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	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

DVP-MVS++		95.98 1	96.36 1	94.82 28	97.78 51	86.00 47	98.29 1	97.49 6	90.75 17	97.62 5	98.06 6	92.59 2	99.61 3	95.64 7	99.02 12	98.86 10

SED-MVS		95.91 2	96.28 2	94.80 30	98.77 5	85.99 49	97.13 14	97.44 15	90.31 26	97.71 1	98.07 4	92.31 4	99.58 8	95.66 5	99.13 3	98.84 13

DVP-MVS		95.67 3	96.02 3	94.64 36	98.78 3	85.93 52	97.09 16	96.73 77	90.27 29	97.04 11	98.05 8	91.47 8	99.55 14	95.62 9	99.08 7	98.45 34
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
DPE-MVS		95.57 4	95.67 4	95.25 9	98.36 25	87.28 15	95.56 83	97.51 5	89.13 59	97.14 9	97.91 11	91.64 7	99.62 1	94.61 15	99.17 2	98.86 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		95.46 5	95.64 5	94.91 19	98.26 28	86.29 43	97.46 6	97.40 20	89.03 62	96.20 17	98.10 2	89.39 16	99.34 32	95.88 4	99.03 11	99.10 4

MSP-MVS		95.42 6	95.56 6	94.98 17	98.49 17	86.52 33	96.91 25	97.47 11	91.73 8	96.10 18	96.69 54	89.90 12	99.30 38	94.70 13	98.04 64	99.13 2
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
CNVR-MVS		95.40 7	95.37 7	95.50 7	98.11 36	88.51 7	95.29 93	96.96 51	92.09 4	95.32 23	97.08 37	89.49 15	99.33 35	95.10 12	98.85 19	98.66 19

SMA-MVS		95.20 8	95.07 11	95.59 5	98.14 35	88.48 8	96.26 45	97.28 30	85.90 139	97.67 3	98.10 2	88.41 20	99.56 10	94.66 14	99.19 1	98.71 18
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
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 23	96.99 72	86.33 39	97.33 7	97.30 28	91.38 10	95.39 22	97.46 18	88.98 19	99.40 28	94.12 19	98.89 18	98.82 15
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS++		95.14 10	94.91 13	95.83 4	98.25 29	89.65 4	95.92 64	96.96 51	91.75 7	94.02 36	96.83 49	88.12 24	99.55 14	93.41 30	98.94 16	98.28 48

SF-MVS		94.97 11	94.90 14	95.20 10	97.84 47	87.76 9	96.65 34	97.48 10	87.76 102	95.71 20	97.70 14	88.28 23	99.35 31	93.89 23	98.78 25	98.48 28

SD-MVS		94.96 12	95.33 8	93.88 54	97.25 69	86.69 25	96.19 48	97.11 42	90.42 25	96.95 13	97.27 26	89.53 14	96.91 235	94.38 17	98.85 19	98.03 68
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TSAR-MVS + MP.		94.85 13	94.94 12	94.58 39	98.25 29	86.33 39	96.11 54	96.62 86	88.14 90	96.10 18	96.96 43	89.09 18	98.94 73	94.48 16	98.68 35	98.48 28
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
NCCC		94.81 14	94.69 16	95.17 12	97.83 48	87.46 14	95.66 77	96.93 55	92.34 2	93.94 37	96.58 64	87.74 27	99.44 27	92.83 38	98.40 50	98.62 20

ACMMP_NAP		94.74 15	94.56 17	95.28 8	98.02 41	87.70 10	95.68 75	97.34 22	88.28 83	95.30 24	97.67 15	85.90 44	99.54 18	93.91 22	98.95 15	98.60 21

test_fmvsm_n_1920		94.71 16	95.11 10	93.50 62	95.79 112	84.62 72	96.15 51	97.64 2	89.85 38	97.19 8	97.89 12	86.28 40	98.71 89	97.11 1	98.08 63	97.17 103

HFP-MVS		94.52 17	94.40 20	94.86 22	98.61 10	86.81 22	96.94 20	97.34 22	88.63 72	93.65 41	97.21 30	86.10 42	99.49 24	92.35 49	98.77 27	98.30 45

ZNCC-MVS		94.47 18	94.28 24	95.03 14	98.52 15	86.96 17	96.85 28	97.32 26	88.24 84	93.15 51	97.04 40	86.17 41	99.62 1	92.40 47	98.81 22	98.52 24

XVS		94.45 19	94.32 21	94.85 23	98.54 13	86.60 31	96.93 22	97.19 34	90.66 22	92.85 58	97.16 35	85.02 55	99.49 24	91.99 62	98.56 46	98.47 31

MCST-MVS		94.45 19	94.20 29	95.19 11	98.46 19	87.50 13	95.00 113	97.12 40	87.13 112	92.51 72	96.30 71	89.24 17	99.34 32	93.46 27	98.62 42	98.73 16

region2R		94.43 21	94.27 26	94.92 18	98.65 8	86.67 27	96.92 24	97.23 33	88.60 74	93.58 43	97.27 26	85.22 51	99.54 18	92.21 52	98.74 29	98.56 23

ACMMPR		94.43 21	94.28 24	94.91 19	98.63 9	86.69 25	96.94 20	97.32 26	88.63 72	93.53 46	97.26 28	85.04 54	99.54 18	92.35 49	98.78 25	98.50 25

MTAPA		94.42 23	94.22 27	95.00 16	98.42 21	86.95 18	94.36 158	96.97 49	91.07 11	93.14 52	97.56 16	84.30 63	99.56 10	93.43 28	98.75 28	98.47 31

CP-MVS		94.34 24	94.21 28	94.74 34	98.39 23	86.64 29	97.60 4	97.24 31	88.53 76	92.73 66	97.23 29	85.20 52	99.32 36	92.15 55	98.83 21	98.25 53

MP-MVS		94.25 25	94.07 33	94.77 32	98.47 18	86.31 41	96.71 31	96.98 48	89.04 61	91.98 81	97.19 32	85.43 49	99.56 10	92.06 61	98.79 23	98.44 35
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 26	94.07 33	94.75 33	98.06 39	86.90 20	95.88 65	96.94 54	85.68 145	95.05 26	97.18 33	87.31 33	99.07 51	91.90 68	98.61 44	98.28 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS		94.23 27	94.17 31	94.43 44	98.21 32	85.78 59	96.40 39	96.90 58	88.20 88	94.33 30	97.40 21	84.75 60	99.03 56	93.35 31	97.99 65	98.48 28

GST-MVS		94.21 28	93.97 36	94.90 21	98.41 22	86.82 21	96.54 36	97.19 34	88.24 84	93.26 48	96.83 49	85.48 48	99.59 7	91.43 75	98.40 50	98.30 45

MP-MVS-pluss		94.21 28	94.00 35	94.85 23	98.17 33	86.65 28	94.82 124	97.17 38	86.26 131	92.83 60	97.87 13	85.57 47	99.56 10	94.37 18	98.92 17	98.34 40
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DeepPCF-MVS	89.96 1	94.20 30	94.77 15	92.49 102	96.52 87	80.00 205	94.00 182	97.08 43	90.05 33	95.65 21	97.29 25	89.66 13	98.97 70	93.95 21	98.71 30	98.50 25

CS-MVS		94.12 31	94.44 19	93.17 69	96.55 84	83.08 116	97.63 3	96.95 53	91.71 9	93.50 47	96.21 74	85.61 45	98.24 124	93.64 25	98.17 56	98.19 56

DeepC-MVS_fast	89.43 2	94.04 32	93.79 39	94.80 30	97.48 61	86.78 23	95.65 79	96.89 59	89.40 51	92.81 61	96.97 42	85.37 50	99.24 41	90.87 85	98.69 33	98.38 39
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CS-MVS-test		94.02 33	94.29 23	93.24 66	96.69 78	83.24 109	97.49 5	96.92 56	92.14 3	92.90 56	95.77 96	85.02 55	98.33 119	93.03 35	98.62 42	98.13 60

HPM-MVS		94.02 33	93.88 37	94.43 44	98.39 23	85.78 59	97.25 10	97.07 44	86.90 120	92.62 69	96.80 53	84.85 59	99.17 45	92.43 45	98.65 40	98.33 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		93.99 35	93.78 40	94.63 37	98.50 16	85.90 56	96.87 26	96.91 57	88.70 70	91.83 90	97.17 34	83.96 67	99.55 14	91.44 74	98.64 41	98.43 36

PGM-MVS		93.96 36	93.72 42	94.68 35	98.43 20	86.22 44	95.30 91	97.78 1	87.45 108	93.26 48	97.33 24	84.62 61	99.51 22	90.75 87	98.57 45	98.32 44

PHI-MVS		93.89 37	93.65 45	94.62 38	96.84 75	86.43 36	96.69 32	97.49 6	85.15 159	93.56 45	96.28 72	85.60 46	99.31 37	92.45 44	98.79 23	98.12 62

SR-MVS-dyc-post		93.82 38	93.82 38	93.82 56	97.92 43	84.57 74	96.28 43	96.76 73	87.46 106	93.75 39	97.43 19	84.24 64	99.01 61	92.73 39	97.80 71	97.88 75

APD-MVS_3200maxsize		93.78 39	93.77 41	93.80 58	97.92 43	84.19 86	96.30 41	96.87 61	86.96 116	93.92 38	97.47 17	83.88 68	98.96 72	92.71 42	97.87 69	98.26 52

patch_mono-2		93.74 40	94.32 21	92.01 118	97.54 57	78.37 243	93.40 206	97.19 34	88.02 92	94.99 27	97.21 30	88.35 21	98.44 110	94.07 20	98.09 61	99.23 1

MSLP-MVS++		93.72 41	94.08 32	92.65 94	97.31 65	83.43 104	95.79 69	97.33 24	90.03 34	93.58 43	96.96 43	84.87 58	97.76 162	92.19 54	98.66 38	96.76 120

TSAR-MVS + GP.		93.66 42	93.41 46	94.41 46	96.59 82	86.78 23	94.40 151	93.93 237	89.77 43	94.21 31	95.59 103	87.35 32	98.61 96	92.72 41	96.15 99	97.83 79

CANet		93.54 43	93.20 50	94.55 40	95.65 118	85.73 61	94.94 116	96.69 82	91.89 6	90.69 106	95.88 90	81.99 91	99.54 18	93.14 34	97.95 67	98.39 37

dcpmvs_2		93.49 44	94.19 30	91.38 152	97.69 54	76.78 275	94.25 161	96.29 102	88.33 80	94.46 28	96.88 46	88.07 25	98.64 92	93.62 26	98.09 61	98.73 16

MVS_111021_HR		93.45 45	93.31 47	93.84 55	96.99 72	84.84 68	93.24 218	97.24 31	88.76 69	91.60 95	95.85 91	86.07 43	98.66 90	91.91 66	98.16 57	98.03 68

train_agg		93.44 46	93.08 51	94.52 41	97.53 58	86.49 34	94.07 174	96.78 70	81.86 230	92.77 63	96.20 75	87.63 29	99.12 49	92.14 56	98.69 33	97.94 71

EC-MVSNet		93.44 46	93.71 43	92.63 95	95.21 132	82.43 137	97.27 9	96.71 80	90.57 24	92.88 57	95.80 94	83.16 72	98.16 130	93.68 24	98.14 58	97.31 96

DELS-MVS		93.43 48	93.25 48	93.97 51	95.42 125	85.04 67	93.06 225	97.13 39	90.74 19	91.84 88	95.09 119	86.32 39	99.21 43	91.22 76	98.45 48	97.65 84
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
HPM-MVS_fast		93.40 49	93.22 49	93.94 53	98.36 25	84.83 69	97.15 13	96.80 69	85.77 142	92.47 73	97.13 36	82.38 80	99.07 51	90.51 92	98.40 50	97.92 74

DeepC-MVS	88.79 3	93.31 50	92.99 53	94.26 49	96.07 102	85.83 57	94.89 119	96.99 47	89.02 64	89.56 120	97.37 23	82.51 79	99.38 29	92.20 53	98.30 53	97.57 89
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
canonicalmvs		93.27 51	92.75 57	94.85 23	95.70 117	87.66 11	96.33 40	96.41 96	90.00 35	94.09 34	94.60 140	82.33 82	98.62 95	92.40 47	92.86 161	98.27 50

ACMMP		93.24 52	92.88 55	94.30 48	98.09 38	85.33 65	96.86 27	97.45 14	88.33 80	90.15 115	97.03 41	81.44 94	99.51 22	90.85 86	95.74 102	98.04 67
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
CSCG		93.23 53	93.05 52	93.76 59	98.04 40	84.07 88	96.22 47	97.37 21	84.15 175	90.05 116	95.66 100	87.77 26	99.15 48	89.91 95	98.27 54	98.07 64

alignmvs		93.08 54	92.50 61	94.81 29	95.62 120	87.61 12	95.99 60	96.07 120	89.77 43	94.12 33	94.87 125	80.56 100	98.66 90	92.42 46	93.10 157	98.15 59

EI-MVSNet-Vis-set		93.01 55	92.92 54	93.29 64	95.01 139	83.51 103	94.48 143	95.77 142	90.87 13	92.52 71	96.67 56	84.50 62	99.00 65	91.99 62	94.44 132	97.36 95

casdiffmvs_mvg		92.96 56	92.83 56	93.35 63	94.59 162	83.40 106	95.00 113	96.34 100	90.30 28	92.05 79	96.05 83	83.43 70	98.15 131	92.07 58	95.67 103	98.49 27
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UA-Net		92.83 57	92.54 60	93.68 60	96.10 100	84.71 71	95.66 77	96.39 97	91.92 5	93.22 50	96.49 67	83.16 72	98.87 77	84.47 161	95.47 108	97.45 94

CDPH-MVS		92.83 57	92.30 63	94.44 42	97.79 49	86.11 46	94.06 176	96.66 83	80.09 257	92.77 63	96.63 61	86.62 36	99.04 55	87.40 123	98.66 38	98.17 58

ETV-MVS		92.74 59	92.66 58	92.97 79	95.20 133	84.04 90	95.07 109	96.51 92	90.73 20	92.96 55	91.19 259	84.06 65	98.34 117	91.72 70	96.54 93	96.54 129

EI-MVSNet-UG-set		92.74 59	92.62 59	93.12 71	94.86 150	83.20 111	94.40 151	95.74 145	90.71 21	92.05 79	96.60 63	84.00 66	98.99 67	91.55 72	93.63 142	97.17 103

DPM-MVS		92.58 61	91.74 69	95.08 13	96.19 95	89.31 5	92.66 235	96.56 91	83.44 193	91.68 94	95.04 120	86.60 38	98.99 67	85.60 147	97.92 68	96.93 116

casdiffmvs		92.51 62	92.43 62	92.74 89	94.41 174	81.98 147	94.54 141	96.23 109	89.57 47	91.96 83	96.17 79	82.58 78	98.01 149	90.95 83	95.45 110	98.23 54
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_111021_LR		92.47 63	92.29 64	92.98 78	95.99 106	84.43 83	93.08 223	96.09 118	88.20 88	91.12 102	95.72 99	81.33 96	97.76 162	91.74 69	97.37 78	96.75 121

3Dnovator+	87.14 4	92.42 64	91.37 72	95.55 6	95.63 119	88.73 6	97.07 18	96.77 72	90.84 14	84.02 244	96.62 62	75.95 151	99.34 32	87.77 117	97.68 74	98.59 22

baseline		92.39 65	92.29 64	92.69 93	94.46 171	81.77 152	94.14 167	96.27 104	89.22 55	91.88 86	96.00 84	82.35 81	97.99 151	91.05 78	95.27 115	98.30 45

VNet		92.24 66	91.91 67	93.24 66	96.59 82	83.43 104	94.84 123	96.44 94	89.19 57	94.08 35	95.90 89	77.85 135	98.17 129	88.90 105	93.38 151	98.13 60

CPTT-MVS		91.99 67	91.80 68	92.55 99	98.24 31	81.98 147	96.76 30	96.49 93	81.89 229	90.24 111	96.44 69	78.59 124	98.61 96	89.68 96	97.85 70	97.06 108

EIA-MVS		91.95 68	91.94 66	91.98 122	95.16 134	80.01 204	95.36 86	96.73 77	88.44 77	89.34 124	92.16 225	83.82 69	98.45 109	89.35 99	97.06 81	97.48 92

DP-MVS Recon		91.95 68	91.28 74	93.96 52	98.33 27	85.92 54	94.66 135	96.66 83	82.69 211	90.03 117	95.82 93	82.30 83	99.03 56	84.57 159	96.48 96	96.91 117

EPNet		91.79 70	91.02 80	94.10 50	90.10 313	85.25 66	96.03 59	92.05 284	92.83 1	87.39 159	95.78 95	79.39 115	99.01 61	88.13 113	97.48 76	98.05 66
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MG-MVS		91.77 71	91.70 70	92.00 121	97.08 71	80.03 203	93.60 200	95.18 183	87.85 100	90.89 104	96.47 68	82.06 89	98.36 114	85.07 151	97.04 82	97.62 85

Vis-MVSNet		91.75 72	91.23 75	93.29 64	95.32 127	83.78 95	96.14 52	95.98 126	89.89 36	90.45 108	96.58 64	75.09 163	98.31 122	84.75 157	96.90 85	97.78 82
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator	86.66 5	91.73 73	90.82 84	94.44 42	94.59 162	86.37 38	97.18 12	97.02 46	89.20 56	84.31 240	96.66 57	73.74 187	99.17 45	86.74 133	97.96 66	97.79 81

EPP-MVSNet		91.70 74	91.56 71	92.13 117	95.88 109	80.50 188	97.33 7	95.25 179	86.15 135	89.76 119	95.60 102	83.42 71	98.32 121	87.37 125	93.25 154	97.56 90

MVSFormer		91.68 75	91.30 73	92.80 85	93.86 195	83.88 93	95.96 62	95.90 133	84.66 170	91.76 91	94.91 123	77.92 132	97.30 206	89.64 97	97.11 79	97.24 99

Effi-MVS+		91.59 76	91.11 77	93.01 77	94.35 178	83.39 107	94.60 137	95.10 187	87.10 113	90.57 107	93.10 197	81.43 95	98.07 145	89.29 101	94.48 130	97.59 88

IS-MVSNet		91.43 77	91.09 79	92.46 103	95.87 111	81.38 164	96.95 19	93.69 248	89.72 45	89.50 122	95.98 86	78.57 125	97.77 161	83.02 179	96.50 95	98.22 55

PVSNet_Blended_VisFu		91.38 78	90.91 82	92.80 85	96.39 90	83.17 112	94.87 121	96.66 83	83.29 197	89.27 125	94.46 144	80.29 102	99.17 45	87.57 121	95.37 111	96.05 147

diffmvs		91.37 79	91.23 75	91.77 137	93.09 217	80.27 191	92.36 244	95.52 162	87.03 115	91.40 99	94.93 122	80.08 104	97.44 190	92.13 57	94.56 127	97.61 86
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		91.31 80	91.11 77	91.93 126	94.37 175	80.14 196	93.46 205	95.80 140	86.46 127	91.35 100	93.77 176	82.21 85	98.09 142	87.57 121	94.95 118	97.55 91

OMC-MVS		91.23 81	90.62 86	93.08 73	96.27 93	84.07 88	93.52 202	95.93 129	86.95 117	89.51 121	96.13 81	78.50 126	98.35 116	85.84 145	92.90 160	96.83 119

PAPM_NR		91.22 82	90.78 85	92.52 101	97.60 56	81.46 161	94.37 157	96.24 108	86.39 129	87.41 156	94.80 131	82.06 89	98.48 103	82.80 185	95.37 111	97.61 86

PS-MVSNAJ		91.18 83	90.92 81	91.96 124	95.26 130	82.60 136	92.09 255	95.70 147	86.27 130	91.84 88	92.46 215	79.70 110	98.99 67	89.08 103	95.86 101	94.29 219

xiu_mvs_v2_base		91.13 84	90.89 83	91.86 131	94.97 142	82.42 138	92.24 249	95.64 154	86.11 138	91.74 93	93.14 195	79.67 113	98.89 76	89.06 104	95.46 109	94.28 220

nrg030		91.08 85	90.39 87	93.17 69	93.07 218	86.91 19	96.41 37	96.26 105	88.30 82	88.37 139	94.85 128	82.19 86	97.64 173	91.09 77	82.95 272	94.96 183

lupinMVS		90.92 86	90.21 90	93.03 76	93.86 195	83.88 93	92.81 232	93.86 241	79.84 260	91.76 91	94.29 150	77.92 132	98.04 147	90.48 93	97.11 79	97.17 103

h-mvs33		90.80 87	90.15 93	92.75 88	96.01 104	82.66 133	95.43 85	95.53 161	89.80 39	93.08 53	95.64 101	75.77 152	99.00 65	92.07 58	78.05 327	96.60 125

jason		90.80 87	90.10 94	92.90 82	93.04 220	83.53 102	93.08 223	94.15 230	80.22 254	91.41 98	94.91 123	76.87 139	97.93 156	90.28 94	96.90 85	97.24 99
jason: jason.
VDD-MVS		90.74 89	89.92 101	93.20 68	96.27 93	83.02 118	95.73 72	93.86 241	88.42 79	92.53 70	96.84 48	62.09 298	98.64 92	90.95 83	92.62 164	97.93 73

PVSNet_Blended		90.73 90	90.32 89	91.98 122	96.12 97	81.25 166	92.55 239	96.83 65	82.04 223	89.10 127	92.56 213	81.04 98	98.85 81	86.72 135	95.91 100	95.84 154

test_yl		90.69 91	90.02 99	92.71 90	95.72 115	82.41 140	94.11 169	95.12 185	85.63 147	91.49 96	94.70 134	74.75 167	98.42 112	86.13 140	92.53 165	97.31 96

DCV-MVSNet		90.69 91	90.02 99	92.71 90	95.72 115	82.41 140	94.11 169	95.12 185	85.63 147	91.49 96	94.70 134	74.75 167	98.42 112	86.13 140	92.53 165	97.31 96

API-MVS		90.66 93	90.07 95	92.45 104	96.36 91	84.57 74	96.06 58	95.22 182	82.39 214	89.13 126	94.27 153	80.32 101	98.46 106	80.16 232	96.71 90	94.33 216

xiu_mvs_v1_base_debu		90.64 94	90.05 96	92.40 105	93.97 192	84.46 80	93.32 208	95.46 164	85.17 156	92.25 74	94.03 158	70.59 222	98.57 99	90.97 80	94.67 122	94.18 221

xiu_mvs_v1_base		90.64 94	90.05 96	92.40 105	93.97 192	84.46 80	93.32 208	95.46 164	85.17 156	92.25 74	94.03 158	70.59 222	98.57 99	90.97 80	94.67 122	94.18 221

xiu_mvs_v1_base_debi		90.64 94	90.05 96	92.40 105	93.97 192	84.46 80	93.32 208	95.46 164	85.17 156	92.25 74	94.03 158	70.59 222	98.57 99	90.97 80	94.67 122	94.18 221

HQP_MVS		90.60 97	90.19 91	91.82 134	94.70 158	82.73 129	95.85 66	96.22 110	90.81 15	86.91 168	94.86 126	74.23 175	98.12 132	88.15 111	89.99 188	94.63 195

FIs		90.51 98	90.35 88	90.99 173	93.99 191	80.98 174	95.73 72	97.54 4	89.15 58	86.72 173	94.68 136	81.83 93	97.24 214	85.18 150	88.31 222	94.76 193

MAR-MVS		90.30 99	89.37 111	93.07 75	96.61 81	84.48 79	95.68 75	95.67 149	82.36 216	87.85 147	92.85 202	76.63 145	98.80 85	80.01 233	96.68 91	95.91 150
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
FC-MVSNet-test		90.27 100	90.18 92	90.53 184	93.71 201	79.85 210	95.77 70	97.59 3	89.31 53	86.27 182	94.67 137	81.93 92	97.01 229	84.26 163	88.09 226	94.71 194

CANet_DTU		90.26 101	89.41 110	92.81 84	93.46 209	83.01 119	93.48 203	94.47 217	89.43 50	87.76 151	94.23 154	70.54 226	99.03 56	84.97 152	96.39 97	96.38 132

OPM-MVS		90.12 102	89.56 105	91.82 134	93.14 215	83.90 92	94.16 166	95.74 145	88.96 65	87.86 146	95.43 107	72.48 203	97.91 157	88.10 115	90.18 187	93.65 255
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LFMVS		90.08 103	89.13 117	92.95 80	96.71 77	82.32 142	96.08 55	89.91 333	86.79 121	92.15 78	96.81 51	62.60 296	98.34 117	87.18 127	93.90 138	98.19 56

GeoE		90.05 104	89.43 109	91.90 130	95.16 134	80.37 190	95.80 68	94.65 214	83.90 180	87.55 155	94.75 133	78.18 130	97.62 175	81.28 212	93.63 142	97.71 83

PAPR		90.02 105	89.27 116	92.29 113	95.78 113	80.95 176	92.68 234	96.22 110	81.91 227	86.66 174	93.75 178	82.23 84	98.44 110	79.40 243	94.79 120	97.48 92

PVSNet_BlendedMVS		89.98 106	89.70 103	90.82 177	96.12 97	81.25 166	93.92 187	96.83 65	83.49 192	89.10 127	92.26 223	81.04 98	98.85 81	86.72 135	87.86 230	92.35 300

PS-MVSNAJss		89.97 107	89.62 104	91.02 170	91.90 250	80.85 179	95.26 96	95.98 126	86.26 131	86.21 183	94.29 150	79.70 110	97.65 170	88.87 106	88.10 224	94.57 200

mvsmamba		89.96 108	89.50 106	91.33 155	92.90 227	81.82 150	96.68 33	92.37 272	89.03 62	87.00 164	94.85 128	73.05 195	97.65 170	91.03 79	88.63 213	94.51 205

XVG-OURS-SEG-HR		89.95 109	89.45 107	91.47 149	94.00 190	81.21 169	91.87 258	96.06 122	85.78 141	88.55 135	95.73 98	74.67 171	97.27 210	88.71 107	89.64 197	95.91 150

UGNet		89.95 109	88.95 121	92.95 80	94.51 168	83.31 108	95.70 74	95.23 180	89.37 52	87.58 153	93.94 166	64.00 287	98.78 86	83.92 168	96.31 98	96.74 122
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
UniMVSNet_NR-MVSNet		89.92 111	89.29 114	91.81 136	93.39 210	83.72 96	94.43 149	97.12 40	89.80 39	86.46 176	93.32 186	83.16 72	97.23 215	84.92 153	81.02 301	94.49 210

AdaColmap		89.89 112	89.07 118	92.37 108	97.41 62	83.03 117	94.42 150	95.92 130	82.81 209	86.34 181	94.65 138	73.89 183	99.02 59	80.69 223	95.51 106	95.05 178

hse-mvs2		89.88 113	89.34 112	91.51 146	94.83 152	81.12 171	93.94 185	93.91 240	89.80 39	93.08 53	93.60 180	75.77 152	97.66 169	92.07 58	77.07 334	95.74 159

UniMVSNet (Re)		89.80 114	89.07 118	92.01 118	93.60 205	84.52 77	94.78 127	97.47 11	89.26 54	86.44 179	92.32 220	82.10 87	97.39 202	84.81 156	80.84 305	94.12 225

HQP-MVS		89.80 114	89.28 115	91.34 154	94.17 181	81.56 155	94.39 153	96.04 123	88.81 66	85.43 207	93.97 165	73.83 185	97.96 153	87.11 130	89.77 195	94.50 208

FA-MVS(test-final)		89.66 116	88.91 123	91.93 126	94.57 165	80.27 191	91.36 269	94.74 211	84.87 164	89.82 118	92.61 212	74.72 170	98.47 105	83.97 167	93.53 145	97.04 110

VPA-MVSNet		89.62 117	88.96 120	91.60 142	93.86 195	82.89 124	95.46 84	97.33 24	87.91 95	88.43 138	93.31 187	74.17 178	97.40 199	87.32 126	82.86 277	94.52 203

WTY-MVS		89.60 118	88.92 122	91.67 140	95.47 124	81.15 170	92.38 243	94.78 209	83.11 201	89.06 129	94.32 148	78.67 123	96.61 249	81.57 209	90.89 181	97.24 99

Vis-MVSNet (Re-imp)		89.59 119	89.44 108	90.03 211	95.74 114	75.85 288	95.61 81	90.80 319	87.66 105	87.83 148	95.40 108	76.79 141	96.46 262	78.37 248	96.73 89	97.80 80

VDDNet		89.56 120	88.49 138	92.76 87	95.07 138	82.09 144	96.30 41	93.19 255	81.05 249	91.88 86	96.86 47	61.16 310	98.33 119	88.43 110	92.49 167	97.84 78

114514_t		89.51 121	88.50 136	92.54 100	98.11 36	81.99 146	95.16 104	96.36 99	70.19 349	85.81 188	95.25 112	76.70 143	98.63 94	82.07 197	96.86 88	97.00 113

QAPM		89.51 121	88.15 147	93.59 61	94.92 146	84.58 73	96.82 29	96.70 81	78.43 282	83.41 259	96.19 78	73.18 194	99.30 38	77.11 264	96.54 93	96.89 118

CLD-MVS		89.47 123	88.90 124	91.18 160	94.22 180	82.07 145	92.13 253	96.09 118	87.90 96	85.37 213	92.45 216	74.38 173	97.56 178	87.15 128	90.43 183	93.93 234
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		89.45 124	88.90 124	91.12 162	94.47 169	81.49 159	95.30 91	96.14 115	86.73 123	85.45 204	95.16 116	69.89 232	98.10 134	87.70 119	89.23 204	93.77 248

CDS-MVSNet		89.45 124	88.51 135	92.29 113	93.62 204	83.61 101	93.01 226	94.68 213	81.95 225	87.82 149	93.24 191	78.69 122	96.99 230	80.34 229	93.23 155	96.28 135
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
iter_conf_final		89.42 126	88.69 129	91.60 142	95.12 137	82.93 122	95.75 71	92.14 281	87.32 110	87.12 163	94.07 156	67.09 262	97.55 179	90.61 89	89.01 208	94.32 217

Fast-Effi-MVS+		89.41 127	88.64 130	91.71 139	94.74 154	80.81 180	93.54 201	95.10 187	83.11 201	86.82 172	90.67 276	79.74 109	97.75 165	80.51 227	93.55 144	96.57 127

ab-mvs		89.41 127	88.35 140	92.60 96	95.15 136	82.65 134	92.20 251	95.60 156	83.97 179	88.55 135	93.70 179	74.16 179	98.21 128	82.46 190	89.37 200	96.94 115

XVG-OURS		89.40 129	88.70 128	91.52 145	94.06 184	81.46 161	91.27 271	96.07 120	86.14 136	88.89 131	95.77 96	68.73 252	97.26 212	87.39 124	89.96 190	95.83 155

test_vis1_n_1920		89.39 130	89.84 102	88.04 270	92.97 224	72.64 318	94.71 132	96.03 125	86.18 134	91.94 85	96.56 66	61.63 301	95.74 294	93.42 29	95.11 117	95.74 159

mvs_anonymous		89.37 131	89.32 113	89.51 234	93.47 208	74.22 301	91.65 265	94.83 205	82.91 207	85.45 204	93.79 174	81.23 97	96.36 268	86.47 137	94.09 135	97.94 71

DU-MVS		89.34 132	88.50 136	91.85 133	93.04 220	83.72 96	94.47 146	96.59 88	89.50 48	86.46 176	93.29 189	77.25 137	97.23 215	84.92 153	81.02 301	94.59 198

TAMVS		89.21 133	88.29 144	91.96 124	93.71 201	82.62 135	93.30 212	94.19 228	82.22 218	87.78 150	93.94 166	78.83 119	96.95 232	77.70 257	92.98 159	96.32 133

ACMM	84.12 9	89.14 134	88.48 139	91.12 162	94.65 161	81.22 168	95.31 89	96.12 117	85.31 155	85.92 187	94.34 146	70.19 230	98.06 146	85.65 146	88.86 211	94.08 229
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		89.10 135	88.64 130	90.48 190	95.53 123	74.97 294	96.08 55	84.89 355	88.13 91	90.16 114	96.65 58	63.29 292	98.10 134	86.14 138	96.90 85	98.39 37

EI-MVSNet		89.10 135	88.86 126	89.80 223	91.84 252	78.30 245	93.70 197	95.01 190	85.73 143	87.15 161	95.28 110	79.87 107	97.21 217	83.81 170	87.36 236	93.88 237

ECVR-MVS		89.09 137	88.53 134	90.77 179	95.62 120	75.89 287	96.16 49	84.22 357	87.89 98	90.20 112	96.65 58	63.19 294	98.10 134	85.90 143	96.94 83	98.33 41

RRT_MVS		89.09 137	88.62 133	90.49 188	92.85 228	79.65 214	96.41 37	94.41 220	88.22 86	85.50 200	94.77 132	69.36 240	97.31 205	89.33 100	86.73 243	94.51 205

CNLPA		89.07 139	87.98 151	92.34 109	96.87 74	84.78 70	94.08 173	93.24 253	81.41 240	84.46 230	95.13 118	75.57 159	96.62 246	77.21 262	93.84 140	95.61 164

PLC	84.53 7	89.06 140	88.03 150	92.15 116	97.27 68	82.69 132	94.29 159	95.44 169	79.71 262	84.01 245	94.18 155	76.68 144	98.75 87	77.28 261	93.41 150	95.02 179
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_djsdf		89.03 141	88.64 130	90.21 201	90.74 298	79.28 226	95.96 62	95.90 133	84.66 170	85.33 215	92.94 201	74.02 181	97.30 206	89.64 97	88.53 215	94.05 231

HY-MVS	83.01 12	89.03 141	87.94 153	92.29 113	94.86 150	82.77 125	92.08 256	94.49 216	81.52 239	86.93 166	92.79 208	78.32 129	98.23 125	79.93 234	90.55 182	95.88 152

ACMP	84.23 8	89.01 143	88.35 140	90.99 173	94.73 155	81.27 165	95.07 109	95.89 135	86.48 126	83.67 252	94.30 149	69.33 241	97.99 151	87.10 132	88.55 214	93.72 252
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
sss		88.93 144	88.26 146	90.94 176	94.05 185	80.78 181	91.71 262	95.38 173	81.55 238	88.63 134	93.91 170	75.04 164	95.47 305	82.47 189	91.61 172	96.57 127

iter_conf05		88.85 145	88.08 149	91.17 161	94.27 179	81.64 154	95.18 101	92.15 280	86.23 133	87.28 160	94.07 156	63.89 290	97.55 179	90.63 88	89.00 209	94.32 217

TranMVSNet+NR-MVSNet		88.84 146	87.95 152	91.49 147	92.68 232	83.01 119	94.92 118	96.31 101	89.88 37	85.53 197	93.85 173	76.63 145	96.96 231	81.91 201	79.87 318	94.50 208

CHOSEN 1792x2688		88.84 146	87.69 156	92.30 112	96.14 96	81.42 163	90.01 295	95.86 137	74.52 321	87.41 156	93.94 166	75.46 160	98.36 114	80.36 228	95.53 105	97.12 107

MVSTER		88.84 146	88.29 144	90.51 187	92.95 225	80.44 189	93.73 194	95.01 190	84.66 170	87.15 161	93.12 196	72.79 199	97.21 217	87.86 116	87.36 236	93.87 238

test_cas_vis1_n_1920		88.83 149	88.85 127	88.78 248	91.15 279	76.72 276	93.85 190	94.93 197	83.23 200	92.81 61	96.00 84	61.17 309	94.45 315	91.67 71	94.84 119	95.17 175

OpenMVS	83.78 11	88.74 150	87.29 166	93.08 73	92.70 231	85.39 64	96.57 35	96.43 95	78.74 277	80.85 288	96.07 82	69.64 236	99.01 61	78.01 255	96.65 92	94.83 190

thisisatest0530		88.67 151	87.61 158	91.86 131	94.87 149	80.07 199	94.63 136	89.90 334	84.00 178	88.46 137	93.78 175	66.88 266	98.46 106	83.30 175	92.65 163	97.06 108

Effi-MVS+-dtu		88.65 152	88.35 140	89.54 231	93.33 211	76.39 282	94.47 146	94.36 222	87.70 103	85.43 207	89.56 298	73.45 190	97.26 212	85.57 148	91.28 174	94.97 180

tttt0517		88.61 153	87.78 155	91.11 165	94.96 143	77.81 258	95.35 87	89.69 337	85.09 161	88.05 144	94.59 141	66.93 264	98.48 103	83.27 176	92.13 170	97.03 111

BH-untuned		88.60 154	88.13 148	90.01 214	95.24 131	78.50 239	93.29 213	94.15 230	84.75 168	84.46 230	93.40 183	75.76 154	97.40 199	77.59 258	94.52 129	94.12 225

NR-MVSNet		88.58 155	87.47 162	91.93 126	93.04 220	84.16 87	94.77 128	96.25 107	89.05 60	80.04 302	93.29 189	79.02 118	97.05 227	81.71 208	80.05 315	94.59 198

1112_ss		88.42 156	87.33 165	91.72 138	94.92 146	80.98 174	92.97 228	94.54 215	78.16 288	83.82 248	93.88 171	78.78 121	97.91 157	79.45 239	89.41 199	96.26 136

WR-MVS		88.38 157	87.67 157	90.52 186	93.30 212	80.18 194	93.26 215	95.96 128	88.57 75	85.47 203	92.81 206	76.12 147	96.91 235	81.24 213	82.29 281	94.47 213

BH-RMVSNet		88.37 158	87.48 161	91.02 170	95.28 128	79.45 218	92.89 230	93.07 257	85.45 152	86.91 168	94.84 130	70.35 227	97.76 162	73.97 292	94.59 126	95.85 153

IterMVS-LS		88.36 159	87.91 154	89.70 227	93.80 198	78.29 246	93.73 194	95.08 189	85.73 143	84.75 222	91.90 239	79.88 106	96.92 234	83.83 169	82.51 278	93.89 235
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
X-MVStestdata		88.31 160	86.13 206	94.85 23	98.54 13	86.60 31	96.93 22	97.19 34	90.66 22	92.85 58	23.41 376	85.02 55	99.49 24	91.99 62	98.56 46	98.47 31

LCM-MVSNet-Re		88.30 161	88.32 143	88.27 262	94.71 157	72.41 323	93.15 219	90.98 314	87.77 101	79.25 310	91.96 237	78.35 128	95.75 293	83.04 178	95.62 104	96.65 124

jajsoiax		88.24 162	87.50 160	90.48 190	90.89 292	80.14 196	95.31 89	95.65 153	84.97 163	84.24 241	94.02 161	65.31 281	97.42 192	88.56 108	88.52 216	93.89 235

VPNet		88.20 163	87.47 162	90.39 195	93.56 206	79.46 217	94.04 177	95.54 160	88.67 71	86.96 165	94.58 142	69.33 241	97.15 219	84.05 166	80.53 310	94.56 201

TAPA-MVS	84.62 6	88.16 164	87.01 174	91.62 141	96.64 80	80.65 183	94.39 153	96.21 113	76.38 301	86.19 184	95.44 105	79.75 108	98.08 144	62.75 349	95.29 113	96.13 140
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline1		88.10 165	87.28 167	90.57 182	94.96 143	80.07 199	94.27 160	91.29 307	86.74 122	87.41 156	94.00 163	76.77 142	96.20 273	80.77 221	79.31 323	95.44 166

Anonymous20240529		88.09 166	86.59 190	92.58 98	96.53 86	81.92 149	95.99 60	95.84 138	74.11 325	89.06 129	95.21 115	61.44 304	98.81 84	83.67 173	87.47 233	97.01 112

HyFIR lowres test		88.09 166	86.81 178	91.93 126	96.00 105	80.63 184	90.01 295	95.79 141	73.42 331	87.68 152	92.10 231	73.86 184	97.96 153	80.75 222	91.70 171	97.19 102

mvs_tets		88.06 168	87.28 167	90.38 197	90.94 288	79.88 208	95.22 98	95.66 151	85.10 160	84.21 242	93.94 166	63.53 291	97.40 199	88.50 109	88.40 220	93.87 238

F-COLMAP		87.95 169	86.80 179	91.40 151	96.35 92	80.88 178	94.73 130	95.45 167	79.65 263	82.04 276	94.61 139	71.13 213	98.50 102	76.24 273	91.05 179	94.80 192

LS3D		87.89 170	86.32 200	92.59 97	96.07 102	82.92 123	95.23 97	94.92 198	75.66 308	82.89 266	95.98 86	72.48 203	99.21 43	68.43 323	95.23 116	95.64 163

anonymousdsp		87.84 171	87.09 170	90.12 207	89.13 325	80.54 187	94.67 134	95.55 158	82.05 221	83.82 248	92.12 228	71.47 211	97.15 219	87.15 128	87.80 232	92.67 289

v2v482		87.84 171	87.06 171	90.17 203	90.99 284	79.23 229	94.00 182	95.13 184	84.87 164	85.53 197	92.07 234	74.45 172	97.45 188	84.71 158	81.75 289	93.85 241

WR-MVS_H		87.80 173	87.37 164	89.10 242	93.23 213	78.12 249	95.61 81	97.30 28	87.90 96	83.72 250	92.01 236	79.65 114	96.01 281	76.36 270	80.54 309	93.16 274

AUN-MVS		87.78 174	86.54 192	91.48 148	94.82 153	81.05 172	93.91 189	93.93 237	83.00 204	86.93 166	93.53 181	69.50 238	97.67 167	86.14 138	77.12 333	95.73 161

PCF-MVS	84.11 10	87.74 175	86.08 210	92.70 92	94.02 186	84.43 83	89.27 305	95.87 136	73.62 330	84.43 232	94.33 147	78.48 127	98.86 79	70.27 309	94.45 131	94.81 191
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Anonymous202405211		87.68 176	86.13 206	92.31 111	96.66 79	80.74 182	94.87 121	91.49 302	80.47 253	89.46 123	95.44 105	54.72 337	98.23 125	82.19 195	89.89 192	97.97 70

V42		87.68 176	86.86 176	90.15 205	90.58 304	80.14 196	94.24 163	95.28 178	83.66 186	85.67 191	91.33 254	74.73 169	97.41 197	84.43 162	81.83 287	92.89 284

thres600view7		87.65 178	86.67 185	90.59 181	96.08 101	78.72 232	94.88 120	91.58 298	87.06 114	88.08 142	92.30 221	68.91 249	98.10 134	70.05 316	91.10 175	94.96 183

XXY-MVS		87.65 178	86.85 177	90.03 211	92.14 242	80.60 186	93.76 193	95.23 180	82.94 206	84.60 225	94.02 161	74.27 174	95.49 304	81.04 215	83.68 265	94.01 233

Test_1112_low_res		87.65 178	86.51 193	91.08 166	94.94 145	79.28 226	91.77 260	94.30 224	76.04 306	83.51 257	92.37 218	77.86 134	97.73 166	78.69 247	89.13 206	96.22 137

thres100view900		87.63 181	86.71 183	90.38 197	96.12 97	78.55 236	95.03 112	91.58 298	87.15 111	88.06 143	92.29 222	68.91 249	98.10 134	70.13 313	91.10 175	94.48 211

CP-MVSNet		87.63 181	87.26 169	88.74 252	93.12 216	76.59 279	95.29 93	96.58 89	88.43 78	83.49 258	92.98 200	75.28 161	95.83 289	78.97 245	81.15 297	93.79 243

thres400		87.62 183	86.64 186	90.57 182	95.99 106	78.64 234	94.58 138	91.98 288	86.94 118	88.09 140	91.77 241	69.18 246	98.10 134	70.13 313	91.10 175	94.96 183

v1144		87.61 184	86.79 180	90.06 210	91.01 283	79.34 222	93.95 184	95.42 172	83.36 196	85.66 192	91.31 257	74.98 165	97.42 192	83.37 174	82.06 283	93.42 264

bld_raw_dy_0_64		87.60 185	86.73 181	90.21 201	91.72 256	80.26 193	95.09 108	88.61 342	85.68 145	85.55 194	94.38 145	63.93 289	96.66 243	87.73 118	87.84 231	93.72 252

tfpn200view9		87.58 186	86.64 186	90.41 194	95.99 106	78.64 234	94.58 138	91.98 288	86.94 118	88.09 140	91.77 241	69.18 246	98.10 134	70.13 313	91.10 175	94.48 211

BH-w/o		87.57 187	87.05 172	89.12 241	94.90 148	77.90 254	92.41 241	93.51 250	82.89 208	83.70 251	91.34 253	75.75 155	97.07 225	75.49 278	93.49 147	92.39 298

UniMVSNet_ETH3D		87.53 188	86.37 197	91.00 172	92.44 235	78.96 231	94.74 129	95.61 155	84.07 177	85.36 214	94.52 143	59.78 318	97.34 204	82.93 180	87.88 229	96.71 123

ET-MVSNet_ETH3D		87.51 189	85.91 218	92.32 110	93.70 203	83.93 91	92.33 246	90.94 315	84.16 174	72.09 348	92.52 214	69.90 231	95.85 288	89.20 102	88.36 221	97.17 103

1314		87.51 189	86.57 191	90.34 199	92.42 236	79.74 212	92.63 236	95.35 177	78.35 283	80.14 299	91.62 248	74.05 180	97.15 219	81.05 214	93.53 145	94.12 225

v8		87.50 191	86.71 183	89.89 217	91.37 269	79.40 219	94.50 142	95.38 173	84.81 167	83.60 255	91.33 254	76.05 148	97.42 192	82.84 183	80.51 312	92.84 286

Fast-Effi-MVS+-dtu		87.44 192	86.72 182	89.63 229	92.04 246	77.68 263	94.03 178	93.94 236	85.81 140	82.42 270	91.32 256	70.33 228	97.06 226	80.33 230	90.23 186	94.14 224

MVS		87.44 192	86.10 209	91.44 150	92.61 233	83.62 100	92.63 236	95.66 151	67.26 353	81.47 280	92.15 226	77.95 131	98.22 127	79.71 236	95.48 107	92.47 295

FE-MVS		87.40 194	86.02 212	91.57 144	94.56 166	79.69 213	90.27 285	93.72 247	80.57 252	88.80 132	91.62 248	65.32 280	98.59 98	74.97 286	94.33 134	96.44 130

FMVSNet3		87.40 194	86.11 208	91.30 156	93.79 200	83.64 99	94.20 165	94.81 207	83.89 181	84.37 233	91.87 240	68.45 255	96.56 254	78.23 252	85.36 250	93.70 254

test_fmvs1		87.34 196	87.56 159	86.68 302	90.59 303	71.80 327	94.01 180	94.04 235	78.30 284	91.97 82	95.22 113	56.28 330	93.71 329	92.89 37	94.71 121	94.52 203

thisisatest0515		87.33 197	85.99 213	91.37 153	93.49 207	79.55 215	90.63 281	89.56 340	80.17 255	87.56 154	90.86 270	67.07 263	98.28 123	81.50 210	93.02 158	96.29 134

PS-CasMVS		87.32 198	86.88 175	88.63 255	92.99 223	76.33 284	95.33 88	96.61 87	88.22 86	83.30 263	93.07 198	73.03 197	95.79 292	78.36 249	81.00 303	93.75 250

GBi-Net		87.26 199	85.98 214	91.08 166	94.01 187	83.10 113	95.14 105	94.94 193	83.57 188	84.37 233	91.64 244	66.59 271	96.34 269	78.23 252	85.36 250	93.79 243

test1		87.26 199	85.98 214	91.08 166	94.01 187	83.10 113	95.14 105	94.94 193	83.57 188	84.37 233	91.64 244	66.59 271	96.34 269	78.23 252	85.36 250	93.79 243

v1192		87.25 201	86.33 199	90.00 215	90.76 297	79.04 230	93.80 191	95.48 163	82.57 212	85.48 202	91.18 261	73.38 193	97.42 192	82.30 193	82.06 283	93.53 258

v10		87.25 201	86.38 196	89.85 218	91.19 275	79.50 216	94.48 143	95.45 167	83.79 184	83.62 254	91.19 259	75.13 162	97.42 192	81.94 200	80.60 307	92.63 291

DP-MVS		87.25 201	85.36 233	92.90 82	97.65 55	83.24 109	94.81 125	92.00 286	74.99 316	81.92 278	95.00 121	72.66 200	99.05 53	66.92 334	92.33 168	96.40 131

miper_ehance_all_eth		87.22 204	86.62 189	89.02 245	92.13 243	77.40 268	90.91 277	94.81 207	81.28 243	84.32 238	90.08 287	79.26 116	96.62 246	83.81 170	82.94 273	93.04 279

test2506		87.21 205	86.28 202	90.02 213	95.62 120	73.64 306	96.25 46	71.38 376	87.89 98	90.45 108	96.65 58	55.29 335	98.09 142	86.03 142	96.94 83	98.33 41

thres200		87.21 205	86.24 204	90.12 207	95.36 126	78.53 237	93.26 215	92.10 282	86.42 128	88.00 145	91.11 265	69.24 245	98.00 150	69.58 317	91.04 180	93.83 242

v144192		87.19 207	86.35 198	89.74 224	90.64 301	78.24 247	93.92 187	95.43 170	81.93 226	85.51 199	91.05 267	74.21 177	97.45 188	82.86 182	81.56 291	93.53 258

FMVSNet2		87.19 207	85.82 220	91.30 156	94.01 187	83.67 98	94.79 126	94.94 193	83.57 188	83.88 247	92.05 235	66.59 271	96.51 257	77.56 259	85.01 253	93.73 251

c3_l		87.14 209	86.50 194	89.04 244	92.20 240	77.26 269	91.22 273	94.70 212	82.01 224	84.34 237	90.43 280	78.81 120	96.61 249	83.70 172	81.09 298	93.25 269

Baseline_NR-MVSNet		87.07 210	86.63 188	88.40 258	91.44 264	77.87 256	94.23 164	92.57 269	84.12 176	85.74 190	92.08 232	77.25 137	96.04 278	82.29 194	79.94 316	91.30 318

v148		87.04 211	86.32 200	89.21 238	90.94 288	77.26 269	93.71 196	94.43 218	84.84 166	84.36 236	90.80 273	76.04 149	97.05 227	82.12 196	79.60 320	93.31 266

test_fmvs1_n		87.03 212	87.04 173	86.97 294	89.74 321	71.86 325	94.55 140	94.43 218	78.47 280	91.95 84	95.50 104	51.16 347	93.81 327	93.02 36	94.56 127	95.26 172

v1921920		86.97 213	86.06 211	89.69 228	90.53 307	78.11 250	93.80 191	95.43 170	81.90 228	85.33 215	91.05 267	72.66 200	97.41 197	82.05 198	81.80 288	93.53 258

tt0805		86.92 214	85.74 226	90.48 190	92.22 239	79.98 206	95.63 80	94.88 201	83.83 183	84.74 223	92.80 207	57.61 326	97.67 167	85.48 149	84.42 257	93.79 243

miper_enhance_ethall		86.90 215	86.18 205	89.06 243	91.66 261	77.58 265	90.22 291	94.82 206	79.16 269	84.48 229	89.10 301	79.19 117	96.66 243	84.06 165	82.94 273	92.94 282

v7n		86.81 216	85.76 224	89.95 216	90.72 299	79.25 228	95.07 109	95.92 130	84.45 173	82.29 271	90.86 270	72.60 202	97.53 182	79.42 242	80.52 311	93.08 278

PEN-MVS		86.80 217	86.27 203	88.40 258	92.32 238	75.71 290	95.18 101	96.38 98	87.97 93	82.82 267	93.15 194	73.39 192	95.92 284	76.15 274	79.03 325	93.59 256

cl22		86.78 218	85.98 214	89.18 240	92.34 237	77.62 264	90.84 278	94.13 232	81.33 242	83.97 246	90.15 285	73.96 182	96.60 251	84.19 164	82.94 273	93.33 265

v1240		86.78 218	85.85 219	89.56 230	90.45 308	77.79 259	93.61 199	95.37 175	81.65 234	85.43 207	91.15 263	71.50 210	97.43 191	81.47 211	82.05 285	93.47 262

TR-MVS		86.78 218	85.76 224	89.82 220	94.37 175	78.41 241	92.47 240	92.83 262	81.11 248	86.36 180	92.40 217	68.73 252	97.48 185	73.75 295	89.85 194	93.57 257

PatchMatch-RL		86.77 221	85.54 227	90.47 193	95.88 109	82.71 131	90.54 282	92.31 275	79.82 261	84.32 238	91.57 252	68.77 251	96.39 265	73.16 297	93.48 149	92.32 301

PAPM		86.68 222	85.39 231	90.53 184	93.05 219	79.33 225	89.79 298	94.77 210	78.82 274	81.95 277	93.24 191	76.81 140	97.30 206	66.94 332	93.16 156	94.95 186

pm-mvs1		86.61 223	85.54 227	89.82 220	91.44 264	80.18 194	95.28 95	94.85 203	83.84 182	81.66 279	92.62 211	72.45 205	96.48 259	79.67 237	78.06 326	92.82 287

GA-MVS		86.61 223	85.27 235	90.66 180	91.33 272	78.71 233	90.40 284	93.81 244	85.34 154	85.12 217	89.57 297	61.25 306	97.11 223	80.99 218	89.59 198	96.15 138

Anonymous20231211		86.59 225	85.13 237	90.98 175	96.52 87	81.50 157	96.14 52	96.16 114	73.78 328	83.65 253	92.15 226	63.26 293	97.37 203	82.82 184	81.74 290	94.06 230

test_vis1_n		86.56 226	86.49 195	86.78 301	88.51 330	72.69 315	94.68 133	93.78 245	79.55 264	90.70 105	95.31 109	48.75 352	93.28 335	93.15 33	93.99 136	94.38 215

DIV-MVS_self_test		86.53 227	85.78 221	88.75 250	92.02 248	76.45 281	90.74 279	94.30 224	81.83 232	83.34 261	90.82 272	75.75 155	96.57 252	81.73 207	81.52 293	93.24 270

cl____		86.52 228	85.78 221	88.75 250	92.03 247	76.46 280	90.74 279	94.30 224	81.83 232	83.34 261	90.78 274	75.74 157	96.57 252	81.74 206	81.54 292	93.22 271

eth_miper_zixun_eth		86.50 229	85.77 223	88.68 253	91.94 249	75.81 289	90.47 283	94.89 199	82.05 221	84.05 243	90.46 279	75.96 150	96.77 239	82.76 186	79.36 322	93.46 263

baseline2		86.50 229	85.39 231	89.84 219	91.12 280	76.70 277	91.88 257	88.58 343	82.35 217	79.95 303	90.95 269	73.42 191	97.63 174	80.27 231	89.95 191	95.19 174

EPNet_dtu		86.49 231	85.94 217	88.14 267	90.24 311	72.82 313	94.11 169	92.20 278	86.66 125	79.42 309	92.36 219	73.52 188	95.81 291	71.26 303	93.66 141	95.80 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
cascas		86.43 232	84.98 240	90.80 178	92.10 245	80.92 177	90.24 289	95.91 132	73.10 334	83.57 256	88.39 312	65.15 282	97.46 187	84.90 155	91.43 173	94.03 232

SCA		86.32 233	85.18 236	89.73 226	92.15 241	76.60 278	91.12 274	91.69 295	83.53 191	85.50 200	88.81 305	66.79 267	96.48 259	76.65 267	90.35 185	96.12 141

LTVRE_ROB	82.13 13	86.26 234	84.90 243	90.34 199	94.44 173	81.50 157	92.31 248	94.89 199	83.03 203	79.63 307	92.67 209	69.69 235	97.79 160	71.20 304	86.26 246	91.72 310
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
DTE-MVSNet		86.11 235	85.48 229	87.98 271	91.65 262	74.92 295	94.93 117	95.75 144	87.36 109	82.26 272	93.04 199	72.85 198	95.82 290	74.04 291	77.46 331	93.20 272

XVG-ACMP-BASELINE		86.00 236	84.84 245	89.45 235	91.20 274	78.00 251	91.70 263	95.55 158	85.05 162	82.97 265	92.25 224	54.49 338	97.48 185	82.93 180	87.45 235	92.89 284

MVP-Stereo		85.97 237	84.86 244	89.32 236	90.92 290	82.19 143	92.11 254	94.19 228	78.76 276	78.77 313	91.63 247	68.38 256	96.56 254	75.01 285	93.95 137	89.20 343
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
D2MVS		85.90 238	85.09 238	88.35 260	90.79 295	77.42 267	91.83 259	95.70 147	80.77 251	80.08 301	90.02 288	66.74 269	96.37 266	81.88 202	87.97 228	91.26 319

test-LLR		85.87 239	85.41 230	87.25 287	90.95 286	71.67 329	89.55 299	89.88 335	83.41 194	84.54 227	87.95 319	67.25 259	95.11 310	81.82 203	93.37 152	94.97 180

FMVSNet1		85.85 240	84.11 254	91.08 166	92.81 229	83.10 113	95.14 105	94.94 193	81.64 235	82.68 268	91.64 244	59.01 322	96.34 269	75.37 280	83.78 262	93.79 243

PatchmatchNet		85.85 240	84.70 247	89.29 237	91.76 255	75.54 291	88.49 317	91.30 306	81.63 236	85.05 218	88.70 309	71.71 207	96.24 272	74.61 289	89.05 207	96.08 144
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CostFormer		85.77 242	84.94 242	88.26 263	91.16 278	72.58 321	89.47 303	91.04 313	76.26 304	86.45 178	89.97 290	70.74 220	96.86 238	82.35 192	87.07 241	95.34 171

PMMVS		85.71 243	84.96 241	87.95 272	88.90 328	77.09 271	88.68 315	90.06 329	72.32 340	86.47 175	90.76 275	72.15 206	94.40 317	81.78 205	93.49 147	92.36 299

PVSNet	78.82 18	85.55 244	84.65 248	88.23 265	94.72 156	71.93 324	87.12 332	92.75 265	78.80 275	84.95 220	90.53 278	64.43 286	96.71 242	74.74 287	93.86 139	96.06 146

IterMVS-SCA-FT		85.45 245	84.53 251	88.18 266	91.71 258	76.87 274	90.19 292	92.65 268	85.40 153	81.44 281	90.54 277	66.79 267	95.00 313	81.04 215	81.05 299	92.66 290

pmmvs4		85.43 246	83.86 259	90.16 204	90.02 316	82.97 121	90.27 285	92.67 267	75.93 307	80.73 289	91.74 243	71.05 214	95.73 295	78.85 246	83.46 269	91.78 309

mvsany_test1		85.42 247	85.30 234	85.77 312	87.95 341	75.41 293	87.61 329	80.97 365	76.82 298	88.68 133	95.83 92	77.44 136	90.82 353	85.90 143	86.51 244	91.08 327

ACMH	80.38 17	85.36 248	83.68 261	90.39 195	94.45 172	80.63 184	94.73 130	94.85 203	82.09 220	77.24 321	92.65 210	60.01 316	97.58 176	72.25 301	84.87 254	92.96 281
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		85.35 249	84.64 249	87.49 281	90.77 296	72.59 320	94.01 180	94.40 221	84.72 169	79.62 308	93.17 193	61.91 300	96.72 240	81.99 199	81.16 295	93.16 274

CR-MVSNet		85.35 249	83.76 260	90.12 207	90.58 304	79.34 222	85.24 344	91.96 290	78.27 285	85.55 194	87.87 322	71.03 215	95.61 296	73.96 293	89.36 201	95.40 168

tpmrst		85.35 249	84.99 239	86.43 304	90.88 293	67.88 350	88.71 314	91.43 304	80.13 256	86.08 186	88.80 307	73.05 195	96.02 280	82.48 188	83.40 271	95.40 168

miper_lstm_enhance		85.27 252	84.59 250	87.31 284	91.28 273	74.63 296	87.69 326	94.09 234	81.20 247	81.36 283	89.85 293	74.97 166	94.30 320	81.03 217	79.84 319	93.01 280

IB-MVS	80.51 15	85.24 253	83.26 265	91.19 159	92.13 243	79.86 209	91.75 261	91.29 307	83.28 198	80.66 291	88.49 311	61.28 305	98.46 106	80.99 218	79.46 321	95.25 173
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
CHOSEN 280x420		85.15 254	83.99 257	88.65 254	92.47 234	78.40 242	79.68 364	92.76 264	74.90 318	81.41 282	89.59 296	69.85 234	95.51 301	79.92 235	95.29 113	92.03 305

RPSCF		85.07 255	84.27 252	87.48 282	92.91 226	70.62 339	91.69 264	92.46 270	76.20 305	82.67 269	95.22 113	63.94 288	97.29 209	77.51 260	85.80 248	94.53 202

MS-PatchMatch		85.05 256	84.16 253	87.73 275	91.42 267	78.51 238	91.25 272	93.53 249	77.50 291	80.15 298	91.58 250	61.99 299	95.51 301	75.69 277	94.35 133	89.16 344

ACMH+	81.04 14	85.05 256	83.46 264	89.82 220	94.66 160	79.37 220	94.44 148	94.12 233	82.19 219	78.04 316	92.82 205	58.23 324	97.54 181	73.77 294	82.90 276	92.54 292

IterMVS		84.88 258	83.98 258	87.60 277	91.44 264	76.03 286	90.18 293	92.41 271	83.24 199	81.06 287	90.42 281	66.60 270	94.28 321	79.46 238	80.98 304	92.48 294
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		84.86 259	83.09 267	90.14 206	93.80 198	80.05 201	89.18 308	93.09 256	78.89 272	78.19 314	91.91 238	65.86 279	97.27 210	68.47 322	88.45 218	93.11 276

tpm		84.73 260	84.02 256	86.87 299	90.33 309	68.90 346	89.06 310	89.94 332	80.85 250	85.75 189	89.86 292	68.54 254	95.97 282	77.76 256	84.05 261	95.75 158

tfpnnormal		84.72 261	83.23 266	89.20 239	92.79 230	80.05 201	94.48 143	95.81 139	82.38 215	81.08 286	91.21 258	69.01 248	96.95 232	61.69 351	80.59 308	90.58 333

CVMVSNet		84.69 262	84.79 246	84.37 323	91.84 252	64.92 359	93.70 197	91.47 303	66.19 355	86.16 185	95.28 110	67.18 261	93.33 334	80.89 220	90.42 184	94.88 188

test-mter		84.54 263	83.64 262	87.25 287	90.95 286	71.67 329	89.55 299	89.88 335	79.17 268	84.54 227	87.95 319	55.56 332	95.11 310	81.82 203	93.37 152	94.97 180

TransMVSNet (Re)		84.43 264	83.06 268	88.54 256	91.72 256	78.44 240	95.18 101	92.82 263	82.73 210	79.67 306	92.12 228	73.49 189	95.96 283	71.10 308	68.73 355	91.21 321

pmmvs5		84.21 265	82.84 272	88.34 261	88.95 327	76.94 273	92.41 241	91.91 292	75.63 309	80.28 296	91.18 261	64.59 285	95.57 297	77.09 265	83.47 268	92.53 293

tpm2		84.08 266	82.94 269	87.48 282	91.39 268	71.27 331	89.23 307	90.37 323	71.95 342	84.64 224	89.33 299	67.30 258	96.55 256	75.17 282	87.09 240	94.63 195

test_fmvs2		83.98 267	84.03 255	83.83 328	87.16 343	67.53 353	93.93 186	92.89 260	77.62 290	86.89 171	93.53 181	47.18 357	92.02 346	90.54 90	86.51 244	91.93 307

COLMAP_ROB	80.39 16	83.96 268	82.04 275	89.74 224	95.28 128	79.75 211	94.25 161	92.28 276	75.17 314	78.02 317	93.77 176	58.60 323	97.84 159	65.06 342	85.92 247	91.63 312
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPMNet		83.95 269	81.53 279	91.21 158	90.58 304	79.34 222	85.24 344	96.76 73	71.44 344	85.55 194	82.97 352	70.87 218	98.91 75	61.01 353	89.36 201	95.40 168

SixPastTwentyTwo		83.91 270	82.90 270	86.92 296	90.99 284	70.67 338	93.48 203	91.99 287	85.54 150	77.62 320	92.11 230	60.59 312	96.87 237	76.05 275	77.75 328	93.20 272

EPMVS		83.90 271	82.70 273	87.51 279	90.23 312	72.67 316	88.62 316	81.96 363	81.37 241	85.01 219	88.34 313	66.31 274	94.45 315	75.30 281	87.12 239	95.43 167

TESTMET0.1,1		83.74 272	82.85 271	86.42 305	89.96 317	71.21 333	89.55 299	87.88 345	77.41 292	83.37 260	87.31 327	56.71 328	93.65 331	80.62 225	92.85 162	94.40 214

MVS_0304		83.46 273	81.92 276	88.10 268	90.63 302	77.49 266	93.26 215	93.75 246	80.04 258	80.44 295	87.24 329	47.94 354	95.55 298	75.79 276	88.16 223	91.26 319

pmmvs6		83.42 274	81.60 278	88.87 247	88.01 339	77.87 256	94.96 115	94.24 227	74.67 320	78.80 312	91.09 266	60.17 315	96.49 258	77.06 266	75.40 339	92.23 303

AllTest		83.42 274	81.39 280	89.52 232	95.01 139	77.79 259	93.12 220	90.89 317	77.41 292	76.12 329	93.34 184	54.08 340	97.51 183	68.31 324	84.27 259	93.26 267

tpmvs		83.35 276	82.07 274	87.20 291	91.07 282	71.00 336	88.31 320	91.70 294	78.91 271	80.49 294	87.18 330	69.30 244	97.08 224	68.12 327	83.56 267	93.51 261

USDC		82.76 277	81.26 282	87.26 286	91.17 276	74.55 297	89.27 305	93.39 252	78.26 286	75.30 334	92.08 232	54.43 339	96.63 245	71.64 302	85.79 249	90.61 330

Patchmtry		82.71 278	80.93 284	88.06 269	90.05 315	76.37 283	84.74 349	91.96 290	72.28 341	81.32 284	87.87 322	71.03 215	95.50 303	68.97 319	80.15 314	92.32 301

PatchT		82.68 279	81.27 281	86.89 298	90.09 314	70.94 337	84.06 351	90.15 326	74.91 317	85.63 193	83.57 348	69.37 239	94.87 314	65.19 339	88.50 217	94.84 189

MIMVSNet		82.59 280	80.53 285	88.76 249	91.51 263	78.32 244	86.57 335	90.13 327	79.32 265	80.70 290	88.69 310	52.98 344	93.07 339	66.03 337	88.86 211	94.90 187

test0.0.03 1		82.41 281	81.69 277	84.59 321	88.23 336	72.89 312	90.24 289	87.83 346	83.41 194	79.86 304	89.78 294	67.25 259	88.99 361	65.18 340	83.42 270	91.90 308

EG-PatchMatch MVS		82.37 282	80.34 288	88.46 257	90.27 310	79.35 221	92.80 233	94.33 223	77.14 296	73.26 345	90.18 284	47.47 356	96.72 240	70.25 310	87.32 238	89.30 341

tpm cat1		81.96 283	80.27 289	87.01 293	91.09 281	71.02 335	87.38 330	91.53 301	66.25 354	80.17 297	86.35 336	68.22 257	96.15 276	69.16 318	82.29 281	93.86 240

our_test_3		81.93 284	80.46 287	86.33 306	88.46 333	73.48 308	88.46 318	91.11 309	76.46 299	76.69 325	88.25 315	66.89 265	94.36 318	68.75 320	79.08 324	91.14 323

ppachtmachnet_test		81.84 285	80.07 293	87.15 292	88.46 333	74.43 300	89.04 311	92.16 279	75.33 312	77.75 318	88.99 302	66.20 275	95.37 306	65.12 341	77.60 329	91.65 311

gg-mvs-nofinetune		81.77 286	79.37 299	88.99 246	90.85 294	77.73 262	86.29 336	79.63 368	74.88 319	83.19 264	69.05 366	60.34 313	96.11 277	75.46 279	94.64 125	93.11 276

CL-MVSNet_self_test		81.74 287	80.53 285	85.36 315	85.96 349	72.45 322	90.25 287	93.07 257	81.24 245	79.85 305	87.29 328	70.93 217	92.52 342	66.95 331	69.23 351	91.11 325

Patchmatch-RL test		81.67 288	79.96 294	86.81 300	85.42 354	71.23 332	82.17 358	87.50 349	78.47 280	77.19 322	82.50 353	70.81 219	93.48 332	82.66 187	72.89 343	95.71 162

ADS-MVSNet2		81.66 289	79.71 297	87.50 280	91.35 270	74.19 302	83.33 354	88.48 344	72.90 336	82.24 273	85.77 340	64.98 283	93.20 337	64.57 343	83.74 263	95.12 176

K. test v3		81.59 290	80.15 292	85.91 311	89.89 319	69.42 345	92.57 238	87.71 347	85.56 149	73.44 344	89.71 295	55.58 331	95.52 300	77.17 263	69.76 349	92.78 288

ADS-MVSNet		81.56 291	79.78 295	86.90 297	91.35 270	71.82 326	83.33 354	89.16 341	72.90 336	82.24 273	85.77 340	64.98 283	93.76 328	64.57 343	83.74 263	95.12 176

FMVSNet5		81.52 292	79.60 298	87.27 285	91.17 276	77.95 252	91.49 267	92.26 277	76.87 297	76.16 328	87.91 321	51.67 345	92.34 343	67.74 328	81.16 295	91.52 313

dp		81.47 293	80.23 290	85.17 318	89.92 318	65.49 357	86.74 333	90.10 328	76.30 303	81.10 285	87.12 331	62.81 295	95.92 284	68.13 326	79.88 317	94.09 228

Patchmatch-test		81.37 294	79.30 300	87.58 278	90.92 290	74.16 303	80.99 360	87.68 348	70.52 348	76.63 326	88.81 305	71.21 212	92.76 341	60.01 357	86.93 242	95.83 155

EU-MVSNet		81.32 295	80.95 283	82.42 334	88.50 332	63.67 360	93.32 208	91.33 305	64.02 358	80.57 293	92.83 204	61.21 308	92.27 344	76.34 271	80.38 313	91.32 317

test_0402		81.30 296	79.17 304	87.67 276	93.19 214	78.17 248	92.98 227	91.71 293	75.25 313	76.02 331	90.31 282	59.23 320	96.37 266	50.22 365	83.63 266	88.47 350

JIA-IIPM		81.04 297	78.98 307	87.25 287	88.64 329	73.48 308	81.75 359	89.61 339	73.19 333	82.05 275	73.71 363	66.07 278	95.87 287	71.18 306	84.60 256	92.41 297

Anonymous20231206		81.03 298	79.77 296	84.82 320	87.85 342	70.26 341	91.42 268	92.08 283	73.67 329	77.75 318	89.25 300	62.43 297	93.08 338	61.50 352	82.00 286	91.12 324

pmmvs-eth3d		80.97 299	78.72 308	87.74 274	84.99 356	79.97 207	90.11 294	91.65 296	75.36 311	73.51 343	86.03 337	59.45 319	93.96 326	75.17 282	72.21 344	89.29 342

testgi		80.94 300	80.20 291	83.18 329	87.96 340	66.29 354	91.28 270	90.70 321	83.70 185	78.12 315	92.84 203	51.37 346	90.82 353	63.34 346	82.46 279	92.43 296

CMPMVS	59.16 21	80.52 301	79.20 303	84.48 322	83.98 357	67.63 352	89.95 297	93.84 243	64.79 357	66.81 358	91.14 264	57.93 325	95.17 308	76.25 272	88.10 224	90.65 329
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20240521		80.44 302	79.21 302	84.11 326	85.75 352	67.89 349	92.86 231	93.23 254	75.61 310	75.59 333	87.47 326	50.03 348	94.33 319	71.14 307	81.21 294	90.12 335

LF4IMVS		80.37 303	79.07 306	84.27 325	86.64 345	69.87 344	89.39 304	91.05 312	76.38 301	74.97 336	90.00 289	47.85 355	94.25 322	74.55 290	80.82 306	88.69 348

KD-MVS_self_test		80.20 304	79.24 301	83.07 330	85.64 353	65.29 358	91.01 276	93.93 237	78.71 278	76.32 327	86.40 335	59.20 321	92.93 340	72.59 299	69.35 350	91.00 328

UnsupCasMVSNet_eth		80.07 305	78.27 309	85.46 314	85.24 355	72.63 319	88.45 319	94.87 202	82.99 205	71.64 351	88.07 318	56.34 329	91.75 349	73.48 296	63.36 362	92.01 306

test20.03		79.95 306	79.08 305	82.55 332	85.79 351	67.74 351	91.09 275	91.08 310	81.23 246	74.48 340	89.96 291	61.63 301	90.15 355	60.08 355	76.38 335	89.76 336

TDRefinement		79.81 307	77.34 311	87.22 290	79.24 366	75.48 292	93.12 220	92.03 285	76.45 300	75.01 335	91.58 250	49.19 351	96.44 263	70.22 312	69.18 352	89.75 337

TinyColmap		79.76 308	77.69 310	85.97 308	91.71 258	73.12 310	89.55 299	90.36 324	75.03 315	72.03 349	90.19 283	46.22 358	96.19 275	63.11 347	81.03 300	88.59 349

OpenMVS_ROB	74.94 19	79.51 309	77.03 316	86.93 295	87.00 344	76.23 285	92.33 246	90.74 320	68.93 351	74.52 339	88.23 316	49.58 350	96.62 246	57.64 359	84.29 258	87.94 352

MIMVSNet1		79.38 310	77.28 312	85.69 313	86.35 346	73.67 305	91.61 266	92.75 265	78.11 289	72.64 347	88.12 317	48.16 353	91.97 348	60.32 354	77.49 330	91.43 316

YYNet1		79.22 311	77.20 313	85.28 317	88.20 338	72.66 317	85.87 338	90.05 331	74.33 323	62.70 360	87.61 324	66.09 277	92.03 345	66.94 332	72.97 342	91.15 322

MDA-MVSNet_test_wron		79.21 312	77.19 314	85.29 316	88.22 337	72.77 314	85.87 338	90.06 329	74.34 322	62.62 361	87.56 325	66.14 276	91.99 347	66.90 335	73.01 341	91.10 326

MDA-MVSNet-bldmvs		78.85 313	76.31 318	86.46 303	89.76 320	73.88 304	88.79 313	90.42 322	79.16 269	59.18 362	88.33 314	60.20 314	94.04 323	62.00 350	68.96 353	91.48 315

KD-MVS_2432*1600		78.50 314	76.02 321	85.93 309	86.22 347	74.47 298	84.80 347	92.33 273	79.29 266	76.98 323	85.92 338	53.81 342	93.97 324	67.39 329	57.42 367	89.36 339

miper_refine_blended		78.50 314	76.02 321	85.93 309	86.22 347	74.47 298	84.80 347	92.33 273	79.29 266	76.98 323	85.92 338	53.81 342	93.97 324	67.39 329	57.42 367	89.36 339

PM-MVS		78.11 316	76.12 320	84.09 327	83.54 359	70.08 342	88.97 312	85.27 354	79.93 259	74.73 338	86.43 334	34.70 365	93.48 332	79.43 241	72.06 345	88.72 347

test_vis1_rt		77.96 317	76.46 317	82.48 333	85.89 350	71.74 328	90.25 287	78.89 369	71.03 347	71.30 352	81.35 355	42.49 361	91.05 352	84.55 160	82.37 280	84.65 355

test_fmvs3		77.67 318	77.16 315	79.22 338	79.52 365	61.14 364	92.34 245	91.64 297	73.98 326	78.86 311	86.59 332	27.38 369	87.03 363	88.12 114	75.97 337	89.50 338

PVSNet_0	73.20 20	77.22 319	74.83 324	84.37 323	90.70 300	71.10 334	83.09 356	89.67 338	72.81 338	73.93 342	83.13 350	60.79 311	93.70 330	68.54 321	50.84 370	88.30 351

DSMNet-mixed		76.94 320	76.29 319	78.89 339	83.10 360	56.11 374	87.78 324	79.77 367	60.65 361	75.64 332	88.71 308	61.56 303	88.34 362	60.07 356	89.29 203	92.21 304

new-patchmatchnet		76.41 321	75.17 323	80.13 336	82.65 362	59.61 366	87.66 327	91.08 310	78.23 287	69.85 354	83.22 349	54.76 336	91.63 351	64.14 345	64.89 360	89.16 344

UnsupCasMVSNet_bld		76.23 322	73.27 325	85.09 319	83.79 358	72.92 311	85.65 341	93.47 251	71.52 343	68.84 356	79.08 358	49.77 349	93.21 336	66.81 336	60.52 364	89.13 346

mvsany_test3		74.95 323	73.26 326	80.02 337	74.61 368	63.16 362	85.53 342	78.42 370	74.16 324	74.89 337	86.46 333	36.02 364	89.09 360	82.39 191	66.91 356	87.82 353

MVS-HIRNet		73.70 324	72.20 327	78.18 342	91.81 254	56.42 373	82.94 357	82.58 361	55.24 363	68.88 355	66.48 367	55.32 334	95.13 309	58.12 358	88.42 219	83.01 358

new_pmnet		72.15 325	70.13 329	78.20 341	82.95 361	65.68 355	83.91 352	82.40 362	62.94 360	64.47 359	79.82 357	42.85 360	86.26 365	57.41 360	74.44 340	82.65 360

test_f		71.95 326	70.87 328	75.21 345	74.21 370	59.37 367	85.07 346	85.82 351	65.25 356	70.42 353	83.13 350	23.62 370	82.93 370	78.32 250	71.94 346	83.33 357

pmmvs3		71.81 327	68.71 330	81.11 335	75.86 367	70.42 340	86.74 333	83.66 358	58.95 362	68.64 357	80.89 356	36.93 363	89.52 358	63.10 348	63.59 361	83.39 356

APD_test1		69.04 328	66.26 332	77.36 344	80.51 363	62.79 363	85.46 343	83.51 359	54.11 365	59.14 363	84.79 344	23.40 372	89.61 357	55.22 361	70.24 348	79.68 363

N_pmnet		68.89 329	68.44 331	70.23 349	89.07 326	28.79 383	88.06 321	19.50 384	69.47 350	71.86 350	84.93 342	61.24 307	91.75 349	54.70 362	77.15 332	90.15 334

LCM-MVSNet		66.00 330	62.16 335	77.51 343	64.51 378	58.29 368	83.87 353	90.90 316	48.17 367	54.69 364	73.31 364	16.83 378	86.75 364	65.47 338	61.67 363	87.48 354

test_vis3_rt		65.12 331	62.60 333	72.69 347	71.44 371	60.71 365	87.17 331	65.55 377	63.80 359	53.22 365	65.65 369	14.54 379	89.44 359	76.65 267	65.38 358	67.91 368

FPMVS		64.63 332	62.55 334	70.88 348	70.80 372	56.71 369	84.42 350	84.42 356	51.78 366	49.57 366	81.61 354	23.49 371	81.48 371	40.61 372	76.25 336	74.46 364

EGC-MVSNET		61.97 333	56.37 337	78.77 340	89.63 323	73.50 307	89.12 309	82.79 360	0.21 381	1.24 382	84.80 343	39.48 362	90.04 356	44.13 367	75.94 338	72.79 365

PMMVS2		59.60 334	56.40 336	69.21 352	68.83 375	46.58 378	73.02 369	77.48 373	55.07 364	49.21 367	72.95 365	17.43 377	80.04 372	49.32 366	44.33 372	80.99 362

testf1		59.54 335	56.11 338	69.85 350	69.28 373	56.61 371	80.37 362	76.55 374	42.58 370	45.68 369	75.61 359	11.26 380	84.18 367	43.20 369	60.44 365	68.75 366

APD_test2		59.54 335	56.11 338	69.85 350	69.28 373	56.61 371	80.37 362	76.55 374	42.58 370	45.68 369	75.61 359	11.26 380	84.18 367	43.20 369	60.44 365	68.75 366

ANet_high		58.88 337	54.22 341	72.86 346	56.50 381	56.67 370	80.75 361	86.00 350	73.09 335	37.39 373	64.63 370	22.17 373	79.49 373	43.51 368	23.96 375	82.43 361

Gipuma		57.99 338	54.91 340	67.24 353	88.51 330	65.59 356	52.21 372	90.33 325	43.58 369	42.84 372	51.18 373	20.29 375	85.07 366	34.77 373	70.45 347	51.05 372
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 339	48.46 343	63.48 354	45.72 383	46.20 379	73.41 368	78.31 371	41.03 372	30.06 375	65.68 368	6.05 382	83.43 369	30.04 374	65.86 357	60.80 369
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_method		50.52 340	48.47 342	56.66 356	52.26 382	18.98 385	41.51 374	81.40 364	10.10 376	44.59 371	75.01 362	28.51 367	68.16 374	53.54 363	49.31 371	82.83 359

MVE	39.65 23	43.39 341	38.59 347	57.77 355	56.52 380	48.77 377	55.38 371	58.64 381	29.33 375	28.96 376	52.65 372	4.68 383	64.62 377	28.11 375	33.07 373	59.93 370
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		43.23 342	42.29 344	46.03 358	65.58 377	37.41 380	73.51 367	64.62 378	33.99 373	28.47 377	47.87 374	19.90 376	67.91 375	22.23 376	24.45 374	32.77 373

EMVS		42.07 343	41.12 345	44.92 359	63.45 379	35.56 382	73.65 366	63.48 379	33.05 374	26.88 378	45.45 375	21.27 374	67.14 376	19.80 377	23.02 376	32.06 374

tmp_tt		35.64 344	39.24 346	24.84 360	14.87 384	23.90 384	62.71 370	51.51 383	6.58 378	36.66 374	62.08 371	44.37 359	30.34 380	52.40 364	22.00 377	20.27 375

cdsmvs_eth3d_5k		22.14 345	29.52 348	0.00 364	0.00 387	0.00 388	0.00 375	95.76 143	0.00 382	0.00 383	94.29 150	75.66 158	0.00 383	0.00 381	0.00 381	0.00 379

wuyk23d		21.27 346	20.48 349	23.63 361	68.59 376	36.41 381	49.57 373	6.85 385	9.37 377	7.89 379	4.46 381	4.03 384	31.37 379	17.47 378	16.07 378	3.12 376

testmvs		8.92 347	11.52 350	1.12 363	1.06 385	0.46 387	86.02 337	0.65 386	0.62 379	2.74 380	9.52 379	0.31 386	0.45 382	2.38 379	0.39 379	2.46 378

test123		8.76 348	11.22 351	1.39 362	0.85 386	0.97 386	85.76 340	0.35 387	0.54 380	2.45 381	8.14 380	0.60 385	0.48 381	2.16 380	0.17 380	2.71 377

ab-mvs-re		7.82 349	10.43 352	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	93.88 171	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

pcd_1.5k_mvsjas		6.64 350	8.86 353	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	79.70 110	0.00 383	0.00 381	0.00 381	0.00 379

test_blank		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet_test		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

DCPMVS		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

sosnet-low-res		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

sosnet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uncertanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

Regformer		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

FOURS1					98.86 1	85.54 63	98.29 1	97.49 6	89.79 42	96.29 16

MSC_two_6792asdad				96.52 1	97.78 51	90.86 1		96.85 62					99.61 3	96.03 2	99.06 9	99.07 5

PC_three_1452									82.47 213	97.09 10	97.07 39	92.72 1	98.04 147	92.70 43	99.02 12	98.86 10

No_MVS				96.52 1	97.78 51	90.86 1		96.85 62					99.61 3	96.03 2	99.06 9	99.07 5

test_one_0601					98.58 11	85.83 57		97.44 15	91.05 12	96.78 14	98.06 6	91.45 11

eth-test2					0.00 387

eth-test					0.00 387

ZD-MVS					98.15 34	86.62 30		97.07 44	83.63 187	94.19 32	96.91 45	87.57 31	99.26 40	91.99 62	98.44 49

RE-MVS-def			93.68 44		97.92 43	84.57 74	96.28 43	96.76 73	87.46 106	93.75 39	97.43 19	82.94 75		92.73 39	97.80 71	97.88 75

IU-MVS					98.77 5	86.00 47		96.84 64	81.26 244	97.26 7				95.50 11	99.13 3	99.03 7

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 37	92.59 2	98.94 73	92.25 51	98.99 14	98.84 13

test_241102_TWO								97.44 15	90.31 26	97.62 5	98.07 4	91.46 10	99.58 8	95.66 5	99.12 6	98.98 9

test_241102_ONE					98.77 5	85.99 49		97.44 15	90.26 31	97.71 1	97.96 10	92.31 4	99.38 29

9.14			94.47 18		97.79 49		96.08 55	97.44 15	86.13 137	95.10 25	97.40 21	88.34 22	99.22 42	93.25 32	98.70 32

save fliter					97.85 46	85.63 62	95.21 99	96.82 67	89.44 49

test_0728_THIRD									90.75 17	97.04 11	98.05 8	92.09 6	99.55 14	95.64 7	99.13 3	99.13 2

test_0728_SECOND				95.01 15	98.79 2	86.43 36	97.09 16	97.49 6					99.61 3	95.62 9	99.08 7	98.99 8

test0726					98.78 3	85.93 52	97.19 11	97.47 11	90.27 29	97.64 4	98.13 1	91.47 8

GSMVS																96.12 141

test_part2					98.55 12	87.22 16				96.40 15

sam_mvs1												71.70 208				96.12 141

sam_mvs												70.60 221

ambc				83.06 331	79.99 364	63.51 361	77.47 365	92.86 261		74.34 341	84.45 345	28.74 366	95.06 312	73.06 298	68.89 354	90.61 330

MTGPA								96.97 49

test_post1							88.00 322				9.81 378	69.31 243	95.53 299	76.65 267

test_post											10.29 377	70.57 225	95.91 286

patchmatchnet-post											83.76 347	71.53 209	96.48 259

GG-mvs-BLEND				87.94 273	89.73 322	77.91 253	87.80 323	78.23 372		80.58 292	83.86 346	59.88 317	95.33 307	71.20 304	92.22 169	90.60 332

MTMP							96.16 49	60.64 380

gm-plane-assit					89.60 324	68.00 348			77.28 295		88.99 302		97.57 177	79.44 240

test9_res														91.91 66	98.71 30	98.07 64

TEST9					97.53 58	86.49 34	94.07 174	96.78 70	81.61 237	92.77 63	96.20 75	87.71 28	99.12 49

test_8					97.49 60	86.30 42	94.02 179	96.76 73	81.86 230	92.70 67	96.20 75	87.63 29	99.02 59

agg_prior2														90.54 90	98.68 35	98.27 50

agg_prior					97.38 63	85.92 54		96.72 79		92.16 77			98.97 70

TestCases				89.52 232	95.01 139	77.79 259		90.89 317	77.41 292	76.12 329	93.34 184	54.08 340	97.51 183	68.31 324	84.27 259	93.26 267

test_prior4						85.96 51	94.11 169

test_prior2							94.12 168		87.67 104	92.63 68	96.39 70	86.62 36		91.50 73	98.67 37

test_prior				93.82 56	97.29 67	84.49 78		96.88 60					98.87 77			98.11 63

旧先验2							93.36 207		71.25 345	94.37 29			97.13 222	86.74 133

新几何2							93.11 222

新几何1				93.10 72	97.30 66	84.35 85		95.56 157	71.09 346	91.26 101	96.24 73	82.87 76	98.86 79	79.19 244	98.10 60	96.07 145

旧先验1					96.79 76	81.81 151		95.67 149			96.81 51	86.69 35			97.66 75	96.97 114

无先验							93.28 214	96.26 105	73.95 327				99.05 53	80.56 226		96.59 126

原ACMM2							92.94 229

原ACMM1				92.01 118	97.34 64	81.05 172		96.81 68	78.89 272	90.45 108	95.92 88	82.65 77	98.84 83	80.68 224	98.26 55	96.14 139

test222					96.55 84	81.70 153	92.22 250	95.01 190	68.36 352	90.20 112	96.14 80	80.26 103			97.80 71	96.05 147

testdata2													98.75 87	78.30 251

segment_acmp												87.16 34

testdata				90.49 188	96.40 89	77.89 255		95.37 175	72.51 339	93.63 42	96.69 54	82.08 88	97.65 170	83.08 177	97.39 77	95.94 149

testdata1							92.15 252		87.94 94

test12				94.34 47	97.13 70	86.15 45		96.29 102		91.04 103		85.08 53	99.01 61		98.13 59	97.86 77

plane_prior7					94.70 158	82.74 128

plane_prior6					94.52 167	82.75 126						74.23 175

plane_prior5								96.22 110					98.12 132	88.15 111	89.99 188	94.63 195

plane_prior4											94.86 126

plane_prior3						82.75 126			90.26 31	86.91 168

plane_prior2							95.85 66		90.81 15

plane_prior1					94.59 162

plane_prior						82.73 129	95.21 99		89.66 46						89.88 193

n2								0.00 388

nn								0.00 388

door-mid								85.49 352

lessismore_v0				86.04 307	88.46 333	68.78 347		80.59 366		73.01 346	90.11 286	55.39 333	96.43 264	75.06 284	65.06 359	92.90 283

LGP-MVS_train				91.12 162	94.47 169	81.49 159		96.14 115	86.73 123	85.45 204	95.16 116	69.89 232	98.10 134	87.70 119	89.23 204	93.77 248

test11								96.57 90

door								85.33 353

HQP5-MVS						81.56 155

HQP-NCC					94.17 181		94.39 153		88.81 66	85.43 207

ACMP_Plane					94.17 181		94.39 153		88.81 66	85.43 207

BP-MVS														87.11 130

HQP4-MVS										85.43 207			97.96 153			94.51 205

HQP3-MVS								96.04 123							89.77 195

HQP2-MVS												73.83 185

NP-MVS					94.37 175	82.42 138					93.98 164

MDTV_nov1_ep13_2view						55.91 375	87.62 328		73.32 332	84.59 226		70.33 228		74.65 288		95.50 165

MDTV_nov1_ep13			83.56 263		91.69 260	69.93 343	87.75 325	91.54 300	78.60 279	84.86 221	88.90 304	69.54 237	96.03 279	70.25 310	88.93 210

ACMMP++_ref															87.47 233

ACMMP++															88.01 227

Test By Simon												80.02 105

ITE_SJBPF				88.24 264	91.88 251	77.05 272		92.92 259	85.54 150	80.13 300	93.30 188	57.29 327	96.20 273	72.46 300	84.71 255	91.49 314

DeepMVS_CX				56.31 357	74.23 369	51.81 376		56.67 382	44.85 368	48.54 368	75.16 361	27.87 368	58.74 378	40.92 371	52.22 369	58.39 371

High-resolution multi-view benchmark