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.

RA-MVS		96.17 1	96.79 1	95.45 1	97.72 3	98.07 4	96.94 6	93.44 1	97.17 1	93.88 1	97.86 1	95.13 3	94.08 1	96.06 1	94.91 5	96.64 15	98.36 4

MED-MVS		95.66 3	96.33 4	94.88 3	96.63 26	97.96 6	96.90 7	92.96 3	96.43 3	92.70 5	97.77 2	94.16 6	93.27 5	95.59 8	94.71 12	96.79 7	97.66 13

aaEdge-Enhanced		95.38 7	95.93 7	94.74 5	96.51 28	97.82 9	96.76 8	92.70 8	95.23 7	92.39 6	97.77 2	94.08 7	93.28 4	94.87 20	94.08 23	96.77 9	97.66 13

DPE-MVS		95.53 6	96.13 6	94.82 4	96.81 23	98.05 5	97.42 1	93.09 2	94.31 12	91.49 10	97.12 4	95.03 4	93.27 5	95.55 9	94.58 16	96.86 6	98.25 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		95.23 8	95.69 9	94.70 8	97.12 11	97.81 10	97.19 2	92.83 6	95.06 9	90.98 13	96.47 5	92.77 13	93.38 3	95.34 12	94.21 20	96.68 12	98.17 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSP-MVS		95.12 9	95.83 8	94.30 9	96.82 22	97.94 7	96.98 5	92.37 15	95.40 6	90.59 16	96.16 6	93.71 9	92.70 11	94.80 22	94.77 10	96.37 18	97.99 9
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
SED-MVS		95.61 4	96.36 3	94.73 6	96.84 20	98.15 3	97.08 3	92.92 4	95.64 5	91.84 8	95.98 7	95.33 1	92.83 10	96.00 2	94.94 4	96.90 4	98.45 3

DVP-MVS++		95.79 2	96.42 2	95.06 2	97.84 2	98.17 2	97.03 4	92.84 5	96.68 2	92.83 4	95.90 8	94.38 5	92.90 8	95.98 3	94.85 7	96.93 3	98.99 1

SF-MVS		94.61 11	94.96 13	94.20 12	96.75 25	97.07 16	95.82 22	92.60 11	93.98 15	91.09 12	95.89 9	92.54 15	91.93 18	94.40 31	93.56 34	97.04 2	97.27 21

DVP-MVS		95.56 5	96.26 5	94.73 6	96.93 17	98.19 1	96.62 11	92.81 7	96.15 4	91.73 9	95.01 10	95.31 2	93.41 2	95.95 4	94.77 10	96.90 4	98.46 2
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TSAR-MVS + MP.		94.48 14	94.97 12	93.90 15	95.53 42	97.01 19	96.69 10	90.71 27	94.24 13	90.92 14	94.97 11	92.19 18	93.03 7	94.83 21	93.60 31	96.51 17	97.97 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		94.53 13	95.22 11	93.73 17	95.69 41	97.03 18	95.77 25	91.95 16	94.41 11	91.35 11	94.97 11	93.34 11	91.80 22	94.72 25	93.99 25	95.82 43	98.07 8
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TSAR-MVS + ACMM		92.97 27	94.51 17	91.16 40	95.88 38	96.59 33	95.09 34	90.45 33	93.42 19	83.01 64	94.68 13	90.74 31	88.74 47	94.75 24	93.78 28	93.82 165	97.63 15

APD-MVS		94.37 15	94.47 19	94.26 10	97.18 9	96.99 20	96.53 12	92.68 10	92.45 26	89.96 20	94.53 14	91.63 24	92.89 9	94.58 26	93.82 27	96.31 23	97.26 22
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SteuartSystems-ACMMP		94.06 17	94.65 15	93.38 21	96.97 16	97.36 13	96.12 14	91.78 18	92.05 31	87.34 34	94.42 15	90.87 30	91.87 21	95.47 11	94.59 15	96.21 28	97.77 12
Skip Steuart: Steuart Systems R&D Blog.
train_agg		92.87 28	93.53 29	92.09 33	96.88 19	95.38 57	95.94 19	90.59 31	90.65 41	83.65 59	94.31 16	91.87 23	90.30 35	93.38 47	92.42 56	95.17 96	96.73 36

HFP-MVS		94.02 18	94.22 22	93.78 16	97.25 8	96.85 24	95.81 23	90.94 26	94.12 14	90.29 19	94.09 17	89.98 36	92.52 14	93.94 37	93.49 37	95.87 38	97.10 27

TSAR-MVS + GP.		92.71 31	93.91 25	91.30 38	91.96 77	96.00 45	93.43 46	87.94 45	92.53 24	86.27 44	93.57 18	91.94 22	91.44 27	93.29 48	92.89 50	96.78 8	97.15 25

ACMMPR		93.72 21	93.94 24	93.48 20	97.07 12	96.93 21	95.78 24	90.66 29	93.88 16	89.24 24	93.53 19	89.08 42	92.24 15	93.89 39	93.50 35	95.88 36	96.73 36

SMA-MVS		94.70 10	95.35 10	93.93 14	97.57 4	97.57 12	95.98 16	91.91 17	94.50 10	90.35 17	93.46 20	92.72 14	91.89 20	95.89 5	95.22 1	95.88 36	98.10 7
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
HPM-MVS++		94.60 12	94.91 14	94.24 11	97.86 1	96.53 35	96.14 13	92.51 12	93.87 17	90.76 15	93.45 21	93.84 8	92.62 12	95.11 15	94.08 23	95.58 60	97.48 18

ACMMP_NAP		93.94 19	94.49 18	93.30 22	97.03 14	97.31 14	95.96 17	91.30 22	93.41 20	88.55 28	93.00 22	90.33 33	91.43 28	95.53 10	94.41 18	95.53 64	97.47 19

PGM-MVS		92.76 29	93.03 32	92.45 30	97.03 14	96.67 31	95.73 26	87.92 46	90.15 48	86.53 40	92.97 23	88.33 48	91.69 23	93.62 45	93.03 46	95.83 42	96.41 43

MP-MVS		93.35 24	93.59 28	93.08 25	97.39 5	96.82 26	95.38 29	90.71 27	90.82 39	88.07 31	92.83 24	90.29 34	91.32 30	94.03 34	93.19 45	95.61 57	97.16 24
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		92.05 35	93.74 26	90.08 45	94.96 46	97.06 17	93.11 50	87.71 48	90.71 40	80.78 92	92.40 25	91.03 28	87.68 59	94.32 32	94.48 17	96.21 28	96.16 47

TSAR-MVS + COLMAP		88.40 63	89.09 59	87.60 86	92.72 72	93.92 99	92.21 55	85.57 59	91.73 33	73.72 142	91.75 26	73.22 153	87.64 60	91.49 75	89.71 118	93.73 169	91.82 159

ACMMP		92.03 36	92.16 35	91.87 37	95.88 38	96.55 34	94.47 40	89.49 36	91.71 34	85.26 47	91.52 27	84.48 62	90.21 37	92.82 56	91.63 64	95.92 35	96.42 42
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
MGCNet		93.46 23	94.44 20	92.32 31	95.88 38	97.84 8	95.25 31	87.99 44	92.23 28	89.16 25	91.23 28	91.51 26	88.98 43	95.64 7	95.04 3	96.67 14	97.57 17

CNVR-MVS		94.37 15	94.65 15	94.04 13	97.29 7	97.11 15	96.00 15	92.43 14	93.45 18	89.85 22	90.92 29	93.04 12	92.59 13	95.77 6	94.82 8	96.11 30	97.42 20

CP-MVS		93.25 25	93.26 30	93.24 23	96.84 20	96.51 36	95.52 27	90.61 30	92.37 27	88.88 26	90.91 30	89.52 38	91.91 19	93.64 44	92.78 51	95.69 50	97.09 28

MCST-MVS		93.81 20	94.06 23	93.53 19	96.79 24	96.85 24	95.95 18	91.69 20	92.20 29	87.17 36	90.83 31	93.41 10	91.96 17	94.49 29	93.50 35	97.61 1	97.12 26

MVS_111021_LR		90.14 50	90.89 45	89.26 57	93.23 62	94.05 91	90.43 85	84.65 67	90.16 47	84.52 53	90.14 32	83.80 65	87.99 55	92.50 60	90.92 76	94.74 119	94.70 73

DeepPCF-MVS	88.51 2	92.64 32	94.42 21	90.56 43	94.84 49	96.92 22	91.31 69	89.61 35	95.16 8	84.55 52	89.91 33	91.45 27	90.15 38	95.12 14	94.81 9	92.90 189	97.58 16

CDPH-MVS		91.14 42	92.01 36	90.11 44	96.18 33	96.18 40	94.89 36	88.80 41	88.76 54	77.88 119	89.18 34	87.71 51	87.29 65	93.13 50	93.31 42	95.62 55	95.84 52

X-MVS		92.36 33	92.75 34	91.90 36	96.89 18	96.70 28	95.25 31	90.48 32	91.50 36	83.95 54	88.20 35	88.82 44	89.11 42	93.75 42	93.43 38	95.75 48	96.83 34

MVS_111021_HR		90.56 44	91.29 42	89.70 52	94.71 51	95.63 54	91.81 63	86.38 53	87.53 59	81.29 85	87.96 36	85.43 57	87.69 58	93.90 38	92.93 48	96.33 21	95.69 55

HQP-MVS		89.13 58	89.58 57	88.60 67	93.53 59	93.67 101	93.29 48	87.58 49	88.53 55	75.50 129	87.60 37	80.32 81	87.07 67	90.66 104	89.95 111	94.62 127	96.35 46

NCCC		93.69 22	93.66 27	93.72 18	97.37 6	96.66 32	95.93 21	92.50 13	93.40 21	88.35 29	87.36 38	92.33 17	92.18 16	94.89 19	94.09 22	96.00 32	96.91 32

EPNet		89.60 53	89.91 52	89.24 58	96.45 30	93.61 103	92.95 52	88.03 43	85.74 70	83.36 61	87.29 39	83.05 69	80.98 132	92.22 65	91.85 61	93.69 171	95.58 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TPM-MVS					96.31 31	96.02 43	94.89 36			86.52 41	87.18 40	92.17 19	86.76 71			95.56 61	93.85 102
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
CSCG		92.76 29	93.16 31	92.29 32	96.30 32	97.74 11	94.67 39	88.98 39	92.46 25	89.73 23	86.67 41	92.15 21	88.69 48	92.26 64	92.92 49	95.40 71	97.89 11

ACM-MVS					96.49 29	96.04 42	95.42 28		89.60 50	83.77 58	86.60 42	91.59 25	86.35 75			94.91 109	96.07 48

LGP-MVS_train		88.25 69	88.55 61	87.89 81	92.84 71	93.66 102	93.35 47	85.22 63	85.77 69	74.03 141	86.60 42	76.29 130	86.62 73	91.20 80	90.58 87	95.29 88	95.75 53

ACMP	83.90 8	88.32 68	88.06 67	88.62 66	92.18 75	93.98 98	91.28 70	85.24 61	86.69 64	81.23 86	85.62 44	75.13 136	87.01 69	89.83 122	89.77 116	94.79 115	95.43 62
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS_fast	88.76 1	93.10 26	93.02 33	93.19 24	97.13 10	96.51 36	95.35 30	91.19 23	93.14 23	88.14 30	85.26 45	89.49 39	91.45 25	95.17 13	95.07 2	95.85 41	96.48 40
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PMMVS		81.65 153	84.05 128	78.86 192	78.56 240	82.63 244	83.10 202	67.22 248	81.39 112	70.11 160	84.91 46	79.74 87	82.12 121	87.31 157	85.70 192	92.03 208	86.67 219

SPE-MVS-test		90.29 47	90.96 43	89.51 55	93.18 63	95.87 50	89.18 112	83.72 90	88.32 56	84.82 51	84.89 47	85.23 59	90.25 36	94.04 33	92.66 55	95.94 34	95.69 55

CPTT-MVS		91.39 40	90.95 44	91.91 35	95.06 44	95.24 61	95.02 35	88.98 39	91.02 38	86.71 38	84.89 47	88.58 47	91.60 24	90.82 96	89.67 119	94.08 150	96.45 41

MVSMamba_PlusPlus		90.78 43	91.67 38	89.74 49	91.80 80	96.07 41	92.21 55	85.88 55	90.36 45	82.63 70	84.71 49	85.27 58	89.59 40	95.08 16	94.64 13	96.36 20	95.58 59

ET-MVSNet_ETH3D		84.65 122	85.58 112	83.56 141	74.99 253	92.62 127	90.29 89	80.38 148	82.16 103	73.01 149	83.41 50	71.10 162	87.05 68	87.77 153	90.17 103	95.62 55	91.82 159

CANet_DTU		85.43 112	87.72 76	82.76 148	90.95 93	93.01 115	89.99 94	75.46 210	82.67 93	64.91 194	83.14 51	80.09 83	80.68 136	92.03 70	91.03 71	94.57 130	92.08 153

CS-MVS		90.34 46	90.58 48	90.07 46	93.11 64	95.82 51	90.57 77	83.62 91	87.07 62	85.35 46	82.98 52	83.47 66	91.37 29	94.94 17	93.37 41	96.37 18	96.41 43

EC-MVSNet		89.96 51	90.77 47	89.01 59	90.54 99	95.15 63	91.34 68	81.43 136	85.27 72	83.08 62	82.83 53	87.22 53	90.97 32	94.79 23	93.38 39	96.73 11	96.71 38

ETV-MVS		89.22 57	89.76 54	88.60 67	91.60 82	94.61 76	89.48 106	83.46 101	85.20 75	81.58 82	82.75 54	82.59 71	88.80 45	94.57 27	93.28 43	96.68 12	95.31 63

RPSCF		83.46 136	83.36 135	83.59 140	87.75 153	87.35 203	84.82 191	79.46 165	83.84 86	78.12 115	82.69 55	79.87 84	82.60 118	82.47 221	81.13 225	88.78 239	86.13 223

sasdasda		89.36 55	89.92 50	88.70 64	91.38 84	95.92 47	91.81 63	82.61 122	90.37 43	82.73 68	82.09 56	79.28 91	88.30 52	91.17 82	93.59 32	95.36 76	97.04 29

canonicalmvs		89.36 55	89.92 50	88.70 64	91.38 84	95.92 47	91.81 63	82.61 122	90.37 43	82.73 68	82.09 56	79.28 91	88.30 52	91.17 82	93.59 32	95.36 76	97.04 29

MGCFI-Net		88.38 66	89.72 55	86.83 96	91.21 87	95.59 55	91.14 71	82.37 125	90.25 46	75.33 135	81.89 58	79.13 93	85.69 82	90.98 93	93.23 44	95.23 92	96.94 31

CLD-MVS		88.66 60	88.52 62	88.82 61	91.37 86	94.22 81	92.82 53	82.08 127	88.27 57	85.14 48	81.86 59	78.53 99	85.93 81	91.17 82	90.61 85	95.55 62	95.00 65
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DeepC-MVS	87.86 3	92.26 34	91.86 37	92.73 27	96.18 33	96.87 23	95.19 33	91.76 19	92.17 30	86.58 39	81.79 60	85.85 55	90.88 33	94.57 27	94.61 14	95.80 44	97.18 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		91.33 41	91.46 40	91.18 39	95.01 45	96.71 27	93.77 43	87.39 50	87.72 58	87.26 35	81.77 61	89.73 37	87.32 64	94.43 30	93.86 26	96.31 23	96.02 50

OMC-MVS		90.23 49	90.40 49	90.03 47	93.45 60	95.29 58	91.89 61	86.34 54	93.25 22	84.94 50	81.72 62	86.65 54	88.90 44	91.69 73	90.27 100	94.65 125	93.95 94

DPM-MVS		91.72 38	91.48 39	92.00 34	95.53 42	95.75 52	95.94 19	91.07 24	91.20 37	85.58 45	81.63 63	90.74 31	88.40 51	93.40 46	93.75 29	95.45 70	93.85 102

EPNet_dtu		81.98 148	83.82 131	79.83 185	94.10 55	85.97 219	87.29 150	84.08 85	80.61 127	59.96 229	81.62 64	77.19 116	62.91 246	87.21 159	86.38 179	90.66 228	87.77 207
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		92.02 37	91.40 41	92.75 26	96.01 36	95.88 49	93.73 45	89.00 37	89.89 49	90.31 18	81.28 65	88.85 43	91.45 25	92.88 55	94.24 19	96.00 32	96.76 35

MVSTER		86.03 104	86.12 100	85.93 109	88.62 138	89.93 162	89.33 109	79.91 160	81.87 108	81.35 84	81.07 66	74.91 137	80.66 138	92.13 69	90.10 104	95.68 51	92.80 135

UGNet		85.90 107	88.23 65	83.18 144	88.96 136	94.10 87	87.52 144	83.60 93	81.66 110	77.90 118	80.76 67	83.19 68	66.70 238	91.13 88	90.71 83	94.39 141	96.06 49
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
baseline		84.89 120	86.06 102	83.52 142	87.25 161	89.67 172	87.76 141	75.68 203	84.92 78	78.40 113	80.10 68	80.98 77	80.20 149	86.69 172	87.05 166	91.86 211	92.99 129

EIA-MVS		87.94 73	88.05 68	87.81 83	91.46 83	95.00 68	88.67 128	82.81 113	82.53 96	80.81 90	80.04 69	80.20 82	87.48 61	92.58 59	91.61 65	95.63 54	94.36 81

UA-Net		86.07 103	87.78 73	84.06 134	92.85 70	95.11 65	87.73 142	84.38 73	73.22 188	73.18 146	79.99 70	89.22 41	71.47 220	93.22 49	93.03 46	94.76 118	90.69 176

TAPA-MVS	84.37 7	88.91 59	88.93 60	88.89 60	93.00 68	94.85 72	92.00 58	84.84 65	91.68 35	80.05 102	79.77 71	84.56 61	88.17 54	90.11 116	89.00 138	95.30 87	92.57 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_Test		86.93 86	87.24 78	86.56 97	90.10 112	93.47 105	90.31 86	80.12 155	83.55 88	78.12 115	79.58 72	79.80 86	85.45 85	90.17 113	90.59 86	95.29 88	93.53 117

hybridnocas07		86.29 100	86.58 94	85.96 108	88.15 147	92.31 129	88.95 124	81.61 134	86.15 65	80.80 91	79.24 73	77.78 110	82.33 120	88.53 143	88.60 145	93.92 158	93.42 119

PVSNet_BlendedMVS		88.19 70	88.00 70	88.42 69	92.71 73	94.82 73	89.08 119	83.81 87	84.91 79	86.38 42	79.14 74	78.11 103	82.66 116	93.05 52	91.10 69	95.86 39	94.86 69

PVSNet_Blended		88.19 70	88.00 70	88.42 69	92.71 73	94.82 73	89.08 119	83.81 87	84.91 79	86.38 42	79.14 74	78.11 103	82.66 116	93.05 52	91.10 69	95.86 39	94.86 69

diffmvs		86.52 94	86.76 88	86.23 103	88.31 146	92.63 125	89.58 103	81.61 134	86.14 66	80.26 100	79.00 76	77.27 114	83.58 104	88.94 136	89.06 135	94.05 152	94.29 82
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DELS-MVS		89.71 52	89.68 56	89.74 49	93.75 57	96.22 39	93.76 44	85.84 56	82.53 96	85.05 49	78.96 77	84.24 63	84.25 100	94.91 18	94.91 5	95.78 47	96.02 50
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
hybrid		86.13 102	86.45 95	85.75 110	88.02 150	92.17 133	88.79 127	81.32 139	85.86 68	80.67 95	78.80 78	78.11 103	82.06 123	88.52 144	88.29 150	93.66 173	93.38 120

FC-MVSNet-train		85.18 117	85.31 116	85.03 120	90.67 94	91.62 139	87.66 143	83.61 92	79.75 138	74.37 139	78.69 79	71.21 161	78.91 166	91.23 78	89.96 110	94.96 106	94.69 75

EPP-MVSNet		86.55 92	87.76 74	85.15 117	90.52 100	94.41 78	87.24 152	82.32 126	81.79 109	73.60 143	78.57 80	82.41 72	82.07 122	91.23 78	90.39 94	95.14 99	95.48 61

viewmamba		86.59 91	86.74 89	86.42 100	88.44 142	92.86 119	89.26 111	82.63 121	87.39 61	80.58 97	78.43 81	77.87 108	83.66 102	88.44 147	88.75 143	93.96 156	93.45 118

AdaColmap		90.29 47	88.38 64	92.53 28	96.10 35	95.19 62	92.98 51	91.40 21	89.08 53	88.65 27	78.35 82	81.44 76	91.30 31	90.81 97	90.21 101	94.72 121	93.59 116

thisisatest0530		85.15 118	85.86 103	84.33 127	89.19 134	92.57 128	87.22 153	80.11 156	82.15 105	74.41 138	78.15 83	73.80 147	79.90 153	90.99 91	89.58 120	95.13 100	93.75 110

tttt0517		85.11 119	85.81 104	84.30 128	89.24 132	92.68 124	87.12 158	80.11 156	81.98 106	74.31 140	78.08 84	73.57 149	79.90 153	91.01 89	89.58 120	95.11 102	93.77 109

onestephybrid01		86.53 93	86.61 92	86.44 99	88.53 139	92.94 117	89.16 116	82.82 112	84.73 82	81.56 83	77.96 85	78.49 100	82.84 112	88.93 137	89.00 138	93.74 168	94.23 87

PCF-MVS	84.60 6	88.66 60	87.75 75	89.73 51	93.06 67	96.02 43	93.22 49	90.00 34	82.44 101	80.02 105	77.96 85	85.16 60	87.36 63	88.54 142	88.54 147	94.72 121	95.61 58
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E2		87.53 78	86.95 82	88.20 74	90.10 112	94.13 85	90.50 83	84.09 84	84.43 83	83.82 57	77.92 87	77.84 109	85.37 87	90.43 107	90.08 105	95.32 86	93.79 108

diffmvs_AUTHOR		86.44 95	86.59 93	86.26 102	88.33 145	92.74 121	89.66 102	81.74 131	85.17 76	80.04 103	77.70 88	77.20 115	83.68 101	89.66 126	89.28 128	94.14 149	94.37 79

Vis-MVSNet		84.38 129	86.68 90	81.70 159	87.65 157	94.89 71	88.14 137	80.90 142	74.48 172	68.23 170	77.53 89	80.72 79	69.98 224	92.68 57	91.90 60	95.33 83	94.58 77
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MAR-MVS		88.39 65	88.44 63	88.33 72	94.90 47	95.06 66	90.51 81	83.59 94	85.27 72	79.07 111	77.13 90	82.89 70	87.70 57	92.19 67	92.32 57	94.23 145	94.20 89
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
viewcassd2359sk11		87.35 82	86.67 91	88.14 76	90.08 114	94.12 86	90.51 81	84.13 82	83.71 87	83.42 60	76.99 91	77.46 112	85.33 88	90.40 108	90.21 101	95.34 81	93.81 107

IS_MVSNet		86.18 101	88.18 66	83.85 137	91.02 90	94.72 75	87.48 145	82.46 124	81.05 118	70.28 158	76.98 92	82.20 74	76.65 182	93.97 36	93.38 39	95.18 95	94.97 66

QAPM		89.49 54	89.58 57	89.38 56	94.73 50	95.94 46	92.35 54	85.00 64	85.69 71	80.03 104	76.97 93	87.81 50	87.87 56	92.18 68	92.10 59	96.33 21	96.40 45

Casviewmamba		88.37 67	88.02 69	88.78 62	90.62 95	94.98 69	91.00 73	85.24 61	86.70 63	83.08 62	76.96 94	78.63 98	87.25 66	92.43 61	91.85 61	95.48 68	94.60 76

viewdifsd2359ckpt09		87.46 79	86.79 87	88.25 73	89.99 118	94.91 70	90.57 77	84.20 78	82.83 92	82.29 71	76.85 95	76.34 126	86.99 70	91.42 77	90.96 75	95.48 68	94.22 88

viewmanbaseed2359cas		87.17 83	86.90 83	87.48 91	90.08 114	94.14 84	90.30 87	83.19 110	84.17 84	80.68 94	76.78 96	77.43 113	85.43 86	90.78 98	90.92 76	95.21 94	94.10 91

casdiffmvs_mvg		87.97 72	87.63 77	88.37 71	90.55 98	94.42 77	91.82 62	84.69 66	84.05 85	82.08 78	76.57 97	79.00 94	85.49 84	92.35 62	92.29 58	95.55 62	94.70 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OPM-MVS		87.56 77	85.80 105	89.62 53	93.90 56	94.09 88	94.12 41	88.18 42	75.40 166	77.30 122	76.41 98	77.93 106	88.79 46	92.20 66	90.82 79	95.40 71	93.72 111
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet (Re-imp)		83.65 135	86.81 86	79.96 183	90.46 103	92.71 122	84.84 190	82.00 128	80.93 120	62.44 211	76.29 99	82.32 73	65.54 241	92.29 63	91.66 63	94.49 135	91.47 170

DCV-MVSNet		85.88 108	86.17 99	85.54 114	89.10 135	89.85 164	89.34 108	80.70 143	83.04 90	78.08 117	76.19 100	79.00 94	82.42 119	89.67 125	90.30 97	93.63 175	95.12 64

E3new		87.09 84	86.27 97	88.05 77	90.04 116	94.08 89	90.53 79	84.16 79	82.52 98	82.94 65	75.92 101	76.91 120	85.29 89	90.27 110	90.34 95	95.36 76	93.82 104

E3		87.08 85	86.27 97	88.04 78	90.04 116	94.08 89	90.53 79	84.16 79	82.52 98	82.86 66	75.91 102	76.93 118	85.27 90	90.27 110	90.33 96	95.36 76	93.82 104

FC-MVSNet-test		76.53 214	81.62 146	70.58 245	84.99 189	85.73 223	74.81 250	78.85 173	77.00 157	39.13 268	75.90 103	73.50 150	54.08 256	86.54 175	85.99 187	91.65 215	86.68 217

casdiffmvs		87.45 80	87.15 79	87.79 85	90.15 111	94.22 81	89.96 95	83.93 86	85.08 77	80.91 87	75.81 104	77.88 107	86.08 78	91.86 71	90.86 78	95.74 49	94.37 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt13		86.88 87	86.35 96	87.50 90	89.91 126	94.19 83	89.89 97	83.43 103	82.94 91	80.82 89	75.76 105	76.45 124	85.95 80	90.72 102	90.49 90	95.00 103	93.88 98

ACMM	83.27 10	87.68 75	86.09 101	89.54 54	93.26 61	92.19 132	91.43 67	86.74 52	86.02 67	82.85 67	75.63 106	75.14 135	88.41 50	90.68 103	89.99 108	94.59 128	92.97 130
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
viewmambaseed2359dif		85.52 111	85.01 118	86.12 106	88.39 143	91.96 135	89.39 107	81.43 136	82.16 103	80.47 99	75.52 107	76.85 121	83.66 102	87.03 163	87.60 158	93.37 182	93.98 93

PLC	83.76 9	88.61 62	86.83 85	90.70 42	94.22 53	92.63 125	91.50 66	87.19 51	89.16 52	86.87 37	75.51 108	80.87 78	89.98 39	90.01 118	89.20 132	94.41 140	90.45 182
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
hybridcas		87.61 76	87.14 80	88.16 75	90.27 110	94.38 79	90.69 76	84.23 75	85.22 74	82.04 79	75.47 109	78.20 102	86.12 76	91.78 72	90.99 74	95.61 57	93.93 95

MDTV_nov1_ep13		79.14 182	79.49 177	78.74 195	85.40 181	86.89 207	84.32 196	70.29 234	78.85 146	69.42 164	75.37 110	73.29 152	75.64 195	80.61 227	79.48 231	87.36 245	81.91 242

viewdifsd2359ckpt07		85.95 106	85.62 110	86.34 101	89.73 128	93.40 108	89.18 112	81.99 129	81.53 111	80.19 101	75.17 111	76.65 122	83.45 107	90.32 109	89.00 138	93.51 177	93.26 122

baseline1		84.54 124	84.43 124	84.67 122	90.62 95	91.16 142	88.63 131	83.75 89	79.78 137	71.16 154	75.14 112	74.10 141	77.84 174	91.56 74	90.67 84	96.04 31	88.58 191

viewdifsd2359ckpt11		84.31 130	83.65 133	85.08 118	88.07 148	91.03 143	86.86 164	80.65 144	79.92 134	79.63 106	75.08 113	73.99 143	82.74 113	86.40 179	85.98 189	92.51 194	93.16 124

viewmsd2359difaftdt		84.31 130	83.65 133	85.07 119	88.07 148	91.03 143	86.86 164	80.65 144	79.92 134	79.61 107	75.08 113	73.98 144	82.74 113	86.40 179	85.99 187	92.51 194	93.16 124

baseline2		82.80 140	82.86 139	82.73 149	87.68 156	90.50 150	84.92 189	78.93 171	78.07 152	73.06 147	75.08 113	69.77 167	77.31 177	88.90 139	86.94 168	94.50 133	90.74 175

CHOSEN 280x420		80.28 164	81.66 145	78.67 197	82.92 215	79.24 258	85.36 184	66.79 251	78.11 150	70.32 156	75.03 116	79.87 84	81.09 131	89.07 134	83.16 213	85.54 256	87.17 213

3Dnovator+	86.06 4	91.60 39	90.86 46	92.47 29	96.00 37	96.50 38	94.70 38	87.83 47	90.49 42	89.92 21	74.68 117	89.35 40	90.66 34	94.02 35	94.14 21	95.67 52	96.85 33

test2506		85.20 116	84.11 127	86.47 98	91.84 78	95.28 59	89.18 112	84.49 69	82.59 94	75.34 134	74.66 118	58.07 235	81.68 125	93.76 40	92.71 52	96.28 26	91.71 161

PVSNet_Blended_VisFu		87.40 81	87.80 72	86.92 95	92.86 69	95.40 56	88.56 134	83.45 102	79.55 140	82.26 72	74.49 119	84.03 64	79.24 165	92.97 54	91.53 66	95.15 98	96.65 39

dtuplus		85.37 113	84.69 121	86.16 104	88.46 140	91.91 136	89.32 110	81.64 132	80.88 121	80.66 96	74.38 120	76.92 119	83.58 104	87.28 158	87.61 157	93.33 183	93.87 99

E5new		86.71 88	85.64 108	87.96 79	89.95 120	93.99 96	90.75 74	84.39 71	80.71 125	82.22 75	74.36 121	76.30 128	85.12 94	89.86 120	90.30 97	95.33 83	93.93 95

E5		86.71 88	85.64 108	87.96 79	89.95 120	93.99 96	90.75 74	84.39 71	80.71 125	82.22 75	74.36 121	76.30 128	85.12 94	89.86 120	90.30 97	95.33 83	93.93 95

3Dnovator	85.17 5	90.48 45	89.90 53	91.16 40	94.88 48	95.74 53	93.82 42	85.36 60	89.28 51	87.81 32	74.34 123	87.40 52	88.56 49	93.07 51	93.74 30	96.53 16	95.71 54

E4		86.66 90	85.61 111	87.87 82	89.94 122	94.00 95	90.47 84	84.16 79	80.46 129	82.16 77	74.11 124	76.35 125	85.14 91	90.04 117	90.45 91	95.37 75	93.86 101

PatchMatch-RL		83.34 137	81.36 149	85.65 111	90.33 107	89.52 175	84.36 194	81.82 130	80.87 123	79.29 109	74.04 125	62.85 208	86.05 79	88.40 148	87.04 167	92.04 207	86.77 216

SCA		79.51 176	80.15 165	78.75 194	86.58 168	87.70 199	83.07 203	68.53 242	81.31 113	66.40 177	73.83 126	75.38 133	79.30 164	80.49 229	79.39 233	88.63 241	82.96 240

test-LLR		79.47 177	79.84 172	79.03 191	87.47 158	82.40 247	81.24 224	78.05 180	73.72 182	62.69 208	73.76 127	74.42 139	73.49 211	84.61 205	82.99 216	91.25 222	87.01 214

TESTMET0.1,1		77.78 199	79.84 172	75.38 227	80.86 232	82.40 247	81.24 224	62.72 262	73.72 182	62.69 208	73.76 127	74.42 139	73.49 211	84.61 205	82.99 216	91.25 222	87.01 214

E6new		86.44 95	85.45 114	87.59 87	89.94 122	94.05 91	90.00 92	83.35 106	80.22 130	81.75 80	73.69 129	75.92 131	85.13 92	90.17 113	90.41 92	95.40 71	93.70 112

E6		86.44 95	85.45 114	87.59 87	89.94 122	94.05 91	90.00 92	83.35 106	80.22 130	81.75 80	73.69 129	75.92 131	85.13 92	90.17 113	90.41 92	95.40 71	93.70 112

test-mter		77.79 198	80.02 167	75.18 228	81.18 231	82.85 242	80.52 230	62.03 263	73.62 184	62.16 213	73.55 131	73.83 146	73.81 208	84.67 204	83.34 212	91.37 220	88.31 194

Effi-MVS+		85.33 114	85.08 117	85.63 112	89.69 129	93.42 107	89.90 96	80.31 153	79.32 142	72.48 152	73.52 132	74.03 142	86.55 74	90.99 91	89.98 109	94.83 113	94.27 86

viewmacassd2359aftdt		86.41 98	85.73 107	87.21 93	89.86 127	94.03 94	90.30 87	83.22 109	80.76 124	79.59 108	73.51 133	76.32 127	85.06 96	90.24 112	91.13 68	95.23 92	94.11 90

CostFormer		80.94 160	80.21 163	81.79 158	87.69 155	88.58 191	87.47 146	70.66 232	80.02 132	77.88 119	73.03 134	71.40 160	78.24 170	79.96 231	79.63 228	88.82 238	88.84 189

USDC		80.69 161	79.89 170	81.62 162	86.48 169	89.11 184	86.53 168	78.86 172	81.15 117	63.48 204	72.98 135	59.12 233	81.16 130	87.10 160	85.01 199	93.23 184	84.77 231

PatchmatchNet		78.67 190	78.85 181	78.46 200	86.85 166	86.03 213	83.77 199	68.11 246	80.88 121	66.19 178	72.90 136	73.40 151	78.06 171	79.25 235	77.71 238	87.75 244	81.75 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
EPMVS		77.53 201	78.07 190	76.90 215	86.89 165	84.91 233	82.18 219	66.64 252	81.00 119	64.11 200	72.75 137	69.68 168	74.42 207	79.36 234	78.13 236	87.14 247	80.68 251

IterMVS-LS		83.28 138	82.95 138	83.65 138	88.39 143	88.63 190	86.80 166	78.64 175	76.56 158	73.43 145	72.52 138	75.35 134	80.81 134	86.43 178	88.51 148	93.84 164	92.66 140
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FA-MVS(training)		85.65 109	85.79 106	85.48 115	90.44 104	93.47 105	88.66 130	73.11 223	83.34 89	82.26 72	71.79 139	78.39 101	83.14 110	91.00 90	89.47 125	95.28 90	93.06 128

LS3D		85.96 105	84.37 125	87.81 83	94.13 54	93.27 110	90.26 90	89.00 37	84.91 79	72.84 150	71.74 140	72.47 155	87.45 62	89.53 129	89.09 134	93.20 185	89.60 185

CDS-MVSNet		81.63 155	82.09 143	81.09 171	87.21 162	90.28 153	87.46 147	80.33 152	69.06 212	70.66 155	71.30 141	73.87 145	67.99 231	89.58 127	89.87 113	92.87 190	90.69 176
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		82.05 147	81.76 144	82.38 153	87.72 154	90.56 149	86.90 163	78.05 180	73.85 181	66.85 175	71.29 142	71.90 158	82.00 124	86.64 173	85.48 194	92.76 191	92.58 144

GG-mvs-BLEND		57.56 259	82.61 141	28.34 267	0.22 282	90.10 158	79.37 235	0.14 277	79.56 139	0.40 283	71.25 143	83.40 67	0.30 280	86.27 181	83.87 208	89.59 235	83.83 234

test0.0.03 1		76.03 220	78.51 182	73.12 239	87.47 158	85.13 231	76.32 246	78.05 180	73.19 190	50.98 253	70.64 144	69.28 170	55.53 252	85.33 193	84.38 207	90.39 230	81.63 245

SixPastTwentyTwo		76.02 221	75.72 223	76.36 220	83.38 206	87.54 201	75.50 248	76.22 196	65.50 236	57.05 238	70.64 144	53.97 253	74.54 204	80.96 226	82.12 221	91.44 218	89.35 187

IterMVS		78.79 188	79.71 175	77.71 203	85.26 184	85.91 221	84.54 193	69.84 238	73.38 187	61.25 223	70.53 146	70.35 164	74.43 206	85.21 197	83.80 210	90.95 226	88.77 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		79.41 179	80.20 164	78.49 199	85.88 173	86.26 210	83.95 197	71.94 227	73.55 186	61.94 215	70.48 147	70.50 163	75.23 197	85.81 187	84.61 205	91.99 209	90.18 183

Fast-Effi-MVS+-dtu		79.95 167	80.69 158	79.08 190	86.36 170	89.14 183	85.85 174	72.28 226	72.85 193	59.32 232	70.43 148	68.42 176	77.57 175	86.14 182	86.44 178	93.11 187	91.39 171

CVMVSNet		76.70 210	78.46 184	74.64 233	83.34 207	84.48 234	81.83 220	74.58 215	68.88 213	51.23 252	69.77 149	70.05 165	67.49 234	84.27 208	83.81 209	89.38 236	87.96 201

GBi-Net		84.51 125	84.80 119	84.17 131	84.20 197	89.95 159	89.70 99	80.37 149	81.17 114	75.50 129	69.63 150	79.69 88	79.75 157	90.73 99	90.72 80	95.52 65	91.71 161

test1		84.51 125	84.80 119	84.17 131	84.20 197	89.95 159	89.70 99	80.37 149	81.17 114	75.50 129	69.63 150	79.69 88	79.75 157	90.73 99	90.72 80	95.52 65	91.71 161

FMVSNet3		84.44 127	84.64 122	84.21 130	84.32 196	90.13 157	89.85 98	80.37 149	81.17 114	75.50 129	69.63 150	79.69 88	79.62 160	89.72 124	90.52 89	95.59 59	91.58 168

tpm		76.30 219	76.05 217	76.59 217	86.97 164	83.01 241	83.83 198	67.06 250	71.83 197	63.87 202	69.56 153	62.88 207	73.41 213	79.79 232	78.59 234	84.41 259	86.68 217

CNLPA		88.40 63	87.00 81	90.03 47	93.73 58	94.28 80	89.56 104	85.81 57	91.87 32	87.55 33	69.53 154	81.49 75	89.23 41	89.45 130	88.59 146	94.31 144	93.82 104

tpmrst		76.55 213	75.99 218	77.20 206	87.32 160	83.05 240	82.86 209	65.62 254	78.61 149	67.22 174	69.19 155	65.71 189	75.87 190	76.75 252	75.33 251	84.31 260	83.28 238

Fast-Effi-MVS+		83.77 134	82.98 137	84.69 121	87.98 151	91.87 137	88.10 138	77.70 184	78.10 151	73.04 148	69.13 156	68.51 174	86.66 72	90.49 106	89.85 114	94.67 124	92.88 132

dps		78.02 196	75.94 219	80.44 179	86.06 172	86.62 209	82.58 211	69.98 236	75.14 167	77.76 121	69.08 157	59.93 224	78.47 168	79.47 233	77.96 237	87.78 243	83.40 236

ACMH	78.52 14	81.86 150	80.45 161	83.51 143	90.51 102	91.22 141	85.62 180	84.23 75	70.29 208	62.21 212	69.04 158	64.05 200	84.48 99	87.57 156	88.45 149	94.01 154	92.54 147
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
testgi		71.92 242	74.20 237	69.27 247	84.58 194	83.06 239	73.40 253	74.39 218	64.04 241	46.17 260	68.90 159	57.15 240	48.89 261	84.07 210	83.08 215	88.18 242	79.09 255

GA-MVS		79.52 175	79.71 175	79.30 189	85.68 177	90.36 152	84.55 192	78.44 176	70.47 207	57.87 237	68.52 160	61.38 216	76.21 187	89.40 132	87.89 152	93.04 188	89.96 184

casdiffseed414692147		85.57 110	83.88 130	87.54 89	89.98 119	93.88 100	90.07 91	83.49 97	79.40 141	80.57 98	68.32 161	71.85 159	86.11 77	89.45 130	90.56 88	95.00 103	93.69 114

DI_MVS_pp		86.41 98	85.54 113	87.42 92	89.24 132	93.13 111	92.16 57	82.65 119	82.30 102	80.75 93	68.30 162	80.41 80	85.01 97	90.56 105	90.07 106	94.70 123	94.01 92

GeoE		84.62 123	83.98 129	85.35 116	89.34 131	92.83 120	88.34 135	78.95 170	79.29 143	77.16 123	68.10 163	74.56 138	83.40 108	89.31 133	89.23 131	94.92 108	94.57 78

ADS-MVSNet		74.53 236	75.69 224	73.17 238	81.57 229	80.71 253	79.27 236	63.03 261	79.27 144	59.94 230	67.86 164	68.32 178	71.08 221	77.33 250	76.83 243	84.12 262	79.53 252

thisisatest0515		79.76 172	80.59 160	78.80 193	84.40 195	88.91 188	79.48 233	76.94 190	72.29 195	67.33 173	67.82 165	65.99 188	70.80 222	88.50 145	87.84 153	93.86 163	92.75 138

OpenMVS	82.53 11	87.71 74	86.84 84	88.73 63	94.42 52	95.06 66	91.02 72	83.49 97	82.50 100	82.24 74	67.62 166	85.48 56	85.56 83	91.19 81	91.30 67	95.67 52	94.75 71

TAMVS		76.42 215	77.16 202	75.56 225	83.05 211	85.55 226	80.58 229	71.43 229	65.40 238	61.04 226	67.27 167	69.22 172	67.99 231	84.88 203	84.78 202	89.28 237	83.01 239

0.4-1-1-0.1		79.43 178	77.51 197	81.66 160	79.11 235	88.57 192	87.37 148	75.16 212	73.57 185	75.70 124	67.26 168	67.91 179	80.67 137	78.11 245	79.88 226	91.94 210	87.30 212

UniMVSNet_NR-MVSNet		81.87 149	81.33 150	82.50 150	85.31 183	91.30 140	85.70 176	84.25 74	75.89 162	64.21 198	66.95 169	64.65 194	80.22 147	87.07 161	89.18 133	95.27 91	94.29 82

0.4-1-1-0.2		78.93 186	76.93 206	81.25 169	78.56 240	87.86 197	86.98 159	74.58 215	72.54 194	75.49 133	66.85 170	67.89 180	80.44 143	77.55 248	79.41 232	91.49 217	86.44 221

MSDG		83.87 132	81.02 154	87.19 94	92.17 76	89.80 166	89.15 117	85.72 58	80.61 127	79.24 110	66.66 171	68.75 173	82.69 115	87.95 152	87.44 160	94.19 146	85.92 225

0.3-1-1-0.015		79.02 184	76.98 205	81.41 164	78.71 239	88.07 195	87.16 155	74.71 214	72.89 191	75.60 125	66.54 172	67.75 181	80.60 142	77.49 249	79.58 229	91.66 214	86.56 220

ACMH+	79.08 13	81.84 151	80.06 166	83.91 136	89.92 125	90.62 148	86.21 171	83.48 100	73.88 180	65.75 185	66.38 173	65.30 191	84.63 98	85.90 185	87.25 163	93.45 179	91.13 174

ECVR-MVS		85.25 115	84.47 123	86.16 104	91.84 78	95.28 59	89.18 112	84.49 69	82.59 94	73.49 144	66.12 174	69.28 170	81.68 125	93.76 40	92.71 52	96.28 26	91.58 168

FMVSNet2		83.87 132	83.73 132	84.05 135	84.20 197	89.95 159	89.70 99	80.21 154	79.17 145	74.89 136	65.91 175	77.49 111	79.75 157	90.87 95	91.00 73	95.52 65	91.71 161

anonymousdsp		77.94 197	79.00 179	76.71 216	79.03 236	87.83 198	79.58 232	72.87 224	65.80 233	58.86 236	65.82 176	62.48 211	75.99 188	86.77 169	88.66 144	93.92 158	95.68 57

dmvs_re		81.08 159	79.92 169	82.44 152	86.66 167	87.70 199	87.91 140	83.30 108	72.86 192	65.29 192	65.76 177	63.43 202	76.69 181	88.93 137	89.50 123	94.80 114	91.23 173

usedtu_blend_shiyan5		77.43 203	75.78 222	79.36 188	69.08 259	86.01 214	86.97 160	75.62 206	68.11 220	75.60 125	65.73 178	67.75 181	76.63 183	78.43 241	76.54 244	92.29 201	87.87 204

blend_shiyan4		78.17 194	76.23 213	80.43 180	77.49 244	85.96 220	85.63 179	74.87 213	72.02 196	75.60 125	65.73 178	67.75 181	76.63 183	77.82 247	76.48 248	92.34 199	87.87 204

FE-MVSNET3		77.14 205	75.80 221	78.71 196	69.08 259	86.01 214	83.06 204	75.62 206	68.11 220	75.60 125	65.73 178	67.75 181	76.63 183	78.43 241	76.54 244	92.29 201	88.01 199

thres100view900		82.55 144	81.01 156	84.34 126	90.30 108	92.27 130	89.04 122	82.77 114	75.14 167	69.56 161	65.72 181	63.13 203	79.62 160	89.97 119	89.26 130	94.73 120	91.61 167

tfpn200view9		82.86 139	81.46 147	84.48 124	90.30 108	93.09 112	89.05 121	82.71 115	75.14 167	69.56 161	65.72 181	63.13 203	80.38 146	91.15 85	89.51 122	94.91 109	92.50 149

thres200		82.77 141	81.25 151	84.54 123	90.38 105	93.05 113	89.13 118	82.67 117	74.40 173	69.53 163	65.69 183	63.03 206	80.63 139	91.15 85	89.42 126	94.88 111	92.04 155

test1111		84.86 121	84.21 126	85.61 113	91.75 81	95.14 64	88.63 131	84.57 68	81.88 107	71.21 153	65.66 184	68.51 174	81.19 129	93.74 43	92.68 54	96.31 23	91.86 158

LTVRE_ROB	74.41 16	75.78 225	74.72 231	77.02 211	85.88 173	89.22 180	82.44 214	77.17 187	50.57 264	45.45 261	65.44 185	52.29 256	81.25 128	85.50 191	87.42 161	89.94 234	92.62 141
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
dtuonly		77.14 205	77.32 199	76.92 214	81.74 227	80.84 251	85.46 183	68.93 241	74.15 177	64.33 197	65.39 186	71.91 157	75.62 196	83.27 215	81.21 224	85.47 258	84.45 233

thres400		82.68 142	81.15 152	84.47 125	90.52 100	92.89 118	88.95 124	82.71 115	74.33 174	69.22 166	65.31 187	62.61 209	80.63 139	90.96 94	89.50 123	94.79 115	92.45 151

DU-MVS		81.20 158	80.30 162	82.25 154	84.98 190	90.94 146	85.70 176	83.58 95	75.74 163	64.21 198	65.30 188	59.60 228	80.22 147	86.89 165	89.31 127	94.77 117	94.29 82

NR-MVSNet		80.25 165	79.98 168	80.56 177	85.20 185	90.94 146	85.65 178	83.58 95	75.74 163	61.36 222	65.30 188	56.75 242	72.38 216	88.46 146	88.80 142	95.16 97	93.87 99

thres600view7		82.53 145	81.02 154	84.28 129	90.61 97	93.05 113	88.57 133	82.67 117	74.12 178	68.56 169	65.09 190	62.13 214	80.40 145	91.15 85	89.02 137	94.88 111	92.59 143

UniMVSNet (Re)		81.22 157	81.08 153	81.39 165	85.35 182	91.76 138	84.93 188	82.88 111	76.13 161	65.02 193	64.94 191	63.09 205	75.17 199	87.71 155	89.04 136	94.97 105	94.88 68

TranMVSNet+NR-MVSNet		80.52 162	79.84 172	81.33 167	84.92 192	90.39 151	85.53 182	84.22 77	74.27 175	60.68 227	64.93 192	59.96 223	77.48 176	86.75 170	89.28 128	95.12 101	93.29 121

IB-MVS	79.09 12	82.60 143	82.19 142	83.07 145	91.08 89	93.55 104	80.90 227	81.35 138	76.56 158	80.87 88	64.81 193	69.97 166	68.87 228	85.64 188	90.06 107	95.36 76	94.74 72
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
pmmvs4		79.99 166	78.08 189	82.22 155	83.04 212	87.16 206	84.95 187	78.80 174	78.64 148	74.53 137	64.61 194	59.41 229	79.45 162	84.13 209	84.54 206	92.53 193	88.08 197

CR-MVSNet		78.71 189	78.86 180	78.55 198	85.85 176	85.15 229	82.30 216	68.23 243	74.71 170	65.37 189	64.39 195	69.59 169	77.18 178	85.10 200	84.87 200	92.34 199	88.21 195

MS-PatchMatch		81.79 152	81.44 148	82.19 156	90.35 106	89.29 179	88.08 139	75.36 211	77.60 154	69.00 167	64.37 196	78.87 97	77.14 180	88.03 151	85.70 192	93.19 186	86.24 222

tpm cat1		77.78 199	75.28 228	80.70 174	87.14 163	85.84 222	85.81 175	70.40 233	77.44 155	78.80 112	63.72 197	64.01 201	76.55 186	75.60 254	75.21 252	85.51 257	85.12 227

RPMNet		77.07 207	77.63 196	76.42 218	85.56 180	85.15 229	81.37 221	65.27 256	74.71 170	60.29 228	63.71 198	66.59 187	73.64 210	82.71 219	82.12 221	92.38 198	88.39 193

pmmvs5		76.93 208	76.33 212	77.62 204	81.97 224	88.40 194	81.32 223	74.35 219	65.42 237	61.42 221	63.07 199	57.95 236	73.23 214	85.60 189	85.35 197	93.41 180	88.55 192

EU-MVSNet		69.98 246	72.30 242	67.28 250	75.67 251	79.39 257	73.12 254	69.94 237	63.59 243	42.80 264	62.93 200	56.71 243	55.07 254	79.13 236	78.55 235	87.06 248	85.82 226

COLMAP_ROB	76.78 15	80.50 163	78.49 183	82.85 146	90.96 92	89.65 173	86.20 172	83.40 104	77.15 156	66.54 176	62.27 201	65.62 190	77.89 173	85.23 195	84.70 203	92.11 206	84.83 230
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
pmnet_mix02		71.95 241	71.83 244	72.10 240	81.40 230	80.63 254	73.78 252	72.85 225	70.90 202	54.89 240	62.17 202	57.42 239	62.92 245	76.80 251	73.98 256	86.74 251	80.87 250

v2v482		79.84 170	78.07 190	81.90 157	83.75 202	90.21 156	87.17 154	79.85 161	70.65 204	65.93 184	61.93 203	60.07 222	80.82 133	85.25 194	86.71 171	93.88 162	91.70 165

usedtu_dtu_shiyan1		79.85 169	79.89 170	79.80 186	77.40 245	89.77 168	85.31 185	80.48 147	77.76 153	64.71 195	61.69 204	67.04 185	75.92 189	87.76 154	87.67 156	94.96 106	87.52 210

PatchT		76.42 215	77.81 194	74.80 231	78.46 242	84.30 235	71.82 256	65.03 258	73.89 179	65.37 189	61.58 205	66.70 186	77.18 178	85.10 200	84.87 200	90.94 227	88.21 195

WR-MVS		76.63 211	78.02 192	75.02 229	84.14 200	89.76 169	78.34 240	80.64 146	69.56 209	52.32 248	61.26 206	61.24 217	60.66 247	84.45 207	87.07 165	93.99 155	92.77 136

v8		79.90 168	78.39 186	81.66 160	83.97 201	89.81 165	87.16 155	77.40 186	71.49 198	67.71 171	61.24 207	62.49 210	79.83 156	85.48 192	86.17 182	93.89 161	92.02 157

PM-MVS		74.17 238	73.10 239	75.41 226	76.07 249	82.53 245	77.56 243	71.69 228	71.04 200	61.92 216	61.23 208	47.30 265	74.82 203	81.78 224	79.80 227	90.42 229	88.05 198

V42		79.59 174	78.43 185	80.94 172	82.79 218	89.71 170	86.66 167	76.73 193	71.38 199	67.42 172	61.01 209	62.30 212	78.39 169	85.56 190	86.48 176	93.65 174	92.60 142

PEN-MVS		76.02 221	76.07 215	75.95 224	83.17 210	87.97 196	79.65 231	80.07 159	66.57 228	51.45 250	60.94 210	55.47 247	66.81 237	82.72 218	86.80 170	94.59 128	92.03 156

DTE-MVSNet		75.14 233	75.44 227	74.80 231	83.18 209	87.19 205	78.25 242	80.11 156	66.05 230	48.31 256	60.88 211	54.67 249	64.54 242	82.57 220	86.17 182	94.43 139	90.53 180

CP-MVSNet		76.36 218	76.41 211	76.32 221	82.73 219	88.64 189	79.39 234	79.62 162	67.21 224	53.70 242	60.72 212	55.22 248	67.91 233	83.52 213	86.34 180	94.55 131	93.19 123

TinyColmap		76.73 209	73.95 238	79.96 183	85.16 187	85.64 225	82.34 215	78.19 178	70.63 205	62.06 214	60.69 213	49.61 261	80.81 134	85.12 199	83.69 211	91.22 224	82.27 241

v10		79.62 173	78.19 188	81.28 168	83.73 203	89.69 171	87.27 151	76.86 191	70.50 206	65.46 187	60.58 214	60.47 220	80.44 143	86.91 164	86.63 174	93.93 157	92.55 146

MDTV_nov1_ep13_2view		73.21 240	72.91 240	73.56 237	80.01 233	84.28 236	78.62 238	66.43 253	68.64 214	59.12 233	60.39 215	59.69 227	69.81 225	78.82 238	77.43 239	87.36 245	81.11 249

v1144		79.38 180	77.83 193	81.18 170	83.62 204	90.23 154	87.15 157	78.35 177	69.13 211	64.02 201	60.20 216	59.41 229	80.14 151	86.78 168	86.57 175	93.81 166	92.53 148

WR-MVS_H		75.84 224	76.93 206	74.57 234	82.86 216	89.50 176	78.34 240	79.36 167	66.90 226	52.51 246	60.20 216	59.71 225	59.73 248	83.61 212	85.77 191	94.65 125	92.84 133

v148		78.59 191	76.84 208	80.62 176	83.61 205	89.16 182	83.65 200	79.24 168	69.38 210	69.34 165	59.88 218	60.41 221	75.19 198	83.81 211	84.63 204	92.70 192	90.63 178

v144192		78.81 187	77.22 201	80.67 175	82.95 213	89.79 167	86.40 169	77.42 185	68.26 217	63.13 206	59.50 219	58.13 234	80.08 152	85.93 184	86.08 184	94.06 151	92.83 134

PS-CasMVS		75.90 223	75.86 220	75.96 223	82.59 220	88.46 193	79.23 237	79.56 164	66.00 231	52.77 245	59.48 220	54.35 252	67.14 236	83.37 214	86.23 181	94.47 136	93.10 127

v1192		78.94 185	77.33 198	80.82 173	83.25 208	89.90 163	86.91 162	77.72 183	68.63 215	62.61 210	59.17 221	57.53 238	80.62 141	86.89 165	86.47 177	93.79 167	92.75 138

TDRefinement		79.05 183	77.05 203	81.39 165	88.45 141	89.00 186	86.92 161	82.65 119	74.21 176	64.41 196	59.17 221	59.16 231	74.52 205	85.23 195	85.09 198	91.37 220	87.51 211

FMVSNet5		75.50 231	76.07 215	74.83 230	76.16 248	81.19 250	81.34 222	70.21 235	73.20 189	61.59 220	58.97 223	68.33 177	68.50 229	85.87 186	85.85 190	91.18 225	79.11 254

FMVSNet1		81.64 154	80.61 159	82.84 147	82.36 222	89.20 181	88.67 128	79.58 163	70.79 203	72.63 151	58.95 224	72.26 156	79.34 163	90.73 99	90.72 80	94.47 136	91.62 166

wanda-best-256-512		75.51 229	74.25 235	76.99 212	69.08 259	86.01 214	83.06 204	75.62 206	68.11 220	66.14 180	58.89 225	64.15 197	75.77 191	78.43 241	76.54 244	92.29 201	87.59 208

FE-blended-shiyan7		75.51 229	74.25 235	76.99 212	69.08 259	86.01 214	83.06 204	75.62 206	68.12 219	66.14 180	58.89 225	64.15 197	75.77 191	78.43 241	76.54 244	92.29 201	87.59 208

v1921920		78.57 192	76.99 204	80.41 181	82.93 214	89.63 174	86.38 170	77.14 188	68.31 216	61.80 218	58.89 225	56.79 241	80.19 150	86.50 177	86.05 186	94.02 153	92.76 137

blended_shiyan6		75.62 227	74.41 233	77.03 210	69.20 257	86.12 212	83.03 208	75.65 204	68.09 223	66.14 180	58.83 228	64.22 195	75.70 194	78.65 239	76.94 240	92.49 197	88.01 199

blended_shiyan8		75.62 227	74.39 234	77.05 209	69.20 257	86.13 211	83.05 207	75.65 204	68.14 218	66.18 179	58.73 229	64.21 196	75.71 193	78.65 239	76.92 241	92.50 196	87.96 201

pm-mvs1		78.51 193	77.75 195	79.40 187	84.83 193	89.30 178	83.55 201	79.38 166	62.64 244	63.68 203	58.73 229	64.68 193	70.78 223	89.79 123	87.84 153	94.17 147	91.28 172

gbinet_0.2-2-1-0.02		75.42 232	74.57 232	76.42 218	67.86 263	86.00 218	82.79 210	76.24 195	65.77 234	65.59 186	58.60 231	65.11 192	73.76 209	79.11 237	76.90 242	92.27 205	90.47 181

v1240		78.15 195	76.53 209	80.04 182	82.85 217	89.48 177	85.61 181	76.77 192	67.05 225	61.18 225	58.37 232	56.16 245	79.89 155	86.11 183	86.08 184	93.92 158	92.47 150

Baseline_NR-MVSNet		79.84 170	78.37 187	81.55 163	84.98 190	86.66 208	85.06 186	83.49 97	75.57 165	63.31 205	58.22 233	60.97 218	78.00 172	86.89 165	87.13 164	94.47 136	93.15 126

Anonymous202405211			82.75 140		89.58 130	92.97 116	89.04 122	84.13 82	78.72 147		57.18 234	76.64 123	83.13 111	89.55 128	89.92 112	93.38 181	94.28 85

TransMVSNet (Re)		76.57 212	75.16 229	78.22 202	85.60 179	87.24 204	82.46 212	81.23 141	59.80 253	59.05 235	57.07 235	59.14 232	66.60 239	88.09 150	86.82 169	94.37 142	87.95 203

v7n		77.22 204	76.23 213	78.38 201	81.89 225	89.10 185	82.24 218	76.36 194	65.96 232	61.21 224	56.56 236	55.79 246	75.07 201	86.55 174	86.68 172	93.52 176	92.95 131

tmp_tt				32.73 266	43.96 275	21.15 277	26.71 276	8.99 272	65.67 235	51.39 251	56.01 237	42.64 269	11.76 275	56.60 267	50.81 268	53.55 274

Anonymous20231211		84.42 128	83.02 136	86.05 107	88.85 137	92.70 123	88.92 126	83.40 104	79.99 133	78.31 114	55.83 238	78.92 96	83.33 109	89.06 135	89.76 117	93.50 178	94.90 67

MIMVSNet		74.69 235	75.60 225	73.62 236	76.02 250	85.31 228	81.21 226	67.43 247	71.02 201	59.07 234	54.48 239	64.07 199	66.14 240	86.52 176	86.64 173	91.83 212	81.17 248

UniMVSNet_ETH3D		79.24 181	76.47 210	82.48 151	85.66 178	90.97 145	86.08 173	81.63 133	64.48 239	68.94 168	54.47 240	57.65 237	78.83 167	85.20 198	88.91 141	93.72 170	93.60 115

MDA-MVSNet-bldmvs		66.22 251	64.49 255	68.24 248	61.67 266	82.11 249	70.07 260	76.16 198	59.14 255	47.94 257	54.35 241	35.82 274	67.33 235	64.94 265	75.68 250	86.30 254	79.36 253

pmmvs-eth3d		74.32 237	71.96 243	77.08 208	77.33 246	82.71 243	78.41 239	76.02 200	66.65 227	65.98 183	54.23 242	49.02 263	73.14 215	82.37 222	82.69 218	91.61 216	86.05 224

WB-MVS		52.27 261	57.26 262	46.45 261	75.64 252	65.62 269	40.45 275	75.80 202	47.10 267	9.11 278	53.83 243	38.98 273	14.47 274	69.44 260	68.29 263	63.24 271	57.56 269

test20.03		68.31 249	70.05 249	66.28 252	82.41 221	80.84 251	67.35 263	76.11 199	58.44 256	40.80 267	53.77 244	54.54 250	42.28 264	83.07 216	81.96 223	88.73 240	77.76 257

CMPMVS	56.49 17	73.84 239	71.73 245	76.31 222	85.20 185	85.67 224	75.80 247	73.23 222	62.26 245	65.40 188	53.40 245	59.70 226	71.77 219	80.25 230	79.56 230	86.45 253	81.28 247
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
EG-PatchMatch MVS		76.40 217	75.47 226	77.48 205	85.86 175	90.22 155	82.45 213	73.96 221	59.64 254	59.60 231	52.75 246	62.20 213	68.44 230	88.23 149	87.50 159	94.55 131	87.78 206

CHOSEN 1792x2688		82.16 146	80.91 157	83.61 139	91.14 88	92.01 134	89.55 105	79.15 169	79.87 136	70.29 157	52.51 247	72.56 154	81.39 127	88.87 140	88.17 151	90.15 232	92.37 152

tfpnnormal		77.46 202	74.86 230	80.49 178	86.34 171	88.92 187	84.33 195	81.26 140	61.39 248	61.70 219	51.99 248	53.66 254	74.84 202	88.63 141	87.38 162	94.50 133	92.08 153

PatchmatchNet3										46.50 259	51.71 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		66.85 250	66.63 252	67.11 251	78.73 238	74.66 263	70.53 258	71.07 230	66.46 229	46.54 258	51.68 250	51.91 258	55.48 253	74.68 255	72.38 258	80.29 266	74.65 260

dtuonlycased		69.72 247	68.74 250	70.86 244	74.97 254	83.54 238	75.33 249	68.22 245	63.98 242	50.82 254	50.34 251	62.09 215	69.26 227	68.11 262	69.75 262	86.54 252	83.37 237

gm-plane-assit		70.29 245	70.65 246	69.88 246	85.03 188	78.50 259	58.41 269	65.47 255	50.39 265	40.88 266	49.60 252	50.11 260	75.14 200	91.43 76	89.78 115	94.32 143	84.73 232

HyFIR lowres test		81.62 156	79.45 178	84.14 133	91.00 91	93.38 109	88.27 136	78.19 178	76.28 160	70.18 159	48.78 253	73.69 148	83.52 106	87.05 162	87.83 155	93.68 172	89.15 188

DeepMVS_CX						48.31 273	48.03 271	26.08 270	56.42 258	25.77 274	47.51 254	31.31 275	51.30 258	48.49 269		53.61 273	61.52 266

pmmvs6		74.83 234	72.89 241	77.09 207	82.11 223	87.50 202	80.88 228	76.97 189	52.79 262	61.91 217	46.66 255	60.49 219	69.28 226	86.74 171	85.46 195	91.39 219	90.56 179

gg-mvs-nofinetune		75.64 226	77.26 200	73.76 235	87.92 152	92.20 131	87.32 149	64.67 259	51.92 263	35.35 271	46.44 256	77.05 117	71.97 217	92.64 58	91.02 72	95.34 81	89.53 186

new-patchmatchnet		63.80 254	63.31 256	64.37 254	76.49 247	75.99 261	63.73 266	70.99 231	57.27 257	43.08 263	45.86 257	43.80 267	45.13 263	73.20 258	70.68 261	86.80 250	76.34 259

FPMVS		63.63 255	60.08 261	67.78 249	80.01 233	71.50 266	72.88 255	69.41 240	61.82 247	53.11 244	45.12 258	42.11 270	50.86 259	66.69 263	63.84 264	80.41 264	69.46 264

Anonymous20231206		70.80 244	70.59 247	71.04 243	81.60 228	82.49 246	74.64 251	75.87 201	64.17 240	49.27 255	44.85 259	53.59 255	54.68 255	83.07 216	82.34 220	90.17 231	83.65 235

MVS-HIRNet		68.83 248	66.39 253	71.68 241	77.58 243	75.52 262	66.45 264	65.05 257	62.16 246	62.84 207	44.76 260	56.60 244	71.96 218	78.04 246	75.06 253	86.18 255	72.56 262

new_pmnet		59.28 258	61.47 260	56.73 259	61.66 267	68.29 268	59.57 268	54.91 264	60.83 250	34.38 272	44.66 261	43.65 268	49.90 260	71.66 259	71.56 260	79.94 267	69.67 263

VLMVS_CLIP		20.42 268	30.84 268	8.27 269	9.48 278	14.89 279	7.31 281	1.43 273	31.73 272	1.73 281	42.31 262	24.42 278	16.57 273	29.99 271	25.85 272	13.11 278	46.66 272

pmmvs3		61.89 257	61.74 258	62.06 257	64.30 265	70.83 267	64.22 265	52.14 267	48.78 266	44.47 262	41.67 263	41.70 271	63.03 244	76.06 253	76.02 249	84.18 261	77.14 258

FE-MVSNET		66.05 252	67.24 251	64.66 253	59.88 268	79.66 256	69.18 261	74.46 217	55.47 261	37.02 270	41.66 264	48.62 264	55.72 250	80.54 228	83.09 214	91.68 213	81.66 244

FE-MVSNET2		71.00 243	70.45 248	71.65 242	66.32 264	85.00 232	76.33 245	76.20 197	61.03 249	52.47 247	41.50 265	50.21 259	64.44 243	84.97 202	85.46 195	94.16 148	84.97 228

MVS_clip		18.62 269	29.48 269	5.95 270	5.46 279	10.98 280	4.66 282	0.97 274	34.09 271	0.72 282	40.29 266	25.13 276	17.18 271	27.33 273	23.64 273	6.69 279	44.89 273

ambc			61.92 257		70.98 256	73.54 265	63.64 267		60.06 251	52.23 249	38.44 267	19.17 279	57.12 249	82.33 223	75.03 254	83.21 263	84.89 229

MIMVSNet1		65.00 253	66.24 254	63.55 255	58.41 270	80.01 255	69.00 262	74.03 220	55.81 259	41.88 265	36.81 268	49.48 262	47.89 262	81.32 225	82.40 219	90.08 233	77.88 256

PMVS	50.48 18	55.81 260	51.93 263	60.33 258	72.90 255	49.34 271	48.78 270	69.51 239	43.49 268	54.25 241	36.26 269	41.04 272	39.71 266	65.07 264	60.70 265	76.85 268	67.58 265
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		41.78 263	48.10 264	34.42 265	10.74 277	19.78 278	44.64 272	17.73 271	59.83 252	38.67 269	35.82 270	54.41 251	34.94 267	62.87 266	43.13 269	59.81 272	60.82 267

usedtu_dtu_shiyan2		62.45 256	61.54 259	63.50 256	49.14 273	78.26 260	71.51 257	67.18 249	43.16 269	53.22 243	33.68 271	45.76 266	53.15 257	74.24 257	74.13 255	86.83 249	81.56 246

PMMVS2		41.68 264	44.74 266	38.10 262	46.97 274	52.32 270	40.63 274	48.08 268	35.51 270	7.36 279	26.86 272	24.64 277	16.72 272	55.24 268	59.03 266	68.85 270	59.59 268

Gipuma		49.17 262	47.05 265	51.65 260	59.67 269	48.39 272	41.98 273	63.47 260	55.64 260	33.33 273	14.90 273	13.78 281	41.34 265	69.31 261	72.30 259	70.11 269	55.00 270
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
VLMVS		8.89 270	13.44 272	3.59 271	5.08 280	6.17 281	2.76 283	0.68 275	15.76 276	2.37 280	14.73 274	16.29 280	7.11 276	9.48 275	8.48 274	3.54 280	23.17 276

E-PMN		31.40 265	26.80 270	36.78 263	51.39 272	29.96 275	20.20 277	54.17 265	25.93 274	12.75 276	14.73 274	8.58 283	34.10 269	27.36 272	37.83 270	48.07 275	43.18 274

MVE	30.17 19	30.88 266	33.52 267	27.80 268	23.78 276	39.16 274	18.69 279	46.90 269	21.88 275	15.39 275	14.37 276	7.31 285	24.41 270	41.63 270	56.22 267	37.64 277	54.07 271
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EMVS		30.49 267	25.44 271	36.39 264	51.47 271	29.89 276	20.17 278	54.00 266	26.49 273	12.02 277	13.94 277	8.84 282	34.37 268	25.04 274	34.37 271	46.29 276	39.53 275

MVS_baseline		4.92 271	8.41 273	0.85 272	0.32 281	0.47 282	0.13 286	0.00 279	9.53 277	0.00 286	11.57 278	7.80 284	4.61 277	4.54 276	4.62 275	0.04 283	20.32 277

testmvs		1.03 272	1.63 274	0.34 273	0.09 283	0.35 283	0.61 284	0.16 276	1.49 278	0.10 284	3.15 279	0.15 286	0.86 279	1.32 277	1.18 276	0.20 281	3.76 279

test123		0.87 273	1.40 275	0.25 274	0.03 284	0.25 284	0.35 285	0.08 278	1.21 279	0.05 285	2.84 280	0.03 287	0.89 278	0.43 278	1.16 277	0.13 282	3.87 278

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

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

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

PatchmatchNet2					78.78 237	73.76 264	70.51 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1												52.02 257	55.56 251	74.53 256	72.48 257	80.30 265	74.43 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							96.76 8	92.70 8		92.16 7						96.77 9

RE-MVS-def										56.08 239

9.14												92.16 20

SR-MVS					96.58 27			90.99 25				92.40 16

our_test_3					81.81 226	83.96 237	76.61 244

MTAPA										92.97 3		91.03 28

MTMP										93.14 2		90.21 35

Patchmatch-RL test							8.55 280

XVS					93.11 64	96.70 28	91.91 59			83.95 54		88.82 44				95.79 45

X-MVStestdata					93.11 64	96.70 28	91.91 59			83.95 54		88.82 44				95.79 45

mPP-MVS					97.06 13							88.08 49

NP-MVS									87.47 60

Patchmtry						85.54 227	82.30 216	68.23 243		65.37 189

High-resolution multi-view benchmark