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		77.32 7	82.51 7	71.26 7	75.43 15	80.19 8	82.22 7	58.26 3	84.83 7	64.36 7	78.19 15	83.46 6	63.61 8	81.00 1	80.28 1	83.66 4	89.62 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
SteuartSystems-ACMMP		75.23 13	79.60 15	70.13 13	76.81 6	78.92 12	81.74 8	57.99 6	75.30 29	59.83 26	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 10
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		75.62 12	79.91 14	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 16	63.04 13	70.69 24	81.15 16	62.99 11	80.23 5	79.54 3	83.11 8	89.16 8

ACMMP_NAP		76.15 9	81.17 9	70.30 11	74.09 21	79.47 10	81.59 12	57.09 14	81.38 11	63.89 10	79.02 13	80.48 19	62.24 17	80.05 6	79.12 4	82.94 11	88.64 9

HPM-MVS++		76.01 10	80.47 12	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 11	78.80 14	82.53 11	64.40 6	78.74 10	78.84 5	81.81 33	87.46 18

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 4	58.16 4	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 16	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 10	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 10	79.99 7	78.56 7	82.31 22	91.03 1
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		77.82 5	83.46 5	71.24 8	75.26 17	80.22 7	82.95 3	57.85 8	85.90 3	64.79 5	88.54 3	83.43 7	66.24 3	78.21 17	78.56 7	80.34 46	89.39 7
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
DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 7	81.93 3	82.92 5	58.10 5	85.86 4	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 27	90.29 4

NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 22	80.51 15	57.09 14	78.25 20	62.28 18	65.54 37	78.26 25	62.18 18	79.13 8	78.51 10	83.01 10	87.68 17

DeepC-MVS	66.32 2	73.85 22	78.10 23	68.90 22	67.92 49	79.31 11	78.16 29	59.28 1	78.24 21	61.13 20	67.36 35	76.10 33	63.40 9	79.11 9	78.41 11	83.52 5	88.16 13
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		74.31 18	78.87 18	68.99 21	73.49 24	78.56 15	79.25 23	56.51 17	75.33 27	60.69 23	75.30 19	79.12 23	61.81 20	77.78 21	77.93 12	82.18 29	88.06 14
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HFP-MVS		74.87 15	78.86 20	70.21 12	73.99 22	77.91 18	80.36 16	56.63 16	78.41 19	64.27 8	74.54 20	77.75 28	62.96 12	78.70 12	77.82 13	83.02 9	86.91 21

ACMMPR		73.79 23	78.41 21	68.40 24	72.35 28	77.79 19	79.32 20	56.38 18	77.67 23	58.30 32	74.16 21	76.66 29	61.40 22	78.32 14	77.80 14	82.68 15	86.51 22

DPE-MVS		78.11 4	83.84 4	71.42 5	77.82 5	81.32 4	82.92 5	57.81 9	84.04 8	63.19 12	88.63 2	86.00 4	64.52 5	78.71 11	77.63 15	82.26 23	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DeepPCF-MVS	66.49 1	74.25 20	80.97 10	66.41 31	67.75 51	78.87 13	75.61 39	54.16 33	84.86 6	58.22 33	77.94 16	81.01 17	62.52 15	78.34 13	77.38 16	80.16 49	88.40 11

X-MVS		71.18 32	75.66 32	65.96 35	71.71 30	76.96 25	77.26 33	55.88 22	72.75 37	54.48 48	64.39 44	74.47 38	54.19 66	77.84 20	77.37 17	82.21 26	85.85 26

PGM-MVS		72.89 25	77.13 26	67.94 25	72.47 27	77.25 23	79.27 22	54.63 29	73.71 34	57.95 34	72.38 22	75.33 35	60.75 27	78.25 16	77.36 18	82.57 19	85.62 28

CSCG		74.68 16	79.22 16	69.40 17	75.69 12	80.01 9	79.12 24	52.83 41	79.34 17	63.99 9	70.49 25	82.02 12	60.35 32	77.48 24	77.22 19	84.38 1	87.97 15

CP-MVS		72.63 27	76.95 27	67.59 26	70.67 36	75.53 34	77.95 31	56.01 21	75.65 26	58.82 29	69.16 29	76.48 31	60.46 30	77.66 22	77.20 20	81.65 37	86.97 20

DeepC-MVS_fast	65.08 3	72.00 29	76.11 28	67.21 28	68.93 45	77.46 21	76.54 35	54.35 31	74.92 31	58.64 31	65.18 39	74.04 43	62.62 14	77.92 19	77.02 21	82.16 30	86.21 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		77.58 6	82.93 6	71.35 6	77.86 4	80.55 6	83.38 1	57.61 10	85.57 5	61.11 21	86.10 7	82.98 8	64.76 4	78.29 15	76.78 22	83.40 6	90.20 5

DPM-MVS		72.80 26	75.90 29	69.19 20	75.51 13	77.68 20	81.62 11	54.83 26	75.96 25	62.06 19	63.96 47	76.58 30	58.55 40	76.66 32	76.77 23	82.60 18	83.68 40

CDPH-MVS		71.47 31	75.82 31	66.41 31	72.97 26	77.15 24	78.14 30	54.71 27	69.88 46	53.07 56	70.98 23	74.83 37	56.95 52	76.22 33	76.57 24	82.62 17	85.09 33

OPM-MVS		69.33 37	71.05 45	67.32 27	72.34 29	75.70 33	79.57 19	56.34 19	55.21 74	53.81 53	59.51 64	68.96 56	59.67 34	77.61 23	76.44 25	82.19 27	83.88 38
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMMP		71.57 30	75.84 30	66.59 30	70.30 40	76.85 28	78.46 28	53.95 34	73.52 35	55.56 39	70.13 26	71.36 48	58.55 40	77.00 27	76.23 26	82.71 14	85.81 27
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
APD-MVS		75.80 11	80.90 11	69.86 15	75.42 16	78.48 16	81.43 13	57.44 12	80.45 14	59.32 27	85.28 8	80.82 18	63.96 7	76.89 28	76.08 27	81.58 39	88.30 12
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		73.89 21	78.25 22	68.80 23	75.25 18	72.27 51	79.75 18	56.05 20	74.87 32	58.97 28	81.83 11	79.76 21	61.05 25	77.39 25	76.01 28	81.71 36	85.61 29

MCST-MVS		73.67 24	77.39 25	69.33 18	76.26 9	78.19 17	78.77 26	54.54 30	75.33 27	59.99 25	67.96 31	79.23 22	62.43 16	78.00 18	75.71 29	84.02 2	87.30 19

TSAR-MVS + MP.		75.22 14	80.06 13	69.56 16	74.61 19	72.74 49	80.59 14	55.70 23	80.80 13	62.65 15	86.25 6	82.92 9	62.07 19	76.89 28	75.66 30	81.77 35	85.19 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		77.13 8	81.70 8	71.79 3	79.32 1	80.76 5	82.96 2	57.49 11	82.82 9	64.79 5	83.69 10	84.46 5	62.83 13	77.13 26	75.21 31	83.35 7	87.85 16

3Dnovator+	62.63 4	69.51 35	72.62 39	65.88 36	68.21 48	76.47 30	73.50 49	52.74 42	70.85 42	58.65 30	55.97 77	69.95 51	61.11 24	76.80 30	75.09 32	81.09 42	83.23 44

MVS_0304		69.49 36	73.96 35	64.28 44	67.92 49	76.13 32	74.90 42	47.60 68	63.29 57	54.09 52	67.44 34	76.35 32	59.53 35	75.81 37	75.03 33	81.62 38	83.70 39

ACMM	60.30 7	67.58 47	68.82 59	66.13 33	70.59 37	72.01 53	76.54 35	54.26 32	65.64 52	54.78 47	50.35 106	61.72 81	58.74 38	75.79 38	75.03 33	81.88 31	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		70.88 33	75.02 33	66.05 34	71.69 31	74.47 41	77.51 32	53.17 38	72.89 36	54.88 45	70.03 27	70.48 50	57.26 48	76.02 35	75.01 35	81.78 34	86.21 23

CLD-MVS		67.02 49	71.57 42	61.71 51	71.01 35	74.81 38	71.62 51	38.91 159	71.86 40	60.70 22	64.97 41	67.88 64	51.88 92	76.77 31	74.98 36	76.11 95	69.75 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_111021_HR		67.62 46	70.39 49	64.39 43	69.77 41	70.45 58	71.44 53	51.72 47	60.77 63	55.06 43	62.14 56	66.40 67	58.13 43	76.13 34	74.79 37	80.19 48	82.04 49

MAR-MVS		68.04 44	70.74 47	64.90 41	71.68 32	76.33 31	74.63 44	50.48 55	63.81 54	55.52 40	54.88 83	69.90 52	57.39 47	75.42 41	74.79 37	79.71 51	80.03 56
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
LGP-MVS_train		68.87 39	72.03 41	65.18 39	69.33 43	74.03 44	76.67 34	53.88 35	68.46 47	52.05 60	63.21 49	63.89 70	56.31 56	75.99 36	74.43 39	82.83 13	84.18 35

PHI-MVS		69.27 38	74.84 34	62.76 50	66.83 54	74.83 37	73.88 47	49.32 60	70.61 43	50.93 63	69.62 28	74.84 36	57.25 49	75.53 39	74.32 40	78.35 67	84.17 36

ACMP	61.42 5	68.72 42	71.37 43	65.64 37	69.06 44	74.45 42	75.88 38	53.30 37	68.10 48	55.74 38	61.53 59	62.29 77	56.97 51	74.70 46	74.23 41	82.88 12	84.31 34
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TSAR-MVS + GP.		69.71 34	73.92 36	64.80 42	68.27 47	70.56 56	71.90 50	50.75 51	71.38 41	57.46 36	68.68 30	75.42 34	60.10 33	73.47 51	73.99 42	80.32 47	83.97 37

SD-MVS		74.43 17	78.87 18	69.26 19	74.39 20	73.70 45	79.06 25	55.24 25	81.04 12	62.71 14	80.18 12	82.61 10	61.70 21	75.43 40	73.92 43	82.44 21	85.22 31
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
TSAR-MVS + ACMM		72.56 28	79.07 17	64.96 40	73.24 25	73.16 48	78.50 27	48.80 66	79.34 17	55.32 41	85.04 9	81.49 15	58.57 39	75.06 43	73.75 44	75.35 107	85.61 29

AdaColmap		67.89 45	68.85 58	66.77 29	73.73 23	74.30 43	75.28 40	53.58 36	70.24 44	57.59 35	51.19 103	59.19 92	60.74 28	75.33 42	73.72 45	79.69 54	77.96 70

3Dnovator	60.86 6	66.99 51	70.32 50	63.11 48	66.63 55	74.52 39	71.56 52	45.76 77	67.37 50	55.00 44	54.31 88	68.19 60	58.49 42	73.97 49	73.63 46	81.22 41	80.23 55

CANet		68.77 40	73.01 37	63.83 45	68.30 46	75.19 35	73.73 48	47.90 67	63.86 53	54.84 46	67.51 33	74.36 41	57.62 44	74.22 48	73.57 47	80.56 44	82.36 46

DELS-MVS		65.87 53	70.30 51	60.71 54	64.05 71	72.68 50	70.90 54	45.43 81	57.49 69	49.05 70	64.43 43	68.66 57	55.11 64	74.31 47	73.02 48	79.70 52	81.51 50
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
EPNet		65.14 59	69.54 55	60.00 58	66.61 56	67.67 76	67.53 64	55.32 24	62.67 59	46.22 80	67.74 32	65.93 68	48.07 110	72.17 57	72.12 49	76.28 91	78.47 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		68.76 41	73.01 37	63.81 46	65.42 61	73.66 46	76.39 37	52.08 43	72.61 38	50.33 65	60.73 60	72.65 46	59.43 36	73.32 52	72.12 49	79.19 60	85.99 25

CS-MVS		65.88 52	69.71 54	61.41 52	61.76 81	68.14 68	67.65 62	44.00 105	59.14 67	52.69 57	65.19 38	68.13 61	60.90 26	74.74 45	71.58 51	81.46 40	81.04 53

Effi-MVS+		63.28 62	65.96 69	60.17 57	64.26 67	68.06 70	68.78 59	45.71 79	54.08 77	46.64 77	55.92 78	63.13 74	55.94 60	70.38 75	71.43 52	79.68 55	78.70 63

QAPM		65.27 55	69.49 56	60.35 55	65.43 60	72.20 52	65.69 85	47.23 69	63.46 55	49.14 68	53.56 89	71.04 49	57.01 50	72.60 56	71.41 53	77.62 71	82.14 48

ETV-MVS		63.23 63	66.08 68	59.91 59	63.13 75	68.13 69	67.62 63	44.62 92	53.39 82	46.23 79	58.74 66	58.19 95	57.45 46	73.60 50	71.38 54	80.39 45	79.13 60

EC-MVSNet		67.01 50	70.27 52	63.21 47	67.21 52	70.47 57	69.01 56	46.96 71	59.16 66	53.23 55	64.01 46	69.71 54	60.37 31	74.92 44	71.24 55	82.50 20	82.41 45

canonicalmvs		65.62 54	72.06 40	58.11 68	63.94 72	71.05 54	64.49 95	43.18 126	74.08 33	47.35 73	64.17 45	71.97 47	51.17 95	71.87 58	70.74 56	78.51 65	80.56 54

EG-PatchMatch MVS		56.98 106	58.24 130	55.50 91	64.66 64	68.62 64	61.48 106	43.63 114	38.44 192	41.44 103	38.05 183	46.18 160	43.95 128	71.71 60	70.61 57	77.87 68	74.08 103

MSLP-MVS++		68.17 43	70.72 48	65.19 38	69.41 42	70.64 55	74.99 41	45.76 77	70.20 45	60.17 24	56.42 75	73.01 44	61.14 23	72.80 54	70.54 58	79.70 52	81.42 51

IB-MVS	54.11 11	58.36 95	60.70 96	55.62 90	58.67 101	68.02 72	61.56 104	43.15 127	46.09 138	44.06 91	44.24 154	50.99 128	48.71 104	66.70 127	70.33 59	77.60 72	78.50 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
anonymousdsp		52.84 138	57.78 134	47.06 157	40.24 203	58.95 150	53.70 160	33.54 192	36.51 199	32.69 142	43.88 156	45.40 164	47.97 111	67.17 119	70.28 60	74.22 116	82.29 47

ACMH	52.42 13	58.24 97	59.56 117	56.70 84	66.34 58	69.59 59	66.71 73	49.12 61	46.08 139	28.90 160	42.67 171	41.20 188	52.60 84	71.39 62	70.28 60	76.51 87	75.72 90
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IS_MVSNet		57.95 100	64.26 80	50.60 121	61.62 83	65.25 102	57.18 132	45.42 82	50.79 97	26.49 174	57.81 71	60.05 89	34.51 175	71.24 65	70.20 62	78.36 66	74.44 99

CS-MVS-test		65.18 57	68.70 60	61.07 53	61.92 78	68.06 70	67.09 70	45.18 85	58.47 68	52.02 61	65.76 36	66.44 66	59.24 37	72.71 55	70.05 63	80.98 43	79.40 59

PVSNet_Blended_VisFu		63.65 61	66.92 62	59.83 60	60.03 93	73.44 47	66.33 76	48.95 62	52.20 93	50.81 64	56.07 76	60.25 88	53.56 72	73.23 53	70.01 64	79.30 57	83.24 43

Vis-MVSNet		58.48 91	65.70 71	50.06 126	53.40 147	67.20 82	60.24 115	43.32 123	48.83 115	30.23 153	62.38 55	61.61 82	40.35 146	71.03 66	69.77 65	72.82 135	79.11 61
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test2506		55.82 118	59.57 116	51.46 117	60.39 90	64.55 108	58.69 123	48.87 63	53.91 78	26.99 169	48.97 112	41.72 187	37.71 158	70.96 67	69.49 66	76.08 96	67.37 143

ECVR-MVS		56.44 113	60.74 95	51.42 118	60.39 90	64.55 108	58.69 123	48.87 63	53.91 78	26.76 171	45.55 144	53.43 116	37.71 158	70.96 67	69.49 66	76.08 96	67.32 145

Fast-Effi-MVS+		60.36 76	63.35 83	56.87 82	58.70 100	65.86 95	65.08 91	37.11 173	53.00 87	45.36 85	52.12 97	56.07 108	56.27 57	71.28 64	69.42 68	78.71 61	75.69 91

PCF-MVS	59.98 8	67.32 48	71.04 46	62.97 49	64.77 63	74.49 40	74.78 43	49.54 57	67.44 49	54.39 51	58.35 69	72.81 45	55.79 62	71.54 61	69.24 69	78.57 62	83.41 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EIA-MVS		61.53 74	63.79 82	58.89 65	63.82 73	67.61 77	65.35 88	42.15 137	49.98 101	45.66 83	57.47 73	56.62 102	56.59 55	70.91 69	69.15 70	79.78 50	74.80 97

EPP-MVSNet		59.39 81	65.45 72	52.32 114	60.96 86	67.70 75	58.42 125	44.75 90	49.71 103	27.23 168	59.03 65	62.20 78	43.34 132	70.71 70	69.13 71	79.25 59	79.63 58

test1111		55.24 124	59.98 109	49.71 127	59.80 96	64.10 113	56.48 139	49.34 59	52.27 92	21.56 186	44.49 152	51.96 122	35.93 170	70.59 71	69.07 72	75.13 109	67.40 141

TranMVSNet+NR-MVSNet		55.87 116	60.14 106	50.88 120	59.46 99	63.82 114	57.93 127	52.98 39	48.94 113	20.52 189	52.87 92	47.33 147	36.81 166	69.12 85	69.03 73	77.56 74	69.89 122

ACMH+	53.71 12	59.26 82	60.28 101	58.06 69	64.17 69	68.46 65	67.51 65	50.93 50	52.46 91	35.83 132	40.83 176	45.12 169	52.32 87	69.88 79	69.00 74	77.59 73	76.21 87

casdiffmvs_mvg		65.26 56	69.48 57	60.33 56	62.99 76	69.34 61	69.80 55	45.27 83	63.38 56	51.11 62	65.12 40	69.75 53	53.51 74	71.74 59	68.86 75	79.33 56	78.19 69
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_NR-MVSNet		56.94 108	61.14 91	52.05 116	60.02 94	65.21 103	57.44 130	52.93 40	49.37 107	24.31 181	54.62 87	50.54 129	39.04 150	68.69 88	68.84 76	78.53 64	70.72 116

OMC-MVS		65.16 58	71.35 44	57.94 72	52.95 150	68.82 63	69.00 57	38.28 167	79.89 15	55.20 42	62.76 52	68.31 59	56.14 59	71.30 63	68.70 77	76.06 99	79.67 57

NR-MVSNet		55.35 123	59.46 118	50.56 122	61.33 84	62.97 118	57.91 128	51.80 45	48.62 121	20.59 188	51.99 98	44.73 175	34.10 178	68.58 91	68.64 78	77.66 70	70.67 120

OpenMVS	57.13 9	62.81 65	65.75 70	59.39 62	66.47 57	69.52 60	64.26 97	43.07 129	61.34 62	50.19 66	47.29 124	64.41 69	54.60 65	70.18 77	68.62 79	77.73 69	78.89 62

ET-MVSNet_ETH3D		58.38 94	61.57 89	54.67 95	42.15 200	65.26 100	65.70 83	43.82 107	48.84 114	42.34 99	59.76 63	47.76 141	56.68 54	67.02 124	68.60 80	77.33 77	73.73 106

FC-MVSNet-train		58.40 93	63.15 84	52.85 110	64.29 66	61.84 124	55.98 145	46.47 73	53.06 85	34.96 135	61.95 58	56.37 106	39.49 148	68.67 89	68.36 81	75.92 101	71.81 111

MVS_111021_LR		63.05 64	66.43 65	59.10 64	61.33 84	63.77 115	65.87 82	43.58 115	60.20 64	53.70 54	62.09 57	62.38 76	55.84 61	70.24 76	68.08 82	74.30 115	78.28 68

GeoE		62.43 68	64.79 77	59.68 61	64.15 70	67.17 83	68.80 58	44.42 96	55.65 73	47.38 72	51.54 100	62.51 75	54.04 69	69.99 78	68.07 83	79.28 58	78.57 64

HyFIR lowres test		56.87 109	58.60 127	54.84 93	56.62 127	69.27 62	64.77 93	42.21 135	45.66 142	37.50 127	33.08 194	57.47 100	53.33 79	65.46 145	67.94 84	74.60 112	71.35 113

UniMVSNet (Re)		55.15 128	60.39 100	49.03 136	55.31 132	64.59 107	55.77 146	50.63 52	48.66 120	20.95 187	51.47 101	50.40 130	34.41 177	67.81 108	67.89 85	77.11 81	71.88 110

thisisatest0530		56.68 110	59.68 111	53.19 106	52.97 149	60.96 134	59.41 118	40.51 149	48.26 124	41.06 108	52.67 93	46.30 157	49.78 97	67.66 112	67.83 86	75.39 105	74.07 104

tttt0517		56.53 112	59.59 113	52.95 109	52.66 152	60.99 133	59.21 120	40.51 149	47.89 127	40.40 111	52.50 96	46.04 161	49.78 97	67.75 110	67.83 86	75.15 108	74.17 101

MSDG		58.46 92	58.97 123	57.85 76	66.27 59	66.23 93	67.72 61	42.33 133	53.43 81	43.68 92	43.39 162	45.35 165	49.75 99	68.66 90	67.77 88	77.38 75	67.96 138

DU-MVS		55.41 122	59.59 113	50.54 123	54.60 138	62.97 118	57.44 130	51.80 45	48.62 121	24.31 181	51.99 98	47.00 150	39.04 150	68.11 101	67.75 89	76.03 100	70.72 116

Anonymous202405211			60.60 97		63.44 74	66.71 90	61.00 111	47.23 69	50.62 99		36.85 186	60.63 87	43.03 136	69.17 83	67.72 90	75.41 104	72.54 108

FA-MVS(training)		60.00 79	63.14 85	56.33 86	59.50 98	64.30 111	65.15 90	38.75 164	56.20 71	45.77 81	53.08 90	56.45 103	52.10 90	69.04 86	67.67 91	76.69 84	75.27 96

DCV-MVSNet		59.49 80	64.00 81	54.23 96	61.81 79	64.33 110	61.42 107	43.77 108	52.85 88	38.94 120	55.62 80	62.15 79	43.24 135	69.39 82	67.66 92	76.22 93	75.97 88

UGNet		57.03 105	65.25 73	47.44 156	46.54 186	66.73 87	56.30 140	43.28 124	50.06 100	32.99 139	62.57 54	63.26 73	33.31 180	68.25 96	67.58 93	72.20 147	78.29 67
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
CHOSEN 1792x2688		55.85 117	58.01 131	53.33 103	57.26 121	62.82 120	63.29 103	41.55 140	46.65 134	38.34 121	34.55 192	53.50 114	52.43 86	67.10 122	67.56 94	67.13 170	73.92 105

CANet_DTU		58.88 85	64.68 78	52.12 115	55.77 130	66.75 86	63.92 98	37.04 174	53.32 83	37.45 128	59.81 62	61.81 80	44.43 127	68.25 96	67.47 95	74.12 117	75.33 94

UA-Net		58.50 90	64.68 78	51.30 119	66.97 53	67.13 84	53.68 161	45.65 80	49.51 106	31.58 147	62.91 51	68.47 58	35.85 171	68.20 99	67.28 96	74.03 118	69.24 133

Effi-MVS+-dtu		60.34 77	62.32 87	58.03 71	64.31 65	67.44 80	65.99 80	42.26 134	49.55 104	42.00 102	48.92 114	59.79 90	56.27 57	68.07 103	67.03 97	77.35 76	75.45 93

GBi-Net		55.20 125	60.25 102	49.31 130	52.42 153	61.44 126	57.03 133	44.04 101	49.18 110	30.47 149	48.28 116	58.19 95	38.22 153	68.05 104	66.96 98	73.69 122	69.65 124

test1		55.20 125	60.25 102	49.31 130	52.42 153	61.44 126	57.03 133	44.04 101	49.18 110	30.47 149	48.28 116	58.19 95	38.22 153	68.05 104	66.96 98	73.69 122	69.65 124

FMVSNet1		54.08 133	58.68 125	48.71 140	50.90 169	61.35 129	56.73 137	43.94 106	45.91 140	29.32 159	42.72 170	56.26 107	37.70 160	68.05 104	66.96 98	73.69 122	69.50 128

thisisatest0515		53.85 134	56.84 141	50.37 124	50.25 173	58.17 159	55.99 144	39.90 156	41.88 172	38.16 123	45.91 138	45.30 166	44.58 126	66.15 137	66.89 101	73.36 128	73.57 107

CDS-MVSNet		52.42 141	57.06 140	47.02 158	53.92 145	58.30 157	55.50 149	46.47 73	42.52 169	29.38 158	49.50 109	52.85 119	28.49 190	66.70 127	66.89 101	68.34 165	62.63 175
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVSTER		57.19 104	61.11 92	52.62 112	50.82 170	58.79 151	61.55 105	37.86 170	48.81 116	41.31 105	57.43 74	52.10 121	48.60 105	68.19 100	66.75 103	75.56 103	75.68 92

MS-PatchMatch		58.19 99	60.20 104	55.85 89	65.17 62	64.16 112	64.82 92	41.48 141	50.95 96	42.17 101	45.38 145	56.42 104	48.08 109	68.30 95	66.70 104	73.39 126	69.46 131

DI_MVS_plusplus_trai		61.88 70	65.17 74	58.06 69	60.05 92	65.26 100	66.03 79	44.22 97	55.75 72	46.73 75	54.64 86	68.12 62	54.13 68	69.13 84	66.66 105	77.18 78	76.61 80

TSAR-MVS + COLMAP		62.65 67	69.90 53	54.19 97	46.31 187	66.73 87	65.49 87	41.36 142	76.57 24	46.31 78	76.80 17	56.68 101	53.27 81	69.50 81	66.65 106	72.40 144	76.36 86

Anonymous20231211		57.71 102	60.79 94	54.13 98	61.68 82	65.81 96	60.81 112	43.70 112	51.97 94	39.67 115	34.82 191	63.59 71	43.31 133	68.55 93	66.63 107	75.59 102	74.13 102

v1144		58.88 85	60.16 105	57.39 78	58.03 105	67.26 81	67.14 68	44.46 94	45.17 144	44.33 90	47.81 121	49.92 134	53.20 82	67.77 109	66.62 108	77.15 79	76.58 81

v10		59.17 84	60.60 97	57.50 77	57.95 106	66.73 87	67.09 70	44.11 98	46.85 132	45.42 84	48.18 120	51.07 125	53.63 71	67.84 107	66.59 109	76.79 82	76.92 77

v1192		58.51 89	59.66 112	57.17 79	57.82 107	67.72 74	66.21 78	44.83 89	44.15 152	43.49 93	46.68 126	47.94 138	53.55 73	67.39 116	66.51 110	77.13 80	77.20 75

LS3D		60.20 78	61.70 88	58.45 67	64.18 68	67.77 73	67.19 66	48.84 65	61.67 61	41.27 106	45.89 139	51.81 123	54.18 67	68.78 87	66.50 111	75.03 110	69.48 129

Fast-Effi-MVS+-dtu		56.30 114	59.29 120	52.82 111	58.64 102	64.89 104	65.56 86	32.89 196	45.80 141	35.04 134	45.89 139	54.14 113	49.41 100	67.16 120	66.45 112	75.37 106	70.69 118

MVS_Test		62.40 69	66.23 67	57.94 72	59.77 97	64.77 106	66.50 75	41.76 138	57.26 70	49.33 67	62.68 53	67.47 65	53.50 76	68.57 92	66.25 113	76.77 83	76.58 81

v7n		55.67 119	57.46 138	53.59 102	56.06 128	65.29 99	61.06 110	43.26 125	40.17 183	37.99 124	40.79 177	45.27 168	47.09 114	67.67 111	66.21 114	76.08 96	76.82 78

FMVSNet2		55.04 129	59.95 110	49.31 130	52.42 153	61.44 126	57.03 133	44.08 100	49.55 104	30.40 152	46.89 125	58.84 93	38.22 153	67.07 123	66.21 114	73.69 122	69.65 124

casdiffmvs		64.09 60	68.13 61	59.37 63	61.81 79	68.32 67	68.48 60	44.45 95	61.95 60	49.12 69	63.04 50	69.67 55	53.83 70	70.46 72	66.06 116	78.55 63	77.43 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v2v482		58.69 88	60.12 108	57.03 80	57.16 124	66.05 94	67.17 67	43.52 117	46.33 136	45.19 86	49.46 110	51.02 126	52.51 85	67.30 117	66.03 117	76.61 85	74.62 98

Baseline_NR-MVSNet		53.50 135	57.89 132	48.37 147	54.60 138	59.25 148	56.10 141	51.84 44	49.32 108	17.92 196	45.38 145	47.68 142	36.93 165	68.11 101	65.95 118	72.84 134	69.57 127

V42		56.97 107	60.14 106	53.28 104	48.16 179	62.78 121	66.30 77	37.93 169	47.44 129	42.68 97	48.19 119	52.59 120	51.90 91	67.46 115	65.94 119	72.72 137	76.55 83

v144192		58.23 98	59.40 119	56.87 82	57.56 108	66.89 85	65.70 83	45.01 87	44.06 153	42.88 95	46.61 128	48.09 137	53.49 77	66.94 125	65.90 120	76.61 85	77.29 73

v1240		57.55 103	58.63 126	56.29 87	57.30 119	66.48 92	63.77 99	44.56 93	42.77 167	42.48 98	45.64 142	46.28 158	53.46 78	66.32 133	65.80 121	76.16 94	77.13 76

v1921920		57.89 101	59.02 122	56.58 85	57.55 109	66.66 91	64.72 94	44.70 91	43.55 157	42.73 96	46.17 136	46.93 151	53.51 74	66.78 126	65.75 122	76.29 90	77.28 74

v8		58.88 85	60.57 99	56.92 81	57.35 116	65.69 97	66.69 74	42.64 131	47.89 127	45.77 81	49.04 111	52.98 118	52.77 83	67.51 114	65.57 123	76.26 92	75.30 95

diffmvs		61.64 71	66.55 64	55.90 88	56.63 126	63.71 116	67.13 69	41.27 143	59.49 65	46.70 76	63.93 48	68.01 63	50.46 96	67.30 117	65.51 124	73.24 132	77.87 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
GA-MVS		55.67 119	58.33 128	52.58 113	55.23 135	63.09 117	61.08 109	40.15 155	42.95 162	37.02 130	52.61 94	47.68 142	47.51 112	65.92 139	65.35 125	74.49 114	70.68 119

IterMVS-LS		58.30 96	61.39 90	54.71 94	59.92 95	58.40 155	59.42 117	43.64 113	48.71 118	40.25 113	57.53 72	58.55 94	52.15 89	65.42 146	65.34 126	72.85 133	75.77 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PLC	52.09 14	59.21 83	62.47 86	55.41 92	53.24 148	64.84 105	64.47 96	40.41 153	65.92 51	44.53 89	46.19 135	55.69 109	55.33 63	68.24 98	65.30 127	74.50 113	71.09 114
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CNLPA		62.78 66	66.31 66	58.65 66	58.47 103	68.41 66	65.98 81	41.22 144	78.02 22	56.04 37	46.65 127	59.50 91	57.50 45	69.67 80	65.27 128	72.70 139	76.67 79

TransMVSNet (Re)		51.92 149	55.38 147	47.88 153	60.95 87	59.90 142	53.95 158	45.14 86	39.47 186	24.85 178	43.87 157	46.51 156	29.15 187	67.55 113	65.23 129	73.26 131	65.16 163

PVSNet_BlendedMVS		61.63 72	64.82 75	57.91 74	57.21 122	67.55 78	63.47 101	46.08 75	54.72 75	52.46 58	58.59 67	60.73 84	51.82 93	70.46 72	65.20 130	76.44 88	76.50 84

PVSNet_Blended		61.63 72	64.82 75	57.91 74	57.21 122	67.55 78	63.47 101	46.08 75	54.72 75	52.46 58	58.59 67	60.73 84	51.82 93	70.46 72	65.20 130	76.44 88	76.50 84

FMVSNet3		54.78 130	59.58 115	49.17 133	52.37 156	61.31 130	56.72 138	44.04 101	49.18 110	30.47 149	48.28 116	58.19 95	38.09 156	65.48 144	65.20 130	73.31 129	69.45 132

UniMVSNet_ETH3D		52.62 139	55.98 143	48.70 141	51.04 167	60.71 136	56.87 136	46.74 72	42.52 169	26.96 170	42.50 172	45.95 162	37.87 157	66.22 135	65.15 133	72.74 136	68.78 136

TAPA-MVS	54.74 10	60.85 75	66.61 63	54.12 99	47.38 183	65.33 98	65.35 88	36.51 176	75.16 30	48.82 71	54.70 85	63.51 72	53.31 80	68.36 94	64.97 134	73.37 127	74.27 100
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
WR-MVS		48.78 169	55.06 151	41.45 183	55.50 131	60.40 137	43.77 199	49.99 56	41.92 171	8.10 215	45.24 148	45.56 163	17.47 204	61.57 162	64.60 135	73.85 119	66.14 155

tfpn200view9		52.53 140	55.51 145	49.06 135	57.31 117	60.24 138	55.42 151	43.77 108	42.85 165	27.81 164	43.00 168	45.06 171	37.32 162	66.38 130	64.54 136	72.71 138	66.54 148

thres400		52.38 143	55.51 145	48.74 139	57.49 112	60.10 141	55.45 150	43.54 116	42.90 164	26.72 172	43.34 164	45.03 173	36.61 167	66.20 136	64.53 137	72.66 140	66.43 149

gg-mvs-nofinetune		49.07 167	52.56 167	45.00 167	61.99 77	59.78 143	53.55 163	41.63 139	31.62 208	12.08 204	29.56 203	53.28 117	29.57 186	66.27 134	64.49 138	71.19 155	62.92 172

baseline2		55.89 115	57.82 133	53.64 100	57.36 115	61.09 132	59.75 116	40.45 151	47.38 130	41.26 107	51.23 102	46.90 152	48.11 108	65.63 143	64.38 139	74.90 111	68.16 137

baseline1		54.48 132	58.69 124	49.57 128	60.63 89	58.29 158	55.70 147	44.95 88	49.20 109	29.62 156	54.77 84	54.75 111	35.29 172	67.15 121	64.08 140	71.21 154	62.58 176

PEN-MVS		49.21 165	54.32 155	43.24 177	54.33 141	59.26 147	47.04 185	51.37 49	41.67 173	9.97 210	46.22 134	41.80 186	22.97 200	60.52 165	64.03 141	73.73 121	66.75 147

pm-mvs1		51.02 153	55.55 144	45.73 162	54.16 142	58.52 153	50.92 168	42.56 132	40.32 181	25.67 176	43.66 159	50.34 131	30.06 185	65.85 140	63.97 142	70.99 156	66.21 152

thres200		52.39 142	55.37 148	48.90 137	57.39 114	60.18 139	55.60 148	43.73 110	42.93 163	27.41 166	43.35 163	45.09 170	36.61 167	66.36 131	63.92 143	72.66 140	65.78 158

pmmvs4		54.66 131	56.07 142	53.00 108	54.63 137	57.08 166	60.43 114	44.10 99	51.69 95	40.55 110	46.55 131	44.79 174	45.95 120	62.54 156	63.66 144	72.36 145	66.20 153

thres100view900		52.04 147	54.81 153	48.80 138	57.31 117	59.33 146	55.30 152	42.92 130	42.85 165	27.81 164	43.00 168	45.06 171	36.99 164	64.74 149	63.51 145	72.47 143	65.21 162

tfpnnormal		50.16 159	52.19 171	47.78 155	56.86 125	58.37 156	54.15 157	44.01 104	38.35 194	25.94 175	36.10 187	37.89 201	34.50 176	65.93 138	63.42 146	71.26 153	65.28 161

Vis-MVSNet (Re-imp)		50.37 157	57.73 136	41.80 182	57.53 110	54.35 172	45.70 191	45.24 84	49.80 102	13.43 202	58.23 70	56.42 104	20.11 203	62.96 154	63.36 147	68.76 164	58.96 188

thres600view7		51.91 150	55.14 149	48.14 149	57.43 113	60.18 139	54.60 156	43.73 110	42.61 168	25.20 177	43.10 167	44.47 178	35.19 173	66.36 131	63.28 148	72.66 140	66.01 156

pmmvs6		48.35 171	51.64 173	44.51 170	51.92 159	57.94 162	49.44 174	42.17 136	34.45 201	24.62 180	28.87 205	46.90 152	29.07 189	64.60 150	63.08 149	69.83 161	65.68 159

COLMAP_ROB	46.52 15	51.99 148	54.86 152	48.63 142	49.13 177	61.73 125	60.53 113	36.57 175	53.14 84	32.95 140	37.10 184	38.68 199	40.49 145	65.72 141	63.08 149	72.11 148	64.60 166
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
gm-plane-assit		44.74 187	45.95 195	43.33 175	60.88 88	46.79 201	36.97 210	32.24 199	24.15 214	11.79 205	29.26 204	32.97 210	46.64 115	65.09 148	62.95 151	71.45 152	60.42 183

DTE-MVSNet		48.03 175	53.28 162	41.91 181	54.64 136	57.50 164	44.63 198	51.66 48	41.02 177	7.97 216	46.26 133	40.90 189	20.24 202	60.45 166	62.89 152	72.33 146	63.97 168

pmmvs-eth3d		51.33 151	52.25 170	50.26 125	50.82 170	54.65 171	56.03 143	43.45 122	43.51 158	37.20 129	39.20 180	39.04 198	42.28 138	61.85 161	62.78 153	71.78 150	64.72 165

LTVRE_ROB	44.17 16	47.06 181	50.15 184	43.44 174	51.39 162	58.42 154	42.90 201	43.51 118	22.27 216	14.85 200	41.94 175	34.57 207	45.43 121	62.28 159	62.77 154	62.56 187	68.83 135
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
EPNet_dtu		52.05 146	58.26 129	44.81 168	54.10 143	50.09 188	52.01 166	40.82 147	53.03 86	27.41 166	54.90 82	57.96 99	26.72 192	62.97 153	62.70 155	67.78 168	66.19 154
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v148		55.58 121	57.61 137	53.20 105	54.59 140	61.86 123	61.18 108	38.70 165	44.30 151	42.25 100	47.53 122	50.24 132	48.73 103	65.15 147	62.61 156	73.79 120	71.61 112

TDRefinement		49.31 162	52.44 168	45.67 164	30.44 213	59.42 145	59.24 119	39.78 157	48.76 117	31.20 148	35.73 188	29.90 213	42.81 137	64.24 151	62.59 157	70.55 157	66.43 149

dmvs_re		52.07 145	55.11 150	48.54 144	57.27 120	51.93 181	57.73 129	43.13 128	43.65 155	26.57 173	44.52 151	50.00 133	36.53 169	66.58 129	62.15 158	69.97 160	66.91 146

CP-MVSNet		48.37 170	53.53 159	42.34 179	51.35 163	58.01 161	46.56 186	50.54 53	41.62 174	10.61 206	46.53 132	40.68 192	23.18 198	58.71 175	61.83 159	71.81 149	67.36 144

PS-CasMVS		48.18 172	53.25 163	42.27 180	51.26 164	57.94 162	46.51 187	50.52 54	41.30 175	10.56 207	45.35 147	40.34 194	23.04 199	58.66 176	61.79 160	71.74 151	67.38 142

IterMVS-SCA-FT		52.18 144	57.75 135	45.68 163	51.01 168	62.06 122	55.10 154	34.75 182	44.85 145	32.86 141	51.13 104	51.22 124	48.74 102	62.47 157	61.51 161	51.61 209	71.02 115

WR-MVS_H		47.65 176	53.67 158	40.63 186	51.45 161	59.74 144	44.71 197	49.37 58	40.69 179	7.61 217	46.04 137	44.34 180	17.32 205	57.79 181	61.18 162	73.30 130	65.86 157

USDC		51.11 152	53.71 157	48.08 151	44.76 192	55.99 169	53.01 165	40.90 145	52.49 90	36.14 131	44.67 150	33.66 209	43.27 134	63.23 152	61.10 163	70.39 159	64.82 164

SixPastTwentyTwo		47.55 178	50.25 183	44.41 171	47.30 184	54.31 173	47.81 180	40.36 154	33.76 202	19.93 191	43.75 158	32.77 211	42.07 139	59.82 168	60.94 164	68.98 162	66.37 151

IterMVS		53.45 136	57.12 139	49.17 133	49.23 176	60.93 135	59.05 121	34.63 184	44.53 147	33.22 137	51.09 105	51.01 127	48.38 106	62.43 158	60.79 165	70.54 158	69.05 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
baseline		55.19 127	60.88 93	48.55 143	49.87 174	58.10 160	58.70 122	34.75 182	52.82 89	39.48 119	60.18 61	60.86 83	45.41 122	61.05 163	60.74 166	63.10 183	72.41 109

CR-MVSNet		50.47 155	52.61 166	47.98 152	49.03 178	52.94 176	48.27 177	38.86 161	44.41 148	39.59 116	44.34 153	44.65 177	46.63 116	58.97 172	60.31 167	65.48 175	62.66 173

PatchT		48.08 173	51.03 178	44.64 169	42.96 197	50.12 187	40.36 206	35.09 180	43.17 160	39.59 116	42.00 174	39.96 195	46.63 116	58.97 172	60.31 167	63.21 182	62.66 173

CMPMVS	37.70 17	49.24 164	52.71 165	45.19 165	45.97 189	51.23 184	47.44 183	29.31 201	43.04 161	44.69 87	34.45 193	48.35 136	43.64 129	62.59 155	59.82 169	60.08 191	69.48 129
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PatchMatch-RL		50.11 160	51.56 174	48.43 145	46.23 188	51.94 180	50.21 171	38.62 166	46.62 135	37.51 126	42.43 173	39.38 196	52.24 88	60.98 164	59.56 170	65.76 174	60.01 186

TinyColmap		47.08 179	47.56 193	46.52 159	42.35 199	53.44 175	51.77 167	40.70 148	43.44 159	31.92 145	29.78 202	23.72 219	45.04 125	61.99 160	59.54 171	67.35 169	61.03 180

PMMVS		49.20 166	54.28 156	43.28 176	34.13 208	45.70 203	48.98 175	26.09 209	46.31 137	34.92 136	55.22 81	53.47 115	47.48 113	59.43 169	59.04 172	68.05 167	60.77 181

pmmvs5		47.07 180	51.02 179	42.46 178	45.18 191	51.47 183	48.23 179	33.09 195	38.17 195	28.62 162	46.60 129	43.48 182	30.74 183	58.28 178	58.63 173	68.92 163	60.48 182

CostFormer		56.57 111	59.13 121	53.60 101	57.52 111	61.12 131	66.94 72	35.95 178	53.44 80	44.68 88	55.87 79	54.44 112	48.21 107	60.37 167	58.33 174	68.27 166	70.33 121

ambc			45.54 199		50.66 172	52.63 179	40.99 205		38.36 193	24.67 179	22.62 212	13.94 222	29.14 188	65.71 142	58.06 175	58.60 195	67.43 140

TAMVS		44.02 190	49.18 187	37.99 194	47.03 185	45.97 202	45.04 194	28.47 204	39.11 189	20.23 190	43.22 166	48.52 135	28.49 190	58.15 179	57.95 176	58.71 193	51.36 199

SCA		50.99 154	53.22 164	48.40 146	51.07 166	56.78 167	50.25 170	39.05 158	48.31 123	41.38 104	49.54 108	46.70 155	46.00 119	58.31 177	56.28 177	62.65 185	56.60 193

dps		50.42 156	51.20 177	49.51 129	55.88 129	56.07 168	53.73 159	38.89 160	43.66 154	40.36 112	45.66 141	37.63 203	45.23 123	59.05 170	56.18 178	62.94 184	60.16 184

MDA-MVSNet-bldmvs		41.36 195	43.15 205	39.27 190	28.74 215	52.68 178	44.95 196	40.84 146	32.89 204	18.13 195	31.61 197	22.09 220	38.97 152	50.45 207	56.11 179	64.01 180	56.23 194

MIMVSNet		43.79 191	48.53 189	38.27 192	41.46 201	48.97 191	50.81 169	32.88 197	44.55 146	22.07 184	32.05 195	47.15 148	24.76 195	58.73 174	56.09 180	57.63 198	52.14 197

test-mter		45.30 186	50.37 180	39.38 189	33.65 210	46.99 198	47.59 181	18.59 215	38.75 190	28.00 163	43.28 165	46.82 154	41.50 142	57.28 183	55.78 181	66.93 173	63.70 170

CVMVSNet		46.38 184	52.01 172	39.81 188	42.40 198	50.26 186	46.15 188	37.68 171	40.03 184	15.09 199	46.56 130	47.56 144	33.72 179	56.50 189	55.65 182	63.80 181	67.53 139

MDTV_nov1_ep13_2view		47.62 177	49.72 186	45.18 166	48.05 180	53.70 174	54.90 155	33.80 190	39.90 185	29.79 155	38.85 181	41.89 185	39.17 149	58.99 171	55.55 183	65.34 177	59.17 187

test-LLR		49.28 163	50.29 181	48.10 150	55.26 133	47.16 196	49.52 172	43.48 120	39.22 187	31.98 143	43.65 160	47.93 139	41.29 143	56.80 185	55.36 184	67.08 171	61.94 177

TESTMET0.1,1		46.09 185	50.29 181	41.18 184	36.91 206	47.16 196	49.52 172	20.32 214	39.22 187	31.98 143	43.65 160	47.93 139	41.29 143	56.80 185	55.36 184	67.08 171	61.94 177

MDTV_nov1_ep13		50.32 158	52.43 169	47.86 154	49.87 174	54.70 170	58.10 126	34.29 186	45.59 143	37.71 125	47.44 123	47.42 146	41.86 140	58.07 180	55.21 186	65.34 177	58.56 189

FMVSNet5		40.96 196	45.81 197	35.29 201	34.30 207	44.55 206	47.28 184	28.84 203	40.76 178	21.62 185	29.85 201	42.44 183	24.77 194	57.53 182	55.00 187	54.93 201	50.56 202

FC-MVSNet-test		39.65 202	48.35 190	29.49 206	44.43 193	39.28 213	30.23 216	40.44 152	43.59 156	3.12 223	53.00 91	42.03 184	10.02 219	55.09 196	54.77 188	48.66 211	50.71 201

test20.03		40.38 201	44.20 201	35.92 199	53.73 146	49.05 189	38.54 208	43.49 119	32.55 205	9.54 211	27.88 206	39.12 197	12.24 211	56.28 190	54.69 189	57.96 197	49.83 207

Anonymous20231206		42.28 193	45.89 196	38.07 193	51.96 158	48.98 190	43.66 200	38.81 163	38.74 191	14.32 201	26.74 207	40.90 189	20.94 201	56.64 188	54.67 190	58.71 193	54.59 195

CHOSEN 280x420		40.80 197	45.05 200	35.84 200	32.95 211	29.57 216	44.98 195	23.71 212	37.54 197	18.42 194	31.36 198	47.07 149	46.41 118	56.71 187	54.65 191	48.55 212	58.47 190

test0.0.03 1		43.15 192	46.95 194	38.72 191	55.26 133	50.56 185	42.48 202	43.48 120	38.16 196	15.11 198	35.07 190	44.69 176	16.47 206	55.95 193	54.34 192	59.54 192	49.87 206

tpm cat1		53.30 137	53.41 160	53.17 107	58.16 104	59.15 149	63.73 100	38.27 168	50.73 98	46.98 74	45.57 143	44.00 181	49.20 101	55.90 194	54.02 193	62.65 185	64.50 167

RPMNet		46.41 182	48.72 188	43.72 172	47.77 182	52.94 176	46.02 190	33.92 188	44.41 148	31.82 146	36.89 185	37.42 204	37.41 161	53.88 200	54.02 193	65.37 176	61.47 179

MIMVSNet1		35.51 206	41.41 206	28.63 207	27.53 217	43.36 207	38.09 209	33.82 189	32.01 206	6.77 218	21.63 213	35.43 206	11.97 213	55.05 197	53.99 195	53.59 206	48.36 209

PatchmatchNet		49.92 161	51.29 175	48.32 148	51.83 160	51.86 182	53.38 164	37.63 172	47.90 126	40.83 109	48.54 115	45.30 166	45.19 124	56.86 184	53.99 195	61.08 190	54.57 196
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		44.55 189	48.13 191	40.37 187	32.85 212	46.82 200	46.11 189	29.28 202	40.48 180	29.99 154	39.98 179	34.39 208	41.80 141	56.08 192	53.88 197	62.19 188	65.31 160

testgi		38.71 203	43.64 203	32.95 203	52.30 157	48.63 192	35.59 213	35.05 181	31.58 209	9.03 214	30.29 199	40.75 191	11.19 217	55.30 195	53.47 198	54.53 204	45.48 210

RPSCF		46.41 182	54.42 154	37.06 196	25.70 220	45.14 204	45.39 193	20.81 213	62.79 58	35.10 133	44.92 149	55.60 110	43.56 130	56.12 191	52.45 199	51.80 208	63.91 169

pmmvs3		35.10 207	38.47 209	31.17 205	26.37 219	40.47 209	34.51 214	18.09 216	24.75 213	16.88 197	23.05 211	26.69 215	32.69 181	50.73 206	51.60 200	58.46 196	51.98 198

GG-mvs-BLEND		36.62 205	53.39 161	17.06 213	0.01 226	58.61 152	48.63 176	0.01 222	47.13 131	0.02 227	43.98 155	60.64 86	0.03 222	54.92 198	51.47 201	53.64 205	56.99 192

tpm		48.82 168	51.27 176	45.96 161	54.10 143	47.35 195	56.05 142	30.23 200	46.70 133	43.21 94	52.54 95	47.55 145	37.28 163	54.11 199	50.50 202	54.90 202	60.12 185

EU-MVSNet		40.63 199	45.65 198	34.78 202	39.11 204	46.94 199	40.02 207	34.03 187	33.50 203	10.37 208	35.57 189	37.80 202	23.65 197	51.90 202	50.21 203	61.49 189	63.62 171

tpmrst		48.08 173	49.88 185	45.98 160	52.71 151	48.11 193	53.62 162	33.70 191	48.70 119	39.74 114	48.96 113	46.23 159	40.29 147	50.14 208	49.28 204	55.80 199	57.71 191

Gipuma		25.87 211	26.91 214	24.66 210	28.98 214	20.17 219	20.46 218	34.62 185	29.55 210	9.10 212	4.91 222	5.31 226	15.76 208	49.37 211	49.10 205	39.03 215	29.95 215
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EPMVS		44.66 188	47.86 192	40.92 185	47.97 181	44.70 205	47.58 182	33.27 193	48.11 125	29.58 157	49.65 107	44.38 179	34.65 174	51.71 203	47.90 206	52.49 207	48.57 208

PMVS	27.84 18	33.81 208	35.28 212	32.09 204	34.13 208	24.81 218	32.51 215	26.48 208	26.41 212	19.37 192	23.76 210	24.02 218	25.18 193	50.78 204	47.24 207	54.89 203	49.95 205
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVS-HIRNet		42.24 194	41.15 207	43.51 173	44.06 196	40.74 208	35.77 212	35.35 179	35.38 200	38.34 121	25.63 209	38.55 200	43.48 131	50.77 205	47.03 208	64.07 179	49.98 204

FPMVS		38.36 204	40.41 208	35.97 198	38.92 205	39.85 211	45.50 192	25.79 210	41.13 176	18.70 193	30.10 200	24.56 217	31.86 182	49.42 210	46.80 209	55.04 200	51.03 200

pmnet_mix02		40.48 200	43.80 202	36.61 197	45.79 190	40.45 210	42.12 203	33.18 194	40.30 182	24.11 183	38.76 182	37.11 205	24.30 196	52.97 201	46.66 210	50.17 210	50.33 203

ADS-MVSNet		40.67 198	43.38 204	37.50 195	44.36 194	39.79 212	42.09 204	32.67 198	44.34 150	28.87 161	40.76 178	40.37 193	30.22 184	48.34 212	45.87 211	46.81 213	44.21 212

N_pmnet		32.67 210	36.85 211	27.79 209	40.55 202	32.13 215	35.80 211	26.79 207	37.24 198	9.10 212	32.02 196	30.94 212	16.30 207	47.22 213	41.21 212	38.21 216	37.21 213

new-patchmatchnet		33.24 209	37.20 210	28.62 208	44.32 195	38.26 214	29.68 217	36.05 177	31.97 207	6.33 219	26.59 208	27.33 214	11.12 218	50.08 209	41.05 213	44.23 214	45.15 211

new_pmnet		23.19 212	28.17 213	17.37 211	17.03 221	24.92 217	19.66 219	16.16 218	27.05 211	4.42 220	20.77 214	19.20 221	12.19 212	37.71 214	36.38 214	34.77 217	31.17 214

MVE	12.28 19	13.53 216	15.72 216	10.96 216	7.39 223	15.71 221	6.05 224	23.73 211	10.29 222	3.01 224	5.77 221	3.41 227	11.91 214	20.11 216	29.79 215	13.67 222	24.98 216
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMMVS2		15.84 213	19.68 215	11.35 215	15.74 222	16.95 220	13.31 220	17.64 217	16.08 218	0.36 226	13.12 216	11.47 223	1.69 221	28.82 215	27.24 216	19.38 221	24.09 217

E-PMN		15.09 214	13.19 218	17.30 212	27.80 216	12.62 222	7.81 223	27.54 205	14.62 220	3.19 221	6.89 219	2.52 229	15.09 209	15.93 218	20.22 217	22.38 218	19.53 218

EMVS		14.49 215	12.45 219	16.87 214	27.02 218	12.56 223	8.13 222	27.19 206	15.05 219	3.14 222	6.69 220	2.67 228	15.08 210	14.60 220	18.05 218	20.67 219	17.56 220

tmp_tt				5.40 218	3.97 224	2.35 226	3.26 226	0.44 221	17.56 217	12.09 203	11.48 218	7.14 224	1.98 220	15.68 219	15.49 219	10.69 223

test_method		12.44 217	14.66 217	9.85 217	1.30 225	3.32 225	13.00 221	3.21 219	22.42 215	10.22 209	14.13 215	25.64 216	11.43 216	19.75 217	11.61 220	19.96 220	5.79 221

testmvs		0.01 218	0.02 220	0.00 219	0.00 227	0.00 227	0.01 228	0.00 223	0.01 223	0.00 228	0.03 224	0.00 230	0.01 223	0.01 222	0.01 221	0.00 225	0.06 223

test123		0.01 218	0.02 220	0.00 219	0.00 227	0.00 227	0.00 229	0.00 223	0.01 223	0.00 228	0.04 223	0.00 230	0.01 223	0.00 223	0.01 221	0.00 225	0.07 222

uanet_test		0.00 220	0.00 222	0.00 219	0.00 227	0.00 227	0.00 229	0.00 223	0.00 225	0.00 228	0.00 225	0.00 230	0.00 225	0.00 223	0.00 223	0.00 225	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 219	0.00 227	0.00 227	0.00 229	0.00 223	0.00 225	0.00 228	0.00 225	0.00 230	0.00 225	0.00 223	0.00 223	0.00 225	0.00 224

sosnet		0.00 220	0.00 222	0.00 219	0.00 227	0.00 227	0.00 229	0.00 223	0.00 225	0.00 228	0.00 225	0.00 230	0.00 225	0.00 223	0.00 223	0.00 225	0.00 224

TPM-MVS					75.48 14	76.70 29	79.31 21			62.34 17	64.71 42	77.88 27	56.94 53			81.88 31	83.68 40

RE-MVS-def										33.01 138

9.14												81.81 13

SR-MVS					71.46 34			54.67 28				81.54 14

our_test_3					51.15 165	57.31 165	55.12 153

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 26

Patchmatch-RL test							1.04 227

XVS					70.49 38	76.96 25	74.36 45			54.48 48		74.47 38				82.24 24

X-MVStestdata					70.49 38	76.96 25	74.36 45			54.48 48		74.47 38				82.24 24

mPP-MVS					71.67 33							74.36 41

NP-MVS									72.00 39

Patchmtry						47.61 194	48.27 177	38.86 161		39.59 116

DeepMVS_CX						6.95 224	5.98 225	2.25 220	11.73 221	2.07 225	11.85 217	5.43 225	11.75 215	11.40 221		8.10 224	18.38 219

High-resolution multi-view benchmark