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.

xxxxxxxxxxxxxcwj		84.33 14	83.20 26	85.64 2	94.57 1	94.55 3	91.01 1	79.94 1	89.15 11	79.85 6	92.37 3	44.71 144	79.75 7	83.52 26	82.72 32	88.75 19	95.37 24

SF-MVS		87.30 5	88.71 5	85.64 2	94.57 1	94.55 3	91.01 1	79.94 1	89.15 11	79.85 6	92.37 3	83.29 9	79.75 7	83.52 26	82.72 32	88.75 19	95.37 24

DPM-MVS		85.41 10	86.72 15	83.89 10	91.66 12	91.92 14	90.49 3	78.09 4	86.90 18	73.95 20	74.52 34	82.01 15	79.29 12	90.24 1	90.65 1	89.86 6	90.78 72

DPE-MVS		87.60 4	90.44 4	84.29 7	92.09 8	93.44 5	88.69 4	75.11 9	93.06 5	80.80 5	94.23 2	86.70 3	81.44 5	84.84 17	83.52 26	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
SED-MVS		88.94 1	90.98 1	86.56 1	92.53 6	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

APDe-MVS		86.37 6	88.41 7	84.00 9	91.43 14	91.83 15	88.34 6	74.67 10	91.19 6	81.76 4	91.13 5	81.94 17	80.07 6	83.38 28	82.58 35	87.69 44	96.78 10

MSP-MVS		87.87 3	90.57 3	84.73 5	89.38 27	91.60 17	88.24 7	74.15 12	93.55 3	82.28 3	94.99 1	83.21 10	85.96 2	87.67 4	84.67 17	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 8	86.99 12	84.31 6	94.07 3	92.80 7	88.15 8	79.10 3	85.66 23	70.72 30	76.50 32	80.45 20	82.17 3	88.35 2	87.49 3	91.63 2	97.65 4

DVP-MVS		88.07 2	90.73 2	84.97 4	91.98 9	95.01 2	87.86 9	76.88 6	93.90 2	85.15 2	90.11 8	86.90 2	79.46 11	86.26 10	84.67 17	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
CNVR-MVS		85.96 7	87.58 10	84.06 8	92.58 5	92.40 10	87.62 10	77.77 5	88.44 14	75.93 17	79.49 25	81.97 16	81.65 4	87.04 6	86.58 4	88.79 17	97.18 7

CSCG		82.90 20	84.52 22	81.02 18	91.85 10	93.43 6	87.14 11	74.01 14	81.96 33	76.14 15	70.84 38	82.49 12	69.71 62	82.32 41	85.18 11	87.26 56	95.40 23

SMA-MVS		85.24 11	88.27 8	81.72 15	91.74 11	90.71 20	86.71 12	73.16 19	90.56 9	74.33 19	83.07 18	85.88 4	77.16 20	86.28 9	85.58 6	87.23 57	95.77 15
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		84.16 16	85.46 20	82.64 11	92.34 7	90.57 23	86.57 13	76.51 8	86.85 20	72.91 23	77.20 31	78.69 26	79.09 14	84.64 19	84.88 15	88.44 29	95.41 22

APD-MVS		84.83 12	87.00 11	82.30 13	89.61 25	89.21 34	86.51 14	73.64 16	90.98 7	77.99 12	89.89 9	80.04 23	79.18 13	82.00 46	81.37 48	86.88 65	95.49 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TSAR-MVS + ACMM		81.59 26	85.84 19	76.63 39	89.82 22	86.53 63	86.32 15	66.72 52	85.96 22	65.43 43	88.98 11	82.29 13	67.57 80	82.06 45	81.33 49	83.93 138	93.75 43

HPM-MVS++		85.64 9	88.43 6	82.39 12	92.65 4	90.24 26	85.83 16	74.21 11	90.68 8	75.63 18	86.77 13	84.15 7	78.68 16	86.33 8	85.26 9	87.32 53	95.60 19

SD-MVS		84.31 15	86.96 13	81.22 16	88.98 31	88.68 38	85.65 17	73.85 15	89.09 13	79.63 8	87.34 12	84.84 5	73.71 35	82.66 35	81.60 45	85.48 103	94.51 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 + MP.		84.39 13	86.58 16	81.83 14	88.09 39	86.47 64	85.63 18	73.62 17	90.13 10	79.24 9	89.67 10	82.99 11	77.72 18	81.22 52	80.92 58	86.68 69	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
train_agg		83.35 18	86.93 14	79.17 27	89.70 23	88.41 41	85.60 19	72.89 21	86.31 21	66.58 41	90.48 7	82.24 14	73.06 42	83.10 31	82.64 34	87.21 61	95.30 26

ACMMP_NAP		83.54 17	86.37 17	80.25 21	89.57 26	90.10 28	85.27 20	71.66 23	87.38 15	73.08 22	84.23 17	80.16 21	75.31 26	84.85 16	83.64 23	86.57 70	94.21 37

SteuartSystems-ACMMP		82.51 21	85.35 21	79.20 26	90.25 17	89.39 33	84.79 21	70.95 25	82.86 29	68.32 38	86.44 14	77.19 27	73.07 41	83.63 25	83.64 23	87.82 40	94.34 33
Skip Steuart: Steuart Systems R&D Blog.
MSLP-MVS++		78.57 38	77.33 51	80.02 22	88.39 34	84.79 76	84.62 22	66.17 56	75.96 54	78.40 10	61.59 60	71.47 45	73.54 39	78.43 75	78.88 72	88.97 14	90.18 80

HFP-MVS		82.48 22	84.12 23	80.56 19	90.15 18	87.55 54	84.28 23	69.67 34	85.22 24	77.95 13	84.69 16	75.94 30	75.04 28	81.85 47	81.17 52	86.30 76	92.40 55

CDPH-MVS		79.39 36	82.13 32	76.19 43	89.22 30	88.34 42	84.20 24	71.00 24	79.67 43	56.97 76	77.77 28	72.24 42	68.50 75	81.33 51	82.74 30	87.23 57	92.84 51

DELS-MVS		79.49 31	79.84 42	79.08 28	88.26 37	92.49 8	84.12 25	70.63 27	65.27 80	69.60 36	61.29 62	66.50 60	72.75 43	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
zzz-MVS		81.65 25	83.10 27	79.97 23	88.14 38	87.62 53	83.96 26	69.90 31	86.92 17	77.67 14	72.47 36	78.74 25	74.13 34	81.59 50	81.15 53	86.01 85	93.19 48

DeepC-MVS_fast	75.41 2	81.69 24	82.10 33	81.20 17	91.04 16	87.81 52	83.42 27	74.04 13	83.77 27	71.09 28	66.88 47	72.44 38	79.48 10	85.08 14	84.97 14	88.12 39	93.78 42
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS	74.46 3	80.30 30	81.05 36	79.42 24	87.42 41	88.50 40	83.23 28	73.27 18	82.78 30	71.01 29	62.86 57	69.93 51	74.80 30	84.30 20	84.20 20	86.79 68	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
ACMMPR		80.62 29	82.98 28	77.87 34	88.41 33	87.05 59	83.02 29	69.18 37	83.91 26	68.35 37	82.89 19	73.64 35	72.16 47	80.78 58	81.13 54	86.10 82	91.43 62

HQP-MVS		78.26 40	80.91 38	75.17 50	85.67 50	84.33 83	83.01 30	69.38 35	79.88 42	55.83 77	79.85 24	64.90 65	70.81 55	82.46 37	81.78 41	86.30 76	93.18 49

PGM-MVS		79.42 35	81.84 34	76.60 40	88.38 35	86.69 61	82.97 31	65.75 58	80.39 40	64.94 44	81.95 22	72.11 43	71.41 53	80.45 59	80.55 62	86.18 78	90.76 74

OPM-MVS		72.74 68	70.93 88	74.85 53	85.30 51	84.34 82	82.82 32	69.79 32	49.96 135	55.39 82	54.09 87	60.14 87	70.04 61	80.38 61	79.43 66	85.74 92	88.20 102

MP-MVS		80.94 27	83.49 25	77.96 32	88.48 32	88.16 45	82.82 32	69.34 36	80.79 39	69.67 34	82.35 20	77.13 28	71.60 52	80.97 57	80.96 57	85.87 89	94.06 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CP-MVS		79.44 32	81.51 35	77.02 38	86.95 43	85.96 70	82.00 34	68.44 42	81.82 34	67.39 39	77.43 29	73.68 34	71.62 51	79.56 67	79.58 65	85.73 93	92.51 54

CLD-MVS		77.36 48	77.29 52	77.45 37	82.21 60	88.11 46	81.92 35	68.96 39	77.97 48	69.62 35	62.08 58	59.44 90	73.57 38	81.75 48	81.27 50	88.41 30	90.39 77
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
3Dnovator	70.49 5	78.42 39	76.77 56	80.35 20	91.43 14	90.27 25	81.84 36	70.79 26	72.10 58	71.95 24	50.02 98	67.86 57	77.47 19	82.89 32	84.24 19	88.61 24	89.99 81

MVS_0304		79.43 33	82.20 31	76.20 42	84.22 53	91.79 16	81.82 37	63.81 70	76.83 52	61.71 56	66.37 49	75.52 31	76.38 24	85.54 13	85.03 13	89.28 11	94.32 34

PCF-MVS	70.85 4	75.73 55	76.55 59	74.78 54	83.67 54	88.04 50	81.47 38	70.62 29	69.24 69	57.52 74	60.59 67	69.18 53	70.65 57	77.11 85	77.65 83	84.75 123	94.01 40
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMMP		77.61 45	79.59 43	75.30 49	85.87 49	85.58 71	81.42 39	67.38 48	79.38 44	62.61 50	78.53 26	65.79 62	68.80 74	78.56 74	78.50 76	85.75 90	90.80 71
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
QAPM		77.50 46	77.43 50	77.59 36	91.52 13	92.00 13	81.41 40	70.63 27	66.22 73	58.05 71	54.70 80	71.79 44	74.49 33	82.46 37	82.04 37	89.46 10	92.79 53

canonicalmvs		77.65 44	79.59 43	75.39 47	81.52 64	89.83 32	81.32 41	60.74 103	80.05 41	66.72 40	68.43 42	65.09 63	74.72 32	78.87 71	82.73 31	87.32 53	92.16 56

CANet		80.90 28	82.93 29	78.53 31	86.83 45	92.26 11	81.19 42	66.95 49	81.60 36	69.90 33	66.93 46	74.80 32	76.79 21	84.68 18	84.77 16	89.50 9	95.50 20

TSAR-MVS + GP.		82.27 23	85.98 18	77.94 33	80.72 71	88.25 44	81.12 43	67.71 45	87.10 16	73.31 21	85.23 15	83.68 8	76.64 22	80.43 60	81.47 47	88.15 38	95.66 18

X-MVS		78.16 41	80.55 39	75.38 48	87.99 40	86.27 66	81.05 44	68.98 38	78.33 46	61.07 60	75.25 33	72.27 39	67.52 81	80.03 62	80.52 63	85.66 100	91.20 66

CPTT-MVS		75.43 56	77.13 54	73.44 59	81.43 65	82.55 95	80.96 45	64.35 66	77.95 49	61.39 57	69.20 41	70.94 47	69.38 69	73.89 119	73.32 134	83.14 150	92.06 58

PHI-MVS		79.43 33	84.06 24	74.04 56	86.15 48	91.57 18	80.85 46	68.90 40	82.22 32	51.81 91	78.10 27	74.28 33	70.39 59	84.01 23	84.00 21	86.14 80	94.24 35

DI_MVS_plusplus_trai		73.94 63	74.85 67	72.88 63	76.57 100	86.80 60	80.41 47	61.47 94	62.35 86	59.44 68	47.91 104	68.12 54	72.24 46	82.84 34	81.50 46	87.15 62	94.42 32

3Dnovator+	70.16 6	77.87 42	77.29 52	78.55 30	89.25 29	88.32 43	80.09 48	67.95 44	74.89 57	71.83 26	52.05 92	70.68 48	76.27 25	82.27 42	82.04 37	85.92 86	90.77 73

MVS_Test		75.22 57	76.69 57	73.51 58	79.30 77	88.82 37	80.06 49	58.74 111	69.77 65	57.50 75	59.78 70	61.35 79	75.31 26	82.07 44	83.60 25	90.13 5	91.41 64

AdaColmap		76.23 54	73.55 72	79.35 25	89.38 27	85.00 75	79.99 50	73.04 20	76.60 53	71.17 27	55.18 79	57.99 99	77.87 17	76.82 88	76.82 89	84.67 125	86.45 115

LGP-MVS_train		72.02 73	73.18 75	70.67 75	82.13 61	80.26 118	79.58 51	63.04 77	70.09 63	51.98 89	65.06 51	55.62 110	62.49 104	75.97 97	76.32 97	84.80 122	88.93 93

EPNet		79.28 37	82.25 30	75.83 45	88.31 36	90.14 27	79.43 52	68.07 43	81.76 35	61.26 58	77.26 30	70.08 50	70.06 60	82.43 39	82.00 39	87.82 40	92.09 57
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MAR-MVS		77.19 49	78.37 48	75.81 46	89.87 21	90.58 22	79.33 53	65.56 60	77.62 50	58.33 70	59.24 71	67.98 55	74.83 29	82.37 40	83.12 28	86.95 63	87.67 106
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
DeepPCF-MVS	76.94 1	83.08 19	87.77 9	77.60 35	90.11 19	90.96 19	78.48 54	72.63 22	93.10 4	65.84 42	80.67 23	81.55 18	74.80 30	85.94 12	85.39 8	83.75 140	96.77 11

casdiffmvs		75.20 58	75.69 63	74.63 55	79.26 78	89.07 35	78.47 55	63.59 73	67.05 71	63.79 47	55.72 77	60.32 85	73.58 37	82.16 43	81.78 41	89.08 13	93.72 44

diffmvs		74.32 60	75.42 64	73.04 62	75.60 108	87.27 56	78.20 56	62.96 78	68.66 70	61.89 54	59.79 69	59.84 88	71.80 49	78.30 78	79.87 64	87.80 42	94.23 36

MVSTER		76.92 50	79.92 41	73.42 60	74.98 112	82.97 91	78.15 57	63.41 74	78.02 47	64.41 46	67.54 43	72.80 37	71.05 54	83.29 30	83.73 22	88.53 27	91.12 67

OpenMVS	67.62 8	74.92 59	73.91 70	76.09 44	90.10 20	90.38 24	78.01 58	66.35 54	66.09 75	62.80 49	46.33 122	64.55 66	71.77 50	79.92 64	80.88 59	87.52 49	89.20 90

ACMP	68.86 7	72.15 72	72.25 77	72.03 67	80.96 67	80.87 112	77.93 59	64.13 68	69.29 67	60.79 63	64.04 53	53.54 122	63.91 94	73.74 122	75.27 109	84.45 130	88.98 92
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_part1		66.32 107	63.35 133	69.77 79	77.40 93	78.35 134	77.85 60	56.25 137	44.52 158	62.15 53	33.05 181	53.91 120	62.38 106	72.19 139	74.65 114	82.59 156	86.81 110

MS-PatchMatch		70.34 84	69.00 98	71.91 69	85.20 52	85.35 72	77.84 61	61.77 92	58.01 103	55.40 81	41.26 141	58.34 96	61.69 108	81.70 49	78.29 77	89.56 8	80.02 158

abl_6				79.06 29	89.68 24	92.14 12	77.70 62	69.68 33	86.87 19	71.88 25	74.29 35	80.06 22	76.56 23			88.84 16	95.82 14

ACMM	66.70 10	70.42 80	68.49 102	72.67 64	82.85 55	77.76 141	77.70 62	64.76 65	64.61 81	60.74 64	49.29 99	53.97 119	65.86 85	74.97 105	75.57 106	84.13 137	83.29 140
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MVS_111021_HR		77.42 47	78.40 47	76.28 41	86.95 43	90.68 21	77.41 64	70.56 30	66.21 74	62.48 52	66.17 50	63.98 67	72.08 48	82.87 33	83.15 27	88.24 35	95.71 17

ET-MVSNet_ETH3D		71.38 77	74.70 68	67.51 99	51.61 205	88.06 49	77.29 65	60.95 102	63.61 83	48.36 108	66.60 48	60.67 83	79.55 9	73.56 123	80.58 61	87.30 55	89.80 83

GG-mvs-BLEND		54.54 179	77.58 49	27.67 208	0.03 222	90.09 29	77.20 66	0.02 219	66.83 72	0.05 223	59.90 68	73.33 36	0.04 218	78.40 76	79.30 68	88.65 22	95.20 27

CostFormer		72.18 71	73.90 71	70.18 78	79.47 75	86.19 69	76.94 67	48.62 178	66.07 76	60.40 66	54.14 86	65.82 61	67.98 76	75.84 98	76.41 95	87.67 45	92.83 52

baseline1		71.47 75	72.02 78	70.82 73	80.56 72	84.51 79	76.61 68	66.93 50	56.22 111	48.66 106	55.40 78	60.43 84	62.55 103	83.35 29	80.99 55	89.60 7	83.28 141

CS-MVS		77.66 43	80.94 37	73.84 57	78.43 81	88.10 48	76.40 69	60.03 109	78.66 45	60.73 65	67.38 44	69.53 52	79.03 15	83.80 24	82.94 29	88.41 30	96.18 13

XVS					82.43 56	86.27 66	75.70 70			61.07 60		72.27 39				85.67 97

X-MVStestdata					82.43 56	86.27 66	75.70 70			61.07 60		72.27 39				85.67 97

CHOSEN 1792x2688		72.55 69	71.98 79	73.22 61	86.57 46	92.41 9	75.63 72	66.77 51	62.08 87	52.32 88	30.27 190	50.74 130	66.14 84	86.22 11	85.41 7	91.90 1	96.75 12

FMVSNet3		70.41 82	71.89 81	68.68 89	70.89 135	79.42 125	75.63 72	60.97 99	65.32 77	51.06 94	47.37 109	62.05 73	64.90 89	82.49 36	82.27 36	88.64 23	84.34 132

Effi-MVS+		70.42 80	71.23 85	69.47 81	78.04 85	85.24 73	75.57 74	58.88 110	59.56 96	48.47 107	52.73 91	54.94 113	69.69 63	78.34 77	77.06 87	86.18 78	90.73 75

CANet_DTU		72.84 67	76.63 58	68.43 92	76.81 97	86.62 62	75.54 75	54.71 159	72.06 59	43.54 126	67.11 45	58.46 94	72.40 45	81.13 55	80.82 60	87.57 48	90.21 79

PVSNet_BlendedMVS		76.84 51	78.47 45	74.95 51	82.37 58	89.90 30	75.45 76	65.45 61	74.99 55	70.66 31	63.07 55	58.27 97	67.60 78	84.24 21	81.70 43	88.18 36	97.10 8

PVSNet_Blended		76.84 51	78.47 45	74.95 51	82.37 58	89.90 30	75.45 76	65.45 61	74.99 55	70.66 31	63.07 55	58.27 97	67.60 78	84.24 21	81.70 43	88.18 36	97.10 8

OMC-MVS		74.03 62	75.82 62	71.95 68	79.56 74	80.98 110	75.35 78	63.21 75	84.48 25	61.83 55	61.54 61	66.89 58	69.41 68	76.60 89	74.07 124	82.34 161	86.15 118

Anonymous20231211		68.44 92	66.37 117	70.86 72	77.58 90	83.49 88	75.15 79	61.89 89	52.54 128	58.50 69	28.89 192	56.78 103	69.29 70	74.96 107	76.61 90	82.73 153	91.36 65

Anonymous202405211			66.35 118		78.00 86	84.41 81	74.85 80	63.18 76	51.00 131		31.37 187	53.73 121	69.67 64	76.28 91	76.84 88	83.21 149	90.85 70

DCV-MVSNet		69.13 87	69.07 97	69.21 83	77.65 89	77.52 143	74.68 81	57.85 121	54.92 120	55.34 83	55.74 76	55.56 111	66.35 83	75.05 104	76.56 92	83.35 144	88.13 103

baseline		72.89 66	74.46 69	71.07 71	75.99 104	87.50 55	74.57 82	60.49 105	70.72 62	57.60 73	60.63 65	60.97 81	70.79 56	75.27 103	76.33 96	86.94 64	89.79 84

GBi-Net		69.21 85	70.40 90	67.81 95	69.49 140	78.65 130	74.54 83	60.97 99	65.32 77	51.06 94	47.37 109	62.05 73	63.43 96	77.49 80	78.22 78	87.37 50	83.73 135

test1		69.21 85	70.40 90	67.81 95	69.49 140	78.65 130	74.54 83	60.97 99	65.32 77	51.06 94	47.37 109	62.05 73	63.43 96	77.49 80	78.22 78	87.37 50	83.73 135

FMVSNet2		68.06 96	68.57 101	67.45 100	69.49 140	78.65 130	74.54 83	60.23 108	56.29 110	49.64 104	42.13 137	57.08 102	63.43 96	81.15 54	80.99 55	87.37 50	83.73 135

thres100view900		67.14 106	66.09 120	68.38 93	77.70 87	83.84 87	74.52 86	66.33 55	49.16 139	43.40 128	43.24 126	41.34 150	62.59 102	79.31 68	75.92 101	85.73 93	89.81 82

TSAR-MVS + COLMAP		73.09 65	76.86 55	68.71 88	74.97 113	82.49 96	74.51 87	61.83 90	83.16 28	49.31 105	82.22 21	51.62 127	68.94 73	78.76 73	75.52 108	82.67 155	84.23 133

tpm cat1		67.47 102	67.05 112	67.98 94	76.63 98	81.51 103	74.49 88	47.65 183	61.18 89	61.12 59	42.51 133	53.02 125	64.74 91	70.11 161	71.50 152	83.22 147	89.49 86

MSDG		65.57 113	61.57 150	70.24 77	82.02 62	76.47 150	74.46 89	68.73 41	56.52 108	50.33 101	38.47 154	41.10 154	62.42 105	72.12 140	72.94 141	83.47 143	73.37 180

TAPA-MVS	67.10 9	71.45 76	73.47 74	69.10 86	77.04 95	80.78 113	73.81 90	62.10 86	80.80 38	51.28 92	60.91 63	63.80 70	67.98 76	74.59 109	72.42 146	82.37 160	80.97 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thres200		65.58 112	64.74 126	66.56 103	77.52 92	81.61 99	73.44 91	62.95 79	46.23 151	42.45 135	42.76 128	41.18 152	58.12 131	76.24 92	75.59 105	84.89 116	89.58 85

ETV-MVS		76.25 53	80.22 40	71.63 70	78.23 83	87.95 51	72.75 92	60.27 107	77.50 51	57.73 72	71.53 37	66.60 59	73.16 40	80.99 56	81.23 51	87.63 47	95.73 16

MVS_111021_LR		74.26 61	75.95 61	72.27 66	79.43 76	85.04 74	72.71 93	65.27 63	70.92 61	63.58 48	69.32 40	60.31 86	69.43 67	77.01 86	77.15 86	83.22 147	91.93 60

PLC	64.00 12	68.54 91	66.66 114	70.74 74	80.28 73	74.88 162	72.64 94	63.70 72	69.26 68	55.71 78	47.24 112	55.31 112	70.42 58	72.05 142	70.67 163	81.66 168	77.19 166
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CS-MVS-test		72.41 70	75.21 65	69.14 84	75.29 110	84.73 77	72.34 95	56.21 139	63.84 82	51.19 93	60.60 66	63.96 69	73.68 36	79.93 63	79.24 69	86.11 81	94.20 38

PVSNet_Blended_VisFu		71.76 74	73.54 73	69.69 80	79.01 79	87.16 58	72.05 96	61.80 91	56.46 109	59.66 67	53.88 88	62.48 71	59.08 127	81.17 53	78.90 71	86.53 72	94.74 29

v2v482		63.68 128	62.85 140	64.65 113	68.01 149	80.46 116	71.90 97	57.60 124	44.26 159	42.82 133	39.80 150	38.62 166	61.56 109	73.06 128	74.86 112	86.03 84	88.90 95

v8		63.44 130	62.58 142	64.43 115	68.28 148	78.07 136	71.82 98	54.85 155	46.70 149	45.20 118	39.40 151	40.91 155	60.54 115	72.85 132	74.39 121	85.92 86	85.76 123

GeoE		68.96 89	69.32 95	68.54 90	76.61 99	83.12 90	71.78 99	56.87 133	60.21 94	54.86 84	45.95 123	54.79 115	64.27 92	74.59 109	75.54 107	86.84 67	91.01 69

EIA-MVS		73.48 64	76.05 60	70.47 76	78.12 84	87.21 57	71.78 99	60.63 104	69.66 66	55.56 80	64.86 52	60.69 82	69.53 65	77.35 84	78.59 73	87.22 59	94.01 40

FMVSNet1		63.48 129	63.07 136	63.97 120	65.31 168	76.37 152	71.77 101	57.90 120	43.32 163	45.66 115	35.06 177	49.43 132	58.57 129	77.49 80	78.22 78	84.59 127	81.60 154

tfpn200view9		65.90 111	64.96 124	67.00 102	77.70 87	81.58 101	71.71 102	62.94 81	49.16 139	43.40 128	43.24 126	41.34 150	61.42 110	76.24 92	74.63 116	84.84 118	88.52 99

v10		63.00 133	62.22 145	63.90 122	67.88 151	77.78 140	71.59 103	54.34 160	45.37 155	42.76 134	38.53 153	38.93 164	61.05 113	74.39 113	74.52 119	85.75 90	86.04 119

thres400		65.18 117	64.44 128	66.04 104	76.40 101	82.63 93	71.52 104	64.27 67	44.93 157	40.69 143	41.86 138	40.79 156	58.12 131	77.67 79	74.64 115	85.26 106	88.56 98

V42		62.86 135	62.97 137	62.74 132	60.84 186	78.99 128	71.46 105	57.13 131	46.85 147	44.28 124	38.87 152	40.73 158	57.63 138	72.60 136	74.14 122	85.09 111	88.63 97

tpmrst		67.15 105	68.12 106	66.03 105	76.21 102	80.98 110	71.27 106	45.05 189	60.69 92	50.63 98	46.95 117	54.15 118	65.30 86	71.80 144	71.77 150	87.72 43	90.48 76

v1144		63.00 133	62.39 144	63.70 123	67.72 152	80.27 117	71.23 107	56.40 134	42.51 164	40.81 142	38.12 158	37.73 167	60.42 117	74.46 111	74.55 118	85.64 101	89.12 91

baseline2		71.22 79	73.01 76	69.13 85	75.76 106	86.34 65	71.23 107	62.78 84	62.62 84	52.85 87	57.32 73	54.31 116	63.27 99	79.74 65	79.31 67	88.89 15	91.43 62

gg-mvs-nofinetune		62.34 136	66.19 119	57.86 161	76.15 103	88.61 39	71.18 109	41.24 206	25.74 209	13.16 211	22.91 203	63.97 68	54.52 147	85.06 15	85.25 10	90.92 3	91.78 61

Fast-Effi-MVS+		67.59 98	67.56 108	67.62 97	73.67 117	81.14 108	71.12 110	54.79 157	58.88 98	50.61 99	46.70 119	47.05 137	69.12 71	76.06 95	76.44 93	86.43 73	86.65 112

DROMVSNet		67.59 98	67.56 108	67.62 97	73.67 117	81.14 108	71.12 110	54.79 157	58.88 98	50.61 99	46.70 119	47.05 137	69.12 71	76.06 95	76.44 93	86.43 73	86.65 112

HyFIR lowres test		68.39 93	68.28 104	68.52 91	80.85 68	88.11 46	71.08 112	58.09 116	54.87 122	47.80 111	27.55 196	55.80 108	64.97 88	79.11 69	79.14 70	88.31 33	93.35 45

CNLPA		71.37 78	70.27 92	72.66 65	80.79 70	81.33 105	71.07 113	65.75 58	82.36 31	64.80 45	42.46 134	56.49 104	72.70 44	73.00 130	70.52 165	80.84 174	85.76 123

tpm		64.85 118	66.02 121	63.48 124	74.52 114	78.38 133	70.98 114	44.99 191	51.61 130	43.28 130	47.66 107	53.18 123	60.57 114	70.58 155	71.30 159	86.54 71	89.45 88

IterMVS-LS		66.08 110	66.56 116	65.51 106	73.67 117	74.88 162	70.89 115	53.55 165	50.42 133	48.32 109	50.59 96	55.66 109	61.83 107	73.93 118	74.42 120	84.82 121	86.01 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Fast-Effi-MVS+-dtu		63.05 132	64.72 127	61.11 141	71.21 133	76.81 149	70.72 116	43.13 198	52.51 129	35.34 169	46.55 121	46.36 139	61.40 111	71.57 147	71.44 154	84.84 118	87.79 105

Effi-MVS+-dtu		64.58 120	64.08 129	65.16 108	73.04 122	75.17 161	70.68 117	56.23 138	54.12 125	44.71 122	47.42 108	51.10 128	63.82 95	68.08 170	66.32 181	82.47 159	86.38 116

LS3D		64.54 122	62.14 146	67.34 101	80.85 68	75.79 156	69.99 118	65.87 57	60.77 91	44.35 123	42.43 135	45.95 141	65.01 87	69.88 162	68.69 172	77.97 189	71.43 187

v1192		62.25 139	61.64 149	62.96 127	66.88 157	79.72 121	69.96 119	55.77 143	41.58 169	39.42 146	37.05 163	35.96 180	60.50 116	74.30 116	74.09 123	85.24 107	88.76 96

CDS-MVSNet		64.22 123	65.89 122	62.28 136	70.05 137	80.59 114	69.91 120	57.98 117	43.53 162	46.58 113	48.22 103	50.76 129	46.45 170	75.68 99	76.08 99	82.70 154	86.34 117
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
GA-MVS		64.55 121	65.76 123	63.12 126	69.68 139	81.56 102	69.59 121	58.16 115	45.23 156	35.58 168	47.01 116	41.82 149	59.41 123	79.62 66	78.54 74	86.32 75	86.56 114

thres600view7		63.77 127	63.14 135	64.51 114	75.49 109	81.61 99	69.59 121	62.95 79	43.96 161	38.90 150	41.09 142	40.24 161	55.25 145	76.24 92	71.54 151	84.89 116	87.30 107

v144192		62.05 143	61.46 151	62.73 133	66.59 161	79.87 120	69.30 123	55.88 141	41.50 171	39.41 147	37.23 161	36.45 175	59.62 121	72.69 135	73.51 129	85.61 102	88.93 93

MDTV_nov1_ep13		65.21 116	67.28 111	62.79 129	70.91 134	81.72 98	69.28 124	49.50 177	58.08 102	43.94 125	50.50 97	56.02 106	58.86 128	70.72 152	73.37 132	84.24 133	80.52 157

EPMVS		66.21 108	67.49 110	64.73 112	75.81 105	84.20 85	68.94 125	44.37 193	61.55 88	48.07 110	49.21 101	54.87 114	62.88 100	71.82 143	71.40 156	88.28 34	79.37 161

EPNet_dtu		66.17 109	70.13 93	61.54 140	81.04 66	77.39 145	68.87 126	62.50 85	69.78 64	33.51 176	63.77 54	56.22 105	37.65 189	72.20 138	72.18 149	85.69 96	79.38 160
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMH+	60.36 13	61.16 148	58.38 168	64.42 116	77.37 94	74.35 167	68.45 127	62.81 83	45.86 153	38.48 152	35.71 172	37.35 170	59.81 120	67.24 172	69.80 169	79.58 182	78.32 164

v1921920		61.66 146	61.10 154	62.31 135	66.32 162	79.57 123	68.41 128	55.49 148	41.03 172	38.69 151	36.64 169	35.27 183	59.60 122	73.23 126	73.41 131	85.37 104	88.51 100

thisisatest0530		68.38 94	70.98 87	65.35 107	72.61 123	84.42 80	68.21 129	57.98 117	59.77 95	50.80 97	54.63 81	58.48 93	57.92 133	76.99 87	77.47 84	84.60 126	85.07 126

v148		62.00 144	61.19 153	62.96 127	67.46 155	79.49 124	67.87 130	57.66 123	42.30 165	45.02 120	38.20 157	38.89 165	54.77 146	69.83 163	72.60 145	84.96 112	87.01 109

UniMVSNet_ETH3D		57.83 167	56.46 177	59.43 152	63.24 177	73.22 171	67.70 131	55.58 146	36.17 189	36.84 160	32.64 182	35.14 184	51.50 154	65.81 175	69.81 168	81.73 167	82.44 149

ACMH	59.42 14	61.59 147	59.22 166	64.36 117	78.92 80	78.26 135	67.65 132	67.48 47	39.81 177	30.98 183	38.25 156	34.59 186	61.37 112	70.55 156	73.47 130	79.74 181	79.59 159
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		67.99 97	70.61 89	64.94 110	71.94 128	83.96 86	67.62 133	57.98 117	59.30 97	49.90 103	54.50 84	57.98 100	57.92 133	76.48 90	77.47 84	84.24 133	84.58 129

IterMVS-SCA-FT		60.21 155	62.97 137	57.00 168	66.64 160	71.84 175	67.53 134	46.93 186	47.56 144	36.77 162	46.85 118	48.21 134	52.51 151	70.36 158	72.40 147	71.63 204	83.53 138

CR-MVSNet		62.31 137	64.75 125	59.47 151	68.63 146	71.29 180	67.53 134	43.18 196	55.83 113	41.40 137	41.04 143	55.85 107	57.29 139	72.76 133	73.27 136	78.77 186	83.23 142

Patchmtry						78.06 137	67.53 134	43.18 196		41.40 137

IterMVS		61.87 145	63.55 131	59.90 147	67.29 156	72.20 174	67.34 137	48.56 179	47.48 145	37.86 157	47.07 114	48.27 133	54.08 148	72.12 140	73.71 127	84.30 132	83.99 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1240		61.09 149	60.55 158	61.72 139	65.92 166	79.28 126	67.16 138	54.91 154	39.79 178	38.10 154	36.08 171	34.64 185	59.15 126	72.86 131	73.36 133	85.10 109	87.84 104

EPP-MVSNet		67.58 100	71.10 86	63.48 124	75.71 107	83.35 89	66.85 139	57.83 122	53.02 127	41.15 140	55.82 75	67.89 56	56.01 142	74.40 112	72.92 142	83.33 145	90.30 78

pmmvs4		63.14 131	62.46 143	63.94 121	66.03 164	76.40 151	66.82 140	57.60 124	56.74 106	50.26 102	40.81 145	37.51 169	59.26 125	71.75 145	71.48 153	83.68 142	82.53 146

dps		64.08 124	63.22 134	65.08 109	75.27 111	79.65 122	66.68 141	46.63 187	56.94 105	55.67 79	43.96 125	43.63 147	64.00 93	69.50 166	69.82 167	82.25 162	79.02 162

tfpnnormal		58.97 161	56.48 176	61.89 137	71.27 132	76.21 153	66.65 142	61.76 93	32.90 197	36.41 163	27.83 195	29.14 203	50.64 159	73.06 128	73.05 140	84.58 128	83.15 144

UGNet		67.57 101	71.69 82	62.76 131	69.88 138	82.58 94	66.43 143	58.64 112	54.71 123	51.87 90	61.74 59	62.01 76	45.46 175	74.78 108	74.99 110	84.24 133	91.02 68
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
PatchmatchNet		65.43 115	67.71 107	62.78 130	73.49 120	82.83 92	66.42 144	45.40 188	60.40 93	45.27 117	49.22 100	57.60 101	60.01 119	70.61 153	71.38 157	86.08 83	81.91 152
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Vis-MVSNet		65.53 114	69.83 94	60.52 144	70.80 136	84.59 78	66.37 145	55.47 149	48.40 142	40.62 144	57.67 72	58.43 95	45.37 176	77.49 80	76.24 98	84.47 129	85.99 121
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
IS_MVSNet		67.29 104	71.98 79	61.82 138	76.92 96	84.32 84	65.90 146	58.22 114	55.75 115	39.22 148	54.51 83	62.47 72	45.99 173	78.83 72	78.52 75	84.70 124	89.47 87

FC-MVSNet-train		68.83 90	68.29 103	69.47 81	78.35 82	79.94 119	64.72 147	66.38 53	54.96 119	54.51 85	56.75 74	47.91 136	66.91 82	75.57 102	75.75 102	85.92 86	87.12 108

IB-MVS	64.48 11	69.02 88	68.97 99	69.09 87	81.75 63	89.01 36	64.50 148	64.91 64	56.65 107	62.59 51	47.89 105	45.23 142	51.99 152	69.18 167	81.88 40	88.77 18	92.93 50
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
pm-mvs1		59.21 160	59.58 165	58.77 157	67.97 150	77.07 148	64.12 149	57.20 129	34.73 194	36.86 159	35.34 174	40.54 160	43.34 180	74.32 115	73.30 135	83.13 151	81.77 153

PMMVS		70.37 83	75.06 66	64.90 111	71.46 129	81.88 97	64.10 150	55.64 145	71.31 60	46.69 112	70.69 39	58.56 91	69.53 65	79.03 70	75.63 104	81.96 165	88.32 101

UniMVSNet_NR-MVSNet		62.30 138	63.51 132	60.89 142	69.48 143	77.83 139	64.07 151	63.94 69	50.03 134	31.17 181	44.82 124	41.12 153	51.37 155	71.02 149	74.81 113	85.30 105	84.95 127

DU-MVS		60.87 151	61.82 148	59.76 149	66.69 158	75.87 154	64.07 151	61.96 87	49.31 137	31.17 181	42.76 128	36.95 172	51.37 155	69.67 164	73.20 139	83.30 146	84.95 127

test-LLR		68.23 95	71.61 83	64.28 118	71.37 130	81.32 106	63.98 153	61.03 97	58.62 100	42.96 131	52.74 89	61.65 77	57.74 136	75.64 100	78.09 81	88.61 24	93.21 46

TESTMET0.1,1		67.38 103	71.61 83	62.45 134	66.05 163	81.32 106	63.98 153	55.36 150	58.62 100	42.96 131	52.74 89	61.65 77	57.74 136	75.64 100	78.09 81	88.61 24	93.21 46

MIMVSNet		57.78 169	59.71 164	55.53 173	54.79 200	77.10 147	63.89 155	45.02 190	46.59 150	36.79 161	28.36 194	40.77 157	45.84 174	74.97 105	76.58 91	86.87 66	73.60 178

FMVSNet5		58.86 162	60.24 160	57.25 166	52.66 204	66.25 192	63.77 156	52.86 170	57.85 104	37.92 156	36.12 170	52.22 126	51.37 155	70.88 151	71.43 155	84.92 113	66.91 196

NR-MVSNet		61.08 150	62.09 147	59.90 147	71.96 127	75.87 154	63.60 157	61.96 87	49.31 137	27.95 186	42.76 128	33.85 190	48.82 162	74.35 114	74.05 125	85.13 108	84.45 130

TransMVSNet (Re)		57.83 167	56.90 174	58.91 156	72.26 125	74.69 165	63.57 158	61.42 95	32.30 199	32.65 177	33.97 179	35.96 180	39.17 187	73.84 121	72.84 143	84.37 131	74.69 173

EG-PatchMatch MVS		58.73 164	58.03 171	59.55 150	72.32 124	80.49 115	63.44 159	55.55 147	32.49 198	38.31 153	28.87 193	37.22 171	42.84 181	74.30 116	75.70 103	84.84 118	77.14 167

TranMVSNet+NR-MVSNet		60.38 154	61.30 152	59.30 153	68.34 147	75.57 160	63.38 160	63.78 71	46.74 148	27.73 187	42.56 132	36.84 173	47.66 165	70.36 158	74.59 117	84.91 115	82.46 147

pmmvs5		59.72 156	60.24 160	59.11 155	62.77 180	77.33 146	63.17 161	54.00 162	40.21 176	37.23 158	40.41 146	35.99 179	51.75 153	72.55 137	72.74 144	85.72 95	82.45 148

USDC		59.69 157	60.03 162	59.28 154	64.04 173	71.84 175	63.15 162	55.36 150	54.90 121	35.02 170	48.34 102	29.79 202	58.16 130	70.60 154	71.33 158	79.99 179	73.42 179

CMPMVS	43.63 17	57.67 170	55.43 178	60.28 146	72.01 126	79.00 127	62.77 163	53.23 167	41.77 168	45.42 116	30.74 189	39.03 163	53.01 150	64.81 181	64.65 187	75.26 196	68.03 194
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
COLMAP_ROB	51.17 15	55.13 174	52.90 187	57.73 163	73.47 121	67.21 190	62.13 164	55.82 142	47.83 143	34.39 172	31.60 186	34.24 187	44.90 177	63.88 186	62.52 194	75.67 194	63.02 203
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
v7n		57.04 172	56.64 175	57.52 164	62.85 179	74.75 164	61.76 165	51.80 173	35.58 193	36.02 166	32.33 184	33.61 191	50.16 160	67.73 171	70.34 166	82.51 157	82.12 150

UniMVSNet (Re)		60.62 152	62.93 139	57.92 160	67.64 153	77.90 138	61.75 166	61.24 96	49.83 136	29.80 185	42.57 131	40.62 159	43.36 179	70.49 157	73.27 136	83.76 139	85.81 122

Baseline_NR-MVSNet		59.47 158	60.28 159	58.54 158	66.69 158	73.90 168	61.63 167	62.90 82	49.15 141	26.87 188	35.18 176	37.62 168	48.20 163	69.67 164	73.61 128	84.92 113	82.82 145

TDRefinement		52.70 184	51.02 193	54.66 177	57.41 197	65.06 196	61.47 168	54.94 152	44.03 160	33.93 174	30.13 191	27.57 205	46.17 172	61.86 188	62.48 195	74.01 200	66.06 197

CHOSEN 280x420		62.23 141	66.57 115	57.17 167	59.88 189	68.92 186	61.20 169	42.28 200	54.17 124	39.57 145	47.78 106	64.97 64	62.68 101	73.85 120	69.52 170	77.43 190	86.75 111

ADS-MVSNet		58.40 166	59.16 167	57.52 164	65.80 167	74.57 166	60.26 170	40.17 207	50.51 132	38.01 155	40.11 149	44.72 143	59.36 124	64.91 179	66.55 179	81.53 169	72.72 183

pmmvs6		54.20 181	53.54 183	54.97 174	63.22 178	72.98 172	60.17 171	52.32 172	26.77 208	34.30 173	23.29 202	36.23 177	40.33 186	68.77 168	68.76 171	79.47 184	78.00 165

UA-Net		64.62 119	68.23 105	60.42 145	77.53 91	81.38 104	60.08 172	57.47 127	47.01 146	44.75 121	60.68 64	71.32 46	41.84 183	73.27 125	72.25 148	80.83 175	71.68 185

SCA		63.90 126	66.67 113	60.66 143	73.75 115	71.78 177	59.87 173	43.66 194	61.13 90	45.03 119	51.64 93	59.45 89	57.92 133	70.96 150	70.80 161	83.71 141	80.92 156

PatchMatch-RL		62.22 142	60.69 156	64.01 119	68.74 145	75.75 157	59.27 174	60.35 106	56.09 112	53.80 86	47.06 115	36.45 175	64.80 90	68.22 169	67.22 176	77.10 191	74.02 175

test-mter		64.06 125	69.24 96	58.01 159	59.07 192	77.40 144	59.13 175	48.11 181	55.64 116	39.18 149	51.56 94	58.54 92	55.38 144	73.52 124	76.00 100	87.22 59	92.05 59

TAMVS		58.86 162	60.91 155	56.47 171	62.38 182	77.57 142	58.97 176	52.98 168	38.76 181	36.17 164	42.26 136	47.94 135	46.45 170	70.23 160	70.79 162	81.86 166	78.82 163

thisisatest0515		59.37 159	60.68 157	57.84 162	64.39 172	75.65 159	58.56 177	53.86 163	41.55 170	42.12 136	40.40 147	39.59 162	47.09 168	71.69 146	73.79 126	81.02 173	82.08 151

MDTV_nov1_ep13_2view		54.47 180	54.61 179	54.30 180	60.50 187	73.82 169	57.92 178	43.38 195	39.43 180	32.51 178	33.23 180	34.05 188	47.26 167	62.36 187	66.21 182	84.24 133	73.19 181

pmmvs-eth3d		55.20 173	53.95 182	56.65 169	57.34 198	67.77 188	57.54 179	53.74 164	40.93 173	41.09 141	31.19 188	29.10 204	49.07 161	65.54 176	67.28 175	81.14 171	75.81 168

TinyColmap		52.66 185	50.09 196	55.65 172	59.72 190	64.02 200	57.15 180	52.96 169	40.28 175	32.51 178	32.42 183	20.97 213	56.65 141	63.95 185	65.15 186	74.91 197	63.87 201

Vis-MVSNet (Re-imp)		62.25 139	68.74 100	54.68 176	73.70 116	78.74 129	56.51 181	57.49 126	55.22 117	26.86 189	54.56 82	61.35 79	31.06 191	73.10 127	74.90 111	82.49 158	83.31 139

our_test_3					63.32 175	71.07 182	55.90 182

CVMVSNet		54.92 178	58.16 169	51.13 186	62.61 181	68.44 187	55.45 183	52.38 171	42.28 166	21.45 197	47.10 113	46.10 140	37.96 188	64.42 184	63.81 188	76.92 192	75.01 172

RPMNet		58.63 165	62.80 141	53.76 181	67.59 154	71.29 180	54.60 184	38.13 208	55.83 113	35.70 167	41.58 140	53.04 124	47.89 164	66.10 174	67.38 174	78.65 188	84.40 131

pmnet_mix02		53.92 182	53.30 184	54.65 178	61.89 183	71.33 179	54.54 185	54.17 161	40.38 174	34.65 171	34.76 178	30.68 201	40.44 185	60.97 189	63.71 189	82.19 163	71.24 188

RPSCF		55.07 175	58.06 170	51.57 183	48.87 208	58.95 205	53.68 186	41.26 205	62.42 85	45.88 114	54.38 85	54.26 117	53.75 149	57.15 196	53.53 206	66.01 206	65.75 198

test0.0.03 1		57.35 171	59.89 163	54.38 179	71.37 130	73.45 170	52.71 187	61.03 97	46.11 152	26.33 190	41.73 139	44.08 145	29.72 193	71.43 148	70.90 160	85.10 109	71.56 186

anonymousdsp		54.99 176	57.24 173	52.36 182	53.82 202	71.75 178	51.49 188	48.14 180	33.74 195	33.66 175	38.34 155	36.13 178	47.54 166	64.53 183	70.60 164	79.53 183	85.59 125

Anonymous20231206		52.23 186	52.80 188	51.56 184	64.70 171	69.41 184	51.01 189	58.60 113	36.63 186	22.44 196	21.80 205	31.42 197	30.52 192	66.79 173	67.83 173	82.10 164	75.73 169

PM-MVS		50.11 191	50.38 195	49.80 187	47.23 210	62.08 203	50.91 190	44.84 192	41.90 167	36.10 165	35.22 175	26.05 209	46.83 169	57.64 194	55.42 205	72.90 201	74.32 174

LTVRE_ROB	47.26 16	49.41 194	49.91 197	48.82 189	64.76 170	69.79 183	49.05 191	47.12 185	20.36 215	16.52 203	36.65 168	26.96 206	50.76 158	60.47 190	63.16 192	64.73 207	72.00 184
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
PEN-MVS		51.04 187	52.94 186	48.82 189	61.45 185	66.00 193	48.68 192	57.20 129	36.87 184	15.36 205	36.98 164	32.72 192	28.77 197	57.63 195	66.37 180	81.44 170	74.00 176

CP-MVSNet		50.57 189	52.60 190	48.21 192	58.77 194	65.82 194	48.17 193	56.29 136	37.41 183	16.59 202	37.14 162	31.95 194	29.21 194	56.60 198	63.71 189	80.22 177	75.56 170

PS-CasMVS		50.17 190	52.02 191	48.02 193	58.60 195	65.54 195	48.04 194	56.19 140	36.42 188	16.42 204	35.68 173	31.33 198	28.85 196	56.42 200	63.54 191	80.01 178	75.18 171

PatchT		60.46 153	63.85 130	56.51 170	65.95 165	75.68 158	47.34 195	41.39 203	53.89 126	41.40 137	37.84 159	50.30 131	57.29 139	72.76 133	73.27 136	85.67 97	83.23 142

SixPastTwentyTwo		49.11 195	49.22 198	48.99 188	58.54 196	64.14 199	47.18 196	47.75 182	31.15 201	24.42 192	41.01 144	26.55 207	44.04 178	54.76 203	58.70 200	71.99 203	68.21 192

N_pmnet		47.67 197	47.00 201	48.45 191	54.72 201	62.78 201	46.95 197	51.25 174	36.01 191	26.09 191	26.59 198	25.93 210	35.50 190	55.67 202	59.01 198	76.22 193	63.04 202

MDA-MVSNet-bldmvs		44.15 201	42.27 206	46.34 196	38.34 212	62.31 202	46.28 198	55.74 144	29.83 202	20.98 198	27.11 197	16.45 218	41.98 182	41.11 210	57.47 201	74.72 198	61.65 206

FPMVS		39.11 205	36.39 207	42.28 200	55.97 199	45.94 212	46.23 199	41.57 202	35.73 192	22.61 194	23.46 201	19.82 215	28.32 198	43.57 207	40.67 209	58.96 210	45.54 210

WR-MVS_H		49.62 193	52.63 189	46.11 198	58.80 193	67.58 189	46.14 200	54.94 152	36.51 187	13.63 210	36.75 167	35.67 182	22.10 204	56.43 199	62.76 193	81.06 172	72.73 182

DTE-MVSNet		49.82 192	51.92 192	47.37 194	61.75 184	64.38 198	45.89 201	57.33 128	36.11 190	12.79 212	36.87 165	31.93 195	25.73 200	58.01 193	65.22 185	80.75 176	70.93 190

WR-MVS		51.02 188	54.56 180	46.90 195	63.84 174	69.23 185	44.78 202	56.38 135	38.19 182	14.19 207	37.38 160	36.82 174	22.39 203	60.14 191	66.20 183	79.81 180	73.95 177

MVS-HIRNet		53.86 183	53.02 185	54.85 175	60.30 188	72.36 173	44.63 203	42.20 201	39.45 179	43.47 127	21.66 206	34.00 189	55.47 143	65.42 177	67.16 177	83.02 152	71.08 189

EU-MVSNet		44.84 200	47.85 200	41.32 203	49.26 207	56.59 208	43.07 204	47.64 184	33.03 196	13.82 208	36.78 166	30.99 199	24.37 201	53.80 204	55.57 204	69.78 205	68.21 192

testgi		48.51 196	50.53 194	46.16 197	64.78 169	67.15 191	41.54 205	54.81 156	29.12 204	17.03 201	32.07 185	31.98 193	20.15 207	65.26 178	67.00 178	78.67 187	61.10 207

test20.03		47.23 199	48.69 199	45.53 199	63.28 176	64.39 197	41.01 206	56.93 132	29.16 203	15.21 206	23.90 199	30.76 200	17.51 210	64.63 182	65.26 184	79.21 185	62.71 204

new-patchmatchnet		42.21 202	42.97 203	41.33 202	53.05 203	59.89 204	39.38 207	49.61 176	28.26 206	12.10 213	22.17 204	21.54 212	19.22 208	50.96 205	56.04 203	74.61 199	61.92 205

MIMVSNet1		40.84 204	43.46 202	37.79 205	32.14 213	58.92 206	39.24 208	50.83 175	27.00 207	11.29 214	16.76 212	26.53 208	17.75 209	57.14 197	61.12 197	75.46 195	56.78 208

pmmvs3		41.86 203	42.29 205	41.36 201	39.80 211	52.66 210	38.93 209	35.85 212	23.40 212	20.22 199	19.30 207	20.84 214	40.56 184	55.98 201	58.79 199	72.80 202	65.03 199

ambc			42.30 204		50.36 206	49.51 211	35.47 210		32.04 200	23.53 193	17.36 209	8.95 220	29.06 195	64.88 180	56.26 202	61.29 209	67.12 195

FC-MVSNet-test		47.24 198	54.37 181	38.93 204	59.49 191	58.25 207	34.48 211	53.36 166	45.66 154	6.66 217	50.62 95	42.02 148	16.62 211	58.39 192	61.21 196	62.99 208	64.40 200

gm-plane-assit		54.99 176	57.99 172	51.49 185	69.27 144	54.42 209	32.32 212	42.59 199	21.18 213	13.71 209	23.61 200	43.84 146	60.21 118	87.09 5	86.55 5	90.81 4	89.28 89

new_pmnet		33.19 206	35.52 208	30.47 207	27.55 217	45.31 213	29.29 213	30.92 213	29.00 205	9.88 216	18.77 208	17.64 217	26.77 199	44.07 206	45.98 208	58.41 211	47.87 209

PMVS	27.44 18	32.08 207	29.07 210	35.60 206	48.33 209	24.79 215	26.97 214	41.34 204	20.45 214	22.50 195	17.11 211	18.64 216	20.44 206	41.99 209	38.06 210	54.02 212	42.44 211
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		28.15 208	34.48 209	20.76 210	6.76 221	21.18 217	21.03 215	18.41 216	36.77 185	17.52 200	15.67 213	31.63 196	24.05 202	41.03 211	26.69 213	36.82 215	68.38 191

Gipuma		24.91 209	24.61 211	25.26 209	31.47 214	21.59 216	18.06 216	37.53 209	25.43 210	10.03 215	4.18 218	4.25 222	14.85 212	43.20 208	47.03 207	39.62 214	26.55 215
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DeepMVS_CX						19.81 219	17.01 217	10.02 217	23.61 211	5.85 218	17.21 210	8.03 221	21.13 205	22.60 214		21.42 219	30.01 213

PMMVS2		20.45 210	22.31 212	18.27 213	20.52 218	26.73 214	14.85 218	28.43 215	13.69 216	0.79 222	10.35 214	9.10 219	3.83 217	27.64 213	32.87 211	41.17 213	35.81 212

tmp_tt				16.09 214	13.07 219	8.12 222	13.61 219	2.08 218	55.09 118	30.10 184	40.26 148	22.83 211	5.35 216	29.91 212	25.25 214	32.33 216

EMVS		14.40 212	10.71 215	18.70 212	28.15 216	12.09 221	7.06 220	36.89 210	11.00 217	3.56 221	4.95 216	2.27 224	13.91 213	10.13 217	16.06 216	22.63 218	18.51 217

E-PMN		15.08 211	11.65 214	19.08 211	28.73 215	12.31 220	6.95 221	36.87 211	10.71 218	3.63 220	5.13 215	2.22 225	13.81 214	11.34 216	18.50 215	24.49 217	21.32 216

MVE	15.98 19	14.37 213	16.36 213	12.04 215	7.72 220	20.24 218	5.90 222	29.05 214	8.28 219	3.92 219	4.72 217	2.42 223	9.57 215	18.89 215	31.46 212	16.07 220	28.53 214
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Patchmatch-RL test							2.17 223

testmvs		0.05 214	0.08 216	0.01 216	0.00 223	0.01 223	0.03 224	0.01 220	0.05 220	0.00 224	0.14 220	0.01 226	0.03 220	0.05 218	0.05 217	0.01 221	0.24 219

test123		0.05 214	0.08 216	0.01 216	0.00 223	0.01 223	0.01 225	0.00 221	0.05 220	0.00 224	0.16 219	0.00 227	0.04 218	0.02 219	0.05 217	0.00 222	0.26 218

uanet_test		0.00 216	0.00 218	0.00 218	0.00 223	0.00 225	0.00 226	0.00 221	0.00 222	0.00 224	0.00 221	0.00 227	0.00 221	0.00 220	0.00 219	0.00 222	0.00 220

sosnet-low-res		0.00 216	0.00 218	0.00 218	0.00 223	0.00 225	0.00 226	0.00 221	0.00 222	0.00 224	0.00 221	0.00 227	0.00 221	0.00 220	0.00 219	0.00 222	0.00 220

sosnet		0.00 216	0.00 218	0.00 218	0.00 223	0.00 225	0.00 226	0.00 221	0.00 222	0.00 224	0.00 221	0.00 227	0.00 221	0.00 220	0.00 219	0.00 222	0.00 220

RE-MVS-def										31.47 180

9.14												84.47 6

SR-MVS					86.33 47			67.54 46				80.78 19

MTAPA										78.32 11		79.42 24

MTMP										76.04 16		76.65 29

mPP-MVS					86.96 42							70.61 49

NP-MVS									81.60 36

High-resolution multi-view benchmark