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 33	91.44 39	86.20 28	94.88 1	89.84 34	94.76 29	77.45 28	85.41 73	74.79 107	88.83 80	88.90 142	78.67 40	96.06 7	95.45 4	96.66 3	95.58 2

DTE-MVSNet		88.99 35	92.77 12	84.59 43	93.31 2	88.10 49	90.96 53	83.09 2	91.38 14	76.21 96	96.03 2	98.04 8	70.78 106	95.65 14	92.32 32	93.18 56	87.84 73

mPP-MVS					93.05 3							95.77 44

MP-MVS		90.84 6	91.95 34	89.55 3	92.92 4	90.90 19	96.56 6	79.60 11	86.83 59	88.75 12	89.00 76	94.38 80	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 39	92.92 9	84.11 52	92.92 4	88.05 51	90.83 55	82.67 5	91.04 18	74.83 106	95.97 3	98.47 3	70.38 107	95.70 13	92.43 30	93.05 60	88.78 65

HPM-MVS++		88.74 40	89.54 52	87.80 15	92.58 6	85.69 69	95.10 26	78.01 22	87.08 56	87.66 19	87.89 89	92.07 109	80.28 30	90.97 69	91.41 43	93.17 57	91.69 37

DVP-MVS++		90.50 10	94.18 4	86.21 27	92.52 7	90.29 28	95.29 22	76.02 41	94.24 5	82.82 54	95.84 5	97.56 15	76.82 55	93.13 38	91.20 44	93.78 45	97.01 1

PS-CasMVS		89.07 32	93.23 7	84.21 50	92.44 8	88.23 48	90.54 62	82.95 3	90.50 26	75.31 103	95.80 6	98.37 6	71.16 100	96.30 5	93.32 21	92.88 61	90.11 50

CP-MVSNet		88.71 41	92.63 15	84.13 51	92.39 9	88.09 50	90.47 66	82.86 4	88.79 42	75.16 104	94.87 9	97.68 13	71.05 102	96.16 6	93.18 23	92.85 62	89.64 55

CP-MVS		91.09 5	92.33 25	89.65 2	92.16 10	90.41 27	96.46 10	80.38 8	88.26 45	89.17 10	87.00 101	96.34 30	83.95 10	95.77 11	94.72 7	95.81 17	93.78 10

ACMMPR		91.30 4	92.88 11	89.46 4	91.92 11	91.61 5	96.60 5	79.46 14	90.08 31	88.53 13	89.54 67	95.57 48	84.25 7	95.24 20	94.27 12	95.97 11	93.85 8

WR-MVS_H		88.99 35	93.28 6	83.99 53	91.92 11	89.13 40	91.95 47	83.23 1	90.14 30	71.92 126	95.85 4	98.01 10	71.83 96	95.82 9	93.19 22	93.07 59	90.83 47

SR-MVS					91.82 13			80.80 7				95.53 50

PGM-MVS		90.42 11	91.58 37	89.05 5	91.77 14	91.06 13	96.51 7	78.94 16	85.41 73	87.67 18	87.02 100	95.26 58	83.62 12	95.01 23	93.94 15	95.79 19	93.40 20

APD-MVS		89.14 29	91.25 42	86.67 24	91.73 15	91.02 15	95.50 20	77.74 24	84.04 85	79.47 82	91.48 46	94.85 68	81.14 25	92.94 41	92.20 35	94.47 38	92.24 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SMA-MVS		90.13 15	92.26 27	87.64 17	91.68 16	90.44 26	95.22 24	77.34 32	90.79 23	87.80 16	90.42 58	92.05 111	79.05 35	93.89 32	93.59 18	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 60		91.62 17	87.97 53	84.48 124		88.64 44	87.93 15	87.38 95	94.82 70	74.53 76	89.14 89	83.86 117	85.94 153	86.84 78

TSAR-MVS + MP.		89.67 24	92.25 28	86.65 25	91.53 18	90.98 17	96.15 13	73.30 56	87.88 49	81.83 66	92.92 30	95.15 62	82.23 18	93.58 34	92.25 33	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 53	87.73 70	85.43 35	91.51 19	82.72 89	94.47 31	74.22 53	81.71 104	81.54 70	89.20 74	92.87 97	78.33 43	90.12 80	88.47 69	92.51 69	89.04 61

X-MVS		89.36 28	90.73 45	87.77 16	91.50 20	91.23 8	96.76 4	78.88 17	87.29 54	87.14 25	78.98 150	94.53 74	76.47 57	95.25 19	94.28 11	95.85 14	93.55 16

HFP-MVS		90.32 13	92.37 22	87.94 13	91.46 21	90.91 18	95.69 17	79.49 12	89.94 34	83.50 50	89.06 75	94.44 78	81.68 22	94.17 30	94.19 13	95.81 17	93.87 7

ACMM	80.67 7	90.67 7	92.46 19	88.57 7	91.35 22	89.93 32	96.34 11	77.36 30	90.17 29	86.88 29	87.32 96	96.63 23	83.32 13	95.79 10	94.49 9	96.19 9	92.91 26
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WR-MVS		89.79 23	93.66 5	85.27 37	91.32 23	88.27 46	93.49 38	79.86 10	92.75 9	75.37 102	96.86 1	98.38 5	75.10 71	95.93 8	94.07 14	96.46 5	89.39 57

SD-MVS		89.91 18	92.23 30	87.19 21	91.31 24	89.79 35	94.31 32	75.34 47	89.26 37	81.79 67	92.68 32	95.08 64	83.88 11	93.10 39	92.69 25	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 25	91.23 8	96.89 2			87.14 25		94.53 74				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 25		94.53 74				95.84 15

DeepC-MVS	83.59 4	90.37 12	92.56 18	87.82 14	91.26 27	92.33 3	94.72 30	80.04 9	90.01 32	84.61 42	93.33 23	94.22 81	80.59 27	92.90 43	92.52 28	95.69 21	92.57 28
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 20	88.56 8	91.24 28	91.60 6	96.49 9	77.53 26	87.89 48	86.87 30	87.24 98	96.46 25	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 17	91.73 35	87.97 12	91.21 29	90.29 28	96.51 7	78.00 23	86.33 62	85.32 40	88.23 86	94.67 72	82.08 20	95.13 22	93.88 16	94.72 35	93.59 13
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		89.86 19	91.96 33	87.42 19	91.00 30	90.08 30	96.00 15	76.61 36	89.28 35	87.73 17	90.04 60	91.80 115	78.71 38	94.36 28	93.82 17	94.48 37	94.32 6

CPTT-MVS		89.63 25	90.52 47	88.59 6	90.95 31	90.74 21	95.71 16	79.13 15	87.70 50	85.68 38	80.05 145	95.74 46	84.77 6	94.28 29	92.68 26	95.28 26	92.45 31

LGP-MVS_train		90.56 9	92.38 21	88.43 9	90.88 32	91.15 11	95.35 21	77.65 25	86.26 65	87.23 23	90.45 57	97.35 17	83.20 14	95.44 16	93.41 20	96.28 8	92.63 27

OPM-MVS		89.82 21	92.24 29	86.99 22	90.86 33	89.35 38	95.07 27	75.91 43	91.16 16	86.87 30	91.07 52	97.29 18	79.13 34	93.32 35	91.99 37	94.12 40	91.49 40
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	80.00 8	90.12 16	92.30 26	87.58 18	90.83 34	91.10 12	94.96 28	76.06 40	87.47 52	85.33 39	88.91 79	97.65 14	82.13 19	95.31 17	93.44 19	96.14 10	92.22 33
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
NCCC		86.74 52	87.97 68	85.31 36	90.64 35	87.25 59	93.27 40	74.59 49	86.50 60	83.72 46	75.92 178	92.39 103	77.08 53	91.72 53	90.68 48	92.57 67	91.30 42

MSP-MVS		88.51 42	91.36 40	85.19 39	90.63 36	92.01 4	95.29 22	77.52 27	90.48 27	80.21 76	90.21 59	96.08 34	76.38 59	88.30 97	91.42 41	91.12 89	91.01 44
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 63	91.12 43	78.71 99	90.48 37	83.72 79	81.76 141	82.41 6	93.84 6	64.43 163	95.41 7	98.76 1	63.72 143	93.63 33	89.74 57	89.47 108	82.74 114

APDe-MVS		89.85 20	92.91 10	86.29 26	90.47 38	91.34 7	96.04 14	76.41 39	91.11 17	78.50 89	93.44 22	95.82 42	81.55 23	93.16 37	91.90 38	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 14	87.39 20	90.16 39	88.75 42	93.64 36	75.78 44	90.00 33	83.70 47	92.97 29	92.22 106	86.13 4	97.01 3	96.79 2	94.94 28	90.96 45
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CNVR-MVS		86.93 51	88.98 56	84.54 44	90.11 40	87.41 58	93.23 41	73.47 55	86.31 63	82.25 61	82.96 133	92.15 107	76.04 62	91.69 54	90.69 47	92.17 74	91.64 39

TSAR-MVS + GP.		85.32 65	87.41 74	82.89 62	90.07 41	85.69 69	89.07 81	72.99 60	82.45 97	74.52 110	85.09 118	87.67 148	79.24 33	91.11 64	90.41 50	91.45 79	89.45 56

DeepC-MVS_fast	81.78 5	87.38 49	89.64 51	84.75 41	89.89 42	90.70 22	92.74 44	74.45 50	86.02 66	82.16 64	86.05 111	91.99 113	75.84 65	91.16 63	90.44 49	93.41 51	91.09 43
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 33	91.69 36	85.91 30	89.72 43	90.81 20	92.56 45	71.69 66	90.83 22	87.24 22	89.71 65	92.07 109	78.37 42	94.43 27	92.59 27	95.86 13	91.35 41

DPE-MVS		89.81 22	92.34 24	86.86 23	89.69 44	91.00 16	95.53 18	76.91 33	88.18 46	83.43 53	93.48 21	95.19 59	81.07 26	92.75 45	92.07 36	94.55 36	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 54	88.52 59	84.48 45	89.61 45	88.27 46	92.86 43	72.69 61	80.55 122	82.71 55	86.92 102	93.32 92	75.55 67	91.00 68	89.85 56	93.47 49	89.71 54

EPNet		79.36 125	79.44 147	79.27 98	89.51 46	77.20 140	88.35 87	77.35 31	68.27 180	74.29 111	76.31 171	79.22 180	59.63 159	85.02 130	85.45 100	86.49 145	84.61 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TSAR-MVS + ACMM		89.14 29	92.11 32	85.67 31	89.27 47	90.61 24	90.98 52	79.48 13	88.86 40	79.80 79	93.01 28	93.53 90	83.17 15	92.75 45	92.45 29	91.32 82	93.59 13

HQP-MVS		85.02 67	86.41 80	83.40 54	89.19 48	86.59 63	91.28 50	71.60 67	82.79 93	83.48 51	78.65 154	93.54 89	72.55 89	86.49 113	85.89 96	92.28 73	90.95 46

AdaColmap		84.15 73	85.14 97	83.00 59	89.08 49	87.14 61	90.56 61	70.90 69	82.40 98	80.41 73	73.82 189	84.69 162	75.19 70	91.58 57	89.90 55	91.87 76	86.48 80

DVP-MVS		89.40 27	92.69 13	85.56 34	89.01 50	89.85 33	93.72 35	75.42 45	92.28 11	80.49 72	94.36 13	94.87 67	81.46 24	92.49 49	91.42 41	93.27 53	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 51	92.86 2	95.51 19	72.17 62	94.95 4	91.27 3	94.11 17	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 52	93.57 1	97.27 1	78.23 21	95.55 1	93.00 1	93.98 18	96.01 38	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

TranMVSNet+NR-MVSNet		85.23 66	89.38 53	80.39 90	88.78 53	83.77 78	87.40 96	76.75 34	85.47 71	68.99 142	95.18 8	97.55 16	67.13 125	91.61 56	89.13 66	93.26 54	82.95 111

MVS_0304		85.73 59	87.94 69	83.14 57	88.68 54	87.98 52	93.34 39	70.74 71	79.78 129	82.37 58	88.32 85	89.44 135	71.34 98	90.61 73	89.64 60	92.40 70	89.79 53

SED-MVS		88.96 37	92.37 22	84.99 40	88.64 55	89.65 37	95.11 25	75.98 42	90.73 24	80.15 77	94.21 15	94.51 77	76.59 56	92.94 41	91.17 45	93.46 50	93.37 22

ACMH+	79.05 11	89.62 26	93.08 8	85.58 32	88.58 56	89.26 39	92.18 46	74.23 52	93.55 8	82.66 57	92.32 37	98.35 7	80.29 29	95.28 18	92.34 31	95.52 22	90.43 48

DU-MVS		84.88 69	88.27 64	80.92 79	88.30 57	83.59 81	87.06 102	78.35 19	80.64 120	70.49 134	92.67 33	96.91 21	68.13 117	91.79 51	89.29 65	93.20 55	83.02 108

Baseline_NR-MVSNet		82.79 91	86.51 77	78.44 103	88.30 57	75.62 154	87.81 90	74.97 48	81.53 108	66.84 157	94.71 12	96.46 25	66.90 126	91.79 51	83.37 124	85.83 155	82.09 119

UniMVSNet_NR-MVSNet		84.62 71	88.00 67	80.68 85	88.18 59	83.83 77	87.06 102	76.47 38	81.46 111	70.49 134	93.24 24	95.56 49	68.13 117	90.43 74	88.47 69	93.78 45	83.02 108

SF-MVS		87.85 48	90.95 44	84.22 49	88.17 60	87.90 54	90.80 56	71.80 65	89.28 35	82.70 56	89.90 62	95.37 55	77.91 47	91.69 54	90.04 54	93.95 44	92.47 29

CSCG		88.12 45	91.45 38	84.23 48	88.12 61	90.59 25	90.57 60	68.60 89	91.37 15	83.45 52	89.94 61	95.14 63	78.71 38	91.45 58	88.21 73	95.96 12	93.44 19

CLD-MVS		82.75 93	87.22 75	77.54 109	88.01 62	85.76 68	90.23 69	54.52 193	82.28 100	82.11 65	88.48 83	95.27 57	63.95 141	89.41 86	88.29 71	86.45 146	81.01 130
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 68	88.53 58	80.78 81	87.82 63	84.21 75	88.03 88	76.50 37	81.18 115	69.29 140	92.63 35	96.83 22	69.07 114	91.23 62	89.60 61	93.97 43	84.00 100

DPM-MVS		81.42 104	82.11 136	80.62 86	87.54 64	85.30 71	90.18 71	68.96 84	81.00 118	79.15 84	70.45 205	83.29 166	67.67 121	82.81 147	83.46 119	90.19 95	88.48 67

DeepPCF-MVS	81.61 6	87.95 47	90.29 49	85.22 38	87.48 65	90.01 31	93.79 34	73.54 54	88.93 39	83.89 45	89.40 70	90.84 126	80.26 31	90.62 72	90.19 53	92.36 71	92.03 35

EC-MVSNet		83.70 77	84.77 106	82.46 66	87.47 66	82.79 88	85.50 112	72.00 63	69.81 171	77.66 93	85.02 120	89.63 133	78.14 44	90.40 75	87.56 75	94.00 41	88.16 70

CANet		82.84 90	84.60 108	80.78 81	87.30 67	85.20 72	90.23 69	69.00 83	72.16 163	78.73 88	84.49 126	90.70 129	69.54 112	87.65 101	86.17 90	89.87 101	85.84 85

MCST-MVS		84.79 70	86.48 78	82.83 63	87.30 67	87.03 62	90.46 67	69.33 81	83.14 90	82.21 63	81.69 141	92.14 108	75.09 72	87.27 105	84.78 107	92.58 65	89.30 58

EIA-MVS		78.57 132	77.90 155	79.35 97	87.24 69	80.71 108	86.16 109	64.03 135	62.63 206	73.49 116	73.60 190	76.12 194	73.83 82	88.49 94	84.93 105	91.36 81	78.78 149

OMC-MVS		88.16 43	91.34 41	84.46 46	86.85 70	90.63 23	93.01 42	67.00 103	90.35 28	87.40 21	86.86 103	96.35 29	77.66 49	92.63 47	90.84 46	94.84 30	91.68 38

3Dnovator+	83.71 3	88.13 44	90.00 50	85.94 29	86.82 71	91.06 13	94.26 33	75.39 46	88.85 41	85.76 37	85.74 114	86.92 151	78.02 45	93.03 40	92.21 34	95.39 25	92.21 34

ETV-MVS		79.01 130	77.98 154	80.22 91	86.69 72	79.73 118	88.80 84	68.27 94	63.22 201	71.56 128	70.25 207	73.63 200	73.66 84	90.30 79	86.77 84	92.33 72	81.95 121

PHI-MVS		86.37 56	88.14 65	84.30 47	86.65 73	87.56 56	90.76 57	70.16 73	82.55 96	89.65 7	84.89 121	92.40 102	75.97 63	90.88 70	89.70 58	92.58 65	89.03 62

ACMH	78.40 12	88.94 38	92.62 16	84.65 42	86.45 74	87.16 60	91.47 49	68.79 87	95.49 2	89.74 6	93.55 20	98.50 2	77.96 46	94.14 31	89.57 62	93.49 47	89.94 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		84.35 72	87.55 71	80.62 86	86.38 75	82.24 94	86.75 105	64.02 136	84.24 81	78.17 92	89.38 71	95.03 66	78.78 37	89.95 82	86.33 89	89.59 105	85.65 87

IS_MVSNet		81.72 101	85.01 98	77.90 105	86.19 76	82.64 91	85.56 111	70.02 74	80.11 125	63.52 165	87.28 97	81.18 174	67.26 122	91.08 67	89.33 64	94.82 31	83.42 105

TPM-MVS					86.18 77	83.43 84	87.57 93			78.77 87	69.75 209	84.63 163	62.24 152			89.88 100	88.48 67
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 74	85.27 94	82.76 64	86.12 78	88.30 45	91.24 51	69.10 82	82.36 99	84.45 43	77.56 162	90.40 131	72.91 88	85.88 118	83.88 115	92.72 64	88.53 66
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		85.51 61	88.36 62	82.19 67	86.05 79	87.69 55	90.50 65	70.60 72	86.40 61	82.33 59	89.69 66	92.52 101	74.01 81	87.53 102	86.84 83	89.63 104	87.80 74

EPP-MVSNet		82.76 92	86.47 79	78.45 102	86.00 80	84.47 74	85.39 115	68.42 91	84.17 82	62.97 167	89.26 73	76.84 190	72.13 93	92.56 48	90.40 51	95.76 20	87.56 76

PLC	76.06 15	85.38 64	87.46 72	82.95 61	85.79 81	88.84 41	88.86 83	68.70 88	87.06 57	83.60 48	79.02 148	90.05 132	77.37 52	90.88 70	89.66 59	93.37 52	86.74 79
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSLP-MVS++		86.29 57	89.10 55	83.01 58	85.71 82	89.79 35	87.04 104	74.39 51	85.17 75	78.92 86	77.59 161	93.57 88	82.60 17	93.23 36	91.88 39	89.42 109	92.46 30

Effi-MVS+-dtu		82.04 98	83.39 128	80.48 89	85.48 83	86.57 64	88.40 86	68.28 93	69.04 178	73.13 119	76.26 173	91.11 125	74.74 75	88.40 95	87.76 74	92.84 63	84.57 93

test1111		79.67 119	84.40 110	74.16 134	85.29 84	79.56 120	81.16 146	73.13 59	84.65 80	56.08 183	88.38 84	86.14 155	60.49 156	89.78 83	85.59 98	88.79 117	76.68 157

v7n		87.11 50	90.46 48	83.19 56	85.22 85	83.69 80	90.03 73	68.20 95	91.01 19	86.71 33	94.80 10	98.46 4	77.69 48	91.10 65	85.98 93	91.30 83	88.19 69

MAR-MVS		81.98 99	82.92 131	80.88 80	85.18 86	85.85 67	89.13 80	69.52 76	71.21 167	82.25 61	71.28 199	88.89 143	69.69 109	88.71 90	86.96 79	89.52 106	87.57 75
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 58	88.37 61	82.96 60	84.69 87	88.62 43	90.62 58	64.22 131	89.15 38	88.05 14	78.83 152	93.71 85	76.20 61	90.11 81	88.22 72	94.00 41	89.97 51
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		81.92 100	83.87 121	79.66 94	84.64 88	79.87 115	89.75 74	65.90 114	76.12 145	75.87 99	84.62 125	92.23 105	71.96 95	86.83 110	83.60 118	89.83 102	83.81 101

SixPastTwentyTwo		89.14 29	92.19 31	85.58 32	84.62 89	82.56 92	90.53 63	71.93 64	91.95 12	85.89 35	94.22 14	97.25 19	85.42 5	95.73 12	91.71 40	95.08 27	91.89 36

MVS_111021_HR		83.95 75	86.10 83	81.44 76	84.62 89	80.29 113	90.51 64	68.05 96	84.07 84	80.38 74	84.74 124	91.37 122	74.23 77	90.37 76	87.25 78	90.86 91	84.59 92

test2506		75.32 155	76.87 164	73.50 138	84.55 91	80.37 111	79.63 162	73.23 57	82.64 94	55.41 187	76.87 168	45.42 232	59.61 160	90.35 77	86.46 86	88.58 123	75.98 160

ECVR-MVS		79.31 127	84.20 116	73.60 136	84.55 91	80.37 111	79.63 162	73.23 57	82.64 94	55.98 184	87.50 92	86.85 152	59.61 160	90.35 77	86.46 86	88.58 123	75.26 167

CNLPA		85.50 62	88.58 57	81.91 71	84.55 91	87.52 57	90.89 54	63.56 141	88.18 46	84.06 44	83.85 130	91.34 123	76.46 58	91.27 60	89.00 67	91.96 75	88.88 63

Effi-MVS+		82.33 94	83.87 121	80.52 88	84.51 94	81.32 102	87.53 94	68.05 96	74.94 151	79.67 80	82.37 138	92.31 104	72.21 90	85.06 126	86.91 81	91.18 85	84.20 97

gm-plane-assit		71.56 175	69.99 191	73.39 140	84.43 95	73.21 170	90.42 68	51.36 206	84.08 83	76.00 98	91.30 49	37.09 233	59.01 164	73.65 195	70.24 194	79.09 186	60.37 208

RPSCF		88.05 46	92.61 17	82.73 65	84.24 96	88.40 44	90.04 72	66.29 107	91.46 13	82.29 60	88.93 78	96.01 38	79.38 32	95.15 21	94.90 6	94.15 39	93.40 20

FC-MVSNet-train		79.20 128	86.29 81	70.94 155	84.06 97	77.67 133	85.68 110	64.11 133	82.90 92	52.22 200	92.57 36	93.69 86	49.52 202	88.30 97	86.93 80	90.03 97	81.95 121

v1192		83.61 78	85.23 95	81.72 73	84.05 98	82.15 95	89.54 76	66.20 108	81.38 113	86.76 32	91.79 43	96.03 36	74.88 74	81.81 156	80.92 141	88.91 116	82.50 116

v1240		83.57 80	84.94 101	81.97 70	84.05 98	81.27 103	89.46 78	66.06 110	81.31 114	87.50 20	91.88 42	95.46 52	76.25 60	81.16 162	80.51 145	88.52 126	82.98 110

test20.03		69.91 179	76.20 170	62.58 194	84.01 100	67.34 190	75.67 189	65.88 115	79.98 126	40.28 220	82.65 134	89.31 138	39.63 215	77.41 179	73.28 184	69.98 203	63.40 199

Anonymous202405211			84.68 107		83.92 101	79.45 121	79.03 166	67.79 98	82.01 102		88.77 82	92.58 100	55.93 176	86.68 111	84.26 112	88.92 115	78.98 146

NR-MVSNet		82.89 89	87.43 73	77.59 108	83.91 102	83.59 81	87.10 101	78.35 19	80.64 120	68.85 143	92.67 33	96.50 24	54.19 185	87.19 108	88.68 68	93.16 58	82.75 113

Gipuma		86.47 55	89.25 54	83.23 55	83.88 103	78.78 126	85.35 116	68.42 91	92.69 10	89.03 11	91.94 39	96.32 32	81.80 21	94.45 26	86.86 82	90.91 90	83.69 102
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CS-MVS		83.57 80	84.79 105	82.14 68	83.83 104	81.48 100	87.29 97	66.54 105	72.73 159	80.05 78	84.04 128	93.12 96	80.35 28	89.50 84	86.34 88	94.76 34	86.32 83

v1921920		83.49 82	84.94 101	81.80 72	83.78 105	81.20 105	89.50 77	65.91 113	81.64 106	87.18 24	91.70 44	95.39 54	75.85 64	81.56 160	80.27 147	88.60 121	82.80 112

v1144		83.22 85	85.01 98	81.14 77	83.76 106	81.60 99	88.95 82	65.58 119	81.89 103	85.80 36	91.68 45	95.84 41	74.04 80	82.12 153	80.56 144	88.70 120	81.41 125

Vis-MVSNet (Re-imp)		76.15 148	80.84 141	70.68 156	83.66 107	74.80 162	81.66 143	69.59 75	80.48 123	46.94 210	87.44 94	80.63 176	53.14 190	86.87 109	84.56 110	89.12 111	71.12 178

v144192		83.43 83	84.97 100	81.63 75	83.43 108	81.23 104	89.42 79	66.04 112	81.45 112	86.40 34	91.46 47	95.70 47	75.76 66	82.14 152	80.23 148	88.74 118	82.57 115

TinyColmap		83.79 76	86.12 82	81.07 78	83.42 109	81.44 101	85.42 114	68.55 90	88.71 43	89.46 8	87.60 91	92.72 98	70.34 108	89.29 87	81.94 133	89.20 110	81.12 129

TransMVSNet (Re)		79.05 129	86.66 76	70.18 161	83.32 110	75.99 149	77.54 171	63.98 137	90.68 25	55.84 186	94.80 10	96.06 35	53.73 188	86.27 115	83.22 125	86.65 141	79.61 144

v10		83.17 87	85.22 96	80.78 81	83.26 111	82.99 87	88.66 85	66.49 106	79.24 133	83.60 48	91.46 47	95.47 51	74.12 78	82.60 150	80.66 142	88.53 125	84.11 99

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 10	83.19 112	86.35 65	93.60 37	78.79 18	95.48 3	91.79 2	93.08 27	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		81.22 108	86.04 85	75.60 119	83.17 113	83.18 85	80.29 153	65.82 116	85.97 67	67.98 151	77.74 159	91.51 118	65.17 136	88.62 92	86.15 91	91.17 86	89.09 59

canonicalmvs		81.22 108	86.04 85	75.60 119	83.17 113	83.18 85	80.29 153	65.82 116	85.97 67	67.98 151	77.74 159	91.51 118	65.17 136	88.62 92	86.15 91	91.17 86	89.09 59

SPE-MVS-test		83.59 79	84.86 103	82.10 69	83.04 115	81.05 107	91.58 48	67.48 102	72.52 160	78.42 90	84.75 123	91.82 114	78.62 41	91.98 50	87.54 76	93.48 48	84.35 95

FPMVS		81.56 102	84.04 119	78.66 100	82.92 116	75.96 150	86.48 108	65.66 118	84.67 79	71.47 129	77.78 158	83.22 167	77.57 50	91.24 61	90.21 52	87.84 131	85.21 89

DCV-MVSNet		80.04 114	85.67 91	73.48 139	82.91 117	81.11 106	80.44 152	66.06 110	85.01 76	62.53 170	78.84 151	94.43 79	58.51 166	88.66 91	85.91 94	90.41 93	85.73 86

MVS_111021_LR		83.20 86	85.33 93	80.73 84	82.88 118	78.23 130	89.61 75	65.23 122	82.08 101	81.19 71	85.31 116	92.04 112	75.22 69	89.50 84	85.90 95	90.24 94	84.23 96

Anonymous20231211		79.37 124	85.78 88	71.89 147	82.87 119	79.66 119	78.77 168	63.93 139	83.36 87	59.39 174	90.54 54	94.66 73	56.46 173	87.38 103	84.12 113	89.92 99	80.74 131

MGCFI-Net		79.42 123	85.64 92	72.15 146	82.80 120	82.09 96	76.92 177	65.46 120	86.31 63	57.48 178	78.15 156	91.38 121	59.10 163	88.23 99	84.47 111	91.14 88	88.88 63

casdiffmvs_mvg		81.50 103	85.70 89	76.60 115	82.68 121	80.54 110	83.50 128	64.49 129	83.40 86	72.53 120	92.15 38	95.40 53	65.84 133	84.69 133	81.89 134	90.59 92	81.86 123
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 96	84.26 113	79.81 93	82.67 122	80.18 114	87.67 92	63.96 138	81.69 105	84.73 41	91.27 50	96.33 31	72.05 94	81.94 155	79.56 152	87.79 132	78.84 148

v8		82.20 96	84.56 109	79.45 95	82.42 123	81.65 98	87.26 98	64.27 130	79.36 132	81.70 68	91.04 53	95.75 45	73.30 87	82.82 146	79.18 155	87.74 133	82.09 119

MSDG		81.39 106	84.23 115	78.09 104	82.40 124	82.47 93	85.31 118	60.91 164	79.73 130	80.26 75	86.30 107	88.27 146	69.67 110	87.20 107	84.98 104	89.97 98	80.67 132

Fast-Effi-MVS+		81.42 104	83.82 123	78.62 101	82.24 125	80.62 109	87.72 91	63.51 142	73.01 155	74.75 108	83.80 131	92.70 99	73.44 86	88.15 100	85.26 101	90.05 96	83.17 106

PVSNet_Blended_VisFu		83.00 88	84.16 117	81.65 74	82.17 126	86.01 66	88.03 88	71.23 68	76.05 146	79.54 81	83.88 129	83.44 164	77.49 51	87.38 103	84.93 105	91.41 80	87.40 77

pmmvs6		80.46 111	88.34 63	71.26 151	81.96 127	77.51 135	77.54 171	68.83 86	93.72 7	55.92 185	93.94 19	98.03 9	55.94 175	89.21 88	85.61 97	87.36 137	80.38 134

IterMVS-LS		79.79 117	82.56 134	76.56 116	81.83 128	77.85 132	79.90 158	69.42 80	78.93 135	71.21 130	90.47 56	85.20 161	70.86 105	80.54 167	80.57 143	86.15 148	84.36 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		73.07 168	77.02 161	68.46 171	81.62 129	72.89 171	79.56 164	70.78 70	69.56 173	52.52 197	77.37 164	81.12 175	42.60 210	84.20 137	83.93 114	83.65 169	70.07 183
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		72.68 171	75.21 177	69.73 163	81.48 130	69.04 185	70.48 203	76.67 35	86.92 58	67.80 154	88.06 88	64.67 208	42.12 212	77.60 178	73.65 183	79.81 182	66.57 190

USDC		81.39 106	83.07 129	79.43 96	81.48 130	78.95 125	82.62 136	66.17 109	87.45 53	90.73 4	82.40 137	93.65 87	66.57 128	83.63 141	77.97 158	89.00 114	77.45 156

casdiffmvs		79.93 115	84.11 118	75.05 126	81.41 132	78.99 124	82.95 133	62.90 149	81.53 108	68.60 147	91.94 39	96.03 36	65.84 133	82.89 145	77.07 167	88.59 122	80.34 138
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		77.16 139	84.26 113	68.88 169	81.02 133	75.02 158	76.52 180	63.30 144	87.29 54	52.40 198	91.24 51	93.97 82	54.85 182	85.46 122	81.08 139	85.18 162	75.76 163

thres600view7		74.34 161	78.43 151	69.56 165	80.47 134	76.28 147	78.65 169	62.56 151	77.39 139	52.53 196	74.03 187	76.78 191	55.90 177	85.06 126	85.19 102	87.25 138	74.29 169

OpenMVS	75.38 16	78.44 133	81.39 140	74.99 129	80.46 135	79.85 116	79.99 156	58.31 180	77.34 140	73.85 113	77.19 165	82.33 172	68.60 116	84.67 134	81.95 132	88.72 119	86.40 82

pm-mvs1		78.21 134	85.68 90	69.50 166	80.38 136	75.73 152	76.25 181	65.04 123	87.59 51	54.47 191	93.16 26	95.99 40	54.20 184	86.37 114	82.98 128	86.64 142	77.96 154

viewmanbaseed2359cas		79.90 116	83.96 120	75.17 125	80.25 137	77.62 134	84.62 122	58.25 181	83.22 89	74.92 105	89.50 68	95.33 56	67.20 123	83.05 142	77.84 160	85.76 157	81.18 126

v148		79.33 126	82.32 135	75.84 118	80.14 138	75.74 151	81.98 140	57.06 185	81.51 110	79.36 83	89.42 69	96.42 27	71.32 99	81.54 161	75.29 179	85.20 161	76.32 158

pmmvs-eth3d		79.64 120	82.06 137	76.83 112	80.05 139	72.64 172	87.47 95	66.59 104	80.83 119	73.50 115	89.32 72	93.20 93	67.78 119	80.78 165	81.64 137	85.58 159	76.01 159

testgi		68.20 188	76.05 171	59.04 201	79.99 140	67.32 191	81.16 146	51.78 204	84.91 77	39.36 221	73.42 191	95.19 59	32.79 221	76.54 185	70.40 193	69.14 206	64.55 195

DI_MVS_pp		77.64 136	79.64 146	75.31 123	79.87 141	76.89 143	81.55 144	63.64 140	76.21 144	72.03 125	85.59 115	82.97 168	66.63 127	79.27 173	77.78 161	88.14 129	78.76 150

FA-MVS(training)		78.93 131	80.63 142	76.93 111	79.79 142	75.57 155	85.44 113	61.95 155	77.19 141	78.97 85	84.82 122	82.47 169	66.43 131	84.09 138	80.13 149	89.02 113	80.15 141

Fast-Effi-MVS+-dtu		76.92 140	77.18 160	76.62 114	79.55 143	79.17 122	84.80 120	77.40 29	64.46 196	68.75 145	70.81 203	86.57 153	63.36 148	81.74 158	81.76 135	85.86 154	75.78 162

thres400		73.13 167	76.99 163	68.62 170	79.46 144	74.93 160	77.23 173	61.23 162	75.54 147	52.31 199	72.20 194	77.10 189	54.89 180	82.92 144	82.62 130	86.57 144	73.66 174

QAPM		80.43 112	84.34 111	75.86 117	79.40 145	82.06 97	79.86 159	61.94 156	83.28 88	74.73 109	81.74 140	85.44 159	70.97 103	84.99 131	84.71 109	88.29 127	88.14 71

DELS-MVS		79.71 118	83.74 124	75.01 128	79.31 146	82.68 90	84.79 121	60.06 170	75.43 149	69.09 141	86.13 109	89.38 137	67.16 124	85.12 125	83.87 116	89.65 103	83.57 103
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 95	86.07 84	77.71 106	79.31 146	84.61 73	87.18 99	61.02 163	85.65 69	76.11 97	85.07 119	85.38 160	70.96 104	87.22 106	86.47 85	91.66 77	88.12 72

ET-MVSNet_ETH3D		74.71 159	74.19 180	75.31 123	79.22 148	75.29 156	82.70 135	64.05 134	65.45 191	70.96 133	77.15 166	57.70 220	65.89 132	84.40 136	81.65 136	89.03 112	77.67 155

test-LLR		62.15 205	59.46 221	65.29 189	79.07 149	52.66 216	69.46 209	62.93 147	50.76 224	53.81 193	63.11 218	58.91 216	52.87 192	66.54 214	62.34 206	73.59 191	61.87 204

test0.0.03 1		61.79 207	65.33 203	57.65 204	79.07 149	64.09 199	68.51 212	62.93 147	61.59 209	33.71 224	61.58 220	71.58 204	33.43 220	70.95 203	68.68 198	68.26 208	58.82 211

baseline1		69.62 181	73.55 184	65.02 192	78.95 151	70.39 178	71.38 202	62.03 154	70.97 168	47.95 208	78.47 155	68.19 206	47.77 206	79.65 172	76.94 171	82.05 178	70.27 181

MVS_Test		76.72 142	79.40 148	73.60 136	78.85 152	74.99 159	79.91 157	61.56 158	69.67 172	72.44 121	85.98 112	90.78 127	63.50 146	78.30 176	75.74 176	85.33 160	80.31 139

FMVSNet1		78.20 135	84.83 104	70.46 159	78.62 153	79.03 123	77.90 170	67.53 101	83.02 91	55.10 189	87.19 99	93.18 94	55.65 178	85.57 119	83.39 121	87.98 130	82.40 117

GA-MVS		75.01 158	76.39 167	73.39 140	78.37 154	75.66 153	80.03 155	58.40 179	70.51 169	75.85 100	83.24 132	76.14 193	63.75 142	77.28 180	76.62 172	83.97 168	75.30 166

thres200		72.41 172	76.00 172	68.21 173	78.28 155	76.28 147	74.94 191	62.56 151	72.14 164	51.35 204	69.59 210	76.51 192	54.89 180	85.06 126	80.51 145	87.25 138	71.92 177

EPNet_dtu		71.90 174	73.03 186	70.59 157	78.28 155	61.64 204	82.44 137	64.12 132	63.26 200	69.74 137	71.47 197	82.41 170	51.89 198	78.83 175	78.01 157	77.07 188	75.60 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs4		75.92 150	77.48 159	74.10 135	78.21 157	70.94 176	84.06 125	64.78 125	75.13 150	68.47 148	84.12 127	83.32 165	64.74 140	75.93 188	79.14 156	84.31 166	73.77 172

PM-MVS		80.42 113	83.63 125	76.67 113	78.04 158	72.37 174	87.14 100	60.18 169	80.13 124	71.75 127	86.12 110	93.92 84	77.08 53	86.56 112	85.12 103	85.83 155	81.18 126

thres100view900		69.86 180	72.97 187	66.24 182	77.97 159	72.49 173	73.29 196	59.12 175	66.81 183	50.82 205	67.30 212	75.67 196	50.54 200	78.24 177	79.40 153	85.71 158	70.88 179

tfpn200view9		72.01 173	75.40 175	68.06 174	77.97 159	76.44 145	77.04 175	62.67 150	66.81 183	50.82 205	67.30 212	75.67 196	52.46 197	85.06 126	82.64 129	87.41 136	73.86 171

dmvs_re		68.11 189	70.60 190	65.21 190	77.91 161	63.73 201	76.72 178	59.65 172	55.93 218	47.79 209	59.79 222	79.91 178	49.72 201	82.48 151	76.98 170	79.48 183	75.41 165

Vis-MVSNet		83.32 84	88.12 66	77.71 106	77.91 161	83.44 83	90.58 59	69.49 78	81.11 116	67.10 156	89.85 63	91.48 120	71.71 97	91.34 59	89.37 63	89.48 107	90.26 49
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchMatch-RL		76.05 149	76.64 165	75.36 122	77.84 163	69.87 182	81.09 148	63.43 143	71.66 165	68.34 149	71.70 195	81.76 173	74.98 73	84.83 132	83.44 120	86.45 146	73.22 175

CANet_DTU		75.04 157	78.45 150	71.07 152	77.27 164	77.96 131	83.88 127	58.00 182	64.11 197	68.67 146	75.65 180	88.37 145	53.92 187	82.05 154	81.11 138	84.67 164	79.88 142

MS-PatchMatch		71.18 178	73.99 182	67.89 177	77.16 165	71.76 175	77.18 174	56.38 187	67.35 181	55.04 190	74.63 185	75.70 195	62.38 150	76.62 183	75.97 175	79.22 185	75.90 161

viewmambaseed2359dif		76.20 147	80.07 144	71.68 149	76.99 166	73.91 168	80.81 149	59.23 174	74.86 152	66.65 158	86.44 105	93.44 91	62.91 149	79.19 174	73.77 182	83.49 172	78.89 147

new-patchmatchnet		62.59 204	73.79 183	49.53 217	76.98 167	53.57 214	53.46 226	54.64 192	85.43 72	28.81 225	91.94 39	96.41 28	25.28 223	76.80 181	53.66 221	57.99 219	58.69 212

GBi-Net		73.17 165	77.64 156	67.95 175	76.76 168	77.36 137	75.77 185	64.57 126	62.99 203	51.83 201	76.05 174	77.76 186	52.73 194	85.57 119	83.39 121	86.04 150	80.37 135

PVSNet_BlendedMVS		76.45 145	78.12 152	74.49 132	76.76 168	78.46 127	79.65 160	63.26 145	65.42 192	73.15 117	75.05 183	88.96 140	66.51 129	82.73 148	77.66 162	87.61 134	78.60 151

PVSNet_Blended		76.45 145	78.12 152	74.49 132	76.76 168	78.46 127	79.65 160	63.26 145	65.42 192	73.15 117	75.05 183	88.96 140	66.51 129	82.73 148	77.66 162	87.61 134	78.60 151

test1		73.17 165	77.64 156	67.95 175	76.76 168	77.36 137	75.77 185	64.57 126	62.99 203	51.83 201	76.05 174	77.76 186	52.73 194	85.57 119	83.39 121	86.04 150	80.37 135

FMVSNet2		74.43 160	79.70 145	68.27 172	76.76 168	77.36 137	75.77 185	65.36 121	72.28 161	52.97 195	81.92 139	85.61 158	52.73 194	80.66 166	79.73 151	86.04 150	80.37 135

IB-MVS	71.28 17	75.21 156	77.00 162	73.12 143	76.76 168	77.45 136	83.05 131	58.92 177	63.01 202	64.31 164	59.99 221	87.57 149	68.64 115	86.26 116	82.34 131	87.05 140	82.36 118
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		81.18 110	84.32 112	77.52 110	76.73 174	74.84 161	85.06 119	61.37 160	81.05 117	73.95 112	88.79 81	89.25 139	75.49 68	85.98 117	84.78 107	92.53 68	85.56 88

IterMVS-SCA-FT		77.23 138	79.18 149	74.96 130	76.67 175	79.85 116	75.58 190	61.34 161	73.10 154	73.79 114	86.23 108	79.61 179	79.00 36	80.28 169	75.50 178	83.41 174	79.70 143

FC-MVSNet-test		75.91 151	83.59 126	66.95 180	76.63 176	69.07 184	85.33 117	64.97 124	84.87 78	41.95 216	93.17 25	87.04 150	47.78 205	91.09 66	85.56 99	85.06 163	74.34 168

Anonymous20231206		67.28 191	73.41 185	60.12 200	76.45 177	63.61 202	74.21 193	56.52 186	76.35 142	42.23 215	75.81 179	90.47 130	41.51 213	74.52 189	69.97 195	69.83 204	63.17 200

diffmvs_AUTHOR		77.61 137	82.84 133	71.49 150	76.16 178	74.80 162	81.22 145	57.90 183	79.89 127	68.06 150	90.49 55	94.78 71	62.29 151	81.77 157	77.04 168	83.33 175	81.14 128

baseline2		68.71 186	68.34 196	69.14 167	75.69 179	69.70 183	76.60 179	55.53 190	60.13 211	62.07 172	66.76 214	60.35 213	60.77 155	76.53 186	74.03 181	84.19 167	70.88 179

diffmvs		76.74 141	81.61 139	71.06 153	75.64 180	74.45 165	80.68 151	57.57 184	77.48 138	67.62 155	88.95 77	93.94 83	61.98 153	79.74 170	76.18 173	82.85 176	80.50 133
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		75.86 152	76.23 169	75.42 121	75.55 181	74.06 166	82.73 134	60.31 166	69.24 174	70.24 136	79.18 147	58.79 218	72.17 91	84.49 135	83.08 126	91.54 78	84.80 90

thisisatest0530		75.54 154	75.95 173	75.05 126	75.08 182	73.56 169	82.15 139	60.31 166	69.17 175	69.32 139	79.02 148	58.78 219	72.17 91	83.88 139	83.08 126	91.30 83	84.20 97

FMVSNet3		71.40 177	75.20 178	66.97 179	75.00 183	76.59 144	74.29 192	64.57 126	62.99 203	51.83 201	76.05 174	77.76 186	51.49 199	76.58 184	77.03 169	84.62 165	79.43 145

tpm cat1		64.79 198	62.74 212	67.17 178	74.61 184	65.91 195	76.18 182	59.32 173	64.88 195	66.41 160	71.21 200	53.56 228	59.17 162	61.53 220	58.16 214	67.33 210	63.95 196

UGNet		79.62 121	85.91 87	72.28 145	73.52 185	83.91 76	86.64 106	69.51 77	79.85 128	62.57 169	85.82 113	89.63 133	53.18 189	88.39 96	87.35 77	88.28 128	86.43 81
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					73.27 186	70.91 177	83.26 129

HyFIR lowres test		73.29 164	74.14 181	72.30 144	73.08 187	78.33 129	83.12 130	62.41 153	63.81 198	62.13 171	76.67 170	78.50 183	71.09 101	74.13 192	77.47 165	81.98 179	70.10 182

MIMVSNet1		73.40 163	81.85 138	63.55 193	72.90 188	64.37 198	84.58 123	53.60 198	90.84 21	53.92 192	87.75 90	96.10 33	45.31 208	85.37 124	79.32 154	70.98 202	69.18 187

CostFormer		66.81 193	66.94 199	66.67 181	72.79 189	68.25 187	79.55 165	55.57 189	65.52 190	62.77 168	76.98 167	60.09 214	56.73 172	65.69 216	62.35 205	72.59 194	69.71 184

CR-MVSNet		69.56 182	68.34 196	70.99 154	72.78 190	67.63 188	64.47 215	67.74 99	59.93 212	72.30 122	80.10 143	56.77 222	65.04 138	71.64 200	72.91 186	83.61 171	69.40 185

CVMVSNet		75.65 153	77.62 158	73.35 142	71.95 191	69.89 181	83.04 132	60.84 165	69.12 176	68.76 144	79.92 146	78.93 182	73.64 85	81.02 163	81.01 140	81.86 180	83.43 104

IterMVS		73.62 162	76.53 166	70.23 160	71.83 192	77.18 141	80.69 150	53.22 200	72.23 162	66.62 159	85.21 117	78.96 181	69.54 112	76.28 187	71.63 190	79.45 184	74.25 170
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		67.02 192	63.99 207	70.56 158	71.55 193	67.63 188	75.81 183	69.44 79	59.93 212	63.24 166	64.32 216	47.51 231	59.68 158	70.37 205	69.64 196	83.64 170	68.49 188

dps		65.14 195	64.50 205	65.89 187	71.41 194	65.81 196	71.44 201	61.59 157	58.56 215	61.43 173	75.45 181	52.70 229	58.06 168	69.57 207	64.65 203	71.39 199	64.77 193

MDTV_nov1_ep13_2view		72.96 169	75.59 174	69.88 162	71.15 195	64.86 197	82.31 138	54.45 194	76.30 143	78.32 91	86.52 104	91.58 116	61.35 154	76.80 181	66.83 201	71.70 195	66.26 191

TAMVS		63.02 199	69.30 193	55.70 208	70.12 196	56.89 210	69.63 207	45.13 212	70.23 170	38.00 222	77.79 157	75.15 198	42.60 210	74.48 190	72.81 188	68.70 207	57.75 215

tpm		62.79 201	63.25 209	62.26 197	70.09 197	53.78 213	71.65 200	47.31 210	65.72 189	76.70 95	80.62 142	56.40 225	48.11 204	64.20 218	58.54 212	59.70 216	63.47 198

V42		79.59 122	83.59 126	74.93 131	69.61 198	77.05 142	86.59 107	55.84 188	78.42 137	77.29 94	89.84 64	95.08 64	74.12 78	83.05 142	80.11 150	86.12 149	81.59 124

PatchmatchNet		64.81 197	63.74 208	66.06 186	69.21 199	58.62 208	73.16 197	60.01 171	65.92 187	66.19 161	76.27 172	59.09 215	60.45 157	66.58 213	61.47 211	67.33 210	58.24 213
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 1792x2688		68.80 185	71.09 188	66.13 184	69.11 200	68.89 186	78.98 167	54.68 191	61.63 208	56.69 180	71.56 196	78.39 184	67.69 120	72.13 199	72.01 189	69.63 205	73.02 176

WB-MVS		72.91 170	82.95 130	61.21 198	68.59 201	73.96 167	73.65 195	61.48 159	90.88 20	42.55 214	94.18 16	95.80 43	53.02 191	85.42 123	75.73 177	67.97 209	64.65 194

MIMVSNet		63.02 199	69.02 194	56.01 206	68.20 202	59.26 207	70.01 206	53.79 197	71.56 166	41.26 219	71.38 198	82.38 171	36.38 217	71.43 202	67.32 200	66.45 212	59.83 210

CMPMVS	55.74 18	71.56 175	76.26 168	66.08 185	68.11 203	63.91 200	63.17 217	50.52 208	68.79 179	75.49 101	70.78 204	85.67 157	63.54 145	81.58 159	77.20 166	75.63 189	85.86 84
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SCA		68.54 187	67.52 198	69.73 163	67.79 204	75.04 157	76.96 176	68.94 85	66.41 185	67.86 153	74.03 187	60.96 211	65.55 135	68.99 208	65.67 202	71.30 200	61.54 207

EU-MVSNet		76.48 144	80.53 143	71.75 148	67.62 205	70.30 179	81.74 142	54.06 196	75.47 148	71.01 132	80.10 143	93.17 95	73.67 83	83.73 140	77.85 159	82.40 177	83.07 107

tpmrst		59.42 209	60.02 219	58.71 202	67.56 206	53.10 215	66.99 213	51.88 203	63.80 199	57.68 177	76.73 169	56.49 224	48.73 203	56.47 224	55.55 217	59.43 217	58.02 214

pmmvs5		68.91 184	74.35 179	62.56 195	67.45 207	66.78 192	71.70 199	51.47 205	67.17 182	56.25 182	82.41 136	88.59 144	47.21 207	73.21 198	74.23 180	81.30 181	68.03 189

MDTV_nov1_ep13		64.96 196	64.77 204	65.18 191	67.08 208	62.46 203	75.80 184	51.10 207	62.27 207	69.74 137	74.12 186	62.65 209	55.64 179	68.19 210	62.16 209	71.70 195	61.57 206

E-PMN		59.07 211	62.79 211	54.72 209	67.01 209	47.81 223	60.44 221	43.40 213	72.95 156	44.63 212	70.42 206	73.17 201	58.73 165	80.97 164	51.98 222	54.14 222	42.26 224

pmnet_mix02		62.60 203	70.81 189	53.02 213	66.56 210	50.44 220	62.81 218	46.84 211	79.13 134	43.76 213	87.45 93	90.75 128	39.85 214	70.48 204	57.09 215	58.27 218	60.32 209

baseline		69.33 183	75.37 176	62.28 196	66.54 211	66.67 193	73.95 194	48.07 209	66.10 186	59.26 175	82.45 135	86.30 154	54.44 183	74.42 191	73.25 185	71.42 198	78.43 153

N_pmnet		54.95 218	65.90 201	42.18 218	66.37 212	43.86 226	57.92 223	39.79 217	79.54 131	17.24 230	86.31 106	87.91 147	25.44 222	64.68 217	51.76 223	46.33 225	47.23 222

MVSTER		68.08 190	69.73 192	66.16 183	66.33 213	70.06 180	75.71 188	52.36 202	55.18 221	58.64 176	70.23 208	56.72 223	57.34 170	79.68 171	76.03 174	86.61 143	80.20 140

EMVS		58.97 212	62.63 213	54.70 210	66.26 214	48.71 221	61.74 219	42.71 214	72.80 158	46.00 211	73.01 193	71.66 202	57.91 169	80.41 168	50.68 224	53.55 223	41.11 225

anonymousdsp		85.62 60	90.53 46	79.88 92	64.64 215	76.35 146	96.28 12	53.53 199	85.63 70	81.59 69	92.81 31	97.71 12	86.88 2	94.56 25	92.83 24	96.35 6	93.84 9

EPMVS		56.62 215	59.77 220	52.94 214	62.41 216	50.55 219	60.66 220	52.83 201	65.15 194	41.80 217	77.46 163	57.28 221	42.68 209	59.81 222	54.82 218	57.23 220	53.35 218

FMVSNet5		56.37 216	60.14 218	51.98 216	60.83 217	59.58 206	66.85 214	42.37 215	52.68 223	41.33 218	47.09 225	54.68 226	35.28 218	73.88 193	70.77 192	65.24 213	62.26 203

ADS-MVSNet		56.89 214	61.09 215	52.00 215	59.48 218	48.10 222	58.02 222	54.37 195	72.82 157	49.19 207	75.32 182	65.97 207	37.96 216	59.34 223	54.66 219	52.99 224	51.42 220

new_pmnet		52.29 219	63.16 210	39.61 220	58.89 219	44.70 225	48.78 228	34.73 220	65.88 188	17.85 229	73.42 191	80.00 177	23.06 224	67.00 212	62.28 208	54.36 221	48.81 221

MVS-HIRNet		59.74 208	58.74 224	60.92 199	57.74 220	45.81 224	56.02 224	58.69 178	55.69 219	65.17 162	70.86 202	71.66 202	56.75 171	61.11 221	53.74 220	71.17 201	52.28 219

PatchT		66.25 194	66.76 200	65.67 188	55.87 221	60.75 205	70.17 204	59.00 176	59.80 214	72.30 122	78.68 153	54.12 227	65.04 138	71.64 200	72.91 186	71.63 197	69.40 185

test-mter		59.39 210	61.59 214	56.82 205	53.21 222	54.82 212	73.12 198	26.57 224	53.19 222	56.31 181	64.71 215	60.47 212	56.36 174	68.69 209	64.27 204	75.38 190	65.00 192

CHOSEN 280x420		56.32 217	58.85 223	53.36 212	51.63 223	39.91 227	69.12 211	38.61 218	56.29 217	36.79 223	48.84 224	62.59 210	63.39 147	73.61 196	67.66 199	60.61 214	63.07 201

TESTMET0.1,1		57.21 213	59.46 221	54.60 211	50.95 224	52.66 216	69.46 209	26.91 223	50.76 224	53.81 193	63.11 218	58.91 216	52.87 192	66.54 214	62.34 206	73.59 191	61.87 204

pmmvs3		62.72 202	68.71 195	55.74 207	50.74 225	57.10 209	70.05 205	28.82 222	61.57 210	57.39 179	71.19 201	85.73 156	53.96 186	73.36 197	69.43 197	73.47 193	62.55 202

MDA-MVSNet-bldmvs		76.51 143	82.87 132	69.09 168	50.71 226	74.72 164	84.05 126	60.27 168	81.62 107	71.16 131	88.21 87	91.58 116	69.62 111	92.78 44	77.48 164	78.75 187	73.69 173

PMMVS		61.98 206	65.61 202	57.74 203	45.03 227	51.76 218	69.54 208	35.05 219	55.49 220	55.32 188	68.23 211	78.39 184	58.09 167	70.21 206	71.56 191	83.42 173	63.66 197

PMMVS2		48.13 221	64.06 206	29.55 221	44.06 228	36.69 228	51.95 227	29.97 221	74.75 153	8.90 232	76.02 177	91.24 124	7.53 226	73.78 194	55.91 216	34.87 227	40.01 226

MVE	41.12 19	51.80 220	60.92 216	41.16 219	35.21 229	34.14 229	48.45 229	41.39 216	69.11 177	19.53 228	63.33 217	73.80 199	63.56 144	67.19 211	61.51 210	38.85 226	57.38 216
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				13.54 224	16.73 230	6.42 231	8.49 232	2.36 227	28.69 228	27.44 226	18.40 228	13.51 235	3.70 227	33.23 225	36.26 225	22.54 230

test_method		22.69 223	26.99 225	17.67 223	2.13 231	4.31 232	27.50 230	4.53 226	37.94 226	24.52 227	36.20 227	51.40 230	15.26 225	29.86 226	17.09 226	32.07 228	12.16 227

test123		1.06 224	1.41 226	0.64 225	0.39 232	0.48 233	0.52 235	0.25 229	1.11 230	1.37 234	2.01 230	1.98 236	0.87 228	1.43 228	1.27 227	0.46 232	1.62 229

testmvs		0.93 225	1.37 227	0.41 226	0.36 233	0.36 234	0.62 234	0.39 228	1.48 229	0.18 235	2.41 229	1.31 237	0.41 229	1.25 229	1.08 228	0.48 231	1.68 228

GG-mvs-BLEND		41.63 222	60.36 217	19.78 222	0.14 234	66.04 194	55.66 225	0.17 230	57.64 216	2.42 233	51.82 223	69.42 205	0.28 230	64.11 219	58.29 213	60.02 215	55.18 217

uanet_test		0.00 226	0.00 228	0.00 227	0.00 235	0.00 235	0.00 236	0.00 231	0.00 231	0.00 236	0.00 231	0.00 238	0.00 231	0.00 230	0.00 229	0.00 233	0.00 230

sosnet-low-res		0.00 226	0.00 228	0.00 227	0.00 235	0.00 235	0.00 236	0.00 231	0.00 231	0.00 236	0.00 231	0.00 238	0.00 231	0.00 230	0.00 229	0.00 233	0.00 230

sosnet		0.00 226	0.00 228	0.00 227	0.00 235	0.00 235	0.00 236	0.00 231	0.00 231	0.00 236	0.00 231	0.00 238	0.00 231	0.00 230	0.00 229	0.00 233	0.00 230

RE-MVS-def										87.10 28

9.14												89.43 136

MTAPA										89.37 9		94.85 68

MTMP										90.54 5		95.16 61

Patchmatch-RL test							4.13 233

NP-MVS									78.65 136

Patchmtry						56.88 211	64.47 215	67.74 99		72.30 122

DeepMVS_CX						17.78 230	20.40 231	6.69 225	31.41 227	9.80 231	38.61 226	34.88 234	33.78 219	28.41 227		23.59 229	45.77 223

High-resolution multi-view benchmark