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.

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 5	76.83 7	94.16 1	86.57 1	90.85 6	87.07 1	86.18 1	86.36 7	85.08 12	88.67 21	98.21 3

DVP-MVS++.		87.98 3	89.76 5	85.89 2	92.57 6	94.57 3	88.34 6	76.61 8	92.40 6	83.40 3	89.26 11	85.57 5	86.04 2	86.24 11	84.89 15	88.39 31	95.42 21

xxxxxxxxxxxxxcwj		84.33 15	83.20 27	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	44.71 145	79.75 8	83.52 26	82.72 32	88.75 19	95.37 24

SF-MVS		87.30 6	88.71 6	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 12	79.85 7	92.37 3	83.29 10	79.75 8	83.52 26	82.72 32	88.75 19	95.37 24

DVP-MVS		88.07 2	90.73 2	84.97 5	91.98 10	95.01 2	87.86 10	76.88 6	93.90 2	85.15 2	90.11 8	86.90 2	79.46 12	86.26 10	84.67 18	88.50 28	98.25 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MSP-MVS		87.87 4	90.57 3	84.73 6	89.38 28	91.60 18	88.24 8	74.15 13	93.55 3	82.28 4	94.99 1	83.21 11	85.96 3	87.67 4	84.67 18	88.32 32	98.29 1
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
MCST-MVS		85.75 9	86.99 13	84.31 7	94.07 3	92.80 8	88.15 9	79.10 3	85.66 24	70.72 31	76.50 33	80.45 21	82.17 4	88.35 2	87.49 3	91.63 2	97.65 4

DPE-MVS		87.60 5	90.44 4	84.29 8	92.09 9	93.44 6	88.69 4	75.11 10	93.06 5	80.80 6	94.23 2	86.70 3	81.44 6	84.84 18	83.52 27	87.64 46	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		85.96 8	87.58 11	84.06 9	92.58 5	92.40 11	87.62 11	77.77 5	88.44 15	75.93 18	79.49 26	81.97 17	81.65 5	87.04 6	86.58 4	88.79 17	97.18 7

APDe-MVS		86.37 7	88.41 8	84.00 10	91.43 15	91.83 16	88.34 6	74.67 11	91.19 7	81.76 5	91.13 5	81.94 18	80.07 7	83.38 28	82.58 35	87.69 44	96.78 10

DPM-MVS		85.41 11	86.72 16	83.89 11	91.66 13	91.92 15	90.49 3	78.09 4	86.90 19	73.95 21	74.52 35	82.01 16	79.29 13	90.24 1	90.65 1	89.86 6	90.78 74

NCCC		84.16 17	85.46 21	82.64 12	92.34 8	90.57 24	86.57 14	76.51 9	86.85 21	72.91 24	77.20 32	78.69 27	79.09 15	84.64 20	84.88 16	88.44 29	95.41 22

HPM-MVS++		85.64 10	88.43 7	82.39 13	92.65 4	90.24 27	85.83 17	74.21 12	90.68 9	75.63 19	86.77 14	84.15 8	78.68 16	86.33 8	85.26 9	87.32 54	95.60 18

APD-MVS		84.83 13	87.00 12	82.30 14	89.61 26	89.21 35	86.51 15	73.64 17	90.98 8	77.99 13	89.89 9	80.04 24	79.18 14	82.00 48	81.37 48	86.88 66	95.49 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + MP.		84.39 14	86.58 17	81.83 15	88.09 40	86.47 65	85.63 19	73.62 18	90.13 11	79.24 10	89.67 10	82.99 12	77.72 18	81.22 54	80.92 58	86.68 70	94.66 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SMA-MVS		85.24 12	88.27 9	81.72 16	91.74 12	90.71 21	86.71 13	73.16 20	90.56 10	74.33 20	83.07 19	85.88 4	77.16 20	86.28 9	85.58 6	87.23 58	95.77 14
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
SD-MVS		84.31 16	86.96 14	81.22 17	88.98 32	88.68 39	85.65 18	73.85 16	89.09 14	79.63 9	87.34 13	84.84 6	73.71 38	82.66 35	81.60 45	85.48 104	94.51 32
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
DeepC-MVS_fast	75.41 2	81.69 25	82.10 34	81.20 18	91.04 17	87.81 52	83.42 28	74.04 14	83.77 28	71.09 29	66.88 47	72.44 39	79.48 11	85.08 15	84.97 14	88.12 39	93.78 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		82.90 21	84.52 23	81.02 19	91.85 11	93.43 7	87.14 12	74.01 15	81.96 34	76.14 16	70.84 39	82.49 13	69.71 64	82.32 41	85.18 11	87.26 57	95.40 23

HFP-MVS		82.48 23	84.12 24	80.56 20	90.15 19	87.55 54	84.28 24	69.67 35	85.22 25	77.95 14	84.69 17	75.94 31	75.04 28	81.85 49	81.17 52	86.30 76	92.40 57

3Dnovator	70.49 5	78.42 40	76.77 59	80.35 21	91.43 15	90.27 26	81.84 37	70.79 27	72.10 60	71.95 25	50.02 100	67.86 58	77.47 19	82.89 32	84.24 20	88.61 24	89.99 83

ACMMP_NAP		83.54 18	86.37 18	80.25 22	89.57 27	90.10 29	85.27 21	71.66 24	87.38 16	73.08 23	84.23 18	80.16 22	75.31 26	84.85 17	83.64 24	86.57 71	94.21 39

MSLP-MVS++		78.57 39	77.33 53	80.02 23	88.39 35	84.79 78	84.62 23	66.17 57	75.96 54	78.40 11	61.59 63	71.47 46	73.54 41	78.43 77	78.88 73	88.97 14	90.18 82

zzz-MVS		81.65 26	83.10 28	79.97 24	88.14 39	87.62 53	83.96 27	69.90 32	86.92 18	77.67 15	72.47 37	78.74 26	74.13 35	81.59 52	81.15 53	86.01 86	93.19 50

DeepC-MVS	74.46 3	80.30 31	81.05 37	79.42 25	87.42 42	88.50 41	83.23 29	73.27 19	82.78 31	71.01 30	62.86 60	69.93 52	74.80 31	84.30 21	84.20 21	86.79 69	94.77 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		76.23 54	73.55 74	79.35 26	89.38 28	85.00 77	79.99 51	73.04 21	76.60 53	71.17 28	55.18 81	57.99 101	77.87 17	76.82 90	76.82 91	84.67 126	86.45 116

SteuartSystems-ACMMP		82.51 22	85.35 22	79.20 27	90.25 18	89.39 34	84.79 22	70.95 26	82.86 30	68.32 39	86.44 15	77.19 28	73.07 43	83.63 25	83.64 24	87.82 40	94.34 34
Skip Steuart: Steuart Systems R&D Blog.
train_agg		83.35 19	86.93 15	79.17 28	89.70 24	88.41 42	85.60 20	72.89 22	86.31 22	66.58 42	90.48 7	82.24 15	73.06 44	83.10 31	82.64 34	87.21 62	95.30 26

DELS-MVS		79.49 32	79.84 42	79.08 29	88.26 38	92.49 9	84.12 26	70.63 28	65.27 83	69.60 37	61.29 65	66.50 62	72.75 45	88.07 3	88.03 2	89.13 12	97.22 6
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
abl_6				79.06 30	89.68 25	92.14 13	77.70 63	69.68 34	86.87 20	71.88 26	74.29 36	80.06 23	76.56 23			88.84 16	95.82 13

3Dnovator+	70.16 6	77.87 43	77.29 54	78.55 31	89.25 30	88.32 44	80.09 49	67.95 45	74.89 58	71.83 27	52.05 94	70.68 49	76.27 25	82.27 42	82.04 37	85.92 87	90.77 75

CANet		80.90 29	82.93 30	78.53 32	86.83 46	92.26 12	81.19 43	66.95 50	81.60 37	69.90 34	66.93 46	74.80 33	76.79 21	84.68 19	84.77 17	89.50 9	95.50 19

MP-MVS		80.94 28	83.49 26	77.96 33	88.48 33	88.16 46	82.82 33	69.34 37	80.79 40	69.67 35	82.35 21	77.13 29	71.60 54	80.97 59	80.96 57	85.87 90	94.06 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + GP.		82.27 24	85.98 19	77.94 34	80.72 72	88.25 45	81.12 44	67.71 46	87.10 17	73.31 22	85.23 16	83.68 9	76.64 22	80.43 62	81.47 47	88.15 38	95.66 17

ACMMPR		80.62 30	82.98 29	77.87 35	88.41 34	87.05 59	83.02 30	69.18 38	83.91 27	68.35 38	82.89 20	73.64 36	72.16 49	80.78 60	81.13 54	86.10 83	91.43 64

DeepPCF-MVS	76.94 1	83.08 20	87.77 10	77.60 36	90.11 20	90.96 20	78.48 55	72.63 23	93.10 4	65.84 43	80.67 24	81.55 19	74.80 31	85.94 13	85.39 8	83.75 141	96.77 11

QAPM		77.50 46	77.43 52	77.59 37	91.52 14	92.00 14	81.41 41	70.63 28	66.22 76	58.05 72	54.70 82	71.79 45	74.49 34	82.46 37	82.04 37	89.46 10	92.79 55

CLD-MVS		77.36 48	77.29 54	77.45 38	82.21 61	88.11 47	81.92 36	68.96 40	77.97 48	69.62 36	62.08 61	59.44 92	73.57 40	81.75 50	81.27 50	88.41 30	90.39 79
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CP-MVS		79.44 33	81.51 36	77.02 39	86.95 44	85.96 71	82.00 35	68.44 43	81.82 35	67.39 40	77.43 30	73.68 35	71.62 53	79.56 68	79.58 67	85.73 94	92.51 56

TSAR-MVS + ACMM		81.59 27	85.84 20	76.63 40	89.82 23	86.53 64	86.32 16	66.72 53	85.96 23	65.43 44	88.98 12	82.29 14	67.57 81	82.06 47	81.33 49	83.93 139	93.75 44

PGM-MVS		79.42 36	81.84 35	76.60 41	88.38 36	86.69 61	82.97 32	65.75 59	80.39 41	64.94 45	81.95 23	72.11 44	71.41 55	80.45 61	80.55 63	86.18 80	90.76 76

MVS_111021_HR		77.42 47	78.40 48	76.28 42	86.95 44	90.68 22	77.41 67	70.56 31	66.21 77	62.48 53	66.17 50	63.98 70	72.08 50	82.87 33	83.15 28	88.24 35	95.71 16

MVS_0304		79.43 34	82.20 32	76.20 43	84.22 54	91.79 17	81.82 38	63.81 71	76.83 52	61.71 57	66.37 49	75.52 32	76.38 24	85.54 14	85.03 13	89.28 11	94.32 36

CDPH-MVS		79.39 37	82.13 33	76.19 44	89.22 31	88.34 43	84.20 25	71.00 25	79.67 44	56.97 77	77.77 29	72.24 43	68.50 76	81.33 53	82.74 30	87.23 58	92.84 53

OpenMVS	67.62 8	74.92 60	73.91 72	76.09 45	90.10 21	90.38 25	78.01 59	66.35 55	66.09 78	62.80 50	46.33 123	64.55 69	71.77 52	79.92 65	80.88 59	87.52 50	89.20 92

EPNet		79.28 38	82.25 31	75.83 46	88.31 37	90.14 28	79.43 53	68.07 44	81.76 36	61.26 60	77.26 31	70.08 51	70.06 62	82.43 39	82.00 39	87.82 40	92.09 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MAR-MVS		77.19 49	78.37 49	75.81 47	89.87 22	90.58 23	79.33 54	65.56 61	77.62 50	58.33 71	59.24 73	67.98 56	74.83 30	82.37 40	83.12 29	86.95 64	87.67 108
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
canonicalmvs		77.65 44	79.59 43	75.39 48	81.52 65	89.83 33	81.32 42	60.74 104	80.05 42	66.72 41	68.43 43	65.09 65	74.72 33	78.87 73	82.73 31	87.32 54	92.16 58

X-MVS		78.16 42	80.55 39	75.38 49	87.99 41	86.27 67	81.05 45	68.98 39	78.33 46	61.07 62	75.25 34	72.27 40	67.52 82	80.03 64	80.52 64	85.66 101	91.20 68

ACMMP		77.61 45	79.59 43	75.30 50	85.87 50	85.58 72	81.42 40	67.38 49	79.38 45	62.61 51	78.53 27	65.79 64	68.80 75	78.56 76	78.50 78	85.75 91	90.80 73
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
HQP-MVS		78.26 41	80.91 38	75.17 51	85.67 51	84.33 84	83.01 31	69.38 36	79.88 43	55.83 78	79.85 25	64.90 67	70.81 57	82.46 37	81.78 41	86.30 76	93.18 51

PVSNet_BlendedMVS		76.84 51	78.47 46	74.95 52	82.37 59	89.90 31	75.45 78	65.45 62	74.99 56	70.66 32	63.07 58	58.27 99	67.60 79	84.24 22	81.70 43	88.18 36	97.10 8

PVSNet_Blended		76.84 51	78.47 46	74.95 52	82.37 59	89.90 31	75.45 78	65.45 62	74.99 56	70.66 32	63.07 58	58.27 99	67.60 79	84.24 22	81.70 43	88.18 36	97.10 8

OPM-MVS		72.74 71	70.93 90	74.85 54	85.30 52	84.34 83	82.82 33	69.79 33	49.96 136	55.39 83	54.09 89	60.14 89	70.04 63	80.38 63	79.43 68	85.74 93	88.20 104
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PCF-MVS	70.85 4	75.73 56	76.55 62	74.78 55	83.67 55	88.04 50	81.47 39	70.62 30	69.24 72	57.52 75	60.59 69	69.18 54	70.65 59	77.11 87	77.65 85	84.75 124	94.01 41
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		75.20 59	75.69 66	74.63 56	79.26 79	89.07 36	78.47 56	63.59 74	67.05 74	63.79 48	55.72 79	60.32 87	73.58 39	82.16 43	81.78 41	89.08 13	93.72 45

PHI-MVS		79.43 34	84.06 25	74.04 57	86.15 49	91.57 19	80.85 47	68.90 41	82.22 33	51.81 94	78.10 28	74.28 34	70.39 61	84.01 24	84.00 22	86.14 82	94.24 37

MVS_Test		75.22 58	76.69 60	73.51 58	79.30 78	88.82 38	80.06 50	58.74 111	69.77 68	57.50 76	59.78 72	61.35 81	75.31 26	82.07 46	83.60 26	90.13 5	91.41 66

CPTT-MVS		75.43 57	77.13 56	73.44 59	81.43 66	82.55 97	80.96 46	64.35 67	77.95 49	61.39 59	69.20 42	70.94 48	69.38 71	73.89 120	73.32 135	83.14 151	92.06 60

MVSTER		76.92 50	79.92 41	73.42 60	74.98 113	82.97 93	78.15 58	63.41 75	78.02 47	64.41 47	67.54 44	72.80 38	71.05 56	83.29 30	83.73 23	88.53 27	91.12 69

CHOSEN 1792x2688		72.55 72	71.98 81	73.22 61	86.57 47	92.41 10	75.63 74	66.77 52	62.08 89	52.32 91	30.27 191	50.74 132	66.14 85	86.22 12	85.41 7	91.90 1	96.75 12

diffmvs		74.32 61	75.42 67	73.04 62	75.60 109	87.27 56	78.20 57	62.96 79	68.66 73	61.89 55	59.79 71	59.84 90	71.80 51	78.30 80	79.87 65	87.80 42	94.23 38

DI_MVS_plusplus_trai		73.94 65	74.85 69	72.88 63	76.57 101	86.80 60	80.41 48	61.47 95	62.35 88	59.44 69	47.91 106	68.12 55	72.24 48	82.84 34	81.50 46	87.15 63	94.42 33

DROMVSNet		76.05 55	78.87 45	72.77 64	78.87 82	86.63 62	77.50 65	57.04 132	75.34 55	61.68 58	64.20 54	69.56 53	73.96 36	82.12 44	80.65 61	87.57 48	93.57 46

ACMM	66.70 10	70.42 82	68.49 104	72.67 65	82.85 56	77.76 142	77.70 63	64.76 66	64.61 84	60.74 66	49.29 101	53.97 121	65.86 86	74.97 106	75.57 107	84.13 138	83.29 141
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CNLPA		71.37 80	70.27 94	72.66 66	80.79 71	81.33 107	71.07 113	65.75 59	82.36 32	64.80 46	42.46 135	56.49 106	72.70 46	73.00 131	70.52 166	80.84 175	85.76 124

MVS_111021_LR		74.26 62	75.95 64	72.27 67	79.43 77	85.04 76	72.71 95	65.27 64	70.92 64	63.58 49	69.32 41	60.31 88	69.43 69	77.01 88	77.15 88	83.22 148	91.93 62

ACMP	68.86 7	72.15 74	72.25 79	72.03 68	80.96 68	80.87 113	77.93 60	64.13 69	69.29 70	60.79 65	64.04 55	53.54 124	63.91 95	73.74 123	75.27 110	84.45 131	88.98 94
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OMC-MVS		74.03 63	75.82 65	71.95 69	79.56 75	80.98 111	75.35 80	63.21 76	84.48 26	61.83 56	61.54 64	66.89 59	69.41 70	76.60 91	74.07 125	82.34 162	86.15 119

MS-PatchMatch		70.34 86	69.00 100	71.91 70	85.20 53	85.35 73	77.84 62	61.77 93	58.01 104	55.40 82	41.26 142	58.34 98	61.69 109	81.70 51	78.29 79	89.56 8	80.02 159

ETV-MVS		76.25 53	80.22 40	71.63 71	78.23 84	87.95 51	72.75 94	60.27 108	77.50 51	57.73 73	71.53 38	66.60 61	73.16 42	80.99 58	81.23 51	87.63 47	95.73 15

baseline		72.89 69	74.46 71	71.07 72	75.99 105	87.50 55	74.57 84	60.49 106	70.72 65	57.60 74	60.63 68	60.97 83	70.79 58	75.27 104	76.33 97	86.94 65	89.79 86

Anonymous20231211		68.44 94	66.37 118	70.86 73	77.58 91	83.49 89	75.15 81	61.89 90	52.54 129	58.50 70	28.89 193	56.78 105	69.29 72	74.96 108	76.61 92	82.73 154	91.36 67

baseline1		71.47 77	72.02 80	70.82 74	80.56 73	84.51 80	76.61 71	66.93 51	56.22 112	48.66 107	55.40 80	60.43 86	62.55 104	83.35 29	80.99 55	89.60 7	83.28 142

PLC	64.00 12	68.54 93	66.66 115	70.74 75	80.28 74	74.88 163	72.64 96	63.70 73	69.26 71	55.71 79	47.24 114	55.31 114	70.42 60	72.05 143	70.67 164	81.66 169	77.19 167
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LGP-MVS_train		72.02 75	73.18 77	70.67 76	82.13 62	80.26 119	79.58 52	63.04 78	70.09 66	51.98 92	65.06 51	55.62 112	62.49 105	75.97 98	76.32 98	84.80 123	88.93 95

CS-MVS-test		73.97 64	76.86 57	70.60 77	75.53 110	83.16 91	77.50 65	57.04 132	71.34 62	53.25 89	63.44 57	64.85 68	73.96 36	82.12 44	78.80 74	86.30 76	94.34 34

EIA-MVS		73.48 67	76.05 63	70.47 78	78.12 85	87.21 57	71.78 100	60.63 105	69.66 69	55.56 81	64.86 52	60.69 84	69.53 67	77.35 86	78.59 75	87.22 60	94.01 41

MSDG		65.57 114	61.57 151	70.24 79	82.02 63	76.47 151	74.46 91	68.73 42	56.52 109	50.33 102	38.47 155	41.10 155	62.42 106	72.12 141	72.94 142	83.47 144	73.37 181

CostFormer		72.18 73	73.90 73	70.18 80	79.47 76	86.19 70	76.94 70	48.62 179	66.07 79	60.40 67	54.14 88	65.82 63	67.98 77	75.84 99	76.41 96	87.67 45	92.83 54

test_part1		66.32 108	63.35 134	69.77 81	77.40 94	78.35 135	77.85 61	56.25 140	44.52 159	62.15 54	33.05 182	53.91 122	62.38 107	72.19 140	74.65 115	82.59 157	86.81 112

PVSNet_Blended_VisFu		71.76 76	73.54 75	69.69 82	79.01 80	87.16 58	72.05 97	61.80 92	56.46 110	59.66 68	53.88 90	62.48 73	59.08 128	81.17 55	78.90 72	86.53 73	94.74 29

CS-MVS		73.80 66	77.47 51	69.53 83	74.86 115	85.07 75	69.93 120	56.91 135	72.12 59	54.28 87	64.82 53	66.85 60	74.88 29	79.25 70	79.64 66	86.30 76	94.52 31

Effi-MVS+		70.42 82	71.23 87	69.47 84	78.04 86	85.24 74	75.57 76	58.88 110	59.56 98	48.47 108	52.73 93	54.94 115	69.69 65	78.34 79	77.06 89	86.18 80	90.73 77

FC-MVSNet-train		68.83 92	68.29 105	69.47 84	78.35 83	79.94 120	64.72 148	66.38 54	54.96 120	54.51 86	56.75 76	47.91 138	66.91 83	75.57 103	75.75 103	85.92 87	87.12 110

DCV-MVSNet		69.13 89	69.07 99	69.21 86	77.65 90	77.52 144	74.68 83	57.85 121	54.92 121	55.34 84	55.74 78	55.56 113	66.35 84	75.05 105	76.56 94	83.35 145	88.13 105

baseline2		71.22 81	73.01 78	69.13 87	75.76 107	86.34 66	71.23 108	62.78 85	62.62 86	52.85 90	57.32 75	54.31 118	63.27 100	79.74 66	79.31 69	88.89 15	91.43 64

TAPA-MVS	67.10 9	71.45 78	73.47 76	69.10 88	77.04 96	80.78 114	73.81 92	62.10 87	80.80 39	51.28 95	60.91 66	63.80 72	67.98 77	74.59 110	72.42 147	82.37 161	80.97 156
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
IB-MVS	64.48 11	69.02 90	68.97 101	69.09 89	81.75 64	89.01 37	64.50 149	64.91 65	56.65 108	62.59 52	47.89 107	45.23 143	51.99 153	69.18 168	81.88 40	88.77 18	92.93 52
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
TSAR-MVS + COLMAP		73.09 68	76.86 57	68.71 90	74.97 114	82.49 98	74.51 89	61.83 91	83.16 29	49.31 106	82.22 22	51.62 129	68.94 74	78.76 75	75.52 109	82.67 156	84.23 134

FMVSNet3		70.41 84	71.89 83	68.68 91	70.89 136	79.42 126	75.63 74	60.97 100	65.32 80	51.06 96	47.37 111	62.05 75	64.90 90	82.49 36	82.27 36	88.64 23	84.34 133

GeoE		68.96 91	69.32 97	68.54 92	76.61 100	83.12 92	71.78 100	56.87 136	60.21 96	54.86 85	45.95 124	54.79 117	64.27 93	74.59 110	75.54 108	86.84 68	91.01 71

HyFIR lowres test		68.39 95	68.28 106	68.52 93	80.85 69	88.11 47	71.08 112	58.09 116	54.87 123	47.80 112	27.55 197	55.80 110	64.97 89	79.11 71	79.14 71	88.31 33	93.35 47

CANet_DTU		72.84 70	76.63 61	68.43 94	76.81 98	86.62 63	75.54 77	54.71 160	72.06 61	43.54 127	67.11 45	58.46 96	72.40 47	81.13 57	80.82 60	87.57 48	90.21 81

thres100view900		67.14 107	66.09 121	68.38 95	77.70 88	83.84 88	74.52 88	66.33 56	49.16 140	43.40 129	43.24 127	41.34 151	62.59 103	79.31 69	75.92 102	85.73 94	89.81 84

tpm cat1		67.47 103	67.05 113	67.98 96	76.63 99	81.51 105	74.49 90	47.65 184	61.18 91	61.12 61	42.51 134	53.02 127	64.74 92	70.11 162	71.50 153	83.22 148	89.49 88

GBi-Net		69.21 87	70.40 92	67.81 97	69.49 141	78.65 131	74.54 85	60.97 100	65.32 80	51.06 96	47.37 111	62.05 75	63.43 97	77.49 82	78.22 80	87.37 51	83.73 136

test1		69.21 87	70.40 92	67.81 97	69.49 141	78.65 131	74.54 85	60.97 100	65.32 80	51.06 96	47.37 111	62.05 75	63.43 97	77.49 82	78.22 80	87.37 51	83.73 136

Fast-Effi-MVS+		67.59 100	67.56 110	67.62 99	73.67 119	81.14 110	71.12 111	54.79 159	58.88 100	50.61 101	46.70 121	47.05 139	69.12 73	76.06 97	76.44 95	86.43 74	86.65 114

ET-MVSNet_ETH3D		71.38 79	74.70 70	67.51 100	51.61 206	88.06 49	77.29 68	60.95 103	63.61 85	48.36 109	66.60 48	60.67 85	79.55 10	73.56 124	80.58 62	87.30 56	89.80 85

FMVSNet2		68.06 98	68.57 103	67.45 101	69.49 141	78.65 131	74.54 85	60.23 109	56.29 111	49.64 105	42.13 138	57.08 104	63.43 97	81.15 56	80.99 55	87.37 51	83.73 136

LS3D		64.54 123	62.14 147	67.34 102	80.85 69	75.79 157	69.99 118	65.87 58	60.77 93	44.35 124	42.43 136	45.95 142	65.01 88	69.88 163	68.69 173	77.97 190	71.43 188

tfpn200view9		65.90 112	64.96 125	67.00 103	77.70 88	81.58 103	71.71 103	62.94 82	49.16 140	43.40 129	43.24 127	41.34 151	61.42 111	76.24 94	74.63 117	84.84 119	88.52 101

thres200		65.58 113	64.74 127	66.56 104	77.52 93	81.61 101	73.44 93	62.95 80	46.23 152	42.45 136	42.76 129	41.18 153	58.12 132	76.24 94	75.59 106	84.89 117	89.58 87

thres400		65.18 118	64.44 129	66.04 105	76.40 102	82.63 95	71.52 105	64.27 68	44.93 158	40.69 144	41.86 139	40.79 157	58.12 132	77.67 81	74.64 116	85.26 107	88.56 100

tpmrst		67.15 106	68.12 108	66.03 106	76.21 103	80.98 111	71.27 107	45.05 190	60.69 94	50.63 100	46.95 119	54.15 120	65.30 87	71.80 145	71.77 151	87.72 43	90.48 78

IterMVS-LS		66.08 111	66.56 117	65.51 107	73.67 119	74.88 163	70.89 115	53.55 166	50.42 134	48.32 110	50.59 98	55.66 111	61.83 108	73.93 119	74.42 121	84.82 122	86.01 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thisisatest0530		68.38 96	70.98 89	65.35 108	72.61 124	84.42 81	68.21 130	57.98 117	59.77 97	50.80 99	54.63 83	58.48 95	57.92 134	76.99 89	77.47 86	84.60 127	85.07 127

Effi-MVS+-dtu		64.58 121	64.08 130	65.16 109	73.04 123	75.17 162	70.68 117	56.23 141	54.12 126	44.71 123	47.42 110	51.10 130	63.82 96	68.08 171	66.32 182	82.47 160	86.38 117

dps		64.08 125	63.22 135	65.08 110	75.27 112	79.65 123	66.68 142	46.63 188	56.94 106	55.67 80	43.96 126	43.63 148	64.00 94	69.50 167	69.82 168	82.25 163	79.02 163

tttt0517		67.99 99	70.61 91	64.94 111	71.94 129	83.96 87	67.62 134	57.98 117	59.30 99	49.90 104	54.50 86	57.98 102	57.92 134	76.48 92	77.47 86	84.24 134	84.58 130

PMMVS		70.37 85	75.06 68	64.90 112	71.46 130	81.88 99	64.10 151	55.64 147	71.31 63	46.69 113	70.69 40	58.56 93	69.53 67	79.03 72	75.63 105	81.96 166	88.32 103

EPMVS		66.21 109	67.49 111	64.73 113	75.81 106	84.20 86	68.94 126	44.37 194	61.55 90	48.07 111	49.21 103	54.87 116	62.88 101	71.82 144	71.40 157	88.28 34	79.37 162

v2v482		63.68 129	62.85 141	64.65 114	68.01 150	80.46 117	71.90 98	57.60 124	44.26 160	42.82 134	39.80 151	38.62 167	61.56 110	73.06 129	74.86 113	86.03 85	88.90 97

thres600view7		63.77 128	63.14 136	64.51 115	75.49 111	81.61 101	69.59 122	62.95 80	43.96 162	38.90 151	41.09 143	40.24 162	55.25 146	76.24 94	71.54 152	84.89 117	87.30 109

v8		63.44 131	62.58 143	64.43 116	68.28 149	78.07 137	71.82 99	54.85 157	46.70 150	45.20 119	39.40 152	40.91 156	60.54 116	72.85 133	74.39 122	85.92 87	85.76 124

ACMH+	60.36 13	61.16 149	58.38 169	64.42 117	77.37 95	74.35 168	68.45 128	62.81 84	45.86 154	38.48 153	35.71 173	37.35 171	59.81 121	67.24 173	69.80 170	79.58 183	78.32 165

ACMH	59.42 14	61.59 148	59.22 167	64.36 118	78.92 81	78.26 136	67.65 133	67.48 48	39.81 178	30.98 184	38.25 157	34.59 187	61.37 113	70.55 157	73.47 131	79.74 182	79.59 160
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test-LLR		68.23 97	71.61 85	64.28 119	71.37 131	81.32 108	63.98 154	61.03 98	58.62 101	42.96 132	52.74 91	61.65 79	57.74 137	75.64 101	78.09 83	88.61 24	93.21 48

PatchMatch-RL		62.22 143	60.69 157	64.01 120	68.74 146	75.75 158	59.27 175	60.35 107	56.09 113	53.80 88	47.06 117	36.45 176	64.80 91	68.22 170	67.22 177	77.10 192	74.02 176

FMVSNet1		63.48 130	63.07 137	63.97 121	65.31 169	76.37 153	71.77 102	57.90 120	43.32 164	45.66 116	35.06 178	49.43 134	58.57 130	77.49 82	78.22 80	84.59 128	81.60 155

pmmvs4		63.14 132	62.46 144	63.94 122	66.03 165	76.40 152	66.82 141	57.60 124	56.74 107	50.26 103	40.81 146	37.51 170	59.26 126	71.75 146	71.48 154	83.68 143	82.53 147

v10		63.00 134	62.22 146	63.90 123	67.88 152	77.78 141	71.59 104	54.34 161	45.37 156	42.76 135	38.53 154	38.93 165	61.05 114	74.39 114	74.52 120	85.75 91	86.04 120

v1144		63.00 134	62.39 145	63.70 124	67.72 153	80.27 118	71.23 108	56.40 137	42.51 165	40.81 143	38.12 159	37.73 168	60.42 118	74.46 112	74.55 119	85.64 102	89.12 93

tpm		64.85 119	66.02 122	63.48 125	74.52 116	78.38 134	70.98 114	44.99 192	51.61 131	43.28 131	47.66 109	53.18 125	60.57 115	70.58 156	71.30 160	86.54 72	89.45 90

EPP-MVSNet		67.58 101	71.10 88	63.48 125	75.71 108	83.35 90	66.85 140	57.83 122	53.02 128	41.15 141	55.82 77	67.89 57	56.01 143	74.40 113	72.92 143	83.33 146	90.30 80

GA-MVS		64.55 122	65.76 124	63.12 127	69.68 140	81.56 104	69.59 122	58.16 115	45.23 157	35.58 169	47.01 118	41.82 150	59.41 124	79.62 67	78.54 76	86.32 75	86.56 115

v1192		62.25 140	61.64 150	62.96 128	66.88 158	79.72 122	69.96 119	55.77 145	41.58 170	39.42 147	37.05 164	35.96 181	60.50 117	74.30 117	74.09 124	85.24 108	88.76 98

v148		62.00 145	61.19 154	62.96 128	67.46 156	79.49 125	67.87 131	57.66 123	42.30 166	45.02 121	38.20 158	38.89 166	54.77 147	69.83 164	72.60 146	84.96 113	87.01 111

MDTV_nov1_ep13		65.21 117	67.28 112	62.79 130	70.91 135	81.72 100	69.28 125	49.50 178	58.08 103	43.94 126	50.50 99	56.02 108	58.86 129	70.72 153	73.37 133	84.24 134	80.52 158

PatchmatchNet		65.43 116	67.71 109	62.78 131	73.49 121	82.83 94	66.42 145	45.40 189	60.40 95	45.27 118	49.22 102	57.60 103	60.01 120	70.61 154	71.38 158	86.08 84	81.91 153
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
UGNet		67.57 102	71.69 84	62.76 132	69.88 139	82.58 96	66.43 144	58.64 112	54.71 124	51.87 93	61.74 62	62.01 78	45.46 176	74.78 109	74.99 111	84.24 134	91.02 70
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
V42		62.86 136	62.97 138	62.74 133	60.84 187	78.99 129	71.46 106	57.13 131	46.85 148	44.28 125	38.87 153	40.73 159	57.63 139	72.60 137	74.14 123	85.09 112	88.63 99

v144192		62.05 144	61.46 152	62.73 134	66.59 162	79.87 121	69.30 124	55.88 143	41.50 172	39.41 148	37.23 162	36.45 176	59.62 122	72.69 136	73.51 130	85.61 103	88.93 95

TESTMET0.1,1		67.38 104	71.61 85	62.45 135	66.05 164	81.32 108	63.98 154	55.36 152	58.62 101	42.96 132	52.74 91	61.65 79	57.74 137	75.64 101	78.09 83	88.61 24	93.21 48

v1921920		61.66 147	61.10 155	62.31 136	66.32 163	79.57 124	68.41 129	55.49 150	41.03 173	38.69 152	36.64 170	35.27 184	59.60 123	73.23 127	73.41 132	85.37 105	88.51 102

CDS-MVSNet		64.22 124	65.89 123	62.28 137	70.05 138	80.59 115	69.91 121	57.98 117	43.53 163	46.58 114	48.22 105	50.76 131	46.45 171	75.68 100	76.08 100	82.70 155	86.34 118
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpnnormal		58.97 162	56.48 177	61.89 138	71.27 133	76.21 154	66.65 143	61.76 94	32.90 198	36.41 164	27.83 196	29.14 204	50.64 160	73.06 129	73.05 141	84.58 129	83.15 145

IS_MVSNet		67.29 105	71.98 81	61.82 139	76.92 97	84.32 85	65.90 147	58.22 114	55.75 116	39.22 149	54.51 85	62.47 74	45.99 174	78.83 74	78.52 77	84.70 125	89.47 89

v1240		61.09 150	60.55 159	61.72 140	65.92 167	79.28 127	67.16 139	54.91 156	39.79 179	38.10 155	36.08 172	34.64 186	59.15 127	72.86 132	73.36 134	85.10 110	87.84 106

EPNet_dtu		66.17 110	70.13 95	61.54 141	81.04 67	77.39 146	68.87 127	62.50 86	69.78 67	33.51 177	63.77 56	56.22 107	37.65 190	72.20 139	72.18 150	85.69 97	79.38 161
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+-dtu		63.05 133	64.72 128	61.11 142	71.21 134	76.81 150	70.72 116	43.13 199	52.51 130	35.34 170	46.55 122	46.36 140	61.40 112	71.57 148	71.44 155	84.84 119	87.79 107

UniMVSNet_NR-MVSNet		62.30 139	63.51 133	60.89 143	69.48 144	77.83 140	64.07 152	63.94 70	50.03 135	31.17 182	44.82 125	41.12 154	51.37 156	71.02 150	74.81 114	85.30 106	84.95 128

SCA		63.90 127	66.67 114	60.66 144	73.75 117	71.78 178	59.87 174	43.66 195	61.13 92	45.03 120	51.64 95	59.45 91	57.92 134	70.96 151	70.80 162	83.71 142	80.92 157

Vis-MVSNet		65.53 115	69.83 96	60.52 145	70.80 137	84.59 79	66.37 146	55.47 151	48.40 143	40.62 145	57.67 74	58.43 97	45.37 177	77.49 82	76.24 99	84.47 130	85.99 122
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UA-Net		64.62 120	68.23 107	60.42 146	77.53 92	81.38 106	60.08 173	57.47 127	47.01 147	44.75 122	60.68 67	71.32 47	41.84 184	73.27 126	72.25 149	80.83 176	71.68 186

CMPMVS	43.63 17	57.67 171	55.43 179	60.28 147	72.01 127	79.00 128	62.77 164	53.23 168	41.77 169	45.42 117	30.74 190	39.03 164	53.01 151	64.81 182	64.65 188	75.26 197	68.03 195
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
NR-MVSNet		61.08 151	62.09 148	59.90 148	71.96 128	75.87 155	63.60 158	61.96 88	49.31 138	27.95 187	42.76 129	33.85 191	48.82 163	74.35 115	74.05 126	85.13 109	84.45 131

IterMVS		61.87 146	63.55 132	59.90 148	67.29 157	72.20 175	67.34 138	48.56 180	47.48 146	37.86 158	47.07 116	48.27 135	54.08 149	72.12 141	73.71 128	84.30 133	83.99 135
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DU-MVS		60.87 152	61.82 149	59.76 150	66.69 159	75.87 155	64.07 152	61.96 88	49.31 138	31.17 182	42.76 129	36.95 173	51.37 156	69.67 165	73.20 140	83.30 147	84.95 128

EG-PatchMatch MVS		58.73 165	58.03 172	59.55 151	72.32 125	80.49 116	63.44 160	55.55 149	32.49 199	38.31 154	28.87 194	37.22 172	42.84 182	74.30 117	75.70 104	84.84 119	77.14 168

CR-MVSNet		62.31 138	64.75 126	59.47 152	68.63 147	71.29 181	67.53 135	43.18 197	55.83 114	41.40 138	41.04 144	55.85 109	57.29 140	72.76 134	73.27 137	78.77 187	83.23 143

UniMVSNet_ETH3D		57.83 168	56.46 178	59.43 153	63.24 178	73.22 172	67.70 132	55.58 148	36.17 190	36.84 161	32.64 183	35.14 185	51.50 155	65.81 176	69.81 169	81.73 168	82.44 150

TranMVSNet+NR-MVSNet		60.38 155	61.30 153	59.30 154	68.34 148	75.57 161	63.38 161	63.78 72	46.74 149	27.73 188	42.56 133	36.84 174	47.66 166	70.36 159	74.59 118	84.91 116	82.46 148

USDC		59.69 158	60.03 163	59.28 155	64.04 174	71.84 176	63.15 163	55.36 152	54.90 122	35.02 171	48.34 104	29.79 203	58.16 131	70.60 155	71.33 159	79.99 180	73.42 180

pmmvs5		59.72 157	60.24 161	59.11 156	62.77 181	77.33 147	63.17 162	54.00 163	40.21 177	37.23 159	40.41 147	35.99 180	51.75 154	72.55 138	72.74 145	85.72 96	82.45 149

TransMVSNet (Re)		57.83 168	56.90 175	58.91 157	72.26 126	74.69 166	63.57 159	61.42 96	32.30 200	32.65 178	33.97 180	35.96 181	39.17 188	73.84 122	72.84 144	84.37 132	74.69 174

pm-mvs1		59.21 161	59.58 166	58.77 158	67.97 151	77.07 149	64.12 150	57.20 129	34.73 195	36.86 160	35.34 175	40.54 161	43.34 181	74.32 116	73.30 136	83.13 152	81.77 154

Baseline_NR-MVSNet		59.47 159	60.28 160	58.54 159	66.69 159	73.90 169	61.63 168	62.90 83	49.15 142	26.87 189	35.18 177	37.62 169	48.20 164	69.67 165	73.61 129	84.92 114	82.82 146

test-mter		64.06 126	69.24 98	58.01 160	59.07 193	77.40 145	59.13 176	48.11 182	55.64 117	39.18 150	51.56 96	58.54 94	55.38 145	73.52 125	76.00 101	87.22 60	92.05 61

UniMVSNet (Re)		60.62 153	62.93 140	57.92 161	67.64 154	77.90 139	61.75 167	61.24 97	49.83 137	29.80 186	42.57 132	40.62 160	43.36 180	70.49 158	73.27 137	83.76 140	85.81 123

gg-mvs-nofinetune		62.34 137	66.19 120	57.86 162	76.15 104	88.61 40	71.18 110	41.24 207	25.74 210	13.16 212	22.91 204	63.97 71	54.52 148	85.06 16	85.25 10	90.92 3	91.78 63

thisisatest0515		59.37 160	60.68 158	57.84 163	64.39 173	75.65 160	58.56 178	53.86 164	41.55 171	42.12 137	40.40 148	39.59 163	47.09 169	71.69 147	73.79 127	81.02 174	82.08 152

COLMAP_ROB	51.17 15	55.13 175	52.90 188	57.73 164	73.47 122	67.21 191	62.13 165	55.82 144	47.83 144	34.39 173	31.60 187	34.24 188	44.90 178	63.88 187	62.52 195	75.67 195	63.02 204
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v7n		57.04 173	56.64 176	57.52 165	62.85 180	74.75 165	61.76 166	51.80 174	35.58 194	36.02 167	32.33 185	33.61 192	50.16 161	67.73 172	70.34 167	82.51 158	82.12 151

ADS-MVSNet		58.40 167	59.16 168	57.52 165	65.80 168	74.57 167	60.26 171	40.17 208	50.51 133	38.01 156	40.11 150	44.72 144	59.36 125	64.91 180	66.55 180	81.53 170	72.72 184

FMVSNet5		58.86 163	60.24 161	57.25 167	52.66 205	66.25 193	63.77 157	52.86 171	57.85 105	37.92 157	36.12 171	52.22 128	51.37 156	70.88 152	71.43 156	84.92 114	66.91 197

CHOSEN 280x420		62.23 142	66.57 116	57.17 168	59.88 190	68.92 187	61.20 170	42.28 201	54.17 125	39.57 146	47.78 108	64.97 66	62.68 102	73.85 121	69.52 171	77.43 191	86.75 113

IterMVS-SCA-FT		60.21 156	62.97 138	57.00 169	66.64 161	71.84 176	67.53 135	46.93 187	47.56 145	36.77 163	46.85 120	48.21 136	52.51 152	70.36 159	72.40 148	71.63 205	83.53 139

pmmvs-eth3d		55.20 174	53.95 183	56.65 170	57.34 199	67.77 189	57.54 180	53.74 165	40.93 174	41.09 142	31.19 189	29.10 205	49.07 162	65.54 177	67.28 176	81.14 172	75.81 169

PatchT		60.46 154	63.85 131	56.51 171	65.95 166	75.68 159	47.34 196	41.39 204	53.89 127	41.40 138	37.84 160	50.30 133	57.29 140	72.76 134	73.27 137	85.67 98	83.23 143

TAMVS		58.86 163	60.91 156	56.47 172	62.38 183	77.57 143	58.97 177	52.98 169	38.76 182	36.17 165	42.26 137	47.94 137	46.45 171	70.23 161	70.79 163	81.86 167	78.82 164

TinyColmap		52.66 186	50.09 197	55.65 173	59.72 191	64.02 201	57.15 181	52.96 170	40.28 176	32.51 179	32.42 184	20.97 214	56.65 142	63.95 186	65.15 187	74.91 198	63.87 202

MIMVSNet		57.78 170	59.71 165	55.53 174	54.79 201	77.10 148	63.89 156	45.02 191	46.59 151	36.79 162	28.36 195	40.77 158	45.84 175	74.97 106	76.58 93	86.87 67	73.60 179

pmmvs6		54.20 182	53.54 184	54.97 175	63.22 179	72.98 173	60.17 172	52.32 173	26.77 209	34.30 174	23.29 203	36.23 178	40.33 187	68.77 169	68.76 172	79.47 185	78.00 166

MVS-HIRNet		53.86 184	53.02 186	54.85 176	60.30 189	72.36 174	44.63 204	42.20 202	39.45 180	43.47 128	21.66 207	34.00 190	55.47 144	65.42 178	67.16 178	83.02 153	71.08 190

Vis-MVSNet (Re-imp)		62.25 140	68.74 102	54.68 177	73.70 118	78.74 130	56.51 182	57.49 126	55.22 118	26.86 190	54.56 84	61.35 81	31.06 192	73.10 128	74.90 112	82.49 159	83.31 140

TDRefinement		52.70 185	51.02 194	54.66 178	57.41 198	65.06 197	61.47 169	54.94 154	44.03 161	33.93 175	30.13 192	27.57 206	46.17 173	61.86 189	62.48 196	74.01 201	66.06 198

pmnet_mix02		53.92 183	53.30 185	54.65 179	61.89 184	71.33 180	54.54 186	54.17 162	40.38 175	34.65 172	34.76 179	30.68 202	40.44 186	60.97 190	63.71 190	82.19 164	71.24 189

test0.0.03 1		57.35 172	59.89 164	54.38 180	71.37 131	73.45 171	52.71 188	61.03 98	46.11 153	26.33 191	41.73 140	44.08 146	29.72 194	71.43 149	70.90 161	85.10 110	71.56 187

MDTV_nov1_ep13_2view		54.47 181	54.61 180	54.30 181	60.50 188	73.82 170	57.92 179	43.38 196	39.43 181	32.51 179	33.23 181	34.05 189	47.26 168	62.36 188	66.21 183	84.24 134	73.19 182

RPMNet		58.63 166	62.80 142	53.76 182	67.59 155	71.29 181	54.60 185	38.13 209	55.83 114	35.70 168	41.58 141	53.04 126	47.89 165	66.10 175	67.38 175	78.65 189	84.40 132

anonymousdsp		54.99 177	57.24 174	52.36 183	53.82 203	71.75 179	51.49 189	48.14 181	33.74 196	33.66 176	38.34 156	36.13 179	47.54 167	64.53 184	70.60 165	79.53 184	85.59 126

RPSCF		55.07 176	58.06 171	51.57 184	48.87 209	58.95 206	53.68 187	41.26 206	62.42 87	45.88 115	54.38 87	54.26 119	53.75 150	57.15 197	53.53 207	66.01 207	65.75 199

Anonymous20231206		52.23 187	52.80 189	51.56 185	64.70 172	69.41 185	51.01 190	58.60 113	36.63 187	22.44 197	21.80 206	31.42 198	30.52 193	66.79 174	67.83 174	82.10 165	75.73 170

gm-plane-assit		54.99 177	57.99 173	51.49 186	69.27 145	54.42 210	32.32 213	42.59 200	21.18 214	13.71 210	23.61 201	43.84 147	60.21 119	87.09 5	86.55 5	90.81 4	89.28 91

CVMVSNet		54.92 179	58.16 170	51.13 187	62.61 182	68.44 188	55.45 184	52.38 172	42.28 167	21.45 198	47.10 115	46.10 141	37.96 189	64.42 185	63.81 189	76.92 193	75.01 173

PM-MVS		50.11 192	50.38 196	49.80 188	47.23 211	62.08 204	50.91 191	44.84 193	41.90 168	36.10 166	35.22 176	26.05 210	46.83 170	57.64 195	55.42 206	72.90 202	74.32 175

SixPastTwentyTwo		49.11 196	49.22 199	48.99 189	58.54 197	64.14 200	47.18 197	47.75 183	31.15 202	24.42 193	41.01 145	26.55 208	44.04 179	54.76 204	58.70 201	71.99 204	68.21 193

PEN-MVS		51.04 188	52.94 187	48.82 190	61.45 186	66.00 194	48.68 193	57.20 129	36.87 185	15.36 206	36.98 165	32.72 193	28.77 198	57.63 196	66.37 181	81.44 171	74.00 177

LTVRE_ROB	47.26 16	49.41 195	49.91 198	48.82 190	64.76 171	69.79 184	49.05 192	47.12 186	20.36 216	16.52 204	36.65 169	26.96 207	50.76 159	60.47 191	63.16 193	64.73 208	72.00 185
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
N_pmnet		47.67 198	47.00 202	48.45 192	54.72 202	62.78 202	46.95 198	51.25 175	36.01 192	26.09 192	26.59 199	25.93 211	35.50 191	55.67 203	59.01 199	76.22 194	63.04 203

CP-MVSNet		50.57 190	52.60 191	48.21 193	58.77 195	65.82 195	48.17 194	56.29 139	37.41 184	16.59 203	37.14 163	31.95 195	29.21 195	56.60 199	63.71 190	80.22 178	75.56 171

PS-CasMVS		50.17 191	52.02 192	48.02 194	58.60 196	65.54 196	48.04 195	56.19 142	36.42 189	16.42 205	35.68 174	31.33 199	28.85 197	56.42 201	63.54 192	80.01 179	75.18 172

DTE-MVSNet		49.82 193	51.92 193	47.37 195	61.75 185	64.38 199	45.89 202	57.33 128	36.11 191	12.79 213	36.87 166	31.93 196	25.73 201	58.01 194	65.22 186	80.75 177	70.93 191

WR-MVS		51.02 189	54.56 181	46.90 196	63.84 175	69.23 186	44.78 203	56.38 138	38.19 183	14.19 208	37.38 161	36.82 175	22.39 204	60.14 192	66.20 184	79.81 181	73.95 178

MDA-MVSNet-bldmvs		44.15 202	42.27 207	46.34 197	38.34 213	62.31 203	46.28 199	55.74 146	29.83 203	20.98 199	27.11 198	16.45 219	41.98 183	41.11 211	57.47 202	74.72 199	61.65 207

testgi		48.51 197	50.53 195	46.16 198	64.78 170	67.15 192	41.54 206	54.81 158	29.12 205	17.03 202	32.07 186	31.98 194	20.15 208	65.26 179	67.00 179	78.67 188	61.10 208

WR-MVS_H		49.62 194	52.63 190	46.11 199	58.80 194	67.58 190	46.14 201	54.94 154	36.51 188	13.63 211	36.75 168	35.67 183	22.10 205	56.43 200	62.76 194	81.06 173	72.73 183

test20.03		47.23 200	48.69 200	45.53 200	63.28 177	64.39 198	41.01 207	56.93 134	29.16 204	15.21 207	23.90 200	30.76 201	17.51 211	64.63 183	65.26 185	79.21 186	62.71 205

FPMVS		39.11 206	36.39 208	42.28 201	55.97 200	45.94 213	46.23 200	41.57 203	35.73 193	22.61 195	23.46 202	19.82 216	28.32 199	43.57 208	40.67 210	58.96 211	45.54 211

pmmvs3		41.86 204	42.29 206	41.36 202	39.80 212	52.66 211	38.93 210	35.85 213	23.40 213	20.22 200	19.30 208	20.84 215	40.56 185	55.98 202	58.79 200	72.80 203	65.03 200

new-patchmatchnet		42.21 203	42.97 204	41.33 203	53.05 204	59.89 205	39.38 208	49.61 177	28.26 207	12.10 214	22.17 205	21.54 213	19.22 209	50.96 206	56.04 204	74.61 200	61.92 206

EU-MVSNet		44.84 201	47.85 201	41.32 204	49.26 208	56.59 209	43.07 205	47.64 185	33.03 197	13.82 209	36.78 167	30.99 200	24.37 202	53.80 205	55.57 205	69.78 206	68.21 193

FC-MVSNet-test		47.24 199	54.37 182	38.93 205	59.49 192	58.25 208	34.48 212	53.36 167	45.66 155	6.66 218	50.62 97	42.02 149	16.62 212	58.39 193	61.21 197	62.99 209	64.40 201

MIMVSNet1		40.84 205	43.46 203	37.79 206	32.14 214	58.92 207	39.24 209	50.83 176	27.00 208	11.29 215	16.76 213	26.53 209	17.75 210	57.14 198	61.12 198	75.46 196	56.78 209

PMVS	27.44 18	32.08 208	29.07 211	35.60 207	48.33 210	24.79 216	26.97 215	41.34 205	20.45 215	22.50 196	17.11 212	18.64 217	20.44 207	41.99 210	38.06 211	54.02 213	42.44 212
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		33.19 207	35.52 209	30.47 208	27.55 218	45.31 214	29.29 214	30.92 214	29.00 206	9.88 217	18.77 209	17.64 218	26.77 200	44.07 207	45.98 209	58.41 212	47.87 210

GG-mvs-BLEND		54.54 180	77.58 50	27.67 209	0.03 223	90.09 30	77.20 69	0.02 220	66.83 75	0.05 224	59.90 70	73.33 37	0.04 219	78.40 78	79.30 70	88.65 22	95.20 27

Gipuma		24.91 210	24.61 212	25.26 210	31.47 215	21.59 217	18.06 217	37.53 210	25.43 211	10.03 216	4.18 219	4.25 223	14.85 213	43.20 209	47.03 208	39.62 215	26.55 216
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		28.15 209	34.48 210	20.76 211	6.76 222	21.18 218	21.03 216	18.41 217	36.77 186	17.52 201	15.67 214	31.63 197	24.05 203	41.03 212	26.69 214	36.82 216	68.38 192

E-PMN		15.08 212	11.65 215	19.08 212	28.73 216	12.31 221	6.95 222	36.87 212	10.71 219	3.63 221	5.13 216	2.22 226	13.81 215	11.34 217	18.50 216	24.49 218	21.32 217

EMVS		14.40 213	10.71 216	18.70 213	28.15 217	12.09 222	7.06 221	36.89 211	11.00 218	3.56 222	4.95 217	2.27 225	13.91 214	10.13 218	16.06 217	22.63 219	18.51 218

PMMVS2		20.45 211	22.31 213	18.27 214	20.52 219	26.73 215	14.85 219	28.43 216	13.69 217	0.79 223	10.35 215	9.10 220	3.83 218	27.64 214	32.87 212	41.17 214	35.81 213

tmp_tt				16.09 215	13.07 220	8.12 223	13.61 220	2.08 219	55.09 119	30.10 185	40.26 149	22.83 212	5.35 217	29.91 213	25.25 215	32.33 217

MVE	15.98 19	14.37 214	16.36 214	12.04 216	7.72 221	20.24 219	5.90 223	29.05 215	8.28 220	3.92 220	4.72 218	2.42 224	9.57 216	18.89 216	31.46 213	16.07 221	28.53 215
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		0.05 215	0.08 217	0.01 217	0.00 224	0.01 224	0.03 225	0.01 221	0.05 221	0.00 225	0.14 221	0.01 227	0.03 221	0.05 219	0.05 218	0.01 222	0.24 220

test123		0.05 215	0.08 217	0.01 217	0.00 224	0.01 224	0.01 226	0.00 222	0.05 221	0.00 225	0.16 220	0.00 228	0.04 219	0.02 220	0.05 218	0.00 223	0.26 219

uanet_test		0.00 217	0.00 219	0.00 219	0.00 224	0.00 226	0.00 227	0.00 222	0.00 223	0.00 225	0.00 222	0.00 228	0.00 222	0.00 221	0.00 220	0.00 223	0.00 221

sosnet-low-res		0.00 217	0.00 219	0.00 219	0.00 224	0.00 226	0.00 227	0.00 222	0.00 223	0.00 225	0.00 222	0.00 228	0.00 222	0.00 221	0.00 220	0.00 223	0.00 221

sosnet		0.00 217	0.00 219	0.00 219	0.00 224	0.00 226	0.00 227	0.00 222	0.00 223	0.00 225	0.00 222	0.00 228	0.00 222	0.00 221	0.00 220	0.00 223	0.00 221

RE-MVS-def										31.47 181

9.14												84.47 7

SR-MVS					86.33 48			67.54 47				80.78 20

Anonymous202405211			66.35 119		78.00 87	84.41 82	74.85 82	63.18 77	51.00 132		31.37 188	53.73 123	69.67 66	76.28 93	76.84 90	83.21 150	90.85 72

our_test_3					63.32 176	71.07 183	55.90 183

ambc			42.30 205		50.36 207	49.51 212	35.47 211		32.04 201	23.53 194	17.36 210	8.95 221	29.06 196	64.88 181	56.26 203	61.29 210	67.12 196

MTAPA										78.32 12		79.42 25

MTMP										76.04 17		76.65 30

Patchmatch-RL test							2.17 224

XVS					82.43 57	86.27 67	75.70 72			61.07 62		72.27 40				85.67 98

X-MVStestdata					82.43 57	86.27 67	75.70 72			61.07 62		72.27 40				85.67 98

mPP-MVS					86.96 43							70.61 50

NP-MVS									81.60 37

Patchmtry						78.06 138	67.53 135	43.18 197		41.40 138

DeepMVS_CX						19.81 220	17.01 218	10.02 218	23.61 212	5.85 219	17.21 211	8.03 222	21.13 206	22.60 215		21.42 220	30.01 214

High-resolution multi-view benchmark