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.

UA-Net		89.02 35	91.44 42	86.20 28	94.88 1	89.84 37	94.76 29	77.45 29	85.41 87	74.79 122	88.83 99	88.90 173	78.67 43	96.06 7	95.45 4	96.66 3	95.58 2

DTE-MVSNet		88.99 37	92.77 13	84.59 45	93.31 2	88.10 52	90.96 57	83.09 2	91.38 15	76.21 110	96.03 2	98.04 8	70.78 110	95.65 14	92.32 33	93.18 58	87.84 77

RA-MVS		90.04 17	93.35 6	86.18 29	93.28 3	89.99 34	93.17 45	77.71 25	92.21 12	77.46 104	94.29 14	96.35 36	81.74 22	93.53 35	94.17 14	93.71 48	92.93 26

mPP-MVS					93.05 4							95.77 59

MP-MVS		90.84 6	91.95 37	89.55 3	92.92 5	90.90 19	96.56 6	79.60 11	86.83 67	88.75 12	89.00 94	94.38 104	84.01 9	94.94 24	94.34 10	95.45 24	93.24 23
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PEN-MVS		88.86 41	92.92 10	84.11 55	92.92 5	88.05 54	90.83 59	82.67 5	91.04 19	74.83 121	95.97 3	98.47 3	70.38 112	95.70 13	92.43 31	93.05 62	88.78 69

HPM-MVS++		88.74 42	89.54 55	87.80 15	92.58 7	85.69 72	95.10 26	78.01 22	87.08 63	87.66 19	87.89 110	92.07 138	80.28 33	90.97 72	91.41 44	93.17 59	91.69 40

DVP-MVS++		90.50 10	94.18 4	86.21 27	92.52 8	90.29 30	95.29 22	76.02 42	94.24 5	82.82 54	95.84 5	97.56 15	76.82 58	93.13 39	91.20 45	93.78 46	97.01 1

PS-CasMVS		89.07 34	93.23 8	84.21 53	92.44 9	88.23 51	90.54 66	82.95 3	90.50 28	75.31 118	95.80 6	98.37 6	71.16 104	96.30 5	93.32 22	92.88 63	90.11 53

CP-MVSNet		88.71 43	92.63 16	84.13 54	92.39 10	88.09 53	90.47 70	82.86 4	88.79 46	75.16 119	94.87 9	97.68 13	71.05 106	96.16 6	93.18 24	92.85 64	89.64 58

CP-MVS		91.09 5	92.33 26	89.65 2	92.16 11	90.41 28	96.46 10	80.38 8	88.26 49	89.17 10	87.00 126	96.34 39	83.95 10	95.77 11	94.72 7	95.81 17	93.78 10

ACMMPR		91.30 4	92.88 12	89.46 4	91.92 12	91.61 5	96.60 5	79.46 14	90.08 33	88.53 13	89.54 84	95.57 63	84.25 7	95.24 20	94.27 12	95.97 11	93.85 8

WR-MVS_H		88.99 37	93.28 7	83.99 56	91.92 12	89.13 43	91.95 51	83.23 1	90.14 32	71.92 145	95.85 4	98.01 10	71.83 99	95.82 9	93.19 23	93.07 61	90.83 50

SR-MVS					91.82 14			80.80 7				95.53 65

PGM-MVS		90.42 11	91.58 40	89.05 5	91.77 15	91.06 13	96.51 7	78.94 16	85.41 87	87.67 18	87.02 125	95.26 76	83.62 12	95.01 23	93.94 16	95.79 19	93.40 20

APD-MVS		89.14 30	91.25 45	86.67 24	91.73 16	91.02 15	95.50 20	77.74 24	84.04 101	79.47 85	91.48 53	94.85 87	81.14 26	92.94 42	92.20 36	94.47 39	92.24 35
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		90.13 15	92.26 28	87.64 17	91.68 17	90.44 27	95.22 24	77.34 33	90.79 25	87.80 16	90.42 73	92.05 140	79.05 38	93.89 32	93.59 19	94.77 32	94.62 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
ambc			88.38 63		91.62 18	87.97 56	84.48 145		88.64 48	87.93 15	87.38 117	94.82 89	74.53 79	89.14 92	83.86 122	85.94 176	86.84 83

TSAR-MVS + MP.		89.67 25	92.25 30	86.65 25	91.53 19	90.98 17	96.15 13	73.30 58	87.88 55	81.83 66	92.92 34	95.15 81	82.23 18	93.58 34	92.25 34	94.87 29	93.01 25
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		86.67 56	87.73 73	85.43 36	91.51 20	82.72 95	94.47 33	74.22 55	81.71 125	81.54 70	89.20 92	92.87 126	78.33 46	90.12 83	88.47 72	92.51 71	89.04 65

X-MVS		89.36 29	90.73 48	87.77 16	91.50 21	91.23 8	96.76 4	78.88 17	87.29 60	87.14 25	78.98 186	94.53 97	76.47 60	95.25 19	94.28 11	95.85 14	93.55 16

HFP-MVS		90.32 13	92.37 23	87.94 13	91.46 22	90.91 18	95.69 17	79.49 12	89.94 36	83.50 50	89.06 93	94.44 102	81.68 23	94.17 30	94.19 13	95.81 17	93.87 7

ACMM	80.67 7	90.67 7	92.46 20	88.57 7	91.35 23	89.93 35	96.34 11	77.36 31	90.17 31	86.88 29	87.32 118	96.63 26	83.32 13	95.79 10	94.49 9	96.19 9	92.91 27
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		89.79 24	93.66 5	85.27 39	91.32 24	88.27 49	93.49 41	79.86 10	92.75 9	75.37 117	96.86 1	98.38 5	75.10 74	95.93 8	94.07 15	96.46 5	89.39 60

SD-MVS		89.91 19	92.23 32	87.19 21	91.31 25	89.79 38	94.31 34	75.34 49	89.26 40	81.79 67	92.68 36	95.08 83	83.88 11	93.10 40	92.69 26	96.54 4	93.02 24
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
XVS					91.28 26	91.23 8	96.89 2			87.14 25		94.53 97				95.84 15

X-MVStestdata					91.28 26	91.23 8	96.89 2			87.14 25		94.53 97				95.84 15

DeepC-MVS	83.59 4	90.37 12	92.56 19	87.82 14	91.26 28	92.33 3	94.72 30	80.04 9	90.01 34	84.61 42	93.33 26	94.22 106	80.59 28	92.90 44	92.52 29	95.69 21	92.57 29
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP		90.63 8	92.40 21	88.56 8	91.24 29	91.60 6	96.49 9	77.53 27	87.89 54	86.87 30	87.24 120	96.46 31	82.87 16	95.59 15	94.50 8	96.35 6	93.51 18
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
SteuartSystems-ACMMP		90.00 18	91.73 38	87.97 12	91.21 30	90.29 30	96.51 7	78.00 23	86.33 72	85.32 40	88.23 106	94.67 95	82.08 20	95.13 22	93.88 17	94.72 35	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		89.86 20	91.96 36	87.42 19	91.00 31	90.08 32	96.00 15	76.61 37	89.28 38	87.73 17	90.04 75	91.80 144	78.71 41	94.36 28	93.82 18	94.48 38	94.32 6

CPTT-MVS		89.63 26	90.52 50	88.59 6	90.95 32	90.74 22	95.71 16	79.13 15	87.70 56	85.68 38	80.05 177	95.74 61	84.77 6	94.28 29	92.68 27	95.28 26	92.45 34

LGP-MVS_train		90.56 9	92.38 22	88.43 9	90.88 33	91.15 11	95.35 21	77.65 26	86.26 75	87.23 23	90.45 72	97.35 17	83.20 14	95.44 16	93.41 21	96.28 8	92.63 28

OPM-MVS		89.82 22	92.24 31	86.99 22	90.86 34	89.35 41	95.07 27	75.91 44	91.16 17	86.87 30	91.07 64	97.29 18	79.13 37	93.32 36	91.99 38	94.12 41	91.49 43
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	80.00 8	90.12 16	92.30 27	87.58 18	90.83 35	91.10 12	94.96 28	76.06 41	87.47 58	85.33 39	88.91 98	97.65 14	82.13 19	95.31 17	93.44 20	96.14 10	92.22 36
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
NCCC		86.74 55	87.97 71	85.31 38	90.64 36	87.25 62	93.27 43	74.59 51	86.50 70	83.72 46	75.92 217	92.39 132	77.08 56	91.72 56	90.68 50	92.57 69	91.30 45

MSP-MVS		88.51 44	91.36 43	85.19 41	90.63 37	92.01 4	95.29 22	77.52 28	90.48 29	80.21 76	90.21 74	96.08 44	76.38 62	88.30 100	91.42 42	91.12 93	91.01 47
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
UniMVSNet_ETH3D		85.39 66	91.12 46	78.71 103	90.48 38	83.72 82	81.76 168	82.41 6	93.84 6	64.43 191	95.41 7	98.76 1	63.72 167	93.63 33	89.74 60	89.47 114	82.74 121

APDe-MVS		89.85 21	92.91 11	86.29 26	90.47 39	91.34 7	96.04 14	76.41 40	91.11 18	78.50 93	93.44 25	95.82 57	81.55 24	93.16 38	91.90 39	94.77 32	93.58 15
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PMVS	79.51 9	90.23 14	92.67 15	87.39 20	90.16 40	88.75 45	93.64 39	75.78 45	90.00 35	83.70 47	92.97 33	92.22 135	86.13 4	97.01 3	96.79 2	94.94 28	90.96 48
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CNVR-MVS		86.93 54	88.98 59	84.54 46	90.11 41	87.41 61	93.23 44	73.47 57	86.31 73	82.25 61	82.96 161	92.15 136	76.04 65	91.69 57	90.69 49	92.17 76	91.64 42

TSAR-MVS + GP.		85.32 68	87.41 78	82.89 65	90.07 42	85.69 72	89.07 86	72.99 62	82.45 115	74.52 127	85.09 146	87.67 181	79.24 36	91.11 67	90.41 52	91.45 83	89.45 59

DeepC-MVS_fast	81.78 5	87.38 52	89.64 54	84.75 43	89.89 43	90.70 23	92.74 48	74.45 52	86.02 77	82.16 64	86.05 139	91.99 142	75.84 68	91.16 66	90.44 51	93.41 53	91.09 46
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		89.02 35	91.69 39	85.91 31	89.72 44	90.81 20	92.56 49	71.69 70	90.83 24	87.24 22	89.71 82	92.07 138	78.37 45	94.43 27	92.59 28	95.86 13	91.35 44

DPE-MVS		89.81 23	92.34 25	86.86 23	89.69 45	91.00 16	95.53 18	76.91 34	88.18 50	83.43 53	93.48 24	95.19 78	81.07 27	92.75 46	92.07 37	94.55 37	93.74 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CDPH-MVS		86.66 57	88.52 62	84.48 47	89.61 46	88.27 49	92.86 47	72.69 63	80.55 144	82.71 55	86.92 127	93.32 121	75.55 70	91.00 71	89.85 59	93.47 51	89.71 57

MED-MVS		89.08 33	92.26 28	85.36 37	89.60 47	90.41 28	94.28 35	75.72 46	91.00 21	77.70 101	93.91 21	94.76 91	80.32 31	92.42 51	90.74 48	94.57 36	92.56 30

EPNet		79.36 144	79.44 177	79.27 101	89.51 48	77.20 160	88.35 92	77.35 32	68.27 220	74.29 128	76.31 209	79.22 220	59.63 192	85.02 140	85.45 104	86.49 163	84.61 96
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
aaEdge-Enhanced		88.45 45	92.03 35	84.27 50	89.33 49	90.77 21	94.55 31	72.48 64	89.22 41	76.86 107	93.91 21	95.41 69	80.41 29	92.07 52	90.28 54	91.99 77	92.56 30

TSAR-MVS + ACMM		89.14 30	92.11 34	85.67 32	89.27 50	90.61 25	90.98 56	79.48 13	88.86 44	79.80 80	93.01 32	93.53 117	83.17 15	92.75 46	92.45 30	91.32 86	93.59 13

HQP-MVS		85.02 70	86.41 84	83.40 57	89.19 51	86.59 66	91.28 54	71.60 71	82.79 111	83.48 51	78.65 192	93.54 116	72.55 92	86.49 118	85.89 100	92.28 75	90.95 49

AdaColmap		84.15 76	85.14 107	83.00 62	89.08 52	87.14 64	90.56 65	70.90 73	82.40 118	80.41 73	73.82 228	84.69 200	75.19 73	91.58 60	89.90 58	91.87 80	86.48 85

DVP-MVS		89.40 28	92.69 14	85.56 35	89.01 53	89.85 36	93.72 38	75.42 47	92.28 11	80.49 72	94.36 13	94.87 86	81.46 25	92.49 50	91.42 42	93.27 55	93.54 17
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
COLMAP_ROB	85.66 2	91.85 2	95.01 2	88.16 11	88.98 54	92.86 2	95.51 19	72.17 66	94.95 4	91.27 3	94.11 18	97.77 11	84.22 8	96.49 4	95.27 5	96.79 2	93.60 12
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TDRefinement		93.16 1	95.57 1	90.36 1	88.79 55	93.57 1	97.27 1	78.23 21	95.55 1	93.00 1	93.98 19	96.01 49	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

TranMVSNet+NR-MVSNet		85.23 69	89.38 56	80.39 93	88.78 56	83.77 81	87.40 103	76.75 35	85.47 85	68.99 164	95.18 8	97.55 16	67.13 143	91.61 59	89.13 69	93.26 56	82.95 118

MGCNet		85.73 62	87.94 72	83.14 60	88.68 57	87.98 55	93.34 42	70.74 75	79.78 153	82.37 58	88.32 105	89.44 165	71.34 101	90.61 76	89.64 63	92.40 72	89.79 56

SED-MVS		88.96 39	92.37 23	84.99 42	88.64 58	89.65 40	95.11 25	75.98 43	90.73 26	80.15 77	94.21 16	94.51 100	76.59 59	92.94 42	91.17 46	93.46 52	93.37 22

ACMH+	79.05 11	89.62 27	93.08 9	85.58 33	88.58 59	89.26 42	92.18 50	74.23 54	93.55 8	82.66 57	92.32 42	98.35 7	80.29 32	95.28 18	92.34 32	95.52 22	90.43 51

DU-MVS		84.88 72	88.27 67	80.92 82	88.30 60	83.59 84	87.06 109	78.35 19	80.64 142	70.49 154	92.67 37	96.91 24	68.13 129	91.79 54	89.29 68	93.20 57	83.02 115

Baseline_NR-MVSNet		82.79 95	86.51 81	78.44 108	88.30 60	75.62 178	87.81 95	74.97 50	81.53 129	66.84 184	94.71 12	96.46 31	66.90 145	91.79 54	83.37 129	85.83 179	82.09 127

UniMVSNet_NR-MVSNet		84.62 74	88.00 70	80.68 88	88.18 62	83.83 80	87.06 109	76.47 39	81.46 132	70.49 154	93.24 27	95.56 64	68.13 129	90.43 77	88.47 72	93.78 46	83.02 115

SF-MVS		87.85 51	90.95 47	84.22 52	88.17 63	87.90 57	90.80 60	71.80 69	89.28 38	82.70 56	89.90 79	95.37 73	77.91 50	91.69 57	90.04 57	93.95 45	92.47 32

CSCG		88.12 48	91.45 41	84.23 51	88.12 64	90.59 26	90.57 64	68.60 93	91.37 16	83.45 52	89.94 78	95.14 82	78.71 41	91.45 61	88.21 76	95.96 12	93.44 19

CLD-MVS		82.75 97	87.22 79	77.54 119	88.01 65	85.76 71	90.23 73	54.52 231	82.28 120	82.11 65	88.48 102	95.27 75	63.95 164	89.41 89	88.29 74	86.45 165	81.01 144
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet (Re)		84.95 71	88.53 61	80.78 84	87.82 66	84.21 78	88.03 93	76.50 38	81.18 137	69.29 162	92.63 40	96.83 25	69.07 122	91.23 65	89.60 64	93.97 44	84.00 105

DPM-MVS		81.42 113	82.11 161	80.62 89	87.54 67	85.30 74	90.18 75	68.96 88	81.00 140	79.15 87	70.45 245	83.29 205	67.67 134	82.81 165	83.46 124	90.19 101	88.48 71

DeepPCF-MVS	81.61 6	87.95 50	90.29 52	85.22 40	87.48 68	90.01 33	93.79 37	73.54 56	88.93 43	83.89 45	89.40 88	90.84 155	80.26 34	90.62 75	90.19 56	92.36 73	92.03 38

ACM-MVS					87.47 69	83.44 87	89.37 84		75.88 174	80.07 78	72.52 233	84.49 202	62.56 176			89.34 116	89.18 62

EC-MVSNet		83.70 80	84.77 117	82.46 69	87.47 69	82.79 94	85.50 128	72.00 67	69.81 211	77.66 102	85.02 148	89.63 163	78.14 47	90.40 78	87.56 78	94.00 42	88.16 74

CANet		82.84 94	84.60 119	80.78 84	87.30 71	85.20 75	90.23 73	69.00 87	72.16 203	78.73 91	84.49 154	90.70 158	69.54 119	87.65 104	86.17 94	89.87 107	85.84 90

MCST-MVS		84.79 73	86.48 82	82.83 66	87.30 71	87.03 65	90.46 71	69.33 85	83.14 108	82.21 63	81.69 171	92.14 137	75.09 75	87.27 108	84.78 111	92.58 67	89.30 61

EIA-MVS		78.57 152	77.90 186	79.35 100	87.24 73	80.71 116	86.16 119	64.03 144	62.63 247	73.49 134	73.60 229	76.12 234	73.83 85	88.49 97	84.93 109	91.36 85	78.78 176

OMC-MVS		88.16 46	91.34 44	84.46 48	86.85 74	90.63 24	93.01 46	67.00 109	90.35 30	87.40 21	86.86 128	96.35 36	77.66 52	92.63 48	90.84 47	94.84 30	91.68 41

3Dnovator+	83.71 3	88.13 47	90.00 53	85.94 30	86.82 75	91.06 13	94.26 36	75.39 48	88.85 45	85.76 37	85.74 142	86.92 184	78.02 48	93.03 41	92.21 35	95.39 25	92.21 37

ETV-MVS		79.01 149	77.98 185	80.22 94	86.69 76	79.73 127	88.80 89	68.27 98	63.22 242	71.56 147	70.25 247	73.63 240	73.66 87	90.30 82	86.77 87	92.33 74	81.95 129

PHI-MVS		86.37 59	88.14 68	84.30 49	86.65 77	87.56 59	90.76 61	70.16 77	82.55 114	89.65 7	84.89 149	92.40 131	75.97 66	90.88 73	89.70 61	92.58 67	89.03 66

ACMH	78.40 12	88.94 40	92.62 17	84.65 44	86.45 78	87.16 63	91.47 53	68.79 91	95.49 2	89.74 6	93.55 23	98.50 2	77.96 49	94.14 31	89.57 65	93.49 49	89.94 55
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		84.35 75	87.55 74	80.62 89	86.38 79	82.24 100	86.75 114	64.02 145	84.24 97	78.17 98	89.38 89	95.03 85	78.78 40	89.95 85	86.33 92	89.59 111	85.65 92

IS_MVSNet		81.72 109	85.01 108	77.90 114	86.19 80	82.64 97	85.56 127	70.02 78	80.11 149	63.52 196	87.28 119	81.18 213	67.26 139	91.08 70	89.33 67	94.82 31	83.42 111

TPM-MVS					86.18 81	83.43 89	87.57 100			78.77 90	69.75 249	84.63 201	62.24 179			89.88 106	88.48 71
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
PCF-MVS	76.59 14	84.11 77	85.27 103	82.76 67	86.12 82	88.30 48	91.24 55	69.10 86	82.36 119	84.45 43	77.56 200	90.40 160	72.91 91	85.88 123	83.88 120	92.72 66	88.53 70
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		85.51 64	88.36 65	82.19 70	86.05 83	87.69 58	90.50 69	70.60 76	86.40 71	82.33 59	89.69 83	92.52 130	74.01 84	87.53 105	86.84 86	89.63 110	87.80 78

EPP-MVSNet		82.76 96	86.47 83	78.45 107	86.00 84	84.47 77	85.39 132	68.42 95	84.17 98	62.97 200	89.26 91	76.84 230	72.13 96	92.56 49	90.40 53	95.76 20	87.56 80

PLC	76.06 15	85.38 67	87.46 76	82.95 64	85.79 85	88.84 44	88.86 88	68.70 92	87.06 64	83.60 48	79.02 183	90.05 161	77.37 55	90.88 73	89.66 62	93.37 54	86.74 84
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSLP-MVS++		86.29 60	89.10 58	83.01 61	85.71 86	89.79 38	87.04 111	74.39 53	85.17 89	78.92 89	77.59 199	93.57 115	82.60 17	93.23 37	91.88 40	89.42 115	92.46 33

Casviewmamba		83.46 86	87.48 75	78.78 102	85.48 87	83.45 86	87.70 98	67.34 108	86.15 76	71.52 148	93.21 28	96.37 35	70.22 114	87.27 108	82.08 138	90.40 98	83.82 106

Effi-MVS+-dtu		82.04 104	83.39 148	80.48 92	85.48 87	86.57 67	88.40 91	68.28 97	69.04 218	73.13 137	76.26 211	91.11 154	74.74 78	88.40 98	87.76 77	92.84 65	84.57 98

test1111		79.67 138	84.40 123	74.16 153	85.29 89	79.56 129	81.16 174	73.13 61	84.65 96	56.08 220	88.38 104	86.14 190	60.49 184	89.78 86	85.59 102	88.79 126	76.68 187

v7n		87.11 53	90.46 51	83.19 59	85.22 90	83.69 83	90.03 77	68.20 99	91.01 20	86.71 33	94.80 10	98.46 4	77.69 51	91.10 68	85.98 97	91.30 87	88.19 73

MAR-MVS		81.98 107	82.92 153	80.88 83	85.18 91	85.85 70	89.13 85	69.52 80	71.21 207	82.25 61	71.28 239	88.89 174	69.69 115	88.71 93	86.96 82	89.52 112	87.57 79
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
TAPA-MVS	78.00 13	85.88 61	88.37 64	82.96 63	84.69 92	88.62 46	90.62 62	64.22 140	89.15 42	88.05 14	78.83 188	93.71 112	76.20 64	90.11 84	88.22 75	94.00 42	89.97 54
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		81.92 108	83.87 138	79.66 97	84.64 93	79.87 123	89.75 78	65.90 122	76.12 172	75.87 114	84.62 153	92.23 134	71.96 98	86.83 114	83.60 123	89.83 108	83.81 107

SixPastTwentyTwo		89.14 30	92.19 33	85.58 33	84.62 94	82.56 98	90.53 67	71.93 68	91.95 13	85.89 35	94.22 15	97.25 19	85.42 5	95.73 12	91.71 41	95.08 27	91.89 39

MVS_111021_HR		83.95 78	86.10 88	81.44 79	84.62 94	80.29 121	90.51 68	68.05 100	84.07 100	80.38 74	84.74 152	91.37 151	74.23 80	90.37 79	87.25 81	90.86 95	84.59 97

test2506		75.32 183	76.87 197	73.50 158	84.55 96	80.37 119	79.63 192	73.23 59	82.64 112	55.41 224	76.87 206	45.42 278	59.61 193	90.35 80	86.46 89	88.58 133	75.98 191

ECVR-MVS		79.31 146	84.20 131	73.60 155	84.55 96	80.37 119	79.63 192	73.23 59	82.64 112	55.98 221	87.50 114	86.85 185	59.61 193	90.35 80	86.46 89	88.58 133	75.26 198

CNLPA		85.50 65	88.58 60	81.91 74	84.55 96	87.52 60	90.89 58	63.56 151	88.18 50	84.06 44	83.85 158	91.34 152	76.46 61	91.27 63	89.00 70	91.96 79	88.88 67

Effi-MVS+		82.33 100	83.87 138	80.52 91	84.51 99	81.32 109	87.53 101	68.05 100	74.94 181	79.66 81	82.37 167	92.31 133	72.21 93	85.06 136	86.91 84	91.18 89	84.20 102

gm-plane-assit		71.56 212	69.99 228	73.39 160	84.43 100	73.21 199	90.42 72	51.36 246	84.08 99	76.00 113	91.30 59	37.09 279	59.01 202	73.65 234	70.24 229	79.09 229	60.37 253

RPSCF		88.05 49	92.61 18	82.73 68	84.24 101	88.40 47	90.04 76	66.29 114	91.46 14	82.29 60	88.93 97	96.01 49	79.38 35	95.15 21	94.90 6	94.15 40	93.40 20

casdiffseed414692147		82.71 98	86.24 86	78.60 106	84.08 102	81.22 112	85.85 124	66.16 117	83.98 102	76.07 112	90.85 66	97.20 21	70.51 111	85.74 124	82.14 137	88.92 123	82.56 123

FC-MVSNet-train		79.20 147	86.29 85	70.94 181	84.06 103	77.67 153	85.68 126	64.11 142	82.90 110	52.22 243	92.57 41	93.69 113	49.52 246	88.30 100	86.93 83	90.03 103	81.95 129

v1192		83.61 81	85.23 105	81.72 76	84.05 104	82.15 101	89.54 80	66.20 115	81.38 135	86.76 32	91.79 50	96.03 47	74.88 77	81.81 179	80.92 149	88.91 125	82.50 124

v1240		83.57 83	84.94 111	81.97 73	84.05 104	81.27 110	89.46 82	66.06 118	81.31 136	87.50 20	91.88 49	95.46 68	76.25 63	81.16 188	80.51 153	88.52 136	82.98 117

test20.03		69.91 216	76.20 205	62.58 234	84.01 106	67.34 232	75.67 228	65.88 123	79.98 150	40.28 265	82.65 162	89.31 169	39.63 260	77.41 211	73.28 216	69.98 248	63.40 243

Anonymous202405211			84.68 118		83.92 107	79.45 130	79.03 197	67.79 102	82.01 122		88.77 101	92.58 129	55.93 215	86.68 115	84.26 117	88.92 123	78.98 173

NR-MVSNet		82.89 93	87.43 77	77.59 117	83.91 108	83.59 84	87.10 108	78.35 19	80.64 142	68.85 165	92.67 37	96.50 29	54.19 226	87.19 112	88.68 71	93.16 60	82.75 120

Gipuma		86.47 58	89.25 57	83.23 58	83.88 109	78.78 136	85.35 133	68.42 95	92.69 10	89.03 11	91.94 46	96.32 41	81.80 21	94.45 26	86.86 85	90.91 94	83.69 108
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CS-MVS		83.57 83	84.79 116	82.14 71	83.83 110	81.48 107	87.29 104	66.54 112	72.73 199	80.05 79	84.04 156	93.12 125	80.35 30	89.50 87	86.34 91	94.76 34	86.32 88

v1921920		83.49 85	84.94 111	81.80 75	83.78 111	81.20 113	89.50 81	65.91 121	81.64 127	87.18 24	91.70 51	95.39 71	75.85 67	81.56 185	80.27 156	88.60 131	82.80 119

v1144		83.22 89	85.01 108	81.14 80	83.76 112	81.60 106	88.95 87	65.58 127	81.89 123	85.80 36	91.68 52	95.84 54	74.04 83	82.12 173	80.56 152	88.70 129	81.41 135

MVSMamba_PlusPlus		80.70 126	82.94 152	78.08 111	83.67 113	81.93 104	85.26 137	65.57 128	72.89 195	74.65 126	79.34 181	89.34 168	69.09 121	85.57 125	84.56 114	90.24 99	86.97 82

Vis-MVSNet (Re-imp)		76.15 174	80.84 169	70.68 182	83.66 114	74.80 187	81.66 170	69.59 79	80.48 145	46.94 255	87.44 116	80.63 215	53.14 233	86.87 113	84.56 114	89.12 119	71.12 218

v144192		83.43 87	84.97 110	81.63 78	83.43 115	81.23 111	89.42 83	66.04 120	81.45 133	86.40 34	91.46 54	95.70 62	75.76 69	82.14 172	80.23 157	88.74 127	82.57 122

TinyColmap		83.79 79	86.12 87	81.07 81	83.42 116	81.44 108	85.42 131	68.55 94	88.71 47	89.46 8	87.60 112	92.72 127	70.34 113	89.29 90	81.94 141	89.20 118	81.12 142

TransMVSNet (Re)		79.05 148	86.66 80	70.18 188	83.32 117	75.99 171	77.54 204	63.98 146	90.68 27	55.84 223	94.80 10	96.06 45	53.73 230	86.27 120	83.22 130	86.65 157	79.61 167

v10		83.17 91	85.22 106	80.78 84	83.26 118	82.99 93	88.66 90	66.49 113	79.24 158	83.60 48	91.46 54	95.47 67	74.12 81	82.60 168	80.66 150	88.53 135	84.11 104

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 10	83.19 119	86.35 68	93.60 40	78.79 18	95.48 3	91.79 2	93.08 31	97.21 20	86.34 3	97.06 2	96.27 3	95.46 23	95.56 3
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
sasdasda		81.22 117	86.04 90	75.60 138	83.17 120	83.18 91	80.29 181	65.82 124	85.97 78	67.98 174	77.74 197	91.51 147	65.17 159	88.62 95	86.15 95	91.17 90	89.09 63

canonicalmvs		81.22 117	86.04 90	75.60 138	83.17 120	83.18 91	80.29 181	65.82 124	85.97 78	67.98 174	77.74 197	91.51 147	65.17 159	88.62 95	86.15 95	91.17 90	89.09 63

SPE-MVS-test		83.59 82	84.86 113	82.10 72	83.04 122	81.05 115	91.58 52	67.48 107	72.52 200	78.42 94	84.75 151	91.82 143	78.62 44	91.98 53	87.54 79	93.48 50	84.35 100

FPMVS		81.56 110	84.04 134	78.66 104	82.92 123	75.96 172	86.48 117	65.66 126	84.67 95	71.47 149	77.78 196	83.22 206	77.57 53	91.24 64	90.21 55	87.84 142	85.21 94

hybridcas		80.80 123	85.25 104	75.61 137	82.91 124	79.79 126	85.07 139	61.72 177	85.56 83	68.49 170	92.67 37	95.38 72	67.22 140	84.31 148	78.61 170	88.24 139	80.42 148

DCV-MVSNet		80.04 132	85.67 97	73.48 159	82.91 124	81.11 114	80.44 180	66.06 118	85.01 91	62.53 203	78.84 187	94.43 103	58.51 204	88.66 94	85.91 98	90.41 97	85.73 91

MVS_111021_LR		83.20 90	85.33 102	80.73 87	82.88 126	78.23 143	89.61 79	65.23 131	82.08 121	81.19 71	85.31 144	92.04 141	75.22 72	89.50 87	85.90 99	90.24 99	84.23 101

Anonymous20231211		79.37 143	85.78 94	71.89 171	82.87 127	79.66 128	78.77 199	63.93 148	83.36 104	59.39 209	90.54 69	94.66 96	56.46 211	87.38 106	84.12 118	89.92 105	80.74 145

MGCFI-Net		79.42 142	85.64 98	72.15 169	82.80 128	82.09 102	76.92 210	65.46 129	86.31 73	57.48 215	78.15 194	91.38 150	59.10 200	88.23 102	84.47 116	91.14 92	88.88 67

casdiffmvs_mvg		81.50 111	85.70 95	76.60 130	82.68 129	80.54 118	83.50 151	64.49 138	83.40 103	72.53 139	92.15 43	95.40 70	65.84 154	84.69 143	81.89 142	90.59 96	81.86 131
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		82.20 102	84.26 128	79.81 96	82.67 130	80.18 122	87.67 99	63.96 147	81.69 126	84.73 41	91.27 60	96.33 40	72.05 97	81.94 177	79.56 161	87.79 143	78.84 175

E6new		81.99 105	85.39 99	78.02 112	82.48 131	78.47 137	87.03 112	63.34 154	87.93 52	79.62 82	92.12 44	97.12 22	68.62 124	83.40 157	78.53 171	87.05 151	80.13 161

E6		81.99 105	85.39 99	78.02 112	82.48 131	78.47 137	87.03 112	63.34 154	87.93 52	79.62 82	92.12 44	97.12 22	68.62 124	83.40 157	78.53 171	87.05 151	80.13 161

v8		82.20 102	84.56 120	79.45 98	82.42 133	81.65 105	87.26 105	64.27 139	79.36 157	81.70 68	91.04 65	95.75 60	73.30 90	82.82 164	79.18 164	87.74 144	82.09 127

E4		81.47 112	84.83 114	77.55 118	82.40 134	78.25 142	86.41 118	62.92 161	87.20 62	78.63 92	91.12 62	96.50 29	68.00 131	82.58 170	77.96 177	86.93 154	80.22 158

MSDG		81.39 115	84.23 130	78.09 110	82.40 134	82.47 99	85.31 135	60.91 186	79.73 154	80.26 75	86.30 134	88.27 178	69.67 116	87.20 111	84.98 108	89.97 104	80.67 146

E5new		81.18 119	84.50 121	77.29 121	82.38 136	78.21 144	86.06 120	62.76 163	86.68 68	78.24 96	90.75 67	95.93 52	67.54 135	82.06 174	77.51 184	86.77 155	80.40 149

E5		81.18 119	84.50 121	77.29 121	82.38 136	78.21 144	86.06 120	62.76 163	86.68 68	78.24 96	90.75 67	95.93 52	67.54 135	82.06 174	77.51 184	86.77 155	80.40 149

Fast-Effi-MVS+		81.42 113	83.81 141	78.62 105	82.24 138	80.62 117	87.72 97	63.51 152	73.01 193	74.75 124	83.80 159	92.70 128	73.44 89	88.15 103	85.26 105	90.05 102	83.17 113

PVSNet_Blended_VisFu		83.00 92	84.16 132	81.65 77	82.17 139	86.01 69	88.03 93	71.23 72	76.05 173	79.54 84	83.88 157	83.44 203	77.49 54	87.38 106	84.93 109	91.41 84	87.40 81

E3new		80.80 123	83.95 136	77.13 123	82.13 140	78.06 146	86.04 122	62.57 166	85.02 90	77.97 100	89.98 77	95.83 55	67.49 138	81.75 181	77.19 190	86.56 161	79.82 164

E3		80.80 123	83.95 136	77.13 123	82.13 140	78.05 147	86.03 123	62.56 167	85.00 92	77.99 99	89.99 76	95.83 55	67.50 137	81.75 181	77.19 190	86.56 161	79.81 165

pmmvs6		80.46 127	88.34 66	71.26 177	81.96 142	77.51 155	77.54 204	68.83 90	93.72 7	55.92 222	93.94 20	98.03 9	55.94 214	89.21 91	85.61 101	87.36 148	80.38 151

viewcassd2359sk11		80.26 130	83.21 149	76.82 127	81.93 143	77.91 150	85.75 125	62.34 171	83.17 107	77.53 103	89.00 94	95.26 76	67.11 144	81.06 190	76.55 198	86.29 168	79.50 169

IterMVS-LS		79.79 135	82.56 157	76.56 131	81.83 144	77.85 151	79.90 188	69.42 84	78.93 160	71.21 150	90.47 71	85.20 198	70.86 109	80.54 195	80.57 151	86.15 169	84.36 99
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
E2		79.77 136	82.52 158	76.56 131	81.77 145	77.80 152	85.49 129	62.14 172	81.45 133	77.16 106	88.03 109	94.73 93	66.75 146	80.40 197	76.02 202	86.07 172	79.22 171

CDS-MVSNet		73.07 202	77.02 193	68.46 205	81.62 146	72.89 202	79.56 194	70.78 74	69.56 213	52.52 240	77.37 202	81.12 214	42.60 255	84.20 150	83.93 119	83.65 205	70.07 223
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		72.68 205	75.21 214	69.73 192	81.48 147	69.04 226	70.48 245	76.67 36	86.92 65	67.80 178	88.06 108	64.67 248	42.12 257	77.60 209	73.65 215	79.81 223	66.57 231

USDC		81.39 115	83.07 150	79.43 99	81.48 147	78.95 135	82.62 161	66.17 116	87.45 59	90.73 4	82.40 166	93.65 114	66.57 148	83.63 155	77.97 176	89.00 122	77.45 185

viewdifsd2359ckpt09		82.38 99	85.92 92	78.26 109	81.46 149	83.33 90	87.76 96	66.85 110	80.47 146	72.93 138	86.68 130	94.75 92	71.25 103	86.58 116	86.23 93	89.30 117	83.41 112

casdiffmvs		79.93 133	84.11 133	75.05 145	81.41 150	78.99 134	82.95 158	62.90 162	81.53 129	68.60 169	91.94 46	96.03 47	65.84 154	82.89 163	77.07 192	88.59 132	80.34 155
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tfpnnormal		77.16 164	84.26 128	68.88 203	81.02 151	75.02 183	76.52 215	63.30 156	87.29 60	52.40 241	91.24 61	93.97 107	54.85 223	85.46 130	81.08 147	85.18 188	75.76 194

viewdifsd2359ckpt13		80.07 131	83.42 147	76.17 133	80.95 152	79.07 132	85.14 138	61.42 181	80.41 147	74.78 123	87.22 121	94.70 94	68.23 128	82.60 168	78.34 173	86.49 163	81.63 133

usedtu_dtu_shiyan2		73.14 200	78.83 180	66.49 218	80.89 153	69.55 224	78.12 201	67.67 105	89.65 37	49.76 250	80.90 172	95.49 66	45.72 252	78.37 206	74.56 211	76.81 232	63.31 244

viewmacassd2359aftdt		81.04 122	85.39 99	75.95 134	80.71 154	77.95 149	85.29 136	58.82 204	86.88 66	76.27 109	91.34 56	96.35 36	68.32 127	84.35 147	79.13 166	86.32 167	81.73 132

thres600view7		74.34 190	78.43 182	69.56 195	80.47 155	76.28 168	78.65 200	62.56 167	77.39 165	52.53 239	74.03 226	76.78 231	55.90 216	85.06 136	85.19 106	87.25 149	74.29 200

viewdifsd2359ckpt07		78.49 153	83.75 142	72.35 166	80.46 156	75.49 180	83.92 149	53.96 235	85.53 84	67.94 176	91.12 62	96.06 45	66.18 152	81.43 187	75.39 208	81.62 220	81.26 136

OpenMVS	75.38 16	78.44 154	81.39 165	74.99 148	80.46 156	79.85 124	79.99 186	58.31 207	77.34 166	73.85 130	77.19 203	82.33 211	68.60 126	84.67 144	81.95 140	88.72 128	86.40 87

pm-mvs1		78.21 159	85.68 96	69.50 197	80.38 158	75.73 175	76.25 216	65.04 132	87.59 57	54.47 228	93.16 30	95.99 51	54.20 225	86.37 119	82.98 133	86.64 158	77.96 182

viewmanbaseed2359cas		79.90 134	83.96 135	75.17 144	80.25 159	77.62 154	84.62 143	58.25 208	83.22 106	74.92 120	89.50 85	95.33 74	67.20 141	83.05 160	77.84 179	85.76 181	81.18 139

v148		79.33 145	82.32 160	75.84 136	80.14 160	75.74 174	81.98 167	57.06 213	81.51 131	79.36 86	89.42 87	96.42 33	71.32 102	81.54 186	75.29 209	85.20 187	76.32 188

pmmvs-eth3d		79.64 139	82.06 162	76.83 126	80.05 161	72.64 209	87.47 102	66.59 111	80.83 141	73.50 133	89.32 90	93.20 122	67.78 132	80.78 193	81.64 145	85.58 185	76.01 190

testgi		68.20 225	76.05 206	59.04 244	79.99 162	67.32 233	81.16 174	51.78 244	84.91 93	39.36 266	73.42 230	95.19 78	32.79 266	76.54 218	70.40 228	69.14 251	64.55 238

DI_MVS_pp		77.64 161	79.64 176	75.31 142	79.87 163	76.89 163	81.55 171	63.64 150	76.21 170	72.03 144	85.59 143	82.97 207	66.63 147	79.27 203	77.78 181	88.14 140	78.76 177

FA-MVS(training)		78.93 150	80.63 170	76.93 125	79.79 164	75.57 179	85.44 130	61.95 175	77.19 167	78.97 88	84.82 150	82.47 208	66.43 151	84.09 151	80.13 158	89.02 121	80.15 160

Fast-Effi-MVS+-dtu		76.92 165	77.18 192	76.62 129	79.55 165	79.17 131	84.80 141	77.40 30	64.46 237	68.75 167	70.81 243	86.57 188	63.36 172	81.74 183	81.76 143	85.86 178	75.78 193

thres400		73.13 201	76.99 195	68.62 204	79.46 166	74.93 185	77.23 206	61.23 184	75.54 176	52.31 242	72.20 234	77.10 229	54.89 221	82.92 162	82.62 135	86.57 160	73.66 209

QAPM		80.43 128	84.34 124	75.86 135	79.40 167	82.06 103	79.86 189	61.94 176	83.28 105	74.73 125	81.74 170	85.44 196	70.97 107	84.99 141	84.71 113	88.29 137	88.14 75

DELS-MVS		79.71 137	83.74 143	75.01 147	79.31 168	82.68 96	84.79 142	60.06 194	75.43 178	69.09 163	86.13 137	89.38 167	67.16 142	85.12 135	83.87 121	89.65 109	83.57 109
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
3Dnovator	79.41 10	82.21 101	86.07 89	77.71 115	79.31 168	84.61 76	87.18 106	61.02 185	85.65 80	76.11 111	85.07 147	85.38 197	70.96 108	87.22 110	86.47 88	91.66 81	88.12 76

ET-MVSNet_ETH3D		74.71 188	74.19 217	75.31 142	79.22 170	75.29 181	82.70 160	64.05 143	65.45 231	70.96 153	77.15 204	57.70 260	65.89 153	84.40 146	81.65 144	89.03 120	77.67 183

test-LLR		62.15 247	59.46 265	65.29 227	79.07 171	52.66 261	69.46 252	62.93 159	50.76 267	53.81 235	63.11 258	58.91 256	52.87 236	66.54 255	62.34 250	73.59 236	61.87 249

test0.0.03 1		61.79 249	65.33 243	57.65 247	79.07 171	64.09 243	68.51 257	62.93 159	61.59 250	33.71 269	61.58 260	71.58 244	33.43 265	70.95 244	68.68 238	68.26 253	58.82 256

baseline1		69.62 218	73.55 221	65.02 230	78.95 173	70.39 218	71.38 243	62.03 174	70.97 208	47.95 253	78.47 193	68.19 246	47.77 250	79.65 202	76.94 196	82.05 216	70.27 221

MVS_Test		76.72 167	79.40 178	73.60 155	78.85 174	74.99 184	79.91 187	61.56 179	69.67 212	72.44 140	85.98 140	90.78 156	63.50 170	78.30 207	75.74 204	85.33 186	80.31 156

FE-MVSNET2		78.59 151	83.83 140	72.48 165	78.67 175	75.81 173	79.06 196	63.78 149	85.63 81	65.66 189	87.12 124	96.21 42	59.04 201	83.72 154	82.07 139	88.67 130	76.26 189

FMVSNet1		78.20 160	84.83 114	70.46 185	78.62 176	79.03 133	77.90 203	67.53 106	83.02 109	55.10 226	87.19 122	93.18 123	55.65 217	85.57 125	83.39 126	87.98 141	82.40 125

viewdifsd2359ckpt11		78.29 157	84.30 126	71.27 175	78.48 177	74.68 192	82.25 164	55.40 223	82.45 115	60.97 208	91.34 56	96.58 28	65.48 157	85.14 133	78.70 168	85.05 195	81.21 137

viewmsd2359difaftdt		78.29 157	84.30 126	71.27 175	78.48 177	74.69 191	82.25 164	55.40 223	82.45 115	60.98 207	91.34 56	96.59 27	65.48 157	85.14 133	78.70 168	85.05 195	81.21 137

onestephybrid01		78.35 155	82.42 159	73.60 155	78.45 179	76.56 165	83.15 153	62.05 173	74.24 186	69.57 160	87.57 113	94.27 105	63.94 165	84.24 149	79.08 167	84.43 200	81.03 143

GA-MVS		75.01 187	76.39 200	73.39 160	78.37 180	75.66 177	80.03 185	58.40 206	70.51 209	75.85 115	83.24 160	76.14 233	63.75 166	77.28 212	76.62 197	83.97 204	75.30 197

thres200		72.41 208	76.00 207	68.21 207	78.28 181	76.28 168	74.94 231	62.56 167	72.14 204	51.35 247	69.59 250	76.51 232	54.89 221	85.06 136	80.51 153	87.25 149	71.92 217

EPNet_dtu		71.90 211	73.03 223	70.59 183	78.28 181	61.64 248	82.44 162	64.12 141	63.26 241	69.74 158	71.47 237	82.41 209	51.89 242	78.83 205	78.01 175	77.07 231	75.60 195
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs4		75.92 177	77.48 191	74.10 154	78.21 183	70.94 216	84.06 147	64.78 134	75.13 180	68.47 171	84.12 155	83.32 204	64.74 163	75.93 221	79.14 165	84.31 201	73.77 207

PM-MVS		80.42 129	83.63 144	76.67 128	78.04 184	72.37 212	87.14 107	60.18 193	80.13 148	71.75 146	86.12 138	93.92 109	77.08 56	86.56 117	85.12 107	85.83 179	81.18 139

thres100view900		69.86 217	72.97 224	66.24 220	77.97 185	72.49 210	73.29 237	59.12 201	66.81 223	50.82 248	67.30 252	75.67 236	50.54 244	78.24 208	79.40 162	85.71 182	70.88 219

tfpn200view9		72.01 210	75.40 212	68.06 209	77.97 185	76.44 166	77.04 208	62.67 165	66.81 223	50.82 248	67.30 252	75.67 236	52.46 241	85.06 136	82.64 134	87.41 147	73.86 206

dmvs_re		68.11 226	70.60 227	65.21 228	77.91 187	63.73 245	76.72 211	59.65 197	55.93 259	47.79 254	59.79 262	79.91 218	49.72 245	82.48 171	76.98 195	79.48 225	75.41 196

Vis-MVSNet		83.32 88	88.12 69	77.71 115	77.91 187	83.44 87	90.58 63	69.49 82	81.11 138	67.10 182	89.85 80	91.48 149	71.71 100	91.34 62	89.37 66	89.48 113	90.26 52
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchMatch-RL		76.05 175	76.64 198	75.36 141	77.84 189	69.87 222	81.09 176	63.43 153	71.66 205	68.34 172	71.70 235	81.76 212	74.98 76	84.83 142	83.44 125	86.45 165	73.22 214

viewmamba		78.33 156	82.83 156	73.07 164	77.55 190	75.72 176	82.97 157	60.76 188	78.06 163	70.14 157	89.47 86	94.50 101	63.04 173	83.55 156	78.24 174	83.99 203	80.28 157

dtuplus		76.59 168	80.58 171	71.94 170	77.50 191	73.54 198	81.21 173	59.20 200	76.13 171	67.10 182	86.78 129	93.90 110	63.03 174	80.39 198	74.68 210	83.59 208	78.65 178

CANet_DTU		75.04 185	78.45 181	71.07 178	77.27 192	77.96 148	83.88 150	58.00 209	64.11 238	68.67 168	75.65 219	88.37 176	53.92 228	82.05 176	81.11 146	84.67 198	79.88 163

MS-PatchMatch		71.18 215	73.99 219	67.89 212	77.16 193	71.76 214	77.18 207	56.38 215	67.35 221	55.04 227	74.63 224	75.70 235	62.38 177	76.62 216	75.97 203	79.22 228	75.90 192

viewmambaseed2359dif		76.20 173	80.07 174	71.68 173	76.99 194	73.91 196	80.81 177	59.23 199	74.86 182	66.65 185	86.44 132	93.44 120	62.91 175	79.19 204	73.77 214	83.49 209	78.89 174

new-patchmatchnet		62.59 245	73.79 220	49.53 261	76.98 195	53.57 259	53.46 273	54.64 230	85.43 86	28.81 271	91.94 46	96.41 34	25.28 269	76.80 214	53.66 265	57.99 265	58.69 257

GBi-Net		73.17 198	77.64 187	67.95 210	76.76 196	77.36 157	75.77 223	64.57 135	62.99 244	51.83 244	76.05 213	77.76 226	52.73 238	85.57 125	83.39 126	86.04 173	80.37 152

PVSNet_BlendedMVS		76.45 171	78.12 183	74.49 151	76.76 196	78.46 139	79.65 190	63.26 157	65.42 232	73.15 135	75.05 222	88.96 171	66.51 149	82.73 166	77.66 182	87.61 145	78.60 179

PVSNet_Blended		76.45 171	78.12 183	74.49 151	76.76 196	78.46 139	79.65 190	63.26 157	65.42 232	73.15 135	75.05 222	88.96 171	66.51 149	82.73 166	77.66 182	87.61 145	78.60 179

test1		73.17 198	77.64 187	67.95 210	76.76 196	77.36 157	75.77 223	64.57 135	62.99 244	51.83 244	76.05 213	77.76 226	52.73 238	85.57 125	83.39 126	86.04 173	80.37 152

FMVSNet2		74.43 189	79.70 175	68.27 206	76.76 196	77.36 157	75.77 223	65.36 130	72.28 201	52.97 238	81.92 168	85.61 195	52.73 238	80.66 194	79.73 160	86.04 173	80.37 152

IB-MVS	71.28 17	75.21 184	77.00 194	73.12 163	76.76 196	77.45 156	83.05 155	58.92 203	63.01 243	64.31 193	59.99 261	87.57 182	68.64 123	86.26 121	82.34 136	87.05 151	82.36 126
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
thisisatest0515		81.18 119	84.32 125	77.52 120	76.73 202	74.84 186	85.06 140	61.37 182	81.05 139	73.95 129	88.79 100	89.25 170	75.49 71	85.98 122	84.78 111	92.53 70	85.56 93

IterMVS-SCA-FT		77.23 163	79.18 179	74.96 149	76.67 203	79.85 124	75.58 230	61.34 183	73.10 192	73.79 131	86.23 136	79.61 219	79.00 39	80.28 199	75.50 207	83.41 211	79.70 166

FC-MVSNet-test		75.91 178	83.59 145	66.95 216	76.63 204	69.07 225	85.33 134	64.97 133	84.87 94	41.95 261	93.17 29	87.04 183	47.78 249	91.09 69	85.56 103	85.06 190	74.34 199

Anonymous20231206		67.28 229	73.41 222	60.12 243	76.45 205	63.61 246	74.21 234	56.52 214	76.35 168	42.23 260	75.81 218	90.47 159	41.51 258	74.52 224	69.97 230	69.83 249	63.17 245

usedtu_dtu_shiyan1		73.59 193	77.49 190	69.05 200	76.40 206	72.84 203	75.67 228	60.47 189	74.12 187	59.35 210	79.02 183	88.33 177	56.25 213	77.46 210	77.81 180	86.14 170	72.84 216

gbinet_0.2-2-1-0.02		73.88 191	76.94 196	70.31 186	76.23 207	74.72 189	77.93 202	57.54 212	72.77 198	64.37 192	80.14 174	85.20 198	60.60 183	76.92 213	71.41 224	85.16 189	77.45 185

diffmvs_AUTHOR		77.61 162	82.84 155	71.49 174	76.16 208	74.80 187	81.22 172	57.90 210	79.89 151	68.06 173	90.49 70	94.78 90	62.29 178	81.77 180	77.04 193	83.33 212	81.14 141

blended_shiyan6		73.23 196	76.38 201	69.56 195	75.93 209	73.03 201	76.58 213	55.73 219	74.84 183	63.74 195	79.66 180	86.74 186	59.75 187	75.14 223	70.97 226	85.65 184	74.26 201

blended_shiyan8		73.23 196	76.36 202	69.57 194	75.91 210	73.04 200	76.56 214	55.74 218	74.84 183	63.75 194	79.69 179	86.62 187	59.80 186	75.17 222	71.00 225	85.67 183	74.20 204

baseline2		68.71 223	68.34 234	69.14 198	75.69 211	69.70 223	76.60 212	55.53 221	60.13 252	62.07 205	66.76 254	60.35 253	60.77 182	76.53 219	74.03 213	84.19 202	70.88 219

diffmvs		76.74 166	81.61 164	71.06 179	75.64 212	74.45 193	80.68 179	57.57 211	77.48 164	67.62 179	88.95 96	93.94 108	61.98 180	79.74 200	76.18 199	82.85 213	80.50 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tttt0517		75.86 179	76.23 204	75.42 140	75.55 213	74.06 194	82.73 159	60.31 190	69.24 214	70.24 156	79.18 182	58.79 258	72.17 94	84.49 145	83.08 131	91.54 82	84.80 95

wanda-best-256-512		72.50 206	75.48 210	69.03 201	75.29 214	72.66 205	75.85 218	55.31 225	73.43 188	63.41 197	78.69 189	86.04 191	59.27 197	74.34 227	69.81 231	85.06 190	73.37 212

FE-blended-shiyan7		72.50 206	75.48 210	69.03 201	75.29 214	72.66 205	75.85 218	55.31 225	73.43 188	63.41 197	78.69 189	86.04 191	59.27 197	74.34 227	69.81 231	85.06 190	73.37 212

usedtu_blend_shiyan5		67.09 230	67.69 237	66.40 219	75.29 214	72.66 205	69.07 256	55.31 225	73.43 188	53.98 230	53.29 266	56.81 264	59.69 188	74.34 227	69.81 231	85.06 190	73.46 210

FE-MVSNET3		67.68 228	67.80 236	67.53 213	75.29 214	72.66 205	75.85 218	55.31 225	73.43 188	53.98 230	53.29 266	56.81 264	59.69 188	74.34 227	69.81 231	85.06 190	74.26 201

thisisatest0530		75.54 182	75.95 208	75.05 145	75.08 218	73.56 197	82.15 166	60.31 190	69.17 215	69.32 161	79.02 183	58.78 259	72.17 94	83.88 152	83.08 131	91.30 87	84.20 102

FMVSNet3		71.40 214	75.20 215	66.97 215	75.00 219	76.59 164	74.29 233	64.57 135	62.99 244	51.83 244	76.05 213	77.76 226	51.49 243	76.58 217	77.03 194	84.62 199	79.43 170

hybridnocas07		76.05 175	81.19 166	70.05 189	74.83 220	72.76 204	80.26 183	56.12 216	75.67 175	67.35 180	88.47 103	93.87 111	59.44 196	81.83 178	76.14 200	82.29 215	79.61 167

tpm cat1		64.79 237	62.74 253	67.17 214	74.61 221	65.91 239	76.18 217	59.32 198	64.88 235	66.41 187	71.21 240	53.56 274	59.17 199	61.53 265	58.16 258	67.33 255	63.95 240

hybrid		75.61 181	80.58 171	69.81 191	74.36 222	72.39 211	80.17 184	55.48 222	75.16 179	67.30 181	87.14 123	93.52 118	59.56 195	81.16 188	75.66 206	82.01 217	79.03 172

FE-MVSNET		75.03 186	80.98 168	68.08 208	73.53 223	71.43 215	75.74 226	59.74 196	81.81 124	58.16 213	82.47 163	93.51 119	55.42 219	83.18 159	80.51 153	85.90 177	73.94 205

UGNet		79.62 140	85.91 93	72.28 168	73.52 224	83.91 79	86.64 115	69.51 81	79.85 152	62.57 202	85.82 141	89.63 163	53.18 232	88.39 99	87.35 80	88.28 138	86.43 86
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
our_test_3					73.27 225	70.91 217	83.26 152

HyFIR lowres test		73.29 195	74.14 218	72.30 167	73.08 226	78.33 141	83.12 154	62.41 170	63.81 239	62.13 204	76.67 208	78.50 223	71.09 105	74.13 231	77.47 187	81.98 218	70.10 222

MIMVSNet1		73.40 194	81.85 163	63.55 231	72.90 227	64.37 242	84.58 144	53.60 237	90.84 23	53.92 234	87.75 111	96.10 43	45.31 253	85.37 132	79.32 163	70.98 247	69.18 227

CostFormer		66.81 232	66.94 239	66.67 217	72.79 228	68.25 228	79.55 195	55.57 220	65.52 230	62.77 201	76.98 205	60.09 254	56.73 210	65.69 257	62.35 249	72.59 239	69.71 224

CR-MVSNet		69.56 219	68.34 234	70.99 180	72.78 229	67.63 230	64.47 261	67.74 103	59.93 253	72.30 141	80.10 175	56.77 268	65.04 161	71.64 241	72.91 218	83.61 207	69.40 225

CVMVSNet		75.65 180	77.62 189	73.35 162	71.95 230	69.89 221	83.04 156	60.84 187	69.12 216	68.76 166	79.92 178	78.93 222	73.64 88	81.02 191	81.01 148	81.86 219	83.43 110

IterMVS		73.62 192	76.53 199	70.23 187	71.83 231	77.18 161	80.69 178	53.22 239	72.23 202	66.62 186	85.21 145	78.96 221	69.54 119	76.28 220	71.63 222	79.45 226	74.25 203
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		67.02 231	63.99 247	70.56 184	71.55 232	67.63 230	75.81 221	69.44 83	59.93 253	63.24 199	64.32 256	47.51 277	59.68 191	70.37 246	69.64 235	83.64 206	68.49 228

dps		65.14 234	64.50 245	65.89 225	71.41 233	65.81 240	71.44 242	61.59 178	58.56 256	61.43 206	75.45 220	52.70 275	58.06 206	69.57 248	64.65 244	71.39 244	64.77 236

MDTV_nov1_ep13_2view		72.96 203	75.59 209	69.88 190	71.15 234	64.86 241	82.31 163	54.45 232	76.30 169	78.32 95	86.52 131	91.58 145	61.35 181	76.80 214	66.83 242	71.70 240	66.26 232

TAMVS		63.02 239	69.30 230	55.70 252	70.12 235	56.89 254	69.63 250	45.13 255	70.23 210	38.00 267	77.79 195	75.15 238	42.60 255	74.48 225	72.80 220	68.70 252	57.75 260

tpm		62.79 241	63.25 250	62.26 237	70.09 236	53.78 258	71.65 241	47.31 253	65.72 229	76.70 108	80.62 173	56.40 271	48.11 248	64.20 261	58.54 256	59.70 262	63.47 242

V42		79.59 141	83.59 145	74.93 150	69.61 237	77.05 162	86.59 116	55.84 217	78.42 162	77.29 105	89.84 81	95.08 83	74.12 81	83.05 160	80.11 159	86.12 171	81.59 134

PatchmatchNet		64.81 236	63.74 248	66.06 224	69.21 238	58.62 252	73.16 238	60.01 195	65.92 227	66.19 188	76.27 210	59.09 255	60.45 185	66.58 254	61.47 255	67.33 255	58.24 258
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 1792x2688		68.80 222	71.09 225	66.13 222	69.11 239	68.88 227	78.98 198	54.68 229	61.63 249	56.69 217	71.56 236	78.39 224	67.69 133	72.13 238	72.01 221	69.63 250	73.02 215

WB-MVS		72.91 204	82.95 151	61.21 241	68.59 240	73.96 195	73.65 236	61.48 180	90.88 22	42.55 259	94.18 17	95.80 58	53.02 234	85.42 131	75.73 205	67.97 254	64.65 237

MIMVSNet		63.02 239	69.02 231	56.01 249	68.20 241	59.26 251	70.01 248	53.79 236	71.56 206	41.26 264	71.38 238	82.38 210	36.38 262	71.43 243	67.32 241	66.45 257	59.83 255

CMPMVS	55.74 18	71.56 212	76.26 203	66.08 223	68.11 242	63.91 244	63.17 263	50.52 248	68.79 219	75.49 116	70.78 244	85.67 194	63.54 169	81.58 184	77.20 189	75.63 233	85.86 89
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SCA		68.54 224	67.52 238	69.73 192	67.79 243	75.04 182	76.96 209	68.94 89	66.41 225	67.86 177	74.03 226	60.96 251	65.55 156	68.99 249	65.67 243	71.30 245	61.54 252

EU-MVSNet		76.48 170	80.53 173	71.75 172	67.62 244	70.30 219	81.74 169	54.06 234	75.47 177	71.01 152	80.10 175	93.17 124	73.67 86	83.73 153	77.85 178	82.40 214	83.07 114

tpmrst		59.42 253	60.02 263	58.71 245	67.56 245	53.10 260	66.99 258	51.88 243	63.80 240	57.68 214	76.73 207	56.49 270	48.73 247	56.47 269	55.55 261	59.43 263	58.02 259

pmmvs5		68.91 221	74.35 216	62.56 235	67.45 246	66.78 235	71.70 240	51.47 245	67.17 222	56.25 219	82.41 165	88.59 175	47.21 251	73.21 237	74.23 212	81.30 221	68.03 229

MDTV_nov1_ep13		64.96 235	64.77 244	65.18 229	67.08 247	62.46 247	75.80 222	51.10 247	62.27 248	69.74 158	74.12 225	62.65 249	55.64 218	68.19 251	62.16 253	71.70 240	61.57 251

E-PMN		59.07 255	62.79 252	54.72 253	67.01 248	47.81 268	60.44 267	43.40 256	72.95 194	44.63 257	70.42 246	73.17 241	58.73 203	80.97 192	51.98 266	54.14 268	42.26 270

0.4-1-1-0.1		62.35 246	62.12 255	62.60 233	66.85 249	68.23 229	70.78 244	49.40 249	52.78 264	54.44 229	59.25 263	57.42 261	53.76 229	65.41 258	64.40 245	80.41 222	67.37 230

dtuonlycased		72.06 209	81.13 167	61.48 239	66.59 250	76.01 170	84.21 146	41.25 260	79.57 155	31.88 270	81.89 169	89.95 162	69.64 117	85.52 129	77.35 188	75.27 235	77.61 184

pmnet_mix02		62.60 244	70.81 226	53.02 257	66.56 251	50.44 265	62.81 264	46.84 254	79.13 159	43.76 258	87.45 115	90.75 157	39.85 259	70.48 245	57.09 259	58.27 264	60.32 254

baseline		69.33 220	75.37 213	62.28 236	66.54 252	66.67 237	73.95 235	48.07 251	66.10 226	59.26 211	82.45 164	86.30 189	54.44 224	74.42 226	73.25 217	71.42 243	78.43 181

N_pmnet		54.95 262	65.90 241	42.18 262	66.37 253	43.86 271	57.92 269	39.79 261	79.54 156	17.24 277	86.31 133	87.91 180	25.44 267	64.68 259	51.76 268	46.33 272	47.23 267

MVSTER		68.08 227	69.73 229	66.16 221	66.33 254	70.06 220	75.71 227	52.36 242	55.18 262	58.64 212	70.23 248	56.72 269	57.34 208	79.68 201	76.03 201	86.61 159	80.20 159

EMVS		58.97 256	62.63 254	54.70 254	66.26 255	48.71 266	61.74 265	42.71 257	72.80 197	46.00 256	73.01 232	71.66 242	57.91 207	80.41 196	50.68 269	53.55 269	41.11 271

0.3-1-1-0.015		61.14 250	60.59 259	61.78 238	65.65 256	67.14 234	69.76 249	48.31 250	51.00 266	53.98 230	56.11 265	56.81 264	53.29 231	63.79 263	63.19 247	79.66 224	66.07 233

0.4-1-1-0.2		60.88 251	60.45 260	61.38 240	65.29 257	66.73 236	69.11 255	48.01 252	50.14 269	53.73 237	57.22 264	57.01 263	52.91 235	63.57 264	62.64 248	79.23 227	65.82 234

anonymousdsp		85.62 63	90.53 49	79.88 95	64.64 258	76.35 167	96.28 12	53.53 238	85.63 81	81.59 69	92.81 35	97.71 12	86.88 2	94.56 25	92.83 25	96.35 6	93.84 9

PatchmatchNet2					64.26 259	41.70 272	56.82 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
EPMVS		56.62 259	59.77 264	52.94 258	62.41 260	50.55 264	60.66 266	52.83 240	65.15 234	41.80 262	77.46 201	57.28 262	42.68 254	59.81 267	54.82 262	57.23 266	53.35 263

blend_shiyan4		63.43 238	63.66 249	63.17 232	62.30 261	71.99 213	65.44 260	52.82 241	48.52 270	53.98 230	53.29 266	56.81 264	59.69 188	71.98 240	69.57 236	84.81 197	73.46 210

FMVSNet5		56.37 260	60.14 262	51.98 260	60.83 262	59.58 250	66.85 259	42.37 258	52.68 265	41.33 263	47.09 271	54.68 272	35.28 263	73.88 232	70.77 227	65.24 258	62.26 248

ADS-MVSNet		56.89 258	61.09 257	52.00 259	59.48 263	48.10 267	58.02 268	54.37 233	72.82 196	49.19 251	75.32 221	65.97 247	37.96 261	59.34 268	54.66 263	52.99 270	51.42 265

new_pmnet		52.29 263	63.16 251	39.61 264	58.89 264	44.70 270	48.78 275	34.73 265	65.88 228	17.85 275	73.42 230	80.00 217	23.06 270	67.00 253	62.28 252	54.36 267	48.81 266

dtuonly		62.71 243	68.55 233	55.89 250	58.38 265	55.27 256	74.41 232	36.47 263	64.61 236	48.30 252	76.18 212	80.16 216	54.95 220	71.99 239	67.49 240	62.86 259	64.12 239

MVS-HIRNet		59.74 252	58.74 268	60.92 242	57.74 266	45.81 269	56.02 271	58.69 205	55.69 260	65.17 190	70.86 242	71.66 242	56.75 209	61.11 266	53.74 264	71.17 246	52.28 264

PatchT		66.25 233	66.76 240	65.67 226	55.87 267	60.75 249	70.17 246	59.00 202	59.80 255	72.30 141	78.68 191	54.12 273	65.04 161	71.64 241	72.91 218	71.63 242	69.40 225

test-mter		59.39 254	61.59 256	56.82 248	53.21 268	54.82 257	73.12 239	26.57 269	53.19 263	56.31 218	64.71 255	60.47 252	56.36 212	68.69 250	64.27 246	75.38 234	65.00 235

CHOSEN 280x420		56.32 261	58.85 267	53.36 256	51.63 269	39.91 273	69.12 254	38.61 262	56.29 258	36.79 268	48.84 270	62.59 250	63.39 171	73.61 235	67.66 239	60.61 260	63.07 246

TESTMET0.1,1		57.21 257	59.46 265	54.60 255	50.95 270	52.66 261	69.46 252	26.91 268	50.76 267	53.81 235	63.11 258	58.91 256	52.87 236	66.54 255	62.34 250	73.59 236	61.87 249

pmmvs3		62.72 242	68.71 232	55.74 251	50.74 271	57.10 253	70.05 247	28.82 267	61.57 251	57.39 216	71.19 241	85.73 193	53.96 227	73.36 236	69.43 237	73.47 238	62.55 247

MDA-MVSNet-bldmvs		76.51 169	82.87 154	69.09 199	50.71 272	74.72 189	84.05 148	60.27 192	81.62 128	71.16 151	88.21 107	91.58 145	69.62 118	92.78 45	77.48 186	78.75 230	73.69 208

PMMVS		61.98 248	65.61 242	57.74 246	45.03 273	51.76 263	69.54 251	35.05 264	55.49 261	55.32 225	68.23 251	78.39 224	58.09 205	70.21 247	71.56 223	83.42 210	63.66 241

PMMVS2		48.13 265	64.06 246	29.55 265	44.06 274	36.69 274	51.95 274	29.97 266	74.75 185	8.90 279	76.02 216	91.24 153	7.53 274	73.78 233	55.91 260	34.87 274	40.01 272

MVE	41.12 19	51.80 264	60.92 258	41.16 263	35.21 275	34.14 275	48.45 276	41.39 259	69.11 217	19.53 274	63.33 257	73.80 239	63.56 168	67.19 252	61.51 254	38.85 273	57.38 261
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		15.19 268	17.84 271	12.09 269	31.85 276	14.34 277	3.33 281	13.23 270	15.35 275	3.95 280	18.75 275	17.87 282	14.99 272	18.62 273	15.68 273	5.20 278	24.28 274

tmp_tt				13.54 268	16.73 277	6.42 279	8.49 279	2.36 274	28.69 273	27.44 272	18.40 276	13.51 283	3.70 276	33.23 270	36.26 270	22.54 277

MVS_clip		13.15 269	20.01 270	5.15 270	9.47 278	8.55 278	2.73 282	2.62 273	19.66 274	0.76 284	26.96 274	24.20 281	12.53 273	17.90 274	16.55 272	2.80 279	26.23 273

VLMVS		2.47 271	3.49 273	1.28 271	2.52 279	1.70 281	0.71 283	0.70 275	3.87 277	0.83 283	3.23 278	5.07 285	2.15 277	2.21 275	1.81 275	0.75 280	6.54 277

test_method		22.69 267	26.99 269	17.67 267	2.13 280	4.31 280	27.50 277	4.53 272	37.94 271	24.52 273	36.20 273	51.40 276	15.26 271	29.86 271	17.09 271	32.07 275	12.16 276

MVS_baseline		3.67 270	6.07 272	0.86 272	1.13 281	0.44 283	0.17 286	0.00 279	5.57 276	0.00 286	6.81 277	7.78 284	3.86 275	2.15 276	2.53 274	0.02 283	17.25 275

test123		1.06 272	1.41 274	0.64 273	0.39 282	0.48 282	0.52 285	0.25 277	1.11 279	1.37 282	2.01 280	1.98 286	0.87 278	1.43 277	1.27 276	0.46 282	1.62 279

testmvs		0.93 273	1.37 275	0.41 274	0.36 283	0.36 284	0.62 284	0.39 276	1.48 278	0.18 285	2.41 279	1.31 287	0.41 279	1.25 278	1.08 277	0.48 281	1.68 278

GG-mvs-BLEND		41.63 266	60.36 261	19.78 266	0.14 284	66.04 238	55.66 272	0.17 278	57.64 257	2.42 281	51.82 269	69.42 245	0.28 280	64.11 262	58.29 257	60.02 261	55.18 262

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

PatchmatchNet1												87.99 179	25.44 267	64.23 260	51.81 267	46.37 271	47.19 268
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										17.36 276	86.27 135
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							94.55 31	72.48 64		73.73 132						91.99 77

RE-MVS-def										87.10 28

9.14												89.43 166

MTAPA										89.37 9		94.85 87

MTMP										90.54 5		95.16 80

Patchmatch-RL test							4.13 280

NP-MVS									78.65 161

Patchmtry						56.88 255	64.47 261	67.74 103		72.30 141

DeepMVS_CX						17.78 276	20.40 278	6.69 271	31.41 272	9.80 278	38.61 272	34.88 280	33.78 264	28.41 272		23.59 276	45.77 269

High-resolution multi-view benchmark