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.

test_0728_THIRD									97.32 33	99.45 18	99.46 16	97.88 1	99.94 5	98.47 28	99.86 1	99.85 5

PC_three_1452									95.08 148	99.60 12	99.16 67	97.86 2	98.47 265	97.52 88	99.72 47	99.74 31

DVP-MVS++		99.08 2	98.89 3	99.64 3	99.17 91	99.23 7	99.69 1	98.88 54	97.32 33	99.53 16	99.47 13	97.81 3	99.94 5	98.47 28	99.72 47	99.74 31

OPU-MVS				99.37 20	99.24 84	99.05 14	99.02 74				99.16 67	97.81 3	99.37 160	97.24 97	99.73 44	99.70 47

SteuartSystems-ACMMP		98.90 6	98.75 7	99.36 21	99.22 86	98.43 33	99.10 58	98.87 61	97.38 30	99.35 24	99.40 21	97.78 5	99.87 48	97.77 67	99.85 5	99.78 16
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.66 26	99.25 2		98.86 67	97.55 20	99.20 30	99.47 13	97.57 6

SED-MVS		99.09 1	98.91 2	99.63 4	99.71 19	99.24 5	99.02 74	98.87 61	97.65 14	99.73 4	99.48 11	97.53 7	99.94 5	98.43 32	99.81 12	99.70 47

test_241102_ONE					99.71 19	99.24 5		98.87 61	97.62 16	99.73 4	99.39 22	97.53 7	99.74 101

DVP-MVS		99.03 3	98.83 6	99.63 4	99.72 12	99.25 2	98.97 84	98.58 140	97.62 16	99.45 18	99.46 16	97.42 9	99.94 5	98.47 28	99.81 12	99.69 50
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					99.72 12	99.25 2	99.06 63	98.88 54	97.62 16	99.56 13	99.50 8	97.42 9

test_241102_TWO								98.87 61	97.65 14	99.53 16	99.48 11	97.34 11	99.94 5	98.43 32	99.80 19	99.83 8

DPE-MVS		98.92 5	98.67 9	99.65 2	99.58 32	99.20 9	98.42 192	98.91 48	97.58 19	99.54 15	99.46 16	97.10 12	99.94 5	97.64 77	99.84 10	99.83 8
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		98.78 8	98.56 13	99.45 15	99.32 60	98.87 19	98.47 184	98.81 78	97.72 10	98.76 58	99.16 67	97.05 13	99.78 91	98.06 47	99.66 56	99.69 50

segment_acmp												96.85 14

patch_mono-2		98.36 43	98.87 4	96.82 202	99.53 36	90.68 304	98.64 159	99.29 9	97.88 8	99.19 32	99.52 4	96.80 15	99.97 1	99.11 6	99.86 1	99.82 11

MCST-MVS		98.65 12	98.37 23	99.48 13	99.60 31	98.87 19	98.41 193	98.68 115	97.04 53	98.52 75	98.80 118	96.78 16	99.83 59	97.93 54	99.61 67	99.74 31

APDe-MVS		99.02 4	98.84 5	99.55 9	99.57 33	98.96 16	99.39 12	98.93 42	97.38 30	99.41 20	99.54 2	96.66 17	99.84 57	98.86 11	99.85 5	99.87 2

NCCC		98.61 15	98.35 26	99.38 18	99.28 74	98.61 26	98.45 185	98.76 96	97.82 9	98.45 79	98.93 104	96.65 18	99.83 59	97.38 94	99.41 97	99.71 43

SD-MVS		98.64 13	98.68 8	98.53 79	99.33 57	98.36 40	98.90 97	98.85 70	97.28 36	99.72 6	99.39 22	96.63 19	97.60 333	98.17 42	99.85 5	99.64 65
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
PHI-MVS		98.34 46	98.06 50	99.18 41	99.15 97	98.12 54	99.04 68	99.09 24	93.32 227	98.83 54	99.10 76	96.54 20	99.83 59	97.70 74	99.76 34	99.59 73

SMA-MVS		98.58 20	98.25 38	99.56 8	99.51 39	99.04 15	98.95 90	98.80 85	93.67 213	99.37 23	99.52 4	96.52 21	99.89 39	98.06 47	99.81 12	99.76 28
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
MSLP-MVS++		98.56 25	98.57 12	98.55 75	99.26 77	96.80 99	98.71 145	99.05 29	97.28 36	98.84 52	99.28 44	96.47 22	99.40 158	98.52 26	99.70 50	99.47 93

TSAR-MVS + MP.		98.78 8	98.62 10	99.24 35	99.69 24	98.28 45	99.14 49	98.66 123	96.84 61	99.56 13	99.31 41	96.34 23	99.70 109	98.32 38	99.73 44	99.73 36
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		98.59 18	98.32 34	99.41 17	99.54 35	98.71 22	99.04 68	98.81 78	95.12 143	99.32 25	99.39 22	96.22 24	99.84 57	97.72 70	99.73 44	99.67 59

TSAR-MVS + GP.		98.38 41	98.24 40	98.81 62	99.22 86	97.25 85	98.11 228	98.29 202	97.19 44	98.99 43	99.02 88	96.22 24	99.67 116	98.52 26	98.56 139	99.51 83

TEST9					99.31 62	98.50 29	97.92 243	98.73 103	92.63 252	97.74 120	98.68 132	96.20 26	99.80 78

train_agg		97.97 54	97.52 69	99.33 26	99.31 62	98.50 29	97.92 243	98.73 103	92.98 241	97.74 120	98.68 132	96.20 26	99.80 78	96.59 127	99.57 74	99.68 55

test_8					99.29 70	98.44 31	97.89 249	98.72 105	92.98 241	97.70 124	98.66 135	96.20 26	99.80 78

DeepPCF-MVS	96.37 2	97.93 58	98.48 19	96.30 252	99.00 109	89.54 323	97.43 282	98.87 61	98.16 5	99.26 28	99.38 27	96.12 29	99.64 121	98.30 39	99.77 28	99.72 39

HFP-MVS		98.63 14	98.40 20	99.32 27	99.72 12	98.29 44	99.23 31	98.96 37	96.10 94	98.94 44	99.17 64	96.06 30	99.92 26	97.62 78	99.78 26	99.75 29

9.14			98.06 50		99.47 47		98.71 145	98.82 73	94.36 176	99.16 35	99.29 43	96.05 31	99.81 71	97.00 104	99.71 49

CP-MVS		98.57 23	98.36 24	99.19 39	99.66 26	97.86 61	99.34 18	98.87 61	95.96 99	98.60 71	99.13 72	96.05 31	99.94 5	97.77 67	99.86 1	99.77 22

MSP-MVS		98.74 10	98.55 14	99.29 28	99.75 3	98.23 46	99.26 27	98.88 54	97.52 21	99.41 20	98.78 120	96.00 33	99.79 88	97.79 66	99.59 70	99.85 5
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
MVS_111021_HR		98.47 33	98.34 29	98.88 61	99.22 86	97.32 78	97.91 245	99.58 3	97.20 43	98.33 87	99.00 93	95.99 34	99.64 121	98.05 49	99.76 34	99.69 50

test_prior2							97.80 257		96.12 93	97.89 114	98.69 131	95.96 35		96.89 113	99.60 68

CDPH-MVS		97.94 57	97.49 70	99.28 31	99.47 47	98.44 31	97.91 245	98.67 120	92.57 256	98.77 57	98.85 112	95.93 36	99.72 103	95.56 163	99.69 52	99.68 55

test_fmvsm_n_1920		98.87 7	99.01 1	98.45 87	99.42 54	96.43 120	98.96 89	99.36 7	98.63 2	99.86 2	99.51 6	95.91 37	99.97 1	99.72 2	99.75 38	98.94 164

region2R		98.61 15	98.38 22	99.29 28	99.74 7	98.16 51	99.23 31	98.93 42	96.15 91	98.94 44	99.17 64	95.91 37	99.94 5	97.55 85	99.79 23	99.78 16

XVS		98.70 11	98.49 17	99.34 23	99.70 22	98.35 41	99.29 22	98.88 54	97.40 27	98.46 76	99.20 57	95.90 39	99.89 39	97.85 61	99.74 42	99.78 16

X-MVStestdata		94.06 272	92.30 293	99.34 23	99.70 22	98.35 41	99.29 22	98.88 54	97.40 27	98.46 76	43.50 381	95.90 39	99.89 39	97.85 61	99.74 42	99.78 16

dcpmvs_2		98.08 52	98.59 11	96.56 226	99.57 33	90.34 311	99.15 47	98.38 184	96.82 63	99.29 26	99.49 10	95.78 41	99.57 132	98.94 9	99.86 1	99.77 22

CS-MVS		98.44 36	98.49 17	98.31 99	99.08 102	96.73 103	99.67 3	98.47 166	97.17 45	98.94 44	99.10 76	95.73 42	99.13 184	98.71 14	99.49 88	99.09 147

ZD-MVS					99.46 49	98.70 23		98.79 90	93.21 232	98.67 63	98.97 95	95.70 43	99.83 59	96.07 142	99.58 73

HPM-MVS++		98.58 20	98.25 38	99.55 9	99.50 41	99.08 11	98.72 144	98.66 123	97.51 22	98.15 90	98.83 115	95.70 43	99.92 26	97.53 87	99.67 54	99.66 62

ACMMPR		98.59 18	98.36 24	99.29 28	99.74 7	98.15 52	99.23 31	98.95 38	96.10 94	98.93 48	99.19 62	95.70 43	99.94 5	97.62 78	99.79 23	99.78 16

旧先验1					99.29 70	97.48 74		98.70 111			99.09 82	95.56 46			99.47 91	99.61 69

PGM-MVS		98.49 30	98.23 41	99.27 33	99.72 12	98.08 55	98.99 81	99.49 5	95.43 125	99.03 38	99.32 39	95.56 46	99.94 5	96.80 123	99.77 28	99.78 16

APD-MVS		98.35 45	98.00 53	99.42 16	99.51 39	98.72 21	98.80 125	98.82 73	94.52 171	99.23 29	99.25 51	95.54 48	99.80 78	96.52 131	99.77 28	99.74 31
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ZNCC-MVS		98.49 30	98.20 44	99.35 22	99.73 11	98.39 34	99.19 42	98.86 67	95.77 109	98.31 89	99.10 76	95.46 49	99.93 21	97.57 84	99.81 12	99.74 31

mPP-MVS		98.51 29	98.26 37	99.25 34	99.75 3	98.04 56	99.28 24	98.81 78	96.24 87	98.35 86	99.23 52	95.46 49	99.94 5	97.42 92	99.81 12	99.77 22

EI-MVSNet-Vis-set		98.47 33	98.39 21	98.69 66	99.46 49	96.49 117	98.30 204	98.69 112	97.21 42	98.84 52	99.36 32	95.41 51	99.78 91	98.62 16	99.65 59	99.80 13

ETV-MVS		97.96 55	97.81 56	98.40 94	98.42 158	97.27 80	98.73 140	98.55 146	96.84 61	98.38 83	97.44 251	95.39 52	99.35 161	97.62 78	98.89 121	98.58 193

SR-MVS		98.57 23	98.35 26	99.24 35	99.53 36	98.18 49	99.09 59	98.82 73	96.58 73	99.10 37	99.32 39	95.39 52	99.82 66	97.70 74	99.63 64	99.72 39

ACMMP_NAP		98.61 15	98.30 35	99.55 9	99.62 30	98.95 17	98.82 117	98.81 78	95.80 108	99.16 35	99.47 13	95.37 54	99.92 26	97.89 58	99.75 38	99.79 14

CSCG		97.85 61	97.74 59	98.20 108	99.67 25	95.16 181	99.22 35	99.32 8	93.04 239	97.02 150	98.92 106	95.36 55	99.91 34	97.43 91	99.64 63	99.52 80

SR-MVS-dyc-post		98.54 27	98.35 26	99.13 46	99.49 45	97.86 61	99.11 55	98.80 85	96.49 76	99.17 33	99.35 34	95.34 56	99.82 66	97.72 70	99.65 59	99.71 43

DP-MVS Recon		97.86 60	97.46 73	99.06 51	99.53 36	98.35 41	98.33 197	98.89 51	92.62 253	98.05 96	98.94 103	95.34 56	99.65 119	96.04 146	99.42 96	99.19 133

APD-MVS_3200maxsize		98.53 28	98.33 33	99.15 45	99.50 41	97.92 60	99.15 47	98.81 78	96.24 87	99.20 30	99.37 28	95.30 58	99.80 78	97.73 69	99.67 54	99.72 39

RE-MVS-def			98.34 29		99.49 45	97.86 61	99.11 55	98.80 85	96.49 76	99.17 33	99.35 34	95.29 59		97.72 70	99.65 59	99.71 43

GST-MVS		98.43 38	98.12 47	99.34 23	99.72 12	98.38 35	99.09 59	98.82 73	95.71 113	98.73 61	99.06 86	95.27 60	99.93 21	97.07 103	99.63 64	99.72 39

DeepC-MVS_fast	96.70 1	98.55 26	98.34 29	99.18 41	99.25 78	98.04 56	98.50 181	98.78 92	97.72 10	98.92 49	99.28 44	95.27 60	99.82 66	97.55 85	99.77 28	99.69 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		98.31 49	97.92 55	99.49 12	99.72 12	98.88 18	98.43 190	98.78 92	94.10 182	97.69 125	99.42 20	95.25 62	99.92 26	98.09 46	99.80 19	99.67 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
CS-MVS-test		98.49 30	98.50 16	98.46 86	99.20 89	97.05 90	99.64 4	98.50 160	97.45 26	98.88 50	99.14 71	95.25 62	99.15 181	98.83 12	99.56 80	99.20 129

EI-MVSNet-UG-set		98.41 39	98.34 29	98.61 71	99.45 52	96.32 128	98.28 207	98.68 115	97.17 45	98.74 59	99.37 28	95.25 62	99.79 88	98.57 17	99.54 83	99.73 36

原ACMM1				98.65 69	99.32 60	96.62 106		98.67 120	93.27 231	97.81 115	98.97 95	95.18 65	99.83 59	93.84 217	99.46 94	99.50 85

HPM-MVS_fast		98.38 41	98.13 46	99.12 48	99.75 3	97.86 61	99.44 11	98.82 73	94.46 174	98.94 44	99.20 57	95.16 66	99.74 101	97.58 81	99.85 5	99.77 22

test12				99.18 41	99.16 95	98.19 48		98.53 150		98.07 95		95.13 67	99.72 103		99.56 80	99.63 67

HPM-MVS		98.36 43	98.10 49	99.13 46	99.74 7	97.82 65	99.53 8	98.80 85	94.63 166	98.61 70	98.97 95	95.13 67	99.77 96	97.65 76	99.83 11	99.79 14
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DPM-MVS		97.55 80	96.99 94	99.23 37	99.04 104	98.55 27	97.17 306	98.35 188	94.85 158	97.93 111	98.58 143	95.07 69	99.71 108	92.60 251	99.34 103	99.43 102

MVS_111021_LR		98.34 46	98.23 41	98.67 68	99.27 75	96.90 96	97.95 241	99.58 3	97.14 48	98.44 81	99.01 92	95.03 70	99.62 127	97.91 56	99.75 38	99.50 85

EIA-MVS		97.75 64	97.58 64	98.27 101	98.38 161	96.44 119	99.01 76	98.60 133	95.88 105	97.26 139	97.53 245	94.97 71	99.33 163	97.38 94	99.20 108	99.05 153

DELS-MVS		98.40 40	98.20 44	98.99 53	99.00 109	97.66 67	97.75 261	98.89 51	97.71 12	98.33 87	98.97 95	94.97 71	99.88 47	98.42 34	99.76 34	99.42 104
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
PLC	95.07 4	97.20 100	96.78 104	98.44 89	99.29 70	96.31 130	98.14 223	98.76 96	92.41 262	96.39 180	98.31 175	94.92 73	99.78 91	94.06 211	98.77 129	99.23 126
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		98.58 20	98.29 36	99.46 14	99.76 2	98.64 25	98.90 97	98.74 100	97.27 40	98.02 101	99.39 22	94.81 74	99.96 4	97.91 56	99.79 23	99.77 22

Test By Simon												94.64 75

新几何1				99.16 44	99.34 55	98.01 58		98.69 112	90.06 321	98.13 91	98.95 102	94.60 76	99.89 39	91.97 271	99.47 91	99.59 73

MP-MVS		98.33 48	98.01 52	99.28 31	99.75 3	98.18 49	99.22 35	98.79 90	96.13 92	97.92 112	99.23 52	94.54 77	99.94 5	96.74 126	99.78 26	99.73 36
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
pcd_1.5k_mvsjas		7.88 355	10.50 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	94.51 78	0.00 388	0.00 386	0.00 386	0.00 384

PS-MVSNAJss		96.43 130	96.26 127	96.92 197	95.84 327	95.08 186	99.16 46	98.50 160	95.87 106	93.84 257	98.34 172	94.51 78	98.61 248	96.88 115	93.45 256	97.06 237

PS-MVSNAJ		97.73 65	97.77 57	97.62 153	98.68 140	95.58 164	97.34 291	98.51 155	97.29 35	98.66 67	97.88 212	94.51 78	99.90 37	97.87 60	99.17 110	97.39 229

API-MVS		97.41 89	97.25 83	97.91 127	98.70 137	96.80 99	98.82 117	98.69 112	94.53 169	98.11 92	98.28 177	94.50 81	99.57 132	94.12 208	99.49 88	97.37 231

ACMMP		98.23 50	97.95 54	99.09 49	99.74 7	97.62 70	99.03 71	99.41 6	95.98 97	97.60 133	99.36 32	94.45 82	99.93 21	97.14 100	98.85 125	99.70 47
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
testdata				98.26 103	99.20 89	95.36 173		98.68 115	91.89 278	98.60 71	99.10 76	94.44 83	99.82 66	94.27 203	99.44 95	99.58 77

MVS_0304		98.47 33	98.22 43	99.21 38	99.00 109	97.80 66	98.88 104	95.32 353	98.86 1	98.53 74	99.44 19	94.38 84	99.94 5	99.86 1	99.70 50	99.90 1

xiu_mvs_v2_base		97.66 71	97.70 60	97.56 157	98.61 147	95.46 170	97.44 280	98.46 167	97.15 47	98.65 68	98.15 189	94.33 85	99.80 78	97.84 63	98.66 134	97.41 227

mvsany_test1		97.69 69	97.70 60	97.66 151	98.24 177	94.18 230	97.53 277	97.53 288	95.52 121	99.66 8	99.51 6	94.30 86	99.56 135	98.38 35	98.62 135	99.23 126

PAPR		96.84 115	96.24 128	98.65 69	98.72 136	96.92 95	97.36 289	98.57 142	93.33 226	96.67 165	97.57 242	94.30 86	99.56 135	91.05 288	98.59 137	99.47 93

test_fmvsmvis_n_1920		98.44 36	98.51 15	98.23 106	98.33 171	96.15 135	98.97 84	99.15 21	98.55 3	98.45 79	99.55 1	94.26 88	99.97 1	99.65 3	99.66 56	98.57 194

PAPM_NR		97.46 82	97.11 88	98.50 81	99.50 41	96.41 123	98.63 161	98.60 133	95.18 140	97.06 148	98.06 195	94.26 88	99.57 132	93.80 219	98.87 124	99.52 80

test222					99.23 85	97.17 88	97.40 283	98.66 123	88.68 338	98.05 96	98.96 100	94.14 90			99.53 84	99.61 69

EPP-MVSNet		97.46 82	97.28 82	97.99 123	98.64 144	95.38 172	99.33 21	98.31 194	93.61 217	97.19 141	99.07 85	94.05 91	99.23 171	96.89 113	98.43 147	99.37 107

F-COLMAP		97.09 106	96.80 101	97.97 124	99.45 52	94.95 194	98.55 174	98.62 132	93.02 240	96.17 185	98.58 143	94.01 92	99.81 71	93.95 213	98.90 120	99.14 142

TAPA-MVS	93.98 7	95.35 191	94.56 206	97.74 141	99.13 98	94.83 200	98.33 197	98.64 128	86.62 346	96.29 182	98.61 138	94.00 93	99.29 166	80.00 362	99.41 97	99.09 147
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MG-MVS		97.81 62	97.60 63	98.44 89	99.12 99	95.97 145	97.75 261	98.78 92	96.89 60	98.46 76	99.22 54	93.90 94	99.68 115	94.81 184	99.52 85	99.67 59

EC-MVSNet		98.21 51	98.11 48	98.49 83	98.34 169	97.26 84	99.61 5	98.43 175	96.78 64	98.87 51	98.84 113	93.72 95	99.01 205	98.91 10	99.50 86	99.19 133

CDS-MVSNet		96.99 108	96.69 109	97.90 128	98.05 198	95.98 140	98.20 215	98.33 191	93.67 213	96.95 151	98.49 151	93.54 96	98.42 271	95.24 175	97.74 172	99.31 114
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TAMVS		97.02 107	96.79 103	97.70 145	98.06 197	95.31 177	98.52 176	98.31 194	93.95 191	97.05 149	98.61 138	93.49 97	98.52 259	95.33 169	97.81 168	99.29 119

CNLPA		97.45 85	97.03 92	98.73 64	99.05 103	97.44 77	98.07 230	98.53 150	95.32 133	96.80 162	98.53 147	93.32 98	99.72 103	94.31 202	99.31 105	99.02 155

OMC-MVS		97.55 80	97.34 80	98.20 108	99.33 57	95.92 152	98.28 207	98.59 135	95.52 121	97.97 106	99.10 76	93.28 99	99.49 148	95.09 177	98.88 122	99.19 133

UA-Net		97.96 55	97.62 62	98.98 54	98.86 123	97.47 75	98.89 101	99.08 25	96.67 70	98.72 62	99.54 2	93.15 100	99.81 71	94.87 180	98.83 126	99.65 63

CPTT-MVS		97.72 66	97.32 81	98.92 58	99.64 28	97.10 89	99.12 53	98.81 78	92.34 264	98.09 94	99.08 84	93.01 101	99.92 26	96.06 145	99.77 28	99.75 29

114514_t		96.93 110	96.27 126	98.92 58	99.50 41	97.63 69	98.85 111	98.90 49	84.80 358	97.77 116	99.11 74	92.84 102	99.66 118	94.85 181	99.77 28	99.47 93

PVSNet_Blended_VisFu		97.70 68	97.46 73	98.44 89	99.27 75	95.91 153	98.63 161	99.16 20	94.48 173	97.67 126	98.88 109	92.80 103	99.91 34	97.11 101	99.12 111	99.50 85

PVSNet_BlendedMVS		96.73 118	96.60 113	97.12 181	99.25 78	95.35 175	98.26 210	99.26 10	94.28 177	97.94 109	97.46 248	92.74 104	99.81 71	96.88 115	93.32 259	96.20 324

PVSNet_Blended		97.38 91	97.12 87	98.14 111	99.25 78	95.35 175	97.28 296	99.26 10	93.13 235	97.94 109	98.21 185	92.74 104	99.81 71	96.88 115	99.40 99	99.27 121

MVS_Test		97.28 95	97.00 93	98.13 114	98.33 171	95.97 145	98.74 136	98.07 243	94.27 178	98.44 81	98.07 194	92.48 106	99.26 167	96.43 134	98.19 156	99.16 139

miper_enhance_ethall		95.10 205	94.75 198	96.12 259	97.53 234	93.73 244	96.61 338	98.08 241	92.20 272	93.89 253	96.65 310	92.44 107	98.30 292	94.21 205	91.16 286	96.34 318

MVSFormer		97.57 78	97.49 70	97.84 130	98.07 195	95.76 159	99.47 9	98.40 179	94.98 151	98.79 55	98.83 115	92.34 108	98.41 279	96.91 109	99.59 70	99.34 108

lupinMVS		97.44 86	97.22 85	98.12 116	98.07 195	95.76 159	97.68 266	97.76 269	94.50 172	98.79 55	98.61 138	92.34 108	99.30 165	97.58 81	99.59 70	99.31 114

CHOSEN 280x420		97.18 101	97.18 86	97.20 174	98.81 128	93.27 261	95.78 351	99.15 21	95.25 137	96.79 163	98.11 192	92.29 110	99.07 195	98.56 19	99.85 5	99.25 125

canonicalmvs		97.67 70	97.23 84	98.98 54	98.70 137	98.38 35	99.34 18	98.39 181	96.76 66	97.67 126	97.40 254	92.26 111	99.49 148	98.28 40	96.28 209	99.08 151

IterMVS-LS		95.46 180	95.21 176	96.22 255	98.12 192	93.72 245	98.32 201	98.13 229	93.71 206	94.26 235	97.31 258	92.24 112	98.10 306	94.63 188	90.12 297	96.84 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		95.96 152	95.83 143	96.36 247	97.93 205	93.70 246	98.12 226	98.27 203	93.70 208	95.07 204	99.02 88	92.23 113	98.54 257	94.68 186	93.46 254	96.84 263

WTY-MVS		97.37 93	96.92 97	98.72 65	98.86 123	96.89 98	98.31 202	98.71 108	95.26 136	97.67 126	98.56 146	92.21 114	99.78 91	95.89 150	96.85 188	99.48 91

Effi-MVS+		97.12 104	96.69 109	98.39 95	98.19 185	96.72 104	97.37 287	98.43 175	93.71 206	97.65 129	98.02 198	92.20 115	99.25 168	96.87 118	97.79 169	99.19 133

1112_ss		96.63 121	96.00 137	98.50 81	98.56 149	96.37 125	98.18 221	98.10 236	92.92 244	94.84 209	98.43 158	92.14 116	99.58 131	94.35 199	96.51 199	99.56 79

LS3D		97.16 102	96.66 112	98.68 67	98.53 152	97.19 87	98.93 94	98.90 49	92.83 248	95.99 190	99.37 28	92.12 117	99.87 48	93.67 223	99.57 74	98.97 160

nrg030		96.28 140	95.72 149	97.96 126	96.90 277	98.15 52	99.39 12	98.31 194	95.47 123	94.42 227	98.35 168	92.09 118	98.69 241	97.50 89	89.05 314	97.04 238

mvs_anonymous		96.70 120	96.53 117	97.18 176	98.19 185	93.78 239	98.31 202	98.19 215	94.01 187	94.47 221	98.27 180	92.08 119	98.46 266	97.39 93	97.91 164	99.31 114

FC-MVSNet-test		96.42 131	96.05 134	97.53 158	96.95 272	97.27 80	99.36 15	99.23 14	95.83 107	93.93 251	98.37 166	92.00 120	98.32 288	96.02 147	92.72 269	97.00 241

FIs		96.51 128	96.12 131	97.67 148	97.13 263	97.54 73	99.36 15	99.22 17	95.89 103	94.03 248	98.35 168	91.98 121	98.44 269	96.40 135	92.76 268	97.01 240

sss		97.39 90	96.98 95	98.61 71	98.60 148	96.61 108	98.22 212	98.93 42	93.97 190	98.01 104	98.48 152	91.98 121	99.85 53	96.45 133	98.15 157	99.39 105

miper_ehance_all_eth		95.01 209	94.69 201	95.97 264	97.70 219	93.31 260	97.02 314	98.07 243	92.23 269	93.51 269	96.96 292	91.85 123	98.15 302	93.68 221	91.16 286	96.44 315

DP-MVS		96.59 123	95.93 140	98.57 73	99.34 55	96.19 134	98.70 149	98.39 181	89.45 331	94.52 219	99.35 34	91.85 123	99.85 53	92.89 247	98.88 122	99.68 55

Test_1112_low_res		96.34 137	95.66 157	98.36 96	98.56 149	95.94 148	97.71 264	98.07 243	92.10 273	94.79 213	97.29 259	91.75 125	99.56 135	94.17 206	96.50 200	99.58 77

UniMVSNet_NR-MVSNet		95.71 168	95.15 178	97.40 166	96.84 280	96.97 92	98.74 136	99.24 12	95.16 141	93.88 254	97.72 227	91.68 126	98.31 290	95.81 153	87.25 335	96.92 247

UniMVSNet (Re)		95.78 164	95.19 177	97.58 155	96.99 270	97.47 75	98.79 130	99.18 19	95.60 117	93.92 252	97.04 283	91.68 126	98.48 262	95.80 155	87.66 329	96.79 267

casdiffmvs_mvg		97.72 66	97.48 72	98.44 89	98.42 158	96.59 111	98.92 95	98.44 171	96.20 89	97.76 117	99.20 57	91.66 128	99.23 171	98.27 41	98.41 148	99.49 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HY-MVS	93.96 8	96.82 116	96.23 129	98.57 73	98.46 156	97.00 91	98.14 223	98.21 211	93.95 191	96.72 164	97.99 202	91.58 129	99.76 97	94.51 195	96.54 198	98.95 163

xiu_mvs_v1_base_debu		97.60 74	97.56 66	97.72 142	98.35 164	95.98 140	97.86 252	98.51 155	97.13 49	99.01 40	98.40 162	91.56 130	99.80 78	98.53 20	98.68 130	97.37 231

xiu_mvs_v1_base		97.60 74	97.56 66	97.72 142	98.35 164	95.98 140	97.86 252	98.51 155	97.13 49	99.01 40	98.40 162	91.56 130	99.80 78	98.53 20	98.68 130	97.37 231

xiu_mvs_v1_base_debi		97.60 74	97.56 66	97.72 142	98.35 164	95.98 140	97.86 252	98.51 155	97.13 49	99.01 40	98.40 162	91.56 130	99.80 78	98.53 20	98.68 130	97.37 231

MAR-MVS		96.91 111	96.40 121	98.45 87	98.69 139	96.90 96	98.66 157	98.68 115	92.40 263	97.07 147	97.96 205	91.54 133	99.75 99	93.68 221	98.92 119	98.69 181
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
CANet		98.05 53	97.76 58	98.90 60	98.73 132	97.27 80	98.35 195	98.78 92	97.37 32	97.72 123	98.96 100	91.53 134	99.92 26	98.79 13	99.65 59	99.51 83

c3_l		94.79 221	94.43 216	95.89 269	97.75 214	93.12 268	97.16 308	98.03 251	92.23 269	93.46 272	97.05 282	91.39 135	98.01 313	93.58 226	89.21 312	96.53 301

EPNet		97.28 95	96.87 99	98.51 80	94.98 344	96.14 136	98.90 97	97.02 321	98.28 4	95.99 190	99.11 74	91.36 136	99.89 39	96.98 105	99.19 109	99.50 85
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
baseline		97.64 72	97.44 75	98.25 104	98.35 164	96.20 132	99.00 78	98.32 192	96.33 86	98.03 99	99.17 64	91.35 137	99.16 178	98.10 45	98.29 155	99.39 105

1314		96.25 142	95.73 148	97.79 135	97.13 263	95.55 167	98.19 218	98.59 135	93.47 221	92.03 311	97.82 220	91.33 138	99.49 148	94.62 190	98.44 145	98.32 204

diffmvs		97.58 77	97.40 77	98.13 114	98.32 174	95.81 158	98.06 231	98.37 185	96.20 89	98.74 59	98.89 108	91.31 139	99.25 168	98.16 43	98.52 140	99.34 108
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PAPM		94.95 215	94.00 237	97.78 136	97.04 267	95.65 162	96.03 347	98.25 208	91.23 301	94.19 240	97.80 222	91.27 140	98.86 228	82.61 356	97.61 176	98.84 171

casdiffmvs		97.63 73	97.41 76	98.28 100	98.33 171	96.14 136	98.82 117	98.32 192	96.38 84	97.95 107	99.21 55	91.23 141	99.23 171	98.12 44	98.37 149	99.48 91
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jason		97.32 94	97.08 90	98.06 120	97.45 241	95.59 163	97.87 251	97.91 263	94.79 159	98.55 73	98.83 115	91.12 142	99.23 171	97.58 81	99.60 68	99.34 108
jason: jason.
IS-MVSNet		97.22 97	96.88 98	98.25 104	98.85 125	96.36 126	99.19 42	97.97 256	95.39 127	97.23 140	98.99 94	91.11 143	98.93 217	94.60 191	98.59 137	99.47 93

PMMVS		96.60 122	96.33 123	97.41 164	97.90 207	93.93 235	97.35 290	98.41 177	92.84 247	97.76 117	97.45 250	91.10 144	99.20 175	96.26 138	97.91 164	99.11 145

MVS		94.67 229	93.54 269	98.08 118	96.88 278	96.56 113	98.19 218	98.50 160	78.05 368	92.69 294	98.02 198	91.07 145	99.63 124	90.09 299	98.36 151	98.04 212

Fast-Effi-MVS+		96.28 140	95.70 154	98.03 121	98.29 176	95.97 145	98.58 167	98.25 208	91.74 281	95.29 201	97.23 264	91.03 146	99.15 181	92.90 245	97.96 163	98.97 160

mvsmamba		96.57 126	96.32 124	97.32 170	96.60 292	96.43 120	99.54 7	97.98 254	96.49 76	95.20 202	98.64 136	90.82 147	98.55 255	97.97 51	93.65 249	96.98 242

Effi-MVS+-dtu		96.29 138	96.56 114	95.51 281	97.89 208	90.22 312	98.80 125	98.10 236	96.57 75	96.45 179	96.66 308	90.81 148	98.91 219	95.72 157	97.99 161	97.40 228

test_yl		97.22 97	96.78 104	98.54 77	98.73 132	96.60 109	98.45 185	98.31 194	94.70 160	98.02 101	98.42 160	90.80 149	99.70 109	96.81 121	96.79 190	99.34 108

DCV-MVSNet		97.22 97	96.78 104	98.54 77	98.73 132	96.60 109	98.45 185	98.31 194	94.70 160	98.02 101	98.42 160	90.80 149	99.70 109	96.81 121	96.79 190	99.34 108

alignmvs		97.56 79	97.07 91	99.01 52	98.66 142	98.37 39	98.83 115	98.06 248	96.74 67	98.00 105	97.65 234	90.80 149	99.48 152	98.37 36	96.56 197	99.19 133

AdaColmap		97.15 103	96.70 108	98.48 84	99.16 95	96.69 105	98.01 236	98.89 51	94.44 175	96.83 158	98.68 132	90.69 152	99.76 97	94.36 198	99.29 106	98.98 159

cdsmvs_eth3d_5k		23.98 351	31.98 353	0.00 369	0.00 392	0.00 393	0.00 380	98.59 135	0.00 387	0.00 388	98.61 138	90.60 153	0.00 388	0.00 386	0.00 386	0.00 384

eth_miper_zixun_eth		94.68 226	94.41 217	95.47 283	97.64 223	91.71 287	96.73 335	98.07 243	92.71 251	93.64 262	97.21 266	90.54 154	98.17 301	93.38 229	89.76 301	96.54 299

DeepC-MVS	95.98 3	97.88 59	97.58 64	98.77 63	99.25 78	96.93 94	98.83 115	98.75 98	96.96 57	96.89 157	99.50 8	90.46 155	99.87 48	97.84 63	99.76 34	99.52 80
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
WR-MVS_H		95.05 208	94.46 212	96.81 203	96.86 279	95.82 157	99.24 30	99.24 12	93.87 195	92.53 299	96.84 302	90.37 156	98.24 298	93.24 233	87.93 326	96.38 317

EPNet_dtu		95.21 199	94.95 190	95.99 262	96.17 313	90.45 308	98.16 222	97.27 308	96.77 65	93.14 282	98.33 173	90.34 157	98.42 271	85.57 341	98.81 128	99.09 147
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
VNet		97.79 63	97.40 77	98.96 56	98.88 121	97.55 72	98.63 161	98.93 42	96.74 67	99.02 39	98.84 113	90.33 158	99.83 59	98.53 20	96.66 193	99.50 85

MSDG		95.93 156	95.30 173	97.83 131	98.90 119	95.36 173	96.83 331	98.37 185	91.32 296	94.43 226	98.73 128	90.27 159	99.60 129	90.05 302	98.82 127	98.52 195

LCM-MVSNet-Re		95.22 198	95.32 170	94.91 299	98.18 187	87.85 350	98.75 133	95.66 350	95.11 144	88.96 337	96.85 301	90.26 160	97.65 331	95.65 161	98.44 145	99.22 128

Vis-MVSNet (Re-imp)		96.87 113	96.55 115	97.83 131	98.73 132	95.46 170	99.20 40	98.30 200	94.96 153	96.60 169	98.87 110	90.05 161	98.59 251	93.67 223	98.60 136	99.46 97

miper_lstm_enhance		94.33 252	94.07 232	95.11 294	97.75 214	90.97 298	97.22 299	98.03 251	91.67 285	92.76 291	96.97 290	90.03 162	97.78 328	92.51 258	89.64 303	96.56 296

baseline1		95.84 161	95.12 181	98.01 122	98.49 155	95.98 140	98.73 140	97.03 319	95.37 130	96.22 183	98.19 187	89.96 163	99.16 178	94.60 191	87.48 330	98.90 167

MDTV_nov1_ep13_2view						84.26 359	96.89 326		90.97 306	97.90 113		89.89 164		93.91 215		99.18 138

h-mvs33		96.17 143	95.62 158	97.81 134	99.03 105	94.45 216	98.64 159	98.75 98	97.48 23	98.67 63	98.72 129	89.76 165	99.86 52	97.95 52	81.59 357	99.11 145

hse-mvs2		95.71 168	95.30 173	96.93 194	98.50 153	93.53 251	98.36 194	98.10 236	97.48 23	98.67 63	97.99 202	89.76 165	99.02 203	97.95 52	80.91 361	98.22 207

GeoE		96.58 125	96.07 133	98.10 117	98.35 164	95.89 155	99.34 18	98.12 230	93.12 236	96.09 186	98.87 110	89.71 167	98.97 207	92.95 243	98.08 160	99.43 102

our_test_3		93.65 279	93.30 276	94.69 307	95.45 338	89.68 321	96.91 321	97.65 274	91.97 276	91.66 315	96.88 298	89.67 168	97.93 320	88.02 327	91.49 281	96.48 312

tpmrst		95.63 173	95.69 155	95.44 285	97.54 232	88.54 339	96.97 316	97.56 281	93.50 220	97.52 135	96.93 296	89.49 169	99.16 178	95.25 174	96.42 202	98.64 187

D2MVS		95.18 201	95.08 183	95.48 282	97.10 265	92.07 279	98.30 204	99.13 23	94.02 186	92.90 287	96.73 305	89.48 170	98.73 239	94.48 196	93.60 252	95.65 337

FA-MVS(test-final)		96.41 135	95.94 139	97.82 133	98.21 181	95.20 180	97.80 257	97.58 279	93.21 232	97.36 137	97.70 228	89.47 171	99.56 135	94.12 208	97.99 161	98.71 180

sam_mvs1												89.45 172				99.20 129

patchmatchnet-post											95.10 344	89.42 173	98.89 223

3Dnovator+	94.38 6	97.43 87	96.78 104	99.38 18	97.83 210	98.52 28	99.37 14	98.71 108	97.09 52	92.99 286	99.13 72	89.36 174	99.89 39	96.97 106	99.57 74	99.71 43

NR-MVSNet		94.98 213	94.16 227	97.44 161	96.53 296	97.22 86	98.74 136	98.95 38	94.96 153	89.25 336	97.69 230	89.32 175	98.18 300	94.59 193	87.40 332	96.92 247

HyFIR lowres test		96.90 112	96.49 118	98.14 111	99.33 57	95.56 165	97.38 285	99.65 2	92.34 264	97.61 132	98.20 186	89.29 176	99.10 192	96.97 106	97.60 177	99.77 22

RRT_MVS		95.98 151	95.78 145	96.56 226	96.48 300	94.22 229	99.57 6	97.92 261	95.89 103	93.95 250	98.70 130	89.27 177	98.42 271	97.23 98	93.02 263	97.04 238

3Dnovator	94.51 5	97.46 82	96.93 96	99.07 50	97.78 212	97.64 68	99.35 17	99.06 27	97.02 54	93.75 261	99.16 67	89.25 178	99.92 26	97.22 99	99.75 38	99.64 65

PatchmatchNet		95.71 168	95.52 159	96.29 253	97.58 227	90.72 303	96.84 330	97.52 289	94.06 183	97.08 145	96.96 292	89.24 179	98.90 222	92.03 269	98.37 149	99.26 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MDTV_nov1_ep13			95.40 161		97.48 236	88.34 343	96.85 329	97.29 306	93.74 203	97.48 136	97.26 260	89.18 180	99.05 196	91.92 272	97.43 180

test_djsdf		96.00 150	95.69 155	96.93 194	95.72 329	95.49 169	99.47 9	98.40 179	94.98 151	94.58 217	97.86 213	89.16 181	98.41 279	96.91 109	94.12 235	96.88 256

DIV-MVS_self_test		94.52 240	94.03 233	95.99 262	97.57 231	93.38 258	97.05 312	97.94 259	91.74 281	92.81 289	97.10 270	89.12 182	98.07 310	92.60 251	90.30 294	96.53 301

QAPM		96.29 138	95.40 161	98.96 56	97.85 209	97.60 71	99.23 31	98.93 42	89.76 326	93.11 283	99.02 88	89.11 183	99.93 21	91.99 270	99.62 66	99.34 108

pmmvs4		94.69 224	93.99 239	96.81 203	95.74 328	95.94 148	97.40 283	97.67 273	90.42 315	93.37 273	97.59 240	89.08 184	98.20 299	92.97 242	91.67 279	96.30 321

cl____		94.51 241	94.01 236	96.02 261	97.58 227	93.40 257	97.05 312	97.96 258	91.73 283	92.76 291	97.08 276	89.06 185	98.13 304	92.61 250	90.29 295	96.52 304

sam_mvs												88.99 186

Patchmatch-test		94.42 248	93.68 263	96.63 216	97.60 226	91.76 284	94.83 361	97.49 293	89.45 331	94.14 242	97.10 270	88.99 186	98.83 231	85.37 344	98.13 158	99.29 119

Patchmatch-RL test		91.49 303	90.85 304	93.41 326	91.37 366	84.40 358	92.81 369	95.93 348	91.87 279	87.25 347	94.87 346	88.99 186	96.53 356	92.54 257	82.00 354	99.30 117

Fast-Effi-MVS+-dtu		95.87 159	95.85 142	95.91 267	97.74 217	91.74 286	98.69 151	98.15 226	95.56 119	94.92 207	97.68 233	88.98 189	98.79 235	93.19 235	97.78 170	97.20 235

BH-untuned		95.95 153	95.72 149	96.65 212	98.55 151	92.26 276	98.23 211	97.79 268	93.73 204	94.62 216	98.01 200	88.97 190	99.00 206	93.04 240	98.51 141	98.68 182

XVG-OURS		96.55 127	96.41 120	96.99 188	98.75 131	93.76 240	97.50 279	98.52 153	95.67 115	96.83 158	99.30 42	88.95 191	99.53 143	95.88 151	96.26 210	97.69 223

PVSNet	91.96 18	96.35 136	96.15 130	96.96 192	99.17 91	92.05 280	96.08 344	98.68 115	93.69 209	97.75 119	97.80 222	88.86 192	99.69 114	94.26 204	99.01 116	99.15 140

test_post											31.83 384	88.83 193	98.91 219

v8		94.47 245	93.77 255	96.57 225	96.36 305	94.83 200	99.05 65	98.19 215	91.92 277	93.16 279	96.97 290	88.82 194	98.48 262	91.69 277	87.79 327	96.39 316

BH-w/o		95.38 187	95.08 183	96.26 254	98.34 169	91.79 283	97.70 265	97.43 298	92.87 246	94.24 237	97.22 265	88.66 195	98.84 229	91.55 279	97.70 174	98.16 210

tpmvs		94.60 232	94.36 219	95.33 289	97.46 238	88.60 338	96.88 327	97.68 272	91.29 298	93.80 259	96.42 318	88.58 196	99.24 170	91.06 286	96.04 216	98.17 209

DU-MVS		95.42 184	94.76 197	97.40 166	96.53 296	96.97 92	98.66 157	98.99 34	95.43 125	93.88 254	97.69 230	88.57 197	98.31 290	95.81 153	87.25 335	96.92 247

Baseline_NR-MVSNet		94.35 251	93.81 251	95.96 265	96.20 311	94.05 233	98.61 164	96.67 338	91.44 290	93.85 256	97.60 239	88.57 197	98.14 303	94.39 197	86.93 338	95.68 336

PCF-MVS	93.45 11	94.68 226	93.43 273	98.42 93	98.62 146	96.77 101	95.48 355	98.20 213	84.63 359	93.34 274	98.32 174	88.55 199	99.81 71	84.80 348	98.96 118	98.68 182
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
v148		94.29 255	93.76 257	95.91 267	96.10 316	92.93 271	98.58 167	97.97 256	92.59 255	93.47 271	96.95 294	88.53 200	98.32 288	92.56 255	87.06 337	96.49 310

PatchMatch-RL		96.59 123	96.03 136	98.27 101	99.31 62	96.51 116	97.91 245	99.06 27	93.72 205	96.92 155	98.06 195	88.50 201	99.65 119	91.77 275	99.00 117	98.66 185

V42		94.78 222	94.14 229	96.70 209	96.33 308	95.22 179	98.97 84	98.09 240	92.32 266	94.31 233	97.06 280	88.39 202	98.55 255	92.90 245	88.87 318	96.34 318

v7n		94.19 261	93.43 273	96.47 238	95.90 324	94.38 221	99.26 27	98.34 190	91.99 275	92.76 291	97.13 269	88.31 203	98.52 259	89.48 314	87.70 328	96.52 304

TranMVSNet+NR-MVSNet		95.14 203	94.48 210	97.11 182	96.45 302	96.36 126	99.03 71	99.03 30	95.04 149	93.58 264	97.93 207	88.27 204	98.03 312	94.13 207	86.90 340	96.95 246

MVSTER		96.06 148	95.72 149	97.08 184	98.23 179	95.93 151	98.73 140	98.27 203	94.86 157	95.07 204	98.09 193	88.21 205	98.54 257	96.59 127	93.46 254	96.79 267

CHOSEN 1792x2688		97.12 104	96.80 101	98.08 118	99.30 66	94.56 214	98.05 232	99.71 1	93.57 218	97.09 144	98.91 107	88.17 206	99.89 39	96.87 118	99.56 80	99.81 12

CR-MVSNet		94.76 223	94.15 228	96.59 222	97.00 268	93.43 254	94.96 357	97.56 281	92.46 257	96.93 153	96.24 321	88.15 207	97.88 325	87.38 330	96.65 194	98.46 197

Patchmtry		93.22 288	92.35 292	95.84 271	96.77 282	93.09 269	94.66 364	97.56 281	87.37 344	92.90 287	96.24 321	88.15 207	97.90 321	87.37 331	90.10 298	96.53 301

v10		94.29 255	93.55 268	96.51 234	96.39 304	94.80 202	98.99 81	98.19 215	91.35 294	93.02 285	96.99 288	88.09 209	98.41 279	90.50 295	88.41 322	96.33 320

ppachtmachnet_test		93.22 288	92.63 288	94.97 298	95.45 338	90.84 300	96.88 327	97.88 264	90.60 310	92.08 310	97.26 260	88.08 210	97.86 326	85.12 345	90.33 293	96.22 323

Vis-MVSNet		97.42 88	97.11 88	98.34 97	98.66 142	96.23 131	99.22 35	99.00 32	96.63 72	98.04 98	99.21 55	88.05 211	99.35 161	96.01 148	99.21 107	99.45 99
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1144		94.59 234	93.92 242	96.60 221	96.21 310	94.78 204	98.59 165	98.14 228	91.86 280	94.21 239	97.02 285	87.97 212	98.41 279	91.72 276	89.57 304	96.61 289

PatchT		93.06 292	91.97 296	96.35 248	96.69 288	92.67 273	94.48 365	97.08 314	86.62 346	97.08 145	92.23 365	87.94 213	97.90 321	78.89 366	96.69 192	98.49 196

ADS-MVSNet2		94.58 235	94.40 218	95.11 294	98.00 199	88.74 336	96.04 345	97.30 305	90.15 319	96.47 177	96.64 311	87.89 214	97.56 336	90.08 300	97.06 184	99.02 155

ADS-MVSNet		95.00 210	94.45 214	96.63 216	98.00 199	91.91 282	96.04 345	97.74 271	90.15 319	96.47 177	96.64 311	87.89 214	98.96 211	90.08 300	97.06 184	99.02 155

XVG-OURS-SEG-HR		96.51 128	96.34 122	97.02 187	98.77 130	93.76 240	97.79 259	98.50 160	95.45 124	96.94 152	99.09 82	87.87 216	99.55 142	96.76 125	95.83 218	97.74 220

test_post1							96.68 336				30.43 385	87.85 217	98.69 241	92.59 253

iter_conf_final		96.42 131	96.12 131	97.34 169	98.46 156	96.55 115	99.08 61	98.06 248	96.03 96	95.63 196	98.46 156	87.72 218	98.59 251	97.84 63	93.80 244	96.87 258

test-LLR		95.10 205	94.87 194	95.80 272	96.77 282	89.70 319	96.91 321	95.21 354	95.11 144	94.83 211	95.72 337	87.71 219	98.97 207	93.06 238	98.50 142	98.72 178

test0.0.03 1		94.08 270	93.51 270	95.80 272	95.53 335	92.89 272	97.38 285	95.97 346	95.11 144	92.51 301	96.66 308	87.71 219	96.94 347	87.03 332	93.67 247	97.57 225

JIA-IIPM		93.35 283	92.49 290	95.92 266	96.48 300	90.65 305	95.01 356	96.96 323	85.93 352	96.08 187	87.33 371	87.70 221	98.78 236	91.35 281	95.58 221	98.34 202

v2v482		94.69 224	94.03 233	96.65 212	96.17 313	94.79 203	98.67 155	98.08 241	92.72 250	94.00 249	97.16 268	87.69 222	98.45 267	92.91 244	88.87 318	96.72 275

CVMVSNet		95.43 183	96.04 135	93.57 324	97.93 205	83.62 361	98.12 226	98.59 135	95.68 114	96.56 170	99.02 88	87.51 223	97.51 338	93.56 227	97.44 179	99.60 71

WR-MVS		95.15 202	94.46 212	97.22 173	96.67 290	96.45 118	98.21 213	98.81 78	94.15 180	93.16 279	97.69 230	87.51 223	98.30 292	95.29 172	88.62 320	96.90 254

anonymousdsp		95.42 184	94.91 191	96.94 193	95.10 343	95.90 154	99.14 49	98.41 177	93.75 201	93.16 279	97.46 248	87.50 225	98.41 279	95.63 162	94.03 237	96.50 309

v144192		94.39 250	93.70 261	96.48 237	96.06 318	94.35 222	98.58 167	98.16 225	91.45 289	94.33 232	97.02 285	87.50 225	98.45 267	91.08 285	89.11 313	96.63 287

baseline2		95.11 204	94.52 208	96.87 199	96.65 291	93.56 248	98.27 209	94.10 368	93.45 222	92.02 312	97.43 252	87.45 227	99.19 176	93.88 216	97.41 181	97.87 216

EU-MVSNet		93.66 277	94.14 229	92.25 339	95.96 323	83.38 362	98.52 176	98.12 230	94.69 162	92.61 296	98.13 191	87.36 228	96.39 358	91.82 273	90.00 299	96.98 242

CP-MVSNet		94.94 217	94.30 220	96.83 201	96.72 287	95.56 165	99.11 55	98.95 38	93.89 193	92.42 304	97.90 209	87.19 229	98.12 305	94.32 201	88.21 323	96.82 266

HQP_MVS		96.14 145	95.90 141	96.85 200	97.42 243	94.60 212	98.80 125	98.56 144	97.28 36	95.34 199	98.28 177	87.09 230	99.03 200	96.07 142	94.27 227	96.92 247

plane_prior6					97.35 248	94.61 210						87.09 230

RPSCF		94.87 219	95.40 161	93.26 330	98.89 120	82.06 366	98.33 197	98.06 248	90.30 318	96.56 170	99.26 47	87.09 230	99.49 148	93.82 218	96.32 205	98.24 205

RPMNet		92.81 294	91.34 301	97.24 172	97.00 268	93.43 254	94.96 357	98.80 85	82.27 363	96.93 153	92.12 366	86.98 233	99.82 66	76.32 370	96.65 194	98.46 197

v1192		94.32 253	93.58 266	96.53 232	96.10 316	94.45 216	98.50 181	98.17 223	91.54 287	94.19 240	97.06 280	86.95 234	98.43 270	90.14 298	89.57 304	96.70 279

CANet_DTU		96.96 109	96.55 115	98.21 107	98.17 189	96.07 138	97.98 239	98.21 211	97.24 41	97.13 143	98.93 104	86.88 235	99.91 34	95.00 179	99.37 102	98.66 185

HQP2-MVS												86.75 236

HQP-MVS		95.72 167	95.40 161	96.69 210	97.20 256	94.25 227	98.05 232	98.46 167	96.43 79	94.45 222	97.73 225	86.75 236	98.96 211	95.30 170	94.18 231	96.86 261

OpenMVS	93.04 13	95.83 162	95.00 186	98.32 98	97.18 260	97.32 78	99.21 38	98.97 35	89.96 322	91.14 319	99.05 87	86.64 238	99.92 26	93.38 229	99.47 91	97.73 221

cl22		94.68 226	94.19 224	96.13 258	98.11 193	93.60 247	96.94 318	98.31 194	92.43 261	93.32 275	96.87 300	86.51 239	98.28 296	94.10 210	91.16 286	96.51 307

ET-MVSNet_ETH3D		94.13 265	92.98 281	97.58 155	98.22 180	96.20 132	97.31 294	95.37 352	94.53 169	79.56 367	97.63 238	86.51 239	97.53 337	96.91 109	90.74 290	99.02 155

YYNet1		90.70 313	89.39 316	94.62 310	94.79 349	90.65 305	97.20 301	97.46 294	87.54 343	72.54 373	95.74 333	86.51 239	96.66 354	86.00 338	86.76 342	96.54 299

MDA-MVSNet_test_wron		90.71 312	89.38 317	94.68 308	94.83 347	90.78 302	97.19 303	97.46 294	87.60 342	72.41 374	95.72 337	86.51 239	96.71 353	85.92 339	86.80 341	96.56 296

v1921920		94.20 260	93.47 272	96.40 246	95.98 321	94.08 232	98.52 176	98.15 226	91.33 295	94.25 236	97.20 267	86.41 243	98.42 271	90.04 303	89.39 310	96.69 284

COLMAP_ROB	93.27 12	95.33 193	94.87 194	96.71 207	99.29 70	93.24 264	98.58 167	98.11 233	89.92 323	93.57 265	99.10 76	86.37 244	99.79 88	90.78 291	98.10 159	97.09 236
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MVP-Stereo		94.28 257	93.92 242	95.35 288	94.95 345	92.60 274	97.97 240	97.65 274	91.61 286	90.68 324	97.09 274	86.32 245	98.42 271	89.70 309	99.34 103	95.02 348
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CLD-MVS		95.62 174	95.34 167	96.46 241	97.52 235	93.75 242	97.27 297	98.46 167	95.53 120	94.42 227	98.00 201	86.21 246	98.97 207	96.25 140	94.37 225	96.66 285
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpm cat1		93.36 282	92.80 284	95.07 296	97.58 227	87.97 348	96.76 333	97.86 265	82.17 364	93.53 266	96.04 329	86.13 247	99.13 184	89.24 317	95.87 217	98.10 211

PEN-MVS		94.42 248	93.73 259	96.49 235	96.28 309	94.84 198	99.17 45	99.00 32	93.51 219	92.23 307	97.83 219	86.10 248	97.90 321	92.55 256	86.92 339	96.74 272

v1240		94.06 272	93.29 277	96.34 249	96.03 320	93.90 236	98.44 188	98.17 223	91.18 304	94.13 243	97.01 287	86.05 249	98.42 271	89.13 319	89.50 308	96.70 279

CostFormer		94.95 215	94.73 199	95.60 280	97.28 250	89.06 330	97.53 277	96.89 329	89.66 328	96.82 160	96.72 306	86.05 249	98.95 216	95.53 165	96.13 215	98.79 173

ACMM	93.85 9	95.69 171	95.38 165	96.61 219	97.61 225	93.84 238	98.91 96	98.44 171	95.25 137	94.28 234	98.47 154	86.04 251	99.12 186	95.50 166	93.95 240	96.87 258
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SDMVSNet		96.85 114	96.42 119	98.14 111	99.30 66	96.38 124	99.21 38	99.23 14	95.92 100	95.96 192	98.76 126	85.88 252	99.44 157	97.93 54	95.59 219	98.60 189

DTE-MVSNet		93.98 274	93.26 278	96.14 257	96.06 318	94.39 220	99.20 40	98.86 67	93.06 238	91.78 313	97.81 221	85.87 253	97.58 335	90.53 294	86.17 344	96.46 314

bld_raw_dy_0_64		95.74 166	95.31 172	97.03 186	96.35 306	95.76 159	99.12 53	97.37 303	95.97 98	94.70 215	98.48 152	85.80 254	98.49 261	96.55 129	93.48 253	96.84 263

VPA-MVSNet		95.75 165	95.11 182	97.69 146	97.24 252	97.27 80	98.94 92	99.23 14	95.13 142	95.51 198	97.32 257	85.73 255	98.91 219	97.33 96	89.55 306	96.89 255

EPMVS		94.99 211	94.48 210	96.52 233	97.22 254	91.75 285	97.23 298	91.66 376	94.11 181	97.28 138	96.81 303	85.70 256	98.84 229	93.04 240	97.28 182	98.97 160

TransMVSNet (Re)		92.67 295	91.51 300	96.15 256	96.58 294	94.65 205	98.90 97	96.73 334	90.86 308	89.46 335	97.86 213	85.62 257	98.09 308	86.45 335	81.12 358	95.71 335

AUN-MVS		94.53 239	93.73 259	96.92 197	98.50 153	93.52 252	98.34 196	98.10 236	93.83 198	95.94 194	97.98 204	85.59 258	99.03 200	94.35 199	80.94 360	98.22 207

iter_conf05		96.13 146	95.79 144	97.15 178	98.16 190	95.99 139	98.88 104	97.98 254	95.91 102	95.58 197	98.46 156	85.53 259	98.59 251	97.88 59	93.75 245	96.86 261

dp		94.15 264	93.90 245	94.90 300	97.31 249	86.82 355	96.97 316	97.19 312	91.22 302	96.02 189	96.61 313	85.51 260	99.02 203	90.00 304	94.30 226	98.85 169

LPG-MVS_test		95.62 174	95.34 167	96.47 238	97.46 238	93.54 249	98.99 81	98.54 148	94.67 164	94.36 230	98.77 122	85.39 261	99.11 188	95.71 158	94.15 233	96.76 270

LGP-MVS_train				96.47 238	97.46 238	93.54 249		98.54 148	94.67 164	94.36 230	98.77 122	85.39 261	99.11 188	95.71 158	94.15 233	96.76 270

PS-CasMVS		94.67 229	93.99 239	96.71 207	96.68 289	95.26 178	99.13 52	99.03 30	93.68 211	92.33 305	97.95 206	85.35 263	98.10 306	93.59 225	88.16 325	96.79 267

ab-mvs		96.42 131	95.71 152	98.55 75	98.63 145	96.75 102	97.88 250	98.74 100	93.84 196	96.54 174	98.18 188	85.34 264	99.75 99	95.93 149	96.35 203	99.15 140

N_pmnet		87.12 332	87.77 330	85.17 352	95.46 337	61.92 383	97.37 287	70.66 389	85.83 353	88.73 342	96.04 329	85.33 265	97.76 329	80.02 361	90.48 292	95.84 332

FE-MVS		95.62 174	94.90 192	97.78 136	98.37 163	94.92 195	97.17 306	97.38 302	90.95 307	97.73 122	97.70 228	85.32 266	99.63 124	91.18 283	98.33 152	98.79 173

dmvs_testset		87.64 329	88.93 322	83.79 354	95.25 341	63.36 382	97.20 301	91.17 377	93.07 237	85.64 358	95.98 331	85.30 267	91.52 377	69.42 375	87.33 333	96.49 310

OPM-MVS		95.69 171	95.33 169	96.76 205	96.16 315	94.63 207	98.43 190	98.39 181	96.64 71	95.02 206	98.78 120	85.15 268	99.05 196	95.21 176	94.20 230	96.60 290
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-RMVSNet		95.92 157	95.32 170	97.69 146	98.32 174	94.64 206	98.19 218	97.45 296	94.56 167	96.03 188	98.61 138	85.02 269	99.12 186	90.68 293	99.06 112	99.30 117

DSMNet-mixed		92.52 297	92.58 289	92.33 337	94.15 353	82.65 364	98.30 204	94.26 365	89.08 336	92.65 295	95.73 335	85.01 270	95.76 361	86.24 336	97.76 171	98.59 191

tfpnnormal		93.66 277	92.70 287	96.55 231	96.94 273	95.94 148	98.97 84	99.19 18	91.04 305	91.38 317	97.34 255	84.94 271	98.61 248	85.45 343	89.02 316	95.11 345

LTVRE_ROB	92.95 15	94.60 232	93.90 245	96.68 211	97.41 246	94.42 218	98.52 176	98.59 135	91.69 284	91.21 318	98.35 168	84.87 272	99.04 199	91.06 286	93.44 257	96.60 290
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
XXY-MVS		95.20 200	94.45 214	97.46 159	96.75 285	96.56 113	98.86 110	98.65 127	93.30 229	93.27 276	98.27 180	84.85 273	98.87 226	94.82 183	91.26 285	96.96 244

thisisatest0515		95.61 177	94.89 193	97.76 139	98.15 191	95.15 183	96.77 332	94.41 362	92.95 243	97.18 142	97.43 252	84.78 274	99.45 156	94.63 188	97.73 173	98.68 182

CL-MVSNet_self_test		90.11 316	89.14 319	93.02 333	91.86 365	88.23 346	96.51 341	98.07 243	90.49 311	90.49 326	94.41 348	84.75 275	95.34 364	80.79 360	74.95 371	95.50 338

test_cas_vis1_n_1920		97.38 91	97.36 79	97.45 160	98.95 116	93.25 263	99.00 78	98.53 150	97.70 13	99.77 3	99.35 34	84.71 276	99.85 53	98.57 17	99.66 56	99.26 123

AllTest		95.24 197	94.65 202	96.99 188	99.25 78	93.21 265	98.59 165	98.18 218	91.36 292	93.52 267	98.77 122	84.67 277	99.72 103	89.70 309	97.87 166	98.02 213

TestCases				96.99 188	99.25 78	93.21 265		98.18 218	91.36 292	93.52 267	98.77 122	84.67 277	99.72 103	89.70 309	97.87 166	98.02 213

thres200		95.25 196	94.57 205	97.28 171	98.81 128	94.92 195	98.20 215	97.11 313	95.24 139	96.54 174	96.22 325	84.58 279	99.53 143	87.93 328	96.50 200	97.39 229

pm-mvs1		93.94 275	93.06 280	96.59 222	96.49 299	95.16 181	98.95 90	98.03 251	92.32 266	91.08 320	97.84 216	84.54 280	98.41 279	92.16 263	86.13 346	96.19 325

ACMP	93.49 10	95.34 192	94.98 188	96.43 243	97.67 221	93.48 253	98.73 140	98.44 171	94.94 156	92.53 299	98.53 147	84.50 281	99.14 183	95.48 167	94.00 238	96.66 285
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thres100view900		95.38 187	94.70 200	97.41 164	98.98 114	94.92 195	98.87 108	96.90 327	95.38 128	96.61 168	96.88 298	84.29 282	99.56 135	88.11 324	96.29 206	97.76 218

thres600view7		95.49 178	94.77 196	97.67 148	98.98 114	95.02 187	98.85 111	96.90 327	95.38 128	96.63 167	96.90 297	84.29 282	99.59 130	88.65 323	96.33 204	98.40 199

dmvs_re		94.48 244	94.18 226	95.37 287	97.68 220	90.11 314	98.54 175	97.08 314	94.56 167	94.42 227	97.24 263	84.25 284	97.76 329	91.02 289	92.83 267	98.24 205

FMVSNet3		94.97 214	94.26 221	97.11 182	98.18 187	96.62 106	98.56 173	98.26 207	93.67 213	94.09 244	97.10 270	84.25 284	98.01 313	92.08 265	92.14 272	96.70 279

tfpn200view9		95.32 194	94.62 203	97.43 162	98.94 117	94.98 191	98.68 152	96.93 325	95.33 131	96.55 172	96.53 314	84.23 286	99.56 135	88.11 324	96.29 206	97.76 218

thres400		95.38 187	94.62 203	97.65 152	98.94 117	94.98 191	98.68 152	96.93 325	95.33 131	96.55 172	96.53 314	84.23 286	99.56 135	88.11 324	96.29 206	98.40 199

cascas		94.63 231	93.86 248	96.93 194	96.91 276	94.27 225	96.00 348	98.51 155	85.55 355	94.54 218	96.23 323	84.20 288	98.87 226	95.80 155	96.98 187	97.66 224

tpm		94.13 265	93.80 252	95.12 293	96.50 298	87.91 349	97.44 280	95.89 349	92.62 253	96.37 181	96.30 320	84.13 289	98.30 292	93.24 233	91.66 280	99.14 142

tttt0517		96.07 147	95.51 160	97.78 136	98.41 160	94.84 198	99.28 24	94.33 364	94.26 179	97.64 130	98.64 136	84.05 290	99.47 154	95.34 168	97.60 177	99.03 154

IterMVS		94.09 269	93.85 249	94.80 305	97.99 201	90.35 310	97.18 304	98.12 230	93.68 211	92.46 303	97.34 255	84.05 290	97.41 340	92.51 258	91.33 282	96.62 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		94.11 267	93.87 247	94.85 302	97.98 203	90.56 307	97.18 304	98.11 233	93.75 201	92.58 297	97.48 247	83.97 292	97.41 340	92.48 260	91.30 283	96.58 292

SCA		95.46 180	95.13 179	96.46 241	97.67 221	91.29 294	97.33 292	97.60 278	94.68 163	96.92 155	97.10 270	83.97 292	98.89 223	92.59 253	98.32 154	99.20 129

TR-MVS		94.94 217	94.20 223	97.17 177	97.75 214	94.14 231	97.59 274	97.02 321	92.28 268	95.75 195	97.64 236	83.88 294	98.96 211	89.77 306	96.15 214	98.40 199

jajsoiax		95.45 182	95.03 185	96.73 206	95.42 340	94.63 207	99.14 49	98.52 153	95.74 110	93.22 277	98.36 167	83.87 295	98.65 246	96.95 108	94.04 236	96.91 252

Anonymous20231206		91.66 302	91.10 302	93.33 328	94.02 357	87.35 352	98.58 167	97.26 309	90.48 312	90.16 328	96.31 319	83.83 296	96.53 356	79.36 364	89.90 300	96.12 326

thisisatest0530		96.01 149	95.36 166	97.97 124	98.38 161	95.52 168	98.88 104	94.19 366	94.04 184	97.64 130	98.31 175	83.82 297	99.46 155	95.29 172	97.70 174	98.93 165

tpm2		94.19 261	93.76 257	95.46 284	97.23 253	89.04 331	97.31 294	96.85 333	87.08 345	96.21 184	96.79 304	83.75 298	98.74 238	92.43 261	96.23 212	98.59 191

mvs_tets		95.41 186	95.00 186	96.65 212	95.58 333	94.42 218	99.00 78	98.55 146	95.73 112	93.21 278	98.38 165	83.45 299	98.63 247	97.09 102	94.00 238	96.91 252

OurMVSNet-221017-0		94.21 259	94.00 237	94.85 302	95.60 332	89.22 328	98.89 101	97.43 298	95.29 134	92.18 308	98.52 150	82.86 300	98.59 251	93.46 228	91.76 277	96.74 272

sd_testset		96.17 143	95.76 147	97.42 163	99.30 66	94.34 223	98.82 117	99.08 25	95.92 100	95.96 192	98.76 126	82.83 301	99.32 164	95.56 163	95.59 219	98.60 189

UGNet		96.78 117	96.30 125	98.19 110	98.24 177	95.89 155	98.88 104	98.93 42	97.39 29	96.81 161	97.84 216	82.60 302	99.90 37	96.53 130	99.49 88	98.79 173
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
pmmvs5		93.65 279	92.97 282	95.68 276	95.49 336	92.37 275	98.20 215	97.28 307	89.66 328	92.58 297	97.26 260	82.14 303	98.09 308	93.18 236	90.95 289	96.58 292

ACMH	92.88 16	94.55 236	93.95 241	96.34 249	97.63 224	93.26 262	98.81 124	98.49 165	93.43 223	89.74 331	98.53 147	81.91 304	99.08 194	93.69 220	93.30 260	96.70 279
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ITE_SJBPF				95.44 285	97.42 243	91.32 293		97.50 291	95.09 147	93.59 263	98.35 168	81.70 305	98.88 225	89.71 308	93.39 258	96.12 326

Anonymous20231211		94.10 268	93.26 278	96.61 219	99.11 100	94.28 224	99.01 76	98.88 54	86.43 348	92.81 289	97.57 242	81.66 306	98.68 244	94.83 182	89.02 316	96.88 256

test1111		95.94 155	95.78 145	96.41 244	98.99 113	90.12 313	99.04 68	92.45 374	96.99 56	98.03 99	99.27 46	81.40 307	99.48 152	96.87 118	99.04 113	99.63 67

ECVR-MVS		95.95 153	95.71 152	96.65 212	99.02 106	90.86 299	99.03 71	91.80 375	96.96 57	98.10 93	99.26 47	81.31 308	99.51 147	96.90 112	99.04 113	99.59 73

GBi-Net		94.49 242	93.80 252	96.56 226	98.21 181	95.00 188	98.82 117	98.18 218	92.46 257	94.09 244	97.07 277	81.16 309	97.95 317	92.08 265	92.14 272	96.72 275

test1		94.49 242	93.80 252	96.56 226	98.21 181	95.00 188	98.82 117	98.18 218	92.46 257	94.09 244	97.07 277	81.16 309	97.95 317	92.08 265	92.14 272	96.72 275

FMVSNet2		94.47 245	93.61 265	97.04 185	98.21 181	96.43 120	98.79 130	98.27 203	92.46 257	93.50 270	97.09 274	81.16 309	98.00 315	91.09 284	91.93 275	96.70 279

GA-MVS		94.81 220	94.03 233	97.14 179	97.15 262	93.86 237	96.76 333	97.58 279	94.00 188	94.76 214	97.04 283	80.91 312	98.48 262	91.79 274	96.25 211	99.09 147

SixPastTwentyTwo		93.34 284	92.86 283	94.75 306	95.67 330	89.41 326	98.75 133	96.67 338	93.89 193	90.15 329	98.25 183	80.87 313	98.27 297	90.90 290	90.64 291	96.57 294

ACMH+	92.99 14	94.30 254	93.77 255	95.88 270	97.81 211	92.04 281	98.71 145	98.37 185	93.99 189	90.60 325	98.47 154	80.86 314	99.05 196	92.75 249	92.40 271	96.55 298

gg-mvs-nofinetune		92.21 299	90.58 307	97.13 180	96.75 285	95.09 185	95.85 349	89.40 381	85.43 356	94.50 220	81.98 374	80.80 315	98.40 285	92.16 263	98.33 152	97.88 215

test20.03		90.89 311	90.38 309	92.43 336	93.48 359	88.14 347	98.33 197	97.56 281	93.40 224	87.96 344	96.71 307	80.69 316	94.13 370	79.15 365	86.17 344	95.01 349

VPNet		94.99 211	94.19 224	97.40 166	97.16 261	96.57 112	98.71 145	98.97 35	95.67 115	94.84 209	98.24 184	80.36 317	98.67 245	96.46 132	87.32 334	96.96 244

test_fmvs1		96.42 131	96.67 111	95.66 277	98.82 127	88.53 340	98.80 125	98.20 213	96.39 83	99.64 10	99.20 57	80.35 318	99.67 116	99.04 7	99.57 74	98.78 176

GG-mvs-BLEND				96.59 222	96.34 307	94.98 191	96.51 341	88.58 382		93.10 284	94.34 352	80.34 319	98.05 311	89.53 312	96.99 186	96.74 272

KD-MVS_self_test		90.38 314	89.38 317	93.40 327	92.85 362	88.94 334	97.95 241	97.94 259	90.35 317	90.25 327	93.96 353	79.82 320	95.94 360	84.62 350	76.69 369	95.33 340

PVSNet_0	88.72 19	91.28 306	90.03 312	95.00 297	97.99 201	87.29 353	94.84 360	98.50 160	92.06 274	89.86 330	95.19 342	79.81 321	99.39 159	92.27 262	69.79 374	98.33 203

MS-PatchMatch		93.84 276	93.63 264	94.46 316	96.18 312	89.45 324	97.76 260	98.27 203	92.23 269	92.13 309	97.49 246	79.50 322	98.69 241	89.75 307	99.38 101	95.25 341

MVS-HIRNet		89.46 323	88.40 323	92.64 335	97.58 227	82.15 365	94.16 368	93.05 373	75.73 370	90.90 321	82.52 373	79.42 323	98.33 287	83.53 353	98.68 130	97.43 226

MDA-MVSNet-bldmvs		89.97 318	88.35 324	94.83 304	95.21 342	91.34 292	97.64 270	97.51 290	88.36 340	71.17 375	96.13 327	79.22 324	96.63 355	83.65 352	86.27 343	96.52 304

XVG-ACMP-BASELINE		94.54 237	94.14 229	95.75 275	96.55 295	91.65 288	98.11 228	98.44 171	94.96 153	94.22 238	97.90 209	79.18 325	99.11 188	94.05 212	93.85 242	96.48 312

Anonymous20240529		95.10 205	94.22 222	97.75 140	99.01 108	94.26 226	98.87 108	98.83 72	85.79 354	96.64 166	98.97 95	78.73 326	99.85 53	96.27 137	94.89 224	99.12 144

TESTMET0.1,1		94.18 263	93.69 262	95.63 278	96.92 274	89.12 329	96.91 321	94.78 359	93.17 234	94.88 208	96.45 317	78.52 327	98.92 218	93.09 237	98.50 142	98.85 169

test_vis1_n_1920		96.71 119	96.84 100	96.31 251	99.11 100	89.74 318	99.05 65	98.58 140	98.08 6	99.87 1	99.37 28	78.48 328	99.93 21	99.29 4	99.69 52	99.27 121

pmmvs-eth3d		90.36 315	89.05 320	94.32 318	91.10 368	92.12 277	97.63 273	96.95 324	88.86 337	84.91 361	93.13 360	78.32 329	96.74 350	88.70 322	81.81 356	94.09 358

KD-MVS_2432*1600		89.61 321	87.96 328	94.54 311	94.06 355	91.59 289	95.59 353	97.63 276	89.87 324	88.95 338	94.38 350	78.28 330	96.82 348	84.83 346	68.05 375	95.21 342

miper_refine_blended		89.61 321	87.96 328	94.54 311	94.06 355	91.59 289	95.59 353	97.63 276	89.87 324	88.95 338	94.38 350	78.28 330	96.82 348	84.83 346	68.05 375	95.21 342

Anonymous202405211		95.28 195	94.49 209	97.67 148	99.00 109	93.75 242	98.70 149	97.04 318	90.66 309	96.49 176	98.80 118	78.13 332	99.83 59	96.21 141	95.36 223	99.44 100

IB-MVS	91.98 17	93.27 286	91.97 296	97.19 175	97.47 237	93.41 256	97.09 311	95.99 345	93.32 227	92.47 302	95.73 335	78.06 333	99.53 143	94.59 193	82.98 352	98.62 188
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
LF4IMVS		93.14 291	92.79 285	94.20 319	95.88 325	88.67 337	97.66 268	97.07 316	93.81 199	91.71 314	97.65 234	77.96 334	98.81 233	91.47 280	91.92 276	95.12 344

test-mter		94.08 270	93.51 270	95.80 272	96.77 282	89.70 319	96.91 321	95.21 354	92.89 245	94.83 211	95.72 337	77.69 335	98.97 207	93.06 238	98.50 142	98.72 178

USDC		93.33 285	92.71 286	95.21 290	96.83 281	90.83 301	96.91 321	97.50 291	93.84 196	90.72 323	98.14 190	77.69 335	98.82 232	89.51 313	93.21 262	95.97 330

test_0402		91.32 304	90.27 310	94.48 314	96.60 292	91.12 296	98.50 181	97.22 311	86.10 351	88.30 343	96.98 289	77.65 337	97.99 316	78.13 368	92.94 265	94.34 352

K. test v3		92.55 296	91.91 298	94.48 314	95.64 331	89.24 327	99.07 62	94.88 358	94.04 184	86.78 350	97.59 240	77.64 338	97.64 332	92.08 265	89.43 309	96.57 294

TDRefinement		91.06 309	89.68 314	95.21 290	85.35 379	91.49 291	98.51 180	97.07 316	91.47 288	88.83 341	97.84 216	77.31 339	99.09 193	92.79 248	77.98 367	95.04 347

test2506		94.44 247	93.91 244	96.04 260	99.02 106	88.99 333	99.06 63	79.47 388	96.96 57	98.36 84	99.26 47	77.21 340	99.52 146	96.78 124	99.04 113	99.59 73

new_pmnet		90.06 317	89.00 321	93.22 331	94.18 352	88.32 344	96.42 343	96.89 329	86.19 349	85.67 357	93.62 355	77.18 341	97.10 344	81.61 358	89.29 311	94.23 354

Anonymous20240521		91.18 307	90.44 308	93.42 325	93.70 358	88.47 341	98.94 92	97.56 281	88.46 339	89.56 334	95.08 345	77.15 342	96.97 346	83.92 351	89.55 306	94.82 350

tt0805		94.54 237	93.85 249	96.63 216	97.98 203	93.06 270	98.77 132	97.84 266	93.67 213	93.80 259	98.04 197	76.88 343	98.96 211	94.79 185	92.86 266	97.86 217

new-patchmatchnet		88.50 326	87.45 331	91.67 341	90.31 370	85.89 357	97.16 308	97.33 304	89.47 330	83.63 363	92.77 362	76.38 344	95.06 367	82.70 355	77.29 368	94.06 360

lessismore_v0				94.45 317	94.93 346	88.44 342		91.03 378		86.77 351	97.64 236	76.23 345	98.42 271	90.31 297	85.64 347	96.51 307

TinyColmap		92.31 298	91.53 299	94.65 309	96.92 274	89.75 317	96.92 319	96.68 337	90.45 314	89.62 332	97.85 215	76.06 346	98.81 233	86.74 333	92.51 270	95.41 339

pmmvs6		91.77 301	90.63 306	95.17 292	94.69 351	91.24 295	98.67 155	97.92 261	86.14 350	89.62 332	97.56 244	75.79 347	98.34 286	90.75 292	84.56 348	95.94 331

MIMVSNet		93.26 287	92.21 294	96.41 244	97.73 218	93.13 267	95.65 352	97.03 319	91.27 300	94.04 247	96.06 328	75.33 348	97.19 343	86.56 334	96.23 212	98.92 166

UnsupCasMVSNet_eth		90.99 310	89.92 313	94.19 320	94.08 354	89.83 316	97.13 310	98.67 120	93.69 209	85.83 356	96.19 326	75.15 349	96.74 350	89.14 318	79.41 363	96.00 329

LFMVS		95.86 160	94.98 188	98.47 85	98.87 122	96.32 128	98.84 114	96.02 344	93.40 224	98.62 69	99.20 57	74.99 350	99.63 124	97.72 70	97.20 183	99.46 97

CMPMVS	66.06 21	89.70 319	89.67 315	89.78 344	93.19 360	76.56 369	97.00 315	98.35 188	80.97 365	81.57 365	97.75 224	74.75 351	98.61 248	89.85 305	93.63 250	94.17 356
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		91.81 300	90.92 303	94.49 313	97.21 255	92.09 278	98.00 238	97.55 286	89.31 334	90.86 322	95.61 340	74.48 352	95.32 365	85.57 341	89.70 302	96.07 328

testgi		93.06 292	92.45 291	94.88 301	96.43 303	89.90 315	98.75 133	97.54 287	95.60 117	91.63 316	97.91 208	74.46 353	97.02 345	86.10 337	93.67 247	97.72 222

VDD-MVS		95.82 163	95.23 175	97.61 154	98.84 126	93.98 234	98.68 152	97.40 300	95.02 150	97.95 107	99.34 38	74.37 354	99.78 91	98.64 15	96.80 189	99.08 151

test_fmvs1_n		95.90 158	95.99 138	95.63 278	98.67 141	88.32 344	99.26 27	98.22 210	96.40 82	99.67 7	99.26 47	73.91 355	99.70 109	99.02 8	99.50 86	98.87 168

FMVSNet1		93.19 290	92.07 295	96.56 226	97.54 232	95.00 188	98.82 117	98.18 218	90.38 316	92.27 306	97.07 277	73.68 356	97.95 317	89.36 316	91.30 283	96.72 275

VDDNet		95.36 190	94.53 207	97.86 129	98.10 194	95.13 184	98.85 111	97.75 270	90.46 313	98.36 84	99.39 22	73.27 357	99.64 121	97.98 50	96.58 196	98.81 172

UniMVSNet_ETH3D		94.24 258	93.33 275	96.97 191	97.19 259	93.38 258	98.74 136	98.57 142	91.21 303	93.81 258	98.58 143	72.85 358	98.77 237	95.05 178	93.93 241	98.77 177

DeepMVS_CX				86.78 349	97.09 266	72.30 376		95.17 357	75.92 369	84.34 362	95.19 342	70.58 359	95.35 363	79.98 363	89.04 315	92.68 367

test_fmvs2		93.43 281	93.58 266	92.95 334	96.97 271	83.91 360	99.19 42	97.24 310	95.74 110	95.20 202	98.27 180	69.65 360	98.72 240	96.26 138	93.73 246	96.24 322

OpenMVS_ROB	86.42 20	89.00 324	87.43 332	93.69 323	93.08 361	89.42 325	97.91 245	96.89 329	78.58 367	85.86 355	94.69 347	69.48 361	98.29 295	77.13 369	93.29 261	93.36 364

EGC-MVSNET		75.22 343	69.54 346	92.28 338	94.81 348	89.58 322	97.64 270	96.50 341	1.82 386	5.57 387	95.74 333	68.21 362	96.26 359	73.80 372	91.71 278	90.99 368

EG-PatchMatch MVS		91.13 308	90.12 311	94.17 321	94.73 350	89.00 332	98.13 225	97.81 267	89.22 335	85.32 360	96.46 316	67.71 363	98.42 271	87.89 329	93.82 243	95.08 346

MIMVSNet1		89.67 320	88.28 325	93.82 322	92.81 363	91.08 297	98.01 236	97.45 296	87.95 341	87.90 345	95.87 332	67.63 364	94.56 369	78.73 367	88.18 324	95.83 333

test_vis1_n		95.47 179	95.13 179	96.49 235	97.77 213	90.41 309	99.27 26	98.11 233	96.58 73	99.66 8	99.18 63	67.00 365	99.62 127	99.21 5	99.40 99	99.44 100

pmmvs3		86.67 333	84.86 337	92.11 340	88.16 373	87.19 354	96.63 337	94.75 360	79.88 366	87.22 348	92.75 363	66.56 366	95.20 366	81.24 359	76.56 370	93.96 361

tmp_tt		68.90 345	66.97 347	74.68 362	50.78 389	59.95 385	87.13 374	83.47 385	38.80 382	62.21 378	96.23 323	64.70 367	76.91 384	88.91 321	30.49 382	87.19 373

UnsupCasMVSNet_bld		87.17 330	85.12 336	93.31 329	91.94 364	88.77 335	94.92 359	98.30 200	84.30 360	82.30 364	90.04 368	63.96 368	97.25 342	85.85 340	74.47 373	93.93 362

test_vis1_rt		91.29 305	90.65 305	93.19 332	97.45 241	86.25 356	98.57 172	90.90 379	93.30 229	86.94 349	93.59 356	62.07 369	99.11 188	97.48 90	95.58 221	94.22 355

APD_test1		88.22 327	88.01 327	88.86 346	95.98 321	74.66 375	97.21 300	96.44 342	83.96 361	86.66 352	97.90 209	60.95 370	97.84 327	82.73 354	90.23 296	94.09 358

test_method		79.03 336	78.17 338	81.63 358	86.06 378	54.40 388	82.75 377	96.89 329	39.54 381	80.98 366	95.57 341	58.37 371	94.73 368	84.74 349	78.61 364	95.75 334

mvsany_test3		88.80 325	88.04 326	91.09 343	89.78 371	81.57 367	97.83 256	95.49 351	93.81 199	87.53 346	93.95 354	56.14 372	97.43 339	94.68 186	83.13 351	94.26 353

PM-MVS		87.77 328	86.55 334	91.40 342	91.03 369	83.36 363	96.92 319	95.18 356	91.28 299	86.48 354	93.42 357	53.27 373	96.74 350	89.43 315	81.97 355	94.11 357

ambc				89.49 345	86.66 376	75.78 370	92.66 370	96.72 335		86.55 353	92.50 364	46.01 374	97.90 321	90.32 296	82.09 353	94.80 351

Gipuma		78.40 340	76.75 343	83.38 355	95.54 334	80.43 368	79.42 378	97.40 300	64.67 375	73.46 372	80.82 376	45.65 375	93.14 374	66.32 377	87.43 331	76.56 378
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvs3		87.17 330	87.06 333	87.50 348	91.21 367	75.66 371	99.05 65	96.61 340	92.79 249	88.85 340	92.78 361	43.72 376	93.49 371	93.95 213	84.56 348	93.34 365

EMVS		64.07 348	63.26 351	66.53 365	81.73 382	58.81 387	91.85 371	84.75 384	51.93 380	59.09 380	75.13 379	43.32 377	79.09 383	42.03 382	39.47 380	61.69 379

test_f		86.07 334	85.39 335	88.10 347	89.28 372	75.57 372	97.73 263	96.33 343	89.41 333	85.35 359	91.56 367	43.31 378	95.53 362	91.32 282	84.23 350	93.21 366

E-PMN		64.94 347	64.25 349	67.02 364	82.28 381	59.36 386	91.83 372	85.63 383	52.69 378	60.22 379	77.28 378	41.06 379	80.12 382	46.15 381	41.14 379	61.57 380

FPMVS		77.62 342	77.14 342	79.05 360	79.25 383	60.97 384	95.79 350	95.94 347	65.96 374	67.93 376	94.40 349	37.73 380	88.88 379	68.83 376	88.46 321	87.29 372

PMMVS2		77.95 341	75.44 345	85.46 351	82.54 380	74.95 373	94.23 367	93.08 372	72.80 371	74.68 369	87.38 370	36.36 381	91.56 376	73.95 371	63.94 377	89.87 369

testf1		79.02 337	77.70 339	82.99 356	88.10 374	66.90 379	94.67 362	93.11 370	71.08 372	74.02 370	93.41 358	34.15 382	93.25 372	72.25 373	78.50 365	88.82 370

APD_test2		79.02 337	77.70 339	82.99 356	88.10 374	66.90 379	94.67 362	93.11 370	71.08 372	74.02 370	93.41 358	34.15 382	93.25 372	72.25 373	78.50 365	88.82 370

LCM-MVSNet		78.70 339	76.24 344	86.08 350	77.26 385	71.99 377	94.34 366	96.72 335	61.62 376	76.53 368	89.33 369	33.91 384	92.78 375	81.85 357	74.60 372	93.46 363

ANet_high		69.08 344	65.37 348	80.22 359	65.99 387	71.96 378	90.91 373	90.09 380	82.62 362	49.93 382	78.39 377	29.36 385	81.75 380	62.49 378	38.52 381	86.95 374

test_vis3_rt		79.22 335	77.40 341	84.67 353	86.44 377	74.85 374	97.66 268	81.43 386	84.98 357	67.12 377	81.91 375	28.09 386	97.60 333	88.96 320	80.04 362	81.55 375

PMVS	61.03 23	65.95 346	63.57 350	73.09 363	57.90 388	51.22 389	85.05 376	93.93 369	54.45 377	44.32 383	83.57 372	13.22 387	89.15 378	58.68 379	81.00 359	78.91 377
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		20.95 353	23.72 356	12.64 367	13.54 391	8.19 391	96.55 340	6.13 392	7.48 385	16.74 385	37.98 383	12.97 388	6.05 386	16.69 384	5.43 385	23.68 381

wuyk23d		30.17 350	30.18 354	30.16 366	78.61 384	43.29 390	66.79 379	14.21 390	17.31 383	14.82 386	11.93 386	11.55 389	41.43 385	37.08 383	19.30 383	5.76 383

MVE	62.14 22	63.28 349	59.38 352	74.99 361	74.33 386	65.47 381	85.55 375	80.50 387	52.02 379	51.10 381	75.00 380	10.91 390	80.50 381	51.60 380	53.40 378	78.99 376
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		21.48 352	24.95 355	11.09 368	14.89 390	6.47 392	96.56 339	9.87 391	7.55 384	17.93 384	39.02 382	9.43 391	5.90 387	16.56 385	12.72 384	20.91 382

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		8.20 354	10.94 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	98.43 158	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

FOURS1					99.82 1	98.66 24	99.69 1	98.95 38	97.46 25	99.39 22

MSC_two_6792asdad				99.62 6	99.17 91	99.08 11		98.63 130					99.94 5	98.53 20	99.80 19	99.86 3

No_MVS				99.62 6	99.17 91	99.08 11		98.63 130					99.94 5	98.53 20	99.80 19	99.86 3

eth-test2					0.00 392

eth-test					0.00 392

IU-MVS					99.71 19	99.23 7		98.64 128	95.28 135	99.63 11				98.35 37	99.81 12	99.83 8

save fliter					99.46 49	98.38 35	98.21 213	98.71 108	97.95 7

test_0728_SECOND				99.71 1	99.72 12	99.35 1	98.97 84	98.88 54					99.94 5	98.47 28	99.81 12	99.84 7

GSMVS																99.20 129

test_part2					99.63 29	99.18 10				99.27 27

MTGPA								98.74 100

MTMP							98.89 101	94.14 367

gm-plane-assit					95.88 325	87.47 351			89.74 327		96.94 295		99.19 176	93.32 232

test9_res														96.39 136	99.57 74	99.69 50

agg_prior2														95.87 152	99.57 74	99.68 55

agg_prior					99.30 66	98.38 35		98.72 105		97.57 134			99.81 71

test_prior4						98.01 58	97.86 252

test_prior				99.19 39	99.31 62	98.22 47		98.84 71					99.70 109			99.65 63

旧先验2							97.57 276		91.30 297	98.67 63			99.80 78	95.70 160

新几何2							97.64 270

无先验							97.58 275	98.72 105	91.38 291				99.87 48	93.36 231		99.60 71

原ACMM2							97.67 267

testdata2													99.89 39	91.65 278

testdata1							97.32 293		96.34 85

plane_prior7					97.42 243	94.63 207

plane_prior5								98.56 144					99.03 200	96.07 142	94.27 227	96.92 247

plane_prior4											98.28 177

plane_prior3						94.61 210			97.02 54	95.34 199

plane_prior2							98.80 125		97.28 36

plane_prior1					97.37 247

plane_prior						94.60 212	98.44 188		96.74 67						94.22 229

n2								0.00 393

nn								0.00 393

door-mid								94.37 363

test11								98.66 123

door								94.64 361

HQP5-MVS						94.25 227

HQP-NCC					97.20 256		98.05 232		96.43 79	94.45 222

ACMP_Plane					97.20 256		98.05 232		96.43 79	94.45 222

BP-MVS														95.30 170

HQP4-MVS										94.45 222			98.96 211			96.87 258

HQP3-MVS								98.46 167							94.18 231

NP-MVS					97.28 250	94.51 215					97.73 225

ACMMP++_ref															92.97 264

ACMMP++															93.61 251

High-resolution multi-view benchmark