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.

SMA-MVS		95.20 10	95.07 20	95.59 6	98.14 41	88.48 9	96.26 54	97.28 40	85.90 207	97.67 4	98.10 14	88.41 24	99.56 16	94.66 48	99.19 1	98.71 25
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
DPE-MVS		95.57 5	95.67 5	95.25 12	98.36 31	87.28 19	95.56 119	97.51 10	89.13 89	97.14 17	97.91 34	91.64 8	99.62 4	94.61 49	99.17 2	98.86 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SED-MVS		95.91 3	96.28 3	94.80 38	98.77 8	85.99 56	97.13 19	97.44 20	90.31 43	97.71 2	98.07 22	92.31 5	99.58 13	95.66 30	99.13 3	98.84 19

IU-MVS					98.77 8	86.00 54		96.84 82	81.26 342	97.26 13				95.50 36	99.13 3	99.03 10

test_0728_THIRD									90.75 31	97.04 21	98.05 27	92.09 7	99.55 20	95.64 32	99.13 3	99.13 4

test_241102_TWO								97.44 20	90.31 43	97.62 8	98.07 22	91.46 11	99.58 13	95.66 30	99.12 6	98.98 12

DVP-MVS		95.67 4	96.02 4	94.64 44	98.78 6	85.93 59	97.09 21	96.73 98	90.27 47	97.04 21	98.05 27	91.47 9	99.55 20	95.62 34	99.08 7	98.45 41
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
test_0728_SECOND				95.01 18	98.79 5	86.43 40	97.09 21	97.49 11					99.61 6	95.62 34	99.08 7	98.99 11

MSC_two_6792asdad				96.52 1	97.78 60	90.86 1		96.85 80					99.61 6	96.03 27	99.06 9	99.07 7

No_MVS				96.52 1	97.78 60	90.86 1		96.85 80					99.61 6	96.03 27	99.06 9	99.07 7

APDe-MVS		95.46 6	95.64 6	94.91 23	98.26 34	86.29 47	97.46 7	97.40 26	89.03 95	96.20 35	98.10 14	89.39 17	99.34 42	95.88 29	99.03 11	99.10 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		95.98 1	96.36 1	94.82 35	97.78 60	86.00 54	98.29 1	97.49 11	90.75 31	97.62 8	98.06 24	92.59 2	99.61 6	95.64 32	99.02 12	98.86 16

PC_three_1452									82.47 305	97.09 19	97.07 72	92.72 1	98.04 198	92.70 80	99.02 12	98.86 16

OPU-MVS				96.21 3	98.00 48	90.85 3	97.13 19				97.08 70	92.59 2	98.94 92	92.25 92	98.99 14	98.84 19

ACMMP_NAP		94.74 25	94.56 33	95.28 11	98.02 47	87.70 12	95.68 107	97.34 30	88.28 122	95.30 51	97.67 43	85.90 55	99.54 24	93.91 56	98.95 15	98.60 28

HPM-MVS++		95.14 13	94.91 26	95.83 4	98.25 35	89.65 4	95.92 87	96.96 68	91.75 13	94.02 72	96.83 82	88.12 28	99.55 20	93.41 66	98.94 16	98.28 61

MP-MVS-pluss		94.21 45	94.00 59	94.85 28	98.17 39	86.65 32	94.82 167	97.17 49	86.26 199	92.83 98	97.87 36	85.57 59	99.56 16	94.37 52	98.92 17	98.34 48
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		95.20 10	95.32 13	94.85 28	96.99 82	86.33 43	97.33 8	97.30 37	91.38 19	95.39 49	97.46 50	88.98 23	99.40 34	94.12 53	98.89 18	98.82 21
Skip Steuart: Steuart Systems R&D Blog.
BridgeMVS		93.98 57	94.22 48	93.26 92	96.13 110	83.29 140	96.27 53	96.52 116	89.82 59	95.56 48	95.51 161	84.50 79	98.79 113	94.83 46	98.86 19	97.72 126

MED-MVS test				94.84 34	98.88 1	85.89 65	97.32 10	97.86 1	88.11 131	97.21 14	97.54 46		99.67 1	95.27 40	98.85 20	98.95 13

MED-MVS		95.95 2	96.29 2	94.90 25	98.88 1	85.89 65	97.32 10	97.86 1	90.76 29	97.21 14	98.09 18	92.42 4	99.67 1	95.27 40	98.85 20	99.14 2

ME-MVS		95.17 12	95.29 14	94.81 36	98.39 28	85.89 65	95.91 88	97.55 8	89.01 97	95.86 42	97.54 46	89.24 19	99.59 10	95.27 40	98.85 20	98.95 13

SD-MVS		94.96 18	95.33 12	93.88 71	97.25 79	86.69 29	96.19 57	97.11 58	90.42 39	96.95 23	97.27 58	89.53 15	96.91 316	94.38 51	98.85 20	98.03 90
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
CNVR-MVS		95.40 8	95.37 11	95.50 8	98.11 42	88.51 8	95.29 131	96.96 68	92.09 10	95.32 50	97.08 70	89.49 16	99.33 45	95.10 43	98.85 20	98.66 26

CP-MVS		94.34 40	94.21 50	94.74 42	98.39 28	86.64 33	97.60 5	97.24 41	88.53 115	92.73 104	97.23 61	85.20 65	99.32 46	92.15 97	98.83 25	98.25 68

ZNCC-MVS		94.47 33	94.28 45	95.03 17	98.52 18	86.96 21	96.85 33	97.32 34	88.24 123	93.15 88	97.04 73	86.17 52	99.62 4	92.40 86	98.81 26	98.52 31

MP-MVS		94.25 42	94.07 56	94.77 40	98.47 21	86.31 45	96.71 36	96.98 64	89.04 93	91.98 124	97.19 65	85.43 61	99.56 16	92.06 103	98.79 27	98.44 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		93.89 60	93.65 74	94.62 46	96.84 85	86.43 40	96.69 37	97.49 11	85.15 238	93.56 82	96.28 106	85.60 58	99.31 47	92.45 83	98.79 27	98.12 80

SF-MVS		94.97 17	94.90 28	95.20 13	97.84 56	87.76 11	96.65 39	97.48 15	87.76 152	95.71 44	97.70 42	88.28 27	99.35 41	93.89 57	98.78 29	98.48 35

ACMMPR		94.43 36	94.28 45	94.91 23	98.63 12	86.69 29	96.94 25	97.32 34	88.63 110	93.53 83	97.26 60	85.04 68	99.54 24	92.35 89	98.78 29	98.50 32

HFP-MVS		94.52 31	94.40 38	94.86 27	98.61 13	86.81 26	96.94 25	97.34 30	88.63 110	93.65 78	97.21 62	86.10 53	99.49 30	92.35 89	98.77 31	98.30 55

MM		95.10 14	94.91 26	95.68 5	96.09 116	88.34 10	96.68 38	94.37 299	95.08 1	94.68 58	97.72 41	82.94 100	99.64 3	97.85 5	98.76 32	99.06 9

MTAPA		94.42 39	94.22 48	95.00 19	98.42 24	86.95 22	94.36 209	96.97 65	91.07 22	93.14 89	97.56 45	84.30 81	99.56 16	93.43 64	98.75 33	98.47 38

region2R		94.43 36	94.27 47	94.92 22	98.65 11	86.67 31	96.92 29	97.23 43	88.60 113	93.58 80	97.27 58	85.22 64	99.54 24	92.21 94	98.74 34	98.56 30

test9_res														91.91 109	98.71 35	98.07 82

DeepPCF-MVS	89.96 1	94.20 47	94.77 31	92.49 150	96.52 98	80.00 275	94.00 238	97.08 59	90.05 51	95.65 47	97.29 57	89.66 14	98.97 87	93.95 55	98.71 35	98.50 32

9.14			94.47 35		97.79 58		96.08 69	97.44 20	86.13 205	95.10 55	97.40 53	88.34 26	99.22 53	93.25 68	98.70 37

train_agg		93.44 75	93.08 85	94.52 49	97.53 67	86.49 38	94.07 229	96.78 90	81.86 325	92.77 101	96.20 109	87.63 33	99.12 63	92.14 98	98.69 38	97.94 97

DeepC-MVS_fast	89.43 2	94.04 53	93.79 65	94.80 38	97.48 70	86.78 27	95.65 112	96.89 77	89.40 77	92.81 99	96.97 75	85.37 62	99.24 52	90.87 129	98.69 38	98.38 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCNet		94.18 50	93.80 64	95.34 10	94.91 183	87.62 15	95.97 82	93.01 350	92.58 6	94.22 63	97.20 64	80.56 139	99.59 10	97.04 20	98.68 40	98.81 22

TSAR-MVS + MP.		94.85 19	94.94 24	94.58 47	98.25 35	86.33 43	96.11 67	96.62 108	88.14 128	96.10 36	96.96 76	89.09 21	98.94 92	94.48 50	98.68 40	98.48 35
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
agg_prior2														90.54 134	98.68 40	98.27 63

test_prior2							94.12 221		87.67 156	92.63 109	96.39 104	86.62 45		91.50 118	98.67 43

MVSMamba_PlusPlus		93.44 75	93.54 76	93.14 101	96.58 94	83.05 154	96.06 73	96.50 118	84.42 259	94.09 68	95.56 160	85.01 72	98.69 124	94.96 44	98.66 44	97.67 129

MSLP-MVS++		93.72 66	94.08 55	92.65 139	97.31 75	83.43 134	95.79 98	97.33 32	90.03 52	93.58 80	96.96 76	84.87 74	97.76 229	92.19 96	98.66 44	96.76 197

CDPH-MVS		92.83 94	92.30 101	94.44 50	97.79 58	86.11 53	94.06 231	96.66 105	80.09 356	92.77 101	96.63 94	86.62 45	99.04 69	87.40 188	98.66 44	98.17 73

HPM-MVS		94.02 54	93.88 61	94.43 52	98.39 28	85.78 70	97.25 15	97.07 60	86.90 183	92.62 110	96.80 86	84.85 75	99.17 57	92.43 84	98.65 47	98.33 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		93.99 56	93.78 66	94.63 45	98.50 19	85.90 64	96.87 31	96.91 75	88.70 108	91.83 134	97.17 67	83.96 85	99.55 20	91.44 119	98.64 48	98.43 43

SPE-MVS-test		94.02 54	94.29 44	93.24 93	96.69 88	83.24 141	97.49 6	96.92 73	92.14 9	92.90 94	95.77 149	85.02 69	98.33 165	93.03 72	98.62 49	98.13 77

MCST-MVS		94.45 34	94.20 51	95.19 14	98.46 22	87.50 17	95.00 154	97.12 55	87.13 173	92.51 113	96.30 105	89.24 19	99.34 42	93.46 63	98.62 49	98.73 23

APD-MVS		94.24 43	94.07 56	94.75 41	98.06 45	86.90 24	95.88 90	96.94 71	85.68 214	95.05 56	97.18 66	87.31 39	99.07 65	91.90 111	98.61 51	98.28 61
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PGM-MVS		93.96 58	93.72 70	94.68 43	98.43 23	86.22 49	95.30 129	97.78 3	87.45 163	93.26 85	97.33 56	84.62 78	99.51 28	90.75 131	98.57 52	98.32 54

XVS		94.45 34	94.32 41	94.85 28	98.54 16	86.60 35	96.93 27	97.19 44	90.66 36	92.85 96	97.16 68	85.02 69	99.49 30	91.99 105	98.56 53	98.47 38

X-MVStestdata		88.31 234	86.13 283	94.85 28	98.54 16	86.60 35	96.93 27	97.19 44	90.66 36	92.85 96	23.41 498	85.02 69	99.49 30	91.99 105	98.56 53	98.47 38

DELS-MVS		93.43 79	93.25 81	93.97 68	95.42 152	85.04 83	93.06 295	97.13 54	90.74 33	91.84 132	95.09 185	86.32 50	99.21 55	91.22 121	98.45 55	97.65 130
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
ZD-MVS					98.15 40	86.62 34		97.07 60	83.63 275	94.19 65	96.91 78	87.57 35	99.26 51	91.99 105	98.44 56

GST-MVS		94.21 45	93.97 60	94.90 25	98.41 25	86.82 25	96.54 41	97.19 44	88.24 123	93.26 85	96.83 82	85.48 60	99.59 10	91.43 120	98.40 57	98.30 55

HPM-MVS_fast		93.40 80	93.22 82	93.94 70	98.36 31	84.83 87	97.15 18	96.80 89	85.77 211	92.47 114	97.13 69	82.38 107	99.07 65	90.51 136	98.40 57	97.92 106

NCCC		94.81 22	94.69 32	95.17 15	97.83 57	87.46 18	95.66 110	96.93 72	92.34 7	93.94 73	96.58 97	87.74 31	99.44 33	92.83 75	98.40 57	98.62 27

DeepC-MVS	88.79 3	93.31 81	92.99 88	94.26 62	96.07 118	85.83 68	94.89 160	96.99 63	89.02 96	89.56 190	97.37 55	82.51 106	99.38 35	92.20 95	98.30 60	97.57 136
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CSCG		93.23 85	93.05 86	93.76 78	98.04 46	84.07 113	96.22 56	97.37 27	84.15 262	90.05 182	95.66 154	87.77 30	99.15 61	89.91 145	98.27 61	98.07 82

fmvsm_l_conf0.5_n_9		94.65 27	95.28 15	92.77 125	95.95 129	81.83 196	95.53 120	97.12 55	91.68 16	97.89 1	98.06 24	85.71 56	98.65 127	97.32 12	98.26 62	97.83 117

NormalMVS		93.46 72	93.16 84	94.37 57	98.40 26	86.20 50	96.30 47	96.27 136	91.65 17	92.68 106	96.13 119	77.97 184	98.84 106	90.75 131	98.26 62	98.07 82

lecture		95.10 14	95.46 9	94.01 66	98.40 26	84.36 107	97.70 3	97.78 3	91.19 20	96.22 34	98.08 21	86.64 44	99.37 37	94.91 45	98.26 62	98.29 60

原ACMM1				92.01 182	97.34 73	81.05 226		96.81 88	78.89 372	90.45 169	95.92 134	82.65 104	98.84 106	80.68 305	98.26 62	96.14 224

reproduce-ours		94.82 20	94.97 22	94.38 55	97.91 53	85.46 75	95.86 91	97.15 51	89.82 59	95.23 53	98.10 14	87.09 41	99.37 37	95.30 38	98.25 66	98.30 55

our_new_method		94.82 20	94.97 22	94.38 55	97.91 53	85.46 75	95.86 91	97.15 51	89.82 59	95.23 53	98.10 14	87.09 41	99.37 37	95.30 38	98.25 66	98.30 55

fmvsm_s_conf0.5_n_6		94.11 52	94.56 33	92.76 128	94.98 176	81.96 194	95.79 98	97.29 39	89.31 81	97.52 11	97.61 44	83.25 94	98.88 99	97.05 19	98.22 68	97.43 144

CS-MVS		94.12 51	94.44 37	93.17 99	96.55 95	83.08 153	97.63 4	96.95 70	91.71 15	93.50 84	96.21 108	85.61 57	98.24 170	93.64 61	98.17 69	98.19 71

fmvsm_s_conf0.5_n_11		94.60 28	95.23 16	92.69 136	96.05 120	82.00 190	96.31 46	96.71 101	92.27 8	96.68 30	98.39 2	85.32 63	98.92 95	97.20 14	98.16 70	97.17 160

MVS_111021_HR		93.45 74	93.31 79	93.84 73	96.99 82	84.84 86	93.24 286	97.24 41	88.76 105	91.60 140	95.85 141	86.07 54	98.66 125	91.91 109	98.16 70	98.03 90

reproduce_model		94.76 24	94.92 25	94.29 61	97.92 49	85.18 81	95.95 85	97.19 44	89.67 69	95.27 52	98.16 6	86.53 48	99.36 40	95.42 37	98.15 72	98.33 50

EC-MVSNet		93.44 75	93.71 71	92.63 140	95.21 163	82.43 178	97.27 14	96.71 101	90.57 38	92.88 95	95.80 145	83.16 95	98.16 176	93.68 59	98.14 73	97.31 146

test12				94.34 58	97.13 80	86.15 52		96.29 132		91.04 161		85.08 67	99.01 75		98.13 74	97.86 112

新几何1				93.10 103	97.30 76	84.35 108		95.56 217	71.09 460	91.26 149	96.24 107	82.87 102	98.86 102	79.19 337	98.10 75	96.07 230

patch_mono-2		93.74 65	94.32 41	92.01 182	97.54 66	78.37 324	93.40 273	97.19 44	88.02 136	94.99 57	97.21 62	88.35 25	98.44 153	94.07 54	98.09 76	99.23 1

dcpmvs_2		93.49 70	94.19 52	91.38 220	97.69 63	76.78 367	94.25 214	96.29 132	88.33 119	94.46 60	96.88 79	88.07 29	98.64 130	93.62 62	98.09 76	98.73 23

test_fmvsm_n_1920		94.71 26	95.11 19	93.50 85	95.79 133	84.62 92	96.15 62	97.64 5	89.85 58	97.19 16	97.89 35	86.28 51	98.71 122	97.11 16	98.08 78	97.17 160

MSP-MVS		95.42 7	95.56 7	94.98 21	98.49 20	86.52 37	96.91 30	97.47 16	91.73 14	96.10 36	96.69 87	89.90 13	99.30 48	94.70 47	98.04 79	99.13 4
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
fmvsm_s_conf0.5_n_7		93.15 89	93.76 68	91.31 223	94.42 227	79.48 291	94.52 187	97.14 53	89.33 80	94.17 66	98.09 18	81.83 124	97.49 255	96.33 26	98.02 80	96.95 183

SR-MVS		94.23 44	94.17 54	94.43 52	98.21 38	85.78 70	96.40 43	96.90 76	88.20 126	94.33 62	97.40 53	84.75 77	99.03 70	93.35 67	97.99 81	98.48 35

3Dnovator	86.66 5	91.73 121	90.82 140	94.44 50	94.59 209	86.37 42	97.18 17	97.02 62	89.20 86	84.31 327	96.66 90	73.74 255	99.17 57	86.74 198	97.96 82	97.79 121

CANet		93.54 69	93.20 83	94.55 48	95.65 141	85.73 72	94.94 157	96.69 104	91.89 12	90.69 165	95.88 137	81.99 121	99.54 24	93.14 70	97.95 83	98.39 45

fmvsm_s_conf0.5_n_9		94.99 16	95.50 8	93.44 86	96.51 100	82.25 185	95.76 102	96.92 73	93.37 3	97.63 7	98.43 1	84.82 76	99.16 60	98.15 1	97.92 84	98.90 15

DPM-MVS		92.58 99	91.74 109	95.08 16	96.19 107	89.31 5	92.66 312	96.56 113	83.44 281	91.68 139	95.04 186	86.60 47	98.99 82	85.60 215	97.92 84	96.93 186

fmvsm_s_conf0.5_n_10		94.43 36	94.84 29	93.20 95	95.73 136	83.19 144	95.99 79	97.31 36	91.08 21	97.67 4	98.11 11	81.87 123	99.22 53	97.86 4	97.91 86	97.20 158

APD-MVS_3200maxsize		93.78 63	93.77 67	93.80 76	97.92 49	84.19 111	96.30 47	96.87 79	86.96 179	93.92 74	97.47 49	83.88 86	98.96 89	92.71 79	97.87 87	98.26 67

CPTT-MVS		91.99 108	91.80 108	92.55 145	98.24 37	81.98 192	96.76 35	96.49 119	81.89 324	90.24 173	96.44 103	78.59 175	98.61 135	89.68 151	97.85 88	97.06 173

test_fmvsmconf_n		94.60 28	94.81 30	93.98 67	94.62 205	84.96 85	96.15 62	97.35 29	89.37 78	96.03 39	98.11 11	86.36 49	99.01 75	97.45 10	97.83 89	97.96 95

fmvsm_s_conf0.5_n_8		94.56 30	95.12 18	92.87 118	95.96 128	81.32 214	95.76 102	97.57 7	93.48 2	97.53 10	98.32 3	81.78 126	99.13 62	97.91 2	97.81 90	98.16 74

fmvsm_l_conf0.5_n_3		94.80 23	95.01 21	94.15 64	95.64 142	85.08 82	96.09 68	97.36 28	90.98 24	97.09 19	98.12 10	84.98 73	98.94 92	97.07 17	97.80 91	98.43 43

SR-MVS-dyc-post		93.82 62	93.82 63	93.82 74	97.92 49	84.57 94	96.28 51	96.76 93	87.46 161	93.75 76	97.43 51	84.24 82	99.01 75	92.73 76	97.80 91	97.88 110

RE-MVS-def			93.68 72		97.92 49	84.57 94	96.28 51	96.76 93	87.46 161	93.75 76	97.43 51	82.94 100		92.73 76	97.80 91	97.88 110

test222					96.55 95	81.70 202	92.22 331	95.01 256	68.36 468	90.20 175	96.14 118	80.26 144			97.80 91	96.05 233

test_fmvsmconf0.1_n		94.20 47	94.31 43	93.88 71	92.46 325	84.80 88	96.18 59	96.82 85	89.29 83	95.68 46	98.11 11	85.10 66	98.99 82	97.38 11	97.75 95	97.86 112

3Dnovator+	87.14 4	92.42 103	91.37 125	95.55 7	95.63 143	88.73 7	97.07 23	96.77 92	90.84 26	84.02 332	96.62 95	75.95 214	99.34 42	87.77 181	97.68 96	98.59 29

旧先验1					96.79 86	81.81 197		95.67 208			96.81 84	86.69 43			97.66 97	96.97 182

fmvsm_s_conf0.5_n_3		94.49 32	95.13 17	92.56 144	95.49 150	81.10 224	95.93 86	97.16 50	92.96 4	97.39 12	98.13 7	83.63 88	98.80 111	97.89 3	97.61 98	97.78 122

EPNet		91.79 112	91.02 134	94.10 65	90.10 411	85.25 80	96.03 76	92.05 377	92.83 5	87.39 238	95.78 148	79.39 165	99.01 75	88.13 175	97.48 99	98.05 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		93.44 75	93.55 75	93.10 103	93.67 281	84.26 109	95.83 95	96.14 159	89.00 98	92.43 115	97.50 48	83.37 92	98.72 120	96.61 24	97.44 100	96.32 214

testdata				90.49 265	96.40 101	77.89 339		95.37 236	72.51 452	93.63 79	96.69 87	82.08 118	97.65 238	83.08 254	97.39 101	95.94 235

MVS_111021_LR		92.47 102	92.29 102	92.98 111	95.99 125	84.43 103	93.08 292	96.09 166	88.20 126	91.12 154	95.72 152	81.33 131	97.76 229	91.74 113	97.37 102	96.75 198

BP-MVS1		92.48 101	92.07 104	93.72 80	94.50 218	84.39 106	95.90 89	94.30 302	90.39 40	92.67 108	95.94 132	74.46 238	98.65 127	93.14 70	97.35 103	98.13 77

fmvsm_s_conf0.5_n_5		93.96 58	94.18 53	93.30 89	94.79 190	83.81 122	95.77 100	96.74 97	88.02 136	96.23 33	97.84 38	83.36 93	98.83 109	97.49 8	97.34 104	97.25 153

test_fmvsmconf0.01_n		93.19 86	93.02 87	93.71 81	89.25 424	84.42 105	96.06 73	96.29 132	89.06 91	94.68 58	98.13 7	79.22 167	98.98 86	97.22 13	97.24 105	97.74 124

MVSFormer		91.68 127	91.30 126	92.80 123	93.86 266	83.88 120	95.96 83	95.90 185	84.66 255	91.76 136	94.91 192	77.92 187	97.30 281	89.64 153	97.11 106	97.24 154

lupinMVS		90.92 145	90.21 151	93.03 108	93.86 266	83.88 120	92.81 306	93.86 321	79.84 359	91.76 136	94.29 225	77.92 187	98.04 198	90.48 137	97.11 106	97.17 160

EIA-MVS		91.95 109	91.94 106	91.98 186	95.16 166	80.01 274	95.36 124	96.73 98	88.44 116	89.34 195	92.16 302	83.82 87	98.45 151	89.35 155	97.06 108	97.48 140

MG-MVS		91.77 117	91.70 110	92.00 185	97.08 81	80.03 273	93.60 266	95.18 248	87.85 148	90.89 163	96.47 102	82.06 119	98.36 160	85.07 221	97.04 109	97.62 131

fmvsm_l_conf0.5_n_a		94.20 47	94.40 38	93.60 83	95.29 157	84.98 84	95.61 115	96.28 135	86.31 197	96.75 28	97.86 37	87.40 37	98.74 119	97.07 17	97.02 110	97.07 172

TestfortrainingZip a		95.33 9	95.44 10	94.99 20	98.88 1	86.26 48	97.32 10	97.43 25	90.76 29	96.80 26	98.09 18	89.00 22	99.58 13	93.66 60	96.99 111	99.14 2

test2506		87.21 279	86.28 278	90.02 292	95.62 144	73.64 406	96.25 55	71.38 496	87.89 146	90.45 169	96.65 91	55.29 441	98.09 188	86.03 210	96.94 112	98.33 50

ECVR-MVS		89.09 209	88.53 205	90.77 251	95.62 144	75.89 380	96.16 60	84.22 473	87.89 146	90.20 175	96.65 91	63.19 385	98.10 180	85.90 211	96.94 112	98.33 50

balanced_ft_v1		92.23 106	92.05 105	92.77 125	95.40 153	81.78 200	95.80 96	95.69 207	87.94 140	91.92 129	95.04 186	75.91 215	98.71 122	93.83 58	96.94 112	97.82 119

test1111		89.10 207	88.64 202	90.48 266	95.53 149	74.97 390	96.08 69	84.89 471	88.13 129	90.16 180	96.65 91	63.29 382	98.10 180	86.14 206	96.90 115	98.39 45

jason		90.80 147	90.10 155	92.90 116	93.04 305	83.53 132	93.08 292	94.15 310	80.22 353	91.41 146	94.91 192	76.87 197	97.93 218	90.28 138	96.90 115	97.24 154
jason: jason.
Vis-MVSNet		91.75 119	91.23 129	93.29 90	95.32 156	83.78 123	96.14 64	95.98 175	89.89 55	90.45 169	96.58 97	75.09 227	98.31 168	84.75 227	96.90 115	97.78 122
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
114514_t		89.51 191	88.50 207	92.54 146	98.11 42	81.99 191	95.16 146	96.36 128	70.19 464	85.81 272	95.25 174	76.70 201	98.63 132	82.07 277	96.86 118	97.00 180

fmvsm_l_conf0.5_n		94.29 41	94.46 36	93.79 77	95.28 158	85.43 77	95.68 107	96.43 121	86.56 191	96.84 25	97.81 39	87.56 36	98.77 115	97.14 15	96.82 119	97.16 167

fmvsm_s_conf0.5_n_4		93.86 61	94.37 40	92.33 163	95.13 169	80.95 231	95.64 113	96.97 65	89.60 71	96.85 24	97.77 40	83.08 98	98.92 95	97.49 8	96.78 120	97.13 168

Vis-MVSNet (Re-imp)		89.59 189	89.44 176	90.03 290	95.74 135	75.85 381	95.61 115	90.80 415	87.66 157	87.83 227	95.40 167	76.79 199	96.46 354	78.37 343	96.73 121	97.80 120

API-MVS		90.66 155	90.07 157	92.45 153	96.36 103	84.57 94	96.06 73	95.22 247	82.39 306	89.13 198	94.27 228	80.32 141	98.46 147	80.16 315	96.71 122	94.33 306

MAR-MVS		90.30 164	89.37 179	93.07 107	96.61 91	84.48 99	95.68 107	95.67 208	82.36 308	87.85 225	92.85 278	76.63 203	98.80 111	80.01 317	96.68 123	95.91 236
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
OpenMVS	83.78 11	88.74 221	87.29 240	93.08 105	92.70 320	85.39 78	96.57 40	96.43 121	78.74 378	80.85 382	96.07 122	69.64 313	99.01 75	78.01 350	96.65 124	94.83 282

fmvsm_s_conf0.5_n_2		93.47 71	93.83 62	92.39 157	95.36 154	81.19 220	95.20 143	96.56 113	90.37 41	97.13 18	98.03 31	77.47 193	98.96 89	97.79 6	96.58 125	97.03 176

ETV-MVS		92.74 97	92.66 94	92.97 112	95.20 164	84.04 117	95.07 150	96.51 117	90.73 34	92.96 93	91.19 339	84.06 83	98.34 163	91.72 114	96.54 126	96.54 209

QAPM		89.51 191	88.15 218	93.59 84	94.92 181	84.58 93	96.82 34	96.70 103	78.43 383	83.41 350	96.19 112	73.18 264	99.30 48	77.11 359	96.54 126	96.89 189

IS-MVSNet		91.43 131	91.09 133	92.46 151	95.87 132	81.38 213	96.95 24	93.69 334	89.72 68	89.50 193	95.98 129	78.57 176	97.77 228	83.02 256	96.50 128	98.22 70

DP-MVS Recon		91.95 109	91.28 128	93.96 69	98.33 33	85.92 61	94.66 180	96.66 105	82.69 303	90.03 183	95.82 144	82.30 111	99.03 70	84.57 233	96.48 129	96.91 188

CANet_DTU		90.26 166	89.41 178	92.81 121	93.46 288	83.01 157	93.48 269	94.47 294	89.43 76	87.76 230	94.23 230	70.54 301	99.03 70	84.97 222	96.39 130	96.38 212

KinetiMVS		91.82 111	91.30 126	93.39 87	94.72 197	83.36 138	95.45 122	96.37 127	90.33 42	92.17 119	96.03 126	72.32 276	98.75 116	87.94 178	96.34 131	98.07 82

UGNet		89.95 178	88.95 194	92.95 114	94.51 217	83.31 139	95.70 106	95.23 245	89.37 78	87.58 232	93.94 241	64.00 377	98.78 114	83.92 243	96.31 132	96.74 199
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
fmvsm_s_conf0.5_n		93.76 64	94.06 58	92.86 119	95.62 144	83.17 145	96.14 64	96.12 163	88.13 129	95.82 43	98.04 30	83.43 89	98.48 143	96.97 21	96.23 133	96.92 187

fmvsm_s_conf0.1_n_2		93.16 88	93.42 77	92.37 158	94.62 205	81.13 222	95.23 136	95.89 187	90.30 45	96.74 29	98.02 32	76.14 205	98.95 91	97.64 7	96.21 134	97.03 176

fmvsm_s_conf0.1_n		93.46 72	93.66 73	92.85 120	93.75 273	83.13 147	96.02 77	95.74 199	87.68 155	95.89 41	98.17 5	82.78 103	98.46 147	96.71 22	96.17 135	96.98 181

TSAR-MVS + GP.		93.66 67	93.41 78	94.41 54	96.59 92	86.78 27	94.40 201	93.93 317	89.77 66	94.21 64	95.59 158	87.35 38	98.61 135	92.72 78	96.15 136	97.83 117

mvsmamba		90.33 163	89.69 169	92.25 175	95.17 165	81.64 203	95.27 134	93.36 340	84.88 245	89.51 191	94.27 228	69.29 322	97.42 266	89.34 156	96.12 137	97.68 128

GDP-MVS		92.04 107	91.46 122	93.75 79	94.55 215	84.69 91	95.60 118	96.56 113	87.83 149	93.07 92	95.89 136	73.44 259	98.65 127	90.22 139	96.03 138	97.91 108

PVSNet_Blended		90.73 150	90.32 149	91.98 186	96.12 111	81.25 216	92.55 316	96.83 83	82.04 317	89.10 199	92.56 290	81.04 135	98.85 104	86.72 200	95.91 139	95.84 241

PS-MVSNAJ		91.18 138	90.92 136	91.96 188	95.26 161	82.60 176	92.09 336	95.70 205	86.27 198	91.84 132	92.46 292	79.70 157	98.99 82	89.08 160	95.86 140	94.29 307

TestfortrainingZip				95.40 9	97.32 74	88.97 6	97.32 10	96.82 85	89.07 90	95.69 45	96.49 100	89.27 18	99.29 50		95.80 141	97.95 96

Elysia		90.12 168	89.10 186	93.18 97	93.16 295	84.05 115	95.22 138	96.27 136	85.16 236	90.59 166	94.68 204	64.64 369	98.37 158	86.38 204	95.77 142	97.12 169

StellarMVS		90.12 168	89.10 186	93.18 97	93.16 295	84.05 115	95.22 138	96.27 136	85.16 236	90.59 166	94.68 204	64.64 369	98.37 158	86.38 204	95.77 142	97.12 169

ACMMP		93.24 84	92.88 90	94.30 60	98.09 44	85.33 79	96.86 32	97.45 19	88.33 119	90.15 181	97.03 74	81.44 129	99.51 28	90.85 130	95.74 144	98.04 89
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
casdiffmvs_mvg		92.96 93	92.83 91	93.35 88	94.59 209	83.40 136	95.00 154	96.34 129	90.30 45	92.05 122	96.05 123	83.43 89	98.15 177	92.07 100	95.67 145	98.49 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LCM-MVSNet-Re		88.30 235	88.32 214	88.27 359	94.71 199	72.41 426	93.15 287	90.98 408	87.77 151	79.25 411	91.96 315	78.35 181	95.75 391	83.04 255	95.62 146	96.65 203

CHOSEN 1792x2688		88.84 217	87.69 230	92.30 168	96.14 109	81.42 212	90.01 399	95.86 191	74.52 432	87.41 235	93.94 241	75.46 224	98.36 160	80.36 310	95.53 147	97.12 169

fmvsm_s_conf0.5_n_a		93.57 68	93.76 68	93.00 110	95.02 171	83.67 126	96.19 57	96.10 165	87.27 167	95.98 40	98.05 27	83.07 99	98.45 151	96.68 23	95.51 148	96.88 190

AdaColmap		89.89 181	89.07 188	92.37 158	97.41 71	83.03 155	94.42 196	95.92 182	82.81 300	86.34 261	94.65 209	73.89 251	99.02 73	80.69 304	95.51 148	95.05 269

MVS		87.44 266	86.10 286	91.44 217	92.61 322	83.62 129	92.63 313	95.66 210	67.26 470	81.47 374	92.15 303	77.95 186	98.22 173	79.71 321	95.48 150	92.47 398

UA-Net		92.83 94	92.54 97	93.68 82	96.10 115	84.71 90	95.66 110	96.39 125	91.92 11	93.22 87	96.49 100	83.16 95	98.87 100	84.47 235	95.47 151	97.45 142

xiu_mvs_v2_base		91.13 140	90.89 138	91.86 197	94.97 177	82.42 179	92.24 329	95.64 213	86.11 206	91.74 138	93.14 271	79.67 162	98.89 98	89.06 161	95.46 152	94.28 308

casdiffmvs		92.51 100	92.43 99	92.74 132	94.41 228	81.98 192	94.54 186	96.23 144	89.57 72	91.96 126	96.17 113	82.58 105	98.01 205	90.95 127	95.45 153	98.23 69
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_conf0.1_n_a		93.19 86	93.26 80	92.97 112	92.49 323	83.62 129	96.02 77	95.72 203	86.78 185	96.04 38	98.19 4	82.30 111	98.43 155	96.38 25	95.42 154	96.86 191

PVSNet_Blended_VisFu		91.38 132	90.91 137	92.80 123	96.39 102	83.17 145	94.87 162	96.66 105	83.29 286	89.27 197	94.46 220	80.29 142	99.17 57	87.57 185	95.37 155	96.05 233

PAPM_NR		91.22 136	90.78 141	92.52 148	97.60 65	81.46 210	94.37 207	96.24 143	86.39 196	87.41 235	94.80 200	82.06 119	98.48 143	82.80 262	95.37 155	97.61 132

CHOSEN 280x420		85.15 338	83.99 345	88.65 348	92.47 324	78.40 323	79.68 486	92.76 357	74.90 429	81.41 376	89.59 392	69.85 311	95.51 400	79.92 319	95.29 157	92.03 411

TAPA-MVS	84.62 6	88.16 238	87.01 248	91.62 209	96.64 90	80.65 244	94.39 203	96.21 148	76.38 411	86.19 265	95.44 164	79.75 155	98.08 190	62.75 458	95.29 157	96.13 225
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
baseline		92.39 104	92.29 102	92.69 136	94.46 223	81.77 201	94.14 220	96.27 136	89.22 85	91.88 130	96.00 127	82.35 108	97.99 207	91.05 123	95.27 159	98.30 55

LS3D		87.89 244	86.32 276	92.59 142	96.07 118	82.92 160	95.23 136	94.92 269	75.66 419	82.89 357	95.98 129	72.48 273	99.21 55	68.43 428	95.23 160	95.64 250

test_vis1_n_1920		89.39 201	89.84 164	88.04 366	92.97 309	72.64 421	94.71 177	96.03 173	86.18 201	91.94 128	96.56 99	61.63 394	95.74 392	93.42 65	95.11 161	95.74 246

diffmvs_AUTHOR		91.51 130	91.44 123	91.73 205	93.09 300	80.27 258	92.51 317	95.58 216	87.22 169	91.80 135	95.57 159	79.96 147	97.48 256	92.23 93	94.97 162	97.45 142

MVS_Test		91.31 134	91.11 131	91.93 191	94.37 229	80.14 263	93.46 271	95.80 194	86.46 194	91.35 148	93.77 251	82.21 114	98.09 188	87.57 185	94.95 163	97.55 138

viewmanbaseed2359cas		91.78 115	91.58 114	92.37 158	94.32 236	81.07 225	93.76 254	95.96 179	87.26 168	91.50 142	95.88 137	80.92 137	97.97 212	89.70 150	94.92 164	98.07 82

RRT-MVS		90.85 146	90.70 143	91.30 224	94.25 243	76.83 366	94.85 165	96.13 162	89.04 93	90.23 174	94.88 194	70.15 306	98.72 120	91.86 112	94.88 165	98.34 48

test_cas_vis1_n_1920		88.83 220	88.85 200	88.78 342	91.15 373	76.72 368	93.85 249	94.93 268	83.23 289	92.81 99	96.00 127	61.17 405	94.45 418	91.67 115	94.84 166	95.17 265

PAPR		90.02 174	89.27 184	92.29 170	95.78 134	80.95 231	92.68 311	96.22 145	81.91 321	86.66 252	93.75 253	82.23 113	98.44 153	79.40 336	94.79 167	97.48 140

SymmetryMVS		92.81 96	92.31 100	94.32 59	96.15 108	86.20 50	96.30 47	94.43 295	91.65 17	92.68 106	96.13 119	77.97 184	98.84 106	90.75 131	94.72 168	97.92 106

test_fmvs1		87.34 270	87.56 233	86.68 406	90.59 398	71.80 430	94.01 236	94.04 315	78.30 385	91.97 125	95.22 175	56.28 434	93.71 435	92.89 74	94.71 169	94.52 295

viewmacassd2359aftdt		91.67 128	91.43 124	92.37 158	93.95 264	81.00 228	93.90 248	95.97 178	87.75 153	91.45 145	96.04 125	79.92 148	97.97 212	89.26 158	94.67 170	98.14 76

xiu_mvs_v1_base_debu		90.64 156	90.05 158	92.40 154	93.97 261	84.46 100	93.32 277	95.46 225	85.17 233	92.25 116	94.03 233	70.59 297	98.57 138	90.97 124	94.67 170	94.18 310

xiu_mvs_v1_base		90.64 156	90.05 158	92.40 154	93.97 261	84.46 100	93.32 277	95.46 225	85.17 233	92.25 116	94.03 233	70.59 297	98.57 138	90.97 124	94.67 170	94.18 310

xiu_mvs_v1_base_debi		90.64 156	90.05 158	92.40 154	93.97 261	84.46 100	93.32 277	95.46 225	85.17 233	92.25 116	94.03 233	70.59 297	98.57 138	90.97 124	94.67 170	94.18 310

gg-mvs-nofinetune		81.77 386	79.37 400	88.99 339	90.85 389	77.73 351	86.29 454	79.63 484	74.88 430	83.19 355	69.05 487	60.34 409	96.11 372	75.46 375	94.64 174	93.11 372

BH-RMVSNet		88.37 232	87.48 235	91.02 238	95.28 158	79.45 293	92.89 303	93.07 348	85.45 225	86.91 244	94.84 199	70.35 302	97.76 229	73.97 391	94.59 175	95.85 240

test_fmvs1_n		87.03 287	87.04 247	86.97 397	89.74 419	71.86 428	94.55 185	94.43 295	78.47 381	91.95 127	95.50 162	51.16 459	93.81 433	93.02 73	94.56 176	95.26 262

diffmvs		91.37 133	91.23 129	91.77 204	93.09 300	80.27 258	92.36 322	95.52 222	87.03 176	91.40 147	94.93 191	80.08 145	97.44 264	92.13 99	94.56 176	97.61 132
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		88.60 225	88.13 219	90.01 293	95.24 162	78.50 320	93.29 282	94.15 310	84.75 251	84.46 317	93.40 259	75.76 218	97.40 274	77.59 353	94.52 178	94.12 314

Effi-MVS+		91.59 129	91.11 131	93.01 109	94.35 233	83.39 137	94.60 182	95.10 252	87.10 174	90.57 168	93.10 273	81.43 130	98.07 192	89.29 157	94.48 179	97.59 135

PCF-MVS	84.11 10	87.74 249	86.08 287	92.70 135	94.02 255	84.43 103	89.27 412	95.87 190	73.62 442	84.43 319	94.33 222	78.48 180	98.86 102	70.27 414	94.45 180	94.81 283
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EI-MVSNet-Vis-set		93.01 92	92.92 89	93.29 90	95.01 172	83.51 133	94.48 189	95.77 196	90.87 25	92.52 112	96.67 89	84.50 79	99.00 80	91.99 105	94.44 181	97.36 145

viewcassd2359sk11		91.79 112	91.62 111	92.29 170	94.62 205	80.88 235	93.70 261	96.18 155	87.38 165	91.13 153	95.85 141	81.62 128	98.06 193	89.71 149	94.40 182	97.94 97

E3new		91.76 118	91.58 114	92.28 174	94.69 202	80.90 234	93.68 264	96.17 156	87.15 171	91.09 160	95.70 153	81.75 127	98.05 197	89.67 152	94.35 183	97.90 109

MS-PatchMatch		85.05 340	84.16 340	87.73 373	91.42 361	78.51 319	91.25 363	93.53 335	77.50 393	80.15 392	91.58 330	61.99 391	95.51 400	75.69 373	94.35 183	89.16 459

FE-MVS		87.40 268	86.02 289	91.57 211	94.56 214	79.69 288	90.27 386	93.72 332	80.57 350	88.80 207	91.62 328	65.32 362	98.59 137	74.97 382	94.33 185	96.44 210

E2		91.79 112	91.61 112	92.31 165	94.49 219	80.86 237	93.74 256	96.19 149	87.63 158	91.16 150	95.94 132	81.31 132	98.06 193	89.76 147	94.29 186	97.99 92

E3		91.78 115	91.61 112	92.30 168	94.48 220	80.86 237	93.73 257	96.19 149	87.63 158	91.16 150	95.95 131	81.30 133	98.06 193	89.76 147	94.29 186	97.99 92

viewdifsd2359ckpt09		91.18 138	90.65 144	92.75 130	94.61 208	82.36 183	94.32 210	95.74 199	84.72 252	89.66 189	95.15 183	79.69 160	98.04 198	87.70 182	94.27 188	97.85 115

LuminaMVS		90.55 160	89.81 165	92.77 125	92.78 318	84.21 110	94.09 227	94.17 309	85.82 208	91.54 141	94.14 232	69.93 307	97.92 219	91.62 116	94.21 189	96.18 222

SSM_0404		90.73 150	90.08 156	92.69 136	95.00 175	83.13 147	94.32 210	95.00 260	85.41 226	89.84 184	95.35 169	76.13 206	97.98 210	85.46 218	94.18 190	96.95 183

mvs_anonymous		89.37 202	89.32 181	89.51 326	93.47 287	74.22 399	91.65 349	94.83 276	82.91 298	85.45 287	93.79 249	81.23 134	96.36 362	86.47 202	94.09 191	97.94 97

E4		91.74 120	91.55 117	92.31 165	94.27 241	80.80 241	93.81 251	96.17 156	87.97 138	91.11 155	96.05 123	80.75 138	98.08 190	89.78 146	94.02 192	98.06 87

test_vis1_n		86.56 306	86.49 271	86.78 404	88.51 430	72.69 418	94.68 178	93.78 329	79.55 363	90.70 164	95.31 171	48.75 465	93.28 441	93.15 69	93.99 193	94.38 305

MVP-Stereo		85.97 319	84.86 327	89.32 329	90.92 385	82.19 186	92.11 335	94.19 307	78.76 377	78.77 420	91.63 327	68.38 335	96.56 345	75.01 381	93.95 194	89.20 458
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LFMVS		90.08 171	89.13 185	92.95 114	96.71 87	82.32 184	96.08 69	89.91 435	86.79 184	92.15 121	96.81 84	62.60 388	98.34 163	87.18 192	93.90 195	98.19 71

viewdifsd2359ckpt13		91.20 137	90.75 142	92.54 146	94.30 239	82.13 187	94.03 233	95.89 187	85.60 217	90.20 175	95.36 168	79.69 160	97.90 222	87.85 180	93.86 196	97.61 132

PVSNet	78.82 18	85.55 327	84.65 331	88.23 362	94.72 197	71.93 427	87.12 448	92.75 358	78.80 376	84.95 305	90.53 364	64.43 372	96.71 324	74.74 384	93.86 196	96.06 232

CNLPA		89.07 210	87.98 222	92.34 162	96.87 84	84.78 89	94.08 228	93.24 342	81.41 338	84.46 317	95.13 184	75.57 223	96.62 333	77.21 357	93.84 198	95.61 253

guyue		91.12 141	90.84 139	91.96 188	94.59 209	80.57 252	94.87 162	93.71 333	88.96 99	91.14 152	95.22 175	73.22 263	97.76 229	92.01 104	93.81 199	97.54 139

E5new		91.71 122	91.55 117	92.20 176	94.33 234	80.62 247	94.41 197	96.19 149	88.06 132	91.11 155	96.16 114	79.92 148	98.03 201	90.00 140	93.80 200	97.94 97

E6new		91.71 122	91.55 117	92.20 176	94.32 236	80.62 247	94.41 197	96.19 149	88.06 132	91.11 155	96.16 114	79.92 148	98.03 201	90.00 140	93.80 200	97.94 97

E6		91.71 122	91.55 117	92.20 176	94.32 236	80.62 247	94.41 197	96.19 149	88.06 132	91.11 155	96.16 114	79.92 148	98.03 201	90.00 140	93.80 200	97.94 97

E5		91.71 122	91.55 117	92.20 176	94.33 234	80.62 247	94.41 197	96.19 149	88.06 132	91.11 155	96.16 114	79.92 148	98.03 201	90.00 140	93.80 200	97.94 97

EPNet_dtu		86.49 311	85.94 294	88.14 364	90.24 409	72.82 416	94.11 223	92.20 373	86.66 190	79.42 407	92.36 296	73.52 256	95.81 388	71.26 406	93.66 204	95.80 244
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GeoE		90.05 172	89.43 177	91.90 196	95.16 166	80.37 257	95.80 96	94.65 286	83.90 267	87.55 234	94.75 201	78.18 183	97.62 242	81.28 293	93.63 205	97.71 127

EI-MVSNet-UG-set		92.74 97	92.62 96	93.12 102	94.86 186	83.20 143	94.40 201	95.74 199	90.71 35	92.05 122	96.60 96	84.00 84	98.99 82	91.55 117	93.63 205	97.17 160

viewdifsd2359ckpt07		91.11 142	91.02 134	91.41 218	94.21 246	78.37 324	92.91 302	95.71 204	87.50 160	90.32 172	95.88 137	80.27 143	97.99 207	88.78 168	93.55 207	97.86 112

Fast-Effi-MVS+		89.41 198	88.64 202	91.71 207	94.74 194	80.81 240	93.54 267	95.10 252	83.11 290	86.82 250	90.67 362	79.74 156	97.75 233	80.51 308	93.55 207	96.57 207

FA-MVS(test-final)		89.66 186	88.91 196	91.93 191	94.57 213	80.27 258	91.36 357	94.74 282	84.87 246	89.82 185	92.61 289	74.72 234	98.47 146	83.97 242	93.53 209	97.04 175

1314		87.51 263	86.57 266	90.34 276	92.42 327	79.74 286	92.63 313	95.35 238	78.35 384	80.14 393	91.62 328	74.05 247	97.15 294	81.05 295	93.53 209	94.12 314

BH-w/o		87.57 261	87.05 246	89.12 334	94.90 184	77.90 338	92.41 319	93.51 337	82.89 299	83.70 340	91.34 333	75.75 219	97.07 303	75.49 374	93.49 211	92.39 403

PMMVS		85.71 326	84.96 324	87.95 368	88.90 428	77.09 360	88.68 422	90.06 430	72.32 454	86.47 254	90.76 358	72.15 277	94.40 421	81.78 285	93.49 211	92.36 404

PatchMatch-RL		86.77 299	85.54 308	90.47 269	95.88 130	82.71 168	90.54 381	92.31 369	79.82 360	84.32 325	91.57 332	68.77 330	96.39 359	73.16 397	93.48 213	92.32 406

casdiffseed414692147		91.11 142	90.55 146	92.81 121	94.27 241	82.58 177	94.81 168	96.03 173	87.93 142	90.17 179	95.62 156	78.51 177	97.90 222	84.18 239	93.45 214	97.94 97

PLC	84.53 7	89.06 211	88.03 220	92.15 180	97.27 78	82.69 169	94.29 212	95.44 230	79.71 361	84.01 333	94.18 231	76.68 202	98.75 116	77.28 356	93.41 215	95.02 270
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VNet		92.24 105	91.91 107	93.24 93	96.59 92	83.43 134	94.84 166	96.44 120	89.19 87	94.08 71	95.90 135	77.85 190	98.17 175	88.90 165	93.38 216	98.13 77

test-LLR		85.87 321	85.41 311	87.25 389	90.95 381	71.67 433	89.55 406	89.88 437	83.41 282	84.54 313	87.95 419	67.25 340	95.11 411	81.82 283	93.37 217	94.97 271

test-mter		84.54 352	83.64 350	87.25 389	90.95 381	71.67 433	89.55 406	89.88 437	79.17 367	84.54 313	87.95 419	55.56 436	95.11 411	81.82 283	93.37 217	94.97 271

myMVS_eth3d28		85.80 324	85.26 318	87.42 383	94.73 195	69.92 451	90.60 379	90.95 410	87.21 170	86.06 268	90.04 381	59.47 415	96.02 375	74.89 383	93.35 219	96.33 213

EPP-MVSNet		91.70 126	91.56 116	92.13 181	95.88 130	80.50 254	97.33 8	95.25 244	86.15 202	89.76 188	95.60 157	83.42 91	98.32 167	87.37 190	93.25 220	97.56 137

CDS-MVSNet		89.45 194	88.51 206	92.29 170	93.62 283	83.61 131	93.01 296	94.68 285	81.95 319	87.82 228	93.24 267	78.69 173	96.99 310	80.34 311	93.23 221	96.28 217
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
viewmambaseed2359dif		90.04 173	89.78 167	90.83 247	92.85 315	77.92 336	92.23 330	95.01 256	81.90 322	90.20 175	95.45 163	79.64 164	97.34 279	87.52 187	93.17 222	97.23 157

PAPM		86.68 302	85.39 312	90.53 258	93.05 304	79.33 303	89.79 402	94.77 281	78.82 375	81.95 370	93.24 267	76.81 198	97.30 281	66.94 438	93.16 223	94.95 278

mamba_0408		89.06 211	87.92 225	92.50 149	94.76 191	82.66 170	79.84 484	94.64 287	85.18 231	88.96 203	95.00 188	76.00 211	97.98 210	83.74 247	93.15 224	96.85 192

SSM_04072		88.57 228	87.92 225	90.51 263	94.76 191	82.66 170	79.84 484	94.64 287	85.18 231	88.96 203	95.00 188	76.00 211	92.03 454	83.74 247	93.15 224	96.85 192

SSM_0407		90.47 162	89.80 166	92.46 151	94.76 191	82.66 170	93.98 240	95.00 260	85.41 226	88.96 203	95.35 169	76.13 206	97.88 224	85.46 218	93.15 224	96.85 192

alignmvs		93.08 90	92.50 98	94.81 36	95.62 144	87.61 16	95.99 79	96.07 168	89.77 66	94.12 67	94.87 195	80.56 139	98.66 125	92.42 85	93.10 227	98.15 75

thisisatest0515		87.33 271	85.99 290	91.37 221	93.49 286	79.55 289	90.63 378	89.56 444	80.17 354	87.56 233	90.86 352	67.07 343	98.28 169	81.50 290	93.02 228	96.29 216

TAMVS		89.21 204	88.29 215	91.96 188	93.71 278	82.62 175	93.30 281	94.19 307	82.22 311	87.78 229	93.94 241	78.83 170	96.95 313	77.70 352	92.98 229	96.32 214

OMC-MVS		91.23 135	90.62 145	93.08 105	96.27 105	84.07 113	93.52 268	95.93 181	86.95 180	89.51 191	96.13 119	78.50 178	98.35 162	85.84 213	92.90 230	96.83 196

sasdasda		93.27 82	92.75 92	94.85 28	95.70 139	87.66 13	96.33 44	96.41 123	90.00 53	94.09 68	94.60 211	82.33 109	98.62 133	92.40 86	92.86 231	98.27 63

canonicalmvs		93.27 82	92.75 92	94.85 28	95.70 139	87.66 13	96.33 44	96.41 123	90.00 53	94.09 68	94.60 211	82.33 109	98.62 133	92.40 86	92.86 231	98.27 63

TESTMET0.1,1		83.74 364	82.85 364	86.42 410	89.96 415	71.21 438	89.55 406	87.88 455	77.41 394	83.37 351	87.31 427	56.71 432	93.65 437	80.62 306	92.85 233	94.40 304

MGCFI-Net		93.03 91	92.63 95	94.23 63	95.62 144	85.92 61	96.08 69	96.33 130	89.86 57	93.89 75	94.66 208	82.11 116	98.50 141	92.33 91	92.82 234	98.27 63

AstraMVS		90.69 152	90.30 150	91.84 200	93.81 269	79.85 281	94.76 173	92.39 365	88.96 99	91.01 162	95.87 140	70.69 295	97.94 217	92.49 82	92.70 235	97.73 125

icg_test_0407_2		89.15 205	88.97 192	89.68 316	93.72 274	77.75 347	88.26 430	95.34 239	85.53 221	88.34 216	94.49 216	77.69 191	93.99 429	84.75 227	92.65 236	97.28 149

IMVS_0407		89.85 183	89.51 174	90.88 246	93.72 274	77.75 347	93.07 294	95.34 239	85.53 221	88.34 216	94.49 216	77.69 191	97.60 243	84.75 227	92.65 236	97.28 149

IMVS_0404		87.60 259	86.84 252	89.89 297	93.72 274	77.75 347	88.56 424	95.34 239	85.53 221	79.98 397	94.49 216	66.54 354	94.64 417	84.75 227	92.65 236	97.28 149

IMVS_0403		89.97 176	89.64 170	90.96 244	93.72 274	77.75 347	93.00 297	95.34 239	85.53 221	88.77 208	94.49 216	78.49 179	97.84 225	84.75 227	92.65 236	97.28 149

thisisatest0530		88.67 222	87.61 232	91.86 197	94.87 185	80.07 268	94.63 181	89.90 436	84.00 265	88.46 213	93.78 250	66.88 346	98.46 147	83.30 252	92.65 236	97.06 173

UWE-MVS		83.69 365	83.09 358	85.48 420	93.06 303	65.27 471	90.92 372	86.14 463	79.90 358	86.26 263	90.72 361	57.17 431	95.81 388	71.03 412	92.62 241	95.35 260

VDD-MVS		90.74 149	89.92 163	93.20 95	96.27 105	83.02 156	95.73 104	93.86 321	88.42 118	92.53 111	96.84 81	62.09 390	98.64 130	90.95 127	92.62 241	97.93 105

test_yl		90.69 152	90.02 161	92.71 133	95.72 137	82.41 181	94.11 223	95.12 250	85.63 215	91.49 143	94.70 202	74.75 231	98.42 156	86.13 208	92.53 243	97.31 146

DCV-MVSNet		90.69 152	90.02 161	92.71 133	95.72 137	82.41 181	94.11 223	95.12 250	85.63 215	91.49 143	94.70 202	74.75 231	98.42 156	86.13 208	92.53 243	97.31 146

VDDNet		89.56 190	88.49 209	92.76 128	95.07 170	82.09 188	96.30 47	93.19 345	81.05 347	91.88 130	96.86 80	61.16 406	98.33 165	88.43 172	92.49 245	97.84 116

DP-MVS		87.25 275	85.36 314	92.90 116	97.65 64	83.24 141	94.81 168	92.00 379	74.99 427	81.92 371	95.00 188	72.66 269	99.05 67	66.92 440	92.33 246	96.40 211

GG-mvs-BLEND				87.94 369	89.73 420	77.91 337	87.80 436	78.23 489		80.58 387	83.86 453	59.88 413	95.33 407	71.20 407	92.22 247	90.60 443

tttt0517		88.61 224	87.78 229	91.11 233	94.96 178	77.81 342	95.35 125	89.69 439	85.09 240	88.05 222	94.59 213	66.93 344	98.48 143	83.27 253	92.13 248	97.03 176

UBG		85.51 328	84.57 335	88.35 355	94.21 246	71.78 431	90.07 397	89.66 441	82.28 310	85.91 271	89.01 401	61.30 399	97.06 304	76.58 365	92.06 249	96.22 219

HyFIR lowres test		88.09 240	86.81 253	91.93 191	96.00 122	80.63 245	90.01 399	95.79 195	73.42 444	87.68 231	92.10 308	73.86 252	97.96 214	80.75 303	91.70 250	97.19 159

sss		88.93 216	88.26 217	90.94 245	94.05 254	80.78 242	91.71 346	95.38 234	81.55 336	88.63 210	93.91 245	75.04 228	95.47 404	82.47 266	91.61 251	96.57 207

testing222		84.84 346	83.32 353	89.43 328	94.15 251	75.94 379	91.09 367	89.41 448	84.90 244	85.78 273	89.44 395	52.70 455	96.28 366	70.80 413	91.57 252	96.07 230

cascas		86.43 313	84.98 323	90.80 250	92.10 336	80.92 233	90.24 390	95.91 184	73.10 447	83.57 345	88.39 412	65.15 364	97.46 260	84.90 225	91.43 253	94.03 321

ETVMVS		84.43 353	82.92 362	88.97 340	94.37 229	74.67 393	91.23 364	88.35 453	83.37 284	86.06 268	89.04 400	55.38 439	95.67 395	67.12 436	91.34 254	96.58 206

Effi-MVS+-dtu		88.65 223	88.35 211	89.54 321	93.33 291	76.39 374	94.47 192	94.36 300	87.70 154	85.43 290	89.56 394	73.45 258	97.26 287	85.57 216	91.28 255	94.97 271

thres100view900		87.63 255	86.71 257	90.38 274	96.12 111	78.55 317	95.03 153	91.58 392	87.15 171	88.06 221	92.29 299	68.91 328	98.10 180	70.13 418	91.10 256	94.48 301

tfpn200view9		87.58 260	86.64 261	90.41 271	95.99 125	78.64 314	94.58 183	91.98 381	86.94 181	88.09 218	91.77 320	69.18 324	98.10 180	70.13 418	91.10 256	94.48 301

thres600view7		87.65 252	86.67 260	90.59 253	96.08 117	78.72 311	94.88 161	91.58 392	87.06 175	88.08 220	92.30 298	68.91 328	98.10 180	70.05 421	91.10 256	94.96 274

thres400		87.62 257	86.64 261	90.57 254	95.99 125	78.64 314	94.58 183	91.98 381	86.94 181	88.09 218	91.77 320	69.18 324	98.10 180	70.13 418	91.10 256	94.96 274

testing11		86.44 312	85.35 315	89.69 312	94.29 240	75.40 388	91.30 359	90.53 420	84.76 250	85.06 302	90.13 378	58.95 423	97.45 261	82.08 276	91.09 260	96.21 221

F-COLMAP		87.95 243	86.80 254	91.40 219	96.35 104	80.88 235	94.73 175	95.45 228	79.65 362	82.04 369	94.61 210	71.13 287	98.50 141	76.24 369	91.05 261	94.80 284

thres200		87.21 279	86.24 280	90.12 284	95.36 154	78.53 318	93.26 284	92.10 375	86.42 195	88.00 223	91.11 345	69.24 323	98.00 206	69.58 422	91.04 262	93.83 334

WTY-MVS		89.60 188	88.92 195	91.67 208	95.47 151	81.15 221	92.38 321	94.78 280	83.11 290	89.06 201	94.32 223	78.67 174	96.61 336	81.57 289	90.89 263	97.24 154

testing91		87.11 284	86.18 281	89.92 296	94.43 226	75.38 389	91.53 352	92.27 371	86.48 192	86.50 253	90.24 372	61.19 404	97.53 249	82.10 275	90.88 264	96.84 195

testing3-2		86.72 300	86.71 257	86.74 405	96.11 114	65.92 466	93.39 274	89.65 442	89.46 74	87.84 226	92.79 284	59.17 420	97.60 243	81.31 292	90.72 265	96.70 201

testing99		86.72 300	85.73 305	89.69 312	94.23 244	74.91 392	91.35 358	90.97 409	86.14 203	86.36 259	90.22 373	59.41 417	97.48 256	82.24 272	90.66 266	96.69 202

HY-MVS	83.01 12	89.03 213	87.94 224	92.29 170	94.86 186	82.77 162	92.08 337	94.49 293	81.52 337	86.93 242	92.79 284	78.32 182	98.23 171	79.93 318	90.55 267	95.88 239

WB-MVSnew		83.77 363	83.28 354	85.26 425	91.48 357	71.03 440	91.89 339	87.98 454	78.91 370	84.78 307	90.22 373	69.11 326	94.02 428	64.70 450	90.44 268	90.71 439

CLD-MVS		89.47 193	88.90 197	91.18 229	94.22 245	82.07 189	92.13 334	96.09 166	87.90 144	85.37 296	92.45 293	74.38 240	97.56 247	87.15 193	90.43 269	93.93 324
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CVMVSNet		84.69 350	84.79 329	84.37 434	91.84 345	64.92 472	93.70 261	91.47 397	66.19 474	86.16 266	95.28 172	67.18 342	93.33 440	80.89 301	90.42 270	94.88 280

SCA		86.32 315	85.18 319	89.73 309	92.15 332	76.60 370	91.12 366	91.69 388	83.53 279	85.50 284	88.81 405	66.79 347	96.48 351	76.65 362	90.35 271	96.12 226

UWE-MVS-28		78.98 423	78.38 415	80.80 452	88.18 439	60.66 482	90.65 377	78.51 486	78.84 374	77.93 426	90.93 351	59.08 421	89.02 476	50.96 480	90.33 272	92.72 386

Fast-Effi-MVS+-dtu		87.44 266	86.72 256	89.63 318	92.04 337	77.68 352	94.03 233	93.94 316	85.81 209	82.42 362	91.32 336	70.33 303	97.06 304	80.33 312	90.23 273	94.14 313

OPM-MVS		90.12 168	89.56 173	91.82 201	93.14 297	83.90 119	94.16 219	95.74 199	88.96 99	87.86 224	95.43 166	72.48 273	97.91 220	88.10 177	90.18 274	93.65 347
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SD_0403		84.71 349	84.65 331	84.92 429	92.95 310	65.95 465	92.07 338	93.23 343	83.82 271	79.03 412	93.73 254	73.90 250	92.91 447	63.02 457	90.05 275	95.89 238

HQP_MVS		90.60 159	90.19 152	91.82 201	94.70 200	82.73 166	95.85 93	96.22 145	90.81 27	86.91 244	94.86 196	74.23 242	98.12 178	88.15 173	89.99 276	94.63 287

plane_prior5								96.22 145					98.12 178	88.15 173	89.99 276	94.63 287

XVG-OURS		89.40 200	88.70 201	91.52 212	94.06 253	81.46 210	91.27 362	96.07 168	86.14 203	88.89 206	95.77 149	68.73 331	97.26 287	87.39 189	89.96 278	95.83 242

baseline2		86.50 309	85.39 312	89.84 300	91.12 374	76.70 369	91.88 340	88.58 451	82.35 309	79.95 398	90.95 350	73.42 260	97.63 241	80.27 313	89.95 279	95.19 264

Anonymous202405211		87.68 250	86.13 283	92.31 165	96.66 89	80.74 243	94.87 162	91.49 396	80.47 352	89.46 194	95.44 164	54.72 447	98.23 171	82.19 273	89.89 280	97.97 94

plane_prior						82.73 166	95.21 141		89.66 70						89.88 281

SDMVSNet		90.19 167	89.61 172	91.93 191	96.00 122	83.09 152	92.89 303	95.98 175	88.73 106	86.85 248	95.20 179	72.09 280	97.08 301	88.90 165	89.85 282	95.63 251

sd_testset		88.59 226	87.85 228	90.83 247	96.00 122	80.42 256	92.35 324	94.71 283	88.73 106	86.85 248	95.20 179	67.31 338	96.43 357	79.64 324	89.85 282	95.63 251

TR-MVS		86.78 296	85.76 302	89.82 301	94.37 229	78.41 322	92.47 318	92.83 354	81.11 346	86.36 259	92.40 294	68.73 331	97.48 256	73.75 395	89.85 282	93.57 349

HQP3-MVS								96.04 171							89.77 285

HQP-MVS		89.80 184	89.28 183	91.34 222	94.17 248	81.56 204	94.39 203	96.04 171	88.81 102	85.43 290	93.97 240	73.83 253	97.96 214	87.11 195	89.77 285	94.50 298

XVG-OURS-SEG-HR		89.95 178	89.45 175	91.47 216	94.00 259	81.21 219	91.87 341	96.06 170	85.78 210	88.55 211	95.73 151	74.67 235	97.27 285	88.71 169	89.64 287	95.91 236

GA-MVS		86.61 303	85.27 317	90.66 252	91.33 366	78.71 313	90.40 385	93.81 327	85.34 229	85.12 300	89.57 393	61.25 401	97.11 299	80.99 299	89.59 288	96.15 223

1112_ss		88.42 229	87.33 239	91.72 206	94.92 181	80.98 229	92.97 300	94.54 290	78.16 389	83.82 336	93.88 246	78.78 172	97.91 220	79.45 332	89.41 289	96.26 218

ab-mvs		89.41 198	88.35 211	92.60 141	95.15 168	82.65 174	92.20 332	95.60 215	83.97 266	88.55 211	93.70 255	74.16 246	98.21 174	82.46 267	89.37 290	96.94 185

CR-MVSNet		85.35 333	83.76 348	90.12 284	90.58 399	79.34 300	85.24 462	91.96 383	78.27 386	85.55 279	87.87 422	71.03 289	95.61 396	73.96 392	89.36 291	95.40 257

RPMNet		83.95 360	81.53 371	91.21 227	90.58 399	79.34 300	85.24 462	96.76 93	71.44 458	85.55 279	82.97 462	70.87 292	98.91 97	61.01 462	89.36 291	95.40 257

DSMNet-mixed		76.94 432	76.29 430	78.89 456	83.10 476	56.11 492	87.78 438	79.77 483	60.65 482	75.64 445	88.71 408	61.56 397	88.34 478	60.07 466	89.29 293	92.21 409

LPG-MVS_test		89.45 194	88.90 197	91.12 230	94.47 221	81.49 208	95.30 129	96.14 159	86.73 187	85.45 287	95.16 181	69.89 309	98.10 180	87.70 182	89.23 294	93.77 340

LGP-MVS_train				91.12 230	94.47 221	81.49 208		96.14 159	86.73 187	85.45 287	95.16 181	69.89 309	98.10 180	87.70 182	89.23 294	93.77 340

Test_1112_low_res		87.65 252	86.51 269	91.08 234	94.94 180	79.28 304	91.77 344	94.30 302	76.04 417	83.51 346	92.37 295	77.86 189	97.73 234	78.69 342	89.13 296	96.22 219

PatchmatchNet		85.85 322	84.70 330	89.29 330	91.76 349	75.54 385	88.49 426	91.30 400	81.63 333	85.05 303	88.70 409	71.71 281	96.24 367	74.61 387	89.05 297	96.08 229
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13			83.56 351		91.69 353	69.93 450	87.75 440	91.54 394	78.60 380	84.86 306	88.90 404	69.54 315	96.03 374	70.25 415	88.93 298

MIMVSNet		82.59 374	80.53 377	88.76 343	91.51 356	78.32 326	86.57 453	90.13 428	79.32 364	80.70 385	88.69 410	52.98 454	93.07 445	66.03 444	88.86 299	94.90 279

ACMM	84.12 9	89.14 206	88.48 210	91.12 230	94.65 204	81.22 218	95.31 127	96.12 163	85.31 230	85.92 270	94.34 221	70.19 305	98.06 193	85.65 214	88.86 299	94.08 318
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	84.23 8	89.01 215	88.35 211	90.99 241	94.73 195	81.27 215	95.07 150	95.89 187	86.48 192	83.67 341	94.30 224	69.33 318	97.99 207	87.10 197	88.55 301	93.72 345
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_djsdf		89.03 213	88.64 202	90.21 279	90.74 394	79.28 304	95.96 83	95.90 185	84.66 255	85.33 298	92.94 277	74.02 248	97.30 281	89.64 153	88.53 302	94.05 320

jajsoiax		88.24 236	87.50 234	90.48 266	90.89 387	80.14 263	95.31 127	95.65 212	84.97 243	84.24 328	94.02 236	65.31 363	97.42 266	88.56 170	88.52 303	93.89 325

PatchT		82.68 373	81.27 373	86.89 401	90.09 412	70.94 443	84.06 469	90.15 427	74.91 428	85.63 278	83.57 457	69.37 317	94.87 416	65.19 446	88.50 304	94.84 281

MSDG		84.86 345	83.09 358	90.14 283	93.80 270	80.05 270	89.18 415	93.09 347	78.89 372	78.19 422	91.91 317	65.86 361	97.27 285	68.47 427	88.45 305	93.11 372

MVS-HIRNet		73.70 439	72.20 441	78.18 459	91.81 348	56.42 491	82.94 475	82.58 477	55.24 485	68.88 471	66.48 488	55.32 440	95.13 410	58.12 472	88.42 306	83.01 476

mvs_tets		88.06 242	87.28 241	90.38 274	90.94 383	79.88 279	95.22 138	95.66 210	85.10 239	84.21 329	93.94 241	63.53 380	97.40 274	88.50 171	88.40 307	93.87 329

ET-MVSNet_ETH3D		87.51 263	85.91 295	92.32 164	93.70 280	83.93 118	92.33 326	90.94 411	84.16 261	72.09 462	92.52 291	69.90 308	95.85 385	89.20 159	88.36 308	97.17 160

FIs		90.51 161	90.35 148	90.99 241	93.99 260	80.98 229	95.73 104	97.54 9	89.15 88	86.72 251	94.68 204	81.83 124	97.24 289	85.18 220	88.31 309	94.76 285

PS-MVSNAJss		89.97 176	89.62 171	91.02 238	91.90 343	80.85 239	95.26 135	95.98 175	86.26 199	86.21 264	94.29 225	79.70 157	97.65 238	88.87 167	88.10 310	94.57 292

CMPMVS	59.16 21	80.52 406	79.20 405	84.48 433	83.98 471	67.63 462	89.95 401	93.84 323	64.79 477	66.81 475	91.14 344	57.93 426	95.17 409	76.25 368	88.10 310	90.65 440
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FC-MVSNet-test		90.27 165	90.18 153	90.53 258	93.71 278	79.85 281	95.77 100	97.59 6	89.31 81	86.27 262	94.67 207	81.93 122	97.01 309	84.26 237	88.09 312	94.71 286

ACMMP++															88.01 313

D2MVS		85.90 320	85.09 321	88.35 355	90.79 390	77.42 355	91.83 343	95.70 205	80.77 349	80.08 395	90.02 382	66.74 349	96.37 360	81.88 282	87.97 314	91.26 430

UniMVSNet_ETH3D		87.53 262	86.37 273	91.00 240	92.44 326	78.96 309	94.74 174	95.61 214	84.07 264	85.36 297	94.52 215	59.78 414	97.34 279	82.93 257	87.88 315	96.71 200

PVSNet_BlendedMVS		89.98 175	89.70 168	90.82 249	96.12 111	81.25 216	93.92 244	96.83 83	83.49 280	89.10 199	92.26 300	81.04 135	98.85 104	86.72 200	87.86 316	92.35 405

Syy-MVS		80.07 412	79.78 394	80.94 451	91.92 341	59.93 483	89.75 404	87.40 460	81.72 329	78.82 417	87.20 429	66.29 356	91.29 463	47.06 483	87.84 317	91.60 419

myMVS_eth3d		79.67 417	78.79 411	82.32 448	91.92 341	64.08 474	89.75 404	87.40 460	81.72 329	78.82 417	87.20 429	45.33 475	91.29 463	59.09 470	87.84 317	91.60 419

anonymousdsp		87.84 245	87.09 244	90.12 284	89.13 425	80.54 253	94.67 179	95.55 218	82.05 315	83.82 336	92.12 305	71.47 285	97.15 294	87.15 193	87.80 319	92.67 387

testing3		80.46 407	79.59 399	83.06 442	93.44 289	64.64 473	93.33 276	85.47 468	84.34 260	79.93 399	90.84 354	44.35 477	92.39 451	57.06 475	87.56 320	92.16 410

Anonymous20240529		88.09 240	86.59 265	92.58 143	96.53 97	81.92 195	95.99 79	95.84 192	74.11 437	89.06 201	95.21 178	61.44 398	98.81 110	83.67 250	87.47 321	97.01 179

ACMMP++_ref															87.47 321

XVG-ACMP-BASELINE		86.00 318	84.84 328	89.45 327	91.20 368	78.00 334	91.70 347	95.55 218	85.05 241	82.97 356	92.25 301	54.49 448	97.48 256	82.93 257	87.45 323	92.89 380

EI-MVSNet		89.10 207	88.86 199	89.80 304	91.84 345	78.30 327	93.70 261	95.01 256	85.73 212	87.15 239	95.28 172	79.87 154	97.21 292	83.81 245	87.36 324	93.88 328

MVSTER		88.84 217	88.29 215	90.51 263	92.95 310	80.44 255	93.73 257	95.01 256	84.66 255	87.15 239	93.12 272	72.79 268	97.21 292	87.86 179	87.36 324	93.87 329

EG-PatchMatch MVS		82.37 380	80.34 382	88.46 352	90.27 408	79.35 298	92.80 309	94.33 301	77.14 398	73.26 459	90.18 376	47.47 468	96.72 322	70.25 415	87.32 326	89.30 455

EPMVS		83.90 362	82.70 366	87.51 378	90.23 410	72.67 419	88.62 423	81.96 479	81.37 339	85.01 304	88.34 413	66.31 355	94.45 418	75.30 377	87.12 327	95.43 256

tpm2		84.08 357	82.94 361	87.48 381	91.39 362	71.27 436	89.23 414	90.37 422	71.95 456	84.64 310	89.33 396	67.30 339	96.55 347	75.17 378	87.09 328	94.63 287

CostFormer		85.77 325	84.94 325	88.26 360	91.16 372	72.58 424	89.47 410	91.04 407	76.26 414	86.45 257	89.97 384	70.74 294	96.86 319	82.35 269	87.07 329	95.34 261

Patchmatch-test		81.37 396	79.30 402	87.58 377	90.92 385	74.16 401	80.99 479	87.68 458	70.52 462	76.63 437	88.81 405	71.21 286	92.76 449	60.01 467	86.93 330	95.83 242

mvsany_test1		85.42 331	85.30 316	85.77 418	87.95 442	75.41 387	87.61 444	80.97 481	76.82 407	88.68 209	95.83 143	77.44 194	90.82 467	85.90 211	86.51 331	91.08 437

test_fmvs2		83.98 358	84.03 343	83.83 439	87.16 446	67.53 463	93.93 243	92.89 352	77.62 391	86.89 247	93.53 257	47.18 469	92.02 456	90.54 134	86.51 331	91.93 413

LTVRE_ROB	82.13 13	86.26 316	84.90 326	90.34 276	94.44 225	81.50 206	92.31 328	94.89 270	83.03 294	79.63 405	92.67 286	69.69 312	97.79 227	71.20 407	86.26 333	91.72 416
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
COLMAP_ROB	80.39 16	83.96 359	82.04 368	89.74 307	95.28 158	79.75 285	94.25 214	92.28 370	75.17 425	78.02 425	93.77 251	58.60 424	97.84 225	65.06 449	85.92 334	91.63 418
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
RPSCF		85.07 339	84.27 337	87.48 381	92.91 312	70.62 445	91.69 348	92.46 363	76.20 416	82.67 360	95.22 175	63.94 378	97.29 284	77.51 355	85.80 335	94.53 294

USDC		82.76 371	81.26 374	87.26 388	91.17 370	74.55 395	89.27 412	93.39 339	78.26 387	75.30 447	92.08 309	54.43 449	96.63 330	71.64 404	85.79 336	90.61 441

dmvs_re		84.20 356	83.22 357	87.14 395	91.83 347	77.81 342	90.04 398	90.19 426	84.70 254	81.49 373	89.17 398	64.37 373	91.13 465	71.58 405	85.65 337	92.46 399

usedtu_dtu_shiyan1		86.84 292	85.61 306	90.53 258	90.50 403	81.80 198	90.97 370	94.96 262	83.05 292	83.50 347	90.32 369	72.15 277	96.65 327	79.49 329	85.55 338	93.15 370

FE-MVSNET3		86.84 292	85.61 306	90.53 258	90.50 403	81.80 198	90.97 370	94.96 262	83.05 292	83.50 347	90.32 369	72.15 277	96.65 327	79.49 329	85.55 338	93.15 370

GBi-Net		87.26 273	85.98 291	91.08 234	94.01 256	83.10 149	95.14 147	94.94 264	83.57 276	84.37 320	91.64 324	66.59 351	96.34 363	78.23 347	85.36 340	93.79 335

test1		87.26 273	85.98 291	91.08 234	94.01 256	83.10 149	95.14 147	94.94 264	83.57 276	84.37 320	91.64 324	66.59 351	96.34 363	78.23 347	85.36 340	93.79 335

FMVSNet3		87.40 268	86.11 285	91.30 224	93.79 272	83.64 128	94.20 218	94.81 278	83.89 268	84.37 320	91.87 319	68.45 334	96.56 345	78.23 347	85.36 340	93.70 346

FMVSNet2		87.19 281	85.82 298	91.30 224	94.01 256	83.67 126	94.79 170	94.94 264	83.57 276	83.88 335	92.05 312	66.59 351	96.51 349	77.56 354	85.01 343	93.73 344

viewdifsd2359ckpt11		89.43 196	89.05 190	90.56 256	92.89 313	77.00 362	92.81 306	94.52 291	87.03 176	89.77 186	95.79 146	74.67 235	97.51 251	88.97 163	84.98 344	97.17 160

viewmsd2359difaftdt		89.43 196	89.05 190	90.56 256	92.89 313	77.00 362	92.81 306	94.52 291	87.03 176	89.77 186	95.79 146	74.67 235	97.51 251	88.97 163	84.98 344	97.17 160

ACMH	80.38 17	85.36 332	83.68 349	90.39 272	94.45 224	80.63 245	94.73 175	94.85 274	82.09 313	77.24 431	92.65 287	60.01 412	97.58 245	72.25 402	84.87 346	92.96 377
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ITE_SJBPF				88.24 361	91.88 344	77.05 361		92.92 351	85.54 219	80.13 394	93.30 264	57.29 430	96.20 368	72.46 401	84.71 347	91.49 424

JIA-IIPM		81.04 399	78.98 410	87.25 389	88.64 429	73.48 408	81.75 478	89.61 443	73.19 446	82.05 368	73.71 483	66.07 360	95.87 384	71.18 409	84.60 348	92.41 401

tt0805		86.92 289	85.74 304	90.48 266	92.22 330	79.98 276	95.63 114	94.88 272	83.83 270	84.74 309	92.80 283	57.61 429	97.67 235	85.48 217	84.42 349	93.79 335

OpenMVS_ROB	74.94 19	79.51 419	77.03 426	86.93 398	87.00 447	76.23 377	92.33 326	90.74 417	68.93 466	74.52 452	88.23 416	49.58 462	96.62 333	57.64 473	84.29 350	87.94 470

AllTest		83.42 366	81.39 372	89.52 324	95.01 172	77.79 344	93.12 288	90.89 413	77.41 394	76.12 440	93.34 260	54.08 450	97.51 251	68.31 429	84.27 351	93.26 360

TestCases				89.52 324	95.01 172	77.79 344		90.89 413	77.41 394	76.12 440	93.34 260	54.08 450	97.51 251	68.31 429	84.27 351	93.26 360

VortexMVS		88.42 229	88.01 221	89.63 318	93.89 265	78.82 310	93.82 250	95.47 224	86.67 189	84.53 315	91.99 314	72.62 271	96.65 327	89.02 162	84.09 353	93.41 357

tpm		84.73 347	84.02 344	86.87 402	90.33 407	68.90 454	89.06 417	89.94 434	80.85 348	85.75 274	89.86 387	68.54 333	95.97 378	77.76 351	84.05 354	95.75 245

WBMVS		84.97 343	84.18 339	87.34 384	94.14 252	71.62 435	90.20 393	92.35 366	81.61 334	84.06 330	90.76 358	61.82 393	96.52 348	78.93 339	83.81 355	93.89 325

FMVSNet1		85.85 322	84.11 342	91.08 234	92.81 316	83.10 149	95.14 147	94.94 264	81.64 332	82.68 359	91.64 324	59.01 422	96.34 363	75.37 376	83.78 356	93.79 335

ADS-MVSNet2		81.66 389	79.71 397	87.50 379	91.35 364	74.19 400	83.33 472	88.48 452	72.90 449	82.24 365	85.77 445	64.98 365	93.20 443	64.57 451	83.74 357	95.12 266

ADS-MVSNet		81.56 391	79.78 394	86.90 400	91.35 364	71.82 429	83.33 472	89.16 450	72.90 449	82.24 365	85.77 445	64.98 365	93.76 434	64.57 451	83.74 357	95.12 266

XXY-MVS		87.65 252	86.85 251	90.03 290	92.14 333	80.60 251	93.76 254	95.23 245	82.94 297	84.60 311	94.02 236	74.27 241	95.49 403	81.04 296	83.68 359	94.01 322

test_0402		81.30 398	79.17 406	87.67 375	93.19 294	78.17 330	92.98 299	91.71 386	75.25 424	76.02 443	90.31 371	59.23 418	96.37 360	50.22 481	83.63 360	88.47 467

tpmvs		83.35 368	82.07 367	87.20 393	91.07 376	71.00 442	88.31 429	91.70 387	78.91 370	80.49 389	87.18 431	69.30 321	97.08 301	68.12 432	83.56 361	93.51 353

pmmvs5		84.21 355	82.84 365	88.34 357	88.95 427	76.94 364	92.41 319	91.91 385	75.63 420	80.28 390	91.18 341	64.59 371	95.57 397	77.09 360	83.47 362	92.53 396

pmmvs4		85.43 330	83.86 347	90.16 281	90.02 414	82.97 159	90.27 386	92.67 360	75.93 418	80.73 384	91.74 322	71.05 288	95.73 393	78.85 341	83.46 363	91.78 415

test0.0.03 1		82.41 378	81.69 369	84.59 432	88.23 436	72.89 415	90.24 390	87.83 456	83.41 282	79.86 400	89.78 389	67.25 340	88.99 477	65.18 447	83.42 364	91.90 414

tpmrst		85.35 333	84.99 322	86.43 409	90.88 388	67.88 459	88.71 421	91.43 398	80.13 355	86.08 267	88.80 407	73.05 265	96.02 375	82.48 265	83.40 365	95.40 257

SSC-MVS3.2		84.60 351	84.19 338	85.85 417	92.74 319	68.07 456	88.15 432	93.81 327	87.42 164	83.76 338	91.07 347	62.91 386	95.73 393	74.56 388	83.24 366	93.75 342

nrg030		91.08 144	90.39 147	93.17 99	93.07 302	86.91 23	96.41 42	96.26 140	88.30 121	88.37 215	94.85 198	82.19 115	97.64 240	91.09 122	82.95 367	94.96 274

cl22		86.78 296	85.98 291	89.18 333	92.34 328	77.62 353	90.84 374	94.13 312	81.33 340	83.97 334	90.15 377	73.96 249	96.60 340	84.19 238	82.94 368	93.33 358

miper_ehance_all_eth		87.22 278	86.62 264	89.02 338	92.13 334	77.40 356	90.91 373	94.81 278	81.28 341	84.32 325	90.08 380	79.26 166	96.62 333	83.81 245	82.94 368	93.04 375

miper_enhance_ethall		86.90 290	86.18 281	89.06 336	91.66 354	77.58 354	90.22 392	94.82 277	79.16 368	84.48 316	89.10 399	79.19 168	96.66 326	84.06 240	82.94 368	92.94 378

ACMH+	81.04 14	85.05 340	83.46 352	89.82 301	94.66 203	79.37 297	94.44 194	94.12 313	82.19 312	78.04 424	92.82 281	58.23 425	97.54 248	73.77 394	82.90 371	92.54 395

VPA-MVSNet		89.62 187	88.96 193	91.60 210	93.86 266	82.89 161	95.46 121	97.33 32	87.91 143	88.43 214	93.31 263	74.17 245	97.40 274	87.32 191	82.86 372	94.52 295

IterMVS-LS		88.36 233	87.91 227	89.70 310	93.80 270	78.29 328	93.73 257	95.08 254	85.73 212	84.75 308	91.90 318	79.88 153	96.92 315	83.83 244	82.51 373	93.89 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MonoMVSNet		86.89 291	86.55 267	87.92 370	89.46 423	73.75 403	94.12 221	93.10 346	87.82 150	85.10 301	90.76 358	69.59 314	94.94 415	86.47 202	82.50 374	95.07 268

testgi		80.94 403	80.20 385	83.18 440	87.96 441	66.29 464	91.28 361	90.70 419	83.70 273	78.12 423	92.84 279	51.37 458	90.82 467	63.34 454	82.46 375	92.43 400

test_vis1_rt		77.96 429	76.46 428	82.48 446	85.89 455	71.74 432	90.25 388	78.89 485	71.03 461	71.30 467	81.35 472	42.49 479	91.05 466	84.55 234	82.37 376	84.65 473

WR-MVS		88.38 231	87.67 231	90.52 262	93.30 292	80.18 261	93.26 284	95.96 179	88.57 114	85.47 286	92.81 282	76.12 208	96.91 316	81.24 294	82.29 377	94.47 303

tpm cat1		81.96 381	80.27 383	87.01 396	91.09 375	71.02 441	87.38 446	91.53 395	66.25 473	80.17 391	86.35 441	68.22 336	96.15 371	69.16 423	82.29 377	93.86 331

v1192		87.25 275	86.33 275	90.00 294	90.76 393	79.04 308	93.80 252	95.48 223	82.57 304	85.48 285	91.18 341	73.38 262	97.42 266	82.30 270	82.06 379	93.53 350

v1144		87.61 258	86.79 255	90.06 288	91.01 378	79.34 300	93.95 241	95.42 233	83.36 285	85.66 277	91.31 337	74.98 229	97.42 266	83.37 251	82.06 379	93.42 356

v1240		86.78 296	85.85 297	89.56 320	90.45 406	77.79 344	93.61 265	95.37 236	81.65 331	85.43 290	91.15 343	71.50 284	97.43 265	81.47 291	82.05 381	93.47 354

Anonymous20231206		81.03 400	79.77 396	84.82 430	87.85 443	70.26 448	91.42 354	92.08 376	73.67 441	77.75 428	89.25 397	62.43 389	93.08 444	61.50 461	82.00 382	91.12 434

V42		87.68 250	86.86 250	90.15 282	90.58 399	80.14 263	94.24 216	95.28 243	83.66 274	85.67 276	91.33 334	74.73 233	97.41 272	84.43 236	81.83 383	92.89 380

v1921920		86.97 288	86.06 288	89.69 312	90.53 402	78.11 332	93.80 252	95.43 231	81.90 322	85.33 298	91.05 348	72.66 269	97.41 272	82.05 278	81.80 384	93.53 350

v2v482		87.84 245	87.06 245	90.17 280	90.99 379	79.23 307	94.00 238	95.13 249	84.87 246	85.53 281	92.07 311	74.45 239	97.45 261	84.71 232	81.75 385	93.85 332

Anonymous20231211		86.59 305	85.13 320	90.98 243	96.52 98	81.50 206	96.14 64	96.16 158	73.78 440	83.65 342	92.15 303	63.26 383	97.37 278	82.82 261	81.74 386	94.06 319

v144192		87.19 281	86.35 274	89.74 307	90.64 397	78.24 329	93.92 244	95.43 231	81.93 320	85.51 283	91.05 348	74.21 244	97.45 261	82.86 259	81.56 387	93.53 350

cl____		86.52 308	85.78 299	88.75 344	92.03 338	76.46 372	90.74 375	94.30 302	81.83 327	83.34 352	90.78 357	75.74 221	96.57 343	81.74 286	81.54 388	93.22 364

DIV-MVS_self_test		86.53 307	85.78 299	88.75 344	92.02 339	76.45 373	90.74 375	94.30 302	81.83 327	83.34 352	90.82 355	75.75 219	96.57 343	81.73 287	81.52 389	93.24 363

Anonymous20240521		80.44 408	79.21 404	84.11 437	85.75 457	67.89 458	92.86 305	93.23 343	75.61 421	75.59 446	87.47 426	50.03 460	94.33 423	71.14 410	81.21 390	90.12 448

OurMVSNet-221017-0		85.35 333	84.64 333	87.49 380	90.77 392	72.59 423	94.01 236	94.40 298	84.72 252	79.62 406	93.17 269	61.91 392	96.72 322	81.99 279	81.16 391	93.16 368

FMVSNet5		81.52 394	79.60 398	87.27 387	91.17 370	77.95 335	91.49 353	92.26 372	76.87 406	76.16 439	87.91 421	51.67 457	92.34 452	67.74 433	81.16 391	91.52 422

CP-MVSNet		87.63 255	87.26 243	88.74 346	93.12 298	76.59 371	95.29 131	96.58 111	88.43 117	83.49 349	92.98 276	75.28 225	95.83 386	78.97 338	81.15 393	93.79 335

c3_l		87.14 283	86.50 270	89.04 337	92.20 331	77.26 358	91.22 365	94.70 284	82.01 318	84.34 324	90.43 367	78.81 171	96.61 336	83.70 249	81.09 394	93.25 362

IterMVS-SCA-FT		85.45 329	84.53 336	88.18 363	91.71 351	76.87 365	90.19 394	92.65 361	85.40 228	81.44 375	90.54 363	66.79 347	95.00 414	81.04 296	81.05 395	92.66 388

TinyColmap		79.76 416	77.69 418	85.97 413	91.71 351	73.12 412	89.55 406	90.36 423	75.03 426	72.03 463	90.19 375	46.22 474	96.19 370	63.11 455	81.03 396	88.59 466

UniMVSNet_NR-MVSNet		89.92 180	89.29 182	91.81 203	93.39 290	83.72 124	94.43 195	97.12 55	89.80 62	86.46 255	93.32 262	83.16 95	97.23 290	84.92 223	81.02 397	94.49 300

DU-MVS		89.34 203	88.50 207	91.85 199	93.04 305	83.72 124	94.47 192	96.59 110	89.50 73	86.46 255	93.29 265	77.25 195	97.23 290	84.92 223	81.02 397	94.59 290

PS-CasMVS		87.32 272	86.88 249	88.63 349	92.99 308	76.33 376	95.33 126	96.61 109	88.22 125	83.30 354	93.07 274	73.03 266	95.79 390	78.36 344	81.00 399	93.75 342

IterMVS		84.88 344	83.98 346	87.60 376	91.44 358	76.03 378	90.18 395	92.41 364	83.24 288	81.06 381	90.42 368	66.60 350	94.28 425	79.46 331	80.98 400	92.48 397
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet (Re)		89.80 184	89.07 188	92.01 182	93.60 284	84.52 97	94.78 171	97.47 16	89.26 84	86.44 258	92.32 297	82.10 117	97.39 277	84.81 226	80.84 401	94.12 314

LF4IMVS		80.37 409	79.07 409	84.27 436	86.64 448	69.87 452	89.39 411	91.05 406	76.38 411	74.97 449	90.00 383	47.85 467	94.25 426	74.55 389	80.82 402	88.69 465

v10		87.25 275	86.38 272	89.85 299	91.19 369	79.50 290	94.48 189	95.45 228	83.79 272	83.62 343	91.19 339	75.13 226	97.42 266	81.94 280	80.60 403	92.63 389

tfpnnormal		84.72 348	83.23 356	89.20 332	92.79 317	80.05 270	94.48 189	95.81 193	82.38 307	81.08 380	91.21 338	69.01 327	96.95 313	61.69 460	80.59 404	90.58 444

WR-MVS_H		87.80 247	87.37 238	89.10 335	93.23 293	78.12 331	95.61 115	97.30 37	87.90 144	83.72 339	92.01 313	79.65 163	96.01 377	76.36 366	80.54 405	93.16 368

VPNet		88.20 237	87.47 236	90.39 272	93.56 285	79.46 292	94.04 232	95.54 220	88.67 109	86.96 241	94.58 214	69.33 318	97.15 294	84.05 241	80.53 406	94.56 293

v7n		86.81 294	85.76 302	89.95 295	90.72 395	79.25 306	95.07 150	95.92 182	84.45 258	82.29 363	90.86 352	72.60 272	97.53 249	79.42 335	80.52 407	93.08 374

v8		87.50 265	86.71 257	89.89 297	91.37 363	79.40 296	94.50 188	95.38 234	84.81 249	83.60 344	91.33 334	76.05 209	97.42 266	82.84 260	80.51 408	92.84 382

EU-MVSNet		81.32 397	80.95 375	82.42 447	88.50 432	63.67 476	93.32 277	91.33 399	64.02 478	80.57 388	92.83 280	61.21 403	92.27 453	76.34 367	80.38 409	91.32 428

Patchmtry		82.71 372	80.93 376	88.06 365	90.05 413	76.37 375	84.74 467	91.96 383	72.28 455	81.32 378	87.87 422	71.03 289	95.50 402	68.97 424	80.15 410	92.32 406

NR-MVSNet		88.58 227	87.47 236	91.93 191	93.04 305	84.16 112	94.77 172	96.25 142	89.05 92	80.04 396	93.29 265	79.02 169	97.05 306	81.71 288	80.05 411	94.59 290

Baseline_NR-MVSNet		87.07 285	86.63 263	88.40 353	91.44 358	77.87 340	94.23 217	92.57 362	84.12 263	85.74 275	92.08 309	77.25 195	96.04 373	82.29 271	79.94 412	91.30 429

dp		81.47 395	80.23 384	85.17 426	89.92 416	65.49 469	86.74 451	90.10 429	76.30 413	81.10 379	87.12 432	62.81 387	95.92 381	68.13 431	79.88 413	94.09 317

TranMVSNet+NR-MVSNet		88.84 217	87.95 223	91.49 214	92.68 321	83.01 157	94.92 159	96.31 131	89.88 56	85.53 281	93.85 248	76.63 203	96.96 312	81.91 281	79.87 414	94.50 298

miper_lstm_enhance		85.27 336	84.59 334	87.31 386	91.28 367	74.63 394	87.69 441	94.09 314	81.20 345	81.36 377	89.85 388	74.97 230	94.30 424	81.03 298	79.84 415	93.01 376

reproduce_monomvs		86.37 314	85.87 296	87.87 371	93.66 282	73.71 404	93.44 272	95.02 255	88.61 112	82.64 361	91.94 316	57.88 427	96.68 325	89.96 144	79.71 416	93.22 364

v148		87.04 286	86.32 276	89.21 331	90.94 383	77.26 358	93.71 260	94.43 295	84.84 248	84.36 323	90.80 356	76.04 210	97.05 306	82.12 274	79.60 417	93.31 359

IB-MVS	80.51 15	85.24 337	83.26 355	91.19 228	92.13 334	79.86 280	91.75 345	91.29 401	83.28 287	80.66 386	88.49 411	61.28 400	98.46 147	80.99 299	79.46 418	95.25 263
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
eth_miper_zixun_eth		86.50 309	85.77 301	88.68 347	91.94 340	75.81 382	90.47 384	94.89 270	82.05 315	84.05 331	90.46 366	75.96 213	96.77 320	82.76 263	79.36 419	93.46 355

baseline1		88.10 239	87.28 241	90.57 254	94.96 178	80.07 268	94.27 213	91.29 401	86.74 186	87.41 235	94.00 238	76.77 200	96.20 368	80.77 302	79.31 420	95.44 255

our_test_3		81.93 383	80.46 381	86.33 411	88.46 433	73.48 408	88.46 427	91.11 403	76.46 408	76.69 436	88.25 415	66.89 345	94.36 422	68.75 425	79.08 421	91.14 433

PEN-MVS		86.80 295	86.27 279	88.40 353	92.32 329	75.71 384	95.18 144	96.38 126	87.97 138	82.82 358	93.15 270	73.39 261	95.92 381	76.15 370	79.03 422	93.59 348

pm-mvs1		86.61 303	85.54 308	89.82 301	91.44 358	80.18 261	95.28 133	94.85 274	83.84 269	81.66 372	92.62 288	72.45 275	96.48 351	79.67 323	78.06 423	92.82 383

h-mvs33		90.80 147	90.15 154	92.75 130	96.01 121	82.66 170	95.43 123	95.53 221	89.80 62	93.08 90	95.64 155	75.77 216	99.00 80	92.07 100	78.05 424	96.60 204

SixPastTwentyTwo		83.91 361	82.90 363	86.92 399	90.99 379	70.67 444	93.48 269	91.99 380	85.54 219	77.62 430	92.11 307	60.59 408	96.87 318	76.05 371	77.75 425	93.20 366

ppachtmachnet_test		81.84 384	80.07 388	87.15 394	88.46 433	74.43 398	89.04 418	92.16 374	75.33 423	77.75 428	88.99 402	66.20 357	95.37 406	65.12 448	77.60 426	91.65 417

MIMVSNet1		79.38 420	77.28 422	85.69 419	86.35 450	73.67 405	91.61 350	92.75 358	78.11 390	72.64 461	88.12 417	48.16 466	91.97 458	60.32 464	77.49 427	91.43 427

DTE-MVSNet		86.11 317	85.48 310	87.98 367	91.65 355	74.92 391	94.93 158	95.75 198	87.36 166	82.26 364	93.04 275	72.85 267	95.82 387	74.04 390	77.46 428	93.20 366

N_pmnet		68.89 445	68.44 447	70.23 467	89.07 426	28.79 506	88.06 433	19.50 506	69.47 465	71.86 465	84.93 449	61.24 402	91.75 460	54.70 477	77.15 429	90.15 447

AUN-MVS		87.78 248	86.54 268	91.48 215	94.82 189	81.05 226	93.91 246	93.93 317	83.00 295	86.93 242	93.53 257	69.50 316	97.67 235	86.14 206	77.12 430	95.73 248

hse-mvs2		89.88 182	89.34 180	91.51 213	94.83 188	81.12 223	93.94 242	93.91 320	89.80 62	93.08 90	93.60 256	75.77 216	97.66 237	92.07 100	77.07 431	95.74 246

dmvs_testset		74.57 438	75.81 435	70.86 466	87.72 444	40.47 501	87.05 449	77.90 491	82.75 301	71.15 468	85.47 447	67.98 337	84.12 488	45.26 484	76.98 432	88.00 469

test20.03		79.95 414	79.08 408	82.55 444	85.79 456	67.74 461	91.09 367	91.08 404	81.23 344	74.48 453	89.96 385	61.63 394	90.15 469	60.08 465	76.38 433	89.76 450

FPMVS		64.63 450	62.55 452	70.88 465	70.80 494	56.71 487	84.42 468	84.42 472	51.78 488	49.57 488	81.61 471	23.49 492	81.48 491	40.61 490	76.25 434	74.46 484

test_fmvs3		77.67 430	77.16 425	79.22 455	79.52 484	61.14 480	92.34 325	91.64 391	73.98 438	78.86 416	86.59 435	27.38 490	87.03 479	88.12 176	75.97 435	89.50 452

EGC-MVSNET		61.97 451	56.37 456	78.77 457	89.63 421	73.50 407	89.12 416	82.79 476	0.21 503	1.24 504	84.80 450	39.48 480	90.04 470	44.13 485	75.94 436	72.79 485

pmmvs6		83.42 366	81.60 370	88.87 341	88.01 440	77.87 340	94.96 156	94.24 306	74.67 431	78.80 419	91.09 346	60.17 411	96.49 350	77.06 361	75.40 437	92.23 408

new_pmnet		72.15 441	70.13 444	78.20 458	82.95 477	65.68 467	83.91 470	82.40 478	62.94 480	64.47 477	79.82 474	42.85 478	86.26 483	57.41 474	74.44 438	82.65 478

FE-MVSNET2		81.82 385	79.99 391	87.34 384	84.74 469	77.36 357	92.72 310	94.55 289	82.09 313	73.79 456	86.46 436	57.80 428	94.45 418	74.65 385	73.10 439	90.20 446

MDA-MVSNet_test_wron		79.21 422	77.19 424	85.29 423	88.22 437	72.77 417	85.87 456	90.06 430	74.34 433	62.62 480	87.56 425	66.14 358	91.99 457	66.90 441	73.01 440	91.10 436

YYNet1		79.22 421	77.20 423	85.28 424	88.20 438	72.66 420	85.87 456	90.05 432	74.33 434	62.70 478	87.61 424	66.09 359	92.03 454	66.94 438	72.97 441	91.15 432

Patchmatch-RL test		81.67 388	79.96 392	86.81 403	85.42 462	71.23 437	82.17 477	87.50 459	78.47 381	77.19 432	82.50 469	70.81 293	93.48 438	82.66 264	72.89 442	95.71 249

pmmvs-eth3d		80.97 402	78.72 412	87.74 372	84.99 468	79.97 277	90.11 396	91.65 390	75.36 422	73.51 457	86.03 442	59.45 416	93.96 432	75.17 378	72.21 443	89.29 457

0.4-1-1-0.1		81.55 392	78.59 414	90.42 270	87.55 445	79.90 278	88.56 424	89.19 449	77.01 403	79.72 403	77.71 476	54.84 444	97.11 299	80.50 309	72.20 444	94.26 309

PM-MVS		78.11 428	76.12 431	84.09 438	83.54 474	70.08 449	88.97 419	85.27 470	79.93 357	74.73 451	86.43 438	34.70 486	93.48 438	79.43 334	72.06 445	88.72 464

0.4-1-1-0.2		80.84 404	77.77 417	90.06 288	86.18 453	79.35 298	86.75 450	89.54 445	76.23 415	78.59 421	75.46 480	55.03 443	96.99 310	80.11 316	72.05 446	93.85 332

test_f		71.95 442	70.87 443	75.21 462	74.21 492	59.37 485	85.07 464	85.82 465	65.25 476	70.42 469	83.13 459	23.62 491	82.93 490	78.32 345	71.94 447	83.33 475

0.3-1-1-0.015		80.75 405	77.58 419	90.25 278	86.55 449	79.72 287	87.46 445	89.48 447	76.43 410	77.93 426	75.94 477	52.31 456	97.05 306	80.25 314	71.85 448	93.99 323

sc_t1		81.53 393	78.67 413	90.12 284	90.78 391	78.64 314	93.91 246	90.20 425	68.42 467	80.82 383	89.88 386	46.48 471	96.76 321	76.03 372	71.47 449	94.96 274

tt0320		80.13 411	77.41 420	88.29 358	90.50 403	78.02 333	93.10 291	90.71 418	66.06 475	76.75 435	86.97 434	49.56 463	95.40 405	71.65 403	71.41 450	91.46 426

Gipuma		57.99 457	54.91 459	67.24 473	88.51 430	65.59 468	52.21 494	90.33 424	43.58 491	42.84 494	51.18 495	20.29 496	85.07 485	34.77 491	70.45 451	51.05 494
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
FE-MVSNET		78.19 427	76.03 432	84.69 431	83.70 473	73.31 410	90.58 380	90.00 433	77.11 402	71.91 464	85.47 447	55.53 437	91.94 459	59.69 468	70.24 452	88.83 463

APD_test1		69.04 444	66.26 450	77.36 461	80.51 482	62.79 479	85.46 461	83.51 475	54.11 487	59.14 484	84.79 451	23.40 493	89.61 472	55.22 476	70.24 452	79.68 482

blend_shiyan4		81.94 382	79.35 401	89.70 310	85.52 460	80.08 266	91.29 360	93.82 324	77.12 401	79.31 409	82.94 463	54.81 445	96.60 340	79.60 325	69.78 454	92.41 401

K. test v3		81.59 390	80.15 387	85.91 416	89.89 417	69.42 453	92.57 315	87.71 457	85.56 218	73.44 458	89.71 391	55.58 435	95.52 399	77.17 358	69.76 455	92.78 385

KD-MVS_self_test		80.20 410	79.24 403	83.07 441	85.64 458	65.29 470	91.01 369	93.93 317	78.71 379	76.32 438	86.40 440	59.20 419	92.93 446	72.59 400	69.35 456	91.00 438

CL-MVSNet_self_test		81.74 387	80.53 377	85.36 422	85.96 454	72.45 425	90.25 388	93.07 348	81.24 343	79.85 401	87.29 428	70.93 291	92.52 450	66.95 437	69.23 457	91.11 435

TDRefinement		79.81 415	77.34 421	87.22 392	79.24 485	75.48 386	93.12 288	92.03 378	76.45 409	75.01 448	91.58 330	49.19 464	96.44 356	70.22 417	69.18 458	89.75 451

gbinet_0.2-2-1-0.02		82.59 374	80.19 386	89.77 305	85.23 464	80.05 270	91.59 351	93.52 336	77.60 392	79.78 402	82.87 464	63.26 383	96.45 355	78.93 339	68.97 459	92.81 384

MDA-MVSNet-bldmvs		78.85 424	76.31 429	86.46 407	89.76 418	73.88 402	88.79 420	90.42 421	79.16 368	59.18 483	88.33 414	60.20 410	94.04 427	62.00 459	68.96 460	91.48 425

ambc				83.06 442	79.99 483	63.51 477	77.47 487	92.86 353		74.34 454	84.45 452	28.74 487	95.06 413	73.06 398	68.89 461	90.61 441

blended_shiyan8		82.79 369	80.49 379	89.69 312	85.50 461	79.83 283	91.38 355	93.82 324	77.14 398	79.39 408	83.73 455	64.95 368	96.63 330	79.75 320	68.77 462	92.62 391

wanda-best-256-512		82.44 376	80.07 388	89.53 322	85.12 465	79.44 294	90.49 382	93.75 330	76.97 404	79.00 413	82.72 465	64.29 374	96.61 336	79.56 327	68.75 463	92.55 392

FE-blended-shiyan7		82.44 376	80.07 388	89.53 322	85.12 465	79.44 294	90.49 382	93.75 330	76.97 404	79.00 413	82.72 465	64.29 374	96.61 336	79.56 327	68.75 463	92.55 392

blended_shiyan6		82.78 370	80.48 380	89.67 317	85.53 459	79.76 284	91.37 356	93.82 324	77.14 398	79.30 410	83.73 455	64.96 367	96.63 330	79.68 322	68.75 463	92.63 389

usedtu_blend_shiyan5		82.39 379	79.93 393	89.75 306	85.12 465	80.08 266	92.36 322	93.26 341	74.29 435	79.00 413	82.72 465	64.29 374	96.60 340	79.60 325	68.75 463	92.55 392

TransMVSNet (Re)		84.43 353	83.06 360	88.54 350	91.72 350	78.44 321	95.18 144	92.82 356	82.73 302	79.67 404	92.12 305	73.49 257	95.96 379	71.10 411	68.73 467	91.21 431

tt0320-xc		79.63 418	76.66 427	88.52 351	91.03 377	78.72 311	93.00 297	89.53 446	66.37 472	76.11 442	87.11 433	46.36 473	95.32 408	72.78 399	67.67 468	91.51 423

mvsany_test3		74.95 436	73.26 440	80.02 454	74.61 490	63.16 478	85.53 460	78.42 487	74.16 436	74.89 450	86.46 436	36.02 485	89.09 475	82.39 268	66.91 469	87.82 471

mvs5depth		80.98 401	79.15 407	86.45 408	84.57 470	73.29 411	87.79 437	91.67 389	80.52 351	82.20 367	89.72 390	55.14 442	95.93 380	73.93 393	66.83 470	90.12 448

usedtu_dtu_shiyan2		74.72 437	71.30 442	84.98 428	77.78 487	70.58 446	91.85 342	90.76 416	67.24 471	68.06 474	82.17 470	37.13 483	92.78 448	60.69 463	66.03 471	91.59 421

PMVS	47.18 22	52.22 459	48.46 463	63.48 474	45.72 505	46.20 497	73.41 490	78.31 488	41.03 494	30.06 497	65.68 489	6.05 503	83.43 489	30.04 493	65.86 472	60.80 489
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		65.12 449	62.60 451	72.69 464	71.44 493	60.71 481	87.17 447	65.55 497	63.80 479	53.22 487	65.65 490	14.54 500	89.44 474	76.65 362	65.38 473	67.91 488

lessismore_v0				86.04 412	88.46 433	68.78 455		80.59 482		73.01 460	90.11 379	55.39 438	96.43 357	75.06 380	65.06 474	92.90 379

new-patchmatchnet		76.41 434	75.17 436	80.13 453	82.65 478	59.61 484	87.66 442	91.08 404	78.23 388	69.85 470	83.22 458	54.76 446	91.63 462	64.14 453	64.89 475	89.16 459

pmmvs3		71.81 443	68.71 446	81.11 450	75.86 489	70.42 447	86.74 451	83.66 474	58.95 484	68.64 473	80.89 473	36.93 484	89.52 473	63.10 456	63.59 476	83.39 474

UnsupCasMVSNet_eth		80.07 412	78.27 416	85.46 421	85.24 463	72.63 422	88.45 428	94.87 273	82.99 296	71.64 466	88.07 418	56.34 433	91.75 460	73.48 396	63.36 477	92.01 412

ttmdpeth		76.55 433	74.64 438	82.29 449	82.25 479	67.81 460	89.76 403	85.69 466	70.35 463	75.76 444	91.69 323	46.88 470	89.77 471	66.16 443	63.23 478	89.30 455

mmtdpeth		85.04 342	84.15 341	87.72 374	93.11 299	75.74 383	94.37 207	92.83 354	84.98 242	89.31 196	86.41 439	61.61 396	97.14 297	92.63 81	62.11 479	90.29 445

LCM-MVSNet		66.00 448	62.16 453	77.51 460	64.51 500	58.29 486	83.87 471	90.90 412	48.17 489	54.69 486	73.31 484	16.83 499	86.75 480	65.47 445	61.67 480	87.48 472

UnsupCasMVSNet_bld		76.23 435	73.27 439	85.09 427	83.79 472	72.92 414	85.65 459	93.47 338	71.52 457	68.84 472	79.08 475	49.77 461	93.21 442	66.81 442	60.52 481	89.13 461

testf1		59.54 453	56.11 457	69.85 468	69.28 495	56.61 489	80.37 481	76.55 494	42.58 492	45.68 491	75.61 478	11.26 501	84.18 486	43.20 487	60.44 482	68.75 486

APD_test2		59.54 453	56.11 457	69.85 468	69.28 495	56.61 489	80.37 481	76.55 494	42.58 492	45.68 491	75.61 478	11.26 501	84.18 486	43.20 487	60.44 482	68.75 486

KD-MVS_2432*1600		78.50 425	76.02 433	85.93 414	86.22 451	74.47 396	84.80 465	92.33 367	79.29 365	76.98 433	85.92 443	53.81 452	93.97 430	67.39 434	57.42 484	89.36 453

miper_refine_blended		78.50 425	76.02 433	85.93 414	86.22 451	74.47 396	84.80 465	92.33 367	79.29 365	76.98 433	85.92 443	53.81 452	93.97 430	67.39 434	57.42 484	89.36 453

MVStest1		72.91 440	69.70 445	82.54 445	78.14 486	73.05 413	88.21 431	86.21 462	60.69 481	64.70 476	90.53 364	46.44 472	85.70 484	58.78 471	53.62 486	88.87 462

DeepMVS_CX				56.31 478	74.23 491	51.81 494		56.67 502	44.85 490	48.54 490	75.16 481	27.87 489	58.74 500	40.92 489	52.22 487	58.39 492

WB-MVS		67.92 446	67.49 448	69.21 470	81.09 480	41.17 500	88.03 434	78.00 490	73.50 443	62.63 479	83.11 461	63.94 378	86.52 481	25.66 495	51.45 488	79.94 481

PVSNet_0	73.20 20	77.22 431	74.83 437	84.37 434	90.70 396	71.10 439	83.09 474	89.67 440	72.81 451	73.93 455	83.13 459	60.79 407	93.70 436	68.54 426	50.84 489	88.30 468

test_method		50.52 460	48.47 462	56.66 477	52.26 504	18.98 508	41.51 496	81.40 480	10.10 498	44.59 493	75.01 482	28.51 488	68.16 495	53.54 478	49.31 490	82.83 477

SSC-MVS		67.06 447	66.56 449	68.56 472	80.54 481	40.06 502	87.77 439	77.37 493	72.38 453	61.75 481	82.66 468	63.37 381	86.45 482	24.48 496	48.69 491	79.16 483

PMMVS2		59.60 452	56.40 455	69.21 470	68.83 497	46.58 496	73.02 491	77.48 492	55.07 486	49.21 489	72.95 485	17.43 498	80.04 492	49.32 482	44.33 492	80.99 480

dongtai		58.82 456	58.24 454	60.56 475	83.13 475	45.09 499	82.32 476	48.22 505	67.61 469	61.70 482	69.15 486	38.75 481	76.05 494	32.01 492	41.31 493	60.55 490

kuosan		53.51 458	53.30 461	54.13 479	76.06 488	45.36 498	80.11 483	48.36 504	59.63 483	54.84 485	63.43 492	37.41 482	62.07 499	20.73 498	39.10 494	54.96 493

MVE	39.65 23	43.39 461	38.59 467	57.77 476	56.52 502	48.77 495	55.38 493	58.64 501	29.33 497	28.96 498	52.65 494	4.68 504	64.62 498	28.11 494	33.07 495	59.93 491
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		43.23 462	42.29 464	46.03 480	65.58 499	37.41 503	73.51 489	64.62 498	33.99 495	28.47 499	47.87 496	19.90 497	67.91 496	22.23 497	24.45 496	32.77 495

ANet_high		58.88 455	54.22 460	72.86 463	56.50 503	56.67 488	80.75 480	86.00 464	73.09 448	37.39 495	64.63 491	22.17 494	79.49 493	43.51 486	23.96 497	82.43 479

EMVS		42.07 463	41.12 465	44.92 481	63.45 501	35.56 505	73.65 488	63.48 499	33.05 496	26.88 500	45.45 497	21.27 495	67.14 497	19.80 499	23.02 498	32.06 496

tmp_tt		35.64 464	39.24 466	24.84 482	14.87 506	23.90 507	62.71 492	51.51 503	6.58 500	36.66 496	62.08 493	44.37 476	30.34 502	52.40 479	22.00 499	20.27 497

wuyk23d		21.27 466	20.48 469	23.63 483	68.59 498	36.41 504	49.57 495	6.85 507	9.37 499	7.89 501	4.46 503	4.03 505	31.37 501	17.47 500	16.07 500	3.12 498

testmvs		8.92 467	11.52 470	1.12 485	1.06 507	0.46 510	86.02 455	0.65 508	0.62 501	2.74 502	9.52 501	0.31 507	0.45 504	2.38 501	0.39 501	2.46 500

test123		8.76 468	11.22 471	1.39 484	0.85 508	0.97 509	85.76 458	0.35 509	0.54 502	2.45 503	8.14 502	0.60 506	0.48 503	2.16 502	0.17 502	2.71 499

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		22.14 465	29.52 468	0.00 486	0.00 509	0.00 511	0.00 497	95.76 197	0.00 504	0.00 505	94.29 225	75.66 222	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		6.64 470	8.86 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	79.70 157	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		7.82 469	10.43 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	93.88 246	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						64.08 474								59.14 469

FOURS1					98.86 4	85.54 74	98.29 1	97.49 11	89.79 65	96.29 32

test_one_0601					98.58 14	85.83 68		97.44 20	91.05 23	96.78 27	98.06 24	91.45 12

eth-test2					0.00 509

eth-test					0.00 509

test_241102_ONE					98.77 8	85.99 56		97.44 20	90.26 49	97.71 2	97.96 33	92.31 5	99.38 35

save fliter					97.85 55	85.63 73	95.21 141	96.82 85	89.44 75

test0726					98.78 6	85.93 59	97.19 16	97.47 16	90.27 47	97.64 6	98.13 7	91.47 9

GSMVS																96.12 226

test_part2					98.55 15	87.22 20				96.40 31

sam_mvs1												71.70 282				96.12 226

sam_mvs												70.60 296

MTGPA								96.97 65

test_post1							88.00 435				9.81 500	69.31 320	95.53 398	76.65 362

test_post											10.29 499	70.57 300	95.91 383

patchmatchnet-post											83.76 454	71.53 283	96.48 351

MTMP							96.16 60	60.64 500

gm-plane-assit					89.60 422	68.00 457			77.28 397		88.99 402		97.57 246	79.44 333

TEST9					97.53 67	86.49 38	94.07 229	96.78 90	81.61 334	92.77 101	96.20 109	87.71 32	99.12 63

test_8					97.49 69	86.30 46	94.02 235	96.76 93	81.86 325	92.70 105	96.20 109	87.63 33	99.02 73

agg_prior					97.38 72	85.92 61		96.72 100		92.16 120			98.97 87

test_prior4						85.96 58	94.11 223

test_prior				93.82 74	97.29 77	84.49 98		96.88 78					98.87 100			98.11 81

旧先验2							93.36 275		71.25 459	94.37 61			97.13 298	86.74 198

新几何2							93.11 290

无先验							93.28 283	96.26 140	73.95 439				99.05 67	80.56 307		96.59 205

原ACMM2							92.94 301

testdata2													98.75 116	78.30 346

segment_acmp												87.16 40

testdata1							92.15 333		87.94 140

plane_prior7					94.70 200	82.74 165

plane_prior6					94.52 216	82.75 163						74.23 242

plane_prior4											94.86 196

plane_prior3						82.75 163			90.26 49	86.91 244

plane_prior2							95.85 93		90.81 27

plane_prior1					94.59 209

n2								0.00 510

nn								0.00 510

door-mid								85.49 467

test11								96.57 112

door								85.33 469

HQP5-MVS						81.56 204

HQP-NCC					94.17 248		94.39 203		88.81 102	85.43 290

ACMP_Plane					94.17 248		94.39 203		88.81 102	85.43 290

BP-MVS														87.11 195

HQP4-MVS										85.43 290			97.96 214			94.51 297

HQP2-MVS												73.83 253

NP-MVS					94.37 229	82.42 179					93.98 239

MDTV_nov1_ep13_2view						55.91 493	87.62 443		73.32 445	84.59 312		70.33 303		74.65 385		95.50 254

Test By Simon												80.02 146

High-resolution multi-view benchmark