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.

DPE-MVS		88.63 4	91.29 4	85.53 3	90.87 8	92.20 4	91.98 2	76.00 6	90.55 8	82.09 6	93.85 1	90.75 2	81.25 1	88.62 8	87.59 14	90.96 9	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 4	91.18 1	81.17 2	89.55 2	87.93 8	91.01 7	96.21 1

SED-MVS		88.85 2	91.59 3	85.67 2	90.54 15	92.29 3	91.71 3	76.40 2	92.41 3	83.24 2	92.50 3	90.64 4	81.10 3	89.53 3	88.02 7	91.00 8	95.73 3

MSP-MVS		88.09 5	90.84 5	84.88 7	90.00 23	91.80 6	91.63 5	75.80 7	91.99 4	81.23 8	92.54 2	89.18 6	80.89 4	87.99 15	87.91 9	89.70 45	94.51 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
APDe-MVS		88.00 6	90.50 6	85.08 5	90.95 7	91.58 7	92.03 1	75.53 12	91.15 5	80.10 14	92.27 5	88.34 11	80.80 5	88.00 14	86.99 18	91.09 5	95.16 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 16	92.36 2	90.69 9	76.15 4	93.08 2	82.75 4	92.19 6	90.71 3	80.45 6	89.27 6	87.91 9	90.82 11	95.84 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
APD-MVS		86.84 12	88.91 14	84.41 10	90.66 11	90.10 12	90.78 7	75.64 9	87.38 16	78.72 18	90.68 10	86.82 17	80.15 7	87.13 24	86.45 28	90.51 21	93.83 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		86.88 11	89.23 10	84.14 12	89.78 26	88.67 30	90.59 10	73.46 26	88.99 11	80.52 12	91.26 7	88.65 9	79.91 8	86.96 29	86.22 31	90.59 19	93.83 14
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		87.09 9	88.92 13	84.95 6	92.61 1	87.91 40	90.23 15	76.06 5	88.85 12	81.20 9	87.33 13	87.93 12	79.47 9	88.59 9	88.23 5	90.15 34	93.60 20

SF-MVS		87.47 8	89.70 8	84.86 8	91.26 6	91.10 8	90.90 6	75.65 8	89.21 9	81.25 7	91.12 8	88.93 7	78.82 10	87.42 19	86.23 30	91.28 3	93.90 13

CNVR-MVS		86.36 14	88.19 17	84.23 11	91.33 5	89.84 14	90.34 11	75.56 10	87.36 17	78.97 17	81.19 28	86.76 18	78.74 11	89.30 5	88.58 2	90.45 27	94.33 10

SD-MVS		86.96 10	89.45 9	84.05 14	90.13 19	89.23 22	89.77 18	74.59 14	89.17 10	80.70 10	89.93 11	89.67 5	78.47 12	87.57 18	86.79 22	90.67 17	93.76 16
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
MCST-MVS		85.13 22	86.62 23	83.39 17	90.55 14	89.82 16	89.29 21	73.89 22	84.38 30	76.03 29	79.01 31	85.90 21	78.47 12	87.81 16	86.11 33	92.11 1	93.29 22

HFP-MVS		86.15 15	87.95 18	84.06 13	90.80 9	89.20 23	89.62 19	74.26 16	87.52 14	80.63 11	86.82 16	84.19 28	78.22 14	87.58 17	87.19 16	90.81 12	93.13 24

SMA-MVS		87.56 7	90.17 7	84.52 9	91.71 3	90.57 9	90.77 8	75.19 13	90.67 7	80.50 13	86.59 17	88.86 8	78.09 15	89.92 1	89.41 1	90.84 10	95.19 5
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
NCCC		85.34 19	86.59 24	83.88 15	91.48 4	88.88 25	89.79 17	75.54 11	86.67 20	77.94 22	76.55 34	84.99 25	78.07 16	88.04 12	87.68 12	90.46 26	93.31 21

TSAR-MVS + GP.		83.69 29	86.58 25	80.32 35	85.14 54	86.96 44	84.91 50	70.25 41	84.71 28	73.91 36	85.16 21	85.63 22	77.92 17	85.44 42	85.71 36	89.77 41	92.45 26

MSLP-MVS++		82.09 36	82.66 40	81.42 29	87.03 43	87.22 43	85.82 42	70.04 42	80.30 44	78.66 19	68.67 72	81.04 44	77.81 18	85.19 46	84.88 43	89.19 56	91.31 36

ACMMPR		85.52 17	87.53 20	83.17 21	90.13 19	89.27 20	89.30 20	73.97 20	86.89 19	77.14 24	86.09 18	83.18 32	77.74 19	87.42 19	87.20 15	90.77 13	92.63 25

DeepC-MVS_fast	78.24 3	84.27 28	85.50 30	82.85 22	90.46 17	89.24 21	87.83 33	74.24 17	84.88 25	76.23 28	75.26 39	81.05 43	77.62 20	88.02 13	87.62 13	90.69 16	92.41 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS	78.47 2	84.81 25	86.03 28	83.37 18	89.29 32	90.38 11	88.61 26	76.50 1	86.25 22	77.22 23	75.12 40	80.28 45	77.59 21	88.39 10	88.17 6	91.02 6	93.66 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	79.04 1	85.30 20	88.93 12	81.06 31	88.77 36	90.48 10	85.46 46	73.08 28	90.97 6	73.77 37	84.81 22	85.95 20	77.43 22	88.22 11	87.73 11	87.85 86	94.34 9

MP-MVS		85.50 18	87.40 21	83.28 19	90.65 12	89.51 19	89.16 23	74.11 18	83.70 33	78.06 21	85.54 20	84.89 27	77.31 23	87.40 21	87.14 17	90.41 28	93.65 19
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
SteuartSystems-ACMMP		85.99 16	88.31 16	83.27 20	90.73 10	89.84 14	90.27 14	74.31 15	84.56 29	75.88 30	87.32 14	85.04 24	77.31 23	89.01 7	88.46 3	91.14 4	93.96 12
Skip Steuart: Steuart Systems R&D Blog.
CP-MVS		84.74 26	86.43 26	82.77 23	89.48 30	88.13 39	88.64 25	73.93 21	84.92 24	76.77 26	81.94 26	83.50 30	77.29 25	86.92 30	86.49 27	90.49 22	93.14 23

3Dnovator+	75.73 4	82.40 34	82.76 39	81.97 28	88.02 38	89.67 17	86.60 37	71.48 36	81.28 43	78.18 20	64.78 87	77.96 52	77.13 26	87.32 22	86.83 21	90.41 28	91.48 35

PGM-MVS		84.42 27	86.29 27	82.23 25	90.04 22	88.82 26	89.23 22	71.74 35	82.82 38	74.61 33	84.41 23	82.09 35	77.03 27	87.13 24	86.73 24	90.73 15	92.06 31

ACMMP_NAP		86.52 13	89.01 11	83.62 16	90.28 18	90.09 13	90.32 13	74.05 19	88.32 13	79.74 15	87.04 15	85.59 23	76.97 28	89.35 4	88.44 4	90.35 30	94.27 11

AdaColmap		79.74 46	78.62 64	81.05 32	89.23 33	86.06 52	84.95 49	71.96 33	79.39 48	75.51 31	63.16 93	68.84 97	76.51 29	83.55 61	82.85 59	88.13 76	86.46 78

CS-MVS		79.22 51	81.11 50	77.01 54	81.36 77	84.03 67	80.35 67	63.25 96	73.43 66	70.37 53	74.10 46	76.03 59	76.40 30	86.32 37	83.95 50	90.34 31	89.93 49

CPTT-MVS		81.77 37	83.10 38	80.21 36	85.93 50	86.45 49	87.72 34	70.98 38	82.54 40	71.53 48	74.23 45	81.49 40	76.31 31	82.85 71	81.87 67	88.79 65	92.26 29

EC-MVSNet		79.44 48	81.35 47	77.22 52	82.95 63	84.67 63	81.31 60	63.65 92	72.47 69	68.75 57	73.15 47	78.33 49	75.99 32	86.06 40	83.96 49	90.67 17	90.79 41

train_agg		84.86 24	87.21 22	82.11 26	90.59 13	85.47 55	89.81 16	73.55 25	83.95 31	73.30 38	89.84 12	87.23 15	75.61 33	86.47 33	85.46 38	89.78 40	92.06 31

ACMMP		83.42 30	85.27 31	81.26 30	88.47 37	88.49 33	88.31 31	72.09 32	83.42 34	72.77 40	82.65 24	78.22 50	75.18 34	86.24 38	85.76 35	90.74 14	92.13 30
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
CS-MVS-test		78.79 58	80.72 52	76.53 57	81.11 82	83.88 70	79.69 76	63.72 91	73.80 63	69.95 55	75.40 38	76.17 56	74.85 35	84.50 53	82.78 60	89.87 39	88.54 60

TSAR-MVS + ACMM		85.10 23	88.81 15	80.77 34	89.55 29	88.53 32	88.59 27	72.55 30	87.39 15	71.90 42	90.95 9	87.55 13	74.57 36	87.08 26	86.54 26	87.47 93	93.67 17

CNLPA		77.20 65	77.54 70	76.80 56	82.63 65	84.31 66	79.77 73	64.64 81	85.17 23	73.18 39	56.37 131	69.81 88	74.53 37	81.12 92	78.69 117	86.04 133	87.29 70

MVS_0304		81.73 38	83.86 35	79.26 41	86.22 49	89.18 24	86.41 38	67.15 64	75.28 55	70.75 52	74.59 42	83.49 31	74.42 38	87.05 27	86.34 29	90.58 20	91.08 39

OPM-MVS		79.68 47	79.28 62	80.15 37	87.99 39	86.77 46	88.52 28	72.72 29	64.55 100	67.65 63	67.87 76	74.33 67	74.31 39	86.37 35	85.25 40	89.73 44	89.81 51
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
3Dnovator	73.76 5	79.75 45	80.52 55	78.84 43	84.94 59	87.35 41	84.43 52	65.54 75	78.29 49	73.97 35	63.00 95	75.62 62	74.07 40	85.00 47	85.34 39	90.11 35	89.04 56

CSCG		85.28 21	87.68 19	82.49 24	89.95 24	91.99 5	88.82 24	71.20 37	86.41 21	79.63 16	79.26 29	88.36 10	73.94 41	86.64 31	86.67 25	91.40 2	94.41 8

PLC	68.99 11	75.68 72	75.31 84	76.12 60	82.94 64	81.26 96	79.94 71	66.10 70	77.15 52	66.86 69	59.13 114	68.53 99	73.73 42	80.38 102	79.04 112	87.13 101	81.68 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ACMM	72.26 8	78.86 57	78.13 66	79.71 39	86.89 44	83.40 77	86.02 40	70.50 39	75.28 55	71.49 49	63.01 94	69.26 91	73.57 43	84.11 56	83.98 48	89.76 42	87.84 65
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETV-MVS		77.32 64	78.81 63	75.58 62	82.24 71	83.64 75	79.98 69	64.02 88	69.64 76	63.90 79	70.89 60	69.94 87	73.41 44	85.39 45	83.91 51	89.92 37	88.31 61

OMC-MVS		80.26 41	82.59 41	77.54 50	83.04 62	85.54 54	83.25 56	65.05 79	87.32 18	72.42 41	72.04 54	78.97 47	73.30 45	83.86 57	81.60 71	88.15 75	88.83 58

MVS_111021_HR		80.13 42	81.46 46	78.58 45	85.77 51	85.17 59	83.45 55	69.28 49	74.08 62	70.31 54	74.31 44	75.26 63	73.13 46	86.46 34	85.15 41	89.53 47	89.81 51

PHI-MVS		82.36 35	85.89 29	78.24 47	86.40 47	89.52 18	85.52 44	69.52 48	82.38 41	65.67 71	81.35 27	82.36 34	73.07 47	87.31 23	86.76 23	89.24 52	91.56 34

DPM-MVS		83.30 31	84.33 34	82.11 26	89.56 28	88.49 33	90.33 12	73.24 27	83.85 32	76.46 27	72.43 52	82.65 33	73.02 48	86.37 35	86.91 19	90.03 36	89.62 53

CANet		81.62 39	83.41 36	79.53 40	87.06 42	88.59 31	85.47 45	67.96 57	76.59 53	74.05 34	74.69 41	81.98 36	72.98 49	86.14 39	85.47 37	89.68 46	90.42 46

QAPM		78.47 59	80.22 58	76.43 58	85.03 56	86.75 47	80.62 66	66.00 72	73.77 64	65.35 73	65.54 83	78.02 51	72.69 50	83.71 59	83.36 56	88.87 62	90.41 47

MVS_111021_LR		78.13 61	79.85 60	76.13 59	81.12 81	81.50 92	80.28 68	65.25 77	76.09 54	71.32 50	76.49 35	72.87 73	72.21 51	82.79 72	81.29 73	86.59 119	87.91 64

MAR-MVS		79.21 52	80.32 57	77.92 49	87.46 40	88.15 38	83.95 53	67.48 63	74.28 59	68.25 59	64.70 88	77.04 53	72.17 52	85.42 43	85.00 42	88.22 72	87.62 67
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
ET-MVSNet_ETH3D		72.46 90	74.19 89	70.44 94	62.50 202	81.17 97	79.90 72	62.46 118	64.52 101	57.52 102	71.49 58	59.15 132	72.08 53	78.61 128	81.11 75	88.16 74	83.29 115

ACMP	73.23 7	79.79 44	80.53 54	78.94 42	85.61 52	85.68 53	85.61 43	69.59 46	77.33 51	71.00 51	74.45 43	69.16 92	71.88 54	83.15 67	83.37 55	89.92 37	90.57 45
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	71.42 9	77.69 63	80.05 59	74.94 67	80.68 86	84.52 65	81.36 59	63.14 100	84.77 26	64.82 76	68.72 70	75.91 60	71.86 55	81.62 78	79.55 106	87.80 88	85.24 92
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDPH-MVS		82.64 33	85.03 33	79.86 38	89.41 31	88.31 36	88.32 30	71.84 34	80.11 45	67.47 64	82.09 25	81.44 41	71.85 56	85.89 41	86.15 32	90.24 32	91.25 37

PCF-MVS	73.28 6	79.42 49	80.41 56	78.26 46	84.88 60	88.17 37	86.08 39	69.85 43	75.23 57	68.43 58	68.03 75	78.38 48	71.76 57	81.26 89	80.65 89	88.56 68	91.18 38
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
X-MVS		83.23 32	85.20 32	80.92 33	89.71 27	88.68 27	88.21 32	73.60 23	82.57 39	71.81 45	77.07 32	81.92 37	71.72 58	86.98 28	86.86 20	90.47 23	92.36 28

HQP-MVS		81.19 40	83.27 37	78.76 44	87.40 41	85.45 56	86.95 35	70.47 40	81.31 42	66.91 68	79.24 30	76.63 54	71.67 59	84.43 54	83.78 52	89.19 56	92.05 33

EIA-MVS		75.64 73	76.60 80	74.53 72	82.43 68	83.84 71	78.32 91	62.28 120	65.96 90	63.28 83	68.95 68	67.54 102	71.61 60	82.55 73	81.63 70	89.24 52	85.72 83

TSAR-MVS + COLMAP		78.34 60	81.64 45	74.48 73	80.13 94	85.01 60	81.73 58	65.93 74	84.75 27	61.68 85	85.79 19	66.27 107	71.39 61	82.91 70	80.78 80	86.01 134	85.98 80

LGP-MVS_train		79.83 43	81.22 49	78.22 48	86.28 48	85.36 58	86.76 36	69.59 46	77.34 50	65.14 74	75.68 36	70.79 81	71.37 62	84.60 50	84.01 47	90.18 33	90.74 42

TPM-MVS					90.07 21	88.36 35	88.45 29			77.10 25	75.60 37	83.98 29	71.33 63			89.75 43	89.62 53
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
Fast-Effi-MVS+		73.11 86	73.66 92	72.48 80	77.72 112	80.88 102	78.55 88	58.83 159	65.19 94	60.36 88	59.98 108	62.42 119	71.22 64	81.66 77	80.61 91	88.20 73	84.88 100

LS3D		74.08 80	73.39 95	74.88 68	85.05 55	82.62 86	79.71 75	68.66 52	72.82 67	58.80 93	57.61 125	61.31 122	71.07 65	80.32 103	78.87 116	86.00 135	80.18 144

Effi-MVS+		75.28 75	76.20 81	74.20 74	81.15 80	83.24 80	81.11 61	63.13 101	66.37 86	60.27 89	64.30 91	68.88 96	70.93 66	81.56 80	81.69 69	88.61 66	87.35 68

OpenMVS	70.44 10	76.15 71	76.82 79	75.37 65	85.01 57	84.79 61	78.99 84	62.07 122	71.27 70	67.88 62	57.91 124	72.36 74	70.15 67	82.23 76	81.41 72	88.12 77	87.78 66

DELS-MVS		79.15 55	81.07 51	76.91 55	83.54 61	87.31 42	84.45 51	64.92 80	69.98 71	69.34 56	71.62 56	76.26 55	69.84 68	86.57 32	85.90 34	89.39 49	89.88 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
sasdasda		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 63	63.18 98	82.90 36	67.34 65	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

canonicalmvs		79.16 53	82.37 42	75.41 63	82.33 69	86.38 50	80.80 63	63.18 98	82.90 36	67.34 65	72.79 49	76.07 57	69.62 69	83.46 64	84.41 45	89.20 54	90.60 43

PatchMatch-RL		67.78 139	66.65 159	69.10 111	73.01 154	72.69 171	68.49 167	61.85 125	62.93 114	60.20 90	56.83 130	50.42 189	69.52 71	75.62 154	74.46 164	81.51 169	73.62 186

casdiffmvs		76.76 66	78.46 65	74.77 69	80.32 91	83.73 74	80.65 65	63.24 97	73.58 65	66.11 70	69.39 67	74.09 68	69.49 72	82.52 74	79.35 111	88.84 64	86.52 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
DI_MVS_plusplus_trai		75.13 76	76.12 82	73.96 75	78.18 106	81.55 90	80.97 62	62.54 115	68.59 77	65.13 75	61.43 98	74.81 64	69.32 73	81.01 94	79.59 104	87.64 91	85.89 81

casdiffmvs_mvg		77.79 62	79.55 61	75.73 61	81.56 74	84.70 62	82.12 57	64.26 87	74.27 60	67.93 61	70.83 61	74.66 65	69.19 74	83.33 66	81.94 66	89.29 51	87.14 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
MVS_Test		75.37 74	77.13 77	73.31 78	79.07 100	81.32 95	79.98 69	60.12 144	69.72 74	64.11 78	70.53 62	73.22 70	68.90 75	80.14 109	79.48 108	87.67 90	85.50 87

Effi-MVS+-dtu		71.82 94	71.86 109	71.78 83	78.77 101	80.47 105	78.55 88	61.67 129	60.68 130	55.49 111	58.48 118	65.48 109	68.85 76	76.92 145	75.55 157	87.35 95	85.46 88

ACMH	65.37 14	70.71 105	70.00 120	71.54 84	82.51 67	82.47 87	77.78 95	68.13 54	56.19 159	46.06 169	54.30 143	51.20 185	68.68 77	80.66 98	80.72 82	86.07 129	84.45 106
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	66.54 13	71.36 101	70.09 119	72.85 79	82.59 66	81.13 98	78.56 87	68.04 55	61.55 124	52.52 133	51.50 173	54.14 158	68.56 78	78.85 125	79.50 107	86.82 109	83.94 109

CLD-MVS		79.35 50	81.23 48	77.16 53	85.01 57	86.92 45	85.87 41	60.89 133	80.07 47	75.35 32	72.96 48	73.21 71	68.43 79	85.41 44	84.63 44	87.41 94	85.44 89
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		74.23 79	74.84 87	73.52 76	80.42 90	81.46 93	79.77 73	61.06 131	67.23 83	63.67 80	59.56 111	68.74 98	67.90 80	80.25 107	79.37 110	88.31 69	87.26 71

HyFIR lowres test		69.47 120	68.94 134	70.09 100	76.77 120	82.93 84	76.63 107	60.17 142	59.00 139	54.03 119	40.54 204	65.23 110	67.89 81	76.54 151	78.30 122	85.03 151	80.07 145

FA-MVS(training)		73.66 82	74.95 86	72.15 81	78.63 104	80.46 106	78.92 85	54.79 173	69.71 75	65.37 72	62.04 96	66.89 105	67.10 82	80.72 96	79.87 99	88.10 79	84.97 97

PVSNet_Blended_VisFu		76.57 67	77.90 67	75.02 66	80.56 87	86.58 48	79.24 80	66.18 69	64.81 97	68.18 60	65.61 81	71.45 76	67.05 83	84.16 55	81.80 68	88.90 60	90.92 40

PVSNet_BlendedMVS		76.21 69	77.52 71	74.69 70	79.46 97	83.79 72	77.50 98	64.34 85	69.88 72	71.88 43	68.54 73	70.42 83	67.05 83	83.48 62	79.63 102	87.89 84	86.87 74

PVSNet_Blended		76.21 69	77.52 71	74.69 70	79.46 97	83.79 72	77.50 98	64.34 85	69.88 72	71.88 43	68.54 73	70.42 83	67.05 83	83.48 62	79.63 102	87.89 84	86.87 74

v10		70.22 111	69.76 124	70.74 87	74.79 137	80.30 110	79.22 81	59.81 147	57.71 147	56.58 108	54.22 149	55.31 151	66.95 86	78.28 131	77.47 135	87.12 103	85.07 95

v1192		69.50 119	68.83 135	70.29 96	74.49 140	80.92 101	78.55 88	60.54 137	55.04 167	54.21 116	52.79 165	52.33 178	66.92 87	77.88 135	77.35 139	87.04 104	85.51 86

CHOSEN 1792x2688		69.20 123	69.26 130	69.13 110	76.86 119	78.93 119	77.27 101	60.12 144	61.86 122	54.42 115	42.54 198	61.61 121	66.91 88	78.55 129	78.14 124	79.23 179	83.23 116

v1921920		69.03 124	68.32 143	69.86 102	74.03 145	80.37 107	77.55 96	60.25 141	54.62 171	53.59 124	52.36 169	51.50 184	66.75 89	77.17 142	76.69 148	86.96 105	85.56 85

v144192		69.34 121	68.68 139	70.12 99	74.06 144	80.54 104	78.08 94	60.54 137	54.99 169	54.13 118	52.92 163	52.80 176	66.73 90	77.13 143	76.72 146	87.15 97	85.63 84

v1240		68.64 129	67.89 149	69.51 107	73.89 147	80.26 111	76.73 106	59.97 146	53.43 179	53.08 128	51.82 172	50.84 187	66.62 91	76.79 147	76.77 145	86.78 111	85.34 90

v1144		69.93 115	69.36 129	70.61 91	74.89 136	80.93 99	79.11 82	60.64 135	55.97 161	55.31 113	53.85 151	54.14 158	66.54 92	78.10 133	77.44 136	87.14 100	85.09 94

diffmvs		74.86 77	77.37 74	71.93 82	75.62 129	80.35 108	79.42 79	60.15 143	72.81 68	64.63 77	71.51 57	73.11 72	66.53 93	79.02 123	77.98 125	85.25 148	86.83 76
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v2v482		70.05 114	69.46 128	70.74 87	74.62 139	80.32 109	79.00 83	60.62 136	57.41 149	56.89 105	55.43 138	55.14 153	66.39 94	77.25 141	77.14 141	86.90 106	83.57 114

v8		70.23 110	69.86 122	70.67 90	74.69 138	79.82 112	78.79 86	59.18 152	58.80 140	58.20 99	55.00 140	57.33 140	66.31 95	77.51 138	76.71 147	86.82 109	83.88 110

IterMVS-LS		71.69 96	72.82 102	70.37 95	77.54 114	76.34 150	75.13 118	60.46 139	61.53 125	57.57 101	64.89 86	67.33 103	66.04 96	77.09 144	77.37 138	85.48 144	85.18 93
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		71.52 98	69.87 121	73.44 77	82.21 72	79.35 116	79.52 77	64.59 82	66.15 88	61.87 84	53.21 158	56.09 148	65.85 97	78.94 124	78.50 119	86.60 118	76.85 167

V42		68.76 128	69.63 125	67.74 123	64.93 198	78.01 129	78.30 92	56.48 169	58.65 141	56.30 109	54.26 147	57.03 143	64.85 98	77.47 139	77.01 143	85.60 142	84.96 98

EPNet		79.08 56	80.62 53	77.28 51	88.90 35	83.17 82	83.65 54	72.41 31	74.41 58	67.15 67	76.78 33	74.37 66	64.43 99	83.70 60	83.69 53	87.15 97	88.19 62
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
thisisatest0530		71.48 99	73.01 98	69.70 105	73.83 148	78.62 125	74.53 126	59.12 153	64.13 103	58.63 95	64.60 89	58.63 134	64.27 100	80.28 105	80.17 97	87.82 87	84.64 103

tttt0517		71.41 100	72.95 99	69.60 106	73.70 150	78.70 124	74.42 130	59.12 153	63.89 107	58.35 98	64.56 90	58.39 136	64.27 100	80.29 104	80.17 97	87.74 89	84.69 102

RPSCF		67.64 143	71.25 111	63.43 164	61.86 204	70.73 178	67.26 172	50.86 192	74.20 61	58.91 92	67.49 77	69.33 90	64.10 102	71.41 178	68.45 192	77.61 183	77.17 164

LTVRE_ROB	59.44 16	61.82 184	62.64 186	60.87 173	72.83 159	77.19 142	64.37 189	58.97 155	33.56 218	28.00 205	52.59 168	42.21 210	63.93 103	74.52 160	76.28 151	77.15 186	82.13 120
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
MVSTER		72.06 92	74.24 88	69.51 107	70.39 178	75.97 153	76.91 104	57.36 167	64.64 99	61.39 87	68.86 69	63.76 114	63.46 104	81.44 82	79.70 101	87.56 92	85.31 91

PMMVS		65.06 159	69.17 132	60.26 176	55.25 217	63.43 203	66.71 178	43.01 212	62.41 117	50.64 141	69.44 66	67.04 104	63.29 105	74.36 162	73.54 168	82.68 166	73.99 185

IterMVS-SCA-FT		66.89 152	69.22 131	64.17 157	71.30 173	75.64 155	71.33 156	53.17 179	57.63 148	49.08 151	60.72 102	60.05 128	63.09 106	74.99 158	73.92 165	77.07 187	81.57 130

EPP-MVSNet		74.00 81	77.41 73	70.02 101	80.53 88	83.91 69	74.99 121	62.68 113	65.06 95	49.77 147	68.68 71	72.09 75	63.06 107	82.49 75	80.73 81	89.12 58	88.91 57

CHOSEN 280x420		58.70 193	61.88 192	54.98 196	55.45 216	50.55 219	64.92 186	40.36 213	55.21 164	38.13 192	48.31 185	63.76 114	63.03 108	73.73 166	68.58 190	68.00 214	73.04 187

TinyColmap		62.84 170	61.03 195	64.96 153	69.61 183	71.69 174	68.48 168	59.76 148	55.41 163	47.69 159	47.33 188	34.20 218	62.76 109	74.52 160	72.59 173	81.44 170	71.47 189

Fast-Effi-MVS+-dtu		68.34 130	69.47 127	67.01 139	75.15 132	77.97 135	77.12 102	55.40 172	57.87 142	46.68 164	56.17 132	60.39 124	62.36 110	76.32 152	76.25 153	85.35 147	81.34 131

Anonymous20231211		71.90 93	72.48 104	71.21 85	80.14 93	81.53 91	76.92 103	62.89 104	64.46 102	58.94 91	43.80 194	70.98 80	62.22 111	80.70 97	80.19 96	86.18 126	85.73 82

DCV-MVSNet		73.65 83	75.78 83	71.16 86	80.19 92	79.27 117	77.45 100	61.68 128	66.73 85	58.72 94	65.31 84	69.96 86	62.19 112	81.29 88	80.97 77	86.74 112	86.91 73

USDC		67.36 147	67.90 148	66.74 144	71.72 165	75.23 161	71.58 155	60.28 140	67.45 82	50.54 143	60.93 100	45.20 206	62.08 113	76.56 150	74.50 163	84.25 157	75.38 177

Anonymous202405211			72.16 107		80.85 85	81.85 89	76.88 105	65.40 76	62.89 115		46.35 190	67.99 101	62.05 114	81.15 91	80.38 93	85.97 136	84.50 104

MS-PatchMatch		70.17 112	70.49 116	69.79 103	80.98 84	77.97 135	77.51 97	58.95 156	62.33 118	55.22 114	53.14 159	65.90 108	62.03 115	79.08 122	77.11 142	84.08 159	77.91 159

baseline2		69.69 116	70.27 118	69.01 112	75.72 128	77.13 143	73.82 141	58.94 157	61.35 126	57.09 104	61.68 97	57.17 142	61.99 116	78.10 133	76.58 149	86.48 122	79.85 146

v148		67.85 137	67.53 150	68.23 118	73.25 153	77.57 141	74.26 134	57.36 167	55.70 162	57.45 103	53.53 152	55.42 150	61.96 117	75.23 156	73.92 165	85.08 150	81.32 132

pmmvs4		67.89 136	67.39 154	68.48 117	71.60 169	73.57 168	74.45 127	60.98 132	64.65 98	57.97 100	54.95 141	51.73 183	61.88 118	73.78 165	75.11 159	83.99 161	77.91 159

CostFormer		68.92 125	69.58 126	68.15 119	75.98 125	76.17 152	78.22 93	51.86 187	65.80 91	61.56 86	63.57 92	62.83 117	61.85 119	70.40 191	68.67 188	79.42 177	79.62 150

tpm cat1		65.41 156	63.81 179	67.28 134	75.61 130	72.88 170	75.32 112	52.85 181	62.97 113	63.66 81	53.24 157	53.29 173	61.83 120	65.54 202	64.14 204	74.43 199	74.60 180

CANet_DTU		73.29 85	76.96 78	69.00 113	77.04 118	82.06 88	79.49 78	56.30 170	67.85 81	53.29 127	71.12 59	70.37 85	61.81 121	81.59 79	80.96 78	86.09 128	84.73 101

MGCFI-Net		76.55 68	81.71 44	70.52 93	81.71 73	84.62 64	75.02 120	62.17 121	82.91 35	53.58 125	72.78 51	75.87 61	61.75 122	82.96 69	82.61 62	88.86 63	90.26 48

baseline		70.45 108	74.09 90	66.20 147	70.95 175	75.67 154	74.26 134	53.57 175	68.33 78	58.42 96	69.87 65	71.45 76	61.55 123	74.84 159	74.76 162	78.42 181	83.72 112

SCA		65.40 157	66.58 160	64.02 159	70.65 176	73.37 169	67.35 171	53.46 177	63.66 108	54.14 117	60.84 101	60.20 127	61.50 124	69.96 192	68.14 193	77.01 188	69.91 192

GA-MVS		68.14 131	69.17 132	66.93 141	73.77 149	78.50 127	74.45 127	58.28 161	55.11 166	48.44 153	60.08 106	53.99 161	61.50 124	78.43 130	77.57 132	85.13 149	80.54 139

anonymousdsp		65.28 158	67.98 146	62.13 167	58.73 211	73.98 167	67.10 174	50.69 194	48.41 197	47.66 160	54.27 145	52.75 177	61.45 126	76.71 149	80.20 95	87.13 101	89.53 55

v7n		67.05 151	66.94 156	67.17 135	72.35 160	78.97 118	73.26 150	58.88 158	51.16 190	50.90 140	48.21 186	50.11 191	60.96 127	77.70 136	77.38 137	86.68 116	85.05 96

CR-MVSNet		64.83 160	65.54 165	64.01 160	70.64 177	69.41 182	65.97 182	52.74 182	57.81 144	52.65 130	54.27 145	56.31 147	60.92 128	72.20 174	73.09 170	81.12 172	75.69 174

PatchT		61.97 180	64.04 177	59.55 181	60.49 206	67.40 190	56.54 207	48.65 202	56.69 153	52.65 130	51.10 176	52.14 181	60.92 128	72.20 174	73.09 170	78.03 182	75.69 174

dps		64.00 166	62.99 182	65.18 150	73.29 152	72.07 173	68.98 166	53.07 180	57.74 146	58.41 97	55.55 136	47.74 199	60.89 130	69.53 194	67.14 197	76.44 191	71.19 190

IterMVS		66.36 153	68.30 144	64.10 158	69.48 185	74.61 165	73.41 148	50.79 193	57.30 150	48.28 155	60.64 103	59.92 129	60.85 131	74.14 163	72.66 172	81.80 168	78.82 155
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TDRefinement		66.09 154	65.03 171	67.31 132	69.73 182	76.75 146	75.33 111	64.55 83	60.28 134	49.72 148	45.63 192	42.83 209	60.46 132	75.75 153	75.95 154	84.08 159	78.04 158

PatchmatchNet		64.21 165	64.65 173	63.69 161	71.29 174	68.66 186	69.63 162	51.70 189	63.04 112	53.77 122	59.83 110	58.34 137	60.23 133	68.54 198	66.06 200	75.56 194	68.08 198
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
gm-plane-assit		57.00 196	57.62 203	56.28 192	76.10 122	62.43 209	47.62 217	46.57 208	33.84 217	23.24 211	37.52 205	40.19 214	59.61 134	79.81 111	77.55 133	84.55 156	72.03 188

IB-MVS	66.94 12	71.21 102	71.66 110	70.68 89	79.18 99	82.83 85	72.61 151	61.77 126	59.66 136	63.44 82	53.26 156	59.65 130	59.16 135	76.78 148	82.11 65	87.90 83	87.33 69
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
test2506		71.72 95	72.95 99	70.29 96	81.49 75	83.27 78	75.74 109	67.59 61	68.19 79	49.81 146	61.15 99	49.73 193	58.82 136	84.76 48	82.94 57	88.27 70	80.63 138

ECVR-MVS		72.20 91	73.91 91	70.20 98	81.49 75	83.27 78	75.74 109	67.59 61	68.19 79	49.31 150	55.77 133	62.00 120	58.82 136	84.76 48	82.94 57	88.27 70	80.41 142

UniMVSNet_NR-MVSNet		70.59 106	72.19 105	68.72 114	77.72 112	80.72 103	73.81 142	69.65 45	61.99 120	43.23 179	60.54 104	57.50 139	58.57 138	79.56 115	81.07 76	89.34 50	83.97 107

DU-MVS		69.63 117	70.91 113	68.13 120	75.99 123	79.54 113	73.81 142	69.20 50	61.20 128	43.23 179	58.52 116	53.50 165	58.57 138	79.22 120	80.45 92	87.97 81	83.97 107

COLMAP_ROB	62.73 15	67.66 141	66.76 158	68.70 115	80.49 89	77.98 133	75.29 113	62.95 103	63.62 109	49.96 144	47.32 189	50.72 188	58.57 138	76.87 146	75.50 158	84.94 153	75.33 178
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PM-MVS		60.48 188	60.94 196	59.94 177	58.85 209	66.83 193	64.27 190	51.39 190	55.03 168	48.03 156	50.00 181	40.79 213	58.26 141	69.20 196	67.13 198	78.84 180	77.60 161

SixPastTwentyTwo		61.84 182	62.45 188	61.12 172	69.20 186	72.20 172	62.03 197	57.40 165	46.54 202	38.03 193	57.14 129	41.72 211	58.12 142	69.67 193	71.58 176	81.94 167	78.30 157

thisisatest0515		67.40 146	68.78 136	65.80 149	70.02 180	75.24 160	69.36 164	57.37 166	54.94 170	53.67 123	55.53 137	54.85 154	58.00 143	78.19 132	78.91 115	86.39 123	83.78 111

test1111		71.56 97	73.44 94	69.38 109	81.16 79	82.95 83	74.99 121	67.68 59	66.89 84	46.33 166	55.19 139	60.91 123	57.99 144	84.59 51	82.70 61	88.12 77	80.85 135

CMPMVS	47.78 17	62.49 174	62.52 187	62.46 166	70.01 181	70.66 179	62.97 194	51.84 188	51.98 186	56.71 107	42.87 196	53.62 162	57.80 145	72.23 172	70.37 180	75.45 196	75.91 171
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GBi-Net		70.78 103	73.37 96	67.76 121	72.95 155	78.00 130	75.15 115	62.72 108	64.13 103	51.44 135	58.37 119	69.02 93	57.59 146	81.33 85	80.72 82	86.70 113	82.02 121

test1		70.78 103	73.37 96	67.76 121	72.95 155	78.00 130	75.15 115	62.72 108	64.13 103	51.44 135	58.37 119	69.02 93	57.59 146	81.33 85	80.72 82	86.70 113	82.02 121

FMVSNet2		70.39 109	72.67 103	67.72 124	72.95 155	78.00 130	75.15 115	62.69 112	63.29 111	51.25 139	55.64 134	68.49 100	57.59 146	80.91 95	80.35 94	86.70 113	82.02 121

FMVSNet3		70.49 107	72.90 101	67.67 126	72.88 158	77.98 133	74.96 124	62.72 108	64.13 103	51.44 135	58.37 119	69.02 93	57.43 149	79.43 118	79.57 105	86.59 119	81.81 128

MDTV_nov1_ep13		64.37 163	65.24 167	63.37 165	68.94 187	70.81 177	72.40 154	50.29 196	60.10 135	53.91 121	60.07 107	59.15 132	57.21 150	69.43 195	67.30 195	77.47 184	69.78 194

FMVSNet1		68.84 126	70.47 117	66.94 140	71.35 172	77.68 138	74.71 125	62.35 119	56.93 152	49.94 145	50.01 179	64.59 111	57.07 151	81.33 85	80.72 82	86.25 124	82.00 124

UniMVSNet_ETH3D		67.18 150	67.03 155	67.36 131	74.44 141	78.12 128	74.07 137	66.38 67	52.22 184	46.87 161	48.64 184	51.84 182	56.96 152	77.29 140	78.53 118	85.42 145	82.59 118

pmmvs-eth3d		63.52 167	62.44 189	64.77 154	66.82 193	70.12 181	69.41 163	59.48 150	54.34 175	52.71 129	46.24 191	44.35 208	56.93 153	72.37 169	73.77 167	83.30 163	75.91 171

FC-MVSNet-train		72.60 89	75.07 85	69.71 104	81.10 83	78.79 123	73.74 144	65.23 78	66.10 89	53.34 126	70.36 63	63.40 116	56.92 154	81.44 82	80.96 78	87.93 82	84.46 105

tfpn200view9		68.11 132	68.72 138	67.40 130	77.83 110	78.93 119	74.28 132	62.81 105	56.64 154	46.82 162	52.65 166	53.47 168	56.59 155	80.41 99	78.43 120	86.11 127	80.52 140

thres400		67.95 135	68.62 140	67.17 135	77.90 107	78.59 126	74.27 133	62.72 108	56.34 158	45.77 171	53.00 161	53.35 171	56.46 156	80.21 108	78.43 120	85.91 138	80.43 141

thres200		67.98 134	68.55 141	67.30 133	77.89 109	78.86 121	74.18 136	62.75 106	56.35 157	46.48 165	52.98 162	53.54 164	56.46 156	80.41 99	77.97 126	86.05 131	79.78 148

MVS-HIRNet		54.41 202	52.10 209	57.11 190	58.99 208	56.10 215	49.68 215	49.10 199	46.18 203	52.15 134	33.18 212	46.11 203	56.10 158	63.19 208	59.70 211	76.64 190	60.25 211

Baseline_NR-MVSNet		67.53 145	68.77 137	66.09 148	75.99 123	74.75 164	72.43 153	68.41 53	61.33 127	38.33 191	51.31 174	54.13 160	56.03 159	79.22 120	78.19 123	85.37 146	82.45 119

thres100view900		67.60 144	68.02 145	67.12 137	77.83 110	77.75 137	73.90 139	62.52 116	56.64 154	46.82 162	52.65 166	53.47 168	55.92 160	78.77 126	77.62 131	85.72 139	79.23 152

test-mter		60.84 187	64.62 174	56.42 191	55.99 215	64.18 198	65.39 184	34.23 217	54.39 174	46.21 168	57.40 128	59.49 131	55.86 161	71.02 184	69.65 182	80.87 174	76.20 170

tpmrst		62.00 179	62.35 190	61.58 169	71.62 168	64.14 199	69.07 165	48.22 206	62.21 119	53.93 120	58.26 123	55.30 152	55.81 162	63.22 207	62.62 206	70.85 208	70.70 191

TranMVSNet+NR-MVSNet		69.25 122	70.81 114	67.43 129	77.23 117	79.46 115	73.48 147	69.66 44	60.43 133	39.56 187	58.82 115	53.48 167	55.74 163	79.59 113	81.21 74	88.89 61	82.70 117

thres600view7		67.68 140	68.43 142	66.80 142	77.90 107	78.86 121	73.84 140	62.75 106	56.07 160	44.70 177	52.85 164	52.81 175	55.58 164	80.41 99	77.77 128	86.05 131	80.28 143

Vis-MVSNet		72.77 88	77.20 76	67.59 128	74.19 143	84.01 68	76.61 108	61.69 127	60.62 132	50.61 142	70.25 64	71.31 79	55.57 165	83.85 58	82.28 63	86.90 106	88.08 63
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EG-PatchMatch MVS		67.24 148	66.94 156	67.60 127	78.73 102	81.35 94	73.28 149	59.49 149	46.89 201	51.42 138	43.65 195	53.49 166	55.50 166	81.38 84	80.66 88	87.15 97	81.17 133

test-LLR		64.42 162	64.36 175	64.49 156	75.02 134	63.93 200	66.61 179	61.96 123	54.41 172	47.77 157	57.46 126	60.25 125	55.20 167	70.80 185	69.33 183	80.40 175	74.38 182

TESTMET0.1,1		61.10 186	64.36 175	57.29 188	57.53 212	63.93 200	66.61 179	36.22 216	54.41 172	47.77 157	57.46 126	60.25 125	55.20 167	70.80 185	69.33 183	80.40 175	74.38 182

dmvs_re		67.22 149	67.92 147	66.40 146	75.94 126	70.55 180	74.97 123	63.87 89	57.07 151	44.75 175	54.29 144	56.72 145	54.65 169	79.53 116	77.51 134	84.20 158	79.78 148

UA-Net		74.47 78	77.80 68	70.59 92	85.33 53	85.40 57	73.54 145	65.98 73	60.65 131	56.00 110	72.11 53	79.15 46	54.63 170	83.13 68	82.25 64	88.04 80	81.92 127

IS_MVSNet		73.33 84	77.34 75	68.65 116	81.29 78	83.47 76	74.45 127	63.58 94	65.75 92	48.49 152	67.11 80	70.61 82	54.63 170	84.51 52	83.58 54	89.48 48	86.34 79

baseline1		70.10 113	72.17 106	67.69 125	79.74 95	76.80 145	73.91 138	64.38 84	62.74 116	48.30 154	64.94 85	64.08 113	54.17 172	81.46 81	78.92 114	85.66 141	76.22 169

tpm		62.41 175	63.15 181	61.55 170	72.24 161	63.79 202	71.31 157	46.12 210	57.82 143	55.33 112	59.90 109	54.74 155	53.63 173	67.24 201	64.29 203	70.65 209	74.25 184

MDTV_nov1_ep13_2view		60.16 189	60.51 197	59.75 178	65.39 195	69.05 185	68.00 169	48.29 204	51.99 185	45.95 170	48.01 187	49.64 194	53.39 174	68.83 197	66.52 199	77.47 184	69.55 195

UniMVSNet (Re)		69.53 118	71.90 108	66.76 143	76.42 121	80.93 99	72.59 152	68.03 56	61.75 123	41.68 184	58.34 122	57.23 141	53.27 175	79.53 116	80.62 90	88.57 67	84.90 99

RPMNet		61.71 185	62.88 183	60.34 175	69.51 184	69.41 182	63.48 192	49.23 198	57.81 144	45.64 172	50.51 177	50.12 190	53.13 176	68.17 200	68.49 191	81.07 173	75.62 176

tfpnnormal		64.27 164	63.64 180	65.02 152	75.84 127	75.61 156	71.24 158	62.52 116	47.79 198	42.97 181	42.65 197	44.49 207	52.66 177	78.77 126	76.86 144	84.88 154	79.29 151

MDA-MVSNet-bldmvs		53.37 205	53.01 208	53.79 200	43.67 221	67.95 189	59.69 203	57.92 163	43.69 205	32.41 200	41.47 199	27.89 224	52.38 178	56.97 216	65.99 201	76.68 189	67.13 199

NR-MVSNet		68.79 127	70.56 115	66.71 145	77.48 115	79.54 113	73.52 146	69.20 50	61.20 128	39.76 186	58.52 116	50.11 191	51.37 179	80.26 106	80.71 86	88.97 59	83.59 113

EPMVS		60.00 190	61.97 191	57.71 187	68.46 188	63.17 206	64.54 188	48.23 205	63.30 110	44.72 176	60.19 105	56.05 149	50.85 180	65.27 205	62.02 207	69.44 211	63.81 205

CVMVSNet		62.55 172	65.89 161	58.64 184	66.95 191	69.15 184	66.49 181	56.29 171	52.46 183	32.70 199	59.27 113	58.21 138	50.09 181	71.77 177	71.39 177	79.31 178	78.99 154

pmmvs5		62.37 178	64.04 177	60.42 174	65.03 196	71.67 175	67.17 173	52.70 184	50.30 191	44.80 174	54.23 148	51.19 186	49.37 182	72.88 168	73.48 169	83.45 162	74.55 181

UGNet		72.78 87	77.67 69	67.07 138	71.65 167	83.24 80	75.20 114	63.62 93	64.93 96	56.72 106	71.82 55	73.30 69	49.02 183	81.02 93	80.70 87	86.22 125	88.67 59
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
pm-mvs1		65.62 155	67.42 152	63.53 163	73.66 151	76.39 149	69.66 161	60.87 134	49.73 194	43.97 178	51.24 175	57.00 144	48.16 184	79.89 110	77.84 127	84.85 155	79.82 147

gg-mvs-nofinetune		62.55 172	65.05 170	59.62 180	78.72 103	77.61 139	70.83 159	53.63 174	39.71 213	22.04 215	36.36 208	64.32 112	47.53 185	81.16 90	79.03 113	85.00 152	77.17 164

pmmvs6		62.41 175	62.88 183	61.87 168	71.38 171	75.18 163	67.76 170	59.45 151	41.64 209	42.52 183	37.33 206	52.91 174	46.87 186	77.67 137	76.26 152	83.23 164	79.18 153

ADS-MVSNet		55.94 199	58.01 200	53.54 201	62.48 203	58.48 212	59.12 205	46.20 209	59.65 137	42.88 182	52.34 170	53.31 172	46.31 187	62.00 209	60.02 210	64.23 216	60.24 212

pmmvs3		47.65 208	49.08 213	45.99 208	44.61 219	54.79 216	50.04 213	31.95 220	33.91 216	29.90 201	30.37 213	33.53 219	46.31 187	63.50 206	63.67 205	73.14 204	63.77 206

TransMVSNet (Re)		64.74 161	65.66 164	63.66 162	77.40 116	75.33 159	69.86 160	62.67 114	47.63 199	41.21 185	50.01 179	52.33 178	45.31 189	79.57 114	77.69 130	85.49 143	77.07 166

CDS-MVSNet		67.65 142	69.83 123	65.09 151	75.39 131	76.55 148	74.42 130	63.75 90	53.55 177	49.37 149	59.41 112	62.45 118	44.44 190	79.71 112	79.82 100	83.17 165	77.36 163
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		59.58 191	62.81 185	55.81 193	66.03 194	65.64 197	63.86 191	48.74 201	49.95 193	37.07 195	54.77 142	58.54 135	44.44 190	72.29 171	71.79 174	74.70 198	66.66 200

EPNet_dtu		68.08 133	71.00 112	64.67 155	79.64 96	68.62 187	75.05 119	63.30 95	66.36 87	45.27 173	67.40 78	66.84 106	43.64 192	75.37 155	74.98 161	81.15 171	77.44 162
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		57.24 195	60.02 198	53.99 199	56.45 214	62.74 207	65.27 185	47.03 207	55.14 165	39.55 188	40.88 201	53.42 170	41.83 193	72.35 170	71.10 179	73.79 201	64.50 204

ambc			53.42 206		64.99 197	63.36 204	49.96 214		47.07 200	37.12 194	28.97 215	16.36 227	41.82 194	75.10 157	67.34 194	71.55 207	75.72 173

FPMVS		51.87 206	50.00 211	54.07 198	66.83 192	57.25 213	60.25 202	50.91 191	50.25 192	34.36 197	36.04 209	32.02 220	41.49 195	58.98 213	56.07 213	70.56 210	59.36 213

CP-MVSNet		62.68 171	65.49 166	59.40 182	71.84 163	75.34 158	62.87 195	67.04 65	52.64 181	27.19 206	53.38 154	48.15 197	41.40 196	71.26 179	75.68 155	86.07 129	82.00 124

PS-CasMVS		62.38 177	65.06 169	59.25 183	71.73 164	75.21 162	62.77 196	66.99 66	51.94 188	26.96 207	52.00 171	47.52 200	41.06 197	71.16 182	75.60 156	85.97 136	81.97 126

PEN-MVS		62.96 169	65.77 163	59.70 179	73.98 146	75.45 157	63.39 193	67.61 60	52.49 182	25.49 208	53.39 153	49.12 195	40.85 198	71.94 176	77.26 140	86.86 108	80.72 137

MIMVSNet		58.52 194	61.34 194	55.22 195	60.76 205	67.01 192	66.81 176	49.02 200	56.43 156	38.90 189	40.59 203	54.54 157	40.57 199	73.16 167	71.65 175	75.30 197	66.00 201

pmnet_mix02		55.30 200	57.01 204	53.30 202	64.14 199	59.09 211	58.39 206	50.24 197	53.47 178	38.68 190	49.75 182	45.86 204	40.14 200	65.38 204	60.22 209	68.19 213	65.33 202

Vis-MVSNet (Re-imp)		67.83 138	73.52 93	61.19 171	78.37 105	76.72 147	66.80 177	62.96 102	65.50 93	34.17 198	67.19 79	69.68 89	39.20 201	79.39 119	79.44 109	85.68 140	76.73 168

DTE-MVSNet		61.85 181	64.96 172	58.22 185	74.32 142	74.39 166	61.01 199	67.85 58	51.76 189	21.91 216	53.28 155	48.17 196	37.74 202	72.22 173	76.44 150	86.52 121	78.49 156

EU-MVSNet		54.63 201	58.69 199	49.90 205	56.99 213	62.70 208	56.41 208	50.64 195	45.95 204	23.14 212	50.42 178	46.51 202	36.63 203	65.51 203	64.85 202	75.57 193	74.91 179

Anonymous20231206		56.36 198	57.80 202	54.67 197	70.08 179	66.39 194	60.46 201	57.54 164	49.50 196	29.30 203	33.86 211	46.64 201	35.18 204	70.44 189	68.88 187	75.47 195	68.88 197

WR-MVS		63.03 168	67.40 153	57.92 186	75.14 133	77.60 140	60.56 200	66.10 70	54.11 176	23.88 209	53.94 150	53.58 163	34.50 205	73.93 164	77.71 129	87.35 95	80.94 134

WR-MVS_H		61.83 183	65.87 162	57.12 189	71.72 165	76.87 144	61.45 198	66.19 68	51.97 187	22.92 213	53.13 160	52.30 180	33.80 206	71.03 183	75.00 160	86.65 117	80.78 136

PMVS	39.38 18	46.06 212	43.30 215	49.28 206	62.93 200	38.75 221	41.88 219	53.50 176	33.33 219	35.46 196	28.90 216	31.01 221	33.04 207	58.61 215	54.63 216	68.86 212	57.88 214
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test0.0.03 1		58.80 192	61.58 193	55.56 194	75.02 134	68.45 188	59.58 204	61.96 123	52.74 180	29.57 202	49.75 182	54.56 156	31.46 208	71.19 180	69.77 181	75.75 192	64.57 203

N_pmnet		47.35 209	50.13 210	44.11 210	59.98 207	51.64 218	51.86 212	44.80 211	49.58 195	20.76 217	40.65 202	40.05 215	29.64 209	59.84 211	55.15 214	57.63 217	54.00 215

DeepMVS_CX						18.74 227	18.55 225	8.02 222	26.96 221	7.33 224	23.81 219	13.05 228	25.99 210	25.17 222		22.45 227	36.25 221

MIMVSNet1		49.27 207	53.25 207	44.62 209	44.61 219	61.52 210	53.61 210	52.18 185	41.62 210	18.68 219	28.14 217	41.58 212	25.50 211	68.46 199	69.04 185	73.15 203	62.37 209

Gipuma		36.38 215	35.80 217	37.07 212	45.76 218	33.90 222	29.81 221	48.47 203	39.91 212	18.02 220	8.00 225	8.14 229	25.14 212	59.29 212	61.02 208	55.19 219	40.31 218
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testgi		54.39 203	57.86 201	50.35 204	71.59 170	67.24 191	54.95 209	53.25 178	43.36 206	23.78 210	44.64 193	47.87 198	24.96 213	70.45 188	68.66 189	73.60 202	62.78 208

new_pmnet		38.40 214	42.64 216	33.44 214	37.54 224	45.00 220	36.60 220	32.72 219	40.27 211	12.72 222	29.89 214	28.90 222	24.78 214	53.17 217	52.90 217	56.31 218	48.34 216

FC-MVSNet-test		56.90 197	65.20 168	47.21 207	66.98 190	63.20 205	49.11 216	58.60 160	59.38 138	11.50 223	65.60 82	56.68 146	24.66 215	71.17 181	71.36 178	72.38 205	69.02 196

test20.03		53.93 204	56.28 205	51.19 203	72.19 162	65.83 195	53.20 211	61.08 130	42.74 207	22.08 214	37.07 207	45.76 205	24.29 216	70.44 189	69.04 185	74.31 200	63.05 207

EMVS		20.98 219	17.15 222	25.44 216	39.51 223	19.37 226	12.66 226	39.59 215	19.10 223	6.62 226	9.27 223	4.40 231	22.43 217	17.99 224	24.40 222	31.81 224	25.53 223

E-PMN		21.77 218	18.24 221	25.89 215	40.22 222	19.58 225	12.46 227	39.87 214	18.68 224	6.71 225	9.57 222	4.31 232	22.36 218	19.89 223	27.28 221	33.73 223	28.34 222

new-patchmatchnet		46.97 210	49.47 212	44.05 211	62.82 201	56.55 214	45.35 218	52.01 186	42.47 208	17.04 221	35.73 210	35.21 217	21.84 219	61.27 210	54.83 215	65.26 215	60.26 210

test_method		22.26 217	25.94 219	17.95 219	3.24 228	7.17 228	23.83 223	7.27 223	37.35 215	20.44 218	21.87 220	39.16 216	18.67 220	34.56 219	20.84 223	34.28 222	20.64 224

MVE	19.12 19	20.47 220	23.27 220	17.20 220	12.66 227	25.41 224	10.52 228	34.14 218	14.79 225	6.53 227	8.79 224	4.68 230	16.64 221	29.49 221	41.63 218	22.73 226	38.11 219
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		40.01 213	45.06 214	34.13 213	58.84 210	53.28 217	28.60 222	58.10 162	32.93 220	4.65 228	40.92 200	28.33 223	7.26 222	58.86 214	56.09 212	47.36 220	44.98 217

PMMVS2		25.60 216	29.75 218	20.76 218	28.00 225	30.93 223	23.10 224	29.18 221	23.14 222	1.46 229	18.23 221	16.54 226	5.08 223	40.22 218	41.40 219	37.76 221	37.79 220

tmp_tt				14.50 221	14.68 226	7.17 228	10.46 229	2.21 224	37.73 214	28.71 204	25.26 218	16.98 225	4.37 224	31.49 220	29.77 220	26.56 225

GG-mvs-BLEND		46.86 211	67.51 151	22.75 217	0.05 229	76.21 151	64.69 187	0.04 225	61.90 121	0.09 230	55.57 135	71.32 78	0.08 225	70.54 187	67.19 196	71.58 206	69.86 193

test123		0.09 221	0.14 224	0.02 222	0.00 231	0.02 230	0.02 232	0.01 226	0.09 227	0.00 232	0.30 226	0.00 234	0.08 225	0.03 226	0.09 225	0.01 228	0.45 225

testmvs		0.09 221	0.15 223	0.02 222	0.01 230	0.02 230	0.05 231	0.01 226	0.11 226	0.01 231	0.26 227	0.01 233	0.06 227	0.10 225	0.10 224	0.01 228	0.43 226

uanet_test		0.00 223	0.00 225	0.00 224	0.00 231	0.00 232	0.00 233	0.00 228	0.00 228	0.00 232	0.00 228	0.00 234	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 224	0.00 231	0.00 232	0.00 233	0.00 228	0.00 228	0.00 232	0.00 228	0.00 234	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

sosnet		0.00 223	0.00 225	0.00 224	0.00 231	0.00 232	0.00 233	0.00 228	0.00 228	0.00 232	0.00 228	0.00 234	0.00 228	0.00 227	0.00 226	0.00 230	0.00 227

RE-MVS-def										46.24 167

9.14												86.88 16

SR-MVS					88.99 34			73.57 24				87.54 14

our_test_3					67.93 189	70.99 176	66.89 175

MTAPA										83.48 1		86.45 19

MTMP										82.66 5		84.91 26

Patchmatch-RL test							2.85 230

XVS					86.63 45	88.68 27	85.00 47			71.81 45		81.92 37				90.47 23

X-MVStestdata					86.63 45	88.68 27	85.00 47			71.81 45		81.92 37				90.47 23

mPP-MVS					89.90 25							81.29 42

NP-MVS									80.10 46

Patchmtry						65.80 196	65.97 182	52.74 182		52.65 130

High-resolution multi-view benchmark