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 34	91.44 41	86.20 28	94.88 1	89.84 36	94.76 29	77.45 28	85.41 86	74.79 121	88.83 98	88.90 172	78.67 42	96.06 7	95.45 4	96.66 3	95.58 2

DTE-MVSNet		88.99 36	92.77 12	84.59 44	93.31 2	88.10 51	90.96 56	83.09 2	91.38 14	76.21 109	96.03 2	98.04 8	70.78 109	95.65 14	92.32 32	93.18 57	87.84 76

mPP-MVS					93.05 3							95.77 58

MP-MVS		90.84 6	91.95 36	89.55 3	92.92 4	90.90 19	96.56 6	79.60 11	86.83 66	88.75 12	89.00 93	94.38 103	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 40	92.92 9	84.11 54	92.92 4	88.05 53	90.83 58	82.67 5	91.04 18	74.83 120	95.97 3	98.47 3	70.38 111	95.70 13	92.43 30	93.05 61	88.78 68

HPM-MVS++		88.74 41	89.54 54	87.80 15	92.58 6	85.69 71	95.10 26	78.01 22	87.08 62	87.66 19	87.89 109	92.07 137	80.28 32	90.97 71	91.41 43	93.17 58	91.69 39

DVP-MVS++		90.50 10	94.18 4	86.21 27	92.52 7	90.29 30	95.29 22	76.02 41	94.24 5	82.82 54	95.84 5	97.56 15	76.82 57	93.13 38	91.20 44	93.78 46	97.01 1

PS-CasMVS		89.07 33	93.23 7	84.21 52	92.44 8	88.23 50	90.54 65	82.95 3	90.50 27	75.31 117	95.80 6	98.37 6	71.16 103	96.30 5	93.32 21	92.88 62	90.11 52

CP-MVSNet		88.71 42	92.63 15	84.13 53	92.39 9	88.09 52	90.47 69	82.86 4	88.79 45	75.16 118	94.87 9	97.68 13	71.05 105	96.16 6	93.18 23	92.85 63	89.64 57

CP-MVS		91.09 5	92.33 25	89.65 2	92.16 10	90.41 28	96.46 10	80.38 8	88.26 48	89.17 10	87.00 125	96.34 38	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 32	88.53 13	89.54 83	95.57 62	84.25 7	95.24 20	94.27 12	95.97 11	93.85 8

WR-MVS_H		88.99 36	93.28 6	83.99 55	91.92 11	89.13 42	91.95 50	83.23 1	90.14 31	71.92 144	95.85 4	98.01 10	71.83 98	95.82 9	93.19 22	93.07 60	90.83 49

SR-MVS					91.82 13			80.80 7				95.53 64

PGM-MVS		90.42 11	91.58 39	89.05 5	91.77 14	91.06 13	96.51 7	78.94 16	85.41 86	87.67 18	87.02 124	95.26 75	83.62 12	95.01 23	93.94 15	95.79 19	93.40 20

APD-MVS		89.14 29	91.25 44	86.67 24	91.73 15	91.02 15	95.50 20	77.74 24	84.04 100	79.47 85	91.48 52	94.85 86	81.14 25	92.94 41	92.20 35	94.47 39	92.24 34
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 27	95.22 24	77.34 32	90.79 24	87.80 16	90.42 72	92.05 139	79.05 37	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 62		91.62 17	87.97 55	84.48 144		88.64 47	87.93 15	87.38 116	94.82 88	74.53 78	89.14 91	83.86 121	85.94 175	86.84 82

TSAR-MVS + MP.		89.67 24	92.25 29	86.65 25	91.53 18	90.98 17	96.15 13	73.30 57	87.88 54	81.83 66	92.92 33	95.15 80	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 55	87.73 72	85.43 35	91.51 19	82.72 94	94.47 33	74.22 54	81.71 124	81.54 70	89.20 91	92.87 125	78.33 45	90.12 82	88.47 71	92.51 70	89.04 64

X-MVS		89.36 28	90.73 47	87.77 16	91.50 20	91.23 8	96.76 4	78.88 17	87.29 59	87.14 25	78.98 185	94.53 96	76.47 59	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 35	83.50 50	89.06 92	94.44 101	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 34	96.34 11	77.36 30	90.17 30	86.88 29	87.32 117	96.63 26	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 38	91.32 23	88.27 48	93.49 41	79.86 10	92.75 9	75.37 116	96.86 1	98.38 5	75.10 73	95.93 8	94.07 14	96.46 5	89.39 59

SD-MVS		89.91 18	92.23 31	87.19 21	91.31 24	89.79 37	94.31 34	75.34 48	89.26 39	81.79 67	92.68 35	95.08 82	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 96				95.84 15

X-MVStestdata					91.28 25	91.23 8	96.89 2			87.14 25		94.53 96				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 33	84.61 42	93.33 25	94.22 105	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 53	86.87 30	87.24 119	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 17	91.73 37	87.97 12	91.21 29	90.29 30	96.51 7	78.00 23	86.33 71	85.32 40	88.23 105	94.67 94	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 35	87.42 19	91.00 30	90.08 32	96.00 15	76.61 36	89.28 37	87.73 17	90.04 74	91.80 143	78.71 40	94.36 28	93.82 17	94.48 38	94.32 6

CPTT-MVS		89.63 25	90.52 49	88.59 6	90.95 31	90.74 22	95.71 16	79.13 15	87.70 55	85.68 38	80.05 176	95.74 60	84.77 6	94.28 29	92.68 26	95.28 26	92.45 33

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 74	87.23 23	90.45 71	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 30	86.99 22	90.86 33	89.35 40	95.07 27	75.91 43	91.16 16	86.87 30	91.07 63	97.29 18	79.13 36	93.32 35	91.99 37	94.12 41	91.49 42
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 57	85.33 39	88.91 97	97.65 14	82.13 19	95.31 17	93.44 19	96.14 10	92.22 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
NCCC		86.74 54	87.97 70	85.31 37	90.64 35	87.25 61	93.27 43	74.59 50	86.50 69	83.72 46	75.92 216	92.39 131	77.08 55	91.72 55	90.68 49	92.57 68	91.30 44

MSP-MVS		88.51 43	91.36 42	85.19 40	90.63 36	92.01 4	95.29 22	77.52 27	90.48 28	80.21 76	90.21 73	96.08 43	76.38 61	88.30 99	91.42 41	91.12 92	91.01 46
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 65	91.12 45	78.71 102	90.48 37	83.72 81	81.76 167	82.41 6	93.84 6	64.43 190	95.41 7	98.76 1	63.72 166	93.63 33	89.74 59	89.47 113	82.74 120

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 93	93.44 24	95.82 56	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 44	93.64 39	75.78 44	90.00 34	83.70 47	92.97 32	92.22 134	86.13 4	97.01 3	96.79 2	94.94 28	90.96 47
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CNVR-MVS		86.93 53	88.98 58	84.54 45	90.11 40	87.41 60	93.23 44	73.47 56	86.31 72	82.25 61	82.96 160	92.15 135	76.04 64	91.69 56	90.69 48	92.17 75	91.64 41

TSAR-MVS + GP.		85.32 67	87.41 77	82.89 64	90.07 41	85.69 71	89.07 85	72.99 61	82.45 114	74.52 126	85.09 145	87.67 180	79.24 35	91.11 66	90.41 51	91.45 82	89.45 58

DeepC-MVS_fast	81.78 5	87.38 51	89.64 53	84.75 42	89.89 42	90.70 23	92.74 47	74.45 51	86.02 76	82.16 64	86.05 138	91.99 141	75.84 67	91.16 65	90.44 50	93.41 52	91.09 45
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 34	91.69 38	85.91 30	89.72 43	90.81 20	92.56 48	71.69 69	90.83 23	87.24 22	89.71 81	92.07 137	78.37 44	94.43 27	92.59 27	95.86 13	91.35 43

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 49	83.43 53	93.48 23	95.19 77	81.07 26	92.75 45	92.07 36	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 56	88.52 61	84.48 46	89.61 45	88.27 48	92.86 46	72.69 62	80.55 143	82.71 55	86.92 126	93.32 120	75.55 69	91.00 70	89.85 58	93.47 50	89.71 56

MED-MVS		89.08 32	92.26 27	85.36 36	89.60 46	90.41 28	94.28 35	75.72 45	91.00 20	77.70 101	93.91 20	94.76 90	80.32 30	92.42 50	90.74 47	94.57 36	92.56 29

EPNet		79.36 143	79.44 176	79.27 100	89.51 47	77.20 159	88.35 91	77.35 31	68.27 219	74.29 127	76.31 208	79.22 219	59.63 191	85.02 139	85.45 103	86.49 162	84.61 95
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
aaEdge-Enhanced		88.45 44	92.03 34	84.27 49	89.33 48	90.77 21	94.55 31	72.48 63	89.22 40	76.86 106	93.91 20	95.41 68	80.41 28	92.07 51	90.28 53	91.99 76	92.56 29

TSAR-MVS + ACMM		89.14 29	92.11 33	85.67 31	89.27 49	90.61 25	90.98 55	79.48 13	88.86 43	79.80 80	93.01 31	93.53 116	83.17 15	92.75 45	92.45 29	91.32 85	93.59 13

HQP-MVS		85.02 69	86.41 83	83.40 56	89.19 50	86.59 65	91.28 53	71.60 70	82.79 110	83.48 51	78.65 191	93.54 115	72.55 91	86.49 117	85.89 99	92.28 74	90.95 48

AdaColmap		84.15 75	85.14 106	83.00 61	89.08 51	87.14 63	90.56 64	70.90 72	82.40 117	80.41 73	73.82 227	84.69 199	75.19 72	91.58 59	89.90 57	91.87 79	86.48 84

DVP-MVS		89.40 27	92.69 13	85.56 34	89.01 52	89.85 35	93.72 38	75.42 46	92.28 11	80.49 72	94.36 13	94.87 85	81.46 24	92.49 49	91.42 41	93.27 54	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 53	92.86 2	95.51 19	72.17 65	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 54	93.57 1	97.27 1	78.23 21	95.55 1	93.00 1	93.98 18	96.01 48	87.53 1	97.69 1	96.81 1	97.33 1	95.34 4

TranMVSNet+NR-MVSNet		85.23 68	89.38 55	80.39 92	88.78 55	83.77 80	87.40 102	76.75 34	85.47 84	68.99 163	95.18 8	97.55 16	67.13 142	91.61 58	89.13 68	93.26 55	82.95 117

MGCNet		85.73 61	87.94 71	83.14 59	88.68 56	87.98 54	93.34 42	70.74 74	79.78 152	82.37 58	88.32 104	89.44 164	71.34 100	90.61 75	89.64 62	92.40 71	89.79 55

SED-MVS		88.96 38	92.37 22	84.99 41	88.64 57	89.65 39	95.11 25	75.98 42	90.73 25	80.15 77	94.21 15	94.51 99	76.59 58	92.94 41	91.17 45	93.46 51	93.37 22

ACMH+	79.05 11	89.62 26	93.08 8	85.58 32	88.58 58	89.26 41	92.18 49	74.23 53	93.55 8	82.66 57	92.32 41	98.35 7	80.29 31	95.28 18	92.34 31	95.52 22	90.43 50

DU-MVS		84.88 71	88.27 66	80.92 81	88.30 59	83.59 83	87.06 108	78.35 19	80.64 141	70.49 153	92.67 36	96.91 24	68.13 128	91.79 53	89.29 67	93.20 56	83.02 114

Baseline_NR-MVSNet		82.79 94	86.51 80	78.44 107	88.30 59	75.62 177	87.81 94	74.97 49	81.53 128	66.84 183	94.71 12	96.46 31	66.90 144	91.79 53	83.37 128	85.83 178	82.09 126

UniMVSNet_NR-MVSNet		84.62 73	88.00 69	80.68 87	88.18 61	83.83 79	87.06 108	76.47 38	81.46 131	70.49 153	93.24 26	95.56 63	68.13 128	90.43 76	88.47 71	93.78 46	83.02 114

SF-MVS		87.85 50	90.95 46	84.22 51	88.17 62	87.90 56	90.80 59	71.80 68	89.28 37	82.70 56	89.90 78	95.37 72	77.91 49	91.69 56	90.04 56	93.95 45	92.47 31

CSCG		88.12 47	91.45 40	84.23 50	88.12 63	90.59 26	90.57 63	68.60 92	91.37 15	83.45 52	89.94 77	95.14 81	78.71 40	91.45 60	88.21 75	95.96 12	93.44 19

CLD-MVS		82.75 96	87.22 78	77.54 118	88.01 64	85.76 70	90.23 72	54.52 230	82.28 119	82.11 65	88.48 101	95.27 74	63.95 163	89.41 88	88.29 73	86.45 164	81.01 143
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 70	88.53 60	80.78 83	87.82 65	84.21 77	88.03 92	76.50 37	81.18 136	69.29 161	92.63 39	96.83 25	69.07 121	91.23 64	89.60 63	93.97 44	84.00 104

DPM-MVS		81.42 112	82.11 160	80.62 88	87.54 66	85.30 73	90.18 74	68.96 87	81.00 139	79.15 87	70.45 244	83.29 204	67.67 133	82.81 164	83.46 123	90.19 100	88.48 70

DeepPCF-MVS	81.61 6	87.95 49	90.29 51	85.22 39	87.48 67	90.01 33	93.79 37	73.54 55	88.93 42	83.89 45	89.40 87	90.84 154	80.26 33	90.62 74	90.19 55	92.36 72	92.03 37

ACM-MVS					87.47 68	83.44 86	89.37 83		75.88 173	80.07 78	72.52 232	84.49 201	62.56 175			89.34 115	89.18 61

EC-MVSNet		83.70 79	84.77 116	82.46 68	87.47 68	82.79 93	85.50 127	72.00 66	69.81 210	77.66 102	85.02 147	89.63 162	78.14 46	90.40 77	87.56 77	94.00 42	88.16 73

CANet		82.84 93	84.60 118	80.78 83	87.30 70	85.20 74	90.23 72	69.00 86	72.16 202	78.73 91	84.49 153	90.70 157	69.54 118	87.65 103	86.17 93	89.87 106	85.84 89

MCST-MVS		84.79 72	86.48 81	82.83 65	87.30 70	87.03 64	90.46 70	69.33 84	83.14 107	82.21 63	81.69 170	92.14 136	75.09 74	87.27 107	84.78 110	92.58 66	89.30 60

EIA-MVS		78.57 151	77.90 185	79.35 99	87.24 72	80.71 115	86.16 118	64.03 143	62.63 246	73.49 133	73.60 228	76.12 233	73.83 84	88.49 96	84.93 108	91.36 84	78.78 175

OMC-MVS		88.16 45	91.34 43	84.46 47	86.85 73	90.63 24	93.01 45	67.00 108	90.35 29	87.40 21	86.86 127	96.35 36	77.66 51	92.63 47	90.84 46	94.84 30	91.68 40

3Dnovator+	83.71 3	88.13 46	90.00 52	85.94 29	86.82 74	91.06 13	94.26 36	75.39 47	88.85 44	85.76 37	85.74 141	86.92 183	78.02 47	93.03 40	92.21 34	95.39 25	92.21 36

ETV-MVS		79.01 148	77.98 184	80.22 93	86.69 75	79.73 126	88.80 88	68.27 97	63.22 241	71.56 146	70.25 246	73.63 239	73.66 86	90.30 81	86.77 86	92.33 73	81.95 128

PHI-MVS		86.37 58	88.14 67	84.30 48	86.65 76	87.56 58	90.76 60	70.16 76	82.55 113	89.65 7	84.89 148	92.40 130	75.97 65	90.88 72	89.70 60	92.58 66	89.03 65

ACMH	78.40 12	88.94 39	92.62 16	84.65 43	86.45 77	87.16 62	91.47 52	68.79 90	95.49 2	89.74 6	93.55 22	98.50 2	77.96 48	94.14 31	89.57 64	93.49 48	89.94 54
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		84.35 74	87.55 73	80.62 88	86.38 78	82.24 99	86.75 113	64.02 144	84.24 96	78.17 98	89.38 88	95.03 84	78.78 39	89.95 84	86.33 91	89.59 110	85.65 91

IS_MVSNet		81.72 108	85.01 107	77.90 113	86.19 79	82.64 96	85.56 126	70.02 77	80.11 148	63.52 195	87.28 118	81.18 212	67.26 138	91.08 69	89.33 66	94.82 31	83.42 110

TPM-MVS					86.18 80	83.43 88	87.57 99			78.77 90	69.75 248	84.63 200	62.24 178			89.88 105	88.48 70
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 76	85.27 102	82.76 66	86.12 81	88.30 47	91.24 54	69.10 85	82.36 118	84.45 43	77.56 199	90.40 159	72.91 90	85.88 122	83.88 119	92.72 65	88.53 69
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TSAR-MVS + COLMAP		85.51 63	88.36 64	82.19 69	86.05 82	87.69 57	90.50 68	70.60 75	86.40 70	82.33 59	89.69 82	92.52 129	74.01 83	87.53 104	86.84 85	89.63 109	87.80 77

EPP-MVSNet		82.76 95	86.47 82	78.45 106	86.00 83	84.47 76	85.39 131	68.42 94	84.17 97	62.97 199	89.26 90	76.84 229	72.13 95	92.56 48	90.40 52	95.76 20	87.56 79

PLC	76.06 15	85.38 66	87.46 75	82.95 63	85.79 84	88.84 43	88.86 87	68.70 91	87.06 63	83.60 48	79.02 182	90.05 160	77.37 54	90.88 72	89.66 61	93.37 53	86.74 83
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSLP-MVS++		86.29 59	89.10 57	83.01 60	85.71 85	89.79 37	87.04 110	74.39 52	85.17 88	78.92 89	77.59 198	93.57 114	82.60 17	93.23 36	91.88 39	89.42 114	92.46 32

Casviewmamba		83.46 85	87.48 74	78.78 101	85.48 86	83.45 85	87.70 97	67.34 107	86.15 75	71.52 147	93.21 27	96.37 35	70.22 113	87.27 107	82.08 137	90.40 97	83.82 105

Effi-MVS+-dtu		82.04 103	83.39 147	80.48 91	85.48 86	86.57 66	88.40 90	68.28 96	69.04 217	73.13 136	76.26 210	91.11 153	74.74 77	88.40 97	87.76 76	92.84 64	84.57 97

test1111		79.67 137	84.40 122	74.16 152	85.29 88	79.56 128	81.16 173	73.13 60	84.65 95	56.08 219	88.38 103	86.14 189	60.49 183	89.78 85	85.59 101	88.79 125	76.68 186

v7n		87.11 52	90.46 50	83.19 58	85.22 89	83.69 82	90.03 76	68.20 98	91.01 19	86.71 33	94.80 10	98.46 4	77.69 50	91.10 67	85.98 96	91.30 86	88.19 72

MAR-MVS		81.98 106	82.92 152	80.88 82	85.18 90	85.85 69	89.13 84	69.52 79	71.21 206	82.25 61	71.28 238	88.89 173	69.69 114	88.71 92	86.96 81	89.52 111	87.57 78
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 60	88.37 63	82.96 62	84.69 91	88.62 45	90.62 61	64.22 139	89.15 41	88.05 14	78.83 187	93.71 111	76.20 63	90.11 83	88.22 74	94.00 42	89.97 53
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		81.92 107	83.87 137	79.66 96	84.64 92	79.87 122	89.75 77	65.90 121	76.12 171	75.87 113	84.62 152	92.23 133	71.96 97	86.83 113	83.60 122	89.83 107	83.81 106

SixPastTwentyTwo		89.14 29	92.19 32	85.58 32	84.62 93	82.56 97	90.53 66	71.93 67	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 38

MVS_111021_HR		83.95 77	86.10 87	81.44 78	84.62 93	80.29 120	90.51 67	68.05 99	84.07 99	80.38 74	84.74 151	91.37 150	74.23 79	90.37 78	87.25 80	90.86 94	84.59 96

test2506		75.32 182	76.87 196	73.50 157	84.55 95	80.37 118	79.63 191	73.23 58	82.64 111	55.41 223	76.87 205	45.42 277	59.61 192	90.35 79	86.46 88	88.58 132	75.98 190

ECVR-MVS		79.31 145	84.20 130	73.60 154	84.55 95	80.37 118	79.63 191	73.23 58	82.64 111	55.98 220	87.50 113	86.85 184	59.61 192	90.35 79	86.46 88	88.58 132	75.26 197

CNLPA		85.50 64	88.58 59	81.91 73	84.55 95	87.52 59	90.89 57	63.56 150	88.18 49	84.06 44	83.85 157	91.34 151	76.46 60	91.27 62	89.00 69	91.96 78	88.88 66

Effi-MVS+		82.33 99	83.87 137	80.52 90	84.51 98	81.32 108	87.53 100	68.05 99	74.94 180	79.67 81	82.37 166	92.31 132	72.21 92	85.06 135	86.91 83	91.18 88	84.20 101

gm-plane-assit		71.56 211	69.99 227	73.39 159	84.43 99	73.21 198	90.42 71	51.36 245	84.08 98	76.00 112	91.30 58	37.09 278	59.01 201	73.65 233	70.24 228	79.09 228	60.37 252

RPSCF		88.05 48	92.61 17	82.73 67	84.24 100	88.40 46	90.04 75	66.29 113	91.46 13	82.29 60	88.93 96	96.01 48	79.38 34	95.15 21	94.90 6	94.15 40	93.40 20

casdiffseed414692147		82.71 97	86.24 85	78.60 105	84.08 101	81.22 111	85.85 123	66.16 116	83.98 101	76.07 111	90.85 65	97.20 21	70.51 110	85.74 123	82.14 136	88.92 122	82.56 122

FC-MVSNet-train		79.20 146	86.29 84	70.94 180	84.06 102	77.67 152	85.68 125	64.11 141	82.90 109	52.22 242	92.57 40	93.69 112	49.52 245	88.30 99	86.93 82	90.03 102	81.95 128

v1192		83.61 80	85.23 104	81.72 75	84.05 103	82.15 100	89.54 79	66.20 114	81.38 134	86.76 32	91.79 49	96.03 46	74.88 76	81.81 178	80.92 148	88.91 124	82.50 123

v1240		83.57 82	84.94 110	81.97 72	84.05 103	81.27 109	89.46 81	66.06 117	81.31 135	87.50 20	91.88 48	95.46 67	76.25 62	81.16 187	80.51 152	88.52 135	82.98 116

test20.03		69.91 215	76.20 204	62.58 233	84.01 105	67.34 231	75.67 227	65.88 122	79.98 149	40.28 264	82.65 161	89.31 168	39.63 259	77.41 210	73.28 215	69.98 247	63.40 242

Anonymous202405211			84.68 117		83.92 106	79.45 129	79.03 196	67.79 101	82.01 121		88.77 100	92.58 128	55.93 214	86.68 114	84.26 116	88.92 122	78.98 172

NR-MVSNet		82.89 92	87.43 76	77.59 116	83.91 107	83.59 83	87.10 107	78.35 19	80.64 141	68.85 164	92.67 36	96.50 29	54.19 225	87.19 111	88.68 70	93.16 59	82.75 119

Gipuma		86.47 57	89.25 56	83.23 57	83.88 108	78.78 135	85.35 132	68.42 94	92.69 10	89.03 11	91.94 45	96.32 40	81.80 21	94.45 26	86.86 84	90.91 93	83.69 107
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CS-MVS		83.57 82	84.79 115	82.14 70	83.83 109	81.48 106	87.29 103	66.54 111	72.73 198	80.05 79	84.04 155	93.12 124	80.35 29	89.50 86	86.34 90	94.76 34	86.32 87

v1921920		83.49 84	84.94 110	81.80 74	83.78 110	81.20 112	89.50 80	65.91 120	81.64 126	87.18 24	91.70 50	95.39 70	75.85 66	81.56 184	80.27 155	88.60 130	82.80 118

v1144		83.22 88	85.01 107	81.14 79	83.76 111	81.60 105	88.95 86	65.58 126	81.89 122	85.80 36	91.68 51	95.84 53	74.04 82	82.12 172	80.56 151	88.70 128	81.41 134

MVSMamba_PlusPlus		80.70 125	82.94 151	78.08 110	83.67 112	81.93 103	85.26 136	65.57 127	72.89 194	74.65 125	79.34 180	89.34 167	69.09 120	85.57 124	84.56 113	90.24 98	86.97 81

Vis-MVSNet (Re-imp)		76.15 173	80.84 168	70.68 181	83.66 113	74.80 186	81.66 169	69.59 78	80.48 144	46.94 254	87.44 115	80.63 214	53.14 232	86.87 112	84.56 113	89.12 118	71.12 217

v144192		83.43 86	84.97 109	81.63 77	83.43 114	81.23 110	89.42 82	66.04 119	81.45 132	86.40 34	91.46 53	95.70 61	75.76 68	82.14 171	80.23 156	88.74 126	82.57 121

TinyColmap		83.79 78	86.12 86	81.07 80	83.42 115	81.44 107	85.42 130	68.55 93	88.71 46	89.46 8	87.60 111	92.72 126	70.34 112	89.29 89	81.94 140	89.20 117	81.12 141

TransMVSNet (Re)		79.05 147	86.66 79	70.18 187	83.32 116	75.99 170	77.54 203	63.98 145	90.68 26	55.84 222	94.80 10	96.06 44	53.73 229	86.27 119	83.22 129	86.65 156	79.61 166

v10		83.17 90	85.22 105	80.78 83	83.26 117	82.99 92	88.66 89	66.49 112	79.24 157	83.60 48	91.46 53	95.47 66	74.12 80	82.60 167	80.66 149	88.53 134	84.11 103

LTVRE_ROB	86.82 1	91.55 3	94.43 3	88.19 10	83.19 118	86.35 67	93.60 40	78.79 18	95.48 3	91.79 2	93.08 30	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		81.22 116	86.04 89	75.60 137	83.17 119	83.18 90	80.29 180	65.82 123	85.97 77	67.98 173	77.74 196	91.51 146	65.17 158	88.62 94	86.15 94	91.17 89	89.09 62

canonicalmvs		81.22 116	86.04 89	75.60 137	83.17 119	83.18 90	80.29 180	65.82 123	85.97 77	67.98 173	77.74 196	91.51 146	65.17 158	88.62 94	86.15 94	91.17 89	89.09 62

SPE-MVS-test		83.59 81	84.86 112	82.10 71	83.04 121	81.05 114	91.58 51	67.48 106	72.52 199	78.42 94	84.75 150	91.82 142	78.62 43	91.98 52	87.54 78	93.48 49	84.35 99

FPMVS		81.56 109	84.04 133	78.66 103	82.92 122	75.96 171	86.48 116	65.66 125	84.67 94	71.47 148	77.78 195	83.22 205	77.57 52	91.24 63	90.21 54	87.84 141	85.21 93

hybridcas		80.80 122	85.25 103	75.61 136	82.91 123	79.79 125	85.07 138	61.72 176	85.56 82	68.49 169	92.67 36	95.38 71	67.22 139	84.31 147	78.61 169	88.24 138	80.42 147

DCV-MVSNet		80.04 131	85.67 96	73.48 158	82.91 123	81.11 113	80.44 179	66.06 117	85.01 90	62.53 202	78.84 186	94.43 102	58.51 203	88.66 93	85.91 97	90.41 96	85.73 90

MVS_111021_LR		83.20 89	85.33 101	80.73 86	82.88 125	78.23 142	89.61 78	65.23 130	82.08 120	81.19 71	85.31 143	92.04 140	75.22 71	89.50 86	85.90 98	90.24 98	84.23 100

Anonymous20231211		79.37 142	85.78 93	71.89 170	82.87 126	79.66 127	78.77 198	63.93 147	83.36 103	59.39 208	90.54 68	94.66 95	56.46 210	87.38 105	84.12 117	89.92 104	80.74 144

MGCFI-Net		79.42 141	85.64 97	72.15 168	82.80 127	82.09 101	76.92 209	65.46 128	86.31 72	57.48 214	78.15 193	91.38 149	59.10 199	88.23 101	84.47 115	91.14 91	88.88 66

casdiffmvs_mvg		81.50 110	85.70 94	76.60 129	82.68 128	80.54 117	83.50 150	64.49 137	83.40 102	72.53 138	92.15 42	95.40 69	65.84 153	84.69 142	81.89 141	90.59 95	81.86 130
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		82.20 101	84.26 127	79.81 95	82.67 129	80.18 121	87.67 98	63.96 146	81.69 125	84.73 41	91.27 59	96.33 39	72.05 96	81.94 176	79.56 160	87.79 142	78.84 174

E6new		81.99 104	85.39 98	78.02 111	82.48 130	78.47 136	87.03 111	63.34 153	87.93 51	79.62 82	92.12 43	97.12 22	68.62 123	83.40 156	78.53 170	87.05 150	80.13 160

E6		81.99 104	85.39 98	78.02 111	82.48 130	78.47 136	87.03 111	63.34 153	87.93 51	79.62 82	92.12 43	97.12 22	68.62 123	83.40 156	78.53 170	87.05 150	80.13 160

v8		82.20 101	84.56 119	79.45 97	82.42 132	81.65 104	87.26 104	64.27 138	79.36 156	81.70 68	91.04 64	95.75 59	73.30 89	82.82 163	79.18 163	87.74 143	82.09 126

E4		81.47 111	84.83 113	77.55 117	82.40 133	78.25 141	86.41 117	62.92 160	87.20 61	78.63 92	91.12 61	96.50 29	68.00 130	82.58 169	77.96 176	86.93 153	80.22 157

MSDG		81.39 114	84.23 129	78.09 109	82.40 133	82.47 98	85.31 134	60.91 185	79.73 153	80.26 75	86.30 133	88.27 177	69.67 115	87.20 110	84.98 107	89.97 103	80.67 145

E5new		81.18 118	84.50 120	77.29 120	82.38 135	78.21 143	86.06 119	62.76 162	86.68 67	78.24 96	90.75 66	95.93 51	67.54 134	82.06 173	77.51 183	86.77 154	80.40 148

E5		81.18 118	84.50 120	77.29 120	82.38 135	78.21 143	86.06 119	62.76 162	86.68 67	78.24 96	90.75 66	95.93 51	67.54 134	82.06 173	77.51 183	86.77 154	80.40 148

Fast-Effi-MVS+		81.42 112	83.82 140	78.62 104	82.24 137	80.62 116	87.72 96	63.51 151	73.01 192	74.75 123	83.80 158	92.70 127	73.44 88	88.15 102	85.26 104	90.05 101	83.17 112

PVSNet_Blended_VisFu		83.00 91	84.16 131	81.65 76	82.17 138	86.01 68	88.03 92	71.23 71	76.05 172	79.54 84	83.88 156	83.44 202	77.49 53	87.38 105	84.93 108	91.41 83	87.40 80

E3new		80.80 122	83.95 135	77.13 122	82.13 139	78.06 145	86.04 121	62.57 165	85.02 89	77.97 100	89.98 76	95.83 54	67.49 137	81.75 180	77.19 189	86.56 160	79.82 163

E3		80.80 122	83.95 135	77.13 122	82.13 139	78.05 146	86.03 122	62.56 166	85.00 91	77.99 99	89.99 75	95.83 54	67.50 136	81.75 180	77.19 189	86.56 160	79.81 164

pmmvs6		80.46 126	88.34 65	71.26 176	81.96 141	77.51 154	77.54 203	68.83 89	93.72 7	55.92 221	93.94 19	98.03 9	55.94 213	89.21 90	85.61 100	87.36 147	80.38 150

viewcassd2359sk11		80.26 129	83.21 148	76.82 126	81.93 142	77.91 149	85.75 124	62.34 170	83.17 106	77.53 103	89.00 93	95.26 75	67.11 143	81.06 189	76.55 197	86.29 167	79.50 168

IterMVS-LS		79.79 134	82.56 156	76.56 130	81.83 143	77.85 150	79.90 187	69.42 83	78.93 159	71.21 149	90.47 70	85.20 197	70.86 108	80.54 194	80.57 150	86.15 168	84.36 98
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
E2		79.77 135	82.52 157	76.56 130	81.77 144	77.80 151	85.49 128	62.14 171	81.45 132	77.16 105	88.03 108	94.73 92	66.75 145	80.40 196	76.02 201	86.07 171	79.22 170

CDS-MVSNet		73.07 201	77.02 192	68.46 204	81.62 145	72.89 201	79.56 193	70.78 73	69.56 212	52.52 239	77.37 201	81.12 213	42.60 254	84.20 149	83.93 118	83.65 204	70.07 222
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gg-mvs-nofinetune		72.68 204	75.21 213	69.73 191	81.48 146	69.04 225	70.48 244	76.67 35	86.92 64	67.80 177	88.06 107	64.67 247	42.12 256	77.60 208	73.65 214	79.81 222	66.57 230

USDC		81.39 114	83.07 149	79.43 98	81.48 146	78.95 134	82.62 160	66.17 115	87.45 58	90.73 4	82.40 165	93.65 113	66.57 147	83.63 154	77.97 175	89.00 121	77.45 184

viewdifsd2359ckpt09		82.38 98	85.92 91	78.26 108	81.46 148	83.33 89	87.76 95	66.85 109	80.47 145	72.93 137	86.68 129	94.75 91	71.25 102	86.58 115	86.23 92	89.30 116	83.41 111

casdiffmvs		79.93 132	84.11 132	75.05 144	81.41 149	78.99 133	82.95 157	62.90 161	81.53 128	68.60 168	91.94 45	96.03 46	65.84 153	82.89 162	77.07 191	88.59 131	80.34 154
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		77.16 163	84.26 127	68.88 202	81.02 150	75.02 182	76.52 214	63.30 155	87.29 59	52.40 240	91.24 60	93.97 106	54.85 222	85.46 129	81.08 146	85.18 187	75.76 193

viewdifsd2359ckpt13		80.07 130	83.42 146	76.17 132	80.95 151	79.07 131	85.14 137	61.42 180	80.41 146	74.78 122	87.22 120	94.70 93	68.23 127	82.60 167	78.34 172	86.49 162	81.63 132

usedtu_dtu_shiyan2		73.14 199	78.83 179	66.49 217	80.89 152	69.55 223	78.12 200	67.67 104	89.65 36	49.76 249	80.90 171	95.49 65	45.72 251	78.37 205	74.56 210	76.81 231	63.31 243

viewmacassd2359aftdt		81.04 121	85.39 98	75.95 133	80.71 153	77.95 148	85.29 135	58.82 203	86.88 65	76.27 108	91.34 55	96.35 36	68.32 126	84.35 146	79.13 165	86.32 166	81.73 131

thres600view7		74.34 189	78.43 181	69.56 194	80.47 154	76.28 167	78.65 199	62.56 166	77.39 164	52.53 238	74.03 225	76.78 230	55.90 215	85.06 135	85.19 105	87.25 148	74.29 199

viewdifsd2359ckpt07		78.49 152	83.75 141	72.35 165	80.46 155	75.49 179	83.92 148	53.96 234	85.53 83	67.94 175	91.12 61	96.06 44	66.18 151	81.43 186	75.39 207	81.62 219	81.26 135

OpenMVS	75.38 16	78.44 153	81.39 164	74.99 147	80.46 155	79.85 123	79.99 185	58.31 206	77.34 165	73.85 129	77.19 202	82.33 210	68.60 125	84.67 143	81.95 139	88.72 127	86.40 86

pm-mvs1		78.21 158	85.68 95	69.50 196	80.38 157	75.73 174	76.25 215	65.04 131	87.59 56	54.47 227	93.16 29	95.99 50	54.20 224	86.37 118	82.98 132	86.64 157	77.96 181

viewmanbaseed2359cas		79.90 133	83.96 134	75.17 143	80.25 158	77.62 153	84.62 142	58.25 207	83.22 105	74.92 119	89.50 84	95.33 73	67.20 140	83.05 159	77.84 178	85.76 180	81.18 138

v148		79.33 144	82.32 159	75.84 135	80.14 159	75.74 173	81.98 166	57.06 212	81.51 130	79.36 86	89.42 86	96.42 33	71.32 101	81.54 185	75.29 208	85.20 186	76.32 187

pmmvs-eth3d		79.64 138	82.06 161	76.83 125	80.05 160	72.64 208	87.47 101	66.59 110	80.83 140	73.50 132	89.32 89	93.20 121	67.78 131	80.78 192	81.64 144	85.58 184	76.01 189

testgi		68.20 224	76.05 205	59.04 243	79.99 161	67.32 232	81.16 173	51.78 243	84.91 92	39.36 265	73.42 229	95.19 77	32.79 265	76.54 217	70.40 227	69.14 250	64.55 237

DI_MVS_pp		77.64 160	79.64 175	75.31 141	79.87 162	76.89 162	81.55 170	63.64 149	76.21 169	72.03 143	85.59 142	82.97 206	66.63 146	79.27 202	77.78 180	88.14 139	78.76 176

FA-MVS(training)		78.93 149	80.63 169	76.93 124	79.79 163	75.57 178	85.44 129	61.95 174	77.19 166	78.97 88	84.82 149	82.47 207	66.43 150	84.09 150	80.13 157	89.02 120	80.15 159

Fast-Effi-MVS+-dtu		76.92 164	77.18 191	76.62 128	79.55 164	79.17 130	84.80 140	77.40 29	64.46 236	68.75 166	70.81 242	86.57 187	63.36 171	81.74 182	81.76 142	85.86 177	75.78 192

thres400		73.13 200	76.99 194	68.62 203	79.46 165	74.93 184	77.23 205	61.23 183	75.54 175	52.31 241	72.20 233	77.10 228	54.89 220	82.92 161	82.62 134	86.57 159	73.66 208

QAPM		80.43 127	84.34 123	75.86 134	79.40 166	82.06 102	79.86 188	61.94 175	83.28 104	74.73 124	81.74 169	85.44 195	70.97 106	84.99 140	84.71 112	88.29 136	88.14 74

DELS-MVS		79.71 136	83.74 142	75.01 146	79.31 167	82.68 95	84.79 141	60.06 193	75.43 177	69.09 162	86.13 136	89.38 166	67.16 141	85.12 134	83.87 120	89.65 108	83.57 108
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	82.21 100	86.07 88	77.71 114	79.31 167	84.61 75	87.18 105	61.02 184	85.65 79	76.11 110	85.07 146	85.38 196	70.96 107	87.22 109	86.47 87	91.66 80	88.12 75

ET-MVSNet_ETH3D		74.71 187	74.19 216	75.31 141	79.22 169	75.29 180	82.70 159	64.05 142	65.45 230	70.96 152	77.15 203	57.70 259	65.89 152	84.40 145	81.65 143	89.03 119	77.67 182

test-LLR		62.15 246	59.46 264	65.29 226	79.07 170	52.66 260	69.46 251	62.93 158	50.76 266	53.81 234	63.11 257	58.91 255	52.87 235	66.54 254	62.34 249	73.59 235	61.87 248

test0.0.03 1		61.79 248	65.33 242	57.65 246	79.07 170	64.09 242	68.51 256	62.93 158	61.59 249	33.71 268	61.58 259	71.58 243	33.43 264	70.95 243	68.68 237	68.26 252	58.82 255

baseline1		69.62 217	73.55 220	65.02 229	78.95 172	70.39 217	71.38 242	62.03 173	70.97 207	47.95 252	78.47 192	68.19 245	47.77 249	79.65 201	76.94 195	82.05 215	70.27 220

MVS_Test		76.72 166	79.40 177	73.60 154	78.85 173	74.99 183	79.91 186	61.56 178	69.67 211	72.44 139	85.98 139	90.78 155	63.50 169	78.30 206	75.74 203	85.33 185	80.31 155

FE-MVSNET2		78.59 150	83.83 139	72.48 164	78.67 174	75.81 172	79.06 195	63.78 148	85.63 80	65.66 188	87.12 123	96.22 41	59.04 200	83.72 153	82.07 138	88.67 129	76.26 188

FMVSNet1		78.20 159	84.83 113	70.46 184	78.62 175	79.03 132	77.90 202	67.53 105	83.02 108	55.10 225	87.19 121	93.18 122	55.65 216	85.57 124	83.39 125	87.98 140	82.40 124

viewdifsd2359ckpt11		78.29 156	84.30 125	71.27 174	78.48 176	74.68 191	82.25 163	55.40 222	82.45 114	60.97 207	91.34 55	96.58 28	65.48 156	85.14 132	78.70 167	85.05 194	81.21 136

viewmsd2359difaftdt		78.29 156	84.30 125	71.27 174	78.48 176	74.69 190	82.25 163	55.40 222	82.45 114	60.98 206	91.34 55	96.59 27	65.48 156	85.14 132	78.70 167	85.05 194	81.21 136

onestephybrid01		78.35 154	82.42 158	73.60 154	78.45 178	76.56 164	83.15 152	62.05 172	74.24 185	69.57 159	87.57 112	94.27 104	63.94 164	84.24 148	79.08 166	84.43 199	81.03 142

GA-MVS		75.01 186	76.39 199	73.39 159	78.37 179	75.66 176	80.03 184	58.40 205	70.51 208	75.85 114	83.24 159	76.14 232	63.75 165	77.28 211	76.62 196	83.97 203	75.30 196

thres200		72.41 207	76.00 206	68.21 206	78.28 180	76.28 167	74.94 230	62.56 166	72.14 203	51.35 246	69.59 249	76.51 231	54.89 220	85.06 135	80.51 152	87.25 148	71.92 216

EPNet_dtu		71.90 210	73.03 222	70.59 182	78.28 180	61.64 247	82.44 161	64.12 140	63.26 240	69.74 157	71.47 236	82.41 208	51.89 241	78.83 204	78.01 174	77.07 230	75.60 194
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs4		75.92 176	77.48 190	74.10 153	78.21 182	70.94 215	84.06 146	64.78 133	75.13 179	68.47 170	84.12 154	83.32 203	64.74 162	75.93 220	79.14 164	84.31 200	73.77 206

PM-MVS		80.42 128	83.63 143	76.67 127	78.04 183	72.37 211	87.14 106	60.18 192	80.13 147	71.75 145	86.12 137	93.92 108	77.08 55	86.56 116	85.12 106	85.83 178	81.18 138

thres100view900		69.86 216	72.97 223	66.24 219	77.97 184	72.49 209	73.29 236	59.12 200	66.81 222	50.82 247	67.30 251	75.67 235	50.54 243	78.24 207	79.40 161	85.71 181	70.88 218

tfpn200view9		72.01 209	75.40 211	68.06 208	77.97 184	76.44 165	77.04 207	62.67 164	66.81 222	50.82 247	67.30 251	75.67 235	52.46 240	85.06 135	82.64 133	87.41 146	73.86 205

dmvs_re		68.11 225	70.60 226	65.21 227	77.91 186	63.73 244	76.72 210	59.65 196	55.93 258	47.79 253	59.79 261	79.91 217	49.72 244	82.48 170	76.98 194	79.48 224	75.41 195

Vis-MVSNet		83.32 87	88.12 68	77.71 114	77.91 186	83.44 86	90.58 62	69.49 81	81.11 137	67.10 181	89.85 79	91.48 148	71.71 99	91.34 61	89.37 65	89.48 112	90.26 51
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PatchMatch-RL		76.05 174	76.64 197	75.36 140	77.84 188	69.87 221	81.09 175	63.43 152	71.66 204	68.34 171	71.70 234	81.76 211	74.98 75	84.83 141	83.44 124	86.45 164	73.22 213

viewmamba		78.33 155	82.83 155	73.07 163	77.55 189	75.72 175	82.97 156	60.76 187	78.06 162	70.14 156	89.47 85	94.50 100	63.04 172	83.55 155	78.24 173	83.99 202	80.28 156

dtuplus		76.59 167	80.58 170	71.94 169	77.50 190	73.54 197	81.21 172	59.20 199	76.13 170	67.10 181	86.78 128	93.90 109	63.03 173	80.39 197	74.68 209	83.59 207	78.65 177

CANet_DTU		75.04 184	78.45 180	71.07 177	77.27 191	77.96 147	83.88 149	58.00 208	64.11 237	68.67 167	75.65 218	88.37 175	53.92 227	82.05 175	81.11 145	84.67 197	79.88 162

MS-PatchMatch		71.18 214	73.99 218	67.89 211	77.16 192	71.76 213	77.18 206	56.38 214	67.35 220	55.04 226	74.63 223	75.70 234	62.38 176	76.62 215	75.97 202	79.22 227	75.90 191

viewmambaseed2359dif		76.20 172	80.07 173	71.68 172	76.99 193	73.91 195	80.81 176	59.23 198	74.86 181	66.65 184	86.44 131	93.44 119	62.91 174	79.19 203	73.77 213	83.49 208	78.89 173

new-patchmatchnet		62.59 244	73.79 219	49.53 260	76.98 194	53.57 258	53.46 272	54.64 229	85.43 85	28.81 270	91.94 45	96.41 34	25.28 268	76.80 213	53.66 264	57.99 264	58.69 256

GBi-Net		73.17 197	77.64 186	67.95 209	76.76 195	77.36 156	75.77 222	64.57 134	62.99 243	51.83 243	76.05 212	77.76 225	52.73 237	85.57 124	83.39 125	86.04 172	80.37 151

PVSNet_BlendedMVS		76.45 170	78.12 182	74.49 150	76.76 195	78.46 138	79.65 189	63.26 156	65.42 231	73.15 134	75.05 221	88.96 170	66.51 148	82.73 165	77.66 181	87.61 144	78.60 178

PVSNet_Blended		76.45 170	78.12 182	74.49 150	76.76 195	78.46 138	79.65 189	63.26 156	65.42 231	73.15 134	75.05 221	88.96 170	66.51 148	82.73 165	77.66 181	87.61 144	78.60 178

test1		73.17 197	77.64 186	67.95 209	76.76 195	77.36 156	75.77 222	64.57 134	62.99 243	51.83 243	76.05 212	77.76 225	52.73 237	85.57 124	83.39 125	86.04 172	80.37 151

FMVSNet2		74.43 188	79.70 174	68.27 205	76.76 195	77.36 156	75.77 222	65.36 129	72.28 200	52.97 237	81.92 167	85.61 194	52.73 237	80.66 193	79.73 159	86.04 172	80.37 151

IB-MVS	71.28 17	75.21 183	77.00 193	73.12 162	76.76 195	77.45 155	83.05 154	58.92 202	63.01 242	64.31 192	59.99 260	87.57 181	68.64 122	86.26 120	82.34 135	87.05 150	82.36 125
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		81.18 118	84.32 124	77.52 119	76.73 201	74.84 185	85.06 139	61.37 181	81.05 138	73.95 128	88.79 99	89.25 169	75.49 70	85.98 121	84.78 110	92.53 69	85.56 92

IterMVS-SCA-FT		77.23 162	79.18 178	74.96 148	76.67 202	79.85 123	75.58 229	61.34 182	73.10 191	73.79 130	86.23 135	79.61 218	79.00 38	80.28 198	75.50 206	83.41 210	79.70 165

FC-MVSNet-test		75.91 177	83.59 144	66.95 215	76.63 203	69.07 224	85.33 133	64.97 132	84.87 93	41.95 260	93.17 28	87.04 182	47.78 248	91.09 68	85.56 102	85.06 189	74.34 198

Anonymous20231206		67.28 228	73.41 221	60.12 242	76.45 204	63.61 245	74.21 233	56.52 213	76.35 167	42.23 259	75.81 217	90.47 158	41.51 257	74.52 223	69.97 229	69.83 248	63.17 244

usedtu_dtu_shiyan1		73.59 192	77.49 189	69.05 199	76.40 205	72.84 202	75.67 227	60.47 188	74.12 186	59.35 209	79.02 182	88.33 176	56.25 212	77.46 209	77.81 179	86.14 169	72.84 215

gbinet_0.2-2-1-0.02		73.88 190	76.94 195	70.31 185	76.23 206	74.72 188	77.93 201	57.54 211	72.77 197	64.37 191	80.14 173	85.20 197	60.60 182	76.92 212	71.41 223	85.16 188	77.45 184

diffmvs_AUTHOR		77.61 161	82.84 154	71.49 173	76.16 207	74.80 186	81.22 171	57.90 209	79.89 150	68.06 172	90.49 69	94.78 89	62.29 177	81.77 179	77.04 192	83.33 211	81.14 140

blended_shiyan6		73.23 195	76.38 200	69.56 194	75.93 208	73.03 200	76.58 212	55.73 218	74.84 182	63.74 194	79.66 179	86.74 185	59.75 186	75.14 222	70.97 225	85.65 183	74.26 200

blended_shiyan8		73.23 195	76.36 201	69.57 193	75.91 209	73.04 199	76.56 213	55.74 217	74.84 182	63.75 193	79.69 178	86.62 186	59.80 185	75.17 221	71.00 224	85.67 182	74.20 203

baseline2		68.71 222	68.34 233	69.14 197	75.69 210	69.70 222	76.60 211	55.53 220	60.13 251	62.07 204	66.76 253	60.35 252	60.77 181	76.53 218	74.03 212	84.19 201	70.88 218

diffmvs		76.74 165	81.61 163	71.06 178	75.64 211	74.45 192	80.68 178	57.57 210	77.48 163	67.62 178	88.95 95	93.94 107	61.98 179	79.74 199	76.18 198	82.85 212	80.50 146
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		75.86 178	76.23 203	75.42 139	75.55 212	74.06 193	82.73 158	60.31 189	69.24 213	70.24 155	79.18 181	58.79 257	72.17 93	84.49 144	83.08 130	91.54 81	84.80 94

wanda-best-256-512		72.50 205	75.48 209	69.03 200	75.29 213	72.66 204	75.85 217	55.31 224	73.43 187	63.41 196	78.69 188	86.04 190	59.27 196	74.34 226	69.81 230	85.06 189	73.37 211

FE-blended-shiyan7		72.50 205	75.48 209	69.03 200	75.29 213	72.66 204	75.85 217	55.31 224	73.43 187	63.41 196	78.69 188	86.04 190	59.27 196	74.34 226	69.81 230	85.06 189	73.37 211

usedtu_blend_shiyan5		67.09 229	67.69 236	66.40 218	75.29 213	72.66 204	69.07 255	55.31 224	73.43 187	53.98 229	53.29 265	56.81 263	59.69 187	74.34 226	69.81 230	85.06 189	73.46 209

FE-MVSNET3		67.68 227	67.80 235	67.53 212	75.29 213	72.66 204	75.85 217	55.31 224	73.43 187	53.98 229	53.29 265	56.81 263	59.69 187	74.34 226	69.81 230	85.06 189	74.26 200

thisisatest0530		75.54 181	75.95 207	75.05 144	75.08 217	73.56 196	82.15 165	60.31 189	69.17 214	69.32 160	79.02 182	58.78 258	72.17 93	83.88 151	83.08 130	91.30 86	84.20 101

FMVSNet3		71.40 213	75.20 214	66.97 214	75.00 218	76.59 163	74.29 232	64.57 134	62.99 243	51.83 243	76.05 212	77.76 225	51.49 242	76.58 216	77.03 193	84.62 198	79.43 169

hybridnocas07		76.05 174	81.19 165	70.05 188	74.83 219	72.76 203	80.26 182	56.12 215	75.67 174	67.35 179	88.47 102	93.87 110	59.44 195	81.83 177	76.14 199	82.29 214	79.61 166

tpm cat1		64.79 236	62.74 252	67.17 213	74.61 220	65.91 238	76.18 216	59.32 197	64.88 234	66.41 186	71.21 239	53.56 273	59.17 198	61.53 264	58.16 257	67.33 254	63.95 239

hybrid		75.61 180	80.58 170	69.81 190	74.36 221	72.39 210	80.17 183	55.48 221	75.16 178	67.30 180	87.14 122	93.52 117	59.56 194	81.16 187	75.66 205	82.01 216	79.03 171

FE-MVSNET		75.03 185	80.98 167	68.08 207	73.53 222	71.43 214	75.74 225	59.74 195	81.81 123	58.16 212	82.47 162	93.51 118	55.42 218	83.18 158	80.51 152	85.90 176	73.94 204

UGNet		79.62 139	85.91 92	72.28 167	73.52 223	83.91 78	86.64 114	69.51 80	79.85 151	62.57 201	85.82 140	89.63 162	53.18 231	88.39 98	87.35 79	88.28 137	86.43 85
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					73.27 224	70.91 216	83.26 151

HyFIR lowres test		73.29 194	74.14 217	72.30 166	73.08 225	78.33 140	83.12 153	62.41 169	63.81 238	62.13 203	76.67 207	78.50 222	71.09 104	74.13 230	77.47 186	81.98 217	70.10 221

MIMVSNet1		73.40 193	81.85 162	63.55 230	72.90 226	64.37 241	84.58 143	53.60 236	90.84 22	53.92 233	87.75 110	96.10 42	45.31 252	85.37 131	79.32 162	70.98 246	69.18 226

CostFormer		66.81 231	66.94 238	66.67 216	72.79 227	68.25 227	79.55 194	55.57 219	65.52 229	62.77 200	76.98 204	60.09 253	56.73 209	65.69 256	62.35 248	72.59 238	69.71 223

CR-MVSNet		69.56 218	68.34 233	70.99 179	72.78 228	67.63 229	64.47 260	67.74 102	59.93 252	72.30 140	80.10 174	56.77 267	65.04 160	71.64 240	72.91 217	83.61 206	69.40 224

CVMVSNet		75.65 179	77.62 188	73.35 161	71.95 229	69.89 220	83.04 155	60.84 186	69.12 215	68.76 165	79.92 177	78.93 221	73.64 87	81.02 190	81.01 147	81.86 218	83.43 109

IterMVS		73.62 191	76.53 198	70.23 186	71.83 230	77.18 160	80.69 177	53.22 238	72.23 201	66.62 185	85.21 144	78.96 220	69.54 118	76.28 219	71.63 221	79.45 225	74.25 202
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
RPMNet		67.02 230	63.99 246	70.56 183	71.55 231	67.63 229	75.81 220	69.44 82	59.93 252	63.24 198	64.32 255	47.51 276	59.68 190	70.37 245	69.64 234	83.64 205	68.49 227

dps		65.14 233	64.50 244	65.89 224	71.41 232	65.81 239	71.44 241	61.59 177	58.56 255	61.43 205	75.45 219	52.70 274	58.06 205	69.57 247	64.65 243	71.39 243	64.77 235

MDTV_nov1_ep13_2view		72.96 202	75.59 208	69.88 189	71.15 233	64.86 240	82.31 162	54.45 231	76.30 168	78.32 95	86.52 130	91.58 144	61.35 180	76.80 213	66.83 241	71.70 239	66.26 231

TAMVS		63.02 238	69.30 229	55.70 251	70.12 234	56.89 253	69.63 249	45.13 254	70.23 209	38.00 266	77.79 194	75.15 237	42.60 254	74.48 224	72.81 219	68.70 251	57.75 259

tpm		62.79 240	63.25 249	62.26 236	70.09 235	53.78 257	71.65 240	47.31 252	65.72 228	76.70 107	80.62 172	56.40 270	48.11 247	64.20 260	58.54 255	59.70 261	63.47 241

V42		79.59 140	83.59 144	74.93 149	69.61 236	77.05 161	86.59 115	55.84 216	78.42 161	77.29 104	89.84 80	95.08 82	74.12 80	83.05 159	80.11 158	86.12 170	81.59 133

PatchmatchNet		64.81 235	63.74 247	66.06 223	69.21 237	58.62 251	73.16 237	60.01 194	65.92 226	66.19 187	76.27 209	59.09 254	60.45 184	66.58 253	61.47 254	67.33 254	58.24 257
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CHOSEN 1792x2688		68.80 221	71.09 224	66.13 221	69.11 238	68.89 226	78.98 197	54.68 228	61.63 248	56.69 216	71.56 235	78.39 223	67.69 132	72.13 237	72.01 220	69.63 249	73.02 214

WB-MVS		72.91 203	82.95 150	61.21 240	68.59 239	73.96 194	73.65 235	61.48 179	90.88 21	42.55 258	94.18 16	95.80 57	53.02 233	85.42 130	75.73 204	67.97 253	64.65 236

MIMVSNet		63.02 238	69.02 230	56.01 248	68.20 240	59.26 250	70.01 247	53.79 235	71.56 205	41.26 263	71.38 237	82.38 209	36.38 261	71.43 242	67.32 240	66.45 256	59.83 254

CMPMVS	55.74 18	71.56 211	76.26 202	66.08 222	68.11 241	63.91 243	63.17 262	50.52 247	68.79 218	75.49 115	70.78 243	85.67 193	63.54 168	81.58 183	77.20 188	75.63 232	85.86 88
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SCA		68.54 223	67.52 237	69.73 191	67.79 242	75.04 181	76.96 208	68.94 88	66.41 224	67.86 176	74.03 225	60.96 250	65.55 155	68.99 248	65.67 242	71.30 244	61.54 251

EU-MVSNet		76.48 169	80.53 172	71.75 171	67.62 243	70.30 218	81.74 168	54.06 233	75.47 176	71.01 151	80.10 174	93.17 123	73.67 85	83.73 152	77.85 177	82.40 213	83.07 113

tpmrst		59.42 252	60.02 262	58.71 244	67.56 244	53.10 259	66.99 257	51.88 242	63.80 239	57.68 213	76.73 206	56.49 269	48.73 246	56.47 268	55.55 260	59.43 262	58.02 258

pmmvs5		68.91 220	74.35 215	62.56 234	67.45 245	66.78 234	71.70 239	51.47 244	67.17 221	56.25 218	82.41 164	88.59 174	47.21 250	73.21 236	74.23 211	81.30 220	68.03 228

MDTV_nov1_ep13		64.96 234	64.77 243	65.18 228	67.08 246	62.46 246	75.80 221	51.10 246	62.27 247	69.74 157	74.12 224	62.65 248	55.64 217	68.19 250	62.16 252	71.70 239	61.57 250

E-PMN		59.07 254	62.79 251	54.72 252	67.01 247	47.81 267	60.44 266	43.40 255	72.95 193	44.63 256	70.42 245	73.17 240	58.73 202	80.97 191	51.98 265	54.14 267	42.26 269

0.4-1-1-0.1		62.35 245	62.12 254	62.60 232	66.85 248	68.23 228	70.78 243	49.40 248	52.78 263	54.44 228	59.25 262	57.42 260	53.76 228	65.41 257	64.40 244	80.41 221	67.37 229

dtuonlycased		72.06 208	81.13 166	61.48 238	66.59 249	76.01 169	84.21 145	41.25 259	79.57 154	31.88 269	81.89 168	89.95 161	69.64 116	85.52 128	77.35 187	75.27 234	77.61 183

pmnet_mix02		62.60 243	70.81 225	53.02 256	66.56 250	50.44 264	62.81 263	46.84 253	79.13 158	43.76 257	87.45 114	90.75 156	39.85 258	70.48 244	57.09 258	58.27 263	60.32 253

baseline		69.33 219	75.37 212	62.28 235	66.54 251	66.67 236	73.95 234	48.07 250	66.10 225	59.26 210	82.45 163	86.30 188	54.44 223	74.42 225	73.25 216	71.42 242	78.43 180

N_pmnet		54.95 261	65.90 240	42.18 261	66.37 252	43.86 270	57.92 268	39.79 260	79.54 155	17.24 276	86.31 132	87.91 179	25.44 266	64.68 258	51.76 267	46.33 271	47.23 266

MVSTER		68.08 226	69.73 228	66.16 220	66.33 253	70.06 219	75.71 226	52.36 241	55.18 261	58.64 211	70.23 247	56.72 268	57.34 207	79.68 200	76.03 200	86.61 158	80.20 158

EMVS		58.97 255	62.63 253	54.70 253	66.26 254	48.71 265	61.74 264	42.71 256	72.80 196	46.00 255	73.01 231	71.66 241	57.91 206	80.41 195	50.68 268	53.55 268	41.11 270

0.3-1-1-0.015		61.14 249	60.59 258	61.78 237	65.65 255	67.14 233	69.76 248	48.31 249	51.00 265	53.98 229	56.11 264	56.81 263	53.29 230	63.79 262	63.19 246	79.66 223	66.07 232

0.4-1-1-0.2		60.88 250	60.45 259	61.38 239	65.29 256	66.73 235	69.11 254	48.01 251	50.14 268	53.73 236	57.22 263	57.01 262	52.91 234	63.57 263	62.64 247	79.23 226	65.82 233

anonymousdsp		85.62 62	90.53 48	79.88 94	64.64 257	76.35 166	96.28 12	53.53 237	85.63 80	81.59 69	92.81 34	97.71 12	86.88 2	94.56 25	92.83 24	96.35 6	93.84 9

PatchmatchNet2					64.26 258	41.70 271	56.82 269
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
EPMVS		56.62 258	59.77 263	52.94 257	62.41 259	50.55 263	60.66 265	52.83 239	65.15 233	41.80 261	77.46 200	57.28 261	42.68 253	59.81 266	54.82 261	57.23 265	53.35 262

blend_shiyan4		63.43 237	63.66 248	63.17 231	62.30 260	71.99 212	65.44 259	52.82 240	48.52 269	53.98 229	53.29 265	56.81 263	59.69 187	71.98 239	69.57 235	84.81 196	73.46 209

FMVSNet5		56.37 259	60.14 261	51.98 259	60.83 261	59.58 249	66.85 258	42.37 257	52.68 264	41.33 262	47.09 270	54.68 271	35.28 262	73.88 231	70.77 226	65.24 257	62.26 247

ADS-MVSNet		56.89 257	61.09 256	52.00 258	59.48 262	48.10 266	58.02 267	54.37 232	72.82 195	49.19 250	75.32 220	65.97 246	37.96 260	59.34 267	54.66 262	52.99 269	51.42 264

new_pmnet		52.29 262	63.16 250	39.61 263	58.89 263	44.70 269	48.78 274	34.73 264	65.88 227	17.85 274	73.42 229	80.00 216	23.06 269	67.00 252	62.28 251	54.36 266	48.81 265

dtuonly		62.71 242	68.55 232	55.89 249	58.38 264	55.27 255	74.41 231	36.47 262	64.61 235	48.30 251	76.18 211	80.16 215	54.95 219	71.99 238	67.49 239	62.86 258	64.12 238

MVS-HIRNet		59.74 251	58.74 267	60.92 241	57.74 265	45.81 268	56.02 270	58.69 204	55.69 259	65.17 189	70.86 241	71.66 241	56.75 208	61.11 265	53.74 263	71.17 245	52.28 263

PatchT		66.25 232	66.76 239	65.67 225	55.87 266	60.75 248	70.17 245	59.00 201	59.80 254	72.30 140	78.68 190	54.12 272	65.04 160	71.64 240	72.91 217	71.63 241	69.40 224

test-mter		59.39 253	61.59 255	56.82 247	53.21 267	54.82 256	73.12 238	26.57 268	53.19 262	56.31 217	64.71 254	60.47 251	56.36 211	68.69 249	64.27 245	75.38 233	65.00 234

CHOSEN 280x420		56.32 260	58.85 266	53.36 255	51.63 268	39.91 272	69.12 253	38.61 261	56.29 257	36.79 267	48.84 269	62.59 249	63.39 170	73.61 234	67.66 238	60.61 259	63.07 245

TESTMET0.1,1		57.21 256	59.46 264	54.60 254	50.95 269	52.66 260	69.46 251	26.91 267	50.76 266	53.81 234	63.11 257	58.91 255	52.87 235	66.54 254	62.34 249	73.59 235	61.87 248

pmmvs3		62.72 241	68.71 231	55.74 250	50.74 270	57.10 252	70.05 246	28.82 266	61.57 250	57.39 215	71.19 240	85.73 192	53.96 226	73.36 235	69.43 236	73.47 237	62.55 246

MDA-MVSNet-bldmvs		76.51 168	82.87 153	69.09 198	50.71 271	74.72 188	84.05 147	60.27 191	81.62 127	71.16 150	88.21 106	91.58 144	69.62 117	92.78 44	77.48 185	78.75 229	73.69 207

PMMVS		61.98 247	65.61 241	57.74 245	45.03 272	51.76 262	69.54 250	35.05 263	55.49 260	55.32 224	68.23 250	78.39 223	58.09 204	70.21 246	71.56 222	83.42 209	63.66 240

PMMVS2		48.13 264	64.06 245	29.55 264	44.06 273	36.69 273	51.95 273	29.97 265	74.75 184	8.90 278	76.02 215	91.24 152	7.53 273	73.78 232	55.91 259	34.87 273	40.01 271

MVE	41.12 19	51.80 263	60.92 257	41.16 262	35.21 274	34.14 274	48.45 275	41.39 258	69.11 216	19.53 273	63.33 256	73.80 238	63.56 167	67.19 251	61.51 253	38.85 272	57.38 260
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
VLMVS_CLIP		15.19 267	17.84 270	12.09 268	31.85 275	14.34 276	3.33 280	13.23 269	15.35 274	3.95 279	18.75 274	17.87 281	14.99 271	18.62 272	15.68 272	5.20 277	24.28 273

tmp_tt				13.54 267	16.73 276	6.42 278	8.49 278	2.36 273	28.69 272	27.44 271	18.40 275	13.51 282	3.70 275	33.23 269	36.26 269	22.54 276

MVS_clip		13.15 268	20.01 269	5.15 269	9.47 277	8.55 277	2.73 281	2.62 272	19.66 273	0.76 283	26.96 273	24.20 280	12.53 272	17.90 273	16.55 271	2.80 278	26.23 272

VLMVS		2.47 270	3.49 272	1.28 270	2.52 278	1.70 280	0.71 282	0.70 274	3.87 276	0.83 282	3.23 277	5.07 284	2.15 276	2.21 274	1.81 274	0.75 279	6.54 276

test_method		22.69 266	26.99 268	17.67 266	2.13 279	4.31 279	27.50 276	4.53 271	37.94 270	24.52 272	36.20 272	51.40 275	15.26 270	29.86 270	17.09 270	32.07 274	12.16 275

MVS_baseline		3.67 269	6.07 271	0.86 271	1.13 280	0.44 282	0.17 285	0.00 278	5.57 275	0.00 285	6.81 276	7.78 283	3.86 274	2.15 275	2.53 273	0.02 282	17.25 274

test123		1.06 271	1.41 273	0.64 272	0.39 281	0.48 281	0.52 284	0.25 276	1.11 278	1.37 281	2.01 279	1.98 285	0.87 277	1.43 276	1.27 275	0.46 281	1.62 278

testmvs		0.93 272	1.37 274	0.41 273	0.36 282	0.36 283	0.62 283	0.39 275	1.48 277	0.18 284	2.41 278	1.31 286	0.41 278	1.25 277	1.08 276	0.48 280	1.68 277

GG-mvs-BLEND		41.63 265	60.36 260	19.78 265	0.14 283	66.04 237	55.66 271	0.17 277	57.64 256	2.42 280	51.82 268	69.42 244	0.28 279	64.11 261	58.29 256	60.02 260	55.18 261

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

PatchmatchNet1												87.99 178	25.44 266	64.23 259	51.81 266	46.37 270	47.19 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										17.36 275	86.27 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							94.55 31	72.48 63		73.73 131						91.99 76

RE-MVS-def										87.10 28

9.14												89.43 165

MTAPA										89.37 9		94.85 86

MTMP										90.54 5		95.16 79

Patchmatch-RL test							4.13 279

NP-MVS									78.65 160

Patchmtry						56.88 254	64.47 260	67.74 102		72.30 140

DeepMVS_CX						17.78 275	20.40 277	6.69 270	31.41 271	9.80 277	38.61 271	34.88 279	33.78 263	28.41 271		23.59 275	45.77 268

High-resolution multi-view benchmark