 175	85.04 214

CMPMVS	61.19 17	79.86 203	77.46 211	82.66 192	91.54 138	91.82 192	83.25 204	81.57 177	70.51 216	68.64 177	59.89 212	66.77 184	79.63 191	84.00 210	84.30 206	91.34 212	84.89 215
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
N_pmnet		77.55 209	76.68 212	78.56 206	85.43 209	87.30 216	78.84 214	81.88 174	78.30 188	60.61 209	61.46 206	62.15 205	74.03 209	82.04 214	80.69 215	90.59 217	84.81 216

new-patchmatchnet		72.32 213	71.09 216	73.74 212	81.17 219	84.86 220	72.21 222	77.48 197	68.32 218	54.89 219	55.10 217	49.31 227	63.68 218	79.30 218	76.46 219	93.03 203	84.32 217

MVS-HIRNet		78.16 206	77.57 210	78.83 205	85.83 206	87.76 213	76.67 216	70.22 218	75.82 204	67.39 185	55.61 215	70.52 164	81.96 182	86.67 200	85.06 204	90.93 215	81.58 218

test_method		58.10 221	64.61 221	50.51 221	28.26 233	41.71 232	61.28 226	32.07 228	75.92 203	52.04 223	47.94 222	61.83 208	51.80 222	79.83 217	63.95 226	77.60 226	81.05 219

new_pmnet		72.29 214	73.25 214	71.16 216	75.35 222	81.38 221	73.72 221	69.27 219	75.97 202	49.84 226	56.27 214	56.12 222	69.08 211	81.73 215	80.86 214	89.72 220	80.44 220

DeepMVS_CX						71.82 226	68.37 224	48.05 227	77.38 192	46.88 227	65.77 191	47.03 230	67.48 213	64.27 226		76.89 227	76.72 221

FPMVS		69.87 216	67.10 219	73.10 213	84.09 212	78.35 224	79.40 213	76.41 200	71.92 210	57.71 216	54.06 221	50.04 225	56.72 219	71.19 222	68.70 222	84.25 222	75.43 222

PMVS	56.77 18	61.27 218	58.64 222	64.35 217	75.66 221	54.60 229	53.62 228	74.23 205	53.69 226	58.37 214	44.27 225	49.38 226	44.16 225	69.51 224	65.35 224	80.07 224	73.66 223
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		53.68 222	55.72 224	51.30 220	58.84 229	67.02 227	54.23 227	60.97 225	47.50 227	19.42 231	34.81 226	31.97 232	30.88 227	65.84 225	69.99 221	83.47 223	72.92 224

Gipuma		58.52 220	56.17 223	61.27 218	67.14 227	58.06 228	52.16 229	68.40 221	69.00 217	45.02 228	22.79 227	20.57 234	55.11 220	76.27 219	79.33 218	79.80 225	67.16 225
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
WB-MVS		60.76 219	66.86 220	53.64 219	82.24 215	72.70 225	48.70 231	82.04 172	63.91 223	12.91 234	64.77 198	49.00 228	22.74 229	75.95 220	75.36 220	73.22 228	66.33 226

MVE	39.81 19	39.52 224	41.58 225	37.11 225	33.93 232	49.06 230	26.45 234	54.22 226	29.46 230	24.15 230	20.77 229	10.60 237	34.42 226	51.12 227	65.27 225	49.49 232	64.81 227
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		40.00 223	35.74 226	44.98 223	57.69 231	39.15 234	28.05 232	62.70 223	35.52 229	17.78 232	20.90 228	14.36 236	44.47 224	35.89 228	47.86 227	59.15 230	56.47 228

EMVS		39.04 225	34.32 227	44.54 224	58.25 230	39.35 233	27.61 233	62.55 224	35.99 228	16.40 233	20.04 230	14.77 235	44.80 223	33.12 229	44.10 228	57.61 231	52.89 229

test123		3.48 227	5.31 229	1.34 228	0.20 236	1.52 236	2.17 237	0.58 231	6.13 232	0.31 237	9.85 232	0.31 239	3.90 230	2.65 231	5.28 230	0.87 234	11.46 230

testmvs		4.35 226	6.54 228	1.79 227	0.60 234	1.82 235	3.06 236	0.95 230	7.22 231	0.88 236	12.38 231	1.25 238	3.87 231	6.09 230	5.58 229	1.40 233	11.42 231

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										60.19 210

9.14												97.28 23

SR-MVS					98.93 18			96.00 16				97.75 15

our_test_3					86.93 196	89.77 207	81.61 209

MTAPA										95.36 2		97.46 21

MTMP										95.70 1		96.90 27

Patchmatch-RL test							18.47 235

tmp_tt				50.24 222	68.55 226	46.86 231	48.90 230	18.28 229	86.51 132	68.32 179	70.19 172	65.33 190	26.69 228	74.37 221	66.80 223	70.72 229

XVS					95.68 64	98.66 15	94.96 64			88.03 55		96.06 33				98.46 34

X-MVStestdata					95.68 64	98.66 15	94.96 64			88.03 55		96.06 33				98.46 34

mPP-MVS					98.76 23							95.49 40

NP-MVS									91.63 68

Patchmtry						92.39 181	89.18 166	73.30 211		71.08 160

High-resolution multi-view benchmark