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.

DPE-MVS		97.86 4	97.65 9	98.47 5	99.17 34	95.78 7	97.21 186	98.35 38	95.16 36	98.71 30	98.80 36	95.05 10	99.89 3	96.70 63	99.73 1	99.73 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_0728_THIRD									94.78 59	98.73 28	98.87 29	95.87 4	99.84 23	97.45 44	99.72 2	99.77 2

APDe-MVS		97.82 5	97.73 8	98.08 18	99.15 35	94.82 28	98.81 8	98.30 43	94.76 62	98.30 38	98.90 23	93.77 17	99.68 69	97.93 27	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SMA-MVS		97.35 22	97.03 35	98.30 8	99.06 40	95.42 10	97.94 76	98.18 71	90.57 238	98.85 25	98.94 19	93.33 23	99.83 26	96.72 61	99.68 4	99.63 22
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
CP-MVS		97.02 38	96.81 51	97.64 45	99.33 23	93.54 60	98.80 9	98.28 47	92.99 134	96.45 105	98.30 77	91.90 50	99.85 18	95.61 109	99.68 4	99.54 41

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 131	94.92 48	98.73 28	98.87 29	95.08 8	99.84 23	97.52 40	99.67 6	99.48 52
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 47					99.86 9	97.52 40	99.67 6	99.75 6

balanced_conf03		96.84 51	96.89 43	96.68 88	97.63 147	92.22 109	98.17 49	97.82 137	94.44 77	98.23 40	97.36 160	90.97 72	99.22 145	97.74 30	99.66 10	98.61 151

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 50	95.13 38	99.19 11	98.89 26	95.54 5	99.85 18	97.52 40	99.66 10	99.56 36

IU-MVS					99.42 7	95.39 11		97.94 118	90.40 244	98.94 17				97.41 47	99.66 10	99.74 8

test_241102_TWO								98.27 50	95.13 38	98.93 18	98.89 26	94.99 11	99.85 18	97.52 40	99.65 13	99.74 8

MVSMamba_PlusPlus		96.51 69	96.48 67	96.59 97	98.07 114	91.97 120	98.14 50	97.79 139	90.43 242	97.34 64	97.52 152	91.29 64	99.19 148	98.12 26	99.64 14	98.60 152

SD-MVS		97.41 20	97.53 15	97.06 78	98.57 74	94.46 34	97.92 79	98.14 78	94.82 55	99.01 15	98.55 47	94.18 14	97.41 372	96.94 53	99.64 14	99.32 70
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
HPM-MVS_fast		96.51 69	96.27 78	97.22 66	99.32 24	92.74 89	98.74 10	98.06 96	90.57 238	96.77 82	98.35 66	90.21 83	99.53 106	94.80 132	99.63 16	99.38 66

SteuartSystems-ACMMP		97.62 10	97.53 15	97.87 24	98.39 83	94.25 40	98.43 23	98.27 50	95.34 30	98.11 41	98.56 45	94.53 12	99.71 61	96.57 67	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
HPM-MVS		96.69 62	96.45 72	97.40 55	99.36 20	93.11 76	98.87 6	98.06 96	91.17 207	96.40 106	97.99 100	90.99 71	99.58 92	95.61 109	99.61 18	99.49 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 81	96.04 2	99.24 143	95.36 114	99.59 19	99.56 36

HFP-MVS		97.14 32	96.92 42	97.83 26	99.42 7	94.12 46	98.52 16	98.32 41	93.21 121	97.18 67	98.29 78	92.08 46	99.83 26	95.63 107	99.59 19	99.54 41

region2R		97.07 36	96.84 46	97.77 34	99.46 2	93.79 55	98.52 16	98.24 58	93.19 124	97.14 70	98.34 69	91.59 57	99.87 7	95.46 113	99.59 19	99.64 21

ACMMPR		97.07 36	96.84 46	97.79 30	99.44 6	93.88 53	98.52 16	98.31 42	93.21 121	97.15 69	98.33 72	91.35 62	99.86 9	95.63 107	99.59 19	99.62 23

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 63	95.39 11	99.29 1	98.28 47	94.78 59	98.93 18	98.87 29	96.04 2	99.86 9	97.45 44	99.58 23	99.59 28

PC_three_1452									90.77 222	98.89 24	98.28 80	96.24 1	98.35 263	95.76 100	99.58 23	99.59 28

mPP-MVS		96.86 47	96.60 61	97.64 45	99.40 11	93.44 62	98.50 19	98.09 87	93.27 120	95.95 125	98.33 72	91.04 70	99.88 4	95.20 116	99.57 25	99.60 27

ZNCC-MVS		96.96 41	96.67 59	97.85 25	99.37 16	94.12 46	98.49 20	98.18 71	92.64 153	96.39 107	98.18 85	91.61 55	99.88 4	95.59 112	99.55 26	99.57 32

MP-MVS-pluss		96.70 60	96.27 78	97.98 22	99.23 32	94.71 29	96.96 208	98.06 96	90.67 228	95.55 141	98.78 38	91.07 69	99.86 9	96.58 66	99.55 26	99.38 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 55	96.45 72	97.72 39	99.39 13	93.80 54	98.41 24	98.06 96	93.37 116	95.54 143	98.34 69	90.59 80	99.88 4	94.83 129	99.54 28	99.49 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
fmvsm_l_conf0.5_n_9		97.59 11	97.79 5	96.97 82	98.28 89	91.49 139	97.61 131	98.71 12	97.10 4	99.70 1	98.93 20	90.95 73	99.77 46	99.35 5	99.53 29	99.65 19

PHI-MVS		96.77 55	96.46 71	97.71 41	98.40 81	94.07 48	98.21 43	98.45 33	89.86 255	97.11 72	98.01 98	92.52 39	99.69 67	96.03 91	99.53 29	99.36 68

SF-MVS		97.39 21	97.13 26	98.17 15	99.02 44	95.28 19	98.23 40	98.27 50	92.37 158	98.27 39	98.65 43	93.33 23	99.72 59	96.49 69	99.52 31	99.51 45

ACMMP_NAP		97.20 28	96.86 44	98.23 11	99.09 36	95.16 22	97.60 132	98.19 69	92.82 147	97.93 48	98.74 40	91.60 56	99.86 9	96.26 74	99.52 31	99.67 14

DeepC-MVS_fast	93.89 2	96.93 44	96.64 60	97.78 32	98.64 69	94.30 37	97.41 160	98.04 103	94.81 57	96.59 93	98.37 64	91.24 65	99.64 81	95.16 118	99.52 31	99.42 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS++		97.34 23	96.97 38	98.47 5	99.08 38	96.16 4	97.55 142	97.97 115	95.59 23	96.61 91	97.89 109	92.57 38	99.84 23	95.95 93	99.51 34	99.40 62

APD-MVS		96.95 42	96.60 61	98.01 20	99.03 43	94.93 27	97.72 111	98.10 86	91.50 189	98.01 44	98.32 74	92.33 42	99.58 92	94.85 127	99.51 34	99.53 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
patch_mono-2		96.83 52	97.44 21	95.01 208	99.05 41	85.39 345	96.98 206	98.77 8	94.70 64	97.99 45	98.66 41	93.61 19	99.91 1	97.67 35	99.50 36	99.72 12

dcpmvs_2		96.37 76	97.05 33	94.31 253	98.96 51	84.11 366	97.56 137	97.51 178	93.92 93	97.43 61	98.52 49	92.75 32	99.32 135	97.32 49	99.50 36	99.51 45

MTAPA		97.08 34	96.78 54	97.97 23	99.37 16	94.42 36	97.24 179	98.08 88	95.07 42	96.11 117	98.59 44	90.88 76	99.90 2	96.18 86	99.50 36	99.58 31

CNVR-MVS		97.68 6	97.44 21	98.37 7	98.90 55	95.86 6	97.27 177	98.08 88	95.81 18	97.87 52	98.31 75	94.26 13	99.68 69	97.02 52	99.49 39	99.57 32

DeepPCF-MVS	93.97 1	96.61 66	97.09 28	95.15 199	98.09 110	86.63 313	96.00 296	98.15 76	95.43 26	97.95 47	98.56 45	93.40 21	99.36 131	96.77 58	99.48 40	99.45 55

9.14			96.75 56		98.93 52		97.73 108	98.23 61	91.28 200	97.88 49	98.44 58	93.00 26	99.65 73	95.76 100	99.47 41

test_fmvsmconf_n		97.49 18	97.56 13	97.29 60	97.44 159	92.37 103	97.91 80	98.88 4	95.83 17	98.92 21	99.05 12	91.45 58	99.80 35	99.12 14	99.46 42	99.69 13

test_fmvsm_n_1920		97.55 14	97.89 3	96.53 100	98.41 80	91.73 125	98.01 61	99.02 1	96.37 11	99.30 5	98.92 21	92.39 41	99.79 40	99.16 12	99.46 42	98.08 209

TSAR-MVS + MP.		97.42 19	97.33 24	97.69 42	99.25 29	94.24 41	98.07 56	97.85 131	93.72 99	98.57 32	98.35 66	93.69 18	99.40 127	97.06 51	99.46 42	99.44 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSLP-MVS++		96.94 43	97.06 30	96.59 97	98.72 60	91.86 123	97.67 118	98.49 28	94.66 67	97.24 66	98.41 61	92.31 44	98.94 189	96.61 65	99.46 42	98.96 109

PGM-MVS		96.81 53	96.53 64	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 162	97.14 70	98.44 58	91.17 68	99.85 18	94.35 146	99.46 42	99.57 32

CDPH-MVS		95.97 89	95.38 101	97.77 34	98.93 52	94.44 35	96.35 269	97.88 124	86.98 347	96.65 89	97.89 109	91.99 48	99.47 119	92.26 184	99.46 42	99.39 64

DELS-MVS		96.61 66	96.38 75	97.30 59	97.79 134	93.19 74	95.96 298	98.18 71	95.23 33	95.87 127	97.65 137	91.45 58	99.70 66	95.87 94	99.44 48	99.00 104
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
fmvsm_l_conf0.5_n_3		97.64 8	97.60 11	97.79 30	98.14 107	93.94 52	97.93 78	98.65 20	96.70 6	99.38 3	99.07 10	89.92 88	99.81 30	99.16 12	99.43 49	99.61 26

reproduce-ours		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

our_new_method		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

reproduce_model		97.51 17	97.51 17	97.50 50	98.99 48	93.01 78	97.79 100	98.21 62	95.73 22	97.99 45	99.03 13	92.63 36	99.82 28	97.80 29	99.42 52	99.67 14

CPTT-MVS		95.57 103	95.19 107	96.70 87	99.27 28	91.48 141	98.33 27	98.11 84	87.79 328	95.17 151	98.03 95	87.09 141	99.61 84	93.51 162	99.42 52	99.02 98

MVS_111021_HR		96.68 64	96.58 63	96.99 80	98.46 75	92.31 106	96.20 284	98.90 3	94.30 84	95.86 128	97.74 127	92.33 42	99.38 130	96.04 90	99.42 52	99.28 73

test_fmvsmconf0.1_n		97.09 33	97.06 30	97.19 69	95.67 288	92.21 110	97.95 75	98.27 50	95.78 21	98.40 37	99.00 14	89.99 86	99.78 43	99.06 16	99.41 55	99.59 28

MVS_0304		96.74 59	96.31 76	98.02 19	96.87 193	94.65 30	97.58 133	94.39 394	96.47 10	97.16 68	98.39 62	87.53 131	99.87 7	98.97 18	99.41 55	99.55 39

XVS		97.18 29	96.96 40	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	98.29 78	91.70 53	99.80 35	95.66 102	99.40 57	99.62 23

X-MVStestdata		91.71 258	89.67 324	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	32.69 462	91.70 53	99.80 35	95.66 102	99.40 57	99.62 23

MCST-MVS		97.18 29	96.84 46	98.20 14	99.30 26	95.35 15	97.12 193	98.07 93	93.54 108	96.08 119	97.69 132	93.86 16	99.71 61	96.50 68	99.39 59	99.55 39

test9_res														94.81 131	99.38 60	99.45 55

agg_prior2														93.94 153	99.38 60	99.50 48

test_prior2							96.35 269		92.80 148	96.03 120	97.59 146	92.01 47		95.01 122	99.38 60

MM		97.29 27	96.98 37	98.23 11	98.01 117	95.03 26	98.07 56	95.76 328	97.78 1	97.52 56	98.80 36	88.09 115	99.86 9	99.44 2	99.37 63	99.80 1

train_agg		96.30 80	95.83 88	97.72 39	98.70 61	94.19 42	96.41 261	98.02 108	88.58 301	96.03 120	97.56 149	92.73 34	99.59 89	95.04 120	99.37 63	99.39 64

SPE-MVS-test		96.89 45	97.04 34	96.45 113	98.29 88	91.66 132	99.03 4	97.85 131	95.84 16	96.90 77	97.97 102	91.24 65	98.75 215	96.92 54	99.33 65	98.94 113

3Dnovator	91.36 5	95.19 117	94.44 136	97.44 53	96.56 225	93.36 66	98.65 12	98.36 35	94.12 86	89.25 316	98.06 92	82.20 239	99.77 46	93.41 166	99.32 66	99.18 80

ZD-MVS					99.05 41	94.59 32		98.08 88	89.22 276	97.03 75	98.10 88	92.52 39	99.65 73	94.58 141	99.31 67

fmvsm_s_conf0.5_n_6		97.08 34	97.17 25	96.81 84	97.28 164	91.73 125	97.75 104	98.50 27	94.86 50	99.22 9	98.78 38	89.75 91	99.76 48	99.10 15	99.29 68	98.94 113

GST-MVS		96.85 49	96.52 65	97.82 27	99.36 20	94.14 45	98.29 30	98.13 79	92.72 150	96.70 85	98.06 92	91.35 62	99.86 9	94.83 129	99.28 69	99.47 54

SR-MVS		97.01 39	96.86 44	97.47 52	99.09 36	93.27 71	97.98 66	98.07 93	93.75 98	97.45 58	98.48 55	91.43 60	99.59 89	96.22 77	99.27 70	99.54 41

CSCG		96.05 85	95.91 85	96.46 112	99.24 30	90.47 184	98.30 29	98.57 25	89.01 283	93.97 184	97.57 147	92.62 37	99.76 48	94.66 136	99.27 70	99.15 83

SR-MVS-dyc-post		96.88 46	96.80 52	97.11 74	99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	91.40 61	99.56 100	96.05 88	99.26 72	99.43 59

RE-MVS-def			96.72 57		99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	90.71 78		96.05 88	99.26 72	99.43 59

APD-MVS_3200maxsize		96.81 53	96.71 58	97.12 72	99.01 47	92.31 106	97.98 66	98.06 96	93.11 130	97.44 59	98.55 47	90.93 74	99.55 102	96.06 87	99.25 74	99.51 45

test12				97.65 43	98.46 75	94.26 39		97.66 154		95.52 144		90.89 75	99.46 120		99.25 74	99.22 78

DeepC-MVS	93.07 3	96.06 84	95.66 89	97.29 60	97.96 122	93.17 75	97.30 175	98.06 96	93.92 93	93.38 203	98.66 41	86.83 143	99.73 55	95.60 111	99.22 76	98.96 109
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NormalMVS		96.36 77	96.11 81	97.12 72	99.37 16	92.90 83	97.99 63	97.63 160	95.92 14	96.57 96	97.93 104	85.34 169	99.50 114	94.99 123	99.21 77	98.97 106

lecture		97.58 13	97.63 10	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 32	98.65 31	98.90 23	91.97 49	99.80 35	97.63 36	99.21 77	99.57 32

fmvsm_s_conf0.5_n_7		96.45 72	96.80 52	95.37 191	97.29 163	88.38 263	97.23 183	98.47 31	95.14 37	98.43 36	99.09 6	87.58 128	99.72 59	98.80 23	99.21 77	98.02 213

fmvsm_l_conf0.5_n_a		97.63 9	97.76 6	97.26 64	98.25 94	92.59 96	97.81 97	98.68 15	94.93 46	99.24 8	98.87 29	93.52 20	99.79 40	99.32 6	99.21 77	99.40 62

MSP-MVS		97.59 11	97.54 14	97.73 38	99.40 11	93.77 57	98.53 15	98.29 45	95.55 25	98.56 33	97.81 122	93.90 15	99.65 73	96.62 64	99.21 77	99.77 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
CANet		96.39 75	96.02 83	97.50 50	97.62 148	93.38 64	97.02 199	97.96 116	95.42 27	94.86 157	97.81 122	87.38 137	99.82 28	96.88 55	99.20 82	99.29 71

MVS_111021_LR		96.24 82	96.19 80	96.39 118	98.23 99	91.35 147	96.24 282	98.79 7	93.99 91	95.80 130	97.65 137	89.92 88	99.24 143	95.87 94	99.20 82	98.58 155

fmvsm_s_conf0.5_n_3		97.15 31	97.36 23	96.52 102	97.98 120	91.19 155	97.84 89	98.65 20	97.08 5	99.25 7	99.10 5	87.88 121	99.79 40	99.32 6	99.18 84	98.59 154

fmvsm_s_conf0.5_n_8		97.32 25	97.48 20	96.85 83	98.28 89	91.07 163	97.76 102	98.62 22	97.53 2	99.20 10	99.12 4	88.24 113	99.81 30	99.41 3	99.17 85	99.67 14

CS-MVS		96.86 47	97.06 30	96.26 129	98.16 106	91.16 160	99.09 3	97.87 126	95.30 31	97.06 74	98.03 95	91.72 51	98.71 224	97.10 50	99.17 85	98.90 122

NCCC		97.30 26	97.03 35	98.11 17	98.77 58	95.06 25	97.34 170	98.04 103	95.96 13	97.09 73	97.88 112	93.18 25	99.71 61	95.84 98	99.17 85	99.56 36

mamv4		94.66 138	96.10 82	90.37 392	98.01 117	73.41 442	96.82 222	97.78 140	89.95 253	94.52 167	97.43 156	92.91 27	99.09 168	98.28 25	99.16 88	98.60 152

fmvsm_s_conf0.5_n_9		97.33 24	97.57 12	96.62 96	98.43 78	90.32 194	97.80 98	98.53 26	97.24 3	99.62 2	99.14 1	88.65 105	99.80 35	99.54 1	99.15 89	99.74 8

test222					98.24 95	92.21 110	95.33 334	97.60 165	79.22 429	95.25 148	97.84 118	88.80 102			99.15 89	98.72 144

114514_t		93.95 165	93.06 181	96.63 93	99.07 39	91.61 133	97.46 157	97.96 116	77.99 433	93.00 212	97.57 147	86.14 157	99.33 133	89.22 264	99.15 89	98.94 113

fmvsm_l_conf0.5_n		97.65 7	97.75 7	97.34 57	98.21 100	92.75 88	97.83 92	98.73 10	95.04 43	99.30 5	98.84 34	93.34 22	99.78 43	99.32 6	99.13 92	99.50 48

新几何1				97.32 58	98.60 70	93.59 59		97.75 143	81.58 416	95.75 132	97.85 116	90.04 85	99.67 71	86.50 318	99.13 92	98.69 147

原ACMM1				96.38 119	98.59 71	91.09 162		97.89 122	87.41 339	95.22 150	97.68 133	90.25 82	99.54 104	87.95 286	99.12 94	98.49 165

EC-MVSNet		96.42 73	96.47 68	96.26 129	97.01 185	91.52 138	98.89 5	97.75 143	94.42 78	96.64 90	97.68 133	89.32 93	98.60 238	97.45 44	99.11 95	98.67 149

test_fmvsmconf0.01_n		96.15 83	95.85 87	97.03 79	92.66 411	91.83 124	97.97 72	97.84 135	95.57 24	97.53 55	99.00 14	84.20 193	99.76 48	98.82 21	99.08 96	99.48 52

test_fmvsmvis_n_1920		96.70 60	96.84 46	96.31 123	96.62 217	91.73 125	97.98 66	98.30 43	96.19 12	96.10 118	98.95 18	89.42 92	99.76 48	98.90 20	99.08 96	97.43 249

test_cas_vis1_n_1920		94.48 143	94.55 131	94.28 255	96.78 208	86.45 318	97.63 128	97.64 158	93.32 119	97.68 54	98.36 65	73.75 360	99.08 171	96.73 60	99.05 98	97.31 256

MVSFormer		95.37 106	95.16 108	95.99 149	96.34 249	91.21 152	98.22 41	97.57 170	91.42 193	96.22 113	97.32 161	86.20 155	97.92 322	94.07 149	99.05 98	98.85 130

lupinMVS		94.99 125	94.56 128	96.29 127	96.34 249	91.21 152	95.83 306	96.27 306	88.93 289	96.22 113	96.88 194	86.20 155	98.85 199	95.27 115	99.05 98	98.82 134

fmvsm_s_conf0.5_n_5		97.00 40	96.97 38	97.09 75	97.58 155	92.56 97	97.68 117	98.47 31	94.02 89	98.90 23	98.89 26	88.94 99	99.78 43	99.18 10	99.03 101	98.93 117

旧先验1					98.38 84	93.38 64		97.75 143			98.09 90	92.30 45			99.01 102	99.16 81

testdata				95.46 189	98.18 105	88.90 249		97.66 154	82.73 407	97.03 75	98.07 91	90.06 84	98.85 199	89.67 250	98.98 103	98.64 150

3Dnovator+	91.43 4	95.40 105	94.48 134	98.16 16	96.90 192	95.34 16	98.48 21	97.87 126	94.65 68	88.53 333	98.02 97	83.69 200	99.71 61	93.18 170	98.96 104	99.44 57

DPM-MVS		95.69 97	94.92 115	98.01 20	98.08 113	95.71 9	95.27 339	97.62 164	90.43 242	95.55 141	97.07 180	91.72 51	99.50 114	89.62 252	98.94 105	98.82 134

CHOSEN 280x420		93.12 200	92.72 198	94.34 250	96.71 214	87.27 293	90.29 434	97.72 148	86.61 354	91.34 254	95.29 282	84.29 192	98.41 254	93.25 168	98.94 105	97.35 254

jason		94.84 131	94.39 137	96.18 135	95.52 295	90.93 168	96.09 290	96.52 292	89.28 274	96.01 123	97.32 161	84.70 183	98.77 211	95.15 119	98.91 107	98.85 130
jason: jason.
test_vis1_n_1920		94.17 150	94.58 127	92.91 323	97.42 160	82.02 392	97.83 92	97.85 131	94.68 65	98.10 42	98.49 52	70.15 384	99.32 135	97.91 28	98.82 108	97.40 251

QAPM		93.45 188	92.27 215	96.98 81	96.77 210	92.62 94	98.39 25	98.12 81	84.50 388	88.27 341	97.77 125	82.39 236	99.81 30	85.40 337	98.81 109	98.51 162

BP-MVS1		95.89 93	95.49 93	97.08 77	96.67 215	93.20 73	98.08 54	96.32 302	94.56 70	96.32 108	97.84 118	84.07 196	99.15 157	96.75 59	98.78 110	98.90 122

MG-MVS		95.61 101	95.38 101	96.31 123	98.42 79	90.53 182	96.04 293	97.48 183	93.47 113	95.67 138	98.10 88	89.17 95	99.25 142	91.27 213	98.77 111	99.13 85

API-MVS		94.84 131	94.49 133	95.90 153	97.90 128	92.00 119	97.80 98	97.48 183	89.19 277	94.81 160	96.71 201	88.84 101	99.17 153	88.91 272	98.76 112	96.53 277

CHOSEN 1792x2688		94.15 152	93.51 164	96.06 140	98.27 91	89.38 230	95.18 345	98.48 30	85.60 370	93.76 188	97.11 178	83.15 212	99.61 84	91.33 211	98.72 113	99.19 79

EIA-MVS		95.53 104	95.47 95	95.71 171	97.06 178	89.63 215	97.82 94	97.87 126	93.57 104	93.92 185	95.04 294	90.61 79	98.95 187	94.62 138	98.68 114	98.54 158

fmvsm_s_conf0.5_n_4		96.75 57	97.07 29	95.79 163	97.76 136	89.57 219	97.66 121	98.66 18	95.36 28	99.03 14	98.90 23	88.39 110	99.73 55	99.17 11	98.66 115	98.08 209

OpenMVS	89.19 12	92.86 215	91.68 236	96.40 116	95.34 309	92.73 90	98.27 33	98.12 81	84.86 383	85.78 385	97.75 126	78.89 306	99.74 53	87.50 302	98.65 116	96.73 274

fmvsm_s_conf0.5_n		96.85 49	97.13 26	96.04 142	98.07 114	90.28 195	97.97 72	98.76 9	94.93 46	98.84 26	99.06 11	88.80 102	99.65 73	99.06 16	98.63 117	98.18 195

EPNet		95.20 116	94.56 128	97.14 71	92.80 408	92.68 93	97.85 88	94.87 378	96.64 7	92.46 220	97.80 124	86.23 152	99.65 73	93.72 159	98.62 118	99.10 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.1_n		96.58 68	96.77 55	96.01 147	96.67 215	90.25 196	97.91 80	98.38 34	94.48 75	98.84 26	99.14 1	88.06 116	99.62 83	98.82 21	98.60 119	98.15 199

DP-MVS Recon		95.68 98	95.12 111	97.37 56	99.19 33	94.19 42	97.03 197	98.08 88	88.35 310	95.09 153	97.65 137	89.97 87	99.48 118	92.08 195	98.59 120	98.44 173

Vis-MVSNet		95.23 114	94.81 117	96.51 106	97.18 169	91.58 136	98.26 35	98.12 81	94.38 82	94.90 156	98.15 87	82.28 237	98.92 192	91.45 210	98.58 121	99.01 101
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_fmvs1		93.21 195	93.53 161	92.25 346	96.55 227	81.20 399	97.40 164	96.96 256	90.68 227	96.80 79	98.04 94	69.25 392	98.40 255	97.58 39	98.50 122	97.16 262

test2506		91.60 264	90.78 272	94.04 266	97.66 143	83.81 369	98.27 33	75.53 463	93.43 114	95.23 149	98.21 82	67.21 407	99.07 175	93.01 178	98.49 123	99.25 76

ECVR-MVS		93.19 197	92.73 197	94.57 237	97.66 143	85.41 343	98.21 43	88.23 447	93.43 114	94.70 163	98.21 82	72.57 364	99.07 175	93.05 175	98.49 123	99.25 76

test1111		93.19 197	92.82 191	94.30 254	97.58 155	84.56 360	98.21 43	89.02 445	93.53 109	94.58 165	98.21 82	72.69 363	99.05 180	93.06 174	98.48 125	99.28 73

UGNet		94.04 160	93.28 174	96.31 123	96.85 196	91.19 155	97.88 84	97.68 153	94.40 80	93.00 212	96.18 235	73.39 362	99.61 84	91.72 202	98.46 126	98.13 200
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
fmvsm_s_conf0.5_n_2		96.62 65	96.82 50	96.02 144	97.98 120	90.43 187	97.50 146	98.59 23	96.59 8	99.31 4	99.08 7	84.47 187	99.75 52	99.37 4	98.45 127	97.88 222

CANet_DTU		94.37 144	93.65 156	96.55 99	96.46 240	92.13 114	96.21 283	96.67 284	94.38 82	93.53 197	97.03 187	79.34 293	99.71 61	90.76 225	98.45 127	97.82 230

test_fmvs1_n		92.73 221	92.88 189	92.29 343	96.08 272	81.05 400	97.98 66	97.08 239	90.72 225	96.79 81	98.18 85	63.07 426	98.45 252	97.62 38	98.42 129	97.36 252

fmvsm_s_conf0.5_n_a		96.75 57	96.93 41	96.20 134	97.64 145	90.72 177	98.00 62	98.73 10	94.55 71	98.91 22	99.08 7	88.22 114	99.63 82	98.91 19	98.37 130	98.25 190

TAPA-MVS	90.10 7	92.30 236	91.22 255	95.56 178	98.33 86	89.60 217	96.79 225	97.65 156	81.83 413	91.52 249	97.23 170	87.94 119	98.91 194	71.31 437	98.37 130	98.17 198
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
fmvsm_s_conf0.1_n_a		96.40 74	96.47 68	96.16 136	95.48 297	90.69 178	97.91 80	98.33 40	94.07 87	98.93 18	99.14 1	87.44 135	99.61 84	98.63 24	98.32 132	98.18 195

EI-MVSNet-Vis-set		96.51 69	96.47 68	96.63 93	98.24 95	91.20 154	96.89 214	97.73 146	94.74 63	96.49 100	98.49 52	90.88 76	99.58 92	96.44 70	98.32 132	99.13 85

KinetiMVS		95.26 111	94.75 122	96.79 85	96.99 187	92.05 116	97.82 94	97.78 140	94.77 61	96.46 103	97.70 130	80.62 269	99.34 132	92.37 183	98.28 134	98.97 106

PS-MVSNAJ		95.37 106	95.33 103	95.49 185	97.35 161	90.66 180	95.31 336	97.48 183	93.85 96	96.51 99	95.70 265	88.65 105	99.65 73	94.80 132	98.27 135	96.17 288

LS3D		93.57 182	92.61 203	96.47 110	97.59 151	91.61 133	97.67 118	97.72 148	85.17 378	90.29 276	98.34 69	84.60 184	99.73 55	83.85 360	98.27 135	98.06 211

test_vis1_n		92.37 232	92.26 216	92.72 331	94.75 347	82.64 382	98.02 60	96.80 274	91.18 206	97.77 53	97.93 104	58.02 436	98.29 268	97.63 36	98.21 137	97.23 260

ETV-MVS		96.02 86	95.89 86	96.40 116	97.16 170	92.44 101	97.47 155	97.77 142	94.55 71	96.48 101	94.51 322	91.23 67	98.92 192	95.65 105	98.19 138	97.82 230

PVSNet_Blended		94.87 130	94.56 128	95.81 161	98.27 91	89.46 227	95.47 328	98.36 35	88.84 292	94.36 171	96.09 245	88.02 117	99.58 92	93.44 164	98.18 139	98.40 176

MAR-MVS		94.22 148	93.46 166	96.51 106	98.00 119	92.19 113	97.67 118	97.47 187	88.13 318	93.00 212	95.84 253	84.86 182	99.51 111	87.99 285	98.17 140	97.83 229
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
MS-PatchMatch		90.27 324	89.77 320	91.78 362	94.33 364	84.72 359	95.55 323	96.73 276	86.17 363	86.36 381	95.28 284	71.28 373	97.80 335	84.09 354	98.14 141	92.81 412

mvsmamba		94.57 139	94.14 143	95.87 154	97.03 183	89.93 208	97.84 89	95.85 324	91.34 196	94.79 161	96.80 197	80.67 267	98.81 205	94.85 127	98.12 142	98.85 130

AdaColmap		94.34 145	93.68 155	96.31 123	98.59 71	91.68 131	96.59 251	97.81 138	89.87 254	92.15 231	97.06 181	83.62 203	99.54 104	89.34 259	98.07 143	97.70 235

fmvsm_s_conf0.1_n_2		96.33 79	96.44 74	96.00 148	97.30 162	90.37 193	97.53 143	97.92 121	96.52 9	99.14 13	99.08 7	83.21 209	99.74 53	99.22 9	98.06 144	97.88 222

Elysia		94.00 162	93.12 178	96.64 89	96.08 272	92.72 91	97.50 146	97.63 160	91.15 209	94.82 158	97.12 176	74.98 347	99.06 177	90.78 223	98.02 145	98.12 202

StellarMVS		94.00 162	93.12 178	96.64 89	96.08 272	92.72 91	97.50 146	97.63 160	91.15 209	94.82 158	97.12 176	74.98 347	99.06 177	90.78 223	98.02 145	98.12 202

MVP-Stereo		90.74 310	90.08 304	92.71 332	93.19 400	88.20 270	95.86 304	96.27 306	86.07 364	84.86 394	94.76 308	77.84 322	97.75 342	83.88 359	98.01 147	92.17 427
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Vis-MVSNet (Re-imp)		94.15 152	93.88 149	94.95 215	97.61 149	87.92 279	98.10 52	95.80 327	92.22 162	93.02 211	97.45 153	84.53 186	97.91 325	88.24 281	97.97 148	99.02 98

EI-MVSNet-UG-set		96.34 78	96.30 77	96.47 110	98.20 101	90.93 168	96.86 217	97.72 148	94.67 66	96.16 116	98.46 56	90.43 81	99.58 92	96.23 76	97.96 149	98.90 122

GDP-MVS		95.62 100	95.13 109	97.09 75	96.79 204	93.26 72	97.89 83	97.83 136	93.58 103	96.80 79	97.82 120	83.06 216	99.16 155	94.40 144	97.95 150	98.87 128

IS-MVSNet		94.90 127	94.52 132	96.05 141	97.67 141	90.56 181	98.44 22	96.22 309	93.21 121	93.99 182	97.74 127	85.55 167	98.45 252	89.98 241	97.86 151	99.14 84

CNLPA		94.28 146	93.53 161	96.52 102	98.38 84	92.55 98	96.59 251	96.88 268	90.13 250	91.91 239	97.24 169	85.21 173	99.09 168	87.64 298	97.83 152	97.92 219

xiu_mvs_v2_base		95.32 109	95.29 104	95.40 190	97.22 166	90.50 183	95.44 329	97.44 198	93.70 101	96.46 103	96.18 235	88.59 109	99.53 106	94.79 135	97.81 153	96.17 288

PAPM_NR		95.01 121	94.59 126	96.26 129	98.89 56	90.68 179	97.24 179	97.73 146	91.80 176	92.93 217	96.62 215	89.13 96	99.14 160	89.21 265	97.78 154	98.97 106

PVSNet_Blended_VisFu		95.27 110	94.91 116	96.38 119	98.20 101	90.86 171	97.27 177	98.25 56	90.21 246	94.18 177	97.27 167	87.48 134	99.73 55	93.53 161	97.77 155	98.55 157

TSAR-MVS + GP.		96.69 62	96.49 66	97.27 63	98.31 87	93.39 63	96.79 225	96.72 277	94.17 85	97.44 59	97.66 136	92.76 31	99.33 133	96.86 57	97.76 156	99.08 93

ACMMP		96.27 81	95.93 84	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 134	94.56 166	98.39 62	88.96 98	99.85 18	94.57 142	97.63 157	99.36 68
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
BH-RMVSNet		92.72 222	91.97 225	94.97 213	97.16 170	87.99 277	96.15 288	95.60 338	90.62 233	91.87 241	97.15 175	78.41 312	98.57 243	83.16 362	97.60 158	98.36 180

PatchMatch-RL		92.90 212	92.02 223	95.56 178	98.19 103	90.80 173	95.27 339	97.18 228	87.96 320	91.86 242	95.68 266	80.44 273	98.99 185	84.01 355	97.54 159	96.89 270

diffmvs_AUTHOR		95.33 108	95.27 105	95.50 184	96.37 247	89.08 245	96.08 291	97.38 208	93.09 132	96.53 98	97.74 127	86.45 149	98.68 227	96.32 72	97.48 160	98.75 140

xiu_mvs_v1_base_debu		95.01 121	94.76 119	95.75 166	96.58 221	91.71 128	96.25 279	97.35 212	92.99 134	96.70 85	96.63 212	82.67 227	99.44 123	96.22 77	97.46 161	96.11 294

xiu_mvs_v1_base		95.01 121	94.76 119	95.75 166	96.58 221	91.71 128	96.25 279	97.35 212	92.99 134	96.70 85	96.63 212	82.67 227	99.44 123	96.22 77	97.46 161	96.11 294

xiu_mvs_v1_base_debi		95.01 121	94.76 119	95.75 166	96.58 221	91.71 128	96.25 279	97.35 212	92.99 134	96.70 85	96.63 212	82.67 227	99.44 123	96.22 77	97.46 161	96.11 294

MVS		91.71 258	90.44 287	95.51 182	95.20 322	91.59 135	96.04 293	97.45 194	73.44 443	87.36 361	95.60 270	85.42 168	99.10 165	85.97 329	97.46 161	95.83 303

PVSNet	86.66 18	92.24 240	91.74 235	93.73 287	97.77 135	83.69 373	92.88 414	96.72 277	87.91 322	93.00 212	94.86 303	78.51 310	99.05 180	86.53 316	97.45 165	98.47 168

PAPR		94.18 149	93.42 171	96.48 109	97.64 145	91.42 145	95.55 323	97.71 152	88.99 285	92.34 227	95.82 255	89.19 94	99.11 163	86.14 324	97.38 166	98.90 122

LCM-MVSNet-Re		92.50 224	92.52 208	92.44 336	96.82 201	81.89 393	96.92 211	93.71 412	92.41 157	84.30 398	94.60 317	85.08 175	97.03 386	91.51 207	97.36 167	98.40 176

UA-Net		95.95 90	95.53 92	97.20 68	97.67 141	92.98 80	97.65 122	98.13 79	94.81 57	96.61 91	98.35 66	88.87 100	99.51 111	90.36 236	97.35 168	99.11 89

casdiffmvs		95.64 99	95.49 93	96.08 138	96.76 213	90.45 185	97.29 176	97.44 198	94.00 90	95.46 146	97.98 101	87.52 133	98.73 219	95.64 106	97.33 169	99.08 93
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs_mvg		95.81 96	95.57 90	96.51 106	96.87 193	91.49 139	97.50 146	97.56 174	93.99 91	95.13 152	97.92 107	87.89 120	98.78 208	95.97 92	97.33 169	99.26 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RRT-MVS		94.51 141	94.35 138	94.98 211	96.40 243	86.55 316	97.56 137	97.41 203	93.19 124	94.93 155	97.04 182	79.12 297	99.30 139	96.19 84	97.32 171	99.09 91

SSM_0404		94.73 136	94.31 140	95.98 150	97.05 180	90.90 170	97.01 202	97.29 217	91.24 201	94.17 178	97.60 144	85.03 176	98.76 212	92.14 189	97.30 172	98.29 188

PCF-MVS	89.48 11	91.56 268	89.95 312	96.36 121	96.60 219	92.52 99	92.51 419	97.26 221	79.41 428	88.90 321	96.56 217	84.04 197	99.55 102	77.01 413	97.30 172	97.01 264
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
BH-untuned		92.94 210	92.62 202	93.92 280	97.22 166	86.16 327	96.40 265	96.25 308	90.06 251	89.79 295	96.17 237	83.19 210	98.35 263	87.19 308	97.27 174	97.24 259

baseline		95.58 102	95.42 99	96.08 138	96.78 208	90.41 188	97.16 190	97.45 194	93.69 102	95.65 139	97.85 116	87.29 138	98.68 227	95.66 102	97.25 175	99.13 85

gg-mvs-nofinetune		87.82 363	85.61 376	94.44 244	94.46 359	89.27 238	91.21 429	84.61 457	80.88 419	89.89 293	74.98 453	71.50 371	97.53 361	85.75 333	97.21 176	96.51 278

viewmanbaseed2359cas		95.24 113	95.02 113	95.91 152	96.87 193	89.98 204	96.82 222	97.49 181	92.26 160	95.47 145	97.82 120	86.47 148	98.69 225	94.80 132	97.20 177	99.06 96

diffmvs		95.25 112	95.13 109	95.63 174	96.43 242	89.34 232	95.99 297	97.35 212	92.83 146	96.31 109	97.37 159	86.44 150	98.67 230	96.26 74	97.19 178	98.87 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		94.89 128	94.62 125	95.68 172	96.83 199	89.55 221	96.70 236	97.17 230	91.17 207	95.60 140	96.11 244	87.87 122	98.76 212	93.01 178	97.17 179	98.72 144

PLC	91.00 6	94.11 156	93.43 169	96.13 137	98.58 73	91.15 161	96.69 238	97.39 205	87.29 342	91.37 253	96.71 201	88.39 110	99.52 110	87.33 305	97.13 180	97.73 233
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LuminaMVS		94.89 128	94.35 138	96.53 100	95.48 297	92.80 87	96.88 216	96.18 313	92.85 145	95.92 126	96.87 196	81.44 254	98.83 202	96.43 71	97.10 181	97.94 218

1314		92.81 219	92.03 222	95.14 200	95.33 312	89.52 224	96.04 293	97.44 198	87.72 332	86.25 382	95.33 281	83.84 198	98.79 207	89.26 262	97.05 182	97.11 263

viewmacassd2359aftdt		95.07 120	94.80 118	95.87 154	96.53 230	89.84 210	96.90 213	97.48 183	92.44 155	95.36 147	97.89 109	85.23 172	98.68 227	94.40 144	97.00 183	99.09 91

guyue		95.17 118	94.96 114	95.82 160	96.97 189	89.65 214	97.56 137	95.58 340	94.82 55	95.72 133	97.42 157	82.90 221	98.84 201	96.71 62	96.93 184	98.96 109

FE-MVS		92.05 248	91.05 260	95.08 203	96.83 199	87.93 278	93.91 388	95.70 331	86.30 359	94.15 179	94.97 296	76.59 331	99.21 146	84.10 353	96.86 185	98.09 208

EPNet_dtu		91.71 258	91.28 251	92.99 320	93.76 380	83.71 372	96.69 238	95.28 354	93.15 128	87.02 370	95.95 248	83.37 207	97.38 374	79.46 399	96.84 186	97.88 222
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Effi-MVS+		94.93 126	94.45 135	96.36 121	96.61 218	91.47 142	96.41 261	97.41 203	91.02 215	94.50 168	95.92 249	87.53 131	98.78 208	93.89 155	96.81 187	98.84 133

OMC-MVS		95.09 119	94.70 123	96.25 132	98.46 75	91.28 148	96.43 258	97.57 170	92.04 171	94.77 162	97.96 103	87.01 142	99.09 168	91.31 212	96.77 188	98.36 180

test-LLR		91.42 277	91.19 256	92.12 349	94.59 354	80.66 403	94.29 375	92.98 419	91.11 211	90.76 269	92.37 397	79.02 301	98.07 294	88.81 273	96.74 189	97.63 237

test-mter		90.19 329	89.54 328	92.12 349	94.59 354	80.66 403	94.29 375	92.98 419	87.68 333	90.76 269	92.37 397	67.67 403	98.07 294	88.81 273	96.74 189	97.63 237

F-COLMAP		93.58 180	92.98 185	95.37 191	98.40 81	88.98 247	97.18 188	97.29 217	87.75 331	90.49 272	97.10 179	85.21 173	99.50 114	86.70 315	96.72 191	97.63 237

mvs_anonymous		93.82 172	93.74 153	94.06 264	96.44 241	85.41 343	95.81 307	97.05 247	89.85 257	90.09 287	96.36 227	87.44 135	97.75 342	93.97 151	96.69 192	99.02 98

DP-MVS		92.76 220	91.51 244	96.52 102	98.77 58	90.99 164	97.38 167	96.08 316	82.38 409	89.29 313	97.87 113	83.77 199	99.69 67	81.37 383	96.69 192	98.89 126

TESTMET0.1,1		90.06 331	89.42 331	91.97 352	94.41 362	80.62 405	94.29 375	91.97 431	87.28 343	90.44 273	92.47 396	68.79 395	97.67 347	88.50 280	96.60 194	97.61 241

viewmambaseed2359dif		94.28 146	94.14 143	94.71 229	96.21 253	86.97 303	95.93 300	97.11 235	89.00 284	95.00 154	97.70 130	86.02 158	98.59 242	93.71 160	96.59 195	98.57 156

mamba_0408		93.70 177	92.99 182	95.83 159	96.79 204	90.38 190	88.69 444	97.07 242	90.96 217	93.68 189	97.31 163	84.97 179	98.76 212	90.95 219	96.51 196	98.35 182

SSM_04072		93.51 185	92.99 182	95.05 204	96.79 204	90.38 190	88.69 444	97.07 242	90.96 217	93.68 189	97.31 163	84.97 179	96.42 403	90.95 219	96.51 196	98.35 182

SSM_0407		94.54 140	94.12 145	95.80 162	96.79 204	90.38 190	96.79 225	97.29 217	91.24 201	93.68 189	97.60 144	85.03 176	98.67 230	92.14 189	96.51 196	98.35 182

GeoE		93.89 169	93.28 174	95.72 170	96.96 190	89.75 213	98.24 39	96.92 263	89.47 268	92.12 233	97.21 171	84.42 188	98.39 260	87.71 292	96.50 199	99.01 101

EPP-MVSNet		95.22 115	95.04 112	95.76 164	97.49 158	89.56 220	98.67 11	97.00 254	90.69 226	94.24 174	97.62 142	89.79 90	98.81 205	93.39 167	96.49 200	98.92 118

PMMVS		92.86 215	92.34 213	94.42 246	94.92 338	86.73 309	94.53 361	96.38 300	84.78 385	94.27 173	95.12 293	83.13 213	98.40 255	91.47 209	96.49 200	98.12 202

Fast-Effi-MVS+		93.46 186	92.75 195	95.59 177	96.77 210	90.03 199	96.81 224	97.13 232	88.19 313	91.30 257	94.27 340	86.21 154	98.63 235	87.66 297	96.46 202	98.12 202

SymmetryMVS		95.94 91	95.54 91	97.15 70	97.85 130	92.90 83	97.99 63	96.91 264	95.92 14	96.57 96	97.93 104	85.34 169	99.50 114	94.99 123	96.39 203	99.05 97

BH-w/o		92.14 245	91.75 233	93.31 308	96.99 187	85.73 337	95.67 315	95.69 333	88.73 299	89.26 315	94.82 306	82.97 219	98.07 294	85.26 340	96.32 204	96.13 293

FA-MVS(test-final)		93.52 184	92.92 187	95.31 194	96.77 210	88.54 258	94.82 353	96.21 311	89.61 263	94.20 176	95.25 287	83.24 208	99.14 160	90.01 240	96.16 205	98.25 190

sss		94.51 141	93.80 150	96.64 89	97.07 175	91.97 120	96.32 274	98.06 96	88.94 288	94.50 168	96.78 198	84.60 184	99.27 141	91.90 196	96.02 206	98.68 148

SCA		91.84 255	91.18 257	93.83 282	95.59 291	84.95 356	94.72 355	95.58 340	90.82 220	92.25 229	93.69 366	75.80 339	98.10 285	86.20 322	95.98 207	98.45 170

CDS-MVSNet		94.14 155	93.54 160	95.93 151	96.18 261	91.46 143	96.33 273	97.04 249	88.97 287	93.56 194	96.51 219	87.55 129	97.89 326	89.80 246	95.95 208	98.44 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPM		91.52 272	90.30 293	95.20 197	95.30 315	89.83 211	93.38 405	96.85 271	86.26 361	88.59 331	95.80 256	84.88 181	98.15 279	75.67 418	95.93 209	97.63 237

AstraMVS		94.82 133	94.64 124	95.34 193	96.36 248	88.09 275	97.58 133	94.56 387	94.98 44	95.70 136	97.92 107	81.93 247	98.93 190	96.87 56	95.88 210	98.99 105

LFMVS		93.60 179	92.63 201	96.52 102	98.13 109	91.27 149	97.94 76	93.39 415	90.57 238	96.29 110	98.31 75	69.00 394	99.16 155	94.18 148	95.87 211	99.12 88

thisisatest0515		92.29 237	91.30 250	95.25 196	96.60 219	88.90 249	94.36 370	92.32 427	87.92 321	93.43 202	94.57 318	77.28 326	99.00 184	89.42 257	95.86 212	97.86 226

CVMVSNet		91.23 289	91.75 233	89.67 401	95.77 284	74.69 437	96.44 256	94.88 375	85.81 367	92.18 230	97.64 140	79.07 298	95.58 419	88.06 284	95.86 212	98.74 143

TAMVS		94.01 161	93.46 166	95.64 173	96.16 263	90.45 185	96.71 235	96.89 267	89.27 275	93.46 201	96.92 192	87.29 138	97.94 319	88.70 277	95.74 214	98.53 159

Effi-MVS+-dtu		93.08 202	93.21 177	92.68 334	96.02 275	83.25 376	97.14 192	96.72 277	93.85 96	91.20 264	93.44 378	83.08 214	98.30 267	91.69 205	95.73 215	96.50 279

HyFIR lowres test		93.66 178	92.92 187	95.87 154	98.24 95	89.88 209	94.58 359	98.49 28	85.06 380	93.78 187	95.78 260	82.86 222	98.67 230	91.77 201	95.71 216	99.07 95

myMVS_eth3d28		91.52 272	90.97 263	93.17 314	96.91 191	83.24 377	95.61 321	94.96 371	92.24 161	91.98 237	93.28 382	69.31 391	98.40 255	88.71 276	95.68 217	97.88 222

thisisatest0530		93.03 205	92.21 217	95.49 185	97.07 175	89.11 244	97.49 154	92.19 428	90.16 248	94.09 180	96.41 224	76.43 335	99.05 180	90.38 235	95.68 217	98.31 187

mvsany_test1		93.93 168	93.98 147	93.78 286	94.94 337	86.80 306	94.62 357	92.55 426	88.77 298	96.85 78	98.49 52	88.98 97	98.08 290	95.03 121	95.62 219	96.46 282

icg_test_0407_2		93.58 180	93.46 166	93.94 276	96.19 257	86.16 327	93.73 394	97.24 224	91.54 184	93.50 198	97.04 182	85.64 165	96.91 392	90.68 228	95.59 220	98.76 136

IMVS_0407		93.94 166	93.75 152	94.49 241	96.19 257	86.16 327	96.35 269	97.24 224	91.54 184	93.50 198	97.04 182	85.64 165	98.54 245	90.68 228	95.59 220	98.76 136

IMVS_0404		92.44 227	91.92 227	94.00 268	96.19 257	86.16 327	93.84 391	97.24 224	91.54 184	88.17 345	97.04 182	76.96 329	97.09 383	90.68 228	95.59 220	98.76 136

IMVS_0403		93.98 164	93.79 151	94.55 238	96.19 257	86.16 327	96.35 269	97.24 224	91.54 184	93.59 193	97.04 182	85.86 160	98.73 219	90.68 228	95.59 220	98.76 136

UWE-MVS		89.91 334	89.48 330	91.21 374	95.88 277	78.23 430	94.91 352	90.26 441	89.11 279	92.35 226	94.52 321	68.76 396	97.96 313	83.95 357	95.59 220	97.42 250

MVS-HIRNet		82.47 404	81.21 407	86.26 421	95.38 304	69.21 448	88.96 443	89.49 443	66.28 450	80.79 422	74.08 455	68.48 400	97.39 373	71.93 435	95.47 225	92.18 426

tttt0517		92.96 208	92.33 214	94.87 218	97.11 173	87.16 299	97.97 72	92.09 429	90.63 232	93.88 186	97.01 188	76.50 332	99.06 177	90.29 238	95.45 226	98.38 178

GG-mvs-BLEND				93.62 294	93.69 382	89.20 240	92.39 421	83.33 459		87.98 350	89.84 427	71.00 375	96.87 394	82.08 375	95.40 227	94.80 370

PatchmatchNet		91.91 252	91.35 246	93.59 296	95.38 304	84.11 366	93.15 409	95.39 347	89.54 265	92.10 234	93.68 368	82.82 224	98.13 280	84.81 344	95.32 228	98.52 160
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VNet		95.89 93	95.45 96	97.21 67	98.07 114	92.94 81	97.50 146	98.15 76	93.87 95	97.52 56	97.61 143	85.29 171	99.53 106	95.81 99	95.27 229	99.16 81

UBG		91.55 269	90.76 273	93.94 276	96.52 233	85.06 352	95.22 342	94.54 388	90.47 241	91.98 237	92.71 389	72.02 367	98.74 217	88.10 283	95.26 230	98.01 214

DSMNet-mixed		86.34 380	86.12 374	87.00 419	89.88 432	70.43 445	94.93 351	90.08 442	77.97 434	85.42 390	92.78 388	74.44 353	93.96 436	74.43 423	95.14 231	96.62 276

test_yl		94.78 134	94.23 141	96.43 114	97.74 137	91.22 150	96.85 218	97.10 236	91.23 204	95.71 134	96.93 189	84.30 190	99.31 137	93.10 171	95.12 232	98.75 140

DCV-MVSNet		94.78 134	94.23 141	96.43 114	97.74 137	91.22 150	96.85 218	97.10 236	91.23 204	95.71 134	96.93 189	84.30 190	99.31 137	93.10 171	95.12 232	98.75 140

alignmvs		95.87 95	95.23 106	97.78 32	97.56 157	95.19 21	97.86 85	97.17 230	94.39 81	96.47 102	96.40 225	85.89 159	99.20 147	96.21 81	95.11 234	98.95 112

MSDG		91.42 277	90.24 297	94.96 214	97.15 172	88.91 248	93.69 397	96.32 302	85.72 369	86.93 374	96.47 221	80.24 277	98.98 186	80.57 390	95.05 235	96.98 265

VDD-MVS		93.82 172	93.08 180	96.02 144	97.88 129	89.96 207	97.72 111	95.85 324	92.43 156	95.86 128	98.44 58	68.42 401	99.39 128	96.31 73	94.85 236	98.71 146

VDDNet		93.05 204	92.07 219	96.02 144	96.84 197	90.39 189	98.08 54	95.85 324	86.22 362	95.79 131	98.46 56	67.59 404	99.19 148	94.92 126	94.85 236	98.47 168

sasdasda		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 111	96.12 240	87.65 125	99.18 151	96.20 82	94.82 238	98.91 119

canonicalmvs		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 111	96.12 240	87.65 125	99.18 151	96.20 82	94.82 238	98.91 119

Patchmatch-test		89.42 346	87.99 353	93.70 290	95.27 316	85.11 350	88.98 442	94.37 396	81.11 417	87.10 368	93.69 366	82.28 237	97.50 364	74.37 424	94.76 240	98.48 167

cascas		91.20 291	90.08 304	94.58 236	94.97 333	89.16 243	93.65 399	97.59 168	79.90 426	89.40 308	92.92 387	75.36 343	98.36 262	92.14 189	94.75 241	96.23 284

Fast-Effi-MVS+-dtu		92.29 237	91.99 224	93.21 313	95.27 316	85.52 340	97.03 197	96.63 288	92.09 169	89.11 319	95.14 291	80.33 276	98.08 290	87.54 301	94.74 242	96.03 297

MGCFI-Net		95.94 91	95.40 100	97.56 49	97.59 151	94.62 31	98.21 43	97.57 170	94.41 79	96.17 115	96.16 238	87.54 130	99.17 153	96.19 84	94.73 243	98.91 119

WTY-MVS		94.71 137	94.02 146	96.79 85	97.71 139	92.05 116	96.59 251	97.35 212	90.61 234	94.64 164	96.93 189	86.41 151	99.39 128	91.20 215	94.71 244	98.94 113

baseline2		91.63 262	90.86 267	93.94 276	94.33 364	86.32 320	95.92 301	91.64 433	89.37 272	86.94 373	94.69 311	81.62 252	98.69 225	88.64 278	94.57 245	96.81 272

HY-MVS	89.66 9	93.87 170	92.95 186	96.63 93	97.10 174	92.49 100	95.64 320	96.64 285	89.05 282	93.00 212	95.79 259	85.77 163	99.45 122	89.16 268	94.35 246	97.96 216

MDTV_nov1_ep13			90.76 273		95.22 320	80.33 409	93.03 412	95.28 354	88.14 317	92.84 218	93.83 359	81.34 255	98.08 290	82.86 365	94.34 247

UWE-MVS-28		86.81 374	86.41 369	88.02 413	92.87 405	74.60 438	95.38 332	86.70 453	88.17 314	87.28 364	94.67 314	70.83 377	93.30 441	67.45 443	94.31 248	96.17 288

testing11		91.68 261	90.75 275	94.47 242	96.53 230	86.56 315	95.76 311	94.51 390	91.10 213	91.24 262	93.59 372	68.59 398	98.86 197	91.10 216	94.29 249	98.00 215

ETVMVS		90.52 318	89.14 339	94.67 231	96.81 203	87.85 283	95.91 302	93.97 406	89.71 261	92.34 227	92.48 395	65.41 421	97.96 313	81.37 383	94.27 250	98.21 193

testing3-2		92.10 246	92.05 220	92.27 344	97.71 139	79.56 419	97.42 159	94.41 393	93.53 109	93.22 209	95.49 276	69.16 393	99.11 163	93.25 168	94.22 251	98.13 200

WB-MVSnew		89.88 337	89.56 327	90.82 383	94.57 357	83.06 379	95.65 319	92.85 421	87.86 324	90.83 268	94.10 349	79.66 289	96.88 393	76.34 414	94.19 252	92.54 418

thres200		92.23 241	91.39 245	94.75 228	97.61 149	89.03 246	96.60 250	95.09 364	92.08 170	93.28 206	94.00 355	78.39 313	99.04 183	81.26 386	94.18 253	96.19 287

Syy-MVS		87.13 370	87.02 365	87.47 415	95.16 323	73.21 443	95.00 349	93.93 408	88.55 304	86.96 371	91.99 406	75.90 337	94.00 434	61.59 449	94.11 254	95.20 344

myMVS_eth3d		87.18 369	86.38 370	89.58 402	95.16 323	79.53 420	95.00 349	93.93 408	88.55 304	86.96 371	91.99 406	56.23 440	94.00 434	75.47 420	94.11 254	95.20 344

testing3		87.67 365	86.88 366	90.05 396	96.14 266	80.71 402	97.10 194	92.85 421	90.15 249	87.54 356	94.55 319	55.70 441	94.10 433	73.77 428	94.10 256	95.35 333

testing222		90.31 322	88.96 341	94.35 248	96.54 228	87.29 291	95.50 326	93.84 410	90.97 216	91.75 245	92.96 386	62.18 431	98.00 304	82.86 365	94.08 257	97.76 232

thres100view900		92.43 228	91.58 239	94.98 211	97.92 126	89.37 231	97.71 113	94.66 383	92.20 164	93.31 205	94.90 301	78.06 319	99.08 171	81.40 380	94.08 257	96.48 280

tfpn200view9		92.38 231	91.52 242	94.95 215	97.85 130	89.29 235	97.41 160	94.88 375	92.19 166	93.27 207	94.46 327	78.17 315	99.08 171	81.40 380	94.08 257	96.48 280

thres400		92.42 229	91.52 242	95.12 202	97.85 130	89.29 235	97.41 160	94.88 375	92.19 166	93.27 207	94.46 327	78.17 315	99.08 171	81.40 380	94.08 257	96.98 265

thres600view7		92.49 226	91.60 238	95.18 198	97.91 127	89.47 225	97.65 122	94.66 383	92.18 168	93.33 204	94.91 300	78.06 319	99.10 165	81.61 376	94.06 261	96.98 265

CR-MVSNet		90.82 307	89.77 320	93.95 274	94.45 360	87.19 297	90.23 435	95.68 335	86.89 349	92.40 221	92.36 400	80.91 262	97.05 385	81.09 387	93.95 262	97.60 242

RPMNet		88.98 349	87.05 363	94.77 226	94.45 360	87.19 297	90.23 435	98.03 105	77.87 435	92.40 221	87.55 442	80.17 279	99.51 111	68.84 442	93.95 262	97.60 242

testing91		91.90 253	91.02 261	94.53 240	96.54 228	86.55 316	95.86 304	95.64 337	91.77 178	91.89 240	93.47 377	69.94 386	98.86 197	90.23 239	93.86 264	98.18 195

SD_0403		90.01 332	90.02 310	89.96 398	95.65 289	76.76 432	95.76 311	96.46 296	90.58 237	86.59 378	96.29 230	82.12 241	94.78 427	73.00 432	93.76 265	98.35 182

testing99		91.62 263	90.72 278	94.32 251	96.48 237	86.11 332	95.81 307	94.76 380	91.55 183	91.75 245	93.44 378	68.55 399	98.82 203	90.43 233	93.69 266	98.04 212

1112_ss		93.37 190	92.42 212	96.21 133	97.05 180	90.99 164	96.31 275	96.72 277	86.87 350	89.83 294	96.69 205	86.51 147	99.14 160	88.12 282	93.67 267	98.50 163

PatchT		88.87 353	87.42 357	93.22 312	94.08 371	85.10 351	89.51 440	94.64 385	81.92 412	92.36 224	88.15 438	80.05 281	97.01 388	72.43 433	93.65 268	97.54 245

COLMAP_ROB	87.81 15	90.40 321	89.28 334	93.79 285	97.95 123	87.13 300	96.92 211	95.89 323	82.83 406	86.88 376	97.18 172	73.77 359	99.29 140	78.44 404	93.62 269	94.95 354
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GA-MVS		91.38 279	90.31 292	94.59 232	94.65 352	87.62 287	94.34 371	96.19 312	90.73 224	90.35 275	93.83 359	71.84 369	97.96 313	87.22 307	93.61 270	98.21 193

TR-MVS		91.48 275	90.59 283	94.16 260	96.40 243	87.33 290	95.67 315	95.34 353	87.68 333	91.46 251	95.52 275	76.77 330	98.35 263	82.85 367	93.61 270	96.79 273

Test_1112_low_res		92.84 217	91.84 230	95.85 158	97.04 182	89.97 206	95.53 325	96.64 285	85.38 373	89.65 301	95.18 289	85.86 160	99.10 165	87.70 293	93.58 272	98.49 165

ab-mvs		93.57 182	92.55 205	96.64 89	97.28 164	91.96 122	95.40 330	97.45 194	89.81 259	93.22 209	96.28 231	79.62 290	99.46 120	90.74 226	93.11 273	98.50 163

AllTest		90.23 326	88.98 340	93.98 270	97.94 124	86.64 310	96.51 255	95.54 343	85.38 373	85.49 388	96.77 199	70.28 381	99.15 157	80.02 394	92.87 274	96.15 291

TestCases				93.98 270	97.94 124	86.64 310		95.54 343	85.38 373	85.49 388	96.77 199	70.28 381	99.15 157	80.02 394	92.87 274	96.15 291

SDMVSNet		94.17 150	93.61 157	95.86 157	98.09 110	91.37 146	97.35 169	98.20 64	93.18 126	91.79 243	97.28 165	79.13 296	98.93 190	94.61 139	92.84 276	97.28 257

sd_testset		93.10 201	92.45 211	95.05 204	98.09 110	89.21 239	96.89 214	97.64 158	93.18 126	91.79 243	97.28 165	75.35 344	98.65 233	88.99 270	92.84 276	97.28 257

MIMVSNet		88.50 357	86.76 367	93.72 289	94.84 343	87.77 285	91.39 425	94.05 403	86.41 357	87.99 349	92.59 393	63.27 425	95.82 413	77.44 407	92.84 276	97.57 244

Anonymous202405211		92.07 247	90.83 271	95.76 164	98.19 103	88.75 251	97.58 133	95.00 367	86.00 365	93.64 192	97.45 153	66.24 416	99.53 106	90.68 228	92.71 279	99.01 101

EPMVS		90.70 312	89.81 318	93.37 306	94.73 349	84.21 364	93.67 398	88.02 448	89.50 267	92.38 223	93.49 375	77.82 323	97.78 337	86.03 328	92.68 280	98.11 207

XVG-OURS		93.72 176	93.35 172	94.80 224	97.07 175	88.61 254	94.79 354	97.46 189	91.97 174	93.99 182	97.86 115	81.74 250	98.88 196	92.64 182	92.67 281	96.92 269

XVG-OURS-SEG-HR		93.86 171	93.55 159	94.81 221	97.06 178	88.53 259	95.28 337	97.45 194	91.68 181	94.08 181	97.68 133	82.41 235	98.90 195	93.84 157	92.47 282	96.98 265

CLD-MVS		92.98 207	92.53 207	94.32 251	96.12 268	89.20 240	95.28 337	97.47 187	92.66 151	89.90 291	95.62 269	80.58 270	98.40 255	92.73 181	92.40 283	95.38 331
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OPM-MVS		93.28 193	92.76 193	94.82 219	94.63 353	90.77 175	96.65 242	97.18 228	93.72 99	91.68 247	97.26 168	79.33 294	98.63 235	92.13 192	92.28 284	95.07 350
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP_MVS		93.78 174	93.43 169	94.82 219	96.21 253	89.99 202	97.74 106	97.51 178	94.85 51	91.34 254	96.64 208	81.32 256	98.60 238	93.02 176	92.23 285	95.86 299

plane_prior5								97.51 178					98.60 238	93.02 176	92.23 285	95.86 299

RPSCF		90.75 309	90.86 267	90.42 391	96.84 197	76.29 435	95.61 321	96.34 301	83.89 394	91.38 252	97.87 113	76.45 333	98.78 208	87.16 310	92.23 285	96.20 286

CostFormer		91.18 294	90.70 279	92.62 335	94.84 343	81.76 394	94.09 381	94.43 391	84.15 391	92.72 219	93.77 363	79.43 292	98.20 274	90.70 227	92.18 288	97.90 220

plane_prior						89.99 202	97.24 179		94.06 88						92.16 289

HQP3-MVS								97.39 205							92.10 290

HQP-MVS		93.19 197	92.74 196	94.54 239	95.86 278	89.33 233	96.65 242	97.39 205	93.55 105	90.14 278	95.87 251	80.95 260	98.50 248	92.13 192	92.10 290	95.78 307

tpm2		89.96 333	89.21 336	92.23 347	94.91 340	81.25 397	93.78 392	94.42 392	80.62 423	91.56 248	93.44 378	76.44 334	97.94 319	85.60 334	92.08 292	97.49 246

LPG-MVS_test		92.94 210	92.56 204	94.10 262	96.16 263	88.26 267	97.65 122	97.46 189	91.29 197	90.12 284	97.16 173	79.05 299	98.73 219	92.25 186	91.89 293	95.31 336

LGP-MVS_train				94.10 262	96.16 263	88.26 267		97.46 189	91.29 197	90.12 284	97.16 173	79.05 299	98.73 219	92.25 186	91.89 293	95.31 336

ACMM	89.79 8	92.96 208	92.50 209	94.35 248	96.30 251	88.71 252	97.58 133	97.36 211	91.40 195	90.53 271	96.65 207	79.77 286	98.75 215	91.24 214	91.64 295	95.59 317
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
JIA-IIPM		88.26 360	87.04 364	91.91 354	93.52 388	81.42 396	89.38 441	94.38 395	80.84 420	90.93 266	80.74 450	79.22 295	97.92 322	82.76 369	91.62 296	96.38 283

test_djsdf		93.07 203	92.76 193	94.00 268	93.49 390	88.70 253	98.22 41	97.57 170	91.42 193	90.08 288	95.55 273	82.85 223	97.92 322	94.07 149	91.58 297	95.40 329

jajsoiax		92.42 229	91.89 229	94.03 267	93.33 398	88.50 260	97.73 108	97.53 176	92.00 173	88.85 325	96.50 220	75.62 342	98.11 284	93.88 156	91.56 298	95.48 319

mvs_tets		92.31 235	91.76 232	93.94 276	93.41 395	88.29 265	97.63 128	97.53 176	92.04 171	88.76 328	96.45 222	74.62 352	98.09 289	93.91 154	91.48 299	95.45 324

ACMP	89.59 10	92.62 223	92.14 218	94.05 265	96.40 243	88.20 270	97.36 168	97.25 223	91.52 188	88.30 339	96.64 208	78.46 311	98.72 223	91.86 199	91.48 299	95.23 343
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ADS-MVSNet2		89.45 345	88.59 347	92.03 351	95.86 278	82.26 390	90.93 430	94.32 399	83.23 404	91.28 260	91.81 410	79.01 303	95.99 408	79.52 396	91.39 301	97.84 227

ADS-MVSNet		89.89 336	88.68 346	93.53 300	95.86 278	84.89 357	90.93 430	95.07 365	83.23 404	91.28 260	91.81 410	79.01 303	97.85 328	79.52 396	91.39 301	97.84 227

anonymousdsp		92.16 243	91.55 240	93.97 272	92.58 413	89.55 221	97.51 145	97.42 202	89.42 271	88.40 335	94.84 304	80.66 268	97.88 327	91.87 198	91.28 303	94.48 382

CMPMVS	62.92 21	85.62 390	84.92 385	87.74 414	89.14 436	73.12 444	94.17 378	96.80 274	73.98 440	73.65 442	94.93 299	66.36 413	97.61 354	83.95 357	91.28 303	92.48 420
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvs2		89.77 341	89.93 313	89.31 407	93.68 383	76.37 434	97.64 126	95.90 321	89.84 258	91.49 250	96.26 233	58.77 434	97.10 382	94.65 137	91.13 305	94.46 383

Anonymous20240529		91.98 250	90.73 277	95.73 169	98.14 107	89.40 229	97.99 63	97.72 148	79.63 427	93.54 196	97.41 158	69.94 386	99.56 100	91.04 218	91.11 306	98.22 192

XVG-ACMP-BASELINE		90.93 304	90.21 301	93.09 317	94.31 366	85.89 333	95.33 334	97.26 221	91.06 214	89.38 309	95.44 279	68.61 397	98.60 238	89.46 255	91.05 307	94.79 372

ACMMP++															91.02 308

UniMVSNet_ETH3D		91.34 284	90.22 300	94.68 230	94.86 342	87.86 282	97.23 183	97.46 189	87.99 319	89.90 291	96.92 192	66.35 414	98.23 271	90.30 237	90.99 309	97.96 216

D2MVS		91.30 286	90.95 264	92.35 339	94.71 350	85.52 340	96.18 286	98.21 62	88.89 290	86.60 377	93.82 361	79.92 284	97.95 317	89.29 261	90.95 310	93.56 402

PS-MVSNAJss		93.74 175	93.51 164	94.44 244	93.91 375	89.28 237	97.75 104	97.56 174	92.50 154	89.94 290	96.54 218	88.65 105	98.18 277	93.83 158	90.90 311	95.86 299

EG-PatchMatch MVS		87.02 372	85.44 377	91.76 364	92.67 410	85.00 353	96.08 291	96.45 297	83.41 403	79.52 429	93.49 375	57.10 438	97.72 344	79.34 401	90.87 312	92.56 417

PVSNet_BlendedMVS		94.06 158	93.92 148	94.47 242	98.27 91	89.46 227	96.73 232	98.36 35	90.17 247	94.36 171	95.24 288	88.02 117	99.58 92	93.44 164	90.72 313	94.36 387

test_vis1_rt		86.16 383	85.06 383	89.46 403	93.47 392	80.46 407	96.41 261	86.61 454	85.22 376	79.15 431	88.64 433	52.41 446	97.06 384	93.08 173	90.57 314	90.87 437

EI-MVSNet		93.03 205	92.88 189	93.48 302	95.77 284	86.98 302	96.44 256	97.12 233	90.66 230	91.30 257	97.64 140	86.56 145	98.05 297	89.91 243	90.55 315	95.41 326

MVSTER		93.20 196	92.81 192	94.37 247	96.56 225	89.59 218	97.06 196	97.12 233	91.24 201	91.30 257	95.96 247	82.02 243	98.05 297	93.48 163	90.55 315	95.47 321

FIs		94.09 157	93.70 154	95.27 195	95.70 286	92.03 118	98.10 52	98.68 15	93.36 118	90.39 274	96.70 203	87.63 127	97.94 319	92.25 186	90.50 317	95.84 302

FC-MVSNet-test		93.94 166	93.57 158	95.04 206	95.48 297	91.45 144	98.12 51	98.71 12	93.37 116	90.23 277	96.70 203	87.66 124	97.85 328	91.49 208	90.39 318	95.83 303

ACMMP++_ref															90.30 319

LTVRE_ROB	88.41 13	90.99 300	89.92 314	94.19 257	96.18 261	89.55 221	96.31 275	97.09 238	87.88 323	85.67 386	95.91 250	78.79 307	98.57 243	81.50 377	89.98 320	94.44 385
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
tpmvs		89.83 340	89.15 338	91.89 356	94.92 338	80.30 410	93.11 410	95.46 346	86.28 360	88.08 347	92.65 390	80.44 273	98.52 247	81.47 379	89.92 321	96.84 271

ITE_SJBPF				92.43 337	95.34 309	85.37 346		95.92 319	91.47 190	87.75 353	96.39 226	71.00 375	97.96 313	82.36 373	89.86 322	93.97 398

ET-MVSNet_ETH3D		91.49 274	90.11 303	95.63 174	96.40 243	91.57 137	95.34 333	93.48 414	90.60 236	75.58 438	95.49 276	80.08 280	96.79 397	94.25 147	89.76 323	98.52 160

USDC		88.94 350	87.83 355	92.27 344	94.66 351	84.96 355	93.86 389	95.90 321	87.34 341	83.40 408	95.56 272	67.43 405	98.19 276	82.64 372	89.67 324	93.66 401

dmvs_re		90.21 327	89.50 329	92.35 339	95.47 301	85.15 349	95.70 314	94.37 396	90.94 219	88.42 334	93.57 373	74.63 351	95.67 416	82.80 368	89.57 325	96.22 285

ACMH	87.59 16	90.53 317	89.42 331	93.87 281	96.21 253	87.92 279	97.24 179	96.94 258	88.45 307	83.91 406	96.27 232	71.92 368	98.62 237	84.43 349	89.43 326	95.05 352
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tpmrst		91.44 276	91.32 248	91.79 361	95.15 326	79.20 425	93.42 404	95.37 349	88.55 304	93.49 200	93.67 369	82.49 233	98.27 269	90.41 234	89.34 327	97.90 220

test0.0.03 1		89.37 347	88.70 345	91.41 371	92.47 415	85.63 338	95.22 342	92.70 424	91.11 211	86.91 375	93.65 370	79.02 301	93.19 443	78.00 406	89.18 328	95.41 326

viewmsd2359difaftdt		93.46 186	93.23 176	94.17 258	96.12 268	85.42 342	96.43 258	97.08 239	92.91 142	94.21 175	98.00 99	80.82 266	98.74 217	94.41 143	89.05 329	98.34 186

OpenMVS_ROB	81.14 20	84.42 398	82.28 404	90.83 382	90.06 430	84.05 368	95.73 313	94.04 404	73.89 442	80.17 428	91.53 414	59.15 433	97.64 350	66.92 445	89.05 329	90.80 438

GBi-Net		91.35 282	90.27 295	94.59 232	96.51 234	91.18 157	97.50 146	96.93 259	88.82 294	89.35 310	94.51 322	73.87 356	97.29 378	86.12 325	88.82 331	95.31 336

test1		91.35 282	90.27 295	94.59 232	96.51 234	91.18 157	97.50 146	96.93 259	88.82 294	89.35 310	94.51 322	73.87 356	97.29 378	86.12 325	88.82 331	95.31 336

FMVSNet3		91.78 256	90.69 280	95.03 207	96.53 230	92.27 108	97.02 199	96.93 259	89.79 260	89.35 310	94.65 315	77.01 327	97.47 366	86.12 325	88.82 331	95.35 333

tpm cat1		88.36 358	87.21 361	91.81 360	95.13 328	80.55 406	92.58 418	95.70 331	74.97 439	87.45 357	91.96 408	78.01 321	98.17 278	80.39 392	88.74 334	96.72 275

test_0402		86.46 378	84.79 386	91.45 369	95.02 332	85.55 339	96.29 277	94.89 374	80.90 418	82.21 416	93.97 357	68.21 402	97.29 378	62.98 447	88.68 335	91.51 432

FMVSNet2		91.31 285	90.08 304	94.99 209	96.51 234	92.21 110	97.41 160	96.95 257	88.82 294	88.62 330	94.75 309	73.87 356	97.42 371	85.20 341	88.55 336	95.35 333

tt0805		91.09 295	90.07 307	94.16 260	95.61 290	88.31 264	97.56 137	96.51 293	89.56 264	89.17 317	95.64 268	67.08 411	98.38 261	91.07 217	88.44 337	95.80 305

testgi		87.97 361	87.21 361	90.24 394	92.86 406	80.76 401	96.67 241	94.97 369	91.74 179	85.52 387	95.83 254	62.66 429	94.47 430	76.25 415	88.36 338	95.48 319

VortexMVS		92.88 214	92.64 200	93.58 297	96.58 221	87.53 289	96.93 210	97.28 220	92.78 149	89.75 296	94.99 295	82.73 226	97.76 340	94.60 140	88.16 339	95.46 322

ACMH+	87.92 14	90.20 328	89.18 337	93.25 310	96.48 237	86.45 318	96.99 205	96.68 282	88.83 293	84.79 395	96.22 234	70.16 383	98.53 246	84.42 350	88.04 340	94.77 375

tpm		90.25 325	89.74 323	91.76 364	93.92 374	79.73 418	93.98 382	93.54 413	88.28 311	91.99 236	93.25 383	77.51 325	97.44 369	87.30 306	87.94 341	98.12 202

pmmvs4		90.93 304	89.85 316	94.17 258	93.34 397	90.79 174	94.60 358	96.02 317	84.62 386	87.45 357	95.15 290	81.88 248	97.45 368	87.70 293	87.87 342	94.27 392

MonoMVSNet		91.92 251	91.77 231	92.37 338	92.94 404	83.11 378	97.09 195	95.55 342	92.91 142	90.85 267	94.55 319	81.27 258	96.52 401	93.01 178	87.76 343	97.47 248

XXY-MVS		92.16 243	91.23 254	94.95 215	94.75 347	90.94 167	97.47 155	97.43 201	89.14 278	88.90 321	96.43 223	79.71 287	98.24 270	89.56 253	87.68 344	95.67 315

pmmvs5		89.86 339	88.87 344	92.82 327	92.86 406	86.23 323	96.26 278	95.39 347	84.24 390	87.12 365	94.51 322	74.27 354	97.36 375	87.61 300	87.57 345	94.86 363

LF4IMVS		87.94 362	87.25 359	89.98 397	92.38 418	80.05 416	94.38 369	95.25 357	87.59 335	84.34 397	94.74 310	64.31 423	97.66 349	84.83 343	87.45 346	92.23 424

FMVSNet1		89.88 337	88.31 350	94.59 232	95.41 302	91.18 157	97.50 146	96.93 259	86.62 353	87.41 359	94.51 322	65.94 419	97.29 378	83.04 364	87.43 347	95.31 336

dp		88.90 352	88.26 352	90.81 384	94.58 356	76.62 433	92.85 415	94.93 372	85.12 379	90.07 289	93.07 384	75.81 338	98.12 283	80.53 391	87.42 348	97.71 234

WBMVS		90.69 314	89.99 311	92.81 328	96.48 237	85.00 353	95.21 344	96.30 304	89.46 269	89.04 320	94.05 353	72.45 366	97.82 332	89.46 255	87.41 349	95.61 316

OurMVSNet-221017-0		90.51 319	90.19 302	91.44 370	93.41 395	81.25 397	96.98 206	96.28 305	91.68 181	86.55 379	96.30 229	74.20 355	97.98 306	88.96 271	87.40 350	95.09 349

TinyColmap		86.82 373	85.35 380	91.21 374	94.91 340	82.99 380	93.94 385	94.02 405	83.58 400	81.56 419	94.68 312	62.34 430	98.13 280	75.78 416	87.35 351	92.52 419

cl22		91.21 290	90.56 285	93.14 316	96.09 271	86.80 306	94.41 368	96.58 291	87.80 327	88.58 332	93.99 356	80.85 265	97.62 353	89.87 245	86.93 352	94.99 353

miper_ehance_all_eth		91.59 265	91.13 258	92.97 321	95.55 294	86.57 314	94.47 364	96.88 268	87.77 329	88.88 323	94.01 354	86.22 153	97.54 359	89.49 254	86.93 352	94.79 372

miper_enhance_ethall		91.54 271	91.01 262	93.15 315	95.35 308	87.07 301	93.97 383	96.90 265	86.79 351	89.17 317	93.43 381	86.55 146	97.64 350	89.97 242	86.93 352	94.74 376

IterMVS		90.15 330	89.67 324	91.61 366	95.48 297	83.72 371	94.33 372	96.12 315	89.99 252	87.31 363	94.15 348	75.78 341	96.27 406	86.97 313	86.89 355	94.83 365
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		90.31 322	89.81 318	91.82 359	95.52 295	84.20 365	94.30 374	96.15 314	90.61 234	87.39 360	94.27 340	75.80 339	96.44 402	87.34 304	86.88 356	94.82 367

SSC-MVS3.2		89.74 342	89.26 335	91.19 377	95.16 323	80.29 411	94.53 361	97.03 251	91.79 177	88.86 324	94.10 349	69.94 386	97.82 332	85.29 338	86.66 357	95.45 324

our_test_3		88.78 354	87.98 354	91.20 376	92.45 416	82.53 384	93.61 401	95.69 333	85.77 368	84.88 393	93.71 364	79.99 282	96.78 398	79.47 398	86.24 358	94.28 391

EU-MVSNet		88.72 355	88.90 343	88.20 411	93.15 401	74.21 439	96.63 247	94.22 401	85.18 377	87.32 362	95.97 246	76.16 336	94.98 425	85.27 339	86.17 359	95.41 326

Anonymous20231206		87.09 371	86.14 373	89.93 399	91.22 424	80.35 408	96.11 289	95.35 350	83.57 401	84.16 400	93.02 385	73.54 361	95.61 417	72.16 434	86.14 360	93.84 400

IterMVS-LS		92.29 237	91.94 226	93.34 307	96.25 252	86.97 303	96.57 254	97.05 247	90.67 228	89.50 307	94.80 307	86.59 144	97.64 350	89.91 243	86.11 361	95.40 329
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
VPA-MVSNet		93.24 194	92.48 210	95.51 182	95.70 286	92.39 102	97.86 85	98.66 18	92.30 159	92.09 235	95.37 280	80.49 272	98.40 255	93.95 152	85.86 362	95.75 311

nrg030		94.05 159	93.31 173	96.27 128	95.22 320	94.59 32	98.34 26	97.46 189	92.93 141	91.21 263	96.64 208	87.23 140	98.22 272	94.99 123	85.80 363	95.98 298

cl____		90.96 303	90.32 291	92.89 324	95.37 306	86.21 324	94.46 366	96.64 285	87.82 325	88.15 346	94.18 346	82.98 218	97.54 359	87.70 293	85.59 364	94.92 360

DIV-MVS_self_test		90.97 302	90.33 290	92.88 325	95.36 307	86.19 326	94.46 366	96.63 288	87.82 325	88.18 344	94.23 343	82.99 217	97.53 361	87.72 290	85.57 365	94.93 358

v1192		91.07 296	90.23 298	93.58 297	93.70 381	87.82 284	96.73 232	97.07 242	87.77 329	89.58 302	94.32 337	80.90 264	97.97 309	86.52 317	85.48 366	94.95 354

v1240		90.70 312	89.85 316	93.23 311	93.51 389	86.80 306	96.61 248	97.02 253	87.16 345	89.58 302	94.31 338	79.55 291	97.98 306	85.52 335	85.44 367	94.90 361

v1144		91.37 281	90.60 282	93.68 292	93.89 376	88.23 269	96.84 220	97.03 251	88.37 309	89.69 299	94.39 329	82.04 242	97.98 306	87.80 289	85.37 368	94.84 364

Anonymous20240521		86.42 379	85.44 377	89.34 406	90.33 428	79.79 417	96.73 232	95.92 319	83.71 399	83.25 410	91.36 415	63.92 424	96.01 407	78.39 405	85.36 369	92.22 425

FMVSNet5		87.29 368	85.79 375	91.78 362	94.80 345	87.28 292	95.49 327	95.28 354	84.09 392	83.85 407	91.82 409	62.95 427	94.17 432	78.48 403	85.34 370	93.91 399

WR-MVS		92.34 233	91.53 241	94.77 226	95.13 328	90.83 172	96.40 265	97.98 114	91.88 175	89.29 313	95.54 274	82.50 232	97.80 335	89.79 247	85.27 371	95.69 314

v1921920		90.85 306	90.03 309	93.29 309	93.55 386	86.96 305	96.74 231	97.04 249	87.36 340	89.52 306	94.34 334	80.23 278	97.97 309	86.27 320	85.21 372	94.94 356

Anonymous20231211		90.63 315	89.42 331	94.27 256	98.24 95	89.19 242	98.05 58	97.89 122	79.95 425	88.25 342	94.96 297	72.56 365	98.13 280	89.70 249	85.14 373	95.49 318

Patchmtry		88.64 356	87.25 359	92.78 330	94.09 370	86.64 310	89.82 439	95.68 335	80.81 421	87.63 355	92.36 400	80.91 262	97.03 386	78.86 402	85.12 374	94.67 378

V42		91.58 267	90.87 266	93.73 287	94.05 372	88.50 260	97.32 173	96.97 255	88.80 297	89.71 297	94.33 335	82.54 231	98.05 297	89.01 269	85.07 375	94.64 380

SixPastTwentyTwo		89.15 348	88.54 348	90.98 379	93.49 390	80.28 412	96.70 236	94.70 382	90.78 221	84.15 401	95.57 271	71.78 370	97.71 345	84.63 347	85.07 375	94.94 356

v2v482		91.59 265	90.85 269	93.80 284	93.87 377	88.17 272	96.94 209	96.88 268	89.54 265	89.53 305	94.90 301	81.70 251	98.02 302	89.25 263	85.04 377	95.20 344

ppachtmachnet_test		88.35 359	87.29 358	91.53 367	92.45 416	83.57 374	93.75 393	95.97 318	84.28 389	85.32 391	94.18 346	79.00 305	96.93 390	75.71 417	84.99 378	94.10 393

v144192		91.06 297	90.28 294	93.39 305	93.66 384	87.23 296	96.83 221	97.07 242	87.43 338	89.69 299	94.28 339	81.48 253	98.00 304	87.18 309	84.92 379	94.93 358

CP-MVSNet		91.89 254	91.24 253	93.82 283	95.05 331	88.57 256	97.82 94	98.19 69	91.70 180	88.21 343	95.76 261	81.96 244	97.52 363	87.86 287	84.65 380	95.37 332

c3_l		91.38 279	90.89 265	92.88 325	95.58 292	86.30 321	94.68 356	96.84 272	88.17 314	88.83 327	94.23 343	85.65 164	97.47 366	89.36 258	84.63 381	94.89 362

miper_lstm_enhance		90.50 320	90.06 308	91.83 358	95.33 312	83.74 370	93.86 389	96.70 281	87.56 336	87.79 351	93.81 362	83.45 206	96.92 391	87.39 303	84.62 382	94.82 367

reproduce_monomvs		91.30 286	91.10 259	91.92 353	96.82 201	82.48 386	97.01 202	97.49 181	94.64 69	88.35 336	95.27 285	70.53 379	98.10 285	95.20 116	84.60 383	95.19 347

tfpnnormal		89.70 343	88.40 349	93.60 295	95.15 326	90.10 198	97.56 137	98.16 75	87.28 343	86.16 383	94.63 316	77.57 324	98.05 297	74.48 422	84.59 384	92.65 415

EGC-MVSNET		68.77 421	63.01 427	86.07 422	92.49 414	82.24 391	93.96 384	90.96 438	0.71 467	2.62 468	90.89 417	53.66 444	93.46 438	57.25 452	84.55 385	82.51 448

PS-CasMVS		91.55 269	90.84 270	93.69 291	94.96 334	88.28 266	97.84 89	98.24 58	91.46 191	88.04 348	95.80 256	79.67 288	97.48 365	87.02 312	84.54 386	95.31 336

N_pmnet		78.73 411	78.71 412	78.79 429	92.80 408	46.50 468	94.14 379	43.71 470	78.61 431	80.83 421	91.66 413	74.94 349	96.36 404	67.24 444	84.45 387	93.50 403

eth_miper_zixun_eth		91.02 299	90.59 283	92.34 341	95.33 312	84.35 362	94.10 380	96.90 265	88.56 303	88.84 326	94.33 335	84.08 195	97.60 355	88.77 275	84.37 388	95.06 351

WR-MVS_H		92.00 249	91.35 246	93.95 274	95.09 330	89.47 225	98.04 59	98.68 15	91.46 191	88.34 337	94.68 312	85.86 160	97.56 357	85.77 332	84.24 389	94.82 367

v10		91.04 298	90.23 298	93.49 301	94.12 369	88.16 273	97.32 173	97.08 239	88.26 312	88.29 340	94.22 345	82.17 240	97.97 309	86.45 319	84.12 390	94.33 388

UniMVSNet (Re)		93.31 192	92.55 205	95.61 176	95.39 303	93.34 67	97.39 165	98.71 12	93.14 129	90.10 286	94.83 305	87.71 123	98.03 301	91.67 206	83.99 391	95.46 322

UniMVSNet_NR-MVSNet		93.37 190	92.67 199	95.47 188	95.34 309	92.83 85	97.17 189	98.58 24	92.98 139	90.13 282	95.80 256	88.37 112	97.85 328	91.71 203	83.93 392	95.73 313

DU-MVS		92.90 212	92.04 221	95.49 185	94.95 335	92.83 85	97.16 190	98.24 58	93.02 133	90.13 282	95.71 263	83.47 204	97.85 328	91.71 203	83.93 392	95.78 307

v8		91.29 288	90.53 286	93.57 299	94.15 368	88.12 274	97.34 170	97.06 246	88.99 285	88.32 338	94.26 342	83.08 214	98.01 303	87.62 299	83.92 394	94.57 381

baseline1		92.82 218	91.90 228	95.55 180	97.20 168	90.77 175	97.19 187	94.58 386	92.20 164	92.36 224	96.34 228	84.16 194	98.21 273	89.20 266	83.90 395	97.68 236

v7n		90.76 308	89.86 315	93.45 304	93.54 387	87.60 288	97.70 116	97.37 209	88.85 291	87.65 354	94.08 352	81.08 259	98.10 285	84.68 346	83.79 396	94.66 379

VPNet		92.23 241	91.31 249	94.99 209	95.56 293	90.96 166	97.22 185	97.86 130	92.96 140	90.96 265	96.62 215	75.06 345	98.20 274	91.90 196	83.65 397	95.80 305

NR-MVSNet		92.34 233	91.27 252	95.53 181	94.95 335	93.05 77	97.39 165	98.07 93	92.65 152	84.46 396	95.71 263	85.00 178	97.77 339	89.71 248	83.52 398	95.78 307

v148		90.99 300	90.38 289	92.81 328	93.83 378	85.80 334	96.78 229	96.68 282	89.45 270	88.75 329	93.93 358	82.96 220	97.82 332	87.83 288	83.25 399	94.80 370

Baseline_NR-MVSNet		91.20 291	90.62 281	92.95 322	93.83 378	88.03 276	97.01 202	95.12 363	88.42 308	89.70 298	95.13 292	83.47 204	97.44 369	89.66 251	83.24 400	93.37 406

TranMVSNet+NR-MVSNet		92.50 224	91.63 237	95.14 200	94.76 346	92.07 115	97.53 143	98.11 84	92.90 144	89.56 304	96.12 240	83.16 211	97.60 355	89.30 260	83.20 401	95.75 311

PEN-MVS		91.20 291	90.44 287	93.48 302	94.49 358	87.91 281	97.76 102	98.18 71	91.29 197	87.78 352	95.74 262	80.35 275	97.33 376	85.46 336	82.96 402	95.19 347

new_pmnet		82.89 403	81.12 408	88.18 412	89.63 433	80.18 414	91.77 424	92.57 425	76.79 437	75.56 439	88.23 437	61.22 432	94.48 429	71.43 436	82.92 403	89.87 441

FPMVS		71.27 416	69.85 418	75.50 436	74.64 461	59.03 461	91.30 426	91.50 434	58.80 453	57.92 457	88.28 436	29.98 460	85.53 456	53.43 454	82.84 404	81.95 449

MIMVSNet1		84.93 394	83.05 396	90.56 389	89.56 434	84.84 358	95.40 330	95.35 350	83.91 393	80.38 425	92.21 405	57.23 437	93.34 440	70.69 440	82.75 405	93.50 403

dmvs_testset		81.38 407	82.60 401	77.73 430	91.74 422	51.49 465	93.03 412	84.21 458	89.07 280	78.28 434	91.25 416	76.97 328	88.53 453	56.57 453	82.24 406	93.16 407

pm-mvs1		90.72 311	89.65 326	93.96 273	94.29 367	89.63 215	97.79 100	96.82 273	89.07 280	86.12 384	95.48 278	78.61 309	97.78 337	86.97 313	81.67 407	94.46 383

DTE-MVSNet		90.56 316	89.75 322	93.01 319	93.95 373	87.25 294	97.64 126	97.65 156	90.74 223	87.12 365	95.68 266	79.97 283	97.00 389	83.33 361	81.66 408	94.78 374

IB-MVS	87.33 17	89.91 334	88.28 351	94.79 225	95.26 319	87.70 286	95.12 347	93.95 407	89.35 273	87.03 369	92.49 394	70.74 378	99.19 148	89.18 267	81.37 409	97.49 246
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
test20.03		86.14 384	85.40 379	88.35 409	90.12 429	80.06 415	95.90 303	95.20 359	88.59 300	81.29 420	93.62 371	71.43 372	92.65 444	71.26 438	81.17 410	92.34 421

K. test v3		87.64 366	86.75 368	90.32 393	93.02 403	79.48 423	96.61 248	92.08 430	90.66 230	80.25 427	94.09 351	67.21 407	96.65 400	85.96 330	80.83 411	94.83 365

test_fmvs3		83.21 401	83.02 397	83.78 424	86.77 448	68.34 450	96.76 230	94.91 373	86.49 355	84.14 402	89.48 429	36.04 456	91.73 446	91.86 199	80.77 412	91.26 436

APD_test1		79.31 410	77.70 413	84.14 423	89.11 438	69.07 449	92.36 422	91.50 434	69.07 448	73.87 441	92.63 392	39.93 454	94.32 431	70.54 441	80.25 413	89.02 443

MDA-MVSNet_test_wron		85.87 388	84.23 391	90.80 386	92.38 418	82.57 383	93.17 407	95.15 361	82.15 410	67.65 448	92.33 403	78.20 314	95.51 420	77.33 408	79.74 414	94.31 390

h-mvs33		94.15 152	93.52 163	96.04 142	97.81 133	90.22 197	97.62 130	97.58 169	95.19 34	96.74 83	97.45 153	83.67 201	99.61 84	95.85 96	79.73 415	98.29 188

YYNet1		85.87 388	84.23 391	90.78 387	92.38 418	82.46 388	93.17 407	95.14 362	82.12 411	67.69 446	92.36 400	78.16 317	95.50 421	77.31 409	79.73 415	94.39 386

pmmvs6		87.81 364	86.19 372	92.69 333	91.32 423	86.30 321	97.34 170	96.41 299	80.59 424	84.05 405	94.37 331	67.37 406	97.67 347	84.75 345	79.51 417	94.09 395

AUN-MVS		91.76 257	90.75 275	94.81 221	97.00 186	88.57 256	96.65 242	96.49 294	89.63 262	92.15 231	96.12 240	78.66 308	98.50 248	90.83 221	79.18 418	97.36 252

hse-mvs2		93.45 188	92.99 182	94.81 221	97.02 184	88.59 255	96.69 238	96.47 295	95.19 34	96.74 83	96.16 238	83.67 201	98.48 251	95.85 96	79.13 419	97.35 254

test_f		80.57 408	79.62 410	83.41 425	83.38 454	67.80 452	93.57 402	93.72 411	80.80 422	77.91 435	87.63 441	33.40 457	92.08 445	87.14 311	79.04 420	90.34 440

Gipuma		67.86 422	65.41 424	75.18 437	92.66 411	73.45 441	66.50 458	94.52 389	53.33 457	57.80 458	66.07 458	30.81 458	89.20 450	48.15 456	78.88 421	62.90 458
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
sc_t1		86.48 377	84.10 393	93.63 293	93.45 393	85.76 336	96.79 225	94.71 381	73.06 444	86.45 380	94.35 332	55.13 442	97.95 317	84.38 351	78.55 422	97.18 261

tt0320		85.39 392	83.12 395	92.19 348	93.44 394	85.79 335	96.19 285	94.87 378	71.19 446	82.92 414	91.76 412	58.43 435	96.81 396	81.03 388	78.26 423	93.98 397

MDA-MVSNet-bldmvs		85.00 393	82.95 398	91.17 378	93.13 402	83.33 375	94.56 360	95.00 367	84.57 387	65.13 452	92.65 390	70.45 380	95.85 411	73.57 429	77.49 424	94.33 388

Patchmatch-RL test		87.38 367	86.24 371	90.81 384	88.74 441	78.40 429	88.12 449	93.17 417	87.11 346	82.17 417	89.29 430	81.95 245	95.60 418	88.64 278	77.02 425	98.41 175

lessismore_v0				90.45 390	91.96 421	79.09 427		87.19 451		80.32 426	94.39 329	66.31 415	97.55 358	84.00 356	76.84 426	94.70 377

mvsany_test3		83.59 399	82.44 402	87.03 418	83.80 451	73.82 440	93.70 395	90.92 439	86.42 356	82.51 415	90.26 422	46.76 451	95.71 414	90.82 222	76.76 427	91.57 431

pmmvs-eth3d		86.22 382	84.45 389	91.53 367	88.34 443	87.25 294	94.47 364	95.01 366	83.47 402	79.51 430	89.61 428	69.75 389	95.71 414	83.13 363	76.73 428	91.64 429

PM-MVS		83.48 400	81.86 406	88.31 410	87.83 445	77.59 431	93.43 403	91.75 432	86.91 348	80.63 423	89.91 426	44.42 452	95.84 412	85.17 342	76.73 428	91.50 433

mvs5depth		86.53 375	85.08 382	90.87 381	88.74 441	82.52 385	91.91 423	94.23 400	86.35 358	87.11 367	93.70 365	66.52 412	97.76 340	81.37 383	75.80 430	92.31 423

ttmdpeth		85.91 387	84.76 387	89.36 405	89.14 436	80.25 413	95.66 318	93.16 418	83.77 397	83.39 409	95.26 286	66.24 416	95.26 424	80.65 389	75.57 431	92.57 416

ambc				86.56 420	83.60 453	70.00 447	85.69 451	94.97 369		80.60 424	88.45 434	37.42 455	96.84 395	82.69 371	75.44 432	92.86 411

tt0320-xc		84.83 395	82.33 403	92.31 342	93.66 384	86.20 325	96.17 287	94.06 402	71.26 445	82.04 418	92.22 404	55.07 443	96.72 399	81.49 378	75.04 433	94.02 396

TDRefinement		86.53 375	84.76 387	91.85 357	82.23 456	84.25 363	96.38 267	95.35 350	84.97 382	84.09 403	94.94 298	65.76 420	98.34 266	84.60 348	74.52 434	92.97 409

TransMVSNet (Re)		88.94 350	87.56 356	93.08 318	94.35 363	88.45 262	97.73 108	95.23 358	87.47 337	84.26 399	95.29 282	79.86 285	97.33 376	79.44 400	74.44 435	93.45 405

PMVS	53.92 22	58.58 426	55.40 429	68.12 441	51.00 469	48.64 466	78.86 455	87.10 452	46.77 458	35.84 464	74.28 454	8.76 468	86.34 455	42.07 458	73.91 436	69.38 455
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepMVS_CX				74.68 438	90.84 427	64.34 456		81.61 461	65.34 451	67.47 449	88.01 440	48.60 450	80.13 460	62.33 448	73.68 437	79.58 450

KD-MVS_self_test		85.95 386	84.95 384	88.96 408	89.55 435	79.11 426	95.13 346	96.42 298	85.91 366	84.07 404	90.48 420	70.03 385	94.82 426	80.04 393	72.94 438	92.94 410

test_vis3_rt		72.73 414	70.55 417	79.27 428	80.02 457	68.13 451	93.92 387	74.30 465	76.90 436	58.99 456	73.58 456	20.29 465	95.37 422	84.16 352	72.80 439	74.31 453

CL-MVSNet_self_test		86.31 381	85.15 381	89.80 400	88.83 439	81.74 395	93.93 386	96.22 309	86.67 352	85.03 392	90.80 418	78.09 318	94.50 428	74.92 421	71.86 440	93.15 408

UnsupCasMVSNet_eth		85.99 385	84.45 389	90.62 388	89.97 431	82.40 389	93.62 400	97.37 209	89.86 255	78.59 433	92.37 397	65.25 422	95.35 423	82.27 374	70.75 441	94.10 393

new-patchmatchnet		83.18 402	81.87 405	87.11 417	86.88 447	75.99 436	93.70 395	95.18 360	85.02 381	77.30 436	88.40 435	65.99 418	93.88 437	74.19 426	70.18 442	91.47 434

pmmvs3		79.97 409	77.50 414	87.39 416	82.80 455	79.38 424	92.70 417	90.75 440	70.69 447	78.66 432	87.47 443	51.34 447	93.40 439	73.39 430	69.65 443	89.38 442

mmtdpeth		89.70 343	88.96 341	91.90 355	95.84 283	84.42 361	97.46 157	95.53 345	90.27 245	94.46 170	90.50 419	69.74 390	98.95 187	97.39 48	69.48 444	92.34 421

testf1		69.31 419	66.76 422	76.94 433	78.61 458	61.93 457	88.27 447	86.11 455	55.62 454	59.69 454	85.31 446	20.19 466	89.32 448	57.62 450	69.44 445	79.58 450

APD_test2		69.31 419	66.76 422	76.94 433	78.61 458	61.93 457	88.27 447	86.11 455	55.62 454	59.69 454	85.31 446	20.19 466	89.32 448	57.62 450	69.44 445	79.58 450

LCM-MVSNet		72.55 415	69.39 419	82.03 426	70.81 466	65.42 455	90.12 437	94.36 398	55.02 456	65.88 450	81.72 449	24.16 464	89.96 447	74.32 425	68.10 447	90.71 439

WB-MVS		76.77 412	76.63 415	77.18 431	85.32 449	56.82 463	94.53 361	89.39 444	82.66 408	71.35 444	89.18 431	75.03 346	88.88 451	35.42 460	66.79 448	85.84 445

UnsupCasMVSNet_bld		82.13 406	79.46 411	90.14 395	88.00 444	82.47 387	90.89 432	96.62 290	78.94 430	75.61 437	84.40 448	56.63 439	96.31 405	77.30 410	66.77 449	91.63 430

MVStest1		82.38 405	80.04 409	89.37 404	87.63 446	82.83 381	95.03 348	93.37 416	73.90 441	73.50 443	94.35 332	62.89 428	93.25 442	73.80 427	65.92 450	92.04 428

SSC-MVS		76.05 413	75.83 416	76.72 435	84.77 450	56.22 464	94.32 373	88.96 446	81.82 414	70.52 445	88.91 432	74.79 350	88.71 452	33.69 461	64.71 451	85.23 446

test_method		66.11 423	64.89 425	69.79 440	72.62 464	35.23 472	65.19 459	92.83 423	20.35 462	65.20 451	88.08 439	43.14 453	82.70 457	73.12 431	63.46 452	91.45 435

KD-MVS_2432*1600		84.81 396	82.64 399	91.31 372	91.07 425	85.34 347	91.22 427	95.75 329	85.56 371	83.09 411	90.21 423	67.21 407	95.89 409	77.18 411	62.48 453	92.69 413

miper_refine_blended		84.81 396	82.64 399	91.31 372	91.07 425	85.34 347	91.22 427	95.75 329	85.56 371	83.09 411	90.21 423	67.21 407	95.89 409	77.18 411	62.48 453	92.69 413

PVSNet_0	82.17 19	85.46 391	83.64 394	90.92 380	95.27 316	79.49 422	90.55 433	95.60 338	83.76 398	83.00 413	89.95 425	71.09 374	97.97 309	82.75 370	60.79 455	95.31 336

dongtai		69.99 418	69.33 420	71.98 439	88.78 440	61.64 459	89.86 438	59.93 469	75.67 438	74.96 440	85.45 445	50.19 448	81.66 458	43.86 457	55.27 456	72.63 454

PMMVS2		70.19 417	66.92 421	80.01 427	76.35 460	65.67 454	86.22 450	87.58 450	64.83 452	62.38 453	80.29 452	26.78 462	88.49 454	63.79 446	54.07 457	85.88 444

kuosan		65.27 424	64.66 426	67.11 442	83.80 451	61.32 460	88.53 446	60.77 468	68.22 449	67.67 447	80.52 451	49.12 449	70.76 464	29.67 463	53.64 458	69.26 456

MVE	50.73 23	53.25 428	48.81 433	66.58 443	65.34 467	57.50 462	72.49 457	70.94 466	40.15 461	39.28 463	63.51 459	6.89 470	73.48 463	38.29 459	42.38 459	68.76 457
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		53.28 427	52.56 431	55.43 444	74.43 462	47.13 467	83.63 454	76.30 462	42.23 459	42.59 461	62.22 460	28.57 461	74.40 461	31.53 462	31.51 460	44.78 459

ANet_high		63.94 425	59.58 428	77.02 432	61.24 468	66.06 453	85.66 452	87.93 449	78.53 432	42.94 460	71.04 457	25.42 463	80.71 459	52.60 455	30.83 461	84.28 447

EMVS		52.08 429	51.31 432	54.39 445	72.62 464	45.39 469	83.84 453	75.51 464	41.13 460	40.77 462	59.65 461	30.08 459	73.60 462	28.31 464	29.90 462	44.18 460

tmp_tt		51.94 430	53.82 430	46.29 446	33.73 470	45.30 470	78.32 456	67.24 467	18.02 463	50.93 459	87.05 444	52.99 445	53.11 465	70.76 439	25.29 463	40.46 461

wuyk23d		25.11 431	24.57 435	26.74 447	73.98 463	39.89 471	57.88 460	9.80 471	12.27 464	10.39 465	6.97 467	7.03 469	36.44 466	25.43 465	17.39 464	3.89 464

testmvs		13.36 433	16.33 436	4.48 449	5.04 471	2.26 474	93.18 406	3.28 472	2.70 465	8.24 466	21.66 463	2.29 472	2.19 467	7.58 466	2.96 465	9.00 463

test123		13.04 434	15.66 437	5.18 448	4.51 472	3.45 473	92.50 420	1.81 473	2.50 466	7.58 467	20.15 464	3.67 471	2.18 468	7.13 467	1.07 466	9.90 462

mmdepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

cdsmvs_eth3d_5k		23.24 432	30.99 434	0.00 450	0.00 473	0.00 475	0.00 461	97.63 160	0.00 468	0.00 469	96.88 194	84.38 189	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		7.39 436	9.85 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	88.65 105	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		8.06 435	10.74 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	96.69 205	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						79.53 420								75.56 419

FOURS1					99.55 1	93.34 67	99.29 1	98.35 38	94.98 44	98.49 34

test_one_0601					99.32 24	95.20 20		98.25 56	95.13 38	98.48 35	98.87 29	95.16 7

eth-test2					0.00 473

eth-test					0.00 473

test_241102_ONE					99.42 7	95.30 17		98.27 50	95.09 41	99.19 11	98.81 35	95.54 5	99.65 73

save fliter					98.91 54	94.28 38	97.02 199	98.02 108	95.35 29

test0726					99.45 3	95.36 13	98.31 28	98.29 45	94.92 48	98.99 16	98.92 21	95.08 8

GSMVS																98.45 170

test_part2					99.28 27	95.74 8				98.10 42

sam_mvs1												82.76 225				98.45 170

sam_mvs												81.94 246

MTGPA								98.08 88

test_post1							92.81 416				16.58 466	80.53 271	97.68 346	86.20 322

test_post											17.58 465	81.76 249	98.08 290

patchmatchnet-post											90.45 421	82.65 230	98.10 285

MTMP							97.86 85	82.03 460

gm-plane-assit					93.22 399	78.89 428			84.82 384		93.52 374		98.64 234	87.72 290

TEST9					98.70 61	94.19 42	96.41 261	98.02 108	88.17 314	96.03 120	97.56 149	92.74 33	99.59 89

test_8					98.67 63	94.06 49	96.37 268	98.01 111	88.58 301	95.98 124	97.55 151	92.73 34	99.58 92

agg_prior					98.67 63	93.79 55		98.00 112		95.68 137			99.57 99

test_prior4						93.66 58	96.42 260

test_prior				97.23 65	98.67 63	92.99 79		98.00 112					99.41 126			99.29 71

旧先验2							95.94 299		81.66 415	97.34 64			98.82 203	92.26 184

新几何2							95.79 309

无先验							95.79 309	97.87 126	83.87 396				99.65 73	87.68 296		98.89 126

原ACMM2							95.67 315

testdata2													99.67 71	85.96 330

segment_acmp												92.89 30

testdata1							95.26 341		93.10 131

plane_prior7					96.21 253	89.98 204

plane_prior6					96.10 270	90.00 200						81.32 256

plane_prior4											96.64 208

plane_prior3						90.00 200			94.46 76	91.34 254

plane_prior2							97.74 106		94.85 51

plane_prior1					96.14 266

n2								0.00 474

nn								0.00 474

door-mid								91.06 437

test11								97.88 124

door								91.13 436

HQP5-MVS						89.33 233

HQP-NCC					95.86 278		96.65 242		93.55 105	90.14 278

ACMP_Plane					95.86 278		96.65 242		93.55 105	90.14 278

BP-MVS														92.13 192

HQP4-MVS										90.14 278			98.50 248			95.78 307

HQP2-MVS												80.95 260

NP-MVS					95.99 276	89.81 212					95.87 251

MDTV_nov1_ep13_2view						70.35 446	93.10 411		83.88 395	93.55 195		82.47 234		86.25 321		98.38 178

Test By Simon												88.73 104

High-resolution multi-view benchmark