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.

MSC_two_6792asdad				96.52 1	97.78 56	90.86 1		96.85 75					99.61 4	96.03 25	99.06 9	99.07 5

No_MVS				96.52 1	97.78 56	90.86 1		96.85 75					99.61 4	96.03 25	99.06 9	99.07 5

OPU-MVS				96.21 3	98.00 44	90.85 3	97.13 15				97.08 64	92.59 2	98.94 86	92.25 86	98.99 14	98.84 15

HPM-MVS++		95.14 10	94.91 22	95.83 4	98.25 31	89.65 4	95.92 81	96.96 63	91.75 12	94.02 65	96.83 76	88.12 24	99.55 16	93.41 60	98.94 16	98.28 57

MM		95.10 11	94.91 22	95.68 5	96.09 111	88.34 9	96.68 34	94.37 278	95.08 1	94.68 51	97.72 37	82.94 96	99.64 1	97.85 4	98.76 29	99.06 7

SMA-MVS		95.20 8	95.07 16	95.59 6	98.14 37	88.48 8	96.26 49	97.28 35	85.90 189	97.67 4	98.10 12	88.41 20	99.56 12	94.66 44	99.19 1	98.71 21
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
3Dnovator+	87.14 4	92.42 98	91.37 112	95.55 7	95.63 137	88.73 6	97.07 19	96.77 86	90.84 24	84.02 314	96.62 89	75.95 198	99.34 38	87.77 166	97.68 91	98.59 25

CNVR-MVS		95.40 7	95.37 9	95.50 8	98.11 38	88.51 7	95.29 123	96.96 63	92.09 9	95.32 43	97.08 64	89.49 15	99.33 41	95.10 39	98.85 20	98.66 22

MVS_0304		94.18 45	93.80 59	95.34 9	94.91 176	87.62 14	95.97 76	93.01 322	92.58 6	94.22 56	97.20 58	80.56 130	99.59 8	97.04 18	98.68 37	98.81 18

ACMMP_NAP		94.74 22	94.56 28	95.28 10	98.02 43	87.70 11	95.68 99	97.34 26	88.28 116	95.30 44	97.67 39	85.90 51	99.54 20	93.91 52	98.95 15	98.60 24

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 27	87.28 18	95.56 111	97.51 7	89.13 85	97.14 14	97.91 30	91.64 7	99.62 2	94.61 45	99.17 2	98.86 12
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SF-MVS		94.97 14	94.90 24	95.20 12	97.84 52	87.76 10	96.65 35	97.48 12	87.76 138	95.71 38	97.70 38	88.28 23	99.35 37	93.89 53	98.78 26	98.48 31

MCST-MVS		94.45 30	94.20 46	95.19 13	98.46 19	87.50 16	95.00 146	97.12 50	87.13 155	92.51 106	96.30 98	89.24 17	99.34 38	93.46 57	98.62 46	98.73 19

NCCC		94.81 19	94.69 27	95.17 14	97.83 53	87.46 17	95.66 102	96.93 67	92.34 7	93.94 66	96.58 91	87.74 27	99.44 29	92.83 69	98.40 54	98.62 23

DPM-MVS		92.58 94	91.74 104	95.08 15	96.19 102	89.31 5	92.66 293	96.56 106	83.44 262	91.68 131	95.04 169	86.60 43	98.99 76	85.60 199	97.92 80	96.93 168

ZNCC-MVS		94.47 29	94.28 40	95.03 16	98.52 15	86.96 20	96.85 29	97.32 30	88.24 117	93.15 81	97.04 67	86.17 48	99.62 2	92.40 80	98.81 23	98.52 27

test_0728_SECOND				95.01 17	98.79 2	86.43 39	97.09 17	97.49 8					99.61 4	95.62 32	99.08 7	98.99 9

MTAPA		94.42 34	94.22 43	95.00 18	98.42 21	86.95 21	94.36 196	96.97 60	91.07 20	93.14 82	97.56 41	84.30 77	99.56 12	93.43 58	98.75 30	98.47 34

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 26	97.47 13	91.73 13	96.10 31	96.69 81	89.90 12	99.30 44	94.70 43	98.04 75	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
region2R		94.43 32	94.27 42	94.92 20	98.65 8	86.67 30	96.92 25	97.23 38	88.60 107	93.58 73	97.27 52	85.22 60	99.54 20	92.21 88	98.74 31	98.56 26

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 30	86.29 46	97.46 7	97.40 22	89.03 90	96.20 30	98.10 12	89.39 16	99.34 38	95.88 27	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		94.43 32	94.28 40	94.91 21	98.63 9	86.69 28	96.94 21	97.32 30	88.63 104	93.53 76	97.26 54	85.04 64	99.54 20	92.35 83	98.78 26	98.50 28

GST-MVS		94.21 40	93.97 55	94.90 23	98.41 22	86.82 24	96.54 37	97.19 39	88.24 117	93.26 78	96.83 76	85.48 57	99.59 8	91.43 114	98.40 54	98.30 51

HFP-MVS		94.52 27	94.40 33	94.86 24	98.61 10	86.81 25	96.94 21	97.34 26	88.63 104	93.65 71	97.21 56	86.10 49	99.49 26	92.35 83	98.77 28	98.30 51

sasdasda		93.27 77	92.75 87	94.85 25	95.70 132	87.66 12	96.33 40	96.41 116	90.00 49	94.09 61	94.60 193	82.33 105	98.62 125	92.40 80	92.86 213	98.27 59

MP-MVS-pluss		94.21 40	94.00 54	94.85 25	98.17 35	86.65 31	94.82 159	97.17 44	86.26 181	92.83 91	97.87 32	85.57 56	99.56 12	94.37 48	98.92 17	98.34 44
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
canonicalmvs		93.27 77	92.75 87	94.85 25	95.70 132	87.66 12	96.33 40	96.41 116	90.00 49	94.09 61	94.60 193	82.33 105	98.62 125	92.40 80	92.86 213	98.27 59

XVS		94.45 30	94.32 36	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 32	92.85 89	97.16 62	85.02 65	99.49 26	91.99 99	98.56 50	98.47 34

X-MVStestdata		88.31 218	86.13 267	94.85 25	98.54 13	86.60 34	96.93 23	97.19 39	90.66 32	92.85 89	23.41 466	85.02 65	99.49 26	91.99 99	98.56 50	98.47 34

SteuartSystems-ACMMP		95.20 8	95.32 11	94.85 25	96.99 77	86.33 42	97.33 8	97.30 32	91.38 18	95.39 42	97.46 44	88.98 19	99.40 30	94.12 49	98.89 18	98.82 17
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		95.98 1	96.36 1	94.82 31	97.78 56	86.00 52	98.29 1	97.49 8	90.75 27	97.62 7	98.06 20	92.59 2	99.61 4	95.64 30	99.02 12	98.86 12

alignmvs		93.08 85	92.50 93	94.81 32	95.62 138	87.61 15	95.99 74	96.07 153	89.77 62	94.12 60	94.87 177	80.56 130	98.66 117	92.42 79	93.10 209	98.15 71

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 54	97.13 15	97.44 17	90.31 39	97.71 2	98.07 18	92.31 4	99.58 10	95.66 28	99.13 3	98.84 15

DeepC-MVS_fast	89.43 2	94.04 48	93.79 60	94.80 33	97.48 66	86.78 26	95.65 104	96.89 72	89.40 73	92.81 92	96.97 69	85.37 59	99.24 47	90.87 123	98.69 35	98.38 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		94.25 37	94.07 51	94.77 35	98.47 18	86.31 44	96.71 32	96.98 59	89.04 88	91.98 117	97.19 59	85.43 58	99.56 12	92.06 97	98.79 24	98.44 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
APD-MVS		94.24 38	94.07 51	94.75 36	98.06 41	86.90 23	95.88 83	96.94 66	85.68 196	95.05 49	97.18 60	87.31 35	99.07 59	91.90 105	98.61 48	98.28 57
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CP-MVS		94.34 35	94.21 45	94.74 37	98.39 25	86.64 32	97.60 5	97.24 36	88.53 109	92.73 97	97.23 55	85.20 61	99.32 42	92.15 91	98.83 22	98.25 64

PGM-MVS		93.96 53	93.72 65	94.68 38	98.43 20	86.22 47	95.30 121	97.78 1	87.45 146	93.26 78	97.33 50	84.62 74	99.51 24	90.75 125	98.57 49	98.32 50

DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 57	97.09 17	96.73 92	90.27 43	97.04 18	98.05 23	91.47 8	99.55 16	95.62 32	99.08 7	98.45 37
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
mPP-MVS		93.99 51	93.78 61	94.63 40	98.50 16	85.90 62	96.87 27	96.91 70	88.70 102	91.83 126	97.17 61	83.96 81	99.55 16	91.44 113	98.64 45	98.43 39

PHI-MVS		93.89 55	93.65 69	94.62 41	96.84 80	86.43 39	96.69 33	97.49 8	85.15 220	93.56 75	96.28 99	85.60 55	99.31 43	92.45 77	98.79 24	98.12 76

TSAR-MVS + MP.		94.85 16	94.94 20	94.58 42	98.25 31	86.33 42	96.11 62	96.62 101	88.14 122	96.10 31	96.96 70	89.09 18	98.94 86	94.48 46	98.68 37	98.48 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CANet		93.54 64	93.20 78	94.55 43	95.65 135	85.73 67	94.94 149	96.69 97	91.89 11	90.69 149	95.88 123	81.99 117	99.54 20	93.14 64	97.95 79	98.39 41

train_agg		93.44 70	93.08 80	94.52 44	97.53 63	86.49 37	94.07 215	96.78 84	81.86 304	92.77 94	96.20 102	87.63 29	99.12 57	92.14 92	98.69 35	97.94 89

CDPH-MVS		92.83 89	92.30 96	94.44 45	97.79 54	86.11 51	94.06 217	96.66 98	80.09 335	92.77 94	96.63 88	86.62 41	99.04 63	87.40 172	98.66 41	98.17 69

3Dnovator	86.66 5	91.73 111	90.82 126	94.44 45	94.59 200	86.37 41	97.18 13	97.02 57	89.20 82	84.31 309	96.66 84	73.74 238	99.17 51	86.74 182	97.96 78	97.79 104

SR-MVS		94.23 39	94.17 49	94.43 47	98.21 34	85.78 65	96.40 39	96.90 71	88.20 120	94.33 55	97.40 47	84.75 73	99.03 64	93.35 61	97.99 77	98.48 31

HPM-MVS		94.02 49	93.88 56	94.43 47	98.39 25	85.78 65	97.25 11	97.07 55	86.90 165	92.62 103	96.80 80	84.85 71	99.17 51	92.43 78	98.65 44	98.33 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
TSAR-MVS + GP.		93.66 62	93.41 73	94.41 49	96.59 87	86.78 26	94.40 188	93.93 296	89.77 62	94.21 57	95.59 141	87.35 34	98.61 127	92.72 72	96.15 129	97.83 101

reproduce-ours		94.82 17	94.97 18	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 55	95.23 46	98.10 12	87.09 37	99.37 33	95.30 36	98.25 63	98.30 51

our_new_method		94.82 17	94.97 18	94.38 50	97.91 49	85.46 70	95.86 84	97.15 46	89.82 55	95.23 46	98.10 12	87.09 37	99.37 33	95.30 36	98.25 63	98.30 51

NormalMVS		93.46 67	93.16 79	94.37 52	98.40 23	86.20 48	96.30 42	96.27 129	91.65 16	92.68 99	96.13 108	77.97 168	98.84 99	90.75 125	98.26 59	98.07 78

test12				94.34 53	97.13 75	86.15 50		96.29 125		91.04 145		85.08 63	99.01 69		98.13 70	97.86 98

SymmetryMVS		92.81 91	92.31 95	94.32 54	96.15 103	86.20 48	96.30 42	94.43 274	91.65 16	92.68 99	96.13 108	77.97 168	98.84 99	90.75 125	94.72 161	97.92 93

ACMMP		93.24 79	92.88 85	94.30 55	98.09 40	85.33 74	96.86 28	97.45 16	88.33 113	90.15 163	97.03 68	81.44 123	99.51 24	90.85 124	95.74 136	98.04 84
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
reproduce_model		94.76 21	94.92 21	94.29 56	97.92 45	85.18 76	95.95 79	97.19 39	89.67 65	95.27 45	98.16 5	86.53 44	99.36 36	95.42 35	98.15 68	98.33 46

DeepC-MVS	88.79 3	93.31 76	92.99 83	94.26 57	96.07 113	85.83 63	94.89 152	96.99 58	89.02 91	89.56 171	97.37 49	82.51 102	99.38 31	92.20 89	98.30 57	97.57 119
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		93.03 86	92.63 90	94.23 58	95.62 138	85.92 59	96.08 64	96.33 123	89.86 53	93.89 68	94.66 190	82.11 112	98.50 133	92.33 85	92.82 216	98.27 59

fmvsm_l_conf0.5_n_3		94.80 20	95.01 17	94.15 59	95.64 136	85.08 77	96.09 63	97.36 24	90.98 22	97.09 16	98.12 9	84.98 69	98.94 86	97.07 15	97.80 86	98.43 39

EPNet		91.79 106	91.02 121	94.10 60	90.10 391	85.25 75	96.03 71	92.05 349	92.83 5	87.39 220	95.78 133	79.39 150	99.01 69	88.13 160	97.48 94	98.05 83
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lecture		95.10 11	95.46 8	94.01 61	98.40 23	84.36 102	97.70 3	97.78 1	91.19 19	96.22 29	98.08 17	86.64 40	99.37 33	94.91 41	98.26 59	98.29 56

test_fmvsmconf_n		94.60 25	94.81 25	93.98 62	94.62 197	84.96 80	96.15 57	97.35 25	89.37 74	96.03 34	98.11 10	86.36 45	99.01 69	97.45 9	97.83 84	97.96 88

DELS-MVS		93.43 74	93.25 76	93.97 63	95.42 146	85.04 78	93.06 277	97.13 49	90.74 29	91.84 124	95.09 168	86.32 46	99.21 49	91.22 115	98.45 52	97.65 113
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
DP-MVS Recon		91.95 103	91.28 115	93.96 64	98.33 29	85.92 59	94.66 171	96.66 98	82.69 282	90.03 165	95.82 129	82.30 107	99.03 64	84.57 217	96.48 122	96.91 170

HPM-MVS_fast		93.40 75	93.22 77	93.94 65	98.36 27	84.83 82	97.15 14	96.80 83	85.77 193	92.47 107	97.13 63	82.38 103	99.07 59	90.51 130	98.40 54	97.92 93

test_fmvsmconf0.1_n		94.20 42	94.31 38	93.88 66	92.46 307	84.80 83	96.18 54	96.82 80	89.29 79	95.68 39	98.11 10	85.10 62	98.99 76	97.38 10	97.75 90	97.86 98

SD-MVS		94.96 15	95.33 10	93.88 66	97.25 74	86.69 28	96.19 52	97.11 53	90.42 35	96.95 20	97.27 52	89.53 14	96.91 295	94.38 47	98.85 20	98.03 85
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
MVS_111021_HR		93.45 69	93.31 74	93.84 68	96.99 77	84.84 81	93.24 268	97.24 36	88.76 99	91.60 132	95.85 126	86.07 50	98.66 117	91.91 103	98.16 67	98.03 85

SR-MVS-dyc-post		93.82 57	93.82 58	93.82 69	97.92 45	84.57 89	96.28 46	96.76 87	87.46 144	93.75 69	97.43 45	84.24 78	99.01 69	92.73 70	97.80 86	97.88 96

test_prior				93.82 69	97.29 72	84.49 93		96.88 73					98.87 93			98.11 77

APD-MVS_3200maxsize		93.78 58	93.77 62	93.80 71	97.92 45	84.19 106	96.30 42	96.87 74	86.96 161	93.92 67	97.47 43	83.88 82	98.96 83	92.71 73	97.87 82	98.26 63

fmvsm_l_conf0.5_n		94.29 36	94.46 31	93.79 72	95.28 151	85.43 72	95.68 99	96.43 114	86.56 173	96.84 22	97.81 35	87.56 32	98.77 108	97.14 13	96.82 112	97.16 149

CSCG		93.23 80	93.05 81	93.76 73	98.04 42	84.07 108	96.22 51	97.37 23	84.15 243	90.05 164	95.66 138	87.77 26	99.15 55	89.91 135	98.27 58	98.07 78

GDP-MVS		92.04 101	91.46 109	93.75 74	94.55 206	84.69 86	95.60 110	96.56 106	87.83 135	93.07 85	95.89 122	73.44 242	98.65 119	90.22 133	96.03 131	97.91 95

BP-MVS1		92.48 96	92.07 99	93.72 75	94.50 209	84.39 101	95.90 82	94.30 281	90.39 36	92.67 101	95.94 119	74.46 221	98.65 119	93.14 64	97.35 98	98.13 73

test_fmvsmconf0.01_n		93.19 81	93.02 82	93.71 76	89.25 404	84.42 100	96.06 68	96.29 125	89.06 86	94.68 51	98.13 6	79.22 152	98.98 80	97.22 12	97.24 100	97.74 107

UA-Net		92.83 89	92.54 92	93.68 77	96.10 110	84.71 85	95.66 102	96.39 118	91.92 10	93.22 80	96.49 94	83.16 91	98.87 93	84.47 219	95.47 143	97.45 125

fmvsm_l_conf0.5_n_a		94.20 42	94.40 33	93.60 78	95.29 150	84.98 79	95.61 107	96.28 128	86.31 179	96.75 24	97.86 33	87.40 33	98.74 112	97.07 15	97.02 105	97.07 154

QAPM		89.51 175	88.15 202	93.59 79	94.92 174	84.58 88	96.82 30	96.70 96	78.43 362	83.41 330	96.19 105	73.18 247	99.30 44	77.11 330	96.54 119	96.89 171

test_fmvsm_n_1920		94.71 23	95.11 15	93.50 80	95.79 127	84.62 87	96.15 57	97.64 3	89.85 54	97.19 13	97.89 31	86.28 47	98.71 115	97.11 14	98.08 74	97.17 143

fmvsm_s_conf0.5_n_9		94.99 13	95.50 7	93.44 81	96.51 95	82.25 177	95.76 94	96.92 68	93.37 3	97.63 6	98.43 1	84.82 72	99.16 54	98.15 1	97.92 80	98.90 11

KinetiMVS		91.82 105	91.30 113	93.39 82	94.72 190	83.36 133	95.45 114	96.37 120	90.33 38	92.17 112	96.03 114	72.32 259	98.75 109	87.94 163	96.34 124	98.07 78

casdiffmvs_mvg		92.96 88	92.83 86	93.35 83	94.59 200	83.40 131	95.00 146	96.34 122	90.30 41	92.05 115	96.05 112	83.43 85	98.15 169	92.07 94	95.67 137	98.49 30
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
fmvsm_s_conf0.5_n_5		93.96 53	94.18 48	93.30 84	94.79 183	83.81 117	95.77 92	96.74 91	88.02 125	96.23 28	97.84 34	83.36 89	98.83 102	97.49 7	97.34 99	97.25 137

EI-MVSNet-Vis-set		93.01 87	92.92 84	93.29 85	95.01 165	83.51 128	94.48 180	95.77 181	90.87 23	92.52 105	96.67 83	84.50 75	99.00 74	91.99 99	94.44 174	97.36 128

Vis-MVSNet		91.75 110	91.23 116	93.29 85	95.32 149	83.78 118	96.14 59	95.98 160	89.89 51	90.45 153	96.58 91	75.09 210	98.31 160	84.75 211	96.90 108	97.78 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_conf03		93.98 52	94.22 43	93.26 87	96.13 105	83.29 135	96.27 48	96.52 109	89.82 55	95.56 41	95.51 144	84.50 75	98.79 106	94.83 42	98.86 19	97.72 109

SPE-MVS-test		94.02 49	94.29 39	93.24 88	96.69 83	83.24 136	97.49 6	96.92 68	92.14 8	92.90 87	95.77 134	85.02 65	98.33 157	93.03 66	98.62 46	98.13 73

VNet		92.24 100	91.91 101	93.24 88	96.59 87	83.43 129	94.84 158	96.44 113	89.19 83	94.08 64	95.90 121	77.85 174	98.17 167	88.90 151	93.38 198	98.13 73

VDD-MVS		90.74 133	89.92 147	93.20 90	96.27 100	83.02 150	95.73 96	93.86 300	88.42 112	92.53 104	96.84 75	62.09 365	98.64 122	90.95 121	92.62 223	97.93 92

Elysia		90.12 152	89.10 170	93.18 91	93.16 277	84.05 110	95.22 130	96.27 129	85.16 218	90.59 150	94.68 186	64.64 348	98.37 150	86.38 188	95.77 134	97.12 151

StellarMVS		90.12 152	89.10 170	93.18 91	93.16 277	84.05 110	95.22 130	96.27 129	85.16 218	90.59 150	94.68 186	64.64 348	98.37 150	86.38 188	95.77 134	97.12 151

CS-MVS		94.12 46	94.44 32	93.17 93	96.55 90	83.08 147	97.63 4	96.95 65	91.71 14	93.50 77	96.21 101	85.61 54	98.24 162	93.64 55	98.17 66	98.19 67

nrg030		91.08 127	90.39 131	93.17 93	93.07 284	86.91 22	96.41 38	96.26 133	88.30 115	88.37 196	94.85 180	82.19 111	97.64 221	91.09 116	82.95 347	94.96 256

MVSMamba_PlusPlus		93.44 70	93.54 71	93.14 95	96.58 89	83.05 148	96.06 68	96.50 111	84.42 240	94.09 61	95.56 143	85.01 68	98.69 116	94.96 40	98.66 41	97.67 112

EI-MVSNet-UG-set		92.74 92	92.62 91	93.12 96	94.86 179	83.20 138	94.40 188	95.74 184	90.71 31	92.05 115	96.60 90	84.00 80	98.99 76	91.55 111	93.63 189	97.17 143

test_fmvsmvis_n_1920		93.44 70	93.55 70	93.10 97	93.67 263	84.26 104	95.83 88	96.14 144	89.00 92	92.43 108	97.50 42	83.37 88	98.72 113	96.61 22	97.44 95	96.32 196

新几何1				93.10 97	97.30 71	84.35 103		95.56 199	71.09 429	91.26 141	96.24 100	82.87 98	98.86 95	79.19 309	98.10 71	96.07 212

OMC-MVS		91.23 121	90.62 130	93.08 99	96.27 100	84.07 108	93.52 250	95.93 166	86.95 162	89.51 172	96.13 108	78.50 162	98.35 154	85.84 197	92.90 212	96.83 178

OpenMVS	83.78 11	88.74 205	87.29 224	93.08 99	92.70 302	85.39 73	96.57 36	96.43 114	78.74 357	80.85 362	96.07 111	69.64 294	99.01 69	78.01 321	96.65 117	94.83 264

MAR-MVS		90.30 148	89.37 163	93.07 101	96.61 86	84.48 94	95.68 99	95.67 190	82.36 287	87.85 207	92.85 260	76.63 187	98.80 104	80.01 297	96.68 116	95.91 218
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
lupinMVS		90.92 128	90.21 135	93.03 102	93.86 248	83.88 115	92.81 288	93.86 300	79.84 338	91.76 128	94.29 207	77.92 171	98.04 186	90.48 131	97.11 101	97.17 143

Effi-MVS+		91.59 115	91.11 118	93.01 103	94.35 222	83.39 132	94.60 173	95.10 234	87.10 156	90.57 152	93.10 255	81.43 124	98.07 183	89.29 143	94.48 172	97.59 118

fmvsm_s_conf0.5_n_a		93.57 63	93.76 63	93.00 104	95.02 164	83.67 121	96.19 52	96.10 150	87.27 150	95.98 35	98.05 23	83.07 95	98.45 143	96.68 21	95.51 140	96.88 172

MVS_111021_LR		92.47 97	92.29 97	92.98 105	95.99 119	84.43 98	93.08 274	96.09 151	88.20 120	91.12 144	95.72 137	81.33 125	97.76 210	91.74 107	97.37 97	96.75 180

fmvsm_s_conf0.1_n_a		93.19 81	93.26 75	92.97 106	92.49 305	83.62 124	96.02 72	95.72 187	86.78 167	96.04 33	98.19 3	82.30 107	98.43 147	96.38 23	95.42 146	96.86 173

ETV-MVS		92.74 92	92.66 89	92.97 106	95.20 157	84.04 112	95.07 142	96.51 110	90.73 30	92.96 86	91.19 321	84.06 79	98.34 155	91.72 108	96.54 119	96.54 191

LFMVS		90.08 155	89.13 169	92.95 108	96.71 82	82.32 176	96.08 64	89.91 406	86.79 166	92.15 114	96.81 78	62.60 363	98.34 155	87.18 176	93.90 183	98.19 67

UGNet		89.95 162	88.95 178	92.95 108	94.51 208	83.31 134	95.70 98	95.23 227	89.37 74	87.58 214	93.94 223	64.00 353	98.78 107	83.92 226	96.31 125	96.74 181
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
jason		90.80 131	90.10 139	92.90 110	93.04 287	83.53 127	93.08 274	94.15 289	80.22 332	91.41 138	94.91 174	76.87 181	97.93 200	90.28 132	96.90 108	97.24 138
jason: jason.
DP-MVS		87.25 259	85.36 296	92.90 110	97.65 60	83.24 136	94.81 160	92.00 351	74.99 397	81.92 351	95.00 170	72.66 252	99.05 61	66.92 410	92.33 228	96.40 193

fmvsm_s_conf0.5_n_8		94.56 26	95.12 14	92.87 112	95.96 122	81.32 202	95.76 94	97.57 5	93.48 2	97.53 9	98.32 2	81.78 121	99.13 56	97.91 2	97.81 85	98.16 70

fmvsm_s_conf0.5_n		93.76 59	94.06 53	92.86 113	95.62 138	83.17 139	96.14 59	96.12 148	88.13 123	95.82 37	98.04 26	83.43 85	98.48 135	96.97 19	96.23 126	96.92 169

fmvsm_s_conf0.1_n		93.46 67	93.66 68	92.85 114	93.75 255	83.13 141	96.02 72	95.74 184	87.68 141	95.89 36	98.17 4	82.78 99	98.46 139	96.71 20	96.17 128	96.98 163

CANet_DTU		90.26 150	89.41 162	92.81 115	93.46 270	83.01 151	93.48 251	94.47 273	89.43 72	87.76 212	94.23 212	70.54 282	99.03 64	84.97 206	96.39 123	96.38 194

MVSFormer		91.68 113	91.30 113	92.80 116	93.86 248	83.88 115	95.96 77	95.90 170	84.66 236	91.76 128	94.91 174	77.92 171	97.30 262	89.64 139	97.11 101	97.24 138

PVSNet_Blended_VisFu		91.38 118	90.91 123	92.80 116	96.39 97	83.17 139	94.87 154	96.66 98	83.29 267	89.27 178	94.46 202	80.29 133	99.17 51	87.57 169	95.37 147	96.05 215

fmvsm_l_conf0.5_n_9		94.65 24	95.28 12	92.77 118	95.95 123	81.83 187	95.53 112	97.12 50	91.68 15	97.89 1	98.06 20	85.71 53	98.65 119	97.32 11	98.26 59	97.83 101

LuminaMVS		90.55 144	89.81 149	92.77 118	92.78 300	84.21 105	94.09 213	94.17 288	85.82 190	91.54 133	94.14 214	69.93 288	97.92 201	91.62 110	94.21 178	96.18 204

fmvsm_s_conf0.5_n_6		94.11 47	94.56 28	92.76 120	94.98 169	81.96 185	95.79 90	97.29 34	89.31 77	97.52 10	97.61 40	83.25 90	98.88 92	97.05 17	98.22 65	97.43 127

VDDNet		89.56 174	88.49 193	92.76 120	95.07 163	82.09 180	96.30 42	93.19 317	81.05 326	91.88 122	96.86 74	61.16 381	98.33 157	88.43 157	92.49 227	97.84 100

h-mvs33		90.80 131	90.15 138	92.75 122	96.01 115	82.66 164	95.43 115	95.53 203	89.80 58	93.08 83	95.64 139	75.77 199	99.00 74	92.07 94	78.05 404	96.60 186

casdiffmvs		92.51 95	92.43 94	92.74 123	94.41 217	81.98 183	94.54 177	96.23 137	89.57 68	91.96 119	96.17 106	82.58 101	98.01 188	90.95 121	95.45 145	98.23 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_yl		90.69 136	90.02 145	92.71 124	95.72 130	82.41 174	94.11 209	95.12 232	85.63 197	91.49 135	94.70 184	74.75 214	98.42 148	86.13 192	92.53 225	97.31 129

DCV-MVSNet		90.69 136	90.02 145	92.71 124	95.72 130	82.41 174	94.11 209	95.12 232	85.63 197	91.49 135	94.70 184	74.75 214	98.42 148	86.13 192	92.53 225	97.31 129

PCF-MVS	84.11 10	87.74 233	86.08 271	92.70 126	94.02 237	84.43 98	89.27 383	95.87 175	73.62 411	84.43 301	94.33 204	78.48 164	98.86 95	70.27 384	94.45 173	94.81 265
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SSM_0404		90.73 134	90.08 140	92.69 127	95.00 168	83.13 141	94.32 197	95.00 242	85.41 208	89.84 166	95.35 152	76.13 190	97.98 192	85.46 202	94.18 179	96.95 165

baseline		92.39 99	92.29 97	92.69 127	94.46 212	81.77 189	94.14 206	96.27 129	89.22 81	91.88 122	96.00 115	82.35 104	97.99 190	91.05 117	95.27 151	98.30 51

MSLP-MVS++		93.72 61	94.08 50	92.65 129	97.31 70	83.43 129	95.79 90	97.33 28	90.03 48	93.58 73	96.96 70	84.87 70	97.76 210	92.19 90	98.66 41	96.76 179

EC-MVSNet		93.44 70	93.71 66	92.63 130	95.21 156	82.43 171	97.27 10	96.71 95	90.57 34	92.88 88	95.80 130	83.16 91	98.16 168	93.68 54	98.14 69	97.31 129

ab-mvs		89.41 182	88.35 195	92.60 131	95.15 161	82.65 168	92.20 312	95.60 197	83.97 247	88.55 192	93.70 237	74.16 229	98.21 166	82.46 250	89.37 272	96.94 167

LS3D		87.89 228	86.32 260	92.59 132	96.07 113	82.92 154	95.23 128	94.92 249	75.66 389	82.89 337	95.98 117	72.48 256	99.21 49	68.43 398	95.23 152	95.64 232

Anonymous20240529		88.09 224	86.59 249	92.58 133	96.53 92	81.92 186	95.99 74	95.84 177	74.11 406	89.06 182	95.21 162	61.44 373	98.81 103	83.67 233	87.47 303	97.01 161

fmvsm_s_conf0.5_n_3		94.49 28	95.13 13	92.56 134	95.49 144	81.10 212	95.93 80	97.16 45	92.96 4	97.39 11	98.13 6	83.63 84	98.80 104	97.89 3	97.61 93	97.78 105

CPTT-MVS		91.99 102	91.80 102	92.55 135	98.24 33	81.98 183	96.76 31	96.49 112	81.89 303	90.24 156	96.44 96	78.59 160	98.61 127	89.68 138	97.85 83	97.06 155

viewdifsd2359ckpt13		91.20 123	90.75 128	92.54 136	94.30 224	82.13 179	94.03 219	95.89 172	85.60 199	90.20 158	95.36 151	79.69 146	97.90 204	87.85 165	93.86 184	97.61 115

114514_t		89.51 175	88.50 191	92.54 136	98.11 38	81.99 182	95.16 138	96.36 121	70.19 433	85.81 254	95.25 158	76.70 185	98.63 124	82.07 260	96.86 111	97.00 162

PAPM_NR		91.22 122	90.78 127	92.52 138	97.60 61	81.46 198	94.37 194	96.24 136	86.39 178	87.41 217	94.80 182	82.06 115	98.48 135	82.80 245	95.37 147	97.61 115

mamba_0408		89.06 195	87.92 209	92.50 139	94.76 184	82.66 164	79.84 452	94.64 267	85.18 213	88.96 184	95.00 170	76.00 195	97.98 192	83.74 230	93.15 206	96.85 174

DeepPCF-MVS	89.96 1	94.20 42	94.77 26	92.49 140	96.52 93	80.00 252	94.00 224	97.08 54	90.05 47	95.65 40	97.29 51	89.66 13	98.97 81	93.95 51	98.71 32	98.50 28

SSM_0407		90.47 146	89.80 150	92.46 141	94.76 184	82.66 164	93.98 226	95.00 242	85.41 208	88.96 184	95.35 152	76.13 190	97.88 205	85.46 202	93.15 206	96.85 174

IS-MVSNet		91.43 117	91.09 120	92.46 141	95.87 126	81.38 201	96.95 20	93.69 308	89.72 64	89.50 174	95.98 117	78.57 161	97.77 209	83.02 239	96.50 121	98.22 66

API-MVS		90.66 139	90.07 141	92.45 143	96.36 98	84.57 89	96.06 68	95.22 229	82.39 285	89.13 179	94.27 210	80.32 132	98.46 139	80.16 296	96.71 115	94.33 288

xiu_mvs_v1_base_debu		90.64 140	90.05 142	92.40 144	93.97 243	84.46 95	93.32 259	95.46 207	85.17 215	92.25 109	94.03 215	70.59 278	98.57 130	90.97 118	94.67 163	94.18 291

xiu_mvs_v1_base		90.64 140	90.05 142	92.40 144	93.97 243	84.46 95	93.32 259	95.46 207	85.17 215	92.25 109	94.03 215	70.59 278	98.57 130	90.97 118	94.67 163	94.18 291

xiu_mvs_v1_base_debi		90.64 140	90.05 142	92.40 144	93.97 243	84.46 95	93.32 259	95.46 207	85.17 215	92.25 109	94.03 215	70.59 278	98.57 130	90.97 118	94.67 163	94.18 291

fmvsm_s_conf0.5_n_2		93.47 66	93.83 57	92.39 147	95.36 147	81.19 208	95.20 135	96.56 106	90.37 37	97.13 15	98.03 27	77.47 177	98.96 83	97.79 5	96.58 118	97.03 158

viewmacassd2359aftdt		91.67 114	91.43 111	92.37 148	93.95 246	81.00 216	93.90 234	95.97 163	87.75 139	91.45 137	96.04 113	79.92 138	97.97 194	89.26 144	94.67 163	98.14 72

viewmanbaseed2359cas		91.78 108	91.58 107	92.37 148	94.32 223	81.07 213	93.76 239	95.96 164	87.26 151	91.50 134	95.88 123	80.92 129	97.97 194	89.70 137	94.92 157	98.07 78

fmvsm_s_conf0.1_n_2		93.16 83	93.42 72	92.37 148	94.62 197	81.13 210	95.23 128	95.89 172	90.30 41	96.74 25	98.02 28	76.14 189	98.95 85	97.64 6	96.21 127	97.03 158

AdaColmap		89.89 165	89.07 172	92.37 148	97.41 67	83.03 149	94.42 187	95.92 167	82.81 279	86.34 243	94.65 191	73.89 234	99.02 67	80.69 287	95.51 140	95.05 251

CNLPA		89.07 194	87.98 206	92.34 152	96.87 79	84.78 84	94.08 214	93.24 314	81.41 317	84.46 299	95.13 167	75.57 206	96.62 308	77.21 328	93.84 186	95.61 235

fmvsm_s_conf0.5_n_4		93.86 56	94.37 35	92.33 153	95.13 162	80.95 219	95.64 105	96.97 60	89.60 67	96.85 21	97.77 36	83.08 94	98.92 89	97.49 7	96.78 113	97.13 150

ET-MVSNet_ETH3D		87.51 247	85.91 279	92.32 154	93.70 262	83.93 113	92.33 306	90.94 383	84.16 242	72.09 431	92.52 273	69.90 289	95.85 355	89.20 145	88.36 290	97.17 143

Anonymous202405211		87.68 234	86.13 267	92.31 155	96.66 84	80.74 227	94.87 154	91.49 368	80.47 331	89.46 175	95.44 147	54.72 418	98.23 163	82.19 256	89.89 262	97.97 87

CHOSEN 1792x2688		88.84 201	87.69 214	92.30 156	96.14 104	81.42 200	90.01 370	95.86 176	74.52 402	87.41 217	93.94 223	75.46 207	98.36 152	80.36 292	95.53 139	97.12 151

viewcassd2359sk11		91.79 106	91.62 106	92.29 157	94.62 197	80.88 222	93.70 244	96.18 142	87.38 148	91.13 143	95.85 126	81.62 122	98.06 184	89.71 136	94.40 175	97.94 89

HY-MVS	83.01 12	89.03 197	87.94 208	92.29 157	94.86 179	82.77 156	92.08 317	94.49 272	81.52 316	86.93 224	92.79 266	78.32 166	98.23 163	79.93 298	90.55 249	95.88 221

CDS-MVSNet		89.45 178	88.51 190	92.29 157	93.62 265	83.61 126	93.01 278	94.68 265	81.95 297	87.82 210	93.24 249	78.69 158	96.99 289	80.34 293	93.23 203	96.28 199
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		90.02 158	89.27 168	92.29 157	95.78 128	80.95 219	92.68 292	96.22 138	81.91 299	86.66 234	93.75 235	82.23 109	98.44 145	79.40 308	94.79 160	97.48 123

mvsmamba		90.33 147	89.69 153	92.25 161	95.17 158	81.64 191	95.27 126	93.36 313	84.88 227	89.51 172	94.27 210	69.29 303	97.42 247	89.34 142	96.12 130	97.68 111

PLC	84.53 7	89.06 195	88.03 204	92.15 162	97.27 73	82.69 163	94.29 198	95.44 212	79.71 340	84.01 315	94.18 213	76.68 186	98.75 109	77.28 327	93.41 197	95.02 252
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EPP-MVSNet		91.70 112	91.56 108	92.13 163	95.88 124	80.50 234	97.33 8	95.25 226	86.15 184	89.76 170	95.60 140	83.42 87	98.32 159	87.37 174	93.25 202	97.56 120

patch_mono-2		93.74 60	94.32 36	92.01 164	97.54 62	78.37 294	93.40 255	97.19 39	88.02 125	94.99 50	97.21 56	88.35 21	98.44 145	94.07 50	98.09 72	99.23 1

原ACMM1				92.01 164	97.34 69	81.05 214		96.81 82	78.89 351	90.45 153	95.92 120	82.65 100	98.84 99	80.68 288	98.26 59	96.14 206

UniMVSNet (Re)		89.80 168	89.07 172	92.01 164	93.60 266	84.52 92	94.78 162	97.47 13	89.26 80	86.44 240	92.32 279	82.10 113	97.39 258	84.81 210	80.84 381	94.12 295

MG-MVS		91.77 109	91.70 105	92.00 167	97.08 76	80.03 250	93.60 248	95.18 230	87.85 134	90.89 147	96.47 95	82.06 115	98.36 152	85.07 205	97.04 104	97.62 114

EIA-MVS		91.95 103	91.94 100	91.98 168	95.16 159	80.01 251	95.36 116	96.73 92	88.44 110	89.34 176	92.16 284	83.82 83	98.45 143	89.35 141	97.06 103	97.48 123

PVSNet_Blended		90.73 134	90.32 133	91.98 168	96.12 106	81.25 204	92.55 297	96.83 78	82.04 295	89.10 180	92.56 272	81.04 127	98.85 97	86.72 184	95.91 132	95.84 223

guyue		91.12 126	90.84 125	91.96 170	94.59 200	80.57 232	94.87 154	93.71 307	88.96 93	91.14 142	95.22 159	73.22 246	97.76 210	92.01 98	93.81 187	97.54 122

PS-MVSNAJ		91.18 124	90.92 122	91.96 170	95.26 154	82.60 170	92.09 316	95.70 188	86.27 180	91.84 124	92.46 274	79.70 143	98.99 76	89.08 146	95.86 133	94.29 289

TAMVS		89.21 188	88.29 199	91.96 170	93.71 260	82.62 169	93.30 263	94.19 286	82.22 290	87.78 211	93.94 223	78.83 155	96.95 292	77.70 323	92.98 211	96.32 196

SDMVSNet		90.19 151	89.61 156	91.93 173	96.00 116	83.09 146	92.89 285	95.98 160	88.73 100	86.85 230	95.20 163	72.09 261	97.08 281	88.90 151	89.85 264	95.63 233

FA-MVS(test-final)		89.66 170	88.91 180	91.93 173	94.57 204	80.27 238	91.36 333	94.74 262	84.87 228	89.82 167	92.61 271	74.72 217	98.47 138	83.97 225	93.53 192	97.04 157

MVS_Test		91.31 120	91.11 118	91.93 173	94.37 218	80.14 243	93.46 253	95.80 179	86.46 176	91.35 140	93.77 233	82.21 110	98.09 180	87.57 169	94.95 156	97.55 121

NR-MVSNet		88.58 211	87.47 220	91.93 173	93.04 287	84.16 107	94.77 163	96.25 135	89.05 87	80.04 376	93.29 247	79.02 154	97.05 286	81.71 271	80.05 391	94.59 272

HyFIR lowres test		88.09 224	86.81 237	91.93 173	96.00 116	80.63 229	90.01 370	95.79 180	73.42 413	87.68 213	92.10 290	73.86 235	97.96 196	80.75 286	91.70 232	97.19 142

GeoE		90.05 156	89.43 161	91.90 178	95.16 159	80.37 237	95.80 89	94.65 266	83.90 248	87.55 216	94.75 183	78.18 167	97.62 223	81.28 276	93.63 189	97.71 110

thisisatest0530		88.67 206	87.61 216	91.86 179	94.87 178	80.07 246	94.63 172	89.90 407	84.00 246	88.46 194	93.78 232	66.88 327	98.46 139	83.30 235	92.65 218	97.06 155

xiu_mvs_v2_base		91.13 125	90.89 124	91.86 179	94.97 170	82.42 172	92.24 309	95.64 195	86.11 188	91.74 130	93.14 253	79.67 147	98.89 91	89.06 147	95.46 144	94.28 290

DU-MVS		89.34 187	88.50 191	91.85 181	93.04 287	83.72 119	94.47 183	96.59 103	89.50 69	86.46 237	93.29 247	77.25 179	97.23 271	84.92 207	81.02 377	94.59 272

AstraMVS		90.69 136	90.30 134	91.84 182	93.81 251	79.85 257	94.76 164	92.39 337	88.96 93	91.01 146	95.87 125	70.69 276	97.94 199	92.49 76	92.70 217	97.73 108

OPM-MVS		90.12 152	89.56 157	91.82 183	93.14 279	83.90 114	94.16 205	95.74 184	88.96 93	87.86 206	95.43 149	72.48 256	97.91 202	88.10 162	90.18 256	93.65 326
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		90.60 143	90.19 136	91.82 183	94.70 193	82.73 160	95.85 86	96.22 138	90.81 25	86.91 226	94.86 178	74.23 225	98.12 170	88.15 158	89.99 258	94.63 269

UniMVSNet_NR-MVSNet		89.92 164	89.29 166	91.81 185	93.39 272	83.72 119	94.43 186	97.12 50	89.80 58	86.46 237	93.32 244	83.16 91	97.23 271	84.92 207	81.02 377	94.49 282

diffmvs		91.37 119	91.23 116	91.77 186	93.09 282	80.27 238	92.36 303	95.52 204	87.03 158	91.40 139	94.93 173	80.08 135	97.44 245	92.13 93	94.56 169	97.61 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
diffmvs_AUTHOR		91.51 116	91.44 110	91.73 187	93.09 282	80.27 238	92.51 298	95.58 198	87.22 152	91.80 127	95.57 142	79.96 137	97.48 237	92.23 87	94.97 155	97.45 125

1112_ss		88.42 213	87.33 223	91.72 188	94.92 174	80.98 217	92.97 282	94.54 269	78.16 368	83.82 318	93.88 228	78.78 157	97.91 202	79.45 304	89.41 271	96.26 200

Fast-Effi-MVS+		89.41 182	88.64 186	91.71 189	94.74 187	80.81 225	93.54 249	95.10 234	83.11 271	86.82 232	90.67 344	79.74 142	97.75 214	80.51 291	93.55 191	96.57 189

WTY-MVS		89.60 172	88.92 179	91.67 190	95.47 145	81.15 209	92.38 302	94.78 260	83.11 271	89.06 182	94.32 205	78.67 159	96.61 311	81.57 272	90.89 245	97.24 138

TAPA-MVS	84.62 6	88.16 222	87.01 232	91.62 191	96.64 85	80.65 228	94.39 190	96.21 141	76.38 382	86.19 247	95.44 147	79.75 141	98.08 182	62.75 428	95.29 149	96.13 207
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VPA-MVSNet		89.62 171	88.96 177	91.60 192	93.86 248	82.89 155	95.46 113	97.33 28	87.91 129	88.43 195	93.31 245	74.17 228	97.40 255	87.32 175	82.86 352	94.52 277

FE-MVS		87.40 252	86.02 273	91.57 193	94.56 205	79.69 261	90.27 357	93.72 306	80.57 329	88.80 188	91.62 310	65.32 343	98.59 129	74.97 353	94.33 177	96.44 192

XVG-OURS		89.40 184	88.70 185	91.52 194	94.06 235	81.46 198	91.27 337	96.07 153	86.14 185	88.89 187	95.77 134	68.73 312	97.26 268	87.39 173	89.96 260	95.83 224

hse-mvs2		89.88 166	89.34 164	91.51 195	94.83 181	81.12 211	93.94 228	93.91 299	89.80 58	93.08 83	93.60 238	75.77 199	97.66 218	92.07 94	77.07 411	95.74 228

TranMVSNet+NR-MVSNet		88.84 201	87.95 207	91.49 196	92.68 303	83.01 151	94.92 151	96.31 124	89.88 52	85.53 263	93.85 230	76.63 187	96.96 291	81.91 264	79.87 394	94.50 280

AUN-MVS		87.78 232	86.54 252	91.48 197	94.82 182	81.05 214	93.91 232	93.93 296	83.00 274	86.93 224	93.53 239	69.50 297	97.67 216	86.14 190	77.12 410	95.73 230

XVG-OURS-SEG-HR		89.95 162	89.45 159	91.47 198	94.00 241	81.21 207	91.87 321	96.06 155	85.78 192	88.55 192	95.73 136	74.67 218	97.27 266	88.71 154	89.64 269	95.91 218

MVS		87.44 250	86.10 270	91.44 199	92.61 304	83.62 124	92.63 294	95.66 192	67.26 439	81.47 354	92.15 285	77.95 170	98.22 165	79.71 300	95.48 142	92.47 369

F-COLMAP		87.95 227	86.80 238	91.40 200	96.35 99	80.88 222	94.73 166	95.45 210	79.65 341	82.04 349	94.61 192	71.13 268	98.50 133	76.24 340	91.05 243	94.80 266

dcpmvs_2		93.49 65	94.19 47	91.38 201	97.69 59	76.78 335	94.25 200	96.29 125	88.33 113	94.46 53	96.88 73	88.07 25	98.64 122	93.62 56	98.09 72	98.73 19

thisisatest0515		87.33 255	85.99 274	91.37 202	93.49 268	79.55 262	90.63 351	89.56 415	80.17 333	87.56 215	90.86 334	67.07 324	98.28 161	81.50 273	93.02 210	96.29 198

HQP-MVS		89.80 168	89.28 167	91.34 203	94.17 230	81.56 192	94.39 190	96.04 156	88.81 96	85.43 272	93.97 222	73.83 236	97.96 196	87.11 179	89.77 267	94.50 280

fmvsm_s_conf0.5_n_7		93.15 84	93.76 63	91.31 204	94.42 216	79.48 264	94.52 178	97.14 48	89.33 76	94.17 59	98.09 16	81.83 119	97.49 236	96.33 24	98.02 76	96.95 165

RRT-MVS		90.85 130	90.70 129	91.30 205	94.25 226	76.83 334	94.85 157	96.13 147	89.04 88	90.23 157	94.88 176	70.15 287	98.72 113	91.86 106	94.88 158	98.34 44

FMVSNet3		87.40 252	86.11 269	91.30 205	93.79 254	83.64 123	94.20 204	94.81 258	83.89 249	84.37 302	91.87 301	68.45 315	96.56 316	78.23 318	85.36 320	93.70 325

FMVSNet2		87.19 265	85.82 282	91.30 205	94.01 238	83.67 121	94.79 161	94.94 244	83.57 257	83.88 317	92.05 294	66.59 332	96.51 320	77.56 325	85.01 323	93.73 323

RPMNet		83.95 342	81.53 353	91.21 208	90.58 381	79.34 270	85.24 430	96.76 87	71.44 427	85.55 261	82.97 439	70.87 273	98.91 90	61.01 432	89.36 273	95.40 239

IB-MVS	80.51 15	85.24 319	83.26 337	91.19 209	92.13 316	79.86 256	91.75 324	91.29 373	83.28 268	80.66 366	88.49 391	61.28 375	98.46 139	80.99 282	79.46 398	95.25 245
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
CLD-MVS		89.47 177	88.90 181	91.18 210	94.22 228	82.07 181	92.13 314	96.09 151	87.90 130	85.37 278	92.45 275	74.38 223	97.56 228	87.15 177	90.43 251	93.93 304
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		89.45 178	88.90 181	91.12 211	94.47 210	81.49 196	95.30 121	96.14 144	86.73 169	85.45 269	95.16 165	69.89 290	98.10 172	87.70 167	89.23 276	93.77 319

LGP-MVS_train				91.12 211	94.47 210	81.49 196		96.14 144	86.73 169	85.45 269	95.16 165	69.89 290	98.10 172	87.70 167	89.23 276	93.77 319

ACMM	84.12 9	89.14 190	88.48 194	91.12 211	94.65 196	81.22 206	95.31 119	96.12 148	85.31 212	85.92 252	94.34 203	70.19 286	98.06 184	85.65 198	88.86 281	94.08 299
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tttt0517		88.61 208	87.78 213	91.11 214	94.96 171	77.81 311	95.35 117	89.69 410	85.09 222	88.05 204	94.59 195	66.93 325	98.48 135	83.27 236	92.13 230	97.03 158

GBi-Net		87.26 257	85.98 275	91.08 215	94.01 238	83.10 143	95.14 139	94.94 244	83.57 257	84.37 302	91.64 306	66.59 332	96.34 333	78.23 318	85.36 320	93.79 314

test1		87.26 257	85.98 275	91.08 215	94.01 238	83.10 143	95.14 139	94.94 244	83.57 257	84.37 302	91.64 306	66.59 332	96.34 333	78.23 318	85.36 320	93.79 314

FMVSNet1		85.85 304	84.11 324	91.08 215	92.81 298	83.10 143	95.14 139	94.94 244	81.64 311	82.68 339	91.64 306	59.01 397	96.34 333	75.37 347	83.78 336	93.79 314

Test_1112_low_res		87.65 236	86.51 253	91.08 215	94.94 173	79.28 274	91.77 323	94.30 281	76.04 387	83.51 328	92.37 277	77.86 173	97.73 215	78.69 313	89.13 278	96.22 201

PS-MVSNAJss		89.97 160	89.62 155	91.02 219	91.90 325	80.85 224	95.26 127	95.98 160	86.26 181	86.21 246	94.29 207	79.70 143	97.65 219	88.87 153	88.10 292	94.57 274

BH-RMVSNet		88.37 216	87.48 219	91.02 219	95.28 151	79.45 266	92.89 285	93.07 320	85.45 207	86.91 226	94.84 181	70.35 283	97.76 210	73.97 361	94.59 168	95.85 222

UniMVSNet_ETH3D		87.53 246	86.37 257	91.00 221	92.44 308	78.96 279	94.74 165	95.61 196	84.07 245	85.36 279	94.52 197	59.78 389	97.34 260	82.93 240	87.88 297	96.71 182

FIs		90.51 145	90.35 132	90.99 222	93.99 242	80.98 217	95.73 96	97.54 6	89.15 84	86.72 233	94.68 186	81.83 119	97.24 270	85.18 204	88.31 291	94.76 267

ACMP	84.23 8	89.01 199	88.35 195	90.99 222	94.73 188	81.27 203	95.07 142	95.89 172	86.48 174	83.67 323	94.30 206	69.33 299	97.99 190	87.10 181	88.55 283	93.72 324
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous20231211		86.59 287	85.13 302	90.98 224	96.52 93	81.50 194	96.14 59	96.16 143	73.78 409	83.65 324	92.15 285	63.26 359	97.37 259	82.82 244	81.74 366	94.06 300

IMVS_0403		89.97 160	89.64 154	90.96 225	93.72 256	77.75 316	93.00 279	95.34 221	85.53 203	88.77 189	94.49 198	78.49 163	97.84 206	84.75 211	92.65 218	97.28 132

sss		88.93 200	88.26 201	90.94 226	94.05 236	80.78 226	91.71 325	95.38 216	81.55 315	88.63 191	93.91 227	75.04 211	95.47 374	82.47 249	91.61 233	96.57 189

IMVS_0407		89.85 167	89.51 158	90.88 227	93.72 256	77.75 316	93.07 276	95.34 221	85.53 203	88.34 197	94.49 198	77.69 175	97.60 224	84.75 211	92.65 218	97.28 132

viewmambaseed2359dif		90.04 157	89.78 151	90.83 228	92.85 297	77.92 305	92.23 310	95.01 238	81.90 300	90.20 158	95.45 146	79.64 149	97.34 260	87.52 171	93.17 204	97.23 141

sd_testset		88.59 210	87.85 212	90.83 228	96.00 116	80.42 236	92.35 304	94.71 263	88.73 100	86.85 230	95.20 163	67.31 319	96.43 327	79.64 302	89.85 264	95.63 233

PVSNet_BlendedMVS		89.98 159	89.70 152	90.82 230	96.12 106	81.25 204	93.92 230	96.83 78	83.49 261	89.10 180	92.26 282	81.04 127	98.85 97	86.72 184	87.86 298	92.35 375

cascas		86.43 295	84.98 305	90.80 231	92.10 318	80.92 221	90.24 361	95.91 169	73.10 416	83.57 327	88.39 392	65.15 345	97.46 241	84.90 209	91.43 235	94.03 302

ECVR-MVS		89.09 193	88.53 189	90.77 232	95.62 138	75.89 348	96.16 55	84.22 441	87.89 132	90.20 158	96.65 85	63.19 360	98.10 172	85.90 195	96.94 106	98.33 46

GA-MVS		86.61 285	85.27 299	90.66 233	91.33 348	78.71 283	90.40 356	93.81 303	85.34 211	85.12 282	89.57 373	61.25 376	97.11 280	80.99 282	89.59 270	96.15 205

thres600view7		87.65 236	86.67 244	90.59 234	96.08 112	78.72 281	94.88 153	91.58 364	87.06 157	88.08 202	92.30 280	68.91 309	98.10 172	70.05 391	91.10 238	94.96 256

thres400		87.62 241	86.64 245	90.57 235	95.99 119	78.64 284	94.58 174	91.98 353	86.94 163	88.09 200	91.77 302	69.18 305	98.10 172	70.13 388	91.10 238	94.96 256

baseline1		88.10 223	87.28 225	90.57 235	94.96 171	80.07 246	94.27 199	91.29 373	86.74 168	87.41 217	94.00 220	76.77 184	96.20 338	80.77 285	79.31 400	95.44 237

viewdifsd2359ckpt11		89.43 180	89.05 174	90.56 237	92.89 295	77.00 330	92.81 288	94.52 270	87.03 158	89.77 168	95.79 131	74.67 218	97.51 232	88.97 149	84.98 324	97.17 143

viewmsd2359difaftdt		89.43 180	89.05 174	90.56 237	92.89 295	77.00 330	92.81 288	94.52 270	87.03 158	89.77 168	95.79 131	74.67 218	97.51 232	88.97 149	84.98 324	97.17 143

FC-MVSNet-test		90.27 149	90.18 137	90.53 239	93.71 260	79.85 257	95.77 92	97.59 4	89.31 77	86.27 244	94.67 189	81.93 118	97.01 288	84.26 221	88.09 294	94.71 268

PAPM		86.68 284	85.39 294	90.53 239	93.05 286	79.33 273	89.79 373	94.77 261	78.82 354	81.95 350	93.24 249	76.81 182	97.30 262	66.94 408	93.16 205	94.95 260

WR-MVS		88.38 215	87.67 215	90.52 241	93.30 274	80.18 241	93.26 266	95.96 164	88.57 108	85.47 268	92.81 264	76.12 192	96.91 295	81.24 277	82.29 357	94.47 285

SSM_04072		88.57 212	87.92 209	90.51 242	94.76 184	82.66 164	79.84 452	94.64 267	85.18 213	88.96 184	95.00 170	76.00 195	92.03 422	83.74 230	93.15 206	96.85 174

MVSTER		88.84 201	88.29 199	90.51 242	92.95 292	80.44 235	93.73 241	95.01 238	84.66 236	87.15 221	93.12 254	72.79 251	97.21 273	87.86 164	87.36 306	93.87 309

testdata				90.49 244	96.40 96	77.89 308		95.37 218	72.51 421	93.63 72	96.69 81	82.08 114	97.65 219	83.08 237	97.39 96	95.94 217

test1111		89.10 191	88.64 186	90.48 245	95.53 143	74.97 358	96.08 64	84.89 439	88.13 123	90.16 162	96.65 85	63.29 358	98.10 172	86.14 190	96.90 108	98.39 41

tt0805		86.92 273	85.74 288	90.48 245	92.22 312	79.98 253	95.63 106	94.88 252	83.83 251	84.74 291	92.80 265	57.61 403	97.67 216	85.48 201	84.42 329	93.79 314

jajsoiax		88.24 220	87.50 218	90.48 245	90.89 369	80.14 243	95.31 119	95.65 194	84.97 225	84.24 310	94.02 218	65.31 344	97.42 247	88.56 155	88.52 285	93.89 305

PatchMatch-RL		86.77 281	85.54 290	90.47 248	95.88 124	82.71 162	90.54 354	92.31 341	79.82 339	84.32 307	91.57 314	68.77 311	96.39 329	73.16 367	93.48 196	92.32 376

tfpn200view9		87.58 244	86.64 245	90.41 249	95.99 119	78.64 284	94.58 174	91.98 353	86.94 163	88.09 200	91.77 302	69.18 305	98.10 172	70.13 388	91.10 238	94.48 283

VPNet		88.20 221	87.47 220	90.39 250	93.56 267	79.46 265	94.04 218	95.54 202	88.67 103	86.96 223	94.58 196	69.33 299	97.15 275	84.05 224	80.53 386	94.56 275

ACMH	80.38 17	85.36 314	83.68 331	90.39 250	94.45 213	80.63 229	94.73 166	94.85 254	82.09 292	77.24 401	92.65 269	60.01 387	97.58 226	72.25 372	84.87 326	92.96 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres100view900		87.63 239	86.71 241	90.38 252	96.12 106	78.55 287	95.03 145	91.58 364	87.15 154	88.06 203	92.29 281	68.91 309	98.10 172	70.13 388	91.10 238	94.48 283

mvs_tets		88.06 226	87.28 225	90.38 252	90.94 365	79.88 255	95.22 130	95.66 192	85.10 221	84.21 311	93.94 223	63.53 356	97.40 255	88.50 156	88.40 289	93.87 309

1314		87.51 247	86.57 250	90.34 254	92.42 309	79.74 260	92.63 294	95.35 220	78.35 363	80.14 373	91.62 310	74.05 230	97.15 275	81.05 278	93.53 192	94.12 295

LTVRE_ROB	82.13 13	86.26 298	84.90 308	90.34 254	94.44 214	81.50 194	92.31 308	94.89 250	83.03 273	79.63 383	92.67 268	69.69 293	97.79 208	71.20 377	86.26 315	91.72 386
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
test_djsdf		89.03 197	88.64 186	90.21 256	90.74 376	79.28 274	95.96 77	95.90 170	84.66 236	85.33 280	92.94 259	74.02 231	97.30 262	89.64 139	88.53 284	94.05 301

v2v482		87.84 229	87.06 229	90.17 257	90.99 361	79.23 277	94.00 224	95.13 231	84.87 228	85.53 263	92.07 293	74.45 222	97.45 242	84.71 216	81.75 365	93.85 312

pmmvs4		85.43 312	83.86 329	90.16 258	90.02 394	82.97 153	90.27 357	92.67 332	75.93 388	80.73 364	91.74 304	71.05 269	95.73 363	78.85 312	83.46 343	91.78 385

V42		87.68 234	86.86 234	90.15 259	90.58 381	80.14 243	94.24 202	95.28 225	83.66 255	85.67 258	91.33 316	74.73 216	97.41 253	84.43 220	81.83 363	92.89 357

MSDG		84.86 327	83.09 340	90.14 260	93.80 252	80.05 248	89.18 386	93.09 319	78.89 351	78.19 393	91.91 299	65.86 342	97.27 266	68.47 397	88.45 287	93.11 349

sc_t1		81.53 366	78.67 387	90.12 261	90.78 373	78.64 284	93.91 232	90.20 396	68.42 436	80.82 363	89.88 366	46.48 441	96.76 300	76.03 343	71.47 425	94.96 256

anonymousdsp		87.84 229	87.09 228	90.12 261	89.13 405	80.54 233	94.67 170	95.55 200	82.05 293	83.82 318	92.12 287	71.47 266	97.15 275	87.15 177	87.80 301	92.67 363

thres200		87.21 263	86.24 264	90.12 261	95.36 147	78.53 288	93.26 266	92.10 347	86.42 177	88.00 205	91.11 327	69.24 304	98.00 189	69.58 392	91.04 244	93.83 313

CR-MVSNet		85.35 315	83.76 330	90.12 261	90.58 381	79.34 270	85.24 430	91.96 355	78.27 365	85.55 261	87.87 402	71.03 270	95.61 366	73.96 362	89.36 273	95.40 239

v1144		87.61 242	86.79 239	90.06 265	91.01 360	79.34 270	93.95 227	95.42 215	83.36 266	85.66 259	91.31 319	74.98 212	97.42 247	83.37 234	82.06 359	93.42 335

XXY-MVS		87.65 236	86.85 235	90.03 266	92.14 315	80.60 231	93.76 239	95.23 227	82.94 276	84.60 293	94.02 218	74.27 224	95.49 373	81.04 279	83.68 339	94.01 303

Vis-MVSNet (Re-imp)		89.59 173	89.44 160	90.03 266	95.74 129	75.85 349	95.61 107	90.80 387	87.66 143	87.83 209	95.40 150	76.79 183	96.46 325	78.37 314	96.73 114	97.80 103

test2506		87.21 263	86.28 262	90.02 268	95.62 138	73.64 374	96.25 50	71.38 464	87.89 132	90.45 153	96.65 85	55.29 415	98.09 180	86.03 194	96.94 106	98.33 46

BH-untuned		88.60 209	88.13 203	90.01 269	95.24 155	78.50 290	93.29 264	94.15 289	84.75 233	84.46 299	93.40 241	75.76 201	97.40 255	77.59 324	94.52 171	94.12 295

v1192		87.25 259	86.33 259	90.00 270	90.76 375	79.04 278	93.80 237	95.48 205	82.57 283	85.48 267	91.18 323	73.38 245	97.42 247	82.30 253	82.06 359	93.53 329

v7n		86.81 276	85.76 286	89.95 271	90.72 377	79.25 276	95.07 142	95.92 167	84.45 239	82.29 343	90.86 334	72.60 255	97.53 230	79.42 307	80.52 387	93.08 351

testing91		87.11 268	86.18 265	89.92 272	94.43 215	75.38 357	91.53 330	92.27 343	86.48 174	86.50 235	90.24 352	61.19 379	97.53 230	82.10 258	90.88 246	96.84 177

IMVS_0404		87.60 243	86.84 236	89.89 273	93.72 256	77.75 316	88.56 395	95.34 221	85.53 203	79.98 377	94.49 198	66.54 335	94.64 387	84.75 211	92.65 218	97.28 132

v8		87.50 249	86.71 241	89.89 273	91.37 345	79.40 267	94.50 179	95.38 216	84.81 231	83.60 326	91.33 316	76.05 193	97.42 247	82.84 243	80.51 388	92.84 359

v10		87.25 259	86.38 256	89.85 275	91.19 351	79.50 263	94.48 180	95.45 210	83.79 253	83.62 325	91.19 321	75.13 209	97.42 247	81.94 263	80.60 383	92.63 365

baseline2		86.50 291	85.39 294	89.84 276	91.12 356	76.70 337	91.88 320	88.58 419	82.35 288	79.95 378	90.95 332	73.42 243	97.63 222	80.27 295	89.95 261	95.19 246

pm-mvs1		86.61 285	85.54 290	89.82 277	91.44 340	80.18 241	95.28 125	94.85 254	83.84 250	81.66 352	92.62 270	72.45 258	96.48 322	79.67 301	78.06 403	92.82 360

TR-MVS		86.78 278	85.76 286	89.82 277	94.37 218	78.41 292	92.47 299	92.83 326	81.11 325	86.36 241	92.40 276	68.73 312	97.48 237	73.75 365	89.85 264	93.57 328

ACMH+	81.04 14	85.05 322	83.46 334	89.82 277	94.66 195	79.37 268	94.44 185	94.12 292	82.19 291	78.04 395	92.82 263	58.23 400	97.54 229	73.77 364	82.90 351	92.54 366

EI-MVSNet		89.10 191	88.86 183	89.80 280	91.84 327	78.30 296	93.70 244	95.01 238	85.73 194	87.15 221	95.28 156	79.87 140	97.21 273	83.81 228	87.36 306	93.88 308

v144192		87.19 265	86.35 258	89.74 281	90.64 379	78.24 298	93.92 230	95.43 213	81.93 298	85.51 265	91.05 330	74.21 227	97.45 242	82.86 242	81.56 367	93.53 329

COLMAP_ROB	80.39 16	83.96 341	82.04 350	89.74 281	95.28 151	79.75 259	94.25 200	92.28 342	75.17 395	78.02 396	93.77 233	58.60 399	97.84 206	65.06 419	85.92 316	91.63 388
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SCA		86.32 297	85.18 301	89.73 283	92.15 314	76.60 338	91.12 341	91.69 360	83.53 260	85.50 266	88.81 385	66.79 328	96.48 322	76.65 333	90.35 253	96.12 208

IterMVS-LS		88.36 217	87.91 211	89.70 284	93.80 252	78.29 297	93.73 241	95.08 236	85.73 194	84.75 290	91.90 300	79.88 139	96.92 294	83.83 227	82.51 353	93.89 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
testing11		86.44 294	85.35 297	89.69 285	94.29 225	75.40 356	91.30 335	90.53 391	84.76 232	85.06 284	90.13 358	58.95 398	97.45 242	82.08 259	91.09 242	96.21 203

testing99		86.72 282	85.73 289	89.69 285	94.23 227	74.91 360	91.35 334	90.97 381	86.14 185	86.36 241	90.22 353	59.41 392	97.48 237	82.24 255	90.66 248	96.69 184

v1921920		86.97 272	86.06 272	89.69 285	90.53 384	78.11 301	93.80 237	95.43 213	81.90 300	85.33 280	91.05 330	72.66 252	97.41 253	82.05 261	81.80 364	93.53 329

icg_test_0407_2		89.15 189	88.97 176	89.68 288	93.72 256	77.75 316	88.26 400	95.34 221	85.53 203	88.34 197	94.49 198	77.69 175	93.99 398	84.75 211	92.65 218	97.28 132

VortexMVS		88.42 213	88.01 205	89.63 289	93.89 247	78.82 280	93.82 236	95.47 206	86.67 171	84.53 297	91.99 296	72.62 254	96.65 306	89.02 148	84.09 333	93.41 336

Fast-Effi-MVS+-dtu		87.44 250	86.72 240	89.63 289	92.04 319	77.68 321	94.03 219	93.94 295	85.81 191	82.42 342	91.32 318	70.33 284	97.06 284	80.33 294	90.23 255	94.14 294

v1240		86.78 278	85.85 281	89.56 291	90.45 386	77.79 313	93.61 247	95.37 218	81.65 310	85.43 272	91.15 325	71.50 265	97.43 246	81.47 274	82.05 361	93.47 333

Effi-MVS+-dtu		88.65 207	88.35 195	89.54 292	93.33 273	76.39 342	94.47 183	94.36 279	87.70 140	85.43 272	89.56 374	73.45 241	97.26 268	85.57 200	91.28 237	94.97 253

AllTest		83.42 348	81.39 354	89.52 293	95.01 165	77.79 313	93.12 270	90.89 385	77.41 372	76.12 410	93.34 242	54.08 421	97.51 232	68.31 399	84.27 331	93.26 339

TestCases				89.52 293	95.01 165	77.79 313		90.89 385	77.41 372	76.12 410	93.34 242	54.08 421	97.51 232	68.31 399	84.27 331	93.26 339

mvs_anonymous		89.37 186	89.32 165	89.51 295	93.47 269	74.22 367	91.65 328	94.83 256	82.91 277	85.45 269	93.79 231	81.23 126	96.36 332	86.47 186	94.09 180	97.94 89

XVG-ACMP-BASELINE		86.00 300	84.84 310	89.45 296	91.20 350	78.00 303	91.70 326	95.55 200	85.05 223	82.97 336	92.25 283	54.49 419	97.48 237	82.93 240	87.45 305	92.89 357

testing222		84.84 328	83.32 335	89.43 297	94.15 233	75.94 347	91.09 342	89.41 417	84.90 226	85.78 255	89.44 375	52.70 426	96.28 336	70.80 383	91.57 234	96.07 212

MVP-Stereo		85.97 301	84.86 309	89.32 298	90.92 367	82.19 178	92.11 315	94.19 286	78.76 356	78.77 392	91.63 309	68.38 316	96.56 316	75.01 352	93.95 182	89.20 426
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PatchmatchNet		85.85 304	84.70 312	89.29 299	91.76 331	75.54 353	88.49 396	91.30 372	81.63 312	85.05 285	88.70 389	71.71 262	96.24 337	74.61 357	89.05 279	96.08 211
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v148		87.04 270	86.32 260	89.21 300	90.94 365	77.26 326	93.71 243	94.43 274	84.84 230	84.36 305	90.80 338	76.04 194	97.05 286	82.12 257	79.60 397	93.31 338

tfpnnormal		84.72 330	83.23 338	89.20 301	92.79 299	80.05 248	94.48 180	95.81 178	82.38 286	81.08 360	91.21 320	69.01 308	96.95 292	61.69 430	80.59 384	90.58 413

cl22		86.78 278	85.98 275	89.18 302	92.34 310	77.62 322	90.84 347	94.13 291	81.33 319	83.97 316	90.15 357	73.96 232	96.60 313	84.19 222	82.94 348	93.33 337

BH-w/o		87.57 245	87.05 230	89.12 303	94.90 177	77.90 307	92.41 300	93.51 310	82.89 278	83.70 322	91.34 315	75.75 202	97.07 283	75.49 345	93.49 194	92.39 373

WR-MVS_H		87.80 231	87.37 222	89.10 304	93.23 275	78.12 300	95.61 107	97.30 32	87.90 130	83.72 321	92.01 295	79.65 148	96.01 347	76.36 337	80.54 385	93.16 347

miper_enhance_ethall		86.90 274	86.18 265	89.06 305	91.66 336	77.58 323	90.22 363	94.82 257	79.16 347	84.48 298	89.10 379	79.19 153	96.66 305	84.06 223	82.94 348	92.94 355

c3_l		87.14 267	86.50 254	89.04 306	92.20 313	77.26 326	91.22 340	94.70 264	82.01 296	84.34 306	90.43 349	78.81 156	96.61 311	83.70 232	81.09 374	93.25 341

miper_ehance_all_eth		87.22 262	86.62 248	89.02 307	92.13 316	77.40 325	90.91 346	94.81 258	81.28 320	84.32 307	90.08 360	79.26 151	96.62 308	83.81 228	82.94 348	93.04 352

gg-mvs-nofinetune		81.77 360	79.37 375	88.99 308	90.85 371	77.73 320	86.29 422	79.63 452	74.88 400	83.19 335	69.05 455	60.34 384	96.11 342	75.46 346	94.64 167	93.11 349

ETVMVS		84.43 335	82.92 344	88.97 309	94.37 218	74.67 361	91.23 339	88.35 421	83.37 265	86.06 250	89.04 380	55.38 413	95.67 365	67.12 406	91.34 236	96.58 188

pmmvs6		83.42 348	81.60 352	88.87 310	88.01 420	77.87 309	94.96 148	94.24 285	74.67 401	78.80 391	91.09 328	60.17 386	96.49 321	77.06 332	75.40 417	92.23 378

test_cas_vis1_n_1920		88.83 204	88.85 184	88.78 311	91.15 355	76.72 336	93.85 235	94.93 248	83.23 270	92.81 92	96.00 115	61.17 380	94.45 388	91.67 109	94.84 159	95.17 247

MIMVSNet		82.59 354	80.53 359	88.76 312	91.51 338	78.32 295	86.57 421	90.13 399	79.32 343	80.70 365	88.69 390	52.98 425	93.07 414	66.03 414	88.86 281	94.90 261

cl____		86.52 290	85.78 283	88.75 313	92.03 320	76.46 340	90.74 348	94.30 281	81.83 306	83.34 332	90.78 339	75.74 204	96.57 314	81.74 269	81.54 368	93.22 343

DIV-MVS_self_test		86.53 289	85.78 283	88.75 313	92.02 321	76.45 341	90.74 348	94.30 281	81.83 306	83.34 332	90.82 337	75.75 202	96.57 314	81.73 270	81.52 369	93.24 342

CP-MVSNet		87.63 239	87.26 227	88.74 315	93.12 280	76.59 339	95.29 123	96.58 104	88.43 111	83.49 329	92.98 258	75.28 208	95.83 356	78.97 310	81.15 373	93.79 314

eth_miper_zixun_eth		86.50 291	85.77 285	88.68 316	91.94 322	75.81 350	90.47 355	94.89 250	82.05 293	84.05 313	90.46 348	75.96 197	96.77 299	82.76 246	79.36 399	93.46 334

CHOSEN 280x420		85.15 320	83.99 327	88.65 317	92.47 306	78.40 293	79.68 454	92.76 329	74.90 399	81.41 356	89.59 372	69.85 292	95.51 370	79.92 299	95.29 149	92.03 381

PS-CasMVS		87.32 256	86.88 233	88.63 318	92.99 290	76.33 344	95.33 118	96.61 102	88.22 119	83.30 334	93.07 256	73.03 249	95.79 360	78.36 315	81.00 379	93.75 321

TransMVSNet (Re)		84.43 335	83.06 342	88.54 319	91.72 332	78.44 291	95.18 136	92.82 328	82.73 281	79.67 382	92.12 287	73.49 240	95.96 349	71.10 381	68.73 436	91.21 400

tt0320-xc		79.63 389	76.66 398	88.52 320	91.03 359	78.72 281	93.00 279	89.53 416	66.37 440	76.11 412	87.11 413	46.36 443	95.32 378	72.78 369	67.67 437	91.51 392

EG-PatchMatch MVS		82.37 356	80.34 362	88.46 321	90.27 388	79.35 269	92.80 291	94.33 280	77.14 376	73.26 428	90.18 356	47.47 438	96.72 301	70.25 385	87.32 308	89.30 423

PEN-MVS		86.80 277	86.27 263	88.40 322	92.32 311	75.71 352	95.18 136	96.38 119	87.97 127	82.82 338	93.15 252	73.39 244	95.92 351	76.15 341	79.03 402	93.59 327

Baseline_NR-MVSNet		87.07 269	86.63 247	88.40 322	91.44 340	77.87 309	94.23 203	92.57 334	84.12 244	85.74 257	92.08 291	77.25 179	96.04 343	82.29 254	79.94 392	91.30 398

UBG		85.51 310	84.57 317	88.35 324	94.21 229	71.78 399	90.07 368	89.66 412	82.28 289	85.91 253	89.01 381	61.30 374	97.06 284	76.58 336	92.06 231	96.22 201

D2MVS		85.90 302	85.09 303	88.35 324	90.79 372	77.42 324	91.83 322	95.70 188	80.77 328	80.08 375	90.02 362	66.74 330	96.37 330	81.88 265	87.97 296	91.26 399

pmmvs5		84.21 337	82.84 347	88.34 326	88.95 407	76.94 332	92.41 300	91.91 357	75.63 390	80.28 370	91.18 323	64.59 350	95.57 367	77.09 331	83.47 342	92.53 367

mamv4		90.92 128	91.78 103	88.33 327	95.67 134	70.75 412	92.92 284	96.02 159	81.90 300	88.11 199	95.34 154	85.88 52	96.97 290	95.22 38	95.01 154	97.26 136

tt0320		80.13 382	77.41 391	88.29 328	90.50 385	78.02 302	93.10 273	90.71 389	66.06 443	76.75 405	86.97 414	49.56 433	95.40 375	71.65 373	71.41 426	91.46 395

LCM-MVSNet-Re		88.30 219	88.32 198	88.27 329	94.71 192	72.41 394	93.15 269	90.98 380	87.77 137	79.25 386	91.96 297	78.35 165	95.75 361	83.04 238	95.62 138	96.65 185

CostFormer		85.77 307	84.94 307	88.26 330	91.16 354	72.58 392	89.47 381	91.04 379	76.26 385	86.45 239	89.97 364	70.74 275	96.86 298	82.35 252	87.07 311	95.34 243

ITE_SJBPF				88.24 331	91.88 326	77.05 329		92.92 323	85.54 201	80.13 374	93.30 246	57.29 404	96.20 338	72.46 371	84.71 327	91.49 393

PVSNet	78.82 18	85.55 309	84.65 313	88.23 332	94.72 190	71.93 395	87.12 417	92.75 330	78.80 355	84.95 287	90.53 346	64.43 351	96.71 303	74.74 355	93.86 184	96.06 214

IterMVS-SCA-FT		85.45 311	84.53 318	88.18 333	91.71 333	76.87 333	90.19 365	92.65 333	85.40 210	81.44 355	90.54 345	66.79 328	95.00 384	81.04 279	81.05 375	92.66 364

EPNet_dtu		86.49 293	85.94 278	88.14 334	90.24 389	72.82 384	94.11 209	92.20 345	86.66 172	79.42 385	92.36 278	73.52 239	95.81 358	71.26 376	93.66 188	95.80 226
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Patchmtry		82.71 352	80.93 358	88.06 335	90.05 393	76.37 343	84.74 435	91.96 355	72.28 424	81.32 358	87.87 402	71.03 270	95.50 372	68.97 394	80.15 390	92.32 376

test_vis1_n_1920		89.39 185	89.84 148	88.04 336	92.97 291	72.64 389	94.71 168	96.03 158	86.18 183	91.94 121	96.56 93	61.63 369	95.74 362	93.42 59	95.11 153	95.74 228

DTE-MVSNet		86.11 299	85.48 292	87.98 337	91.65 337	74.92 359	94.93 150	95.75 183	87.36 149	82.26 344	93.04 257	72.85 250	95.82 357	74.04 360	77.46 408	93.20 345

PMMVS		85.71 308	84.96 306	87.95 338	88.90 408	77.09 328	88.68 393	90.06 401	72.32 423	86.47 236	90.76 340	72.15 260	94.40 390	81.78 268	93.49 194	92.36 374

GG-mvs-BLEND				87.94 339	89.73 400	77.91 306	87.80 406	78.23 457		80.58 367	83.86 432	59.88 388	95.33 377	71.20 377	92.22 229	90.60 412

MonoMVSNet		86.89 275	86.55 251	87.92 340	89.46 403	73.75 371	94.12 207	93.10 318	87.82 136	85.10 283	90.76 340	69.59 295	94.94 385	86.47 186	82.50 354	95.07 250

reproduce_monomvs		86.37 296	85.87 280	87.87 341	93.66 264	73.71 372	93.44 254	95.02 237	88.61 106	82.64 341	91.94 298	57.88 402	96.68 304	89.96 134	79.71 396	93.22 343

pmmvs-eth3d		80.97 375	78.72 386	87.74 342	84.99 438	79.97 254	90.11 367	91.65 362	75.36 392	73.51 426	86.03 421	59.45 391	93.96 401	75.17 349	72.21 422	89.29 425

MS-PatchMatch		85.05 322	84.16 322	87.73 343	91.42 343	78.51 289	91.25 338	93.53 309	77.50 371	80.15 372	91.58 312	61.99 366	95.51 370	75.69 344	94.35 176	89.16 427

mmtdpeth		85.04 324	84.15 323	87.72 344	93.11 281	75.74 351	94.37 194	92.83 326	84.98 224	89.31 177	86.41 418	61.61 371	97.14 278	92.63 75	62.11 447	90.29 414

test_0402		81.30 371	79.17 380	87.67 345	93.19 276	78.17 299	92.98 281	91.71 358	75.25 394	76.02 413	90.31 351	59.23 393	96.37 330	50.22 450	83.63 340	88.47 435

IterMVS		84.88 326	83.98 328	87.60 346	91.44 340	76.03 346	90.18 366	92.41 336	83.24 269	81.06 361	90.42 350	66.60 331	94.28 394	79.46 303	80.98 380	92.48 368
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Patchmatch-test		81.37 369	79.30 376	87.58 347	90.92 367	74.16 369	80.99 447	87.68 426	70.52 431	76.63 407	88.81 385	71.21 267	92.76 417	60.01 436	86.93 312	95.83 224

EPMVS		83.90 344	82.70 348	87.51 348	90.23 390	72.67 387	88.62 394	81.96 447	81.37 318	85.01 286	88.34 393	66.31 336	94.45 388	75.30 348	87.12 309	95.43 238

ADS-MVSNet2		81.66 363	79.71 372	87.50 349	91.35 346	74.19 368	83.33 440	88.48 420	72.90 418	82.24 345	85.77 424	64.98 346	93.20 412	64.57 421	83.74 337	95.12 248

OurMVSNet-221017-0		85.35 315	84.64 315	87.49 350	90.77 374	72.59 391	94.01 222	94.40 277	84.72 234	79.62 384	93.17 251	61.91 367	96.72 301	81.99 262	81.16 371	93.16 347

tpm2		84.08 339	82.94 343	87.48 351	91.39 344	71.27 404	89.23 385	90.37 393	71.95 425	84.64 292	89.33 376	67.30 320	96.55 318	75.17 349	87.09 310	94.63 269

RPSCF		85.07 321	84.27 319	87.48 351	92.91 294	70.62 414	91.69 327	92.46 335	76.20 386	82.67 340	95.22 159	63.94 354	97.29 265	77.51 326	85.80 317	94.53 276

myMVS_eth3d28		85.80 306	85.26 300	87.42 353	94.73 188	69.92 419	90.60 352	90.95 382	87.21 153	86.06 250	90.04 361	59.47 390	96.02 345	74.89 354	93.35 201	96.33 195

WBMVS		84.97 325	84.18 321	87.34 354	94.14 234	71.62 403	90.20 364	92.35 338	81.61 313	84.06 312	90.76 340	61.82 368	96.52 319	78.93 311	83.81 335	93.89 305

miper_lstm_enhance		85.27 318	84.59 316	87.31 355	91.28 349	74.63 362	87.69 411	94.09 293	81.20 324	81.36 357	89.85 368	74.97 213	94.30 393	81.03 281	79.84 395	93.01 353

FMVSNet5		81.52 367	79.60 373	87.27 356	91.17 352	77.95 304	91.49 331	92.26 344	76.87 378	76.16 409	87.91 401	51.67 427	92.34 420	67.74 403	81.16 371	91.52 391

USDC		82.76 351	81.26 356	87.26 357	91.17 352	74.55 363	89.27 383	93.39 312	78.26 366	75.30 417	92.08 291	54.43 420	96.63 307	71.64 374	85.79 318	90.61 410

test-LLR		85.87 303	85.41 293	87.25 358	90.95 363	71.67 401	89.55 377	89.88 408	83.41 263	84.54 295	87.95 399	67.25 321	95.11 381	81.82 266	93.37 199	94.97 253

test-mter		84.54 334	83.64 332	87.25 358	90.95 363	71.67 401	89.55 377	89.88 408	79.17 346	84.54 295	87.95 399	55.56 410	95.11 381	81.82 266	93.37 199	94.97 253

JIA-IIPM		81.04 372	78.98 384	87.25 358	88.64 409	73.48 376	81.75 446	89.61 414	73.19 415	82.05 348	73.71 451	66.07 341	95.87 354	71.18 379	84.60 328	92.41 372

TDRefinement		79.81 386	77.34 392	87.22 361	79.24 454	75.48 354	93.12 270	92.03 350	76.45 381	75.01 418	91.58 312	49.19 434	96.44 326	70.22 387	69.18 433	89.75 419

tpmvs		83.35 350	82.07 349	87.20 362	91.07 358	71.00 410	88.31 399	91.70 359	78.91 349	80.49 369	87.18 411	69.30 302	97.08 281	68.12 402	83.56 341	93.51 332

ppachtmachnet_test		81.84 359	80.07 367	87.15 363	88.46 413	74.43 366	89.04 389	92.16 346	75.33 393	77.75 398	88.99 382	66.20 338	95.37 376	65.12 418	77.60 406	91.65 387

dmvs_re		84.20 338	83.22 339	87.14 364	91.83 329	77.81 311	90.04 369	90.19 397	84.70 235	81.49 353	89.17 378	64.37 352	91.13 433	71.58 375	85.65 319	92.46 370

tpm cat1		81.96 357	80.27 363	87.01 365	91.09 357	71.02 409	87.38 415	91.53 367	66.25 441	80.17 371	86.35 420	68.22 317	96.15 341	69.16 393	82.29 357	93.86 311

test_fmvs1_n		87.03 271	87.04 231	86.97 366	89.74 399	71.86 396	94.55 176	94.43 274	78.47 360	91.95 120	95.50 145	51.16 429	93.81 402	93.02 67	94.56 169	95.26 244

OpenMVS_ROB	74.94 19	79.51 390	77.03 397	86.93 367	87.00 426	76.23 345	92.33 306	90.74 388	68.93 435	74.52 422	88.23 396	49.58 432	96.62 308	57.64 442	84.29 330	87.94 438

SixPastTwentyTwo		83.91 343	82.90 345	86.92 368	90.99 361	70.67 413	93.48 251	91.99 352	85.54 201	77.62 400	92.11 289	60.59 383	96.87 297	76.05 342	77.75 405	93.20 345

ADS-MVSNet		81.56 365	79.78 369	86.90 369	91.35 346	71.82 397	83.33 440	89.16 418	72.90 418	82.24 345	85.77 424	64.98 346	93.76 403	64.57 421	83.74 337	95.12 248

PatchT		82.68 353	81.27 355	86.89 370	90.09 392	70.94 411	84.06 437	90.15 398	74.91 398	85.63 260	83.57 434	69.37 298	94.87 386	65.19 416	88.50 286	94.84 263

tpm		84.73 329	84.02 326	86.87 371	90.33 387	68.90 422	89.06 388	89.94 405	80.85 327	85.75 256	89.86 367	68.54 314	95.97 348	77.76 322	84.05 334	95.75 227

Patchmatch-RL test		81.67 362	79.96 368	86.81 372	85.42 436	71.23 405	82.17 445	87.50 427	78.47 360	77.19 402	82.50 441	70.81 274	93.48 407	82.66 247	72.89 421	95.71 231

test_vis1_n		86.56 288	86.49 255	86.78 373	88.51 410	72.69 386	94.68 169	93.78 305	79.55 342	90.70 148	95.31 155	48.75 435	93.28 410	93.15 63	93.99 181	94.38 287

testing3-2		86.72 282	86.71 241	86.74 374	96.11 109	65.92 434	93.39 256	89.65 413	89.46 70	87.84 208	92.79 266	59.17 395	97.60 224	81.31 275	90.72 247	96.70 183

test_fmvs1		87.34 254	87.56 217	86.68 375	90.59 380	71.80 398	94.01 222	94.04 294	78.30 364	91.97 118	95.22 159	56.28 408	93.71 404	92.89 68	94.71 162	94.52 277

MDA-MVSNet-bldmvs		78.85 395	76.31 400	86.46 376	89.76 398	73.88 370	88.79 391	90.42 392	79.16 347	59.18 451	88.33 394	60.20 385	94.04 396	62.00 429	68.96 434	91.48 394

mvs5depth		80.98 374	79.15 381	86.45 377	84.57 439	73.29 379	87.79 407	91.67 361	80.52 330	82.20 347	89.72 370	55.14 416	95.93 350	73.93 363	66.83 439	90.12 416

tpmrst		85.35 315	84.99 304	86.43 378	90.88 370	67.88 427	88.71 392	91.43 370	80.13 334	86.08 249	88.80 387	73.05 248	96.02 345	82.48 248	83.40 345	95.40 239

TESTMET0.1,1		83.74 346	82.85 346	86.42 379	89.96 395	71.21 406	89.55 377	87.88 423	77.41 372	83.37 331	87.31 407	56.71 406	93.65 406	80.62 289	92.85 215	94.40 286

our_test_3		81.93 358	80.46 361	86.33 380	88.46 413	73.48 376	88.46 397	91.11 375	76.46 380	76.69 406	88.25 395	66.89 326	94.36 391	68.75 395	79.08 401	91.14 402

lessismore_v0				86.04 381	88.46 413	68.78 423		80.59 450		73.01 429	90.11 359	55.39 412	96.43 327	75.06 351	65.06 442	92.90 356

TinyColmap		79.76 387	77.69 390	85.97 382	91.71 333	73.12 380	89.55 377	90.36 394	75.03 396	72.03 432	90.19 355	46.22 444	96.19 340	63.11 425	81.03 376	88.59 434

KD-MVS_2432*1600		78.50 396	76.02 404	85.93 383	86.22 429	74.47 364	84.80 433	92.33 339	79.29 344	76.98 403	85.92 422	53.81 423	93.97 399	67.39 404	57.42 452	89.36 421

miper_refine_blended		78.50 396	76.02 404	85.93 383	86.22 429	74.47 364	84.80 433	92.33 339	79.29 344	76.98 403	85.92 422	53.81 423	93.97 399	67.39 404	57.42 452	89.36 421

K. test v3		81.59 364	80.15 366	85.91 385	89.89 397	69.42 421	92.57 296	87.71 425	85.56 200	73.44 427	89.71 371	55.58 409	95.52 369	77.17 329	69.76 430	92.78 361

SSC-MVS3.2		84.60 333	84.19 320	85.85 386	92.74 301	68.07 424	88.15 402	93.81 303	87.42 147	83.76 320	91.07 329	62.91 361	95.73 363	74.56 358	83.24 346	93.75 321

mvsany_test1		85.42 313	85.30 298	85.77 387	87.95 422	75.41 355	87.61 414	80.97 449	76.82 379	88.68 190	95.83 128	77.44 178	90.82 435	85.90 195	86.51 313	91.08 406

MIMVSNet1		79.38 391	77.28 393	85.69 388	86.35 428	73.67 373	91.61 329	92.75 330	78.11 369	72.64 430	88.12 397	48.16 436	91.97 426	60.32 433	77.49 407	91.43 396

UWE-MVS		83.69 347	83.09 340	85.48 389	93.06 285	65.27 439	90.92 345	86.14 431	79.90 337	86.26 245	90.72 343	57.17 405	95.81 358	71.03 382	92.62 223	95.35 242

UnsupCasMVSNet_eth		80.07 383	78.27 389	85.46 390	85.24 437	72.63 390	88.45 398	94.87 253	82.99 275	71.64 435	88.07 398	56.34 407	91.75 428	73.48 366	63.36 445	92.01 382

CL-MVSNet_self_test		81.74 361	80.53 359	85.36 391	85.96 431	72.45 393	90.25 359	93.07 320	81.24 322	79.85 381	87.29 408	70.93 272	92.52 418	66.95 407	69.23 432	91.11 404

MDA-MVSNet_test_wron		79.21 393	77.19 395	85.29 392	88.22 417	72.77 385	85.87 424	90.06 401	74.34 403	62.62 448	87.56 405	66.14 339	91.99 425	66.90 411	73.01 419	91.10 405

YYNet1		79.22 392	77.20 394	85.28 393	88.20 418	72.66 388	85.87 424	90.05 403	74.33 404	62.70 446	87.61 404	66.09 340	92.03 422	66.94 408	72.97 420	91.15 401

WB-MVSnew		83.77 345	83.28 336	85.26 394	91.48 339	71.03 408	91.89 319	87.98 422	78.91 349	84.78 289	90.22 353	69.11 307	94.02 397	64.70 420	90.44 250	90.71 408

dp		81.47 368	80.23 364	85.17 395	89.92 396	65.49 437	86.74 419	90.10 400	76.30 384	81.10 359	87.12 412	62.81 362	95.92 351	68.13 401	79.88 393	94.09 298

UnsupCasMVSNet_bld		76.23 406	73.27 410	85.09 396	83.79 441	72.92 382	85.65 427	93.47 311	71.52 426	68.84 441	79.08 446	49.77 431	93.21 411	66.81 412	60.52 449	89.13 429

SD_0403		84.71 331	84.65 313	84.92 397	92.95 292	65.95 433	92.07 318	93.23 315	83.82 252	79.03 387	93.73 236	73.90 233	92.91 416	63.02 427	90.05 257	95.89 220

Anonymous20231206		81.03 373	79.77 371	84.82 398	87.85 423	70.26 416	91.42 332	92.08 348	73.67 410	77.75 398	89.25 377	62.43 364	93.08 413	61.50 431	82.00 362	91.12 403

FE-MVSNET		78.19 398	76.03 403	84.69 399	83.70 442	73.31 378	90.58 353	90.00 404	77.11 377	71.91 433	85.47 426	55.53 411	91.94 427	59.69 437	70.24 428	88.83 431

test0.0.03 1		82.41 355	81.69 351	84.59 400	88.23 416	72.89 383	90.24 361	87.83 424	83.41 263	79.86 380	89.78 369	67.25 321	88.99 445	65.18 417	83.42 344	91.90 384

CMPMVS	59.16 21	80.52 377	79.20 379	84.48 401	83.98 440	67.63 430	89.95 372	93.84 302	64.79 445	66.81 443	91.14 326	57.93 401	95.17 379	76.25 339	88.10 292	90.65 409
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		84.69 332	84.79 311	84.37 402	91.84 327	64.92 440	93.70 244	91.47 369	66.19 442	86.16 248	95.28 156	67.18 323	93.33 409	80.89 284	90.42 252	94.88 262

PVSNet_0	73.20 20	77.22 402	74.83 408	84.37 402	90.70 378	71.10 407	83.09 442	89.67 411	72.81 420	73.93 425	83.13 436	60.79 382	93.70 405	68.54 396	50.84 457	88.30 436

LF4IMVS		80.37 380	79.07 383	84.27 404	86.64 427	69.87 420	89.39 382	91.05 378	76.38 382	74.97 419	90.00 363	47.85 437	94.25 395	74.55 359	80.82 382	88.69 433

Anonymous20240521		80.44 379	79.21 378	84.11 405	85.75 434	67.89 426	92.86 287	93.23 315	75.61 391	75.59 416	87.47 406	50.03 430	94.33 392	71.14 380	81.21 370	90.12 416

PM-MVS		78.11 399	76.12 402	84.09 406	83.54 443	70.08 417	88.97 390	85.27 438	79.93 336	74.73 421	86.43 417	34.70 455	93.48 407	79.43 306	72.06 423	88.72 432

test_fmvs2		83.98 340	84.03 325	83.83 407	87.16 425	67.53 431	93.93 229	92.89 324	77.62 370	86.89 229	93.53 239	47.18 439	92.02 424	90.54 128	86.51 313	91.93 383

testgi		80.94 376	80.20 365	83.18 408	87.96 421	66.29 432	91.28 336	90.70 390	83.70 254	78.12 394	92.84 261	51.37 428	90.82 435	63.34 424	82.46 355	92.43 371

KD-MVS_self_test		80.20 381	79.24 377	83.07 409	85.64 435	65.29 438	91.01 344	93.93 296	78.71 358	76.32 408	86.40 419	59.20 394	92.93 415	72.59 370	69.35 431	91.00 407

testing3		80.46 378	79.59 374	83.06 410	93.44 271	64.64 441	93.33 258	85.47 436	84.34 241	79.93 379	90.84 336	44.35 447	92.39 419	57.06 444	87.56 302	92.16 380

ambc				83.06 410	79.99 452	63.51 445	77.47 455	92.86 325		74.34 424	84.45 431	28.74 456	95.06 383	73.06 368	68.89 435	90.61 410

test20.03		79.95 385	79.08 382	82.55 412	85.79 433	67.74 429	91.09 342	91.08 376	81.23 323	74.48 423	89.96 365	61.63 369	90.15 437	60.08 434	76.38 413	89.76 418

MVStest1		72.91 410	69.70 415	82.54 413	78.14 455	73.05 381	88.21 401	86.21 430	60.69 449	64.70 444	90.53 346	46.44 442	85.70 452	58.78 440	53.62 454	88.87 430

test_vis1_rt		77.96 400	76.46 399	82.48 414	85.89 432	71.74 400	90.25 359	78.89 453	71.03 430	71.30 436	81.35 443	42.49 449	91.05 434	84.55 218	82.37 356	84.65 441

EU-MVSNet		81.32 370	80.95 357	82.42 415	88.50 412	63.67 444	93.32 259	91.33 371	64.02 446	80.57 368	92.83 262	61.21 378	92.27 421	76.34 338	80.38 389	91.32 397

myMVS_eth3d		79.67 388	78.79 385	82.32 416	91.92 323	64.08 442	89.75 375	87.40 428	81.72 308	78.82 389	87.20 409	45.33 445	91.29 431	59.09 439	87.84 299	91.60 389

ttmdpeth		76.55 404	74.64 409	82.29 417	82.25 448	67.81 428	89.76 374	85.69 434	70.35 432	75.76 414	91.69 305	46.88 440	89.77 439	66.16 413	63.23 446	89.30 423

pmmvs3		71.81 413	68.71 416	81.11 418	75.86 457	70.42 415	86.74 419	83.66 442	58.95 452	68.64 442	80.89 444	36.93 453	89.52 441	63.10 426	63.59 444	83.39 442

Syy-MVS		80.07 383	79.78 369	80.94 419	91.92 323	59.93 451	89.75 375	87.40 428	81.72 308	78.82 389	87.20 409	66.29 337	91.29 431	47.06 452	87.84 299	91.60 389

UWE-MVS-28		78.98 394	78.38 388	80.80 420	88.18 419	60.66 450	90.65 350	78.51 454	78.84 353	77.93 397	90.93 333	59.08 396	89.02 444	50.96 449	90.33 254	92.72 362

new-patchmatchnet		76.41 405	75.17 407	80.13 421	82.65 447	59.61 452	87.66 412	91.08 376	78.23 367	69.85 439	83.22 435	54.76 417	91.63 430	64.14 423	64.89 443	89.16 427

mvsany_test3		74.95 407	73.26 411	80.02 422	74.61 458	63.16 446	85.53 428	78.42 455	74.16 405	74.89 420	86.46 416	36.02 454	89.09 443	82.39 251	66.91 438	87.82 439

test_fmvs3		77.67 401	77.16 396	79.22 423	79.52 453	61.14 448	92.34 305	91.64 363	73.98 407	78.86 388	86.59 415	27.38 459	87.03 447	88.12 161	75.97 415	89.50 420

DSMNet-mixed		76.94 403	76.29 401	78.89 424	83.10 445	56.11 460	87.78 408	79.77 451	60.65 450	75.64 415	88.71 388	61.56 372	88.34 446	60.07 435	89.29 275	92.21 379

EGC-MVSNET		61.97 421	56.37 426	78.77 425	89.63 401	73.50 375	89.12 387	82.79 444	0.21 471	1.24 472	84.80 429	39.48 450	90.04 438	44.13 454	75.94 416	72.79 453

new_pmnet		72.15 411	70.13 414	78.20 426	82.95 446	65.68 435	83.91 438	82.40 446	62.94 448	64.47 445	79.82 445	42.85 448	86.26 451	57.41 443	74.44 418	82.65 446

MVS-HIRNet		73.70 409	72.20 412	78.18 427	91.81 330	56.42 459	82.94 443	82.58 445	55.24 453	68.88 440	66.48 456	55.32 414	95.13 380	58.12 441	88.42 288	83.01 444

LCM-MVSNet		66.00 418	62.16 423	77.51 428	64.51 468	58.29 454	83.87 439	90.90 384	48.17 457	54.69 454	73.31 452	16.83 468	86.75 448	65.47 415	61.67 448	87.48 440

APD_test1		69.04 414	66.26 420	77.36 429	80.51 451	62.79 447	85.46 429	83.51 443	54.11 455	59.14 452	84.79 430	23.40 462	89.61 440	55.22 445	70.24 428	79.68 450

test_f		71.95 412	70.87 413	75.21 430	74.21 460	59.37 453	85.07 432	85.82 433	65.25 444	70.42 438	83.13 436	23.62 460	82.93 458	78.32 316	71.94 424	83.33 443

ANet_high		58.88 425	54.22 430	72.86 431	56.50 471	56.67 456	80.75 448	86.00 432	73.09 417	37.39 463	64.63 459	22.17 463	79.49 461	43.51 455	23.96 465	82.43 447

test_vis3_rt		65.12 419	62.60 421	72.69 432	71.44 461	60.71 449	87.17 416	65.55 465	63.80 447	53.22 455	65.65 458	14.54 469	89.44 442	76.65 333	65.38 441	67.91 456

FPMVS		64.63 420	62.55 422	70.88 433	70.80 462	56.71 455	84.42 436	84.42 440	51.78 456	49.57 456	81.61 442	23.49 461	81.48 459	40.61 459	76.25 414	74.46 452

dmvs_testset		74.57 408	75.81 406	70.86 434	87.72 424	40.47 469	87.05 418	77.90 459	82.75 280	71.15 437	85.47 426	67.98 318	84.12 456	45.26 453	76.98 412	88.00 437

N_pmnet		68.89 415	68.44 417	70.23 435	89.07 406	28.79 474	88.06 403	19.50 474	69.47 434	71.86 434	84.93 428	61.24 377	91.75 428	54.70 446	77.15 409	90.15 415

testf1		59.54 423	56.11 427	69.85 436	69.28 463	56.61 457	80.37 449	76.55 462	42.58 460	45.68 459	75.61 447	11.26 470	84.18 454	43.20 456	60.44 450	68.75 454

APD_test2		59.54 423	56.11 427	69.85 436	69.28 463	56.61 457	80.37 449	76.55 462	42.58 460	45.68 459	75.61 447	11.26 470	84.18 454	43.20 456	60.44 450	68.75 454

WB-MVS		67.92 416	67.49 418	69.21 438	81.09 449	41.17 468	88.03 404	78.00 458	73.50 412	62.63 447	83.11 438	63.94 354	86.52 449	25.66 464	51.45 456	79.94 449

PMMVS2		59.60 422	56.40 425	69.21 438	68.83 465	46.58 464	73.02 459	77.48 460	55.07 454	49.21 457	72.95 453	17.43 467	80.04 460	49.32 451	44.33 460	80.99 448

SSC-MVS		67.06 417	66.56 419	68.56 440	80.54 450	40.06 470	87.77 409	77.37 461	72.38 422	61.75 449	82.66 440	63.37 357	86.45 450	24.48 465	48.69 459	79.16 451

Gipuma		57.99 427	54.91 429	67.24 441	88.51 410	65.59 436	52.21 462	90.33 395	43.58 459	42.84 462	51.18 463	20.29 465	85.07 453	34.77 460	70.45 427	51.05 462
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	47.18 22	52.22 429	48.46 433	63.48 442	45.72 473	46.20 465	73.41 458	78.31 456	41.03 462	30.06 465	65.68 457	6.05 472	83.43 457	30.04 462	65.86 440	60.80 457
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
dongtai		58.82 426	58.24 424	60.56 443	83.13 444	45.09 467	82.32 444	48.22 473	67.61 438	61.70 450	69.15 454	38.75 451	76.05 462	32.01 461	41.31 461	60.55 458

MVE	39.65 23	43.39 431	38.59 437	57.77 444	56.52 470	48.77 463	55.38 461	58.64 469	29.33 465	28.96 466	52.65 462	4.68 473	64.62 466	28.11 463	33.07 463	59.93 459
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.52 430	48.47 432	56.66 445	52.26 472	18.98 476	41.51 464	81.40 448	10.10 466	44.59 461	75.01 450	28.51 457	68.16 463	53.54 447	49.31 458	82.83 445

DeepMVS_CX				56.31 446	74.23 459	51.81 462		56.67 470	44.85 458	48.54 458	75.16 449	27.87 458	58.74 468	40.92 458	52.22 455	58.39 460

kuosan		53.51 428	53.30 431	54.13 447	76.06 456	45.36 466	80.11 451	48.36 472	59.63 451	54.84 453	63.43 460	37.41 452	62.07 467	20.73 467	39.10 462	54.96 461

E-PMN		43.23 432	42.29 434	46.03 448	65.58 467	37.41 471	73.51 457	64.62 466	33.99 463	28.47 467	47.87 464	19.90 466	67.91 464	22.23 466	24.45 464	32.77 463

EMVS		42.07 433	41.12 435	44.92 449	63.45 469	35.56 473	73.65 456	63.48 467	33.05 464	26.88 468	45.45 465	21.27 464	67.14 465	19.80 468	23.02 466	32.06 464

tmp_tt		35.64 434	39.24 436	24.84 450	14.87 474	23.90 475	62.71 460	51.51 471	6.58 468	36.66 464	62.08 461	44.37 446	30.34 470	52.40 448	22.00 467	20.27 465

wuyk23d		21.27 436	20.48 439	23.63 451	68.59 466	36.41 472	49.57 463	6.85 475	9.37 467	7.89 469	4.46 471	4.03 474	31.37 469	17.47 469	16.07 468	3.12 466

test123		8.76 438	11.22 441	1.39 452	0.85 476	0.97 477	85.76 426	0.35 477	0.54 470	2.45 471	8.14 470	0.60 475	0.48 471	2.16 471	0.17 470	2.71 467

testmvs		8.92 437	11.52 440	1.12 453	1.06 475	0.46 478	86.02 423	0.65 476	0.62 469	2.74 470	9.52 469	0.31 476	0.45 472	2.38 470	0.39 469	2.46 468

mmdepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

monomultidepth		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

test_blank		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet_test		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

DCPMVS		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

cdsmvs_eth3d_5k		22.14 435	29.52 438	0.00 454	0.00 477	0.00 479	0.00 465	95.76 182	0.00 472	0.00 473	94.29 207	75.66 205	0.00 473	0.00 472	0.00 471	0.00 469

pcd_1.5k_mvsjas		6.64 440	8.86 443	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	79.70 143	0.00 473	0.00 472	0.00 471	0.00 469

sosnet-low-res		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

sosnet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uncertanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

Regformer		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

ab-mvs-re		7.82 439	10.43 442	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	93.88 228	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

uanet		0.00 441	0.00 444	0.00 454	0.00 477	0.00 479	0.00 465	0.00 478	0.00 472	0.00 473	0.00 472	0.00 477	0.00 473	0.00 472	0.00 471	0.00 469

WAC-MVS						64.08 442								59.14 438

FOURS1					98.86 1	85.54 69	98.29 1	97.49 8	89.79 61	96.29 27

PC_three_1452									82.47 284	97.09 16	97.07 66	92.72 1	98.04 186	92.70 74	99.02 12	98.86 12

test_one_0601					98.58 11	85.83 63		97.44 17	91.05 21	96.78 23	98.06 20	91.45 11

eth-test2					0.00 477

eth-test					0.00 477

ZD-MVS					98.15 36	86.62 33		97.07 55	83.63 256	94.19 58	96.91 72	87.57 31	99.26 46	91.99 99	98.44 53

RE-MVS-def			93.68 67		97.92 45	84.57 89	96.28 46	96.76 87	87.46 144	93.75 69	97.43 45	82.94 96		92.73 70	97.80 86	97.88 96

IU-MVS					98.77 5	86.00 52		96.84 77	81.26 321	97.26 12				95.50 34	99.13 3	99.03 8

test_241102_TWO								97.44 17	90.31 39	97.62 7	98.07 18	91.46 10	99.58 10	95.66 28	99.12 6	98.98 10

test_241102_ONE					98.77 5	85.99 54		97.44 17	90.26 45	97.71 2	97.96 29	92.31 4	99.38 31

9.14			94.47 30		97.79 54		96.08 64	97.44 17	86.13 187	95.10 48	97.40 47	88.34 22	99.22 48	93.25 62	98.70 34

save fliter					97.85 51	85.63 68	95.21 133	96.82 80	89.44 71

test_0728_THIRD									90.75 27	97.04 18	98.05 23	92.09 6	99.55 16	95.64 30	99.13 3	99.13 2

test0726					98.78 3	85.93 57	97.19 12	97.47 13	90.27 43	97.64 5	98.13 6	91.47 8

GSMVS																96.12 208

test_part2					98.55 12	87.22 19				96.40 26

sam_mvs1												71.70 263				96.12 208

sam_mvs												70.60 277

MTGPA								96.97 60

test_post1							88.00 405				9.81 468	69.31 301	95.53 368	76.65 333

test_post											10.29 467	70.57 281	95.91 353

patchmatchnet-post											83.76 433	71.53 264	96.48 322

MTMP							96.16 55	60.64 468

gm-plane-assit					89.60 402	68.00 425			77.28 375		88.99 382		97.57 227	79.44 305

test9_res														91.91 103	98.71 32	98.07 78

TEST9					97.53 63	86.49 37	94.07 215	96.78 84	81.61 313	92.77 94	96.20 102	87.71 28	99.12 57

test_8					97.49 65	86.30 45	94.02 221	96.76 87	81.86 304	92.70 98	96.20 102	87.63 29	99.02 67

agg_prior2														90.54 128	98.68 37	98.27 59

agg_prior					97.38 68	85.92 59		96.72 94		92.16 113			98.97 81

test_prior4						85.96 56	94.11 209

test_prior2							94.12 207		87.67 142	92.63 102	96.39 97	86.62 41		91.50 112	98.67 40

旧先验2							93.36 257		71.25 428	94.37 54			97.13 279	86.74 182

新几何2							93.11 272

旧先验1					96.79 81	81.81 188		95.67 190			96.81 78	86.69 39			97.66 92	96.97 164

无先验							93.28 265	96.26 133	73.95 408				99.05 61	80.56 290		96.59 187

原ACMM2							92.94 283

test222					96.55 90	81.70 190	92.22 311	95.01 238	68.36 437	90.20 158	96.14 107	80.26 134			97.80 86	96.05 215

testdata2													98.75 109	78.30 317

segment_acmp												87.16 36

testdata1							92.15 313		87.94 128

plane_prior7					94.70 193	82.74 159

plane_prior6					94.52 207	82.75 157						74.23 225

plane_prior5								96.22 138					98.12 170	88.15 158	89.99 258	94.63 269

plane_prior4											94.86 178

plane_prior3						82.75 157			90.26 45	86.91 226

plane_prior2							95.85 86		90.81 25

plane_prior1					94.59 200

plane_prior						82.73 160	95.21 133		89.66 66						89.88 263

n2								0.00 478

nn								0.00 478

door-mid								85.49 435

test11								96.57 105

door								85.33 437

HQP5-MVS						81.56 192

HQP-NCC					94.17 230		94.39 190		88.81 96	85.43 272

ACMP_Plane					94.17 230		94.39 190		88.81 96	85.43 272

BP-MVS														87.11 179

HQP4-MVS										85.43 272			97.96 196			94.51 279

HQP3-MVS								96.04 156							89.77 267

HQP2-MVS												73.83 236

NP-MVS					94.37 218	82.42 172					93.98 221

MDTV_nov1_ep13_2view						55.91 461	87.62 413		73.32 414	84.59 294		70.33 284		74.65 356		95.50 236

MDTV_nov1_ep13			83.56 333		91.69 335	69.93 418	87.75 410	91.54 366	78.60 359	84.86 288	88.90 384	69.54 296	96.03 344	70.25 385	88.93 280

ACMMP++_ref															87.47 303

ACMMP++															88.01 295

Test By Simon												80.02 136

High-resolution multi-view benchmark