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.

PC_three_1452									90.77 252	98.89 28	98.28 87	96.24 1	98.35 296	95.76 108	99.58 26	99.59 33

DVP-MVS++		98.06 2	97.99 3	98.28 10	98.67 68	95.39 13	99.29 1	98.28 52	94.78 64	98.93 22	98.87 34	96.04 2	99.86 11	97.45 47	99.58 26	99.59 33

OPU-MVS				98.55 3	98.82 62	96.86 3	98.25 40				98.26 88	96.04 2	99.24 153	95.36 127	99.59 22	99.56 41

test_0728_THIRD									94.78 64	98.73 32	98.87 34	95.87 4	99.84 27	97.45 47	99.72 2	99.77 4

SED-MVS		98.05 3	97.99 3	98.24 12	99.42 10	95.30 19	98.25 40	98.27 56	95.13 43	99.19 14	98.89 31	95.54 5	99.85 22	97.52 43	99.66 10	99.56 41

test_241102_ONE					99.42 10	95.30 19		98.27 56	95.09 46	99.19 14	98.81 40	95.54 5	99.65 81

MED-MVS		98.08 1	98.08 2	98.06 21	99.56 1	94.50 37	98.69 11	98.70 16	95.63 26	98.73 32	98.95 21	95.46 7	99.86 11	97.40 51	99.63 17	99.82 1

test_one_0601					99.32 27	95.20 22		98.25 62	95.13 43	98.48 41	98.87 34	95.16 8

DVP-MVS		97.91 5	97.81 6	98.22 15	99.45 6	95.36 15	98.21 48	97.85 139	94.92 53	98.73 32	98.87 34	95.08 9	99.84 27	97.52 43	99.67 6	99.48 57
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
test0726					99.45 6	95.36 15	98.31 32	98.29 50	94.92 53	98.99 19	98.92 26	95.08 9

DPE-MVS		97.86 6	97.65 11	98.47 5	99.17 39	95.78 8	97.21 203	98.35 41	95.16 41	98.71 36	98.80 41	95.05 11	99.89 3	96.70 70	99.73 1	99.73 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_241102_TWO								98.27 56	95.13 43	98.93 22	98.89 31	94.99 12	99.85 22	97.52 43	99.65 14	99.74 10

SteuartSystems-ACMMP		97.62 13	97.53 19	97.87 29	98.39 90	94.25 46	98.43 27	98.27 56	95.34 35	98.11 49	98.56 50	94.53 13	99.71 69	96.57 75	99.62 20	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_l_mol_unc0.5_1		97.99 4	98.12 1	97.58 54	98.16 114	93.34 73	96.88 236	98.28 52	97.29 4	99.72 1	99.45 1	94.43 14	99.79 47	99.20 12	99.66 10	99.62 27

CNVR-MVS		97.68 9	97.44 25	98.37 7	98.90 60	95.86 7	97.27 194	98.08 95	95.81 21	97.87 61	98.31 82	94.26 15	99.68 77	97.02 59	99.49 44	99.57 37

SD-MVS		97.41 24	97.53 19	97.06 84	98.57 79	94.46 40	97.92 85	98.14 85	94.82 60	99.01 18	98.55 52	94.18 16	97.41 418	96.94 60	99.64 15	99.32 75
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
TestfortrainingZip				98.34 8	98.54 80	96.25 4	98.69 11	97.85 139	94.15 92	98.17 47	97.94 114	94.00 17	99.63 90		97.45 176	99.15 89

MSP-MVS		97.59 14	97.54 18	97.73 43	99.40 14	93.77 63	98.53 19	98.29 50	95.55 30	98.56 39	97.81 141	93.90 18	99.65 81	96.62 72	99.21 84	99.77 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
MCST-MVS		97.18 35	96.84 52	98.20 16	99.30 30	95.35 17	97.12 210	98.07 100	93.54 119	96.08 130	97.69 156	93.86 19	99.71 69	96.50 76	99.39 64	99.55 44

APDe-MVS		97.82 7	97.73 10	98.08 20	99.15 40	94.82 31	98.81 8	98.30 48	94.76 67	98.30 44	98.90 28	93.77 20	99.68 77	97.93 30	99.69 3	99.75 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + MP.		97.42 23	97.33 30	97.69 47	99.25 33	94.24 47	98.07 61	97.85 139	93.72 109	98.57 38	98.35 73	93.69 21	99.40 136	97.06 58	99.46 47	99.44 62
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
patch_mono-2		96.83 58	97.44 25	95.01 238	99.05 46	85.39 393	96.98 223	98.77 8	94.70 69	97.99 53	98.66 46	93.61 22	99.91 1	97.67 38	99.50 41	99.72 14

test-260524					99.31 29	95.74 9		98.19 75		97.99 53		93.53 23	99.87 8	98.08 29	99.63 17

fmvsm_l_conf0.5_n_a		97.63 12	97.76 8	97.26 70	98.25 101	92.59 103	97.81 105	98.68 18	94.93 51	99.24 11	98.87 34	93.52 24	99.79 47	99.32 7	99.21 84	99.40 67

TestfortrainingZip a		97.79 8	97.62 13	98.28 10	99.56 1	95.15 25	98.69 11	98.35 41	95.63 26	98.95 20	98.95 21	93.45 25	99.88 4	96.63 71	98.41 137	99.82 1

DeepPCF-MVS	93.97 1	96.61 72	97.09 34	95.15 229	98.09 119	86.63 359	96.00 329	98.15 83	95.43 31	97.95 56	98.56 50	93.40 26	99.36 140	96.77 65	99.48 45	99.45 60

fmvsm_l_conf0.5_n		97.65 10	97.75 9	97.34 63	98.21 108	92.75 95	97.83 100	98.73 10	95.04 48	99.30 8	98.84 39	93.34 27	99.78 51	99.32 7	99.13 98	99.50 53

SF-MVS		97.39 25	97.13 32	98.17 17	99.02 49	95.28 21	98.23 44	98.27 56	92.37 180	98.27 45	98.65 48	93.33 28	99.72 67	96.49 77	99.52 36	99.51 50

SMA-MVS		97.35 26	97.03 41	98.30 9	99.06 45	95.42 12	97.94 82	98.18 78	90.57 269	98.85 29	98.94 24	93.33 28	99.83 32	96.72 68	99.68 4	99.63 26
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
aaEdge-Enhanced		97.54 18	97.39 28	98.00 25	99.21 37	94.50 37	97.75 112	98.34 44	94.23 90	98.15 48	98.53 54	93.32 30	99.84 27	97.40 51	99.58 26	99.65 21

NCCC		97.30 30	97.03 41	98.11 19	98.77 63	95.06 28	97.34 183	98.04 110	95.96 16	97.09 82	97.88 128	93.18 31	99.71 69	95.84 106	99.17 92	99.56 41

9.14			96.75 62		98.93 57		97.73 117	98.23 67	91.28 229	97.88 58	98.44 65	93.00 32	99.65 81	95.76 108	99.47 46

reproduce-ours		97.53 19	97.51 21	97.60 52	98.97 54	93.31 76	97.71 123	98.20 70	95.80 22	97.88 58	98.98 19	92.91 33	99.81 36	97.68 34	99.43 54	99.67 16

our_new_method		97.53 19	97.51 21	97.60 52	98.97 54	93.31 76	97.71 123	98.20 70	95.80 22	97.88 58	98.98 19	92.91 33	99.81 36	97.68 34	99.43 54	99.67 16

segment_acmp												92.89 35

TSAR-MVS + GP.		96.69 68	96.49 72	97.27 69	98.31 94	93.39 69	96.79 249	96.72 310	94.17 91	97.44 68	97.66 160	92.76 36	99.33 142	96.86 64	97.76 165	99.08 101

dcpmvs_2		96.37 82	97.05 39	94.31 290	98.96 56	84.11 414	97.56 148	97.51 197	93.92 102	97.43 70	98.52 56	92.75 37	99.32 144	97.32 56	99.50 41	99.51 50

TEST9					98.70 66	94.19 48	96.41 287	98.02 115	88.17 349	96.03 131	97.56 175	92.74 38	99.59 98

train_agg		96.30 86	95.83 93	97.72 44	98.70 66	94.19 48	96.41 287	98.02 115	88.58 336	96.03 131	97.56 175	92.73 39	99.59 98	95.04 134	99.37 68	99.39 69

test_8					98.67 68	94.06 55	96.37 295	98.01 118	88.58 336	95.98 136	97.55 177	92.73 39	99.58 101

reproduce_model		97.51 21	97.51 21	97.50 56	98.99 53	93.01 85	97.79 108	98.21 68	95.73 25	97.99 53	99.03 16	92.63 41	99.82 34	97.80 32	99.42 57	99.67 16

CSCG		96.05 91	95.91 90	96.46 119	99.24 34	90.47 198	98.30 33	98.57 28	89.01 318	93.97 215	97.57 173	92.62 42	99.76 56	94.66 160	99.27 76	99.15 89

HPM-MVS++		97.34 27	96.97 44	98.47 5	99.08 43	96.16 5	97.55 153	97.97 123	95.59 28	96.61 101	97.89 123	92.57 43	99.84 27	95.95 101	99.51 39	99.40 67

ZD-MVS					99.05 46	94.59 35		98.08 95	89.22 311	97.03 84	98.10 96	92.52 44	99.65 81	94.58 165	99.31 73

PHI-MVS		96.77 61	96.46 77	97.71 46	98.40 88	94.07 54	98.21 48	98.45 36	89.86 286	97.11 81	98.01 107	92.52 44	99.69 75	96.03 99	99.53 34	99.36 73

test_fmvsm_n_1920		97.55 17	97.89 5	96.53 107	98.41 87	91.73 133	98.01 67	99.02 1	96.37 14	99.30 8	98.92 26	92.39 46	99.79 47	99.16 15	99.46 47	98.08 241

APD-MVS		96.95 48	96.60 67	98.01 23	99.03 48	94.93 30	97.72 120	98.10 93	91.50 217	98.01 52	98.32 81	92.33 47	99.58 101	94.85 145	99.51 39	99.53 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		96.68 70	96.58 69	96.99 86	98.46 81	92.31 113	96.20 314	98.90 3	94.30 89	95.86 140	97.74 150	92.33 47	99.38 139	96.04 98	99.42 57	99.28 78

MSLP-MVS++		96.94 49	97.06 36	96.59 104	98.72 65	91.86 131	97.67 128	98.49 31	94.66 72	97.24 75	98.41 68	92.31 49	98.94 198	96.61 73	99.46 47	98.96 120

旧先验1					98.38 91	93.38 70		97.75 151			98.09 98	92.30 50			99.01 108	99.16 87

HFP-MVS		97.14 38	96.92 48	97.83 31	99.42 10	94.12 52	98.52 20	98.32 46	93.21 133	97.18 76	98.29 85	92.08 51	99.83 32	95.63 116	99.59 22	99.54 46

test_prior2							96.35 296		92.80 162	96.03 131	97.59 171	92.01 52		95.01 136	99.38 65

CDPH-MVS		95.97 95	95.38 109	97.77 39	98.93 57	94.44 41	96.35 296	97.88 132	86.98 384	96.65 98	97.89 123	91.99 53	99.47 128	92.26 214	99.46 47	99.39 69

lecture		97.58 16	97.63 12	97.43 60	99.37 19	92.93 89	98.86 7	98.85 5	95.27 37	98.65 37	98.90 28	91.97 54	99.80 41	97.63 39	99.21 84	99.57 37

CP-MVS		97.02 44	96.81 57	97.64 50	99.33 26	93.54 66	98.80 9	98.28 52	92.99 146	96.45 115	98.30 84	91.90 55	99.85 22	95.61 118	99.68 4	99.54 46

CS-MVS		96.86 53	97.06 36	96.26 138	98.16 114	91.16 169	99.09 3	97.87 134	95.30 36	97.06 83	98.03 104	91.72 56	98.71 246	97.10 57	99.17 92	98.90 136

DPM-MVS		95.69 104	94.92 130	98.01 23	98.08 122	95.71 11	95.27 375	97.62 172	90.43 274	95.55 155	97.07 209	91.72 56	99.50 123	89.62 284	98.94 111	98.82 156

XVS		97.18 35	96.96 46	97.81 33	99.38 17	94.03 56	98.59 17	98.20 70	94.85 56	96.59 103	98.29 85	91.70 58	99.80 41	95.66 111	99.40 62	99.62 27

X-MVStestdata		91.71 288	89.67 358	97.81 33	99.38 17	94.03 56	98.59 17	98.20 70	94.85 56	96.59 103	32.69 554	91.70 58	99.80 41	95.66 111	99.40 62	99.62 27

ZNCC-MVS		96.96 47	96.67 65	97.85 30	99.37 19	94.12 52	98.49 24	98.18 78	92.64 170	96.39 117	98.18 92	91.61 60	99.88 4	95.59 121	99.55 31	99.57 37

ACMMP_NAP		97.20 34	96.86 50	98.23 13	99.09 41	95.16 24	97.60 143	98.19 75	92.82 161	97.93 57	98.74 45	91.60 61	99.86 11	96.26 82	99.52 36	99.67 16

region2R		97.07 42	96.84 52	97.77 39	99.46 5	93.79 61	98.52 20	98.24 64	93.19 136	97.14 79	98.34 76	91.59 62	99.87 8	95.46 125	99.59 22	99.64 25

test_fmvsmconf_n		97.49 22	97.56 17	97.29 66	97.44 168	92.37 110	97.91 86	98.88 4	95.83 20	98.92 25	99.05 15	91.45 63	99.80 41	99.12 17	99.46 47	99.69 15

DELS-MVS		96.61 72	96.38 81	97.30 65	97.79 142	93.19 81	95.96 331	98.18 78	95.23 38	95.87 139	97.65 161	91.45 63	99.70 74	95.87 102	99.44 53	99.00 114
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
SR-MVS		97.01 45	96.86 50	97.47 58	99.09 41	93.27 78	97.98 72	98.07 100	93.75 108	97.45 67	98.48 62	91.43 65	99.59 98	96.22 85	99.27 76	99.54 46

SR-MVS-dyc-post		96.88 52	96.80 58	97.11 80	99.02 49	92.34 111	97.98 72	98.03 112	93.52 122	97.43 70	98.51 57	91.40 66	99.56 109	96.05 96	99.26 79	99.43 64

GST-MVS		96.85 55	96.52 71	97.82 32	99.36 23	94.14 51	98.29 34	98.13 86	92.72 164	96.70 94	98.06 100	91.35 67	99.86 11	94.83 148	99.28 75	99.47 59

ACMMPR		97.07 42	96.84 52	97.79 35	99.44 9	93.88 59	98.52 20	98.31 47	93.21 133	97.15 78	98.33 79	91.35 67	99.86 11	95.63 116	99.59 22	99.62 27

MVSMamba_PlusPlus		96.51 75	96.48 73	96.59 104	98.07 123	91.97 127	98.14 55	97.79 148	90.43 274	97.34 73	97.52 178	91.29 69	99.19 158	98.12 28	99.64 15	98.60 181

SPE-MVS-test		96.89 51	97.04 40	96.45 120	98.29 95	91.66 140	99.03 4	97.85 139	95.84 19	96.90 86	97.97 112	91.24 70	98.75 235	96.92 61	99.33 71	98.94 127

DeepC-MVS_fast	93.89 2	96.93 50	96.64 66	97.78 37	98.64 74	94.30 43	97.41 173	98.04 110	94.81 62	96.59 103	98.37 71	91.24 70	99.64 89	95.16 132	99.52 36	99.42 66
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ETV-MVS		96.02 92	95.89 91	96.40 124	97.16 179	92.44 108	97.47 167	97.77 150	94.55 76	96.48 111	94.51 354	91.23 72	98.92 201	95.65 114	98.19 146	97.82 262

PGM-MVS		96.81 59	96.53 70	97.65 48	99.35 25	93.53 67	97.65 132	98.98 2	92.22 187	97.14 79	98.44 65	91.17 73	99.85 22	94.35 172	99.46 47	99.57 37

MP-MVS-pluss		96.70 66	96.27 84	97.98 27	99.23 36	94.71 32	96.96 225	98.06 103	90.67 258	95.55 155	98.78 43	91.07 74	99.86 11	96.58 74	99.55 31	99.38 71
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mPP-MVS		96.86 53	96.60 67	97.64 50	99.40 14	93.44 68	98.50 23	98.09 94	93.27 132	95.95 137	98.33 79	91.04 75	99.88 4	95.20 130	99.57 30	99.60 32

HPM-MVS		96.69 68	96.45 78	97.40 61	99.36 23	93.11 83	98.87 6	98.06 103	91.17 237	96.40 116	97.99 110	90.99 76	99.58 101	95.61 118	99.61 21	99.49 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
BridgeMVS		96.84 57	96.89 49	96.68 95	97.63 156	92.22 116	98.17 54	97.82 146	94.44 82	98.23 46	97.36 188	90.97 77	99.22 155	97.74 33	99.66 10	98.61 180

fmvsm_l_conf0.5_n_9		97.59 14	97.79 7	96.97 88	98.28 96	91.49 147	97.61 142	98.71 13	97.10 6	99.70 2	98.93 25	90.95 78	99.77 54	99.35 6	99.53 34	99.65 21

APD-MVS_3200maxsize		96.81 59	96.71 64	97.12 78	99.01 52	92.31 113	97.98 72	98.06 103	93.11 142	97.44 68	98.55 52	90.93 79	99.55 111	96.06 95	99.25 81	99.51 50

test12				97.65 48	98.46 81	94.26 45		97.66 162		95.52 158		90.89 80	99.46 129		99.25 81	99.22 83

MTAPA		97.08 40	96.78 60	97.97 28	99.37 19	94.42 42	97.24 196	98.08 95	95.07 47	96.11 128	98.59 49	90.88 81	99.90 2	96.18 94	99.50 41	99.58 36

EI-MVSNet-Vis-set		96.51 75	96.47 74	96.63 100	98.24 102	91.20 163	96.89 234	97.73 154	94.74 68	96.49 110	98.49 59	90.88 81	99.58 101	96.44 78	98.32 140	99.13 92

RE-MVS-def			96.72 63		99.02 49	92.34 111	97.98 72	98.03 112	93.52 122	97.43 70	98.51 57	90.71 83		96.05 96	99.26 79	99.43 64

EIA-MVS		95.53 113	95.47 102	95.71 192	97.06 188	89.63 238	97.82 102	97.87 134	93.57 115	93.92 217	95.04 326	90.61 84	98.95 196	94.62 162	98.68 121	98.54 187

MP-MVS		96.77 61	96.45 78	97.72 44	99.39 16	93.80 60	98.41 28	98.06 103	93.37 128	95.54 157	98.34 76	90.59 85	99.88 4	94.83 148	99.54 33	99.49 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		96.34 84	96.30 83	96.47 117	98.20 109	90.93 180	96.86 238	97.72 156	94.67 71	96.16 127	98.46 63	90.43 86	99.58 101	96.23 84	97.96 158	98.90 136

原ACMM1				96.38 127	98.59 76	91.09 172		97.89 130	87.41 376	95.22 171	97.68 157	90.25 87	99.54 113	87.95 321	99.12 100	98.49 194

HPM-MVS_fast		96.51 75	96.27 84	97.22 72	99.32 27	92.74 96	98.74 10	98.06 103	90.57 269	96.77 91	98.35 73	90.21 88	99.53 115	94.80 152	99.63 17	99.38 71

testdata				95.46 214	98.18 113	88.90 278		97.66 162	82.73 455	97.03 84	98.07 99	90.06 89	98.85 208	89.67 282	98.98 109	98.64 178

新几何1				97.32 64	98.60 75	93.59 65		97.75 151	81.58 466	95.75 144	97.85 133	90.04 90	99.67 79	86.50 364	99.13 98	98.69 175

test_fmvsmconf0.1_n		97.09 39	97.06 36	97.19 75	95.67 322	92.21 117	97.95 81	98.27 56	95.78 24	98.40 43	99.00 17	89.99 91	99.78 51	99.06 19	99.41 60	99.59 33

DP-MVS Recon		95.68 105	95.12 121	97.37 62	99.19 38	94.19 48	97.03 214	98.08 95	88.35 345	95.09 174	97.65 161	89.97 92	99.48 127	92.08 225	98.59 127	98.44 202

fmvsm_l_conf0.5_n_3		97.64 11	97.60 14	97.79 35	98.14 116	93.94 58	97.93 84	98.65 23	96.70 9	99.38 6	99.07 12	89.92 93	99.81 36	99.16 15	99.43 54	99.61 31

MVS_111021_LR		96.24 88	96.19 86	96.39 126	98.23 107	91.35 156	96.24 311	98.79 7	93.99 99	95.80 142	97.65 161	89.92 93	99.24 153	95.87 102	99.20 89	98.58 183

EPP-MVSNet		95.22 127	95.04 124	95.76 185	97.49 167	89.56 243	98.67 15	97.00 287	90.69 256	94.24 204	97.62 167	89.79 95	98.81 214	93.39 196	96.49 224	98.92 132

fmvsm_s_conf0.5_n_6		97.08 40	97.17 31	96.81 91	97.28 173	91.73 133	97.75 112	98.50 30	94.86 55	99.22 12	98.78 43	89.75 96	99.76 56	99.10 18	99.29 74	98.94 127

test_fmvsmvis_n_1920		96.70 66	96.84 52	96.31 131	96.62 238	91.73 133	97.98 72	98.30 48	96.19 15	96.10 129	98.95 21	89.42 97	99.76 56	98.90 23	99.08 102	97.43 282

EC-MVSNet		96.42 79	96.47 74	96.26 138	97.01 196	91.52 146	98.89 5	97.75 151	94.42 83	96.64 99	97.68 157	89.32 98	98.60 269	97.45 47	99.11 101	98.67 177

fmvsm_s_conf0.5_n_11		97.30 30	97.59 15	96.43 121	98.42 85	91.37 154	98.04 64	98.00 119	97.30 3	99.45 5	99.21 2	89.28 99	99.80 41	99.27 10	99.35 70	98.12 233

PAPR		94.18 176	93.42 199	96.48 116	97.64 154	91.42 153	95.55 358	97.71 160	88.99 320	92.34 260	95.82 287	89.19 100	99.11 173	86.14 370	97.38 178	98.90 136

MG-MVS		95.61 109	95.38 109	96.31 131	98.42 85	90.53 196	96.04 325	97.48 203	93.47 124	95.67 150	98.10 96	89.17 101	99.25 152	91.27 243	98.77 118	99.13 92

PAPM_NR		95.01 142	94.59 149	96.26 138	98.89 61	90.68 193	97.24 196	97.73 154	91.80 204	92.93 249	96.62 246	89.13 102	99.14 170	89.21 297	97.78 163	98.97 117

mvsany_test1		93.93 196	93.98 174	93.78 325	94.94 371	86.80 352	94.62 400	92.55 475	88.77 333	96.85 87	98.49 59	88.98 103	98.08 328	95.03 135	95.62 251	96.46 319

ACMMP		96.27 87	95.93 89	97.28 68	99.24 34	92.62 101	98.25 40	98.81 6	92.99 146	94.56 195	98.39 69	88.96 104	99.85 22	94.57 166	97.63 166	99.36 73
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
fmvsm_s_conf0.5_n_5		97.00 46	96.97 44	97.09 81	97.58 164	92.56 104	97.68 127	98.47 34	94.02 97	98.90 27	98.89 31	88.94 105	99.78 51	99.18 13	99.03 107	98.93 131

UA-Net		95.95 96	95.53 99	97.20 74	97.67 150	92.98 87	97.65 132	98.13 86	94.81 62	96.61 101	98.35 73	88.87 106	99.51 120	90.36 268	97.35 180	99.11 97

API-MVS		94.84 155	94.49 157	95.90 168	97.90 136	92.00 126	97.80 106	97.48 203	89.19 312	94.81 187	96.71 232	88.84 107	99.17 163	88.91 306	98.76 119	96.53 314

fmvsm_s_conf0.5_n		96.85 55	97.13 32	96.04 154	98.07 123	90.28 211	97.97 78	98.76 9	94.93 51	98.84 30	99.06 13	88.80 108	99.65 81	99.06 19	98.63 124	98.18 226

test222					98.24 102	92.21 117	95.33 370	97.60 174	79.22 479	95.25 168	97.84 135	88.80 108			99.15 95	98.72 172

Test By Simon												88.73 110

fmvsm_s_conf0.5_n_9		97.33 28	97.57 16	96.62 103	98.43 84	90.32 210	97.80 106	98.53 29	97.24 5	99.62 3	99.14 3	88.65 111	99.80 41	99.54 1	99.15 95	99.74 10

pcd_1.5k_mvsjas		7.39 527	9.85 530	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	88.65 111	0.00 563	0.00 562	0.00 562	0.00 559

PS-MVSNAJss		93.74 203	93.51 192	94.44 280	93.91 409	89.28 261	97.75 112	97.56 189	92.50 175	89.94 324	96.54 250	88.65 111	98.18 314	93.83 185	90.90 345	95.86 336

PS-MVSNAJ		95.37 116	95.33 111	95.49 210	97.35 170	90.66 194	95.31 372	97.48 203	93.85 105	96.51 109	95.70 297	88.65 111	99.65 81	94.80 152	98.27 143	96.17 325

xiu_mvs_v2_base		95.32 119	95.29 112	95.40 216	97.22 175	90.50 197	95.44 365	97.44 218	93.70 111	96.46 113	96.18 267	88.59 115	99.53 115	94.79 155	97.81 162	96.17 325

fmvsm_s_conf0.5_n_4		96.75 63	97.07 35	95.79 181	97.76 144	89.57 242	97.66 131	98.66 21	95.36 33	99.03 17	98.90 28	88.39 116	99.73 63	99.17 14	98.66 122	98.08 241

PLC	91.00 6	94.11 184	93.43 197	96.13 147	98.58 78	91.15 170	96.69 263	97.39 226	87.29 379	91.37 286	96.71 232	88.39 116	99.52 119	87.33 350	97.13 192	97.73 266
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UniMVSNet_NR-MVSNet		93.37 219	92.67 228	95.47 213	95.34 343	92.83 92	97.17 206	98.58 27	92.98 151	90.13 316	95.80 288	88.37 118	97.85 366	91.71 233	83.93 430	95.73 350

fmvsm_s_conf0.5_n_8		97.32 29	97.48 24	96.85 90	98.28 96	91.07 173	97.76 110	98.62 25	97.53 2	99.20 13	99.12 6	88.24 119	99.81 36	99.41 3	99.17 92	99.67 16

fmvsm_s_conf0.5_n_a		96.75 63	96.93 47	96.20 143	97.64 154	90.72 191	98.00 68	98.73 10	94.55 76	98.91 26	99.08 9	88.22 120	99.63 90	98.91 22	98.37 138	98.25 221

MM		97.29 32	96.98 43	98.23 13	98.01 126	95.03 29	98.07 61	95.76 368	97.78 1	97.52 65	98.80 41	88.09 121	99.86 11	99.44 2	99.37 68	99.80 3

fmvsm_s_conf0.1_n		96.58 74	96.77 61	96.01 160	96.67 236	90.25 212	97.91 86	98.38 37	94.48 80	98.84 30	99.14 3	88.06 122	99.62 92	98.82 24	98.60 126	98.15 230

PVSNet_BlendedMVS		94.06 186	93.92 176	94.47 278	98.27 98	89.46 251	96.73 257	98.36 38	90.17 279	94.36 200	95.24 320	88.02 123	99.58 101	93.44 193	90.72 347	94.36 433

PVSNet_Blended		94.87 153	94.56 151	95.81 177	98.27 98	89.46 251	95.47 363	98.36 38	88.84 327	94.36 200	96.09 277	88.02 123	99.58 101	93.44 193	98.18 147	98.40 205

PRO-TEST		95.74 103	95.69 94	95.91 166	96.68 235	90.34 209	97.49 165	97.61 173	93.99 99	96.64 99	97.00 218	88.00 125	98.54 276	95.58 122	98.18 147	98.84 153

TAPA-MVS	90.10 7	92.30 265	91.22 284	95.56 199	98.33 93	89.60 240	96.79 249	97.65 164	81.83 463	91.52 282	97.23 198	87.94 126	98.91 203	71.31 488	98.37 138	98.17 229
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
casdiffmvs_mvg		95.81 102	95.57 96	96.51 113	96.87 208	91.49 147	97.50 157	97.56 189	93.99 99	95.13 173	97.92 118	87.89 127	98.78 219	95.97 100	97.33 181	99.26 80
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_3		97.15 37	97.36 29	96.52 109	97.98 128	91.19 164	97.84 97	98.65 23	97.08 7	99.25 10	99.10 7	87.88 128	99.79 47	99.32 7	99.18 91	98.59 182

MVS_Test		94.89 151	94.62 147	95.68 193	96.83 215	89.55 245	96.70 261	97.17 259	91.17 237	95.60 153	96.11 276	87.87 129	98.76 229	93.01 207	97.17 191	98.72 172

fmvsm_s_conf0.5_n_10		97.29 32	97.40 27	96.97 88	98.24 102	91.96 129	97.89 89	98.72 12	96.77 8	99.46 4	99.06 13	87.78 130	99.84 27	99.40 4	99.27 76	99.12 95

UniMVSNet (Re)		93.31 221	92.55 234	95.61 197	95.39 337	93.34 73	97.39 178	98.71 13	93.14 141	90.10 320	94.83 337	87.71 131	98.03 339	91.67 236	83.99 429	95.46 359

FC-MVSNet-test		93.94 194	93.57 186	95.04 236	95.48 331	91.45 152	98.12 56	98.71 13	93.37 128	90.23 311	96.70 234	87.66 132	97.85 366	91.49 238	90.39 352	95.83 340

sasdasda		96.02 92	95.45 103	97.75 41	97.59 160	95.15 25	98.28 35	97.60 174	94.52 78	96.27 122	96.12 272	87.65 133	99.18 161	96.20 90	94.82 270	98.91 133

canonicalmvs		96.02 92	95.45 103	97.75 41	97.59 160	95.15 25	98.28 35	97.60 174	94.52 78	96.27 122	96.12 272	87.65 133	99.18 161	96.20 90	94.82 270	98.91 133

FIs		94.09 185	93.70 182	95.27 222	95.70 320	92.03 125	98.10 57	98.68 18	93.36 130	90.39 308	96.70 234	87.63 135	97.94 357	92.25 216	90.50 351	95.84 339

fmvsm_s_conf0.5_n_7		96.45 78	96.80 58	95.37 217	97.29 172	88.38 299	97.23 200	98.47 34	95.14 42	98.43 42	99.09 8	87.58 136	99.72 67	98.80 26	99.21 84	98.02 245

CDS-MVSNet		94.14 183	93.54 188	95.93 165	96.18 292	91.46 151	96.33 300	97.04 282	88.97 322	93.56 226	96.51 251	87.55 137	97.89 364	89.80 278	95.95 239	98.44 202
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MGCFI-Net		95.94 97	95.40 107	97.56 55	97.59 160	94.62 34	98.21 48	97.57 181	94.41 84	96.17 126	96.16 270	87.54 138	99.17 163	96.19 92	94.73 275	98.91 133

MGCNet		96.74 65	96.31 82	98.02 22	96.87 208	94.65 33	97.58 144	94.39 440	96.47 13	97.16 77	98.39 69	87.53 139	99.87 8	98.97 21	99.41 60	99.55 44

Effi-MVS+		94.93 147	94.45 160	96.36 129	96.61 241	91.47 150	96.41 287	97.41 224	91.02 245	94.50 197	95.92 281	87.53 139	98.78 219	93.89 182	96.81 206	98.84 153

casdiffmvs		95.64 107	95.49 100	96.08 149	96.76 232	90.45 199	97.29 189	97.44 218	94.00 98	95.46 161	97.98 111	87.52 141	98.73 239	95.64 115	97.33 181	99.08 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		95.28 120	95.11 122	95.80 178	97.03 193	89.76 232	96.78 253	97.54 194	92.06 198	95.40 162	97.75 147	87.49 142	98.76 229	94.85 145	97.10 193	98.88 144

PVSNet_Blended_VisFu		95.27 121	94.91 131	96.38 127	98.20 109	90.86 183	97.27 194	98.25 62	90.21 278	94.18 208	97.27 195	87.48 143	99.73 63	93.53 190	97.77 164	98.55 186

fmvsm_s_conf0.1_n_a		96.40 80	96.47 74	96.16 145	95.48 331	90.69 192	97.91 86	98.33 45	94.07 95	98.93 22	99.14 3	87.44 144	99.61 93	98.63 27	98.32 140	98.18 226

mvs_anonymous		93.82 200	93.74 181	94.06 303	96.44 268	85.41 391	95.81 341	97.05 280	89.85 288	90.09 321	96.36 259	87.44 144	97.75 380	93.97 178	96.69 214	99.02 107

CANet		96.39 81	96.02 88	97.50 56	97.62 157	93.38 70	97.02 216	97.96 124	95.42 32	94.86 184	97.81 141	87.38 146	99.82 34	96.88 62	99.20 89	99.29 76

Casviewmamba		95.67 106	95.55 97	96.03 156	96.95 202	90.12 215	97.72 120	97.55 193	94.10 94	95.23 169	98.18 92	87.32 147	98.80 217	95.40 126	97.52 170	99.19 84

baseline		95.58 110	95.42 106	96.08 149	96.78 226	90.41 202	97.16 207	97.45 214	93.69 112	95.65 151	97.85 133	87.29 148	98.68 251	95.66 111	97.25 187	99.13 92

TAMVS		94.01 189	93.46 194	95.64 194	96.16 295	90.45 199	96.71 260	96.89 300	89.27 310	93.46 233	96.92 222	87.29 148	97.94 357	88.70 312	95.74 246	98.53 188

nrg030		94.05 187	93.31 201	96.27 137	95.22 354	94.59 35	98.34 30	97.46 209	92.93 153	91.21 297	96.64 239	87.23 150	98.22 309	94.99 137	85.80 400	95.98 335

viewcassd2359sk11		95.26 122	95.09 123	95.80 178	96.95 202	89.72 234	96.80 248	97.56 189	92.21 189	95.37 164	97.80 143	87.17 151	98.77 223	94.82 150	97.10 193	98.90 136

CPTT-MVS		95.57 111	95.19 116	96.70 94	99.27 32	91.48 149	98.33 31	98.11 91	87.79 364	95.17 172	98.03 104	87.09 152	99.61 93	93.51 191	99.42 57	99.02 107

OMC-MVS		95.09 135	94.70 144	96.25 141	98.46 81	91.28 157	96.43 283	97.57 181	92.04 199	94.77 190	97.96 113	87.01 153	99.09 178	91.31 242	96.77 207	98.36 209

hybridcas		95.46 114	95.29 112	95.96 164	96.83 215	90.08 217	97.63 138	97.49 200	93.76 107	94.79 188	98.04 102	86.87 154	98.72 244	94.71 158	97.53 169	99.08 101

DeepC-MVS	93.07 3	96.06 90	95.66 95	97.29 66	97.96 130	93.17 82	97.30 188	98.06 103	93.92 102	93.38 235	98.66 46	86.83 155	99.73 63	95.60 120	99.22 83	98.96 120
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
viewmamba		95.18 132	95.15 118	95.26 224	96.31 279	88.25 306	96.29 304	97.27 246	93.61 113	95.65 151	97.91 120	86.79 156	98.64 261	95.69 110	96.82 205	98.88 144

E3		95.20 128	95.00 127	95.79 181	96.77 228	89.66 235	96.82 244	97.58 178	92.35 181	95.28 166	97.83 137	86.69 157	98.76 229	94.79 155	96.92 199	98.95 124

E2		95.20 128	95.00 127	95.79 181	96.79 221	89.66 235	96.82 244	97.58 178	92.35 181	95.28 166	97.83 137	86.68 158	98.76 229	94.79 155	96.92 199	98.95 124

IterMVS-LS		92.29 266	91.94 255	93.34 353	96.25 282	86.97 348	96.57 279	97.05 280	90.67 258	89.50 342	94.80 339	86.59 159	97.64 390	89.91 275	86.11 398	95.40 366
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		93.03 234	92.88 218	93.48 348	95.77 318	86.98 347	96.44 281	97.12 262	90.66 260	91.30 291	97.64 164	86.56 160	98.05 335	89.91 275	90.55 349	95.41 363

miper_enhance_ethall		91.54 304	91.01 292	93.15 361	95.35 342	87.07 346	93.97 428	96.90 298	86.79 388	89.17 354	93.43 416	86.55 161	97.64 390	89.97 274	86.93 389	94.74 422

1112_ss		93.37 219	92.42 241	96.21 142	97.05 190	90.99 174	96.31 302	96.72 310	86.87 387	89.83 328	96.69 236	86.51 162	99.14 170	88.12 317	93.67 301	98.50 192

viewmanbaseed2359cas		95.24 125	95.02 125	95.91 166	96.87 208	89.98 223	96.82 244	97.49 200	92.26 185	95.47 160	97.82 139	86.47 163	98.69 249	94.80 152	97.20 189	99.06 105

diffmvs_AUTHOR		95.33 118	95.27 114	95.50 209	96.37 275	89.08 269	96.08 322	97.38 230	93.09 144	96.53 108	97.74 150	86.45 164	98.68 251	96.32 80	97.48 171	98.75 168

diffmvs		95.25 124	95.13 119	95.63 195	96.43 269	89.34 256	95.99 330	97.35 235	92.83 160	96.31 120	97.37 187	86.44 165	98.67 254	96.26 82	97.19 190	98.87 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 164	94.02 172	96.79 92	97.71 148	92.05 123	96.59 276	97.35 235	90.61 264	94.64 193	96.93 219	86.41 166	99.39 137	91.20 245	94.71 276	98.94 127

onestephybrid01		95.12 134	95.01 126	95.46 214	96.39 274	88.92 276	96.28 306	97.27 246	92.67 166	96.00 135	97.73 153	86.28 167	98.66 257	95.58 122	96.85 203	98.79 159

EPNet		95.20 128	94.56 151	97.14 77	92.80 445	92.68 100	97.85 96	94.87 422	96.64 10	92.46 253	97.80 143	86.23 168	99.65 81	93.72 186	98.62 125	99.10 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		91.59 298	91.13 287	92.97 367	95.55 328	86.57 360	94.47 409	96.88 301	87.77 365	88.88 360	94.01 386	86.22 169	97.54 405	89.49 286	86.93 389	94.79 417

Fast-Effi-MVS+		93.46 214	92.75 224	95.59 198	96.77 228	90.03 218	96.81 247	97.13 261	88.19 348	91.30 291	94.27 372	86.21 170	98.63 264	87.66 338	96.46 226	98.12 233

MVSFormer		95.37 116	95.16 117	95.99 162	96.34 277	91.21 161	98.22 46	97.57 181	91.42 221	96.22 124	97.32 189	86.20 171	97.92 360	94.07 175	99.05 104	98.85 149

lupinMVS		94.99 146	94.56 151	96.29 135	96.34 277	91.21 161	95.83 339	96.27 343	88.93 324	96.22 124	96.88 224	86.20 171	98.85 208	95.27 128	99.05 104	98.82 156

114514_t		93.95 193	93.06 210	96.63 100	99.07 44	91.61 141	97.46 169	97.96 124	77.99 485	93.00 244	97.57 173	86.14 173	99.33 142	89.22 296	99.15 95	98.94 127

E4		95.09 135	94.86 136	95.77 184	96.58 247	89.56 243	96.85 239	97.56 189	92.50 175	95.03 179	97.86 131	86.03 174	98.78 219	94.71 158	96.65 217	98.96 120

viewmambaseed2359dif		94.28 173	94.14 169	94.71 260	96.21 284	86.97 348	95.93 333	97.11 266	89.00 319	95.00 181	97.70 154	86.02 175	98.59 273	93.71 187	96.59 219	98.57 185

alignmvs		95.87 101	95.23 115	97.78 37	97.56 166	95.19 23	97.86 93	97.17 259	94.39 86	96.47 112	96.40 257	85.89 176	99.20 157	96.21 89	95.11 266	98.95 124

IMVS_0403		93.98 192	93.79 179	94.55 273	96.19 288	86.16 374	96.35 296	97.24 253	91.54 212	93.59 225	97.04 211	85.86 177	98.73 239	90.68 258	95.59 252	98.76 164

WR-MVS_H		92.00 278	91.35 275	93.95 313	95.09 364	89.47 249	98.04 64	98.68 18	91.46 219	88.34 374	94.68 344	85.86 177	97.56 398	85.77 378	84.24 427	94.82 412

Test_1112_low_res		92.84 246	91.84 259	95.85 174	97.04 192	89.97 225	95.53 360	96.64 318	85.38 411	89.65 335	95.18 321	85.86 177	99.10 175	87.70 331	93.58 306	98.49 194

viewdifsd2359ckpt13		94.87 153	94.52 155	95.90 168	96.88 207	90.19 214	96.92 229	97.36 233	91.26 230	94.65 192	97.46 180	85.79 180	98.64 261	93.64 188	96.76 208	98.88 144

HY-MVS	89.66 9	93.87 198	92.95 215	96.63 100	97.10 184	92.49 107	95.64 354	96.64 318	89.05 317	93.00 244	95.79 291	85.77 181	99.45 131	89.16 300	94.35 279	97.96 248

viewdifsd2359ckpt09		94.81 158	94.37 163	96.12 148	96.91 204	90.75 190	96.94 226	97.31 240	90.51 272	94.31 202	97.38 186	85.70 182	98.71 246	93.54 189	96.75 209	98.90 136

E6new		95.04 138	94.88 132	95.52 203	96.60 243	89.02 271	97.29 189	97.57 181	92.54 171	95.04 175	97.90 121	85.66 183	98.77 223	94.92 140	96.44 227	98.78 160

E6		95.04 138	94.88 132	95.52 203	96.60 243	89.02 271	97.29 189	97.57 181	92.54 171	95.04 175	97.90 121	85.66 183	98.77 223	94.92 140	96.44 227	98.78 160

E5new		95.04 138	94.88 132	95.52 203	96.62 238	89.02 271	97.29 189	97.57 181	92.54 171	95.04 175	97.89 123	85.65 185	98.77 223	94.92 140	96.44 227	98.78 160

E5		95.04 138	94.88 132	95.52 203	96.62 238	89.02 271	97.29 189	97.57 181	92.54 171	95.04 175	97.89 123	85.65 185	98.77 223	94.92 140	96.44 227	98.78 160

c3_l		91.38 312	90.89 295	92.88 371	95.58 326	86.30 368	94.68 399	96.84 305	88.17 349	88.83 364	94.23 375	85.65 185	97.47 412	89.36 290	84.63 418	94.89 401

icg_test_0407_2		93.58 208	93.46 194	93.94 315	96.19 288	86.16 374	93.73 439	97.24 253	91.54 212	93.50 230	97.04 211	85.64 188	96.91 439	90.68 258	95.59 252	98.76 164

IMVS_0407		93.94 194	93.75 180	94.49 277	96.19 288	86.16 374	96.35 296	97.24 253	91.54 212	93.50 230	97.04 211	85.64 188	98.54 276	90.68 258	95.59 252	98.76 164

hybridnocas07		94.93 147	94.78 139	95.37 217	96.27 281	88.62 287	96.10 320	97.26 248	92.35 181	95.58 154	97.48 179	85.60 190	98.65 259	95.47 124	96.90 201	98.85 149

viewdifsd2359ckpt07		94.76 161	94.68 145	95.01 238	96.76 232	87.41 334	96.38 293	97.43 221	92.65 168	94.52 196	97.75 147	85.55 191	98.81 214	94.36 171	96.69 214	98.82 156

IS-MVSNet		94.90 150	94.52 155	96.05 153	97.67 150	90.56 195	98.44 26	96.22 348	93.21 133	93.99 213	97.74 150	85.55 191	98.45 285	89.98 273	97.86 160	99.14 91

hybrid		94.76 161	94.60 148	95.27 222	96.24 283	88.36 300	96.05 324	97.25 251	91.40 223	95.40 162	97.59 171	85.48 193	98.63 264	95.23 129	96.71 213	98.83 155

MVS		91.71 288	90.44 321	95.51 207	95.20 356	91.59 143	96.04 325	97.45 214	73.44 495	87.36 398	95.60 302	85.42 194	99.10 175	85.97 375	97.46 172	95.83 340

NormalMVS		96.36 83	96.11 87	97.12 78	99.37 19	92.90 90	97.99 69	97.63 168	95.92 17	96.57 106	97.93 115	85.34 195	99.50 123	94.99 137	99.21 84	98.97 117

SymmetryMVS		95.94 97	95.54 98	97.15 76	97.85 138	92.90 90	97.99 69	96.91 297	95.92 17	96.57 106	97.93 115	85.34 195	99.50 123	94.99 137	96.39 232	99.05 106

VNet		95.89 99	95.45 103	97.21 73	98.07 123	92.94 88	97.50 157	98.15 83	93.87 104	97.52 65	97.61 168	85.29 197	99.53 115	95.81 107	95.27 261	99.16 87

viewmacassd2359aftdt		95.07 137	94.80 138	95.87 170	96.53 257	89.84 229	96.90 232	97.48 203	92.44 177	95.36 165	97.89 123	85.23 198	98.68 251	94.40 169	97.00 197	99.09 99

CNLPA		94.28 173	93.53 189	96.52 109	98.38 91	92.55 105	96.59 276	96.88 301	90.13 282	91.91 272	97.24 197	85.21 199	99.09 178	87.64 339	97.83 161	97.92 251

F-COLMAP		93.58 208	92.98 214	95.37 217	98.40 88	88.98 275	97.18 205	97.29 242	87.75 367	90.49 306	97.10 208	85.21 199	99.50 123	86.70 361	96.72 212	97.63 270

LCM-MVSNet-Re		92.50 253	92.52 237	92.44 382	96.82 218	81.89 442	96.92 229	93.71 460	92.41 179	84.30 445	94.60 349	85.08 201	97.03 433	91.51 237	97.36 179	98.40 205

SSM_0407		94.54 167	94.12 171	95.80 178	96.79 221	90.38 204	96.79 249	97.29 242	91.24 231	93.68 221	97.60 169	85.03 202	98.67 254	92.14 219	96.51 220	98.35 211

SSM_0404		94.73 163	94.31 166	95.98 163	97.05 190	90.90 182	97.01 219	97.29 242	91.24 231	94.17 209	97.60 169	85.03 202	98.76 229	92.14 219	97.30 184	98.29 218

NR-MVSNet		92.34 262	91.27 281	95.53 202	94.95 369	93.05 84	97.39 178	98.07 100	92.65 168	84.46 442	95.71 295	85.00 204	97.77 377	89.71 280	83.52 436	95.78 344

mamba_0408		93.70 205	92.99 211	95.83 175	96.79 221	90.38 204	88.69 497	97.07 273	90.96 247	93.68 221	97.31 191	84.97 205	98.76 229	90.95 249	96.51 220	98.35 211

SSM_04072		93.51 213	92.99 211	95.05 234	96.79 221	90.38 204	88.69 497	97.07 273	90.96 247	93.68 221	97.31 191	84.97 205	96.42 450	90.95 249	96.51 220	98.35 211

dtuplus		94.16 179	93.98 174	94.70 261	96.18 292	86.85 351	96.04 325	97.07 273	89.75 293	95.02 180	97.79 145	84.94 207	98.62 267	92.62 212	96.43 231	98.62 179

PAPM		91.52 305	90.30 327	95.20 227	95.30 349	89.83 230	93.38 451	96.85 304	86.26 399	88.59 368	95.80 288	84.88 208	98.15 316	75.67 469	95.93 240	97.63 270

MAR-MVS		94.22 175	93.46 194	96.51 113	98.00 127	92.19 120	97.67 128	97.47 207	88.13 353	93.00 244	95.84 285	84.86 209	99.51 120	87.99 320	98.17 149	97.83 261
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
jason		94.84 155	94.39 162	96.18 144	95.52 329	90.93 180	96.09 321	96.52 325	89.28 309	96.01 134	97.32 189	84.70 210	98.77 223	95.15 133	98.91 113	98.85 149
jason: jason.
sss		94.51 168	93.80 178	96.64 96	97.07 185	91.97 127	96.32 301	98.06 103	88.94 323	94.50 197	96.78 228	84.60 211	99.27 150	91.90 226	96.02 237	98.68 176

LS3D		93.57 210	92.61 232	96.47 117	97.59 160	91.61 141	97.67 128	97.72 156	85.17 416	90.29 310	98.34 76	84.60 211	99.73 63	83.85 406	98.27 143	98.06 243

Vis-MVSNet (Re-imp)		94.15 180	93.88 177	94.95 246	97.61 158	87.92 321	98.10 57	95.80 367	92.22 187	93.02 243	97.45 181	84.53 213	97.91 363	88.24 316	97.97 157	99.02 107

fmvsm_s_conf0.5_n_2		96.62 71	96.82 56	96.02 157	97.98 128	90.43 201	97.50 157	98.59 26	96.59 11	99.31 7	99.08 9	84.47 214	99.75 60	99.37 5	98.45 134	97.88 254

GeoE		93.89 197	93.28 202	95.72 191	96.96 201	89.75 233	98.24 43	96.92 296	89.47 303	92.12 266	97.21 199	84.42 215	98.39 293	87.71 330	96.50 223	99.01 111

cdsmvs_eth3d_5k		23.24 516	30.99 509	0.00 543	0.00 567	0.00 570	0.00 555	97.63 168	0.00 562	0.00 563	96.88 224	84.38 216	0.00 563	0.00 562	0.00 562	0.00 559

casdiffseed414692147		94.55 166	94.02 172	96.15 146	96.61 241	90.79 186	97.42 171	97.39 226	92.18 194	93.95 216	97.64 164	84.37 217	98.66 257	90.68 258	95.91 241	99.00 114

test_yl		94.78 159	94.23 167	96.43 121	97.74 146	91.22 159	96.85 239	97.10 267	91.23 234	95.71 146	96.93 219	84.30 218	99.31 146	93.10 200	95.12 264	98.75 168

DCV-MVSNet		94.78 159	94.23 167	96.43 121	97.74 146	91.22 159	96.85 239	97.10 267	91.23 234	95.71 146	96.93 219	84.30 218	99.31 146	93.10 200	95.12 264	98.75 168

CHOSEN 280x420		93.12 229	92.72 227	94.34 286	96.71 234	87.27 338	90.29 487	97.72 156	86.61 392	91.34 288	95.29 314	84.29 220	98.41 287	93.25 197	98.94 111	97.35 287

test_fmvsmconf0.01_n		96.15 89	95.85 92	97.03 85	92.66 448	91.83 132	97.97 78	97.84 144	95.57 29	97.53 64	99.00 17	84.20 221	99.76 56	98.82 24	99.08 102	99.48 57

baseline1		92.82 247	91.90 257	95.55 201	97.20 177	90.77 188	97.19 204	94.58 431	92.20 190	92.36 257	96.34 260	84.16 222	98.21 310	89.20 298	83.90 433	97.68 269

eth_miper_zixun_eth		91.02 332	90.59 317	92.34 387	95.33 346	84.35 410	94.10 425	96.90 298	88.56 338	88.84 363	94.33 367	84.08 223	97.60 395	88.77 310	84.37 426	95.06 390

BP-MVS1		95.89 99	95.49 100	97.08 83	96.67 236	93.20 80	98.08 59	96.32 336	94.56 75	96.32 119	97.84 135	84.07 224	99.15 167	96.75 66	98.78 117	98.90 136

PCF-MVS	89.48 11	91.56 301	89.95 346	96.36 129	96.60 243	92.52 106	92.51 470	97.26 248	79.41 478	88.90 358	96.56 249	84.04 225	99.55 111	77.01 463	97.30 184	97.01 298
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
1314		92.81 248	92.03 251	95.14 230	95.33 346	89.52 248	96.04 325	97.44 218	87.72 368	86.25 419	95.33 313	83.84 226	98.79 218	89.26 294	97.05 196	97.11 297

DP-MVS		92.76 249	91.51 273	96.52 109	98.77 63	90.99 174	97.38 180	96.08 356	82.38 459	89.29 348	97.87 129	83.77 227	99.69 75	81.37 432	96.69 214	98.89 142

testing915		94.92 149	94.46 159	96.28 136	97.76 144	91.12 171	97.88 91	95.70 371	92.69 165	95.50 159	96.74 231	83.71 228	98.70 248	94.04 177	96.15 236	99.02 107

3Dnovator+	91.43 4	95.40 115	94.48 158	98.16 18	96.90 206	95.34 18	98.48 25	97.87 134	94.65 73	88.53 370	98.02 106	83.69 229	99.71 69	93.18 199	98.96 110	99.44 62

h-mvs33		94.15 180	93.52 191	96.04 154	97.81 141	90.22 213	97.62 141	97.58 178	95.19 39	96.74 92	97.45 181	83.67 230	99.61 93	95.85 104	79.73 454	98.29 218

hse-mvs2		93.45 217	92.99 211	94.81 252	97.02 195	88.59 289	96.69 263	96.47 328	95.19 39	96.74 92	96.16 270	83.67 230	98.48 283	95.85 104	79.13 458	97.35 287

AdaColmap		94.34 172	93.68 183	96.31 131	98.59 76	91.68 139	96.59 276	97.81 147	89.87 285	92.15 264	97.06 210	83.62 232	99.54 113	89.34 291	98.07 152	97.70 268

DU-MVS		92.90 241	92.04 250	95.49 210	94.95 369	92.83 92	97.16 207	98.24 64	93.02 145	90.13 316	95.71 295	83.47 233	97.85 366	91.71 233	83.93 430	95.78 344

Baseline_NR-MVSNet		91.20 324	90.62 313	92.95 368	93.83 412	88.03 317	97.01 219	95.12 407	88.42 343	89.70 332	95.13 324	83.47 233	97.44 415	89.66 283	83.24 438	93.37 454

miper_lstm_enhance		90.50 354	90.06 342	91.83 404	95.33 346	83.74 418	93.86 434	96.70 314	87.56 373	87.79 388	93.81 394	83.45 235	96.92 438	87.39 348	84.62 419	94.82 412

EPNet_dtu		91.71 288	91.28 280	92.99 366	93.76 414	83.71 420	96.69 263	95.28 398	93.15 140	87.02 407	95.95 280	83.37 236	97.38 421	79.46 449	96.84 204	97.88 254
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
balanced_ft_v1		95.56 112	95.40 107	96.07 151	97.16 179	90.36 208	98.23 44	97.31 240	92.89 158	96.36 118	97.11 206	83.28 237	99.26 151	97.40 51	98.80 116	98.58 183

FA-MVS(test-final)		93.52 212	92.92 216	95.31 221	96.77 228	88.54 292	94.82 396	96.21 350	89.61 298	94.20 206	95.25 319	83.24 238	99.14 170	90.01 272	96.16 235	98.25 221

fmvsm_s_conf0.1_n_2		96.33 85	96.44 80	96.00 161	97.30 171	90.37 207	97.53 154	97.92 129	96.52 12	99.14 16	99.08 9	83.21 239	99.74 61	99.22 11	98.06 153	97.88 254

BH-untuned		92.94 239	92.62 231	93.92 319	97.22 175	86.16 374	96.40 291	96.25 347	90.06 283	89.79 329	96.17 269	83.19 240	98.35 296	87.19 354	97.27 186	97.24 292

TranMVSNet+NR-MVSNet		92.50 253	91.63 266	95.14 230	94.76 380	92.07 122	97.53 154	98.11 91	92.90 157	89.56 339	96.12 272	83.16 241	97.60 395	89.30 292	83.20 439	95.75 348

CHOSEN 1792x2688		94.15 180	93.51 192	96.06 152	98.27 98	89.38 254	95.18 384	98.48 33	85.60 408	93.76 220	97.11 206	83.15 242	99.61 93	91.33 241	98.72 120	99.19 84

PMMVS		92.86 244	92.34 242	94.42 282	94.92 372	86.73 355	94.53 404	96.38 334	84.78 423	94.27 203	95.12 325	83.13 243	98.40 288	91.47 239	96.49 224	98.12 233

Effi-MVS+-dtu		93.08 231	93.21 206	92.68 380	96.02 309	83.25 424	97.14 209	96.72 310	93.85 105	91.20 298	93.44 413	83.08 244	98.30 302	91.69 235	95.73 247	96.50 316

v8		91.29 321	90.53 320	93.57 343	94.15 402	88.12 315	97.34 183	97.06 279	88.99 320	88.32 375	94.26 374	83.08 244	98.01 341	87.62 340	83.92 432	94.57 427

GDP-MVS		95.62 108	95.13 119	97.09 81	96.79 221	93.26 79	97.89 89	97.83 145	93.58 114	96.80 88	97.82 139	83.06 246	99.16 165	94.40 169	97.95 159	98.87 147

DIV-MVS_self_test		90.97 335	90.33 324	92.88 371	95.36 341	86.19 373	94.46 411	96.63 321	87.82 361	88.18 381	94.23 375	82.99 247	97.53 407	87.72 328	85.57 402	94.93 397

cl____		90.96 336	90.32 325	92.89 370	95.37 340	86.21 371	94.46 411	96.64 318	87.82 361	88.15 383	94.18 378	82.98 248	97.54 405	87.70 331	85.59 401	94.92 399

BH-w/o		92.14 274	91.75 262	93.31 354	96.99 198	85.73 384	95.67 349	95.69 374	88.73 334	89.26 350	94.82 338	82.97 249	98.07 332	85.26 386	96.32 233	96.13 330

v148		90.99 333	90.38 323	92.81 374	93.83 412	85.80 381	96.78 253	96.68 315	89.45 305	88.75 366	93.93 390	82.96 250	97.82 370	87.83 323	83.25 437	94.80 415

guyue		95.17 133	94.96 129	95.82 176	96.97 200	89.65 237	97.56 148	95.58 381	94.82 60	95.72 145	97.42 184	82.90 251	98.84 210	96.71 69	96.93 198	98.96 120

HyFIR lowres test		93.66 206	92.92 216	95.87 170	98.24 102	89.88 228	94.58 402	98.49 31	85.06 418	93.78 219	95.78 292	82.86 252	98.67 254	91.77 231	95.71 248	99.07 104

test_djsdf		93.07 232	92.76 222	94.00 307	93.49 426	88.70 284	98.22 46	97.57 181	91.42 221	90.08 322	95.55 305	82.85 253	97.92 360	94.07 175	91.58 331	95.40 366

PatchmatchNet		91.91 281	91.35 275	93.59 340	95.38 338	84.11 414	93.15 455	95.39 390	89.54 300	92.10 267	93.68 400	82.82 254	98.13 318	84.81 390	95.32 260	98.52 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												82.76 255				98.45 199

VortexMVS		92.88 243	92.64 229	93.58 341	96.58 247	87.53 333	96.93 228	97.28 245	92.78 163	89.75 330	94.99 327	82.73 256	97.76 378	94.60 164	88.16 376	95.46 359

xiu_mvs_v1_base_debu		95.01 142	94.76 140	95.75 187	96.58 247	91.71 136	96.25 308	97.35 235	92.99 146	96.70 94	96.63 243	82.67 257	99.44 132	96.22 85	97.46 172	96.11 331

xiu_mvs_v1_base		95.01 142	94.76 140	95.75 187	96.58 247	91.71 136	96.25 308	97.35 235	92.99 146	96.70 94	96.63 243	82.67 257	99.44 132	96.22 85	97.46 172	96.11 331

xiu_mvs_v1_base_debi		95.01 142	94.76 140	95.75 187	96.58 247	91.71 136	96.25 308	97.35 235	92.99 146	96.70 94	96.63 243	82.67 257	99.44 132	96.22 85	97.46 172	96.11 331

patchmatchnet-post											90.45 461	82.65 260	98.10 323

V42		91.58 300	90.87 296	93.73 326	94.05 406	88.50 295	97.32 186	96.97 288	88.80 332	89.71 331	94.33 367	82.54 261	98.05 335	89.01 302	85.07 412	94.64 426

WR-MVS		92.34 262	91.53 270	94.77 257	95.13 362	90.83 184	96.40 291	97.98 122	91.88 203	89.29 348	95.54 306	82.50 262	97.80 373	89.79 279	85.27 408	95.69 351

tpmrst		91.44 309	91.32 277	91.79 407	95.15 360	79.20 475	93.42 450	95.37 392	88.55 339	93.49 232	93.67 401	82.49 263	98.27 306	90.41 266	89.34 361	97.90 252

MDTV_nov1_ep13_2view						70.35 501	93.10 457		83.88 435	93.55 227		82.47 264		86.25 367		98.38 207

XVG-OURS-SEG-HR		93.86 199	93.55 187	94.81 252	97.06 188	88.53 294	95.28 373	97.45 214	91.68 209	94.08 212	97.68 157	82.41 265	98.90 204	93.84 184	92.47 316	96.98 299

QAPM		93.45 217	92.27 244	96.98 87	96.77 228	92.62 101	98.39 29	98.12 88	84.50 426	88.27 378	97.77 146	82.39 266	99.81 36	85.40 383	98.81 115	98.51 191

Patchmatch-test		89.42 380	87.99 387	93.70 329	95.27 350	85.11 398	88.98 495	94.37 442	81.11 467	87.10 405	93.69 398	82.28 267	97.50 410	74.37 475	94.76 272	98.48 196

Vis-MVSNet		95.23 126	94.81 137	96.51 113	97.18 178	91.58 144	98.26 39	98.12 88	94.38 87	94.90 183	98.15 95	82.28 267	98.92 201	91.45 240	98.58 128	99.01 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
3Dnovator	91.36 5	95.19 131	94.44 161	97.44 59	96.56 252	93.36 72	98.65 16	98.36 38	94.12 93	89.25 351	98.06 100	82.20 269	99.77 54	93.41 195	99.32 72	99.18 86

v10		91.04 331	90.23 332	93.49 347	94.12 403	88.16 314	97.32 186	97.08 270	88.26 347	88.29 377	94.22 377	82.17 270	97.97 347	86.45 365	84.12 428	94.33 434

SD_0403		90.01 366	90.02 344	89.96 445	95.65 323	76.76 484	95.76 345	96.46 329	90.58 268	86.59 415	96.29 262	82.12 271	94.78 477	73.00 483	93.76 299	98.35 211

v1144		91.37 314	90.60 316	93.68 333	93.89 410	88.23 307	96.84 242	97.03 284	88.37 344	89.69 333	94.39 361	82.04 272	97.98 344	87.80 325	85.37 405	94.84 406

MVSTER		93.20 225	92.81 221	94.37 283	96.56 252	89.59 241	97.06 213	97.12 262	91.24 231	91.30 291	95.96 279	82.02 273	98.05 335	93.48 192	90.55 349	95.47 358

CP-MVSNet		91.89 283	91.24 282	93.82 322	95.05 365	88.57 290	97.82 102	98.19 75	91.70 208	88.21 380	95.76 293	81.96 274	97.52 409	87.86 322	84.65 417	95.37 369

Patchmatch-RL test		87.38 403	86.24 405	90.81 431	88.74 487	78.40 480	88.12 504	93.17 465	87.11 383	82.17 465	89.29 471	81.95 275	95.60 466	88.64 313	77.02 465	98.41 204

sam_mvs												81.94 276

AstraMVS		94.82 157	94.64 146	95.34 220	96.36 276	88.09 316	97.58 144	94.56 432	94.98 49	95.70 148	97.92 118	81.93 277	98.93 199	96.87 63	95.88 242	98.99 116

pmmvs4		90.93 337	89.85 350	94.17 296	93.34 433	90.79 186	94.60 401	96.02 357	84.62 424	87.45 394	95.15 322	81.88 278	97.45 414	87.70 331	87.87 379	94.27 438

test_post											17.58 558	81.76 279	98.08 328

XVG-OURS		93.72 204	93.35 200	94.80 255	97.07 185	88.61 288	94.79 397	97.46 209	91.97 202	93.99 213	97.86 131	81.74 280	98.88 205	92.64 211	92.67 315	96.92 304

v2v482		91.59 298	90.85 299	93.80 323	93.87 411	88.17 313	96.94 226	96.88 301	89.54 300	89.53 340	94.90 333	81.70 281	98.02 340	89.25 295	85.04 414	95.20 381

baseline2		91.63 294	90.86 297	93.94 315	94.33 398	86.32 367	95.92 334	91.64 485	89.37 307	86.94 410	94.69 343	81.62 282	98.69 249	88.64 313	94.57 277	96.81 307

v144192		91.06 330	90.28 328	93.39 351	93.66 418	87.23 341	96.83 243	97.07 273	87.43 375	89.69 333	94.28 371	81.48 283	98.00 342	87.18 355	84.92 416	94.93 397

LuminaMVS		94.89 151	94.35 164	96.53 107	95.48 331	92.80 94	96.88 236	96.18 353	92.85 159	95.92 138	96.87 226	81.44 284	98.83 211	96.43 79	97.10 193	97.94 250

MDTV_nov1_ep13			90.76 303		95.22 354	80.33 458	93.03 458	95.28 398	88.14 352	92.84 250	93.83 391	81.34 285	98.08 328	82.86 411	94.34 280

HQP_MVS		93.78 202	93.43 197	94.82 250	96.21 284	89.99 221	97.74 115	97.51 197	94.85 56	91.34 288	96.64 239	81.32 286	98.60 269	93.02 205	92.23 319	95.86 336

plane_prior6					96.10 303	90.00 219						81.32 286

MonoMVSNet		91.92 280	91.77 260	92.37 384	92.94 441	83.11 427	97.09 212	95.55 383	92.91 154	90.85 301	94.55 351	81.27 288	96.52 448	93.01 207	87.76 380	97.47 281

usedtu_dtu_shiyan1		91.65 292	90.67 311	94.60 265	93.65 420	90.95 177	94.86 394	97.12 262	89.69 295	89.21 352	93.62 403	81.17 289	97.67 385	87.54 342	89.14 363	95.17 386

FE-MVSNET3		91.65 292	90.67 311	94.60 265	93.65 420	90.95 177	94.86 394	97.12 262	89.69 295	89.21 352	93.62 403	81.17 289	97.67 385	87.54 342	89.14 363	95.17 386

v7n		90.76 342	89.86 349	93.45 350	93.54 423	87.60 332	97.70 126	97.37 231	88.85 326	87.65 391	94.08 384	81.08 291	98.10 323	84.68 392	83.79 434	94.66 425

HQP2-MVS												80.95 292

HQP-MVS		93.19 226	92.74 225	94.54 274	95.86 312	89.33 257	96.65 267	97.39 226	93.55 116	90.14 312	95.87 283	80.95 292	98.50 280	92.13 222	92.10 324	95.78 344

CR-MVSNet		90.82 341	89.77 354	93.95 313	94.45 394	87.19 342	90.23 488	95.68 376	86.89 386	92.40 254	92.36 437	80.91 294	97.05 432	81.09 436	93.95 296	97.60 275

Patchmtry		88.64 390	87.25 393	92.78 376	94.09 404	86.64 356	89.82 492	95.68 376	80.81 471	87.63 392	92.36 437	80.91 294	97.03 433	78.86 452	85.12 411	94.67 424

v1192		91.07 329	90.23 332	93.58 341	93.70 415	87.82 327	96.73 257	97.07 273	87.77 365	89.58 337	94.32 369	80.90 296	97.97 347	86.52 363	85.48 403	94.95 393

cl22		91.21 323	90.56 319	93.14 362	96.09 304	86.80 352	94.41 413	96.58 324	87.80 363	88.58 369	93.99 388	80.85 297	97.62 393	89.87 277	86.93 389	94.99 392

viewdifsd2359ckpt11		93.46 214	93.22 205	94.17 296	96.11 302	85.42 389	96.43 283	97.07 273	92.91 154	94.20 206	98.00 108	80.82 298	98.73 239	94.42 167	89.04 367	98.34 215

viewmsd2359difaftdt		93.46 214	93.23 204	94.17 296	96.12 300	85.42 389	96.43 283	97.08 270	92.91 154	94.21 205	98.00 108	80.82 298	98.74 237	94.41 168	89.05 365	98.34 215

mvsmamba		94.57 165	94.14 169	95.87 170	97.03 193	89.93 227	97.84 97	95.85 364	91.34 225	94.79 188	96.80 227	80.67 300	98.81 214	94.85 145	98.12 151	98.85 149

anonymousdsp		92.16 272	91.55 269	93.97 311	92.58 450	89.55 245	97.51 156	97.42 223	89.42 306	88.40 372	94.84 336	80.66 301	97.88 365	91.87 228	91.28 337	94.48 428

KinetiMVS		95.26 122	94.75 143	96.79 92	96.99 198	92.05 123	97.82 102	97.78 149	94.77 66	96.46 113	97.70 154	80.62 302	99.34 141	92.37 213	98.28 142	98.97 117

CLD-MVS		92.98 236	92.53 236	94.32 288	96.12 300	89.20 264	95.28 373	97.47 207	92.66 167	89.90 325	95.62 301	80.58 303	98.40 288	92.73 210	92.40 317	95.38 368
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_post1							92.81 463				16.58 559	80.53 304	97.68 384	86.20 368

VPA-MVSNet		93.24 223	92.48 239	95.51 207	95.70 320	92.39 109	97.86 93	98.66 21	92.30 184	92.09 268	95.37 312	80.49 305	98.40 288	93.95 179	85.86 399	95.75 348

tpmvs		89.83 374	89.15 372	91.89 402	94.92 372	80.30 459	93.11 456	95.46 389	86.28 398	88.08 384	92.65 427	80.44 306	98.52 279	81.47 428	89.92 355	96.84 306

PatchMatch-RL		92.90 241	92.02 252	95.56 199	98.19 111	90.80 185	95.27 375	97.18 257	87.96 355	91.86 275	95.68 298	80.44 306	98.99 194	84.01 401	97.54 168	96.89 305

PEN-MVS		91.20 324	90.44 321	93.48 348	94.49 392	87.91 323	97.76 110	98.18 78	91.29 226	87.78 389	95.74 294	80.35 308	97.33 423	85.46 382	82.96 440	95.19 384

Fast-Effi-MVS+-dtu		92.29 266	91.99 253	93.21 359	95.27 350	85.52 387	97.03 214	96.63 321	92.09 196	89.11 356	95.14 323	80.33 309	98.08 328	87.54 342	94.74 274	96.03 334

MSDG		91.42 310	90.24 331	94.96 245	97.15 182	88.91 277	93.69 442	96.32 336	85.72 407	86.93 411	96.47 253	80.24 310	98.98 195	80.57 439	95.05 267	96.98 299

v1921920		90.85 340	90.03 343	93.29 355	93.55 422	86.96 350	96.74 256	97.04 282	87.36 377	89.52 341	94.34 366	80.23 311	97.97 347	86.27 366	85.21 409	94.94 395

RPMNet		88.98 383	87.05 397	94.77 257	94.45 394	87.19 342	90.23 488	98.03 112	77.87 487	92.40 254	87.55 488	80.17 312	99.51 120	68.84 495	93.95 296	97.60 275

ET-MVSNet_ETH3D		91.49 307	90.11 337	95.63 195	96.40 270	91.57 145	95.34 369	93.48 462	90.60 266	75.58 491	95.49 308	80.08 313	96.79 444	94.25 173	89.76 357	98.52 189

PatchT		88.87 387	87.42 391	93.22 358	94.08 405	85.10 399	89.51 493	94.64 429	81.92 462	92.36 257	88.15 481	80.05 314	97.01 435	72.43 484	93.65 302	97.54 278

our_test_3		88.78 388	87.98 388	91.20 423	92.45 453	82.53 433	93.61 447	95.69 374	85.77 406	84.88 439	93.71 396	79.99 315	96.78 445	79.47 448	86.24 395	94.28 437

DTE-MVSNet		90.56 350	89.75 356	93.01 365	93.95 407	87.25 339	97.64 136	97.65 164	90.74 253	87.12 402	95.68 298	79.97 316	97.00 436	83.33 407	81.66 446	94.78 419

D2MVS		91.30 319	90.95 294	92.35 385	94.71 384	85.52 387	96.18 316	98.21 68	88.89 325	86.60 414	93.82 393	79.92 317	97.95 355	89.29 293	90.95 344	93.56 449

TransMVSNet (Re)		88.94 384	87.56 390	93.08 364	94.35 397	88.45 298	97.73 117	95.23 402	87.47 374	84.26 446	95.29 314	79.86 318	97.33 423	79.44 450	74.44 477	93.45 453

ACMM	89.79 8	92.96 237	92.50 238	94.35 284	96.30 280	88.71 283	97.58 144	97.36 233	91.40 223	90.53 305	96.65 238	79.77 319	98.75 235	91.24 244	91.64 329	95.59 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XXY-MVS		92.16 272	91.23 283	94.95 246	94.75 381	90.94 179	97.47 167	97.43 221	89.14 313	88.90 358	96.43 255	79.71 320	98.24 307	89.56 285	87.68 381	95.67 352

PS-CasMVS		91.55 302	90.84 300	93.69 330	94.96 368	88.28 303	97.84 97	98.24 64	91.46 219	88.04 385	95.80 288	79.67 321	97.48 411	87.02 358	84.54 423	95.31 373

WB-MVSnew		89.88 371	89.56 361	90.82 430	94.57 391	83.06 428	95.65 353	92.85 470	87.86 360	90.83 302	94.10 381	79.66 322	96.88 440	76.34 464	94.19 286	92.54 467

dtuonly		90.88 339	91.13 287	90.13 442	92.98 440	75.01 491	92.74 466	95.54 384	87.69 369	91.37 286	96.61 248	79.65 323	98.15 316	87.44 347	96.21 234	97.23 293

ab-mvs		93.57 210	92.55 234	96.64 96	97.28 173	91.96 129	95.40 366	97.45 214	89.81 290	93.22 241	96.28 263	79.62 324	99.46 129	90.74 256	93.11 307	98.50 192

v1240		90.70 346	89.85 350	93.23 357	93.51 425	86.80 352	96.61 273	97.02 286	87.16 382	89.58 337	94.31 370	79.55 325	97.98 344	85.52 381	85.44 404	94.90 400

CostFormer		91.18 327	90.70 309	92.62 381	94.84 377	81.76 443	94.09 426	94.43 437	84.15 430	92.72 251	93.77 395	79.43 326	98.20 311	90.70 257	92.18 322	97.90 252

CANet_DTU		94.37 171	93.65 184	96.55 106	96.46 267	92.13 121	96.21 312	96.67 317	94.38 87	93.53 229	97.03 216	79.34 327	99.71 69	90.76 255	98.45 134	97.82 262

OPM-MVS		93.28 222	92.76 222	94.82 250	94.63 387	90.77 188	96.65 267	97.18 257	93.72 109	91.68 280	97.26 196	79.33 328	98.63 264	92.13 222	92.28 318	95.07 389
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
JIA-IIPM		88.26 394	87.04 398	91.91 400	93.52 424	81.42 445	89.38 494	94.38 441	80.84 470	90.93 300	80.74 512	79.22 329	97.92 360	82.76 415	91.62 330	96.38 320

SDMVSNet		94.17 177	93.61 185	95.86 173	98.09 119	91.37 154	97.35 182	98.20 70	93.18 138	91.79 276	97.28 193	79.13 330	98.93 199	94.61 163	92.84 310	97.28 290

RRT-MVS		94.51 168	94.35 164	94.98 242	96.40 270	86.55 362	97.56 148	97.41 224	93.19 136	94.93 182	97.04 211	79.12 331	99.30 148	96.19 92	97.32 183	99.09 99

CVMVSNet		91.23 322	91.75 262	89.67 448	95.77 318	74.69 492	96.44 281	94.88 419	85.81 405	92.18 263	97.64 164	79.07 332	95.58 467	88.06 319	95.86 244	98.74 171

LPG-MVS_test		92.94 239	92.56 233	94.10 301	96.16 295	88.26 304	97.65 132	97.46 209	91.29 226	90.12 318	97.16 201	79.05 333	98.73 239	92.25 216	91.89 327	95.31 373

LGP-MVS_train				94.10 301	96.16 295	88.26 304		97.46 209	91.29 226	90.12 318	97.16 201	79.05 333	98.73 239	92.25 216	91.89 327	95.31 373

test-LLR		91.42 310	91.19 285	92.12 395	94.59 388	80.66 452	94.29 420	92.98 468	91.11 241	90.76 303	92.37 434	79.02 335	98.07 332	88.81 308	96.74 210	97.63 270

test0.0.03 1		89.37 381	88.70 379	91.41 417	92.47 452	85.63 385	95.22 379	92.70 473	91.11 241	86.91 412	93.65 402	79.02 335	93.19 497	78.00 456	89.18 362	95.41 363

ADS-MVSNet2		89.45 379	88.59 381	92.03 397	95.86 312	82.26 439	90.93 483	94.32 445	83.23 448	91.28 294	91.81 449	79.01 337	95.99 456	79.52 446	91.39 335	97.84 259

ADS-MVSNet		89.89 370	88.68 380	93.53 344	95.86 312	84.89 405	90.93 483	95.07 409	83.23 448	91.28 294	91.81 449	79.01 337	97.85 366	79.52 446	91.39 335	97.84 259

ppachtmachnet_test		88.35 393	87.29 392	91.53 413	92.45 453	83.57 422	93.75 438	95.97 358	84.28 427	85.32 436	94.18 378	79.00 339	96.93 437	75.71 468	84.99 415	94.10 439

OpenMVS	89.19 12	92.86 244	91.68 265	96.40 124	95.34 343	92.73 97	98.27 37	98.12 88	84.86 421	85.78 430	97.75 147	78.89 340	99.74 61	87.50 345	98.65 123	96.73 309

LTVRE_ROB	88.41 13	90.99 333	89.92 348	94.19 295	96.18 292	89.55 245	96.31 302	97.09 269	87.88 358	85.67 431	95.91 282	78.79 341	98.57 274	81.50 426	89.98 354	94.44 431
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
AUN-MVS		91.76 287	90.75 305	94.81 252	97.00 197	88.57 290	96.65 267	96.49 327	89.63 297	92.15 264	96.12 272	78.66 342	98.50 280	90.83 251	79.18 457	97.36 285

pm-mvs1		90.72 345	89.65 360	93.96 312	94.29 401	89.63 238	97.79 108	96.82 306	89.07 315	86.12 424	95.48 310	78.61 343	97.78 375	86.97 359	81.67 445	94.46 429

PVSNet	86.66 18	92.24 269	91.74 264	93.73 326	97.77 143	83.69 421	92.88 460	96.72 310	87.91 357	93.00 244	94.86 335	78.51 344	99.05 189	86.53 362	97.45 176	98.47 197

ACMP	89.59 10	92.62 252	92.14 247	94.05 304	96.40 270	88.20 311	97.36 181	97.25 251	91.52 216	88.30 376	96.64 239	78.46 345	98.72 244	91.86 229	91.48 333	95.23 380
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
BH-RMVSNet		92.72 251	91.97 254	94.97 244	97.16 179	87.99 319	96.15 318	95.60 379	90.62 263	91.87 274	97.15 203	78.41 346	98.57 274	83.16 408	97.60 167	98.36 209

thres200		92.23 270	91.39 274	94.75 259	97.61 158	89.03 270	96.60 275	95.09 408	92.08 197	93.28 238	94.00 387	78.39 347	99.04 192	81.26 435	94.18 287	96.19 324

MDA-MVSNet_test_wron		85.87 434	84.23 435	90.80 433	92.38 456	82.57 432	93.17 453	95.15 405	82.15 460	67.65 502	92.33 440	78.20 348	95.51 470	77.33 458	79.74 453	94.31 436

tfpn200view9		92.38 260	91.52 271	94.95 246	97.85 138	89.29 259	97.41 173	94.88 419	92.19 192	93.27 239	94.46 359	78.17 349	99.08 180	81.40 429	94.08 291	96.48 317

thres400		92.42 258	91.52 271	95.12 232	97.85 138	89.29 259	97.41 173	94.88 419	92.19 192	93.27 239	94.46 359	78.17 349	99.08 180	81.40 429	94.08 291	96.98 299

YYNet1		85.87 434	84.23 435	90.78 434	92.38 456	82.46 437	93.17 453	95.14 406	82.12 461	67.69 500	92.36 437	78.16 351	95.50 471	77.31 459	79.73 454	94.39 432

CL-MVSNet_self_test		86.31 424	85.15 421	89.80 447	88.83 483	81.74 444	93.93 431	96.22 348	86.67 390	85.03 438	90.80 458	78.09 352	94.50 478	74.92 472	71.86 487	93.15 456

thres100view900		92.43 257	91.58 268	94.98 242	97.92 134	89.37 255	97.71 123	94.66 427	92.20 190	93.31 237	94.90 333	78.06 353	99.08 180	81.40 429	94.08 291	96.48 317

thres600view7		92.49 255	91.60 267	95.18 228	97.91 135	89.47 249	97.65 132	94.66 427	92.18 194	93.33 236	94.91 332	78.06 353	99.10 175	81.61 425	94.06 295	96.98 299

tpm cat1		88.36 392	87.21 395	91.81 406	95.13 362	80.55 455	92.58 469	95.70 371	74.97 491	87.45 394	91.96 447	78.01 355	98.17 315	80.39 441	88.74 371	96.72 310

MVP-Stereo		90.74 344	90.08 338	92.71 378	93.19 436	88.20 311	95.86 337	96.27 343	86.07 402	84.86 440	94.76 340	77.84 356	97.75 380	83.88 405	98.01 156	92.17 477
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EPMVS		90.70 346	89.81 352	93.37 352	94.73 383	84.21 412	93.67 443	88.02 502	89.50 302	92.38 256	93.49 409	77.82 357	97.78 375	86.03 374	92.68 314	98.11 239

tfpnnormal		89.70 377	88.40 383	93.60 339	95.15 360	90.10 216	97.56 148	98.16 82	87.28 380	86.16 421	94.63 348	77.57 358	98.05 335	74.48 473	84.59 421	92.65 464

tpm		90.25 359	89.74 357	91.76 410	93.92 408	79.73 467	93.98 427	93.54 461	88.28 346	91.99 269	93.25 419	77.51 359	97.44 415	87.30 352	87.94 378	98.12 233

thisisatest0515		92.29 266	91.30 279	95.25 225	96.60 243	88.90 278	94.36 415	92.32 478	87.92 356	93.43 234	94.57 350	77.28 360	99.00 193	89.42 289	95.86 244	97.86 258

FMVSNet3		91.78 285	90.69 310	95.03 237	96.53 257	92.27 115	97.02 216	96.93 292	89.79 292	89.35 345	94.65 347	77.01 361	97.47 412	86.12 371	88.82 368	95.35 370

dmvs_testset		81.38 456	82.60 447	77.73 487	91.74 460	51.49 527	93.03 458	84.21 514	89.07 315	78.28 486	91.25 456	76.97 362	88.53 509	56.57 515	82.24 444	93.16 455

IMVS_0404		92.44 256	91.92 256	94.00 307	96.19 288	86.16 374	93.84 436	97.24 253	91.54 212	88.17 382	97.04 211	76.96 363	97.09 430	90.68 258	95.59 252	98.76 164

TR-MVS		91.48 308	90.59 317	94.16 299	96.40 270	87.33 335	95.67 349	95.34 396	87.68 370	91.46 284	95.52 307	76.77 364	98.35 296	82.85 413	93.61 304	96.79 308

FE-MVS		92.05 277	91.05 290	95.08 233	96.83 215	87.93 320	93.91 433	95.70 371	86.30 397	94.15 210	94.97 328	76.59 365	99.21 156	84.10 399	96.86 202	98.09 240

tttt0517		92.96 237	92.33 243	94.87 249	97.11 183	87.16 344	97.97 78	92.09 481	90.63 262	93.88 218	97.01 217	76.50 366	99.06 186	90.29 270	95.45 258	98.38 207

RPSCF		90.75 343	90.86 297	90.42 438	96.84 212	76.29 488	95.61 355	96.34 335	83.89 434	91.38 285	97.87 129	76.45 367	98.78 219	87.16 356	92.23 319	96.20 323

tpm2		89.96 367	89.21 370	92.23 393	94.91 374	81.25 446	93.78 437	94.42 438	80.62 473	91.56 281	93.44 413	76.44 368	97.94 357	85.60 380	92.08 326	97.49 279

thisisatest0530		93.03 234	92.21 246	95.49 210	97.07 185	89.11 268	97.49 165	92.19 480	90.16 280	94.09 211	96.41 256	76.43 369	99.05 189	90.38 267	95.68 249	98.31 217

EU-MVSNet		88.72 389	88.90 377	88.20 460	93.15 437	74.21 494	96.63 272	94.22 447	85.18 415	87.32 399	95.97 278	76.16 370	94.98 475	85.27 385	86.17 396	95.41 363

Syy-MVS		87.13 409	87.02 399	87.47 464	95.16 357	73.21 497	95.00 390	93.93 456	88.55 339	86.96 408	91.99 445	75.90 371	94.00 486	61.59 507	94.11 288	95.20 381

dp		88.90 386	88.26 386	90.81 431	94.58 390	76.62 486	92.85 462	94.93 416	85.12 417	90.07 323	93.07 420	75.81 372	98.12 321	80.53 440	87.42 385	97.71 267

IterMVS-SCA-FT		90.31 356	89.81 352	91.82 405	95.52 329	84.20 413	94.30 419	96.15 354	90.61 264	87.39 397	94.27 372	75.80 373	96.44 449	87.34 349	86.88 393	94.82 412

SCA		91.84 284	91.18 286	93.83 321	95.59 325	84.95 404	94.72 398	95.58 381	90.82 250	92.25 262	93.69 398	75.80 373	98.10 323	86.20 368	95.98 238	98.45 199

IterMVS		90.15 364	89.67 358	91.61 412	95.48 331	83.72 419	94.33 417	96.12 355	89.99 284	87.31 400	94.15 380	75.78 375	96.27 454	86.97 359	86.89 392	94.83 407
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		92.42 258	91.89 258	94.03 306	93.33 434	88.50 295	97.73 117	97.53 195	92.00 201	88.85 362	96.50 252	75.62 376	98.11 322	93.88 183	91.56 332	95.48 356

cascas		91.20 324	90.08 338	94.58 271	94.97 367	89.16 267	93.65 445	97.59 177	79.90 476	89.40 343	92.92 423	75.36 377	98.36 295	92.14 219	94.75 273	96.23 321

sd_testset		93.10 230	92.45 240	95.05 234	98.09 119	89.21 263	96.89 234	97.64 166	93.18 138	91.79 276	97.28 193	75.35 378	98.65 259	88.99 303	92.84 310	97.28 290

VPNet		92.23 270	91.31 278	94.99 240	95.56 327	90.96 176	97.22 202	97.86 138	92.96 152	90.96 299	96.62 246	75.06 379	98.20 311	91.90 226	83.65 435	95.80 342

WB-MVS		76.77 462	76.63 465	77.18 488	85.32 503	56.82 524	94.53 404	89.39 498	82.66 458	71.35 498	89.18 472	75.03 380	88.88 507	35.42 528	66.79 502	85.84 503

Elysia		94.00 190	93.12 207	96.64 96	96.08 305	92.72 98	97.50 157	97.63 168	91.15 239	94.82 185	97.12 204	74.98 381	99.06 186	90.78 253	98.02 154	98.12 233

StellarMVS		94.00 190	93.12 207	96.64 96	96.08 305	92.72 98	97.50 157	97.63 168	91.15 239	94.82 185	97.12 204	74.98 381	99.06 186	90.78 253	98.02 154	98.12 233

N_pmnet		78.73 461	78.71 461	78.79 486	92.80 445	46.50 536	94.14 424	43.71 538	78.61 482	80.83 471	91.66 452	74.94 383	96.36 451	67.24 497	84.45 424	93.50 451

SSC-MVS		76.05 463	75.83 466	76.72 492	84.77 504	56.22 525	94.32 418	88.96 500	81.82 464	70.52 499	88.91 474	74.79 384	88.71 508	33.69 530	64.71 506	85.23 506

dmvs_re		90.21 361	89.50 363	92.35 385	95.47 335	85.15 397	95.70 348	94.37 442	90.94 249	88.42 371	93.57 407	74.63 385	95.67 464	82.80 414	89.57 359	96.22 322

mvs_tets		92.31 264	91.76 261	93.94 315	93.41 431	88.29 302	97.63 138	97.53 195	92.04 199	88.76 365	96.45 254	74.62 386	98.09 327	93.91 181	91.48 333	95.45 361

DSMNet-mixed		86.34 423	86.12 408	87.00 470	89.88 475	70.43 500	94.93 392	90.08 496	77.97 486	85.42 435	92.78 424	74.44 387	93.96 488	74.43 474	95.14 263	96.62 313

pmmvs5		89.86 373	88.87 378	92.82 373	92.86 443	86.23 370	96.26 307	95.39 390	84.24 429	87.12 402	94.51 354	74.27 388	97.36 422	87.61 341	87.57 382	94.86 402

OurMVSNet-221017-0		90.51 353	90.19 336	91.44 416	93.41 431	81.25 446	96.98 223	96.28 342	91.68 209	86.55 416	96.30 261	74.20 389	97.98 344	88.96 305	87.40 387	95.09 388

GBi-Net		91.35 315	90.27 329	94.59 267	96.51 261	91.18 166	97.50 157	96.93 292	88.82 329	89.35 345	94.51 354	73.87 390	97.29 425	86.12 371	88.82 368	95.31 373

test1		91.35 315	90.27 329	94.59 267	96.51 261	91.18 166	97.50 157	96.93 292	88.82 329	89.35 345	94.51 354	73.87 390	97.29 425	86.12 371	88.82 368	95.31 373

FMVSNet2		91.31 318	90.08 338	94.99 240	96.51 261	92.21 117	97.41 173	96.95 290	88.82 329	88.62 367	94.75 341	73.87 390	97.42 417	85.20 387	88.55 373	95.35 370

COLMAP_ROB	87.81 15	90.40 355	89.28 368	93.79 324	97.95 131	87.13 345	96.92 229	95.89 363	82.83 451	86.88 413	97.18 200	73.77 393	99.29 149	78.44 454	93.62 303	94.95 393
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_cas_vis1_n_1920		94.48 170	94.55 154	94.28 292	96.78 226	86.45 365	97.63 138	97.64 166	93.32 131	97.68 63	98.36 72	73.75 394	99.08 180	96.73 67	99.05 104	97.31 289

blended_shiyan8		87.58 401	85.55 412	93.66 335	88.76 486	88.54 292	95.21 381	96.29 341	82.81 452	86.25 419	87.73 485	73.70 395	97.58 397	87.81 324	71.42 489	94.85 405

blended_shiyan6		87.55 402	85.52 413	93.64 336	88.78 484	88.50 295	95.23 378	96.30 338	82.80 453	86.09 425	87.70 486	73.69 396	97.56 398	87.70 331	71.36 490	94.86 402

Anonymous20231206		87.09 410	86.14 407	89.93 446	91.22 465	80.35 457	96.11 319	95.35 393	83.57 442	84.16 447	93.02 421	73.54 397	95.61 465	72.16 485	86.14 397	93.84 446

UGNet		94.04 188	93.28 202	96.31 131	96.85 211	91.19 164	97.88 91	97.68 161	94.40 85	93.00 244	96.18 267	73.39 398	99.61 93	91.72 232	98.46 133	98.13 231
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
wanda-best-256-512		87.29 405	85.21 418	93.53 344	88.54 490	88.21 309	94.51 407	96.27 343	82.69 456	85.92 427	86.89 494	73.04 399	97.55 400	87.68 335	71.36 490	94.83 407

FE-blended-shiyan7		87.29 405	85.21 418	93.53 344	88.54 490	88.21 309	94.51 407	96.27 343	82.69 456	85.92 427	86.89 494	73.03 400	97.55 400	87.68 335	71.36 490	94.83 407

usedtu_blend_shiyan5		87.06 411	84.84 426	93.69 330	88.54 490	88.70 284	95.83 339	95.54 384	78.74 481	85.92 427	86.89 494	73.03 400	97.55 400	87.73 326	71.36 490	94.83 407

test1111		93.19 226	92.82 220	94.30 291	97.58 164	84.56 408	98.21 48	89.02 499	93.53 120	94.58 194	98.21 89	72.69 402	99.05 189	93.06 203	98.48 132	99.28 78

ECVR-MVS		93.19 226	92.73 226	94.57 272	97.66 152	85.41 391	98.21 48	88.23 501	93.43 126	94.70 191	98.21 89	72.57 403	99.07 184	93.05 204	98.49 130	99.25 81

Anonymous20231211		90.63 349	89.42 365	94.27 293	98.24 102	89.19 266	98.05 63	97.89 130	79.95 475	88.25 379	94.96 329	72.56 404	98.13 318	89.70 281	85.14 410	95.49 355

WBMVS		90.69 348	89.99 345	92.81 374	96.48 264	85.00 401	95.21 381	96.30 338	89.46 304	89.04 357	94.05 385	72.45 405	97.82 370	89.46 287	87.41 386	95.61 353

nomal-1		91.63 294	90.62 313	94.66 264	96.07 308	87.86 324	95.58 357	94.63 430	89.80 291	89.61 336	92.66 426	72.05 406	98.29 303	90.61 264	94.55 278	97.82 262

UBG		91.55 302	90.76 303	93.94 315	96.52 260	85.06 400	95.22 379	94.54 433	90.47 273	91.98 270	92.71 425	72.02 407	98.74 237	88.10 318	95.26 262	98.01 246

ACMH	87.59 16	90.53 351	89.42 365	93.87 320	96.21 284	87.92 321	97.24 196	96.94 291	88.45 342	83.91 453	96.27 264	71.92 408	98.62 267	84.43 395	89.43 360	95.05 391
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		91.38 312	90.31 326	94.59 267	94.65 386	87.62 331	94.34 416	96.19 352	90.73 254	90.35 309	93.83 391	71.84 409	97.96 351	87.22 353	93.61 304	98.21 224

SixPastTwentyTwo		89.15 382	88.54 382	90.98 426	93.49 426	80.28 461	96.70 261	94.70 426	90.78 251	84.15 448	95.57 303	71.78 410	97.71 383	84.63 393	85.07 412	94.94 395

dtuonlycased		85.91 432	85.69 410	86.60 471	92.42 455	76.96 483	93.66 444	94.49 436	86.68 389	80.87 470	92.00 444	71.52 411	93.23 496	79.58 445	79.97 452	89.60 495

gg-mvs-nofinetune		87.82 397	85.61 411	94.44 280	94.46 393	89.27 262	91.21 481	84.61 512	80.88 469	89.89 327	74.98 518	71.50 412	97.53 407	85.75 379	97.21 188	96.51 315

test20.03		86.14 428	85.40 416	88.35 458	90.12 472	80.06 464	95.90 336	95.20 403	88.59 335	81.29 469	93.62 403	71.43 413	92.65 499	71.26 489	81.17 448	92.34 471

MS-PatchMatch		90.27 358	89.77 354	91.78 408	94.33 398	84.72 407	95.55 358	96.73 309	86.17 401	86.36 418	95.28 316	71.28 414	97.80 373	84.09 400	98.14 150	92.81 460

gbinet_0.2-2-1-0.02		87.30 404	85.16 420	93.69 330	88.70 489	88.81 281	95.14 386	96.20 351	83.03 450	86.14 423	87.06 492	71.26 415	97.40 419	87.46 346	71.49 488	94.86 402

PVSNet_0	82.17 19	85.46 437	83.64 438	90.92 427	95.27 350	79.49 472	90.55 486	95.60 379	83.76 438	83.00 460	89.95 465	71.09 416	97.97 347	82.75 416	60.79 511	95.31 373

GG-mvs-BLEND				93.62 338	93.69 416	89.20 264	92.39 472	83.33 515		87.98 387	89.84 467	71.00 417	96.87 441	82.08 422	95.40 259	94.80 415

ITE_SJBPF				92.43 383	95.34 343	85.37 394		95.92 359	91.47 218	87.75 390	96.39 258	71.00 417	97.96 351	82.36 420	89.86 356	93.97 444

UWE-MVS-28		86.81 416	86.41 403	88.02 462	92.87 442	74.60 493	95.38 368	86.70 508	88.17 349	87.28 401	94.67 346	70.83 419	93.30 494	67.45 496	94.31 281	96.17 325

IB-MVS	87.33 17	89.91 368	88.28 385	94.79 256	95.26 353	87.70 329	95.12 388	93.95 455	89.35 308	87.03 406	92.49 431	70.74 420	99.19 158	89.18 299	81.37 447	97.49 279
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
reproduce_monomvs		91.30 319	91.10 289	91.92 399	96.82 218	82.48 435	97.01 219	97.49 200	94.64 74	88.35 373	95.27 317	70.53 421	98.10 323	95.20 130	84.60 420	95.19 384

MDA-MVSNet-bldmvs		85.00 439	82.95 444	91.17 425	93.13 438	83.33 423	94.56 403	95.00 411	84.57 425	65.13 506	92.65 427	70.45 422	95.85 459	73.57 480	77.49 463	94.33 434

AllTest		90.23 360	88.98 374	93.98 309	97.94 132	86.64 356	96.51 280	95.54 384	85.38 411	85.49 433	96.77 229	70.28 423	99.15 167	80.02 443	92.87 308	96.15 328

TestCases				93.98 309	97.94 132	86.64 356		95.54 384	85.38 411	85.49 433	96.77 229	70.28 423	99.15 167	80.02 443	92.87 308	96.15 328

ACMH+	87.92 14	90.20 362	89.18 371	93.25 356	96.48 264	86.45 365	96.99 222	96.68 315	88.83 328	84.79 441	96.22 266	70.16 425	98.53 278	84.42 396	88.04 377	94.77 420

test_vis1_n_1920		94.17 177	94.58 150	92.91 369	97.42 169	82.02 441	97.83 100	97.85 139	94.68 70	98.10 50	98.49 59	70.15 426	99.32 144	97.91 31	98.82 114	97.40 284

KD-MVS_self_test		85.95 431	84.95 424	88.96 457	89.55 478	79.11 476	95.13 387	96.42 331	85.91 404	84.07 451	90.48 460	70.03 427	94.82 476	80.04 442	72.94 483	92.94 458

SSC-MVS3.2		89.74 376	89.26 369	91.19 424	95.16 357	80.29 460	94.53 404	97.03 284	91.79 205	88.86 361	94.10 381	69.94 428	97.82 370	85.29 384	86.66 394	95.45 361

testing91		91.90 282	91.02 291	94.53 275	96.54 255	86.55 362	95.86 337	95.64 378	91.77 206	91.89 273	93.47 411	69.94 428	98.86 206	90.23 271	93.86 298	98.18 226

Anonymous20240529		91.98 279	90.73 307	95.73 190	98.14 116	89.40 253	97.99 69	97.72 156	79.63 477	93.54 228	97.41 185	69.94 428	99.56 109	91.04 248	91.11 340	98.22 223

pmmvs-eth3d		86.22 426	84.45 432	91.53 413	88.34 493	87.25 339	94.47 409	95.01 410	83.47 444	79.51 480	89.61 469	69.75 431	95.71 462	83.13 409	76.73 468	91.64 480

mmtdpeth		89.70 377	88.96 375	91.90 401	95.84 317	84.42 409	97.46 169	95.53 388	90.27 277	94.46 199	90.50 459	69.74 432	98.95 196	97.39 55	69.48 497	92.34 471

FBQ-MVS		91.77 286	90.62 313	95.21 226	96.84 212	88.89 280	96.90 232	95.31 397	90.60 266	92.64 252	92.29 441	69.43 433	98.48 283	87.33 350	94.21 285	98.27 220

myMVS_eth3d28		91.52 305	90.97 293	93.17 360	96.91 204	83.24 425	95.61 355	94.96 415	92.24 186	91.98 270	93.28 418	69.31 434	98.40 288	88.71 311	95.68 249	97.88 254

test_fmvs1		93.21 224	93.53 189	92.25 392	96.55 254	81.20 448	97.40 177	96.96 289	90.68 257	96.80 88	98.04 102	69.25 435	98.40 288	97.58 42	98.50 129	97.16 296

testing3-2		92.10 275	92.05 249	92.27 390	97.71 148	79.56 469	97.42 171	94.41 439	93.53 120	93.22 241	95.49 308	69.16 436	99.11 173	93.25 197	94.22 284	98.13 231

LFMVS		93.60 207	92.63 230	96.52 109	98.13 118	91.27 158	97.94 82	93.39 463	90.57 269	96.29 121	98.31 82	69.00 437	99.16 165	94.18 174	95.87 243	99.12 95

TESTMET0.1,1		90.06 365	89.42 365	91.97 398	94.41 396	80.62 454	94.29 420	91.97 483	87.28 380	90.44 307	92.47 433	68.79 438	97.67 385	88.50 315	96.60 218	97.61 274

UWE-MVS		89.91 368	89.48 364	91.21 421	95.88 311	78.23 481	94.91 393	90.26 495	89.11 314	92.35 259	94.52 353	68.76 439	97.96 351	83.95 403	95.59 252	97.42 283

XVG-ACMP-BASELINE		90.93 337	90.21 335	93.09 363	94.31 400	85.89 380	95.33 370	97.26 248	91.06 244	89.38 344	95.44 311	68.61 440	98.60 269	89.46 287	91.05 341	94.79 417

testing11		91.68 291	90.75 305	94.47 278	96.53 257	86.56 361	95.76 345	94.51 435	91.10 243	91.24 296	93.59 406	68.59 441	98.86 206	91.10 246	94.29 282	98.00 247

testing99		91.62 296	90.72 308	94.32 288	96.48 264	86.11 379	95.81 341	94.76 424	91.55 211	91.75 278	93.44 413	68.55 442	98.82 212	90.43 265	93.69 300	98.04 244

MVS-HIRNet		82.47 453	81.21 456	86.26 473	95.38 338	69.21 503	88.96 496	89.49 497	66.28 504	80.79 472	74.08 520	68.48 443	97.39 420	71.93 486	95.47 257	92.18 476

VDD-MVS		93.82 200	93.08 209	96.02 157	97.88 137	89.96 226	97.72 120	95.85 364	92.43 178	95.86 140	98.44 65	68.42 444	99.39 137	96.31 81	94.85 268	98.71 174

test_0402		86.46 420	84.79 427	91.45 415	95.02 366	85.55 386	96.29 304	94.89 418	80.90 468	82.21 464	93.97 389	68.21 445	97.29 425	62.98 505	88.68 372	91.51 483

test-mter		90.19 363	89.54 362	92.12 395	94.59 388	80.66 452	94.29 420	92.98 468	87.68 370	90.76 303	92.37 434	67.67 446	98.07 332	88.81 308	96.74 210	97.63 270

VDDNet		93.05 233	92.07 248	96.02 157	96.84 212	90.39 203	98.08 59	95.85 364	86.22 400	95.79 143	98.46 63	67.59 447	99.19 158	94.92 140	94.85 268	98.47 197

USDC		88.94 384	87.83 389	92.27 390	94.66 385	84.96 403	93.86 434	95.90 361	87.34 378	83.40 455	95.56 304	67.43 448	98.19 313	82.64 418	89.67 358	93.66 448

pmmvs6		87.81 398	86.19 406	92.69 379	91.32 464	86.30 368	97.34 183	96.41 332	80.59 474	84.05 452	94.37 363	67.37 449	97.67 385	84.75 391	79.51 456	94.09 441

test2506		91.60 297	90.78 302	94.04 305	97.66 152	83.81 417	98.27 37	75.53 521	93.43 126	95.23 169	98.21 89	67.21 450	99.07 184	93.01 207	98.49 130	99.25 81

KD-MVS_2432*1600		84.81 442	82.64 445	91.31 419	91.07 466	85.34 395	91.22 479	95.75 369	85.56 409	83.09 458	90.21 463	67.21 450	95.89 457	77.18 461	62.48 509	92.69 462

miper_refine_blended		84.81 442	82.64 445	91.31 419	91.07 466	85.34 395	91.22 479	95.75 369	85.56 409	83.09 458	90.21 463	67.21 450	95.89 457	77.18 461	62.48 509	92.69 462

K. test v3		87.64 400	86.75 402	90.32 439	93.02 439	79.48 473	96.61 273	92.08 482	90.66 260	80.25 477	94.09 383	67.21 450	96.65 447	85.96 376	80.83 449	94.83 407

tt0805		91.09 328	90.07 341	94.16 299	95.61 324	88.31 301	97.56 148	96.51 326	89.56 299	89.17 354	95.64 300	67.08 454	98.38 294	91.07 247	88.44 374	95.80 342

mvs5depth		86.53 417	85.08 422	90.87 428	88.74 487	82.52 434	91.91 474	94.23 446	86.35 396	87.11 404	93.70 397	66.52 455	97.76 378	81.37 432	75.80 470	92.31 473

CMPMVS	62.92 21	85.62 436	84.92 425	87.74 463	89.14 479	73.12 498	94.17 423	96.80 307	73.98 492	73.65 495	94.93 331	66.36 456	97.61 394	83.95 403	91.28 337	92.48 469
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UniMVSNet_ETH3D		91.34 317	90.22 334	94.68 262	94.86 376	87.86 324	97.23 200	97.46 209	87.99 354	89.90 325	96.92 222	66.35 457	98.23 308	90.30 269	90.99 343	97.96 248

lessismore_v0				90.45 437	91.96 459	79.09 477		87.19 506		80.32 476	94.39 361	66.31 458	97.55 400	84.00 402	76.84 466	94.70 423

ttmdpeth		85.91 432	84.76 428	89.36 453	89.14 479	80.25 462	95.66 352	93.16 467	83.77 437	83.39 456	95.26 318	66.24 459	95.26 474	80.65 438	75.57 471	92.57 465

Anonymous202405211		92.07 276	90.83 301	95.76 185	98.19 111	88.75 282	97.58 144	95.00 411	86.00 403	93.64 224	97.45 181	66.24 459	99.53 115	90.68 258	92.71 313	99.01 111

new-patchmatchnet		83.18 449	81.87 452	87.11 467	86.88 500	75.99 490	93.70 440	95.18 404	85.02 419	77.30 488	88.40 478	65.99 461	93.88 489	74.19 477	70.18 495	91.47 486

FMVSNet1		89.88 371	88.31 384	94.59 267	95.41 336	91.18 166	97.50 157	96.93 292	86.62 391	87.41 396	94.51 354	65.94 462	97.29 425	83.04 410	87.43 384	95.31 373

TDRefinement		86.53 417	84.76 428	91.85 403	82.23 513	84.25 411	96.38 293	95.35 393	84.97 420	84.09 450	94.94 330	65.76 463	98.34 299	84.60 394	74.52 475	92.97 457

FE-MVSNET		83.85 445	81.97 451	89.51 450	87.19 499	83.19 426	95.21 381	93.17 465	83.45 445	78.90 483	89.05 473	65.46 464	93.84 490	69.71 494	75.56 472	91.51 483

ETVMVS		90.52 352	89.14 373	94.67 263	96.81 220	87.85 326	95.91 335	93.97 454	89.71 294	92.34 260	92.48 432	65.41 465	97.96 351	81.37 432	94.27 283	98.21 224

0.4-1-1-0.2		86.27 425	83.62 439	94.20 294	90.38 470	87.69 330	91.04 482	92.52 476	83.43 446	85.22 437	81.49 510	65.31 466	98.29 303	88.90 307	74.30 478	96.64 312

0.4-1-1-0.1		86.83 414	84.27 434	94.50 276	91.39 463	88.23 307	92.62 468	92.27 479	84.04 432	86.01 426	83.30 505	65.29 467	98.31 300	89.08 301	74.45 476	96.96 303

FE-MVSNET2		86.36 422	84.68 430	91.39 418	87.67 496	86.47 364	96.21 312	96.41 332	87.87 359	79.31 481	89.64 468	65.29 467	95.58 467	82.42 419	77.28 464	92.14 478

UnsupCasMVSNet_eth		85.99 430	84.45 432	90.62 435	89.97 474	82.40 438	93.62 446	97.37 231	89.86 286	78.59 485	92.37 434	65.25 469	95.35 473	82.27 421	70.75 494	94.10 439

blend_shiyan4		86.87 413	84.61 431	93.67 334	88.87 482	88.70 284	95.17 385	96.30 338	82.80 453	86.16 421	87.11 491	65.12 470	97.55 400	87.73 326	72.21 486	94.75 421

LF4IMVS		87.94 396	87.25 393	89.98 444	92.38 456	80.05 465	94.38 414	95.25 401	87.59 372	84.34 444	94.74 342	64.31 471	97.66 389	84.83 389	87.45 383	92.23 474

Anonymous20240521		86.42 421	85.44 414	89.34 454	90.33 471	79.79 466	96.73 257	95.92 359	83.71 439	83.25 457	91.36 455	63.92 472	96.01 455	78.39 455	85.36 406	92.22 475

MIMVSNet		88.50 391	86.76 401	93.72 328	94.84 377	87.77 328	91.39 477	94.05 451	86.41 395	87.99 386	92.59 430	63.27 473	95.82 461	77.44 457	92.84 310	97.57 277

test_fmvs1_n		92.73 250	92.88 218	92.29 389	96.08 305	81.05 449	97.98 72	97.08 270	90.72 255	96.79 90	98.18 92	63.07 474	98.45 285	97.62 41	98.42 136	97.36 285

FMVSNet5		87.29 405	85.79 409	91.78 408	94.80 379	87.28 337	95.49 362	95.28 398	84.09 431	83.85 454	91.82 448	62.95 475	94.17 483	78.48 453	85.34 407	93.91 445

MVStest1		82.38 454	80.04 458	89.37 452	87.63 497	82.83 430	95.03 389	93.37 464	73.90 493	73.50 496	94.35 364	62.89 476	93.25 495	73.80 478	65.92 505	92.04 479

0.3-1-1-0.015		86.11 429	83.37 440	94.34 286	90.58 469	88.02 318	91.64 476	92.45 477	83.56 443	84.46 442	81.84 508	62.73 477	98.31 300	88.98 304	74.09 479	96.70 311

testgi		87.97 395	87.21 395	90.24 440	92.86 443	80.76 450	96.67 266	94.97 413	91.74 207	85.52 432	95.83 286	62.66 478	94.47 480	76.25 465	88.36 375	95.48 356

TinyColmap		86.82 415	85.35 417	91.21 421	94.91 374	82.99 429	93.94 430	94.02 453	83.58 441	81.56 468	94.68 344	62.34 479	98.13 318	75.78 467	87.35 388	92.52 468

testing222		90.31 356	88.96 375	94.35 284	96.54 255	87.29 336	95.50 361	93.84 458	90.97 246	91.75 278	92.96 422	62.18 480	98.00 342	82.86 411	94.08 291	97.76 265

new_pmnet		82.89 452	81.12 457	88.18 461	89.63 476	80.18 463	91.77 475	92.57 474	76.79 489	75.56 492	88.23 480	61.22 481	94.48 479	71.43 487	82.92 441	89.87 493

OpenMVS_ROB	81.14 20	84.42 444	82.28 450	90.83 429	90.06 473	84.05 416	95.73 347	94.04 452	73.89 494	80.17 478	91.53 453	59.15 482	97.64 390	66.92 499	89.05 365	90.80 490

test_fmvs2		89.77 375	89.93 347	89.31 455	93.68 417	76.37 487	97.64 136	95.90 361	89.84 289	91.49 283	96.26 265	58.77 483	97.10 429	94.65 161	91.13 339	94.46 429

tt0320		85.39 438	83.12 441	92.19 394	93.44 430	85.79 382	96.19 315	94.87 422	71.19 499	82.92 461	91.76 451	58.43 484	96.81 443	81.03 437	78.26 462	93.98 443

test_vis1_n		92.37 261	92.26 245	92.72 377	94.75 381	82.64 431	98.02 66	96.80 307	91.18 236	97.77 62	97.93 115	58.02 485	98.29 303	97.63 39	98.21 145	97.23 293

MIMVSNet1		84.93 440	83.05 442	90.56 436	89.56 477	84.84 406	95.40 366	95.35 393	83.91 433	80.38 475	92.21 443	57.23 486	93.34 493	70.69 491	82.75 443	93.50 451

EG-PatchMatch MVS		87.02 412	85.44 414	91.76 410	92.67 447	85.00 401	96.08 322	96.45 330	83.41 447	79.52 479	93.49 409	57.10 487	97.72 382	79.34 451	90.87 346	92.56 466

UnsupCasMVSNet_bld		82.13 455	79.46 460	90.14 441	88.00 494	82.47 436	90.89 485	96.62 323	78.94 480	75.61 490	84.40 503	56.63 488	96.31 453	77.30 460	66.77 503	91.63 481

myMVS_eth3d		87.18 408	86.38 404	89.58 449	95.16 357	79.53 470	95.00 390	93.93 456	88.55 339	86.96 408	91.99 445	56.23 489	94.00 486	75.47 471	94.11 288	95.20 381

testing3		87.67 399	86.88 400	90.05 443	96.14 298	80.71 451	97.10 211	92.85 470	90.15 281	87.54 393	94.55 351	55.70 490	94.10 484	73.77 479	94.10 290	95.35 370

sc_t1		86.48 419	84.10 437	93.63 337	93.45 429	85.76 383	96.79 249	94.71 425	73.06 496	86.45 417	94.35 364	55.13 491	97.95 355	84.38 397	78.55 461	97.18 295

tt0320-xc		84.83 441	82.33 449	92.31 388	93.66 418	86.20 372	96.17 317	94.06 450	71.26 498	82.04 466	92.22 442	55.07 492	96.72 446	81.49 427	75.04 474	94.02 442

EGC-MVSNET		68.77 475	63.01 483	86.07 474	92.49 451	82.24 440	93.96 429	90.96 492	0.71 560	2.62 562	90.89 457	53.66 493	93.46 491	57.25 514	84.55 422	82.51 511

tmp_tt		51.94 492	53.82 490	46.29 514	33.73 562	45.30 538	78.32 518	67.24 528	18.02 539	50.93 522	87.05 493	52.99 494	53.11 535	70.76 490	25.29 546	40.46 536

test_vis1_rt		86.16 427	85.06 423	89.46 451	93.47 428	80.46 456	96.41 287	86.61 509	85.22 414	79.15 482	88.64 476	52.41 495	97.06 431	93.08 202	90.57 348	90.87 489

pmmvs3		79.97 459	77.50 463	87.39 465	82.80 512	79.38 474	92.70 467	90.75 494	70.69 500	78.66 484	87.47 489	51.34 496	93.40 492	73.39 481	69.65 496	89.38 496

dongtai		69.99 472	69.33 471	71.98 500	88.78 484	61.64 517	89.86 491	59.93 530	75.67 490	74.96 493	85.45 500	50.19 497	81.66 521	43.86 523	55.27 515	72.63 520

kuosan		65.27 480	64.66 480	67.11 506	83.80 506	61.32 518	88.53 500	60.77 529	68.22 502	67.67 501	80.52 513	49.12 498	70.76 531	29.67 532	53.64 517	69.26 522

DeepMVS_CX				74.68 497	90.84 468	64.34 514		81.61 517	65.34 506	67.47 503	88.01 483	48.60 499	80.13 524	62.33 506	73.68 481	79.58 514

mvsany_test3		83.59 446	82.44 448	87.03 469	83.80 506	73.82 495	93.70 440	90.92 493	86.42 394	82.51 462	90.26 462	46.76 500	95.71 462	90.82 252	76.76 467	91.57 482

ArgMatch-SfM		83.09 450	81.67 455	87.34 466	91.48 462	76.29 488	92.76 464	91.31 489	84.26 428	81.99 467	93.35 417	45.52 501	92.98 498	81.83 423	72.49 485	92.76 461

ArgMatch-Sym		83.08 451	81.73 454	87.11 467	91.53 461	76.72 485	92.86 461	91.54 486	83.66 440	82.34 463	93.45 412	44.99 502	92.15 500	81.78 424	73.46 482	92.47 470

usedtu_dtu_shiyan2		80.00 458	76.91 464	89.27 456	82.13 514	79.69 468	95.45 364	94.20 448	72.95 497	75.80 489	87.75 484	44.44 503	94.30 482	70.64 492	68.81 500	93.84 446

PM-MVS		83.48 447	81.86 453	88.31 459	87.83 495	77.59 482	93.43 449	91.75 484	86.91 385	80.63 473	89.91 466	44.42 504	95.84 460	85.17 388	76.73 468	91.50 485

test_method		66.11 479	64.89 479	69.79 502	72.62 533	35.23 542	65.19 531	92.83 472	20.35 537	65.20 505	88.08 482	43.14 505	82.70 519	73.12 482	63.46 507	91.45 487

APD_test1		79.31 460	77.70 462	84.14 475	89.11 481	69.07 504	92.36 473	91.50 487	69.07 501	73.87 494	92.63 429	39.93 506	94.32 481	70.54 493	80.25 451	89.02 497

ambc				86.56 472	83.60 508	70.00 502	85.69 509	94.97 413		80.60 474	88.45 477	37.42 507	96.84 442	82.69 417	75.44 473	92.86 459

test_fmvs3		83.21 448	83.02 443	83.78 476	86.77 501	68.34 505	96.76 255	94.91 417	86.49 393	84.14 449	89.48 470	36.04 508	91.73 502	91.86 229	80.77 450	91.26 488

test_f		80.57 457	79.62 459	83.41 478	83.38 510	67.80 507	93.57 448	93.72 459	80.80 472	77.91 487	87.63 487	33.40 509	92.08 501	87.14 357	79.04 459	90.34 492

Gipuma		67.86 477	65.41 478	75.18 495	92.66 448	73.45 496	66.50 530	94.52 434	53.33 520	57.80 516	66.07 526	30.81 510	89.20 506	48.15 521	78.88 460	62.90 529
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EMVS		52.08 491	51.31 493	54.39 511	72.62 533	45.39 537	83.84 513	75.51 522	41.13 525	40.77 530	59.65 532	30.08 511	73.60 529	28.31 533	29.90 541	44.18 534

FPMVS		71.27 468	69.85 469	75.50 494	74.64 525	59.03 521	91.30 478	91.50 487	58.80 512	57.92 515	88.28 479	29.98 512	85.53 515	53.43 518	82.84 442	81.95 512

E-PMN		53.28 488	52.56 491	55.43 509	74.43 527	47.13 535	83.63 514	76.30 520	42.23 524	42.59 528	62.22 530	28.57 513	74.40 528	31.53 531	31.51 535	44.78 533

PMMVS2		70.19 471	66.92 475	80.01 482	76.35 523	65.67 510	86.22 508	87.58 504	64.83 508	62.38 509	80.29 514	26.78 514	88.49 510	63.79 503	54.07 516	85.88 502

LoFTR		72.43 467	68.71 473	83.60 477	85.67 502	65.61 511	88.04 505	87.40 505	66.11 505	55.94 519	85.54 499	25.43 515	95.55 469	60.87 508	63.38 508	89.63 494

ANet_high		63.94 483	59.58 486	77.02 489	61.24 542	66.06 509	85.66 510	87.93 503	78.53 483	42.94 527	71.04 522	25.42 516	80.71 523	52.60 519	30.83 537	84.28 508

MASt3R-SfM		71.17 469	70.37 468	73.55 498	74.50 526	51.20 528	82.17 515	80.88 519	64.49 509	72.54 497	91.37 454	25.17 517	81.85 520	75.86 466	66.37 504	87.59 499

LCM-MVSNet		72.55 465	69.39 470	82.03 480	70.81 535	65.42 512	90.12 490	94.36 444	55.02 517	65.88 504	81.72 509	24.16 518	89.96 503	74.32 476	68.10 501	90.71 491

PDCNetPlus		61.05 484	58.26 487	69.44 503	75.52 524	55.68 526	81.49 516	51.76 535	62.45 511	51.54 521	82.02 507	23.69 519	78.90 525	65.91 501	29.91 540	73.74 518

DenseAffine		72.53 466	69.17 472	82.59 479	87.49 498	70.91 499	88.38 501	81.13 518	67.58 503	64.27 508	87.44 490	23.61 520	88.47 511	66.10 500	56.56 513	88.38 498

RoMa-SfM		70.64 470	67.48 474	80.09 481	84.70 505	66.61 508	88.62 499	73.09 525	65.10 507	64.98 507	88.91 474	22.38 521	87.00 512	63.51 504	56.06 514	86.67 501

MatchFormer		67.84 478	63.81 482	79.93 483	83.26 511	60.99 519	87.61 506	84.49 513	54.89 518	51.76 520	81.06 511	22.08 522	94.10 484	50.36 520	58.82 512	84.72 507

test_vis3_rt		72.73 464	70.55 467	79.27 484	80.02 518	68.13 506	93.92 432	74.30 524	76.90 488	58.99 514	73.58 521	20.29 523	95.37 472	84.16 398	72.80 484	74.31 517

testf1		69.31 473	66.76 476	76.94 490	78.61 521	61.93 515	88.27 502	86.11 510	55.62 515	59.69 510	85.31 501	20.19 524	89.32 504	57.62 512	69.44 498	79.58 514

APD_test2		69.31 473	66.76 476	76.94 490	78.61 521	61.93 515	88.27 502	86.11 510	55.62 515	59.69 510	85.31 501	20.19 524	89.32 504	57.62 512	69.44 498	79.58 514

MVS_clip		37.19 503	40.69 506	26.70 528	52.35 552	23.34 560	43.13 543	10.51 563	12.50 552	56.71 517	80.13 515	19.51 526	16.50 559	43.87 522	47.47 519	40.26 537

ALIKED-LG		47.63 493	45.22 496	54.88 510	81.48 515	48.47 532	71.83 523	45.44 537	32.66 528	37.07 532	63.26 529	19.21 527	63.71 532	15.49 542	40.53 529	52.46 530

SP-DiffGlue		43.94 497	43.32 498	45.79 517	47.79 558	33.03 543	63.37 532	42.65 541	25.71 531	41.26 529	69.27 523	18.83 528	38.88 543	34.96 529	46.05 520	65.47 528

ALIKED-NN		46.19 495	43.87 497	53.16 513	80.39 517	47.77 533	69.82 529	43.65 539	27.89 529	36.60 533	63.35 528	17.30 529	61.29 534	15.84 541	39.98 530	50.41 532

RoMa-HiRes		64.40 481	60.91 484	74.89 496	78.66 520	58.85 522	85.22 511	58.46 532	58.65 513	59.29 513	86.60 497	16.97 530	83.91 517	59.14 510	45.20 523	81.91 513

SP-LightGlue		43.37 498	42.49 501	46.03 515	74.26 528	31.37 545	71.24 525	40.98 543	23.86 533	33.18 538	56.34 536	16.78 531	39.73 540	21.09 538	44.68 524	66.97 524

SP-SuperGlue		43.33 499	42.50 500	45.81 516	73.95 530	31.24 546	71.34 524	41.17 542	23.96 532	33.42 537	56.47 534	16.72 532	39.64 541	21.11 537	44.32 525	66.57 525

DKM		67.96 476	64.19 481	79.27 484	83.41 509	64.35 513	86.88 507	68.11 527	63.15 510	59.36 512	86.08 498	16.45 533	86.15 514	64.54 502	49.73 518	87.32 500

VLMVS		20.83 519	22.16 522	16.83 539	23.35 563	13.77 566	21.05 553	12.13 562	1.76 559	31.04 541	45.78 540	15.59 534	13.56 560	13.60 544	35.16 534	23.18 540

SP-NN		42.37 500	41.40 503	45.29 519	72.86 532	30.45 548	70.32 528	39.16 546	22.21 534	31.32 539	56.73 533	15.45 535	39.53 542	20.27 539	44.25 526	65.88 527

SP-MNN		42.11 501	40.98 505	45.49 518	72.87 531	30.19 550	70.72 527	39.96 544	20.98 535	30.21 542	55.72 538	15.26 536	40.07 539	19.70 540	43.42 527	66.21 526

ALIKED-MNN		45.42 496	42.62 499	53.80 512	80.52 516	47.58 534	70.83 526	43.05 540	27.21 530	34.32 536	61.10 531	14.85 537	62.94 533	14.90 543	36.82 532	50.89 531

VLMVS_CLIP		39.93 502	41.64 502	34.80 521	33.81 561	19.16 562	46.81 538	59.30 531	16.50 540	47.57 523	67.74 525	14.11 538	49.88 536	42.98 524	45.94 521	35.36 539

XFeat-MNN		35.01 504	34.34 507	37.02 520	42.54 559	25.71 557	54.01 535	39.41 545	20.70 536	30.13 543	55.85 537	14.08 539	44.62 537	22.90 535	29.45 544	40.75 535

XFeat-NN		33.93 505	33.70 508	34.60 522	41.69 560	24.48 558	51.85 536	36.02 547	19.55 538	31.20 540	56.38 535	13.46 540	40.91 538	22.51 536	30.65 538	38.42 538

DKM-HiRes		64.02 482	59.97 485	76.17 493	79.46 519	59.20 520	84.48 512	58.37 533	58.52 514	56.03 518	83.71 504	13.19 541	83.72 518	60.49 509	45.50 522	85.59 504

GLUNet-SfM		46.44 494	41.21 504	62.14 508	51.92 553	38.44 541	58.72 533	57.51 534	34.08 527	34.61 535	67.84 524	11.40 542	74.90 527	35.48 527	19.30 552	73.08 519

ELoFTR		60.03 485	55.86 488	72.52 499	67.65 537	48.49 531	76.21 520	75.14 523	53.94 519	45.93 525	79.98 516	9.14 543	85.06 516	55.39 516	39.36 531	84.02 509

PMVS	53.92 22	58.58 486	55.40 489	68.12 504	51.00 556	48.64 530	78.86 517	87.10 507	46.77 523	35.84 534	74.28 519	8.76 544	86.34 513	42.07 525	73.91 480	69.38 521
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-NN		28.47 506	28.54 510	28.27 523	64.38 539	31.62 544	48.50 537	24.78 549	14.32 541	19.55 545	40.46 541	7.22 545	31.96 545	6.20 548	31.47 536	21.24 541

wuyk23d		25.11 512	24.57 516	26.74 527	73.98 529	39.89 540	57.88 534	9.80 565	12.27 553	10.39 556	6.97 560	7.03 546	36.44 544	25.43 534	17.39 554	3.89 558

MVE	50.73 23	53.25 489	48.81 494	66.58 507	65.34 538	57.50 523	72.49 521	70.94 526	40.15 526	39.28 531	63.51 527	6.89 547	73.48 530	38.29 526	42.38 528	68.76 523
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-MNN		27.50 507	27.40 511	27.80 524	61.71 541	30.57 547	46.59 539	24.66 550	14.04 542	17.35 546	39.90 542	6.52 548	31.80 546	6.13 549	29.65 542	21.04 542

SIFT-NN-NCMNet		27.16 508	27.05 512	27.51 525	59.97 544	30.42 549	46.49 540	24.52 551	13.94 544	17.23 547	39.47 543	6.39 549	31.40 547	5.94 550	29.49 543	20.72 544

SIFT-NN-UMatch		25.24 511	25.01 515	25.92 531	54.55 550	27.33 554	44.97 541	22.85 552	13.97 543	13.40 551	39.41 544	6.28 550	30.23 550	5.83 551	23.82 547	20.21 545

SIFT-NN-CMatch		25.59 510	25.23 514	26.67 529	56.47 548	28.89 553	42.75 544	22.52 554	13.89 545	16.98 548	39.39 545	6.26 551	30.38 549	5.77 552	22.99 548	20.75 543

SIFT-NN-PointCN		23.81 515	23.84 518	23.73 534	52.41 551	22.80 561	42.30 546	20.98 556	13.02 551	15.14 549	37.74 550	6.20 552	28.40 554	5.52 554	21.24 549	19.98 546

SIFT-NCM-Cal		25.87 509	25.57 513	26.75 526	60.60 543	29.37 551	44.96 542	22.64 553	13.57 547	11.67 554	37.90 548	5.81 553	31.26 548	5.32 556	27.70 545	19.63 547

SIFT-ConvMatch		24.62 513	24.14 517	26.03 530	58.66 545	29.15 552	40.80 547	21.31 555	13.69 546	13.51 550	38.52 546	5.65 554	30.22 551	5.51 555	19.65 551	18.73 549

SIFT-CM-Cal		23.18 517	22.70 520	24.60 533	57.42 546	26.79 555	37.63 549	18.36 558	13.35 549	12.57 552	37.37 551	5.54 555	28.79 553	5.17 558	16.92 556	18.23 550

SIFT-UMatch		24.03 514	23.67 519	25.10 532	57.10 547	26.49 556	42.43 545	20.05 557	13.49 548	12.40 553	38.51 547	5.45 556	30.07 552	5.56 553	18.08 553	18.74 548

SIFT-UM-Cal		22.52 518	22.27 521	23.27 535	56.41 549	23.87 559	39.94 548	16.81 560	13.33 550	10.54 555	37.90 548	5.16 557	28.36 555	5.23 557	15.12 557	17.57 551

PMatch-SfM		57.38 487	52.53 492	71.95 501	68.62 536	49.38 529	77.61 519	45.82 536	52.41 521	46.59 524	82.04 506	4.86 558	81.03 522	58.34 511	36.49 533	85.43 505

SIFT-PCN-Cal		20.26 521	20.34 524	20.01 537	51.70 554	17.74 564	35.64 551	16.15 561	11.90 555	10.28 557	33.69 552	4.55 559	25.68 556	4.57 559	14.59 558	16.60 554

SIFT-PointCN		20.70 520	20.89 523	20.14 536	51.62 555	18.11 563	37.52 550	17.71 559	12.03 554	10.05 558	33.23 553	4.33 560	25.40 557	4.55 560	16.94 555	16.90 552

PMatch-Up-SfM		52.53 490	47.58 495	67.36 505	63.24 540	43.29 539	72.10 522	34.71 548	47.03 522	43.51 526	79.07 517	3.90 561	75.83 526	54.68 517	30.02 539	82.95 510

test123		13.04 524	15.66 527	5.18 541	4.51 566	3.45 567	92.50 471	1.81 568	2.50 558	7.58 561	20.15 557	3.67 562	2.18 562	7.13 547	1.07 561	9.90 556

SIFT-NCMNet		17.70 522	17.74 525	17.60 538	49.47 557	16.50 565	30.22 552	10.39 564	11.77 556	8.79 559	29.74 555	3.61 563	22.42 558	3.97 561	11.69 559	13.89 555

MVS_baseline		12.31 525	14.46 528	5.86 540	16.09 564	0.78 569	6.53 554	1.85 567	0.36 561	23.99 544	49.92 539	2.55 564	0.00 563	8.94 545	19.86 550	16.82 553

testmvs		13.36 523	16.33 526	4.48 542	5.04 565	2.26 568	93.18 452	3.28 566	2.70 557	8.24 560	21.66 556	2.29 565	2.19 561	7.58 546	2.96 560	9.00 557

mmdepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

monomultidepth		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

test_blank		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet_test		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

DCPMVS		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet-low-res		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

sosnet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uncertanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Regformer		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

ab-mvs-re		8.06 526	10.74 529	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	96.69 236	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

uanet		0.00 528	0.00 531	0.00 543	0.00 567	0.00 570	0.00 555	0.00 569	0.00 562	0.00 563	0.00 561	0.00 566	0.00 563	0.00 562	0.00 562	0.00 559

Meshroom													0.00 563
: In preparation.
AliceVision / Meshro													0.00 563
: In preparation.
AliceVision_Meshroom													0.00 563
: In preparation.
PatchmatchNet2					0.00 567	79.04 478	92.75 465	94.19 449	78.18 484
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														67.11 498	84.43 425	93.53 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													96.32 452
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				98.00 25	99.56 1	94.50 37	98.69 11	98.70 16	93.45 125	98.73 32	98.53 54		99.86 11	97.40 51	99.58 26	99.65 21

WAC-MVS						79.53 470								75.56 470

FOURS1					99.55 4	93.34 73	99.29 1	98.35 41	94.98 49	98.49 40

MSC_two_6792asdad				98.86 1	98.67 68	96.94 1		97.93 127					99.86 11	97.68 34	99.67 6	99.77 4

No_MVS				98.86 1	98.67 68	96.94 1		97.93 127					99.86 11	97.68 34	99.67 6	99.77 4

eth-test2					0.00 567

eth-test					0.00 567

IU-MVS					99.42 10	95.39 13		97.94 126	90.40 276	98.94 21				97.41 50	99.66 10	99.74 10

save fliter					98.91 59	94.28 44	97.02 216	98.02 115	95.35 34

test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 11	97.52 43	99.67 6	99.75 8

GSMVS																98.45 199

test_part2					99.28 31	95.74 9				98.10 50

MTGPA								98.08 95

MTMP							97.86 93	82.03 516

gm-plane-assit					93.22 435	78.89 479			84.82 422		93.52 408		98.64 261	87.72 328

test9_res														94.81 151	99.38 65	99.45 60

agg_prior2														93.94 180	99.38 65	99.50 53

agg_prior					98.67 68	93.79 61		98.00 119		95.68 149			99.57 108

test_prior4						93.66 64	96.42 286

test_prior				97.23 71	98.67 68	92.99 86		98.00 119					99.41 135			99.29 76

旧先验2							95.94 332		81.66 465	97.34 73			98.82 212	92.26 214

新几何2							95.79 343

无先验							95.79 343	97.87 134	83.87 436				99.65 81	87.68 335		98.89 142

原ACMM2							95.67 349

testdata2													99.67 79	85.96 376

testdata1							95.26 377		93.10 143

plane_prior7					96.21 284	89.98 223

plane_prior5								97.51 197					98.60 269	93.02 205	92.23 319	95.86 336

plane_prior4											96.64 239

plane_prior3						90.00 219			94.46 81	91.34 288

plane_prior2							97.74 115		94.85 56

plane_prior1					96.14 298

plane_prior						89.99 221	97.24 196		94.06 96						92.16 323

n2								0.00 569

nn								0.00 569

door-mid								91.06 491

test11								97.88 132

door								91.13 490

HQP5-MVS						89.33 257

HQP-NCC					95.86 312		96.65 267		93.55 116	90.14 312

ACMP_Plane					95.86 312		96.65 267		93.55 116	90.14 312

BP-MVS														92.13 222

HQP4-MVS										90.14 312			98.50 280			95.78 344

HQP3-MVS								97.39 226							92.10 324

NP-MVS					95.99 310	89.81 231					95.87 283

ACMMP++_ref															90.30 353

ACMMP++															91.02 342

High-resolution multi-view benchmark