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.

AdaColmap		97.23 126	96.80 135	98.51 128	99.99 1	95.60 194	99.09 295	98.84 62	93.32 197	96.74 206	99.72 89	86.04 254	100.00 1	98.01 147	99.43 124	99.94 82

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 20	98.69 77	98.20 9	99.93 2	99.98 2	96.82 24	100.00 1	99.75 37	100.00 1	99.99 23

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 38	98.64 86	98.47 3	99.13 102	99.92 13	96.38 34	100.00 1	99.74 39	100.00 1	100.00 1

mPP-MVS		98.39 53	98.20 51	98.97 88	99.97 3	96.92 133	99.95 67	98.38 179	95.04 118	98.61 133	99.80 54	93.39 114	100.00 1	98.64 110	100.00 1	99.98 52

CPTT-MVS		97.64 106	97.32 110	98.58 117	99.97 3	95.77 183	99.96 48	98.35 185	89.90 327	98.36 148	99.79 58	91.18 173	99.99 36	98.37 126	99.99 21	99.99 23

DP-MVS Recon		98.41 50	98.02 65	99.56 25	99.97 3	98.70 48	99.92 94	98.44 143	92.06 260	98.40 147	99.84 44	95.68 44	100.00 1	98.19 136	99.71 88	99.97 62

PAPR		98.52 40	98.16 55	99.58 24	99.97 3	98.77 42	99.95 67	98.43 151	95.35 112	98.03 162	99.75 75	94.03 99	99.98 47	98.11 141	99.83 77	99.99 23

HFP-MVS		98.56 36	98.37 40	99.14 68	99.96 8	97.43 109	99.95 67	98.61 94	94.77 128	99.31 91	99.85 33	94.22 92	100.00 1	98.70 105	99.98 32	99.98 52

region2R		98.54 38	98.37 40	99.05 78	99.96 8	97.18 119	99.96 48	98.55 114	94.87 125	99.45 78	99.85 33	94.07 98	100.00 1	98.67 107	100.00 1	99.98 52

ACMMPR		98.50 41	98.32 44	99.05 78	99.96 8	97.18 119	99.95 67	98.60 96	94.77 128	99.31 91	99.84 44	93.73 108	100.00 1	98.70 105	99.98 32	99.98 52

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 38	98.62 93	98.02 21	99.90 6	99.95 3	97.33 17	100.00 1	99.54 54	100.00 1	100.00 1

CP-MVS		98.45 45	98.32 44	98.87 93	99.96 8	96.62 146	99.97 38	98.39 175	94.43 145	98.90 114	99.87 27	94.30 89	100.00 1	99.04 80	99.99 21	99.99 23

test_one_0601					99.94 13	99.30 12		98.41 168	96.63 72	99.75 39	99.93 11	97.49 10

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 67	98.43 151					100.00 1	99.99 5	100.00 1	100.00 1

XVS		98.70 29	98.55 28	99.15 66	99.94 13	97.50 105	99.94 84	98.42 163	96.22 89	99.41 83	99.78 62	94.34 86	99.96 71	98.92 90	99.95 50	99.99 23

X-MVStestdata		93.83 264	92.06 299	99.15 66	99.94 13	97.50 105	99.94 84	98.42 163	96.22 89	99.41 83	41.37 472	94.34 86	99.96 71	98.92 90	99.95 50	99.99 23

test_prior				99.43 36	99.94 13	98.49 61		98.65 83					99.80 137			99.99 23

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 62	99.98 20	98.86 56	97.10 52	99.80 25	99.94 4	95.92 40	100.00 1	99.51 55	100.00 1	100.00 1

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 102	98.39 175	97.20 50	99.46 77	99.85 33	95.53 48	99.79 139	99.86 23	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MP-MVS		98.23 68	97.97 69	99.03 80	99.94 13	97.17 122	99.95 67	98.39 175	94.70 132	98.26 154	99.81 53	91.84 164	100.00 1	98.85 96	99.97 42	99.93 83
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CDPH-MVS		98.65 32	98.36 42	99.49 32	99.94 13	98.73 46	99.87 124	98.33 190	93.97 170	99.76 38	99.87 27	94.99 64	99.75 148	98.55 114	100.00 1	99.98 52

PAPM_NR		98.12 72	97.93 75	98.70 104	99.94 13	96.13 172	99.82 153	98.43 151	94.56 136	97.52 179	99.70 95	94.40 81	99.98 47	97.00 184	99.98 32	99.99 23

MG-MVS		98.91 19	98.65 24	99.68 16	99.94 13	99.07 24	99.64 212	99.44 19	97.33 43	99.00 110	99.72 89	94.03 99	99.98 47	98.73 104	100.00 1	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 48	98.43 151	97.27 46	99.80 25	99.94 4	96.71 27	100.00 1	100.00 1	100.00 1	100.00 1

IU-MVS					99.93 24	99.31 10		98.41 168	97.71 30	99.84 20				100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 151	97.26 48	99.80 25	99.88 24	96.71 27	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 67	98.32 192	97.28 44	99.83 21	99.91 14	97.22 19	100.00 1	99.99 5	100.00 1	99.89 92
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					99.93 24	99.29 15	99.96 48	98.42 163	97.28 44	99.86 14	99.94 4	97.22 19

MSP-MVS		99.09 9	99.12 5	98.98 87	99.93 24	97.24 116	99.95 67	98.42 163	97.50 37	99.52 73	99.88 24	97.43 16	99.71 154	99.50 57	99.98 32	100.00 1
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
agg_prior					99.93 24	98.77 42		98.43 151		99.63 56			99.85 124

FOURS1					99.92 31	97.66 99	99.95 67	98.36 183	95.58 106	99.52 73

ZD-MVS					99.92 31	98.57 56		98.52 123	92.34 248	99.31 91	99.83 46	95.06 59	99.80 137	99.70 45	99.97 42

GST-MVS		98.27 60	97.97 69	99.17 61	99.92 31	97.57 101	99.93 91	98.39 175	94.04 168	98.80 119	99.74 82	92.98 130	100.00 1	98.16 138	99.76 85	99.93 83

TEST9					99.92 31	98.92 29	99.96 48	98.43 151	93.90 176	99.71 46	99.86 29	95.88 41	99.85 124

train_agg		98.88 20	98.65 24	99.59 23	99.92 31	98.92 29	99.96 48	98.43 151	94.35 150	99.71 46	99.86 29	95.94 38	99.85 124	99.69 46	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 48	98.43 151	94.35 150	99.69 48	99.85 33	95.94 38	99.85 124

PGM-MVS		98.34 55	98.13 57	98.99 85	99.92 31	97.00 129	99.75 176	99.50 17	93.90 176	99.37 88	99.76 67	93.24 123	100.00 1	97.75 166	99.96 46	99.98 52

ACMMP		97.74 99	97.44 103	98.66 108	99.92 31	96.13 172	99.18 288	99.45 18	94.84 126	96.41 219	99.71 92	91.40 167	99.99 36	97.99 149	98.03 184	99.87 95
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
DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 67	98.43 151	96.48 77	99.80 25	99.93 11	97.44 14	100.00 1	99.92 13	99.98 32	100.00 1

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 168					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 168					100.00 1	99.96 9	100.00 1	100.00 1

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 67	98.56 108	97.56 36	99.44 79	99.85 33	95.38 52	100.00 1	99.31 67	99.99 21	99.87 95

APD-MVS		98.62 33	98.35 43	99.41 39	99.90 42	98.51 59	99.87 124	98.36 183	94.08 163	99.74 42	99.73 86	94.08 97	99.74 150	99.42 63	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepC-MVS_fast	96.59 1	98.81 23	98.54 29	99.62 20	99.90 42	98.85 35	99.24 283	98.47 135	98.14 15	99.08 105	99.91 14	93.09 127	100.00 1	99.04 80	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 48				99.80 54	97.44 14	100.00 1	100.00 1	99.98 32	100.00 1

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 124	98.44 143	97.48 38	99.64 55	99.94 4	96.68 29	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
test_part2					99.89 45	99.25 18				99.49 76

CSCG		97.10 132	97.04 122	97.27 221	99.89 45	91.92 310	99.90 108	99.07 37	88.67 351	95.26 251	99.82 49	93.17 126	99.98 47	98.15 139	99.47 119	99.90 91

ZNCC-MVS		98.31 57	98.03 64	99.17 61	99.88 49	97.59 100	99.94 84	98.44 143	94.31 153	98.50 140	99.82 49	93.06 128	99.99 36	98.30 130	99.99 21	99.93 83

SR-MVS		98.46 44	98.30 47	98.93 91	99.88 49	97.04 128	99.84 143	98.35 185	94.92 122	99.32 90	99.80 54	93.35 116	99.78 141	99.30 68	99.95 50	99.96 70

9.14			98.38 38		99.87 51		99.91 102	98.33 190	93.22 200	99.78 36	99.89 22	94.57 77	99.85 124	99.84 25	99.97 42

SMA-MVS		98.76 26	98.48 32	99.62 20	99.87 51	98.87 33	99.86 135	98.38 179	93.19 201	99.77 37	99.94 4	95.54 46	100.00 1	99.74 39	99.99 21	100.00 1
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
NormalMVS		97.90 81	97.85 81	98.04 160	99.86 53	95.39 204	99.61 219	97.78 259	96.52 75	98.61 133	99.31 151	92.73 138	99.67 162	96.77 194	99.48 116	99.06 234

lecture		98.67 30	98.46 33	99.28 48	99.86 53	97.88 87	99.97 38	99.25 30	96.07 93	99.79 34	99.70 95	92.53 146	99.98 47	99.51 55	99.48 116	99.97 62

PHI-MVS		98.41 50	98.21 50	99.03 80	99.86 53	97.10 126	99.98 20	98.80 68	90.78 307	99.62 59	99.78 62	95.30 53	100.00 1	99.80 28	99.93 61	99.99 23

MTAPA		98.29 59	97.96 72	99.30 47	99.85 56	97.93 85	99.39 261	98.28 199	95.76 100	97.18 193	99.88 24	92.74 137	100.00 1	98.67 107	99.88 73	99.99 23

LS3D		95.84 196	95.11 209	98.02 161	99.85 56	95.10 222	98.74 345	98.50 132	87.22 373	93.66 272	99.86 29	87.45 231	99.95 80	90.94 310	99.81 83	99.02 238

HPM-MVS		97.96 76	97.72 86	98.68 105	99.84 58	96.39 158	99.90 108	98.17 214	92.61 233	98.62 132	99.57 125	91.87 163	99.67 162	98.87 95	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EI-MVSNet-Vis-set		98.27 60	98.11 59	98.75 101	99.83 59	96.59 150	99.40 257	98.51 126	95.29 114	98.51 139	99.76 67	93.60 112	99.71 154	98.53 117	99.52 109	99.95 78

save fliter					99.82 60	98.79 40	99.96 48	98.40 172	97.66 32

PLC	95.54 3	97.93 79	97.89 79	98.05 159	99.82 60	94.77 232	99.92 94	98.46 137	93.93 173	97.20 191	99.27 156	95.44 51	99.97 59	97.41 171	99.51 112	99.41 185
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
APD-MVS_3200maxsize		98.25 65	98.08 61	98.78 98	99.81 62	96.60 148	99.82 153	98.30 197	93.95 172	99.37 88	99.77 65	92.84 134	99.76 147	98.95 86	99.92 64	99.97 62

EI-MVSNet-UG-set		98.14 71	97.99 67	98.60 113	99.80 63	96.27 161	99.36 267	98.50 132	95.21 116	98.30 151	99.75 75	93.29 120	99.73 153	98.37 126	99.30 133	99.81 104

SR-MVS-dyc-post		98.31 57	98.17 54	98.71 103	99.79 64	96.37 159	99.76 172	98.31 194	94.43 145	99.40 85	99.75 75	93.28 121	99.78 141	98.90 93	99.92 64	99.97 62

RE-MVS-def			98.13 57		99.79 64	96.37 159	99.76 172	98.31 194	94.43 145	99.40 85	99.75 75	92.95 131		98.90 93	99.92 64	99.97 62

HPM-MVS_fast		97.80 93	97.50 99	98.68 105	99.79 64	96.42 154	99.88 121	98.16 219	91.75 271	98.94 112	99.54 128	91.82 165	99.65 166	97.62 169	99.99 21	99.99 23

SF-MVS		98.67 30	98.40 36	99.50 30	99.77 67	98.67 49	99.90 108	98.21 209	93.53 188	99.81 23	99.89 22	94.70 73	99.86 123	99.84 25	99.93 61	99.96 70

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 68	99.21 21	99.99 5	99.34 25	98.70 2	99.44 79	99.75 75	93.24 123	99.99 36	99.94 11	99.41 126	99.95 78

旧先验1					99.76 68	97.52 103		98.64 86			99.85 33	95.63 45			99.94 55	99.99 23

OMC-MVS		97.28 122	97.23 114	97.41 211	99.76 68	93.36 277	99.65 208	97.95 240	96.03 94	97.41 184	99.70 95	89.61 199	99.51 172	96.73 196	98.25 174	99.38 187

新几何1				99.42 38	99.75 71	98.27 66		98.63 92	92.69 228	99.55 68	99.82 49	94.40 81	100.00 1	91.21 302	99.94 55	99.99 23

MP-MVS-pluss		98.07 75	97.64 92	99.38 44	99.74 72	98.41 64	99.74 179	98.18 213	93.35 195	96.45 216	99.85 33	92.64 141	99.97 59	98.91 92	99.89 70	99.77 111
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TSAR-MVS + MP.		98.93 17	98.77 19	99.41 39	99.74 72	98.67 49	99.77 166	98.38 179	96.73 68	99.88 11	99.74 82	94.89 66	99.59 168	99.80 28	99.98 32	99.97 62
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test12				99.43 36	99.74 72	98.56 57		98.40 172		99.65 52		94.76 69	99.75 148		99.98 32	99.99 23

原ACMM1				98.96 89	99.73 75	96.99 130		98.51 126	94.06 166	99.62 59	99.85 33	94.97 65	99.96 71	95.11 223	99.95 50	99.92 88

TSAR-MVS + GP.		98.60 34	98.51 31	98.86 94	99.73 75	96.63 145	99.97 38	97.92 245	98.07 18	98.76 125	99.55 126	95.00 63	99.94 88	99.91 16	97.68 191	99.99 23

CANet		98.27 60	97.82 83	99.63 17	99.72 77	99.10 23	99.98 20	98.51 126	97.00 58	98.52 137	99.71 92	87.80 223	99.95 80	99.75 37	99.38 128	99.83 100

reproduce_model		98.75 27	98.66 23	99.03 80	99.71 78	97.10 126	99.73 186	98.23 207	97.02 57	99.18 100	99.90 18	94.54 78	99.99 36	99.77 33	99.90 69	99.99 23

F-COLMAP		96.93 144	96.95 125	96.87 234	99.71 78	91.74 315	99.85 138	97.95 240	93.11 207	95.72 240	99.16 173	92.35 152	99.94 88	95.32 219	99.35 131	98.92 246

reproduce-ours		98.78 24	98.67 21	99.09 75	99.70 80	97.30 113	99.74 179	98.25 203	97.10 52	99.10 103	99.90 18	94.59 74	99.99 36	99.77 33	99.91 67	99.99 23

our_new_method		98.78 24	98.67 21	99.09 75	99.70 80	97.30 113	99.74 179	98.25 203	97.10 52	99.10 103	99.90 18	94.59 74	99.99 36	99.77 33	99.91 67	99.99 23

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 80	98.73 46	99.94 84	98.34 189	96.38 83	99.81 23	99.76 67	94.59 74	99.98 47	99.84 25	99.96 46	99.97 62
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
patch_mono-2		98.24 66	99.12 5	95.59 275	99.67 83	86.91 398	99.95 67	98.89 52	97.60 33	99.90 6	99.76 67	96.54 32	99.98 47	99.94 11	99.82 81	99.88 93

ACMMP_NAP		98.49 42	98.14 56	99.54 27	99.66 84	98.62 55	99.85 138	98.37 182	94.68 133	99.53 71	99.83 46	92.87 133	100.00 1	98.66 109	99.84 76	99.99 23

DeepPCF-MVS	95.94 2	97.71 103	98.98 12	93.92 341	99.63 85	81.76 433	99.96 48	98.56 108	99.47 1	99.19 99	99.99 1	94.16 96	100.00 1	99.92 13	99.93 61	100.00 1

EPNet		98.49 42	98.40 36	98.77 100	99.62 86	96.80 139	99.90 108	99.51 16	97.60 33	99.20 97	99.36 146	93.71 109	99.91 105	97.99 149	98.71 159	99.61 142
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		98.83 21	98.53 30	99.76 10	99.59 87	99.33 8	99.99 5	99.76 6	98.39 4	99.39 87	99.80 54	90.49 188	99.96 71	99.89 18	99.43 124	99.98 52

PVSNet_BlendedMVS		96.05 187	95.82 182	96.72 240	99.59 87	96.99 130	99.95 67	99.10 34	94.06 166	98.27 152	95.80 346	89.00 211	99.95 80	99.12 74	87.53 338	93.24 400

PVSNet_Blended		97.94 78	97.64 92	98.83 95	99.59 87	96.99 130	100.00 1	99.10 34	95.38 111	98.27 152	99.08 177	89.00 211	99.95 80	99.12 74	99.25 135	99.57 153

PatchMatch-RL		96.04 188	95.40 196	97.95 163	99.59 87	95.22 217	99.52 239	99.07 37	93.96 171	96.49 215	98.35 261	82.28 299	99.82 136	90.15 326	99.22 138	98.81 253

dcpmvs_2		97.42 117	98.09 60	95.42 282	99.58 91	87.24 394	99.23 284	96.95 373	94.28 156	98.93 113	99.73 86	94.39 84	99.16 200	99.89 18	99.82 81	99.86 97

test222					99.55 92	97.41 111	99.34 269	98.55 114	91.86 266	99.27 95	99.83 46	93.84 106			99.95 50	99.99 23

CNLPA		97.76 97	97.38 106	98.92 92	99.53 93	96.84 135	99.87 124	98.14 223	93.78 180	96.55 213	99.69 99	92.28 154	99.98 47	97.13 179	99.44 123	99.93 83

API-MVS		97.86 84	97.66 90	98.47 130	99.52 94	95.41 202	99.47 249	98.87 55	91.68 272	98.84 116	99.85 33	92.34 153	99.99 36	98.44 122	99.96 46	100.00 1

PVSNet	91.05 13	97.13 131	96.69 141	98.45 132	99.52 94	95.81 181	99.95 67	99.65 12	94.73 130	99.04 108	99.21 166	84.48 282	99.95 80	94.92 229	98.74 158	99.58 151

114514_t		97.41 118	96.83 132	99.14 68	99.51 96	97.83 89	99.89 118	98.27 201	88.48 355	99.06 107	99.66 110	90.30 191	99.64 167	96.32 204	99.97 42	99.96 70

cl22		93.77 269	93.25 273	95.33 286	99.49 97	94.43 239	99.61 219	98.09 226	90.38 315	89.16 342	95.61 354	90.56 186	97.34 328	91.93 293	84.45 359	94.21 345

testdata				98.42 136	99.47 98	95.33 208		98.56 108	93.78 180	99.79 34	99.85 33	93.64 111	99.94 88	94.97 227	99.94 55	100.00 1

MAR-MVS		97.43 113	97.19 116	98.15 152	99.47 98	94.79 231	99.05 306	98.76 69	92.65 231	98.66 130	99.82 49	88.52 217	99.98 47	98.12 140	99.63 94	99.67 125
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
DP-MVS		94.54 241	93.42 263	97.91 169	99.46 100	94.04 254	98.93 324	97.48 296	81.15 427	90.04 313	99.55 126	87.02 239	99.95 80	88.97 338	98.11 180	99.73 115

MVS_111021_LR		98.42 49	98.38 38	98.53 125	99.39 101	95.79 182	99.87 124	99.86 2	96.70 69	98.78 120	99.79 58	92.03 160	99.90 107	99.17 73	99.86 75	99.88 93

CHOSEN 280x420		99.01 14	99.03 10	98.95 90	99.38 102	98.87 33	98.46 364	99.42 21	97.03 56	99.02 109	99.09 176	99.35 2	98.21 290	99.73 41	99.78 84	99.77 111

MVS_111021_HR		98.72 28	98.62 26	99.01 84	99.36 103	97.18 119	99.93 91	99.90 1	96.81 66	98.67 129	99.77 65	93.92 101	99.89 112	99.27 69	99.94 55	99.96 70

DPM-MVS		98.83 21	98.46 33	99.97 1	99.33 104	99.92 1	99.96 48	98.44 143	97.96 22	99.55 68	99.94 4	97.18 21	100.00 1	93.81 260	99.94 55	99.98 52

TAPA-MVS	92.12 8	94.42 249	93.60 255	96.90 233	99.33 104	91.78 314	99.78 162	98.00 234	89.89 328	94.52 257	99.47 132	91.97 161	99.18 197	69.90 444	99.52 109	99.73 115
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
reproduce_monomvs		95.38 213	95.07 211	96.32 255	99.32 106	96.60 148	99.76 172	98.85 59	96.65 71	87.83 364	96.05 343	99.52 1	98.11 295	96.58 199	81.07 388	94.25 340

fmvsm_s_conf0.5_n_9		98.15 70	98.02 65	98.55 119	99.28 107	95.84 180	99.99 5	98.57 102	98.17 12	99.93 2	99.74 82	87.04 238	99.97 59	99.86 23	99.59 103	99.83 100

SPE-MVS-test		97.88 82	97.94 74	97.70 186	99.28 107	95.20 218	99.98 20	97.15 340	95.53 108	99.62 59	99.79 58	92.08 159	98.38 273	98.75 103	99.28 134	99.52 165

test_fmvsm_n_1920		98.44 46	98.61 27	97.92 167	99.27 109	95.18 219	100.00 1	98.90 50	98.05 19	99.80 25	99.73 86	92.64 141	99.99 36	99.58 53	99.51 112	98.59 263

fmvsm_s_conf0.5_n_10		98.24 66	97.90 77	99.26 50	99.24 110	97.88 87	99.99 5	98.76 69	98.20 9	99.92 4	99.74 82	85.97 256	99.94 88	99.72 42	99.53 108	99.96 70

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 48	99.21 111	97.91 86	99.98 20	98.85 59	98.25 5	99.92 4	99.75 75	94.72 71	99.97 59	99.87 21	99.64 92	99.95 78

fmvsm_s_conf0.5_n_8		98.38 54	98.05 63	99.35 45	99.20 112	98.12 72	99.98 20	98.81 64	98.22 7	99.80 25	99.71 92	87.37 233	99.97 59	99.91 16	99.48 116	99.97 62

test_yl		97.83 88	97.37 107	99.21 55	99.18 113	97.98 81	99.64 212	99.27 27	91.43 281	97.88 169	98.99 187	95.84 42	99.84 132	98.82 97	95.32 265	99.79 107

DCV-MVSNet		97.83 88	97.37 107	99.21 55	99.18 113	97.98 81	99.64 212	99.27 27	91.43 281	97.88 169	98.99 187	95.84 42	99.84 132	98.82 97	95.32 265	99.79 107

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 51	99.17 115	97.81 91	99.98 20	98.86 56	98.25 5	99.90 6	99.76 67	94.21 94	99.97 59	99.87 21	99.52 109	99.98 52

DeepC-MVS	94.51 4	96.92 145	96.40 154	98.45 132	99.16 116	95.90 178	99.66 207	98.06 229	96.37 86	94.37 263	99.49 131	83.29 292	99.90 107	97.63 168	99.61 99	99.55 155
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DELS-MVS		98.54 38	98.22 49	99.50 30	99.15 117	98.65 53	100.00 1	98.58 100	97.70 31	98.21 157	99.24 162	92.58 144	99.94 88	98.63 112	99.94 55	99.92 88
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		98.41 50	98.08 61	99.39 41	99.12 118	98.29 65	99.98 20	98.64 86	98.14 15	99.86 14	99.76 67	87.99 222	99.97 59	99.72 42	99.54 106	99.91 90

fmvsm_l_conf0.5_n_9		98.55 37	98.23 48	99.49 32	99.10 119	98.50 60	99.99 5	98.70 75	98.14 15	99.94 1	99.68 106	89.02 210	99.98 47	99.89 18	99.61 99	99.99 23

CS-MVS		97.79 95	97.91 76	97.43 209	99.10 119	94.42 240	99.99 5	97.10 352	95.07 117	99.68 49	99.75 75	92.95 131	98.34 277	98.38 124	99.14 140	99.54 159

Anonymous202405211		93.10 287	91.99 300	96.40 251	99.10 119	89.65 364	98.88 330	97.93 242	83.71 411	94.00 269	98.75 223	68.79 405	99.88 118	95.08 224	91.71 298	99.68 123

fmvsm_s_conf0.5_n		97.80 93	97.85 81	97.67 187	99.06 122	94.41 241	99.98 20	98.97 43	97.34 41	99.63 56	99.69 99	87.27 234	99.97 59	99.62 51	99.06 145	98.62 262

HyFIR lowres test		96.66 160	96.43 152	97.36 216	99.05 123	93.91 259	99.70 198	99.80 3	90.54 311	96.26 222	98.08 274	92.15 157	98.23 289	96.84 193	95.46 260	99.93 83

LFMVS		94.75 235	93.56 258	98.30 142	99.03 124	95.70 188	98.74 345	97.98 237	87.81 366	98.47 141	99.39 143	67.43 414	99.53 169	98.01 147	95.20 268	99.67 125

fmvsm_s_conf0.5_n_4		97.75 98	97.86 80	97.42 210	99.01 125	94.69 234	99.97 38	98.76 69	97.91 24	99.87 12	99.76 67	86.70 245	99.93 98	99.67 48	99.12 143	97.64 291

fmvsm_s_conf0.5_n_2		97.59 108	97.28 111	98.53 125	99.01 125	98.15 67	99.98 20	98.59 98	98.17 12	99.75 39	99.63 116	81.83 305	99.94 88	99.78 31	98.79 156	97.51 299

AllTest		92.48 302	91.64 305	95.00 295	99.01 125	88.43 382	98.94 322	96.82 387	86.50 382	88.71 347	98.47 256	74.73 380	99.88 118	85.39 378	96.18 235	96.71 305

TestCases				95.00 295	99.01 125	88.43 382		96.82 387	86.50 382	88.71 347	98.47 256	74.73 380	99.88 118	85.39 378	96.18 235	96.71 305

COLMAP_ROB	90.47 14	92.18 309	91.49 311	94.25 329	99.00 129	88.04 388	98.42 370	96.70 394	82.30 422	88.43 356	99.01 184	76.97 355	99.85 124	86.11 374	96.50 227	94.86 316
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_3		97.95 77	97.66 90	98.81 96	98.99 130	98.07 75	99.98 20	98.81 64	98.18 11	99.89 9	99.70 95	84.15 285	99.97 59	99.76 36	99.50 114	98.39 270

test_fmvs1		95.35 214	95.68 188	94.36 325	98.99 130	84.98 409	99.96 48	96.65 396	97.60 33	99.73 44	98.96 193	71.58 395	99.93 98	98.31 129	99.37 129	98.17 275

HY-MVS	92.50 7	97.79 95	97.17 118	99.63 17	98.98 132	99.32 9	97.49 398	99.52 14	95.69 103	98.32 150	97.41 294	93.32 118	99.77 144	98.08 144	95.75 250	99.81 104

VNet		97.21 127	96.57 146	99.13 72	98.97 133	97.82 90	99.03 309	99.21 32	94.31 153	99.18 100	98.88 205	86.26 252	99.89 112	98.93 88	94.32 278	99.69 122

thres200		96.96 141	96.21 161	99.22 54	98.97 133	98.84 36	99.85 138	99.71 7	93.17 202	96.26 222	98.88 205	89.87 196	99.51 172	94.26 248	94.91 270	99.31 204

tfpn200view9		96.79 149	95.99 168	99.19 57	98.94 135	98.82 37	99.78 162	99.71 7	92.86 216	96.02 230	98.87 212	89.33 203	99.50 174	93.84 257	94.57 274	99.27 213

thres400		96.78 151	95.99 168	99.16 64	98.94 135	98.82 37	99.78 162	99.71 7	92.86 216	96.02 230	98.87 212	89.33 203	99.50 174	93.84 257	94.57 274	99.16 222

sasdasda		97.09 134	96.32 155	99.39 41	98.93 137	98.95 27	99.72 190	97.35 309	94.45 141	97.88 169	99.42 136	86.71 243	99.52 170	98.48 119	93.97 284	99.72 117

Anonymous20231211		89.86 359	88.44 367	94.13 332	98.93 137	90.68 342	98.54 361	98.26 202	76.28 439	86.73 378	95.54 358	70.60 401	97.56 321	90.82 313	80.27 397	94.15 353

canonicalmvs		97.09 134	96.32 155	99.39 41	98.93 137	98.95 27	99.72 190	97.35 309	94.45 141	97.88 169	99.42 136	86.71 243	99.52 170	98.48 119	93.97 284	99.72 117

SDMVSNet		94.80 230	93.96 245	97.33 219	98.92 140	95.42 201	99.59 224	98.99 40	92.41 244	92.55 287	97.85 285	75.81 370	98.93 215	97.90 155	91.62 299	97.64 291

sd_testset		93.55 276	92.83 280	95.74 273	98.92 140	90.89 338	98.24 377	98.85 59	92.41 244	92.55 287	97.85 285	71.07 400	98.68 243	93.93 254	91.62 299	97.64 291

EPNet_dtu		95.71 202	95.39 197	96.66 242	98.92 140	93.41 273	99.57 229	98.90 50	96.19 91	97.52 179	98.56 246	92.65 140	97.36 326	77.89 425	98.33 169	99.20 220
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
WTY-MVS		98.10 73	97.60 94	99.60 22	98.92 140	99.28 17	99.89 118	99.52 14	95.58 106	98.24 156	99.39 143	93.33 117	99.74 150	97.98 151	95.58 259	99.78 110

CHOSEN 1792x2688		96.81 148	96.53 147	97.64 190	98.91 144	93.07 279	99.65 208	99.80 3	95.64 104	95.39 247	98.86 214	84.35 284	99.90 107	96.98 186	99.16 139	99.95 78

thres100view900		96.74 155	95.92 178	99.18 58	98.90 145	98.77 42	99.74 179	99.71 7	92.59 235	95.84 234	98.86 214	89.25 205	99.50 174	93.84 257	94.57 274	99.27 213

thres600view7		96.69 158	95.87 181	99.14 68	98.90 145	98.78 41	99.74 179	99.71 7	92.59 235	95.84 234	98.86 214	89.25 205	99.50 174	93.44 270	94.50 277	99.16 222

MSDG		94.37 251	93.36 270	97.40 212	98.88 147	93.95 258	99.37 265	97.38 305	85.75 393	90.80 306	99.17 170	84.11 287	99.88 118	86.35 370	98.43 167	98.36 272

MGCFI-Net		97.00 139	96.22 160	99.34 46	98.86 148	98.80 39	99.67 206	97.30 318	94.31 153	97.77 175	99.41 140	86.36 250	99.50 174	98.38 124	93.90 286	99.72 117

h-mvs33		94.92 227	94.36 231	96.59 244	98.85 149	91.29 330	98.93 324	98.94 44	95.90 96	98.77 122	98.42 259	90.89 181	99.77 144	97.80 159	70.76 436	98.72 259

Anonymous20240529		92.10 310	90.65 322	96.47 246	98.82 150	90.61 344	98.72 347	98.67 82	75.54 443	93.90 271	98.58 244	66.23 418	99.90 107	94.70 238	90.67 302	98.90 249

PVSNet_Blended_VisFu		97.27 123	96.81 134	98.66 108	98.81 151	96.67 144	99.92 94	98.64 86	94.51 138	96.38 220	98.49 252	89.05 209	99.88 118	97.10 181	98.34 168	99.43 183

PS-MVSNAJ		98.44 46	98.20 51	99.16 64	98.80 152	98.92 29	99.54 237	98.17 214	97.34 41	99.85 17	99.85 33	91.20 170	99.89 112	99.41 64	99.67 90	98.69 260

CANet_DTU		96.76 152	96.15 163	98.60 113	98.78 153	97.53 102	99.84 143	97.63 274	97.25 49	99.20 97	99.64 113	81.36 311	99.98 47	92.77 281	98.89 150	98.28 274

mvsany_test1		97.82 91	97.90 77	97.55 199	98.77 154	93.04 282	99.80 159	97.93 242	96.95 60	99.61 66	99.68 106	90.92 178	99.83 134	99.18 72	98.29 173	99.80 106

alignmvs		97.81 92	97.33 109	99.25 51	98.77 154	98.66 51	99.99 5	98.44 143	94.40 149	98.41 145	99.47 132	93.65 110	99.42 184	98.57 113	94.26 280	99.67 125

SymmetryMVS		97.64 106	97.46 100	98.17 148	98.74 156	95.39 204	99.61 219	99.26 29	96.52 75	98.61 133	99.31 151	92.73 138	99.67 162	96.77 194	95.63 257	99.45 179

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 58	98.72 157	97.71 94	99.98 20	98.44 143	96.85 61	99.80 25	99.91 14	97.57 8	99.85 124	99.44 62	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
xiu_mvs_v2_base		98.23 68	97.97 69	99.02 83	98.69 158	98.66 51	99.52 239	98.08 228	97.05 55	99.86 14	99.86 29	90.65 183	99.71 154	99.39 66	98.63 160	98.69 260

miper_enhance_ethall		94.36 253	93.98 244	95.49 276	98.68 159	95.24 215	99.73 186	97.29 321	93.28 199	89.86 318	95.97 344	94.37 85	97.05 349	92.20 285	84.45 359	94.19 346

fmvsm_s_conf0.5_n_5		98.08 74	97.71 88	99.17 61	98.67 160	97.69 98	99.99 5	98.57 102	97.40 39	99.89 9	99.69 99	85.99 255	99.96 71	99.80 28	99.40 127	99.85 98

ETVMVS		97.03 138	96.64 142	98.20 147	98.67 160	97.12 123	99.89 118	98.57 102	91.10 293	98.17 158	98.59 241	93.86 105	98.19 291	95.64 216	95.24 267	99.28 211

test2506		97.53 110	97.19 116	98.58 117	98.66 162	96.90 134	98.81 339	99.77 5	94.93 120	97.95 164	98.96 193	92.51 147	99.20 195	94.93 228	98.15 177	99.64 131

ECVR-MVS		95.66 205	95.05 212	97.51 203	98.66 162	93.71 263	98.85 336	98.45 138	94.93 120	96.86 202	98.96 193	75.22 376	99.20 195	95.34 218	98.15 177	99.64 131

mamv4		95.24 217	96.90 127	90.25 403	98.65 164	72.11 451	98.28 375	97.64 273	89.99 326	95.93 232	98.25 269	94.74 70	99.11 201	99.01 85	99.64 92	99.53 163

balanced_conf03		98.27 60	97.99 67	99.11 73	98.64 165	98.43 63	99.47 249	97.79 257	94.56 136	99.74 42	98.35 261	94.33 88	99.25 189	99.12 74	99.96 46	99.64 131

fmvsm_s_conf0.5_n_a		97.73 101	97.72 86	97.77 181	98.63 166	94.26 248	99.96 48	98.92 49	97.18 51	99.75 39	99.69 99	87.00 240	99.97 59	99.46 60	98.89 150	99.08 232

MVSMamba_PlusPlus		97.83 88	97.45 102	98.99 85	98.60 167	98.15 67	99.58 226	97.74 264	90.34 318	99.26 96	98.32 264	94.29 90	99.23 190	99.03 83	99.89 70	99.58 151

testing222		97.08 137	96.75 137	98.06 158	98.56 168	96.82 136	99.85 138	98.61 94	92.53 239	98.84 116	98.84 218	93.36 115	98.30 281	95.84 212	94.30 279	99.05 236

test1111		95.57 208	94.98 215	97.37 214	98.56 168	93.37 276	98.86 334	98.45 138	94.95 119	96.63 208	98.95 198	75.21 377	99.11 201	95.02 225	98.14 179	99.64 131

MVSTER		95.53 209	95.22 204	96.45 249	98.56 168	97.72 93	99.91 102	97.67 269	92.38 247	91.39 297	97.14 301	97.24 18	97.30 333	94.80 234	87.85 331	94.34 335

testing3-2		97.72 102	97.43 105	98.60 113	98.55 171	97.11 125	100.00 1	99.23 31	93.78 180	97.90 166	98.73 225	95.50 49	99.69 158	98.53 117	94.63 272	98.99 240

VDD-MVS		93.77 269	92.94 278	96.27 256	98.55 171	90.22 353	98.77 344	97.79 257	90.85 299	96.82 204	99.42 136	61.18 438	99.77 144	98.95 86	94.13 281	98.82 252

tpmvs		94.28 255	93.57 257	96.40 251	98.55 171	91.50 328	95.70 435	98.55 114	87.47 368	92.15 290	94.26 409	91.42 166	98.95 214	88.15 349	95.85 246	98.76 255

UGNet		95.33 215	94.57 227	97.62 194	98.55 171	94.85 227	98.67 353	99.32 26	95.75 101	96.80 205	96.27 333	72.18 392	99.96 71	94.58 241	99.05 146	98.04 280
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
PCF-MVS	94.20 5	95.18 219	94.10 238	98.43 134	98.55 171	95.99 176	97.91 391	97.31 317	90.35 317	89.48 331	99.22 163	85.19 269	99.89 112	90.40 323	98.47 166	99.41 185
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		95.95 190	96.49 148	94.34 326	98.51 176	89.99 358	99.39 261	98.57 102	93.14 204	97.33 187	98.31 266	93.44 113	94.68 426	93.69 267	95.98 240	98.34 273

UWE-MVS		96.79 149	96.72 139	97.00 228	98.51 176	93.70 264	99.71 193	98.60 96	92.96 212	97.09 194	98.34 263	96.67 31	98.85 221	92.11 291	96.50 227	98.44 268

myMVS_eth3d28		97.86 84	97.59 96	98.68 105	98.50 178	97.26 115	99.92 94	98.55 114	93.79 179	98.26 154	98.75 223	95.20 54	99.48 180	98.93 88	96.40 230	99.29 209

test_vis1_n_1920		95.44 211	95.31 200	95.82 270	98.50 178	88.74 376	99.98 20	97.30 318	97.84 27	99.85 17	99.19 168	66.82 416	99.97 59	98.82 97	99.46 121	98.76 255

BH-w/o		95.71 202	95.38 198	96.68 241	98.49 180	92.28 301	99.84 143	97.50 294	92.12 257	92.06 293	98.79 221	84.69 278	98.67 245	95.29 220	99.66 91	99.09 230

baseline1		95.78 198	94.86 218	98.54 123	98.47 181	98.07 75	99.06 302	97.99 235	92.68 229	94.13 268	98.62 238	93.28 121	98.69 242	93.79 262	85.76 346	98.84 251

fmvsm_s_conf0.5_n_7		97.70 104	97.74 85	97.59 197	98.44 182	95.16 221	99.97 38	98.65 83	97.95 23	99.62 59	99.78 62	86.09 253	99.94 88	99.69 46	99.50 114	97.66 290

EPMVS		96.53 167	96.01 167	98.09 156	98.43 183	96.12 174	96.36 422	99.43 20	93.53 188	97.64 177	95.04 386	94.41 80	98.38 273	91.13 304	98.11 180	99.75 113

kuosan		93.17 284	92.60 286	94.86 302	98.40 184	89.54 366	98.44 366	98.53 121	84.46 406	88.49 352	97.92 282	90.57 185	97.05 349	83.10 395	93.49 289	97.99 281

WBMVS		94.52 244	94.03 242	95.98 262	98.38 185	96.68 143	99.92 94	97.63 274	90.75 308	89.64 326	95.25 379	96.77 25	96.90 361	94.35 246	83.57 366	94.35 333

UBG		97.84 87	97.69 89	98.29 143	98.38 185	96.59 150	99.90 108	98.53 121	93.91 175	98.52 137	98.42 259	96.77 25	99.17 198	98.54 115	96.20 234	99.11 229

sss		97.57 109	97.03 123	99.18 58	98.37 187	98.04 78	99.73 186	99.38 22	93.46 191	98.76 125	99.06 179	91.21 169	99.89 112	96.33 203	97.01 218	99.62 138

testing11		97.48 112	97.27 112	98.10 155	98.36 188	96.02 175	99.92 94	98.45 138	93.45 193	98.15 159	98.70 228	95.48 50	99.22 191	97.85 157	95.05 269	99.07 233

BH-untuned		95.18 219	94.83 219	96.22 257	98.36 188	91.22 331	99.80 159	97.32 316	90.91 297	91.08 300	98.67 230	83.51 289	98.54 255	94.23 249	99.61 99	98.92 246

testing91		97.16 129	96.90 127	97.97 162	98.35 190	95.67 191	99.91 102	98.42 163	92.91 215	97.33 187	98.72 226	94.81 68	99.21 192	96.98 186	94.63 272	99.03 237

testing99		97.17 128	96.91 126	97.95 163	98.35 190	95.70 188	99.91 102	98.43 151	92.94 213	97.36 185	98.72 226	94.83 67	99.21 192	97.00 184	94.64 271	98.95 242

ET-MVSNet_ETH3D		94.37 251	93.28 272	97.64 190	98.30 192	97.99 80	99.99 5	97.61 280	94.35 150	71.57 449	99.45 135	96.23 35	95.34 416	96.91 191	85.14 353	99.59 145

AUN-MVS		93.28 281	92.60 286	95.34 285	98.29 193	90.09 356	99.31 273	98.56 108	91.80 270	96.35 221	98.00 277	89.38 202	98.28 284	92.46 282	69.22 441	97.64 291

FMVSNet3		92.69 297	91.58 307	95.99 261	98.29 193	97.42 110	99.26 282	97.62 277	89.80 329	89.68 322	95.32 373	81.62 309	96.27 392	87.01 366	85.65 347	94.29 337

PMMVS		96.76 152	96.76 136	96.76 238	98.28 195	92.10 305	99.91 102	97.98 237	94.12 161	99.53 71	99.39 143	86.93 241	98.73 235	96.95 189	97.73 188	99.45 179

hse-mvs2		94.38 250	94.08 241	95.31 287	98.27 196	90.02 357	99.29 278	98.56 108	95.90 96	98.77 122	98.00 277	90.89 181	98.26 288	97.80 159	69.20 442	97.64 291

PVSNet_0	88.03 19	91.80 317	90.27 331	96.38 253	98.27 196	90.46 348	99.94 84	99.61 13	93.99 169	86.26 388	97.39 296	71.13 399	99.89 112	98.77 101	67.05 448	98.79 254

UA-Net		96.54 166	95.96 174	98.27 144	98.23 198	95.71 187	98.00 389	98.45 138	93.72 184	98.41 145	99.27 156	88.71 216	99.66 165	91.19 303	97.69 189	99.44 182

test_cas_vis1_n_1920		96.59 163	96.23 158	97.65 189	98.22 199	94.23 249	99.99 5	97.25 326	97.77 28	99.58 67	99.08 177	77.10 350	99.97 59	97.64 167	99.45 122	98.74 257

FE-MVS		95.70 204	95.01 214	97.79 177	98.21 200	94.57 236	95.03 436	98.69 77	88.90 345	97.50 181	96.19 335	92.60 143	99.49 179	89.99 328	97.94 186	99.31 204

GG-mvs-BLEND				98.54 123	98.21 200	98.01 79	93.87 441	98.52 123		97.92 165	97.92 282	99.02 3	97.94 308	98.17 137	99.58 104	99.67 125

mvs_anonymous		95.65 206	95.03 213	97.53 201	98.19 202	95.74 185	99.33 270	97.49 295	90.87 298	90.47 309	97.10 303	88.23 219	97.16 340	95.92 210	97.66 192	99.68 123

MVS_Test		96.46 169	95.74 184	98.61 112	98.18 203	97.23 117	99.31 273	97.15 340	91.07 294	98.84 116	97.05 307	88.17 220	98.97 211	94.39 243	97.50 194	99.61 142

BH-RMVSNet		95.18 219	94.31 234	97.80 175	98.17 204	95.23 216	99.76 172	97.53 290	92.52 240	94.27 266	99.25 161	76.84 357	98.80 225	90.89 312	99.54 106	99.35 195

dongtai		91.55 323	91.13 316	92.82 371	98.16 205	86.35 399	99.47 249	98.51 126	83.24 414	85.07 398	97.56 290	90.33 190	94.94 422	76.09 433	91.73 297	97.18 302

RPSCF		91.80 317	92.79 282	88.83 414	98.15 206	69.87 453	98.11 385	96.60 398	83.93 409	94.33 264	99.27 156	79.60 333	99.46 183	91.99 292	93.16 294	97.18 302

ETV-MVS		97.92 80	97.80 84	98.25 145	98.14 207	96.48 152	99.98 20	97.63 274	95.61 105	99.29 94	99.46 134	92.55 145	98.82 223	99.02 84	98.54 164	99.46 176

IS-MVSNet		96.29 180	95.90 179	97.45 206	98.13 208	94.80 230	99.08 297	97.61 280	92.02 262	95.54 245	98.96 193	90.64 184	98.08 297	93.73 265	97.41 198	99.47 174

test_fmvsmconf_n		98.43 48	98.32 44	98.78 98	98.12 209	96.41 155	99.99 5	98.83 63	98.22 7	99.67 50	99.64 113	91.11 174	99.94 88	99.67 48	99.62 95	99.98 52

fmvsm_s_conf0.1_n_2		97.25 124	96.85 131	98.43 134	98.08 210	98.08 74	99.92 94	97.76 263	98.05 19	99.65 52	99.58 122	80.88 318	99.93 98	99.59 52	98.17 175	97.29 300

ab-mvs		94.69 236	93.42 263	98.51 128	98.07 211	96.26 162	96.49 420	98.68 79	90.31 319	94.54 256	97.00 309	76.30 365	99.71 154	95.98 209	93.38 292	99.56 154

XVG-OURS-SEG-HR		94.79 231	94.70 226	95.08 292	98.05 212	89.19 368	99.08 297	97.54 288	93.66 185	94.87 254	99.58 122	78.78 341	99.79 139	97.31 174	93.40 291	96.25 309

EIA-MVS		97.53 110	97.46 100	97.76 183	98.04 213	94.84 228	99.98 20	97.61 280	94.41 148	97.90 166	99.59 119	92.40 151	98.87 219	98.04 146	99.13 141	99.59 145

XVG-OURS		94.82 228	94.74 225	95.06 293	98.00 214	89.19 368	99.08 297	97.55 286	94.10 162	94.71 255	99.62 117	80.51 324	99.74 150	96.04 208	93.06 296	96.25 309

mvsmamba		96.94 142	96.73 138	97.55 199	97.99 215	94.37 245	99.62 215	97.70 266	93.13 205	98.42 144	97.92 282	88.02 221	98.75 233	98.78 100	99.01 147	99.52 165

dp		95.05 222	94.43 229	96.91 231	97.99 215	92.73 290	96.29 425	97.98 237	89.70 330	95.93 232	94.67 399	93.83 107	98.45 261	86.91 369	96.53 226	99.54 159

tpmrst		96.27 182	95.98 170	97.13 223	97.96 217	93.15 278	96.34 423	98.17 214	92.07 258	98.71 128	95.12 383	93.91 102	98.73 235	94.91 231	96.62 224	99.50 171

TR-MVS		94.54 241	93.56 258	97.49 205	97.96 217	94.34 246	98.71 348	97.51 293	90.30 320	94.51 258	98.69 229	75.56 371	98.77 229	92.82 280	95.99 239	99.35 195

Vis-MVSNet (Re-imp)		96.32 177	95.98 170	97.35 218	97.93 219	94.82 229	99.47 249	98.15 222	91.83 267	95.09 252	99.11 175	91.37 168	97.47 324	93.47 269	97.43 195	99.74 114

MDTV_nov1_ep13			95.69 186		97.90 220	94.15 251	95.98 431	98.44 143	93.12 206	97.98 163	95.74 348	95.10 57	98.58 251	90.02 327	96.92 220

Fast-Effi-MVS+		95.02 224	94.19 236	97.52 202	97.88 221	94.55 237	99.97 38	97.08 356	88.85 347	94.47 259	97.96 281	84.59 279	98.41 265	89.84 330	97.10 212	99.59 145

ADS-MVSNet2		93.80 268	93.88 248	93.55 354	97.87 222	85.94 403	94.24 437	96.84 384	90.07 323	96.43 217	94.48 404	90.29 192	95.37 415	87.44 356	97.23 205	99.36 191

ADS-MVSNet		94.79 231	94.02 243	97.11 225	97.87 222	93.79 260	94.24 437	98.16 219	90.07 323	96.43 217	94.48 404	90.29 192	98.19 291	87.44 356	97.23 205	99.36 191

Effi-MVS+		96.30 179	95.69 186	98.16 149	97.85 224	96.26 162	97.41 400	97.21 332	90.37 316	98.65 131	98.58 244	86.61 247	98.70 241	97.11 180	97.37 199	99.52 165

PatchmatchNet		95.94 191	95.45 193	97.39 213	97.83 225	94.41 241	96.05 429	98.40 172	92.86 216	97.09 194	95.28 378	94.21 94	98.07 299	89.26 336	98.11 180	99.70 120
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cascas		94.64 239	93.61 253	97.74 185	97.82 226	96.26 162	99.96 48	97.78 259	85.76 391	94.00 269	97.54 291	76.95 356	99.21 192	97.23 177	95.43 262	97.76 289

1112_ss		96.01 189	95.20 205	98.42 136	97.80 227	96.41 155	99.65 208	96.66 395	92.71 226	92.88 283	99.40 141	92.16 156	99.30 187	91.92 294	93.66 287	99.55 155

Test_1112_low_res		95.72 200	94.83 219	98.42 136	97.79 228	96.41 155	99.65 208	96.65 396	92.70 227	92.86 284	96.13 339	92.15 157	99.30 187	91.88 295	93.64 288	99.55 155

Effi-MVS+-dtu		94.53 243	95.30 201	92.22 379	97.77 229	82.54 426	99.59 224	97.06 360	94.92 122	95.29 249	95.37 371	85.81 257	97.89 309	94.80 234	97.07 213	96.23 311

tpm cat1		93.51 277	92.52 292	96.47 246	97.77 229	91.47 329	96.13 427	98.06 229	80.98 428	92.91 282	93.78 413	89.66 197	98.87 219	87.03 365	96.39 231	99.09 230

FA-MVS(test-final)		95.86 194	95.09 210	98.15 152	97.74 231	95.62 193	96.31 424	98.17 214	91.42 283	96.26 222	96.13 339	90.56 186	99.47 182	92.18 286	97.07 213	99.35 195

xiu_mvs_v1_base_debu		97.43 113	97.06 119	98.55 119	97.74 231	98.14 69	99.31 273	97.86 251	96.43 80	99.62 59	99.69 99	85.56 264	99.68 159	99.05 77	98.31 170	97.83 285

xiu_mvs_v1_base		97.43 113	97.06 119	98.55 119	97.74 231	98.14 69	99.31 273	97.86 251	96.43 80	99.62 59	99.69 99	85.56 264	99.68 159	99.05 77	98.31 170	97.83 285

xiu_mvs_v1_base_debi		97.43 113	97.06 119	98.55 119	97.74 231	98.14 69	99.31 273	97.86 251	96.43 80	99.62 59	99.69 99	85.56 264	99.68 159	99.05 77	98.31 170	97.83 285

EPP-MVSNet		96.69 158	96.60 144	96.96 230	97.74 231	93.05 281	99.37 265	98.56 108	88.75 349	95.83 236	99.01 184	96.01 36	98.56 253	96.92 190	97.20 207	99.25 215

gg-mvs-nofinetune		93.51 277	91.86 304	98.47 130	97.72 236	97.96 84	92.62 447	98.51 126	74.70 446	97.33 187	69.59 463	98.91 4	97.79 312	97.77 164	99.56 105	99.67 125

IB-MVS	92.85 6	94.99 225	93.94 246	98.16 149	97.72 236	95.69 190	99.99 5	98.81 64	94.28 156	92.70 285	96.90 311	95.08 58	99.17 198	96.07 207	73.88 429	99.60 144
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
thisisatest0515		97.41 118	97.02 124	98.59 116	97.71 238	97.52 103	99.97 38	98.54 118	91.83 267	97.45 182	99.04 181	97.50 9	99.10 203	94.75 236	96.37 232	99.16 222

VortexMVS		94.11 257	93.50 260	95.94 264	97.70 239	96.61 147	99.35 268	97.18 335	93.52 190	89.57 329	95.74 348	87.55 228	96.97 357	95.76 215	85.13 354	94.23 342

Syy-MVS		90.00 357	90.63 323	88.11 421	97.68 240	74.66 449	99.71 193	98.35 185	90.79 305	92.10 291	98.67 230	79.10 339	93.09 441	63.35 456	95.95 243	96.59 307

myMVS_eth3d		94.46 248	94.76 224	93.55 354	97.68 240	90.97 333	99.71 193	98.35 185	90.79 305	92.10 291	98.67 230	92.46 150	93.09 441	87.13 362	95.95 243	96.59 307

test_fmvs1_n		94.25 256	94.36 231	93.92 341	97.68 240	83.70 416	99.90 108	96.57 399	97.40 39	99.67 50	98.88 205	61.82 435	99.92 104	98.23 135	99.13 141	98.14 278

fmvsm_s_conf0.5_n_6		98.27 60	97.96 72	99.23 53	97.66 243	98.11 73	99.98 20	98.64 86	97.85 26	99.87 12	99.72 89	88.86 213	99.93 98	99.64 50	99.36 130	99.63 137

RRT-MVS		96.24 183	95.68 188	97.94 166	97.65 244	94.92 226	99.27 281	97.10 352	92.79 222	97.43 183	97.99 279	81.85 304	99.37 186	98.46 121	98.57 161	99.53 163

diffmvs		97.00 139	96.64 142	98.09 156	97.64 245	96.17 171	99.81 155	97.19 333	94.67 134	98.95 111	99.28 153	86.43 248	98.76 231	98.37 126	97.42 197	99.33 198
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewcassd2359sk11		96.59 163	96.23 158	97.66 188	97.63 246	94.70 233	99.77 166	97.33 313	93.41 194	97.34 186	99.17 170	86.72 242	98.83 222	97.40 172	97.32 202	99.46 176

viewdifsd2359ckpt13		96.19 184	95.77 183	97.45 206	97.62 247	94.40 243	99.70 198	97.23 331	92.76 224	96.63 208	99.05 180	84.96 273	98.64 248	96.65 197	97.35 200	99.31 204

Vis-MVSNet		95.72 200	95.15 208	97.45 206	97.62 247	94.28 247	99.28 279	98.24 205	94.27 158	96.84 203	98.94 200	79.39 334	98.76 231	93.25 271	98.49 165	99.30 207
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
thisisatest0530		97.10 132	96.72 139	98.22 146	97.60 249	96.70 140	99.92 94	98.54 118	91.11 292	97.07 196	98.97 191	97.47 12	99.03 206	93.73 265	96.09 237	98.92 246

GDP-MVS		97.88 82	97.59 96	98.75 101	97.59 250	97.81 91	99.95 67	97.37 308	94.44 144	99.08 105	99.58 122	97.13 23	99.08 204	94.99 226	98.17 175	99.37 189

miper_ehance_all_eth		93.16 285	92.60 286	94.82 303	97.57 251	93.56 268	99.50 243	97.07 359	88.75 349	88.85 346	95.52 360	90.97 177	96.74 371	90.77 314	84.45 359	94.17 347

guyue		97.15 130	96.82 133	98.15 152	97.56 252	96.25 166	99.71 193	97.84 254	95.75 101	98.13 160	98.65 233	87.58 227	98.82 223	98.29 131	97.91 187	99.36 191

viewmanbaseed2359cas		96.45 170	96.07 164	97.59 197	97.55 253	94.59 235	99.70 198	97.33 313	93.62 187	97.00 198	99.32 148	85.57 263	98.71 238	97.26 176	97.33 201	99.47 174

testing3		93.92 262	94.23 235	92.99 368	97.54 254	90.23 352	99.99 5	99.16 33	90.57 310	91.33 299	98.63 237	92.99 129	92.52 445	82.46 399	95.39 263	96.22 312

SSM_0404		95.75 199	95.16 207	97.50 204	97.53 255	95.39 204	99.11 293	97.25 326	90.81 301	95.27 250	98.83 219	84.74 275	98.67 245	95.24 221	97.69 189	98.45 267

LCM-MVSNet-Re		92.31 306	92.60 286	91.43 388	97.53 255	79.27 443	99.02 311	91.83 458	92.07 258	80.31 422	94.38 407	83.50 290	95.48 412	97.22 178	97.58 193	99.54 159

GBi-Net		90.88 334	89.82 340	94.08 333	97.53 255	91.97 306	98.43 367	96.95 373	87.05 374	89.68 322	94.72 395	71.34 396	96.11 398	87.01 366	85.65 347	94.17 347

test1		90.88 334	89.82 340	94.08 333	97.53 255	91.97 306	98.43 367	96.95 373	87.05 374	89.68 322	94.72 395	71.34 396	96.11 398	87.01 366	85.65 347	94.17 347

FMVSNet2		91.02 331	89.56 345	95.41 283	97.53 255	95.74 185	98.98 314	97.41 303	87.05 374	88.43 356	95.00 389	71.34 396	96.24 394	85.12 381	85.21 352	94.25 340

tttt0517		96.85 146	96.49 148	97.92 167	97.48 260	95.89 179	99.85 138	98.54 118	90.72 309	96.63 208	98.93 203	97.47 12	99.02 207	93.03 278	95.76 249	98.85 250

BP-MVS1		98.33 56	98.18 53	98.81 96	97.44 261	97.98 81	99.96 48	98.17 214	94.88 124	98.77 122	99.59 119	97.59 7	99.08 204	98.24 134	98.93 149	99.36 191

casdiffmvs_mvg		96.43 171	95.94 176	97.89 171	97.44 261	95.47 197	99.86 135	97.29 321	93.35 195	96.03 229	99.19 168	85.39 267	98.72 237	97.89 156	97.04 215	99.49 173
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EC-MVSNet		97.38 120	97.24 113	97.80 175	97.41 263	95.64 192	99.99 5	97.06 360	94.59 135	99.63 56	99.32 148	89.20 208	98.14 293	98.76 102	99.23 137	99.62 138

viewdifsd2359ckpt07		95.83 197	95.42 195	97.07 226	97.40 264	93.04 282	99.60 222	97.24 329	92.39 246	96.09 228	99.14 174	83.07 295	98.93 215	97.02 183	96.87 221	99.23 218

c3_l		92.53 301	91.87 303	94.52 315	97.40 264	92.99 284	99.40 257	96.93 378	87.86 364	88.69 349	95.44 365	89.95 195	96.44 384	90.45 320	80.69 393	94.14 356

viewmambaseed2359dif		95.92 193	95.55 192	97.04 227	97.38 266	93.41 273	99.78 162	96.97 371	91.14 291	96.58 211	99.27 156	84.85 274	98.75 233	96.87 192	97.12 211	98.97 241

fmvsm_s_conf0.1_n		97.30 121	97.21 115	97.60 196	97.38 266	94.40 243	99.90 108	98.64 86	96.47 79	99.51 75	99.65 112	84.99 272	99.93 98	99.22 71	99.09 144	98.46 266

CDS-MVSNet		96.34 176	96.07 164	97.13 223	97.37 268	94.96 224	99.53 238	97.91 246	91.55 275	95.37 248	98.32 264	95.05 60	97.13 343	93.80 261	95.75 250	99.30 207
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TESTMET0.1,1		96.74 155	96.26 157	98.16 149	97.36 269	96.48 152	99.96 48	98.29 198	91.93 263	95.77 237	98.07 275	95.54 46	98.29 282	90.55 318	98.89 150	99.70 120

miper_lstm_enhance		91.81 314	91.39 313	93.06 367	97.34 270	89.18 370	99.38 263	96.79 389	86.70 381	87.47 370	95.22 380	90.00 194	95.86 407	88.26 347	81.37 382	94.15 353

baseline		96.43 171	95.98 170	97.76 183	97.34 270	95.17 220	99.51 241	97.17 337	93.92 174	96.90 201	99.28 153	85.37 268	98.64 248	97.50 170	96.86 223	99.46 176

cl____		92.31 306	91.58 307	94.52 315	97.33 272	92.77 286	99.57 229	96.78 390	86.97 378	87.56 368	95.51 361	89.43 201	96.62 376	88.60 341	82.44 374	94.16 352

SD_0403		92.63 300	93.38 267	90.40 402	97.32 273	77.91 445	97.75 396	98.03 233	91.89 264	90.83 305	98.29 268	82.00 301	93.79 435	88.51 345	95.75 250	99.52 165

DIV-MVS_self_test		92.32 305	91.60 306	94.47 319	97.31 274	92.74 288	99.58 226	96.75 391	86.99 377	87.64 366	95.54 358	89.55 200	96.50 381	88.58 342	82.44 374	94.17 347

casdiffmvs		96.42 173	95.97 173	97.77 181	97.30 275	94.98 223	99.84 143	97.09 355	93.75 183	96.58 211	99.26 160	85.07 270	98.78 228	97.77 164	97.04 215	99.54 159
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GeoE		94.36 253	93.48 261	96.99 229	97.29 276	93.54 269	99.96 48	96.72 393	88.35 358	93.43 273	98.94 200	82.05 300	98.05 300	88.12 351	96.48 229	99.37 189

eth_miper_zixun_eth		92.41 304	91.93 301	93.84 345	97.28 277	90.68 342	98.83 337	96.97 371	88.57 354	89.19 341	95.73 351	89.24 207	96.69 374	89.97 329	81.55 380	94.15 353

MVSFormer		96.94 142	96.60 144	97.95 163	97.28 277	97.70 96	99.55 235	97.27 323	91.17 288	99.43 81	99.54 128	90.92 178	96.89 362	94.67 239	99.62 95	99.25 215

lupinMVS		97.85 86	97.60 94	98.62 111	97.28 277	97.70 96	99.99 5	97.55 286	95.50 110	99.43 81	99.67 108	90.92 178	98.71 238	98.40 123	99.62 95	99.45 179

diffmvs_AUTHOR		96.75 154	96.41 153	97.79 177	97.20 280	95.46 198	99.69 201	97.15 340	94.46 140	98.78 120	99.21 166	85.64 261	98.77 229	98.27 132	97.31 203	99.13 226

mamba_0408		94.98 226	94.09 239	97.64 190	97.14 281	95.31 209	93.48 444	97.08 356	90.48 312	94.40 260	98.62 238	84.49 280	98.67 245	93.99 252	97.18 208	98.93 243

SSM_04072		94.77 233	94.09 239	96.82 235	97.14 281	95.31 209	93.48 444	97.08 356	90.48 312	94.40 260	98.62 238	84.49 280	96.21 395	93.99 252	97.18 208	98.93 243

SSM_0407		95.62 207	94.95 216	97.61 195	97.14 281	95.31 209	99.00 312	97.25 326	90.81 301	94.40 260	98.83 219	84.74 275	98.58 251	95.24 221	97.18 208	98.93 243

SCA		94.69 236	93.81 250	97.33 219	97.10 284	94.44 238	98.86 334	98.32 192	93.30 198	96.17 227	95.59 356	76.48 363	97.95 306	91.06 306	97.43 195	99.59 145

viewmacassd2359aftdt		95.93 192	95.45 193	97.36 216	97.09 285	94.12 253	99.57 229	97.26 325	93.05 210	96.50 214	99.17 170	82.76 296	98.68 243	96.61 198	97.04 215	99.28 211

KinetiMVS		96.10 185	95.29 202	98.53 125	97.08 286	97.12 123	99.56 232	98.12 225	94.78 127	98.44 142	98.94 200	80.30 328	99.39 185	91.56 299	98.79 156	99.06 234

TAMVS		95.85 195	95.58 190	96.65 243	97.07 287	93.50 270	99.17 289	97.82 256	91.39 285	95.02 253	98.01 276	92.20 155	97.30 333	93.75 264	95.83 247	99.14 225

Fast-Effi-MVS+-dtu		93.72 272	93.86 249	93.29 359	97.06 288	86.16 400	99.80 159	96.83 385	92.66 230	92.58 286	97.83 287	81.39 310	97.67 317	89.75 331	96.87 221	96.05 314

CostFormer		96.10 185	95.88 180	96.78 237	97.03 289	92.55 296	97.08 409	97.83 255	90.04 325	98.72 127	94.89 393	95.01 62	98.29 282	96.54 200	95.77 248	99.50 171

test_fmvsmvis_n_1920		97.67 105	97.59 96	97.91 169	97.02 290	95.34 207	99.95 67	98.45 138	97.87 25	97.02 197	99.59 119	89.64 198	99.98 47	99.41 64	99.34 132	98.42 269

test-LLR		96.47 168	96.04 166	97.78 179	97.02 290	95.44 199	99.96 48	98.21 209	94.07 164	95.55 243	96.38 328	93.90 103	98.27 286	90.42 321	98.83 154	99.64 131

test-mter		96.39 174	95.93 177	97.78 179	97.02 290	95.44 199	99.96 48	98.21 209	91.81 269	95.55 243	96.38 328	95.17 55	98.27 286	90.42 321	98.83 154	99.64 131

icg_test_0407_2		95.04 223	94.78 223	95.84 269	96.97 293	91.64 321	98.63 356	97.12 345	92.33 249	95.60 241	98.88 205	85.65 259	96.56 379	92.12 287	95.70 253	99.32 200

IMVS_0407		95.21 218	94.80 222	96.46 248	96.97 293	91.64 321	98.81 339	97.12 345	92.33 249	95.60 241	98.88 205	85.65 259	98.42 263	92.12 287	95.70 253	99.32 200

IMVS_0404		93.83 264	93.17 274	95.80 271	96.97 293	91.64 321	97.78 395	97.12 345	92.33 249	90.87 304	98.88 205	76.78 358	96.43 385	92.12 287	95.70 253	99.32 200

IMVS_0403		95.25 216	94.81 221	96.58 245	96.97 293	91.64 321	98.97 319	97.12 345	92.33 249	95.43 246	98.88 205	85.78 258	98.79 226	92.12 287	95.70 253	99.32 200

gm-plane-assit					96.97 293	93.76 262			91.47 279		98.96 193		98.79 226	94.92 229

WB-MVSnew		92.90 291	92.77 283	93.26 361	96.95 298	93.63 266	99.71 193	98.16 219	91.49 276	94.28 265	98.14 272	81.33 312	96.48 382	79.47 416	95.46 260	89.68 442

QAPM		95.40 212	94.17 237	99.10 74	96.92 299	97.71 94	99.40 257	98.68 79	89.31 333	88.94 345	98.89 204	82.48 298	99.96 71	93.12 277	99.83 77	99.62 138

KD-MVS_2432*1600		88.00 379	86.10 383	93.70 350	96.91 300	94.04 254	97.17 406	97.12 345	84.93 401	81.96 412	92.41 426	92.48 148	94.51 428	79.23 417	52.68 462	92.56 412

miper_refine_blended		88.00 379	86.10 383	93.70 350	96.91 300	94.04 254	97.17 406	97.12 345	84.93 401	81.96 412	92.41 426	92.48 148	94.51 428	79.23 417	52.68 462	92.56 412

tpm2		95.47 210	95.18 206	96.35 254	96.91 300	91.70 319	96.96 412	97.93 242	88.04 362	98.44 142	95.40 367	93.32 118	97.97 303	94.00 251	95.61 258	99.38 187

FMVSNet5		88.32 375	87.47 377	90.88 391	96.90 303	88.39 384	97.28 403	95.68 420	82.60 421	84.67 400	92.40 428	79.83 331	91.16 450	76.39 432	81.51 381	93.09 403

3Dnovator+	91.53 11	96.31 178	95.24 203	99.52 28	96.88 304	98.64 54	99.72 190	98.24 205	95.27 115	88.42 358	98.98 189	82.76 296	99.94 88	97.10 181	99.83 77	99.96 70

Patchmatch-test		92.65 299	91.50 310	96.10 260	96.85 305	90.49 347	91.50 452	97.19 333	82.76 420	90.23 310	95.59 356	95.02 61	98.00 302	77.41 427	96.98 219	99.82 102

MVS		96.60 162	95.56 191	99.72 13	96.85 305	99.22 20	98.31 373	98.94 44	91.57 274	90.90 303	99.61 118	86.66 246	99.96 71	97.36 173	99.88 73	99.99 23

3Dnovator	91.47 12	96.28 181	95.34 199	99.08 77	96.82 307	97.47 108	99.45 254	98.81 64	95.52 109	89.39 332	99.00 186	81.97 302	99.95 80	97.27 175	99.83 77	99.84 99

EI-MVSNet		93.73 271	93.40 266	94.74 304	96.80 308	92.69 291	99.06 302	97.67 269	88.96 342	91.39 297	99.02 182	88.75 215	97.30 333	91.07 305	87.85 331	94.22 343

CVMVSNet		94.68 238	94.94 217	93.89 344	96.80 308	86.92 397	99.06 302	98.98 41	94.45 141	94.23 267	99.02 182	85.60 262	95.31 417	90.91 311	95.39 263	99.43 183

IterMVS-LS		92.69 297	92.11 297	94.43 323	96.80 308	92.74 288	99.45 254	96.89 381	88.98 340	89.65 325	95.38 370	88.77 214	96.34 389	90.98 309	82.04 377	94.22 343
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AstraMVS		96.57 165	96.46 151	96.91 231	96.79 311	92.50 297	99.90 108	97.38 305	96.02 95	97.79 174	99.32 148	86.36 250	98.99 208	98.26 133	96.33 233	99.23 218

IterMVS		90.91 333	90.17 335	93.12 364	96.78 312	90.42 350	98.89 328	97.05 363	89.03 337	86.49 383	95.42 366	76.59 361	95.02 419	87.22 361	84.09 362	93.93 374
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
1314		96.84 147	95.96 174	99.48 35	96.74 313	98.52 58	98.31 373	98.86 56	95.82 98	89.91 316	98.98 189	87.49 230	99.96 71	97.80 159	99.73 87	99.96 70

IterMVS-SCA-FT		90.85 336	90.16 336	92.93 369	96.72 314	89.96 359	98.89 328	96.99 367	88.95 343	86.63 380	95.67 352	76.48 363	95.00 420	87.04 364	84.04 365	93.84 381

MVS-HIRNet		86.22 386	83.19 399	95.31 287	96.71 315	90.29 351	92.12 449	97.33 313	62.85 457	86.82 377	70.37 462	69.37 404	97.49 323	75.12 435	97.99 185	98.15 276

viewdifsd2359ckpt11		94.09 259	93.63 252	95.46 280	96.68 316	88.92 373	99.62 215	97.12 345	93.07 208	95.73 238	99.22 163	77.05 351	98.88 218	96.52 201	87.69 336	98.58 264

viewmsd2359difaftdt		94.09 259	93.64 251	95.46 280	96.68 316	88.92 373	99.62 215	97.13 344	93.07 208	95.73 238	99.22 163	77.05 351	98.89 217	96.52 201	87.70 335	98.58 264

VDDNet		93.12 286	91.91 302	96.76 238	96.67 318	92.65 294	98.69 351	98.21 209	82.81 419	97.75 176	99.28 153	61.57 436	99.48 180	98.09 143	94.09 282	98.15 276

dmvs_re		93.20 283	93.15 275	93.34 357	96.54 319	83.81 415	98.71 348	98.51 126	91.39 285	92.37 289	98.56 246	78.66 343	97.83 311	93.89 255	89.74 303	98.38 271

Elysia		94.50 245	93.38 267	97.85 173	96.49 320	96.70 140	98.98 314	97.78 259	90.81 301	96.19 225	98.55 248	73.63 387	98.98 209	89.41 332	98.56 162	97.88 283

StellarMVS		94.50 245	93.38 267	97.85 173	96.49 320	96.70 140	98.98 314	97.78 259	90.81 301	96.19 225	98.55 248	73.63 387	98.98 209	89.41 332	98.56 162	97.88 283

MIMVSNet		90.30 349	88.67 363	95.17 291	96.45 322	91.64 321	92.39 448	97.15 340	85.99 388	90.50 308	93.19 421	66.95 415	94.86 424	82.01 403	93.43 290	99.01 239

CR-MVSNet		93.45 280	92.62 285	95.94 264	96.29 323	92.66 292	92.01 450	96.23 407	92.62 232	96.94 199	93.31 419	91.04 175	96.03 403	79.23 417	95.96 241	99.13 226

RPMNet		89.76 361	87.28 378	97.19 222	96.29 323	92.66 292	92.01 450	98.31 194	70.19 453	96.94 199	85.87 455	87.25 235	99.78 141	62.69 457	95.96 241	99.13 226

tt0805		91.28 326	90.18 334	94.60 310	96.26 325	87.55 390	98.39 371	98.72 73	89.00 339	89.22 338	98.47 256	62.98 431	98.96 213	90.57 317	88.00 330	97.28 301

Patchmtry		89.70 362	88.49 366	93.33 358	96.24 326	89.94 362	91.37 453	96.23 407	78.22 436	87.69 365	93.31 419	91.04 175	96.03 403	80.18 415	82.10 376	94.02 364

test_vis1_rt		86.87 384	86.05 386	89.34 410	96.12 327	78.07 444	99.87 124	83.54 470	92.03 261	78.21 433	89.51 440	45.80 456	99.91 105	96.25 205	93.11 295	90.03 439

JIA-IIPM		91.76 320	90.70 321	94.94 297	96.11 328	87.51 391	93.16 446	98.13 224	75.79 442	97.58 178	77.68 460	92.84 134	97.97 303	88.47 346	96.54 225	99.33 198

OpenMVS	90.15 15	94.77 233	93.59 256	98.33 140	96.07 329	97.48 107	99.56 232	98.57 102	90.46 314	86.51 382	98.95 198	78.57 344	99.94 88	93.86 256	99.74 86	97.57 296

PAPM		98.60 34	98.42 35	99.14 68	96.05 330	98.96 26	99.90 108	99.35 24	96.68 70	98.35 149	99.66 110	96.45 33	98.51 256	99.45 61	99.89 70	99.96 70

CLD-MVS		94.06 261	93.90 247	94.55 314	96.02 331	90.69 341	99.98 20	97.72 265	96.62 74	91.05 302	98.85 217	77.21 349	98.47 257	98.11 141	89.51 309	94.48 321
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PatchT		90.38 346	88.75 362	95.25 289	95.99 332	90.16 354	91.22 454	97.54 288	76.80 438	97.26 190	86.01 454	91.88 162	96.07 402	66.16 452	95.91 245	99.51 169

ACMH+	89.98 16	90.35 347	89.54 346	92.78 373	95.99 332	86.12 401	98.81 339	97.18 335	89.38 332	83.14 408	97.76 288	68.42 409	98.43 262	89.11 337	86.05 345	93.78 384

DeepMVS_CX				82.92 432	95.98 334	58.66 463		96.01 412	92.72 225	78.34 432	95.51 361	58.29 442	98.08 297	82.57 398	85.29 350	92.03 420

ACMP	92.05 9	92.74 295	92.42 294	93.73 346	95.91 335	88.72 377	99.81 155	97.53 290	94.13 160	87.00 376	98.23 270	74.07 384	98.47 257	96.22 206	88.86 316	93.99 369
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n		93.61 275	93.03 277	95.35 284	95.86 336	86.94 396	99.87 124	96.36 405	96.85 61	99.54 70	98.79 221	52.41 450	99.83 134	98.64 110	98.97 148	99.29 209

HQP-NCC					95.78 337		99.87 124		96.82 63	93.37 274

ACMP_Plane					95.78 337		99.87 124		96.82 63	93.37 274

HQP-MVS		94.61 240	94.50 228	94.92 298	95.78 337	91.85 311	99.87 124	97.89 247	96.82 63	93.37 274	98.65 233	80.65 322	98.39 269	97.92 153	89.60 304	94.53 317

NP-MVS					95.77 340	91.79 313					98.65 233

test_fmvsmconf0.1_n		97.74 99	97.44 103	98.64 110	95.76 341	96.20 168	99.94 84	98.05 231	98.17 12	98.89 115	99.42 136	87.65 225	99.90 107	99.50 57	99.60 102	99.82 102

plane_prior6					95.76 341	91.72 318						80.47 326

ACMM	91.95 10	92.88 292	92.52 292	93.98 340	95.75 343	89.08 372	99.77 166	97.52 292	93.00 211	89.95 315	97.99 279	76.17 367	98.46 260	93.63 268	88.87 315	94.39 329
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GA-MVS		93.83 264	92.84 279	96.80 236	95.73 344	93.57 267	99.88 121	97.24 329	92.57 237	92.92 281	96.66 320	78.73 342	97.67 317	87.75 354	94.06 283	99.17 221

plane_prior1					95.73 344

jason		97.24 125	96.86 130	98.38 139	95.73 344	97.32 112	99.97 38	97.40 304	95.34 113	98.60 136	99.54 128	87.70 224	98.56 253	97.94 152	99.47 119	99.25 215
jason: jason.
mmtdpeth		88.52 373	87.75 375	90.85 393	95.71 347	83.47 421	98.94 322	94.85 435	88.78 348	97.19 192	89.58 439	63.29 429	98.97 211	98.54 115	62.86 456	90.10 438

HQP_MVS		94.49 247	94.36 231	94.87 299	95.71 347	91.74 315	99.84 143	97.87 249	96.38 83	93.01 279	98.59 241	80.47 326	98.37 275	97.79 162	89.55 307	94.52 319

plane_prior7					95.71 347	91.59 327

ITE_SJBPF				92.38 376	95.69 350	85.14 407		95.71 419	92.81 219	89.33 335	98.11 273	70.23 402	98.42 263	85.91 376	88.16 328	93.59 392

fmvsm_s_conf0.1_n_a		97.09 134	96.90 127	97.63 193	95.65 351	94.21 250	99.83 150	98.50 132	96.27 88	99.65 52	99.64 113	84.72 277	99.93 98	99.04 80	98.84 153	98.74 257

ACMH	89.72 17	90.64 340	89.63 343	93.66 352	95.64 352	88.64 380	98.55 359	97.45 297	89.03 337	81.62 415	97.61 289	69.75 403	98.41 265	89.37 334	87.62 337	93.92 375
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline2		96.71 157	96.49 148	97.37 214	95.63 353	95.96 177	99.74 179	98.88 54	92.94 213	91.61 295	98.97 191	97.72 6	98.62 250	94.83 233	98.08 183	97.53 298

FMVSNet1		88.50 374	86.64 381	94.08 333	95.62 354	91.97 306	98.43 367	96.95 373	83.00 417	86.08 390	94.72 395	59.09 441	96.11 398	81.82 405	84.07 363	94.17 347

LuminaMVS		96.63 161	96.21 161	97.87 172	95.58 355	96.82 136	99.12 291	97.67 269	94.47 139	97.88 169	98.31 266	87.50 229	98.71 238	98.07 145	97.29 204	98.10 279

LPG-MVS_test		92.96 289	92.71 284	93.71 348	95.43 356	88.67 378	99.75 176	97.62 277	92.81 219	90.05 311	98.49 252	75.24 374	98.40 267	95.84 212	89.12 311	94.07 361

LGP-MVS_train				93.71 348	95.43 356	88.67 378		97.62 277	92.81 219	90.05 311	98.49 252	75.24 374	98.40 267	95.84 212	89.12 311	94.07 361

tpm		93.70 273	93.41 265	94.58 312	95.36 358	87.41 392	97.01 410	96.90 380	90.85 299	96.72 207	94.14 410	90.40 189	96.84 366	90.75 315	88.54 323	99.51 169

D2MVS		92.76 294	92.59 290	93.27 360	95.13 359	89.54 366	99.69 201	99.38 22	92.26 254	87.59 367	94.61 401	85.05 271	97.79 312	91.59 298	88.01 329	92.47 415

VPA-MVSNet		92.70 296	91.55 309	96.16 258	95.09 360	96.20 168	98.88 330	99.00 39	91.02 296	91.82 294	95.29 377	76.05 369	97.96 305	95.62 217	81.19 383	94.30 336

LTVRE_ROB	88.28 18	90.29 350	89.05 357	94.02 336	95.08 361	90.15 355	97.19 405	97.43 299	84.91 403	83.99 404	97.06 306	74.00 385	98.28 284	84.08 387	87.71 333	93.62 391
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
TinyColmap		87.87 381	86.51 382	91.94 382	95.05 362	85.57 405	97.65 397	94.08 445	84.40 407	81.82 414	96.85 315	62.14 434	98.33 278	80.25 414	86.37 344	91.91 422

test0.0.03 1		93.86 263	93.61 253	94.64 308	95.02 363	92.18 304	99.93 91	98.58 100	94.07 164	87.96 362	98.50 251	93.90 103	94.96 421	81.33 406	93.17 293	96.78 304

UniMVSNet (Re)		93.07 288	92.13 296	95.88 266	94.84 364	96.24 167	99.88 121	98.98 41	92.49 242	89.25 336	95.40 367	87.09 237	97.14 342	93.13 276	78.16 407	94.26 338

USDC		90.00 357	88.96 358	93.10 366	94.81 365	88.16 386	98.71 348	95.54 424	93.66 185	83.75 406	97.20 300	65.58 420	98.31 280	83.96 390	87.49 339	92.85 409

VPNet		91.81 314	90.46 325	95.85 268	94.74 366	95.54 196	98.98 314	98.59 98	92.14 256	90.77 307	97.44 293	68.73 407	97.54 322	94.89 232	77.89 409	94.46 322

FIs		94.10 258	93.43 262	96.11 259	94.70 367	96.82 136	99.58 226	98.93 48	92.54 238	89.34 334	97.31 297	87.62 226	97.10 346	94.22 250	86.58 342	94.40 328

UniMVSNet_ETH3D		90.06 356	88.58 365	94.49 318	94.67 368	88.09 387	97.81 394	97.57 285	83.91 410	88.44 354	97.41 294	57.44 443	97.62 319	91.41 300	88.59 322	97.77 288

UniMVSNet_NR-MVSNet		92.95 290	92.11 297	95.49 276	94.61 369	95.28 213	99.83 150	99.08 36	91.49 276	89.21 339	96.86 314	87.14 236	96.73 372	93.20 272	77.52 412	94.46 322

test_fmvs2		89.47 366	89.70 342	88.77 417	94.54 370	75.74 446	99.83 150	94.70 441	94.71 131	91.08 300	96.82 319	54.46 446	97.78 314	92.87 279	88.27 326	92.80 410

MonoMVSNet		94.82 228	94.43 229	95.98 262	94.54 370	90.73 340	99.03 309	97.06 360	93.16 203	93.15 278	95.47 364	88.29 218	97.57 320	97.85 157	91.33 301	99.62 138

WR-MVS		92.31 306	91.25 314	95.48 279	94.45 372	95.29 212	99.60 222	98.68 79	90.10 322	88.07 361	96.89 312	80.68 321	96.80 370	93.14 275	79.67 400	94.36 330

nrg030		93.51 277	92.53 291	96.45 249	94.36 373	97.20 118	99.81 155	97.16 339	91.60 273	89.86 318	97.46 292	86.37 249	97.68 316	95.88 211	80.31 396	94.46 322

tfpnnormal		89.29 369	87.61 376	94.34 326	94.35 374	94.13 252	98.95 321	98.94 44	83.94 408	84.47 401	95.51 361	74.84 379	97.39 325	77.05 430	80.41 394	91.48 425

FC-MVSNet-test		93.81 267	93.15 275	95.80 271	94.30 375	96.20 168	99.42 256	98.89 52	92.33 249	89.03 344	97.27 299	87.39 232	96.83 368	93.20 272	86.48 343	94.36 330

SSC-MVS3.2		89.59 364	88.66 364	92.38 376	94.29 376	86.12 401	99.49 245	97.66 272	90.28 321	88.63 351	95.18 381	64.46 425	96.88 364	85.30 380	82.66 371	94.14 356

MS-PatchMatch		90.65 339	90.30 330	91.71 387	94.22 377	85.50 406	98.24 377	97.70 266	88.67 351	86.42 385	96.37 330	67.82 412	98.03 301	83.62 392	99.62 95	91.60 423

WR-MVS_H		91.30 324	90.35 328	94.15 330	94.17 378	92.62 295	99.17 289	98.94 44	88.87 346	86.48 384	94.46 406	84.36 283	96.61 377	88.19 348	78.51 405	93.21 401

DU-MVS		92.46 303	91.45 312	95.49 276	94.05 379	95.28 213	99.81 155	98.74 72	92.25 255	89.21 339	96.64 322	81.66 307	96.73 372	93.20 272	77.52 412	94.46 322

NR-MVSNet		91.56 322	90.22 332	95.60 274	94.05 379	95.76 184	98.25 376	98.70 75	91.16 290	80.78 421	96.64 322	83.23 293	96.57 378	91.41 300	77.73 411	94.46 322

CP-MVSNet		91.23 328	90.22 332	94.26 328	93.96 381	92.39 300	99.09 295	98.57 102	88.95 343	86.42 385	96.57 325	79.19 337	96.37 387	90.29 324	78.95 402	94.02 364

XXY-MVS		91.82 313	90.46 325	95.88 266	93.91 382	95.40 203	98.87 333	97.69 268	88.63 353	87.87 363	97.08 304	74.38 383	97.89 309	91.66 297	84.07 363	94.35 333

PS-CasMVS		90.63 341	89.51 348	93.99 339	93.83 383	91.70 319	98.98 314	98.52 123	88.48 355	86.15 389	96.53 327	75.46 372	96.31 391	88.83 339	78.86 404	93.95 372

test_0402		85.58 388	83.94 393	90.50 399	93.81 384	85.04 408	98.55 359	95.20 432	76.01 440	79.72 427	95.13 382	64.15 427	96.26 393	66.04 453	86.88 341	90.21 436

XVG-ACMP-BASELINE		91.22 329	90.75 320	92.63 375	93.73 385	85.61 404	98.52 363	97.44 298	92.77 223	89.90 317	96.85 315	66.64 417	98.39 269	92.29 284	88.61 320	93.89 377

TranMVSNet+NR-MVSNet		91.68 321	90.61 324	94.87 299	93.69 386	93.98 257	99.69 201	98.65 83	91.03 295	88.44 354	96.83 318	80.05 330	96.18 396	90.26 325	76.89 420	94.45 327

TransMVSNet (Re)		87.25 382	85.28 389	93.16 363	93.56 387	91.03 332	98.54 361	94.05 447	83.69 412	81.09 419	96.16 336	75.32 373	96.40 386	76.69 431	68.41 444	92.06 419

v10		90.25 351	88.82 360	94.57 313	93.53 388	93.43 272	99.08 297	96.87 383	85.00 400	87.34 374	94.51 402	80.93 317	97.02 356	82.85 397	79.23 401	93.26 399

testgi		89.01 371	88.04 372	91.90 383	93.49 389	84.89 410	99.73 186	95.66 421	93.89 178	85.14 396	98.17 271	59.68 440	94.66 427	77.73 426	88.88 314	96.16 313

v8		90.54 343	89.17 353	94.66 307	93.43 390	93.40 275	99.20 286	96.94 377	85.76 391	87.56 368	94.51 402	81.96 303	97.19 339	84.94 383	78.25 406	93.38 397

V42		91.28 326	90.12 337	94.74 304	93.42 391	93.46 271	99.68 204	97.02 364	87.36 370	89.85 320	95.05 385	81.31 313	97.34 328	87.34 359	80.07 398	93.40 395

pm-mvs1		89.36 368	87.81 374	94.01 337	93.40 392	91.93 309	98.62 357	96.48 403	86.25 386	83.86 405	96.14 338	73.68 386	97.04 352	86.16 373	75.73 425	93.04 405

v1144		91.09 330	89.83 339	94.87 299	93.25 393	93.69 265	99.62 215	96.98 369	86.83 380	89.64 326	94.99 390	80.94 316	97.05 349	85.08 382	81.16 384	93.87 379

v1192		90.62 342	89.25 352	94.72 306	93.13 394	93.07 279	99.50 243	97.02 364	86.33 385	89.56 330	95.01 387	79.22 336	97.09 348	82.34 401	81.16 384	94.01 366

v2v482		91.30 324	90.07 338	95.01 294	93.13 394	93.79 260	99.77 166	97.02 364	88.05 361	89.25 336	95.37 371	80.73 320	97.15 341	87.28 360	80.04 399	94.09 360

OPM-MVS		93.21 282	92.80 281	94.44 321	93.12 396	90.85 339	99.77 166	97.61 280	96.19 91	91.56 296	98.65 233	75.16 378	98.47 257	93.78 263	89.39 310	93.99 369
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		90.79 337	89.52 347	94.59 311	93.11 397	92.77 286	99.56 232	96.99 367	86.38 384	89.82 321	94.95 392	80.50 325	97.10 346	83.98 389	80.41 394	93.90 376

PEN-MVS		90.19 353	89.06 356	93.57 353	93.06 398	90.90 337	99.06 302	98.47 135	88.11 360	85.91 391	96.30 332	76.67 359	95.94 406	87.07 363	76.91 419	93.89 377

v1240		90.20 352	88.79 361	94.44 321	93.05 399	92.27 302	99.38 263	96.92 379	85.89 389	89.36 333	94.87 394	77.89 348	97.03 354	80.66 410	81.08 387	94.01 366

v148		90.70 338	89.63 343	93.92 341	92.97 400	90.97 333	99.75 176	96.89 381	87.51 367	88.27 359	95.01 387	81.67 306	97.04 352	87.40 358	77.17 417	93.75 385

v1921920		90.46 344	89.12 354	94.50 317	92.96 401	92.46 298	99.49 245	96.98 369	86.10 387	89.61 328	95.30 374	78.55 345	97.03 354	82.17 402	80.89 392	94.01 366

MVStest1		85.03 394	82.76 403	91.83 384	92.95 402	89.16 371	98.57 358	94.82 436	71.68 451	68.54 454	95.11 384	83.17 294	95.66 410	74.69 436	65.32 451	90.65 432

tt0320-xc		82.94 408	80.35 415	90.72 397	92.90 403	83.54 419	96.85 415	94.73 439	63.12 456	79.85 426	93.77 414	49.43 454	95.46 413	80.98 409	71.54 434	93.16 402

Baseline_NR-MVSNet		90.33 348	89.51 348	92.81 372	92.84 404	89.95 360	99.77 166	93.94 448	84.69 405	89.04 343	95.66 353	81.66 307	96.52 380	90.99 308	76.98 418	91.97 421

test_method		80.79 414	79.70 417	84.08 429	92.83 405	67.06 455	99.51 241	95.42 426	54.34 461	81.07 420	93.53 416	44.48 457	92.22 447	78.90 421	77.23 416	92.94 407

pmmvs4		92.10 310	91.07 318	95.18 290	92.82 406	94.96 224	99.48 248	96.83 385	87.45 369	88.66 350	96.56 326	83.78 288	96.83 368	89.29 335	84.77 357	93.75 385

LF4IMVS		89.25 370	88.85 359	90.45 401	92.81 407	81.19 436	98.12 384	94.79 437	91.44 280	86.29 387	97.11 302	65.30 423	98.11 295	88.53 344	85.25 351	92.07 418

tt0320		83.56 407	81.15 410	90.77 395	92.77 408	83.58 418	96.83 416	95.52 425	63.26 455	81.36 417	92.54 424	53.26 448	95.77 408	80.45 411	74.38 428	92.96 406

DTE-MVSNet		89.40 367	88.24 370	92.88 370	92.66 409	89.95 360	99.10 294	98.22 208	87.29 371	85.12 397	96.22 334	76.27 366	95.30 418	83.56 393	75.74 424	93.41 394

EU-MVSNet		90.14 355	90.34 329	89.54 409	92.55 410	81.06 437	98.69 351	98.04 232	91.41 284	86.59 381	96.84 317	80.83 319	93.31 440	86.20 372	81.91 378	94.26 338

APD_test1		81.15 412	80.92 412	81.86 433	92.45 411	59.76 462	96.04 430	93.61 451	73.29 449	77.06 436	96.64 322	44.28 458	96.16 397	72.35 440	82.52 372	89.67 443

sc_t1		85.01 395	82.46 405	92.67 374	92.44 412	83.09 422	97.39 401	95.72 418	65.06 454	85.64 394	96.16 336	49.50 453	97.34 328	84.86 384	75.39 426	97.57 296

our_test_3		90.39 345	89.48 350	93.12 364	92.40 413	89.57 365	99.33 270	96.35 406	87.84 365	85.30 395	94.99 390	84.14 286	96.09 401	80.38 412	84.56 358	93.71 390

ppachtmachnet_test		89.58 365	88.35 368	93.25 362	92.40 413	90.44 349	99.33 270	96.73 392	85.49 396	85.90 392	95.77 347	81.09 315	96.00 405	76.00 434	82.49 373	93.30 398

v7n		89.65 363	88.29 369	93.72 347	92.22 415	90.56 346	99.07 301	97.10 352	85.42 398	86.73 378	94.72 395	80.06 329	97.13 343	81.14 407	78.12 408	93.49 393

dmvs_testset		83.79 404	86.07 385	76.94 437	92.14 416	48.60 472	96.75 417	90.27 462	89.48 331	78.65 430	98.55 248	79.25 335	86.65 460	66.85 450	82.69 370	95.57 315

PS-MVSNAJss		93.64 274	93.31 271	94.61 309	92.11 417	92.19 303	99.12 291	97.38 305	92.51 241	88.45 353	96.99 310	91.20 170	97.29 336	94.36 244	87.71 333	94.36 330

pmmvs5		90.17 354	89.09 355	93.40 356	92.10 418	89.77 363	99.74 179	95.58 423	85.88 390	87.24 375	95.74 348	73.41 389	96.48 382	88.54 343	83.56 367	93.95 372

N_pmnet		80.06 417	80.78 413	77.89 436	91.94 419	45.28 474	98.80 342	56.82 476	78.10 437	80.08 424	93.33 417	77.03 353	95.76 409	68.14 448	82.81 369	92.64 411

test_djsdf		92.83 293	92.29 295	94.47 319	91.90 420	92.46 298	99.55 235	97.27 323	91.17 288	89.96 314	96.07 342	81.10 314	96.89 362	94.67 239	88.91 313	94.05 363

SixPastTwentyTwo		88.73 372	88.01 373	90.88 391	91.85 421	82.24 428	98.22 381	95.18 433	88.97 341	82.26 411	96.89 312	71.75 394	96.67 375	84.00 388	82.98 368	93.72 389

K. test v3		88.05 378	87.24 379	90.47 400	91.82 422	82.23 429	98.96 320	97.42 301	89.05 336	76.93 438	95.60 355	68.49 408	95.42 414	85.87 377	81.01 390	93.75 385

OurMVSNet-221017-0		89.81 360	89.48 350	90.83 394	91.64 423	81.21 435	98.17 383	95.38 428	91.48 278	85.65 393	97.31 297	72.66 390	97.29 336	88.15 349	84.83 356	93.97 371

mvs_tets		91.81 314	91.08 317	94.00 338	91.63 424	90.58 345	98.67 353	97.43 299	92.43 243	87.37 373	97.05 307	71.76 393	97.32 331	94.75 236	88.68 319	94.11 359

Gipuma		66.95 430	65.00 430	72.79 442	91.52 425	67.96 454	66.16 465	95.15 434	47.89 463	58.54 460	67.99 465	29.74 462	87.54 459	50.20 464	77.83 410	62.87 465
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_fmvsmconf0.01_n		96.39 174	95.74 184	98.32 141	91.47 426	95.56 195	99.84 143	97.30 318	97.74 29	97.89 168	99.35 147	79.62 332	99.85 124	99.25 70	99.24 136	99.55 155

jajsoiax		91.92 312	91.18 315	94.15 330	91.35 427	90.95 336	99.00 312	97.42 301	92.61 233	87.38 372	97.08 304	72.46 391	97.36 326	94.53 242	88.77 317	94.13 358

MDA-MVSNet-bldmvs		84.09 402	81.52 409	91.81 385	91.32 428	88.00 389	98.67 353	95.92 414	80.22 431	55.60 463	93.32 418	68.29 410	93.60 438	73.76 437	76.61 421	93.82 383

MVP-Stereo		90.93 332	90.45 327	92.37 378	91.25 429	88.76 375	98.05 388	96.17 409	87.27 372	84.04 402	95.30 374	78.46 346	97.27 338	83.78 391	99.70 89	91.09 426
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MDA-MVSNet_test_wron		85.51 390	83.32 398	92.10 380	90.96 430	88.58 381	99.20 286	96.52 401	79.70 433	57.12 462	92.69 423	79.11 338	93.86 434	77.10 429	77.46 414	93.86 380

YYNet1		85.50 391	83.33 397	92.00 381	90.89 431	88.38 385	99.22 285	96.55 400	79.60 434	57.26 461	92.72 422	79.09 340	93.78 436	77.25 428	77.37 415	93.84 381

anonymousdsp		91.79 319	90.92 319	94.41 324	90.76 432	92.93 285	98.93 324	97.17 337	89.08 335	87.46 371	95.30 374	78.43 347	96.92 360	92.38 283	88.73 318	93.39 396

lessismore_v0				90.53 398	90.58 433	80.90 438		95.80 415		77.01 437	95.84 345	66.15 419	96.95 358	83.03 396	75.05 427	93.74 388

EG-PatchMatch MVS		85.35 392	83.81 395	89.99 407	90.39 434	81.89 431	98.21 382	96.09 411	81.78 424	74.73 444	93.72 415	51.56 452	97.12 345	79.16 420	88.61 320	90.96 429

EGC-MVSNET		69.38 423	63.76 433	86.26 426	90.32 435	81.66 434	96.24 426	93.85 449	0.99 473	3.22 474	92.33 429	52.44 449	92.92 443	59.53 460	84.90 355	84.21 454

CMPMVS	61.59 21	84.75 398	85.14 390	83.57 430	90.32 435	62.54 458	96.98 411	97.59 284	74.33 447	69.95 451	96.66 320	64.17 426	98.32 279	87.88 353	88.41 325	89.84 441
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		84.49 401	82.92 401	89.21 411	90.03 437	82.60 425	96.89 414	95.62 422	80.59 429	75.77 443	89.17 441	65.04 424	94.79 425	72.12 441	81.02 389	90.23 435

pmmvs6		85.69 387	83.84 394	91.26 390	90.00 438	84.41 413	97.82 393	96.15 410	75.86 441	81.29 418	95.39 369	61.21 437	96.87 365	83.52 394	73.29 430	92.50 414

ttmdpeth		88.23 377	87.06 380	91.75 386	89.91 439	87.35 393	98.92 327	95.73 417	87.92 363	84.02 403	96.31 331	68.23 411	96.84 366	86.33 371	76.12 422	91.06 427

DSMNet-mixed		88.28 376	88.24 370	88.42 419	89.64 440	75.38 448	98.06 387	89.86 463	85.59 395	88.20 360	92.14 430	76.15 368	91.95 448	78.46 423	96.05 238	97.92 282

UnsupCasMVSNet_eth		85.52 389	83.99 391	90.10 405	89.36 441	83.51 420	96.65 418	97.99 235	89.14 334	75.89 442	93.83 412	63.25 430	93.92 432	81.92 404	67.90 447	92.88 408

Anonymous20231206		86.32 385	85.42 388	89.02 413	89.11 442	80.53 441	99.05 306	95.28 429	85.43 397	82.82 409	93.92 411	74.40 382	93.44 439	66.99 449	81.83 379	93.08 404

Anonymous20240521		85.15 393	83.81 395	89.16 412	88.32 443	82.69 424	98.80 342	95.74 416	79.72 432	81.53 416	90.99 433	65.38 422	94.16 430	72.69 439	81.11 386	90.63 433

OpenMVS_ROB	79.82 20	83.77 405	81.68 408	90.03 406	88.30 444	82.82 423	98.46 364	95.22 431	73.92 448	76.00 441	91.29 432	55.00 445	96.94 359	68.40 447	88.51 324	90.34 434

test20.03		84.72 399	83.99 391	86.91 424	88.19 445	80.62 440	98.88 330	95.94 413	88.36 357	78.87 428	94.62 400	68.75 406	89.11 455	66.52 451	75.82 423	91.00 428

KD-MVS_self_test		83.59 406	82.06 406	88.20 420	86.93 446	80.70 439	97.21 404	96.38 404	82.87 418	82.49 410	88.97 442	67.63 413	92.32 446	73.75 438	62.30 458	91.58 424

MIMVSNet1		82.58 409	80.51 414	88.78 415	86.68 447	84.20 414	96.65 418	95.41 427	78.75 435	78.59 431	92.44 425	51.88 451	89.76 454	65.26 454	78.95 402	92.38 417

CL-MVSNet_self_test		84.50 400	83.15 400	88.53 418	86.00 448	81.79 432	98.82 338	97.35 309	85.12 399	83.62 407	90.91 435	76.66 360	91.40 449	69.53 445	60.36 459	92.40 416

UnsupCasMVSNet_bld		79.97 419	77.03 424	88.78 415	85.62 449	81.98 430	93.66 442	97.35 309	75.51 444	70.79 450	83.05 457	48.70 455	94.91 423	78.31 424	60.29 460	89.46 446

mvs5depth		84.87 396	82.90 402	90.77 395	85.59 450	84.84 411	91.10 455	93.29 453	83.14 415	85.07 398	94.33 408	62.17 433	97.32 331	78.83 422	72.59 433	90.14 437

Patchmatch-RL test		86.90 383	85.98 387	89.67 408	84.45 451	75.59 447	89.71 458	92.43 455	86.89 379	77.83 435	90.94 434	94.22 92	93.63 437	87.75 354	69.61 438	99.79 107

pmmvs-eth3d		84.03 403	81.97 407	90.20 404	84.15 452	87.09 395	98.10 386	94.73 439	83.05 416	74.10 447	87.77 448	65.56 421	94.01 431	81.08 408	69.24 440	89.49 445

test_fmvs3		79.99 418	80.17 416	79.45 435	84.02 453	62.83 456	99.05 306	93.49 452	88.29 359	80.06 425	86.65 452	28.09 464	88.00 456	88.63 340	73.27 431	87.54 452

PM-MVS		80.47 415	78.88 419	85.26 427	83.79 454	72.22 450	95.89 433	91.08 460	85.71 394	76.56 440	88.30 444	36.64 460	93.90 433	82.39 400	69.57 439	89.66 444

new-patchmatchnet		81.19 411	79.34 418	86.76 425	82.86 455	80.36 442	97.92 390	95.27 430	82.09 423	72.02 448	86.87 451	62.81 432	90.74 452	71.10 442	63.08 455	89.19 448

FE-MVSNET		81.05 413	78.81 420	87.79 422	81.98 456	83.70 416	98.23 379	91.78 459	81.27 426	74.29 446	87.44 449	60.92 439	90.67 453	64.92 455	68.43 443	89.01 449

mvsany_test3		82.12 410	81.14 411	85.06 428	81.87 457	70.41 452	97.09 408	92.14 456	91.27 287	77.84 434	88.73 443	39.31 459	95.49 411	90.75 315	71.24 435	89.29 447

WB-MVS		76.28 421	77.28 423	73.29 441	81.18 458	54.68 466	97.87 392	94.19 444	81.30 425	69.43 452	90.70 436	77.02 354	82.06 464	35.71 469	68.11 446	83.13 455

test_f		78.40 420	77.59 422	80.81 434	80.82 459	62.48 459	96.96 412	93.08 454	83.44 413	74.57 445	84.57 456	27.95 465	92.63 444	84.15 386	72.79 432	87.32 453

SSC-MVS		75.42 422	76.40 425	72.49 445	80.68 460	53.62 467	97.42 399	94.06 446	80.42 430	68.75 453	90.14 438	76.54 362	81.66 465	33.25 470	66.34 450	82.19 456

pmmvs3		80.27 416	77.77 421	87.76 423	80.32 461	82.43 427	98.23 379	91.97 457	72.74 450	78.75 429	87.97 447	57.30 444	90.99 451	70.31 443	62.37 457	89.87 440

testf1		68.38 426	66.92 427	72.78 443	78.80 462	50.36 469	90.95 456	87.35 468	55.47 459	58.95 458	88.14 445	20.64 469	87.60 457	57.28 461	64.69 452	80.39 458

APD_test2		68.38 426	66.92 427	72.78 443	78.80 462	50.36 469	90.95 456	87.35 468	55.47 459	58.95 458	88.14 445	20.64 469	87.60 457	57.28 461	64.69 452	80.39 458

ambc				83.23 431	77.17 464	62.61 457	87.38 460	94.55 443		76.72 439	86.65 452	30.16 461	96.36 388	84.85 385	69.86 437	90.73 431

test_vis3_rt		68.82 424	66.69 429	75.21 440	76.24 465	60.41 461	96.44 421	68.71 475	75.13 445	50.54 466	69.52 464	16.42 474	96.32 390	80.27 413	66.92 449	68.89 462

TDRefinement		84.76 397	82.56 404	91.38 389	74.58 466	84.80 412	97.36 402	94.56 442	84.73 404	80.21 423	96.12 341	63.56 428	98.39 269	87.92 352	63.97 454	90.95 430

E-PMN		52.30 434	52.18 436	52.67 451	71.51 467	45.40 473	93.62 443	76.60 473	36.01 467	43.50 468	64.13 467	27.11 466	67.31 470	31.06 471	26.06 466	45.30 469

EMVS		51.44 436	51.22 438	52.11 452	70.71 468	44.97 475	94.04 439	75.66 474	35.34 469	42.40 469	61.56 470	28.93 463	65.87 471	27.64 472	24.73 467	45.49 468

PMMVS2		67.15 429	64.15 432	76.14 439	70.56 469	62.07 460	93.89 440	87.52 467	58.09 458	60.02 457	78.32 459	22.38 468	84.54 462	59.56 459	47.03 464	81.80 457

FPMVS		68.72 425	68.72 426	68.71 447	65.95 470	44.27 476	95.97 432	94.74 438	51.13 462	53.26 464	90.50 437	25.11 467	83.00 463	60.80 458	80.97 391	78.87 460

wuyk23d		20.37 440	20.84 443	18.99 455	65.34 471	27.73 478	50.43 466	7.67 479	9.50 472	8.01 473	6.34 473	6.13 477	26.24 472	23.40 473	10.69 471	2.99 470

LCM-MVSNet		67.77 428	64.73 431	76.87 438	62.95 472	56.25 465	89.37 459	93.74 450	44.53 464	61.99 456	80.74 458	20.42 471	86.53 461	69.37 446	59.50 461	87.84 450

MVE	53.74 22	51.54 435	47.86 439	62.60 449	59.56 473	50.93 468	79.41 463	77.69 472	35.69 468	36.27 470	61.76 469	5.79 478	69.63 468	37.97 468	36.61 465	67.24 463
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 432	52.24 435	67.66 448	49.27 474	56.82 464	83.94 461	82.02 471	70.47 452	33.28 471	64.54 466	17.23 473	69.16 469	45.59 466	23.85 468	77.02 461

tmp_tt		65.23 431	62.94 434	72.13 446	44.90 475	50.03 471	81.05 462	89.42 466	38.45 465	48.51 467	99.90 18	54.09 447	78.70 467	91.84 296	18.26 469	87.64 451

PMVS	49.05 23	53.75 433	51.34 437	60.97 450	40.80 476	34.68 477	74.82 464	89.62 465	37.55 466	28.67 472	72.12 461	7.09 476	81.63 466	43.17 467	68.21 445	66.59 464
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test123		37.68 438	39.14 441	33.31 453	19.94 477	24.83 479	98.36 372	9.75 478	15.53 471	51.31 465	87.14 450	19.62 472	17.74 473	47.10 465	3.47 472	57.36 466

testmvs		40.60 437	44.45 440	29.05 454	19.49 478	14.11 480	99.68 204	18.47 477	20.74 470	64.59 455	98.48 255	10.95 475	17.09 474	56.66 463	11.01 470	55.94 467

mmdepth		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

monomultidepth		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

test_blank		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.02 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

eth-test2					0.00 479

eth-test					0.00 479

uanet_test		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

DCPMVS		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

cdsmvs_eth3d_5k		23.43 439	31.24 442	0.00 456	0.00 479	0.00 481	0.00 467	98.09 226	0.00 474	0.00 475	99.67 108	83.37 291	0.00 475	0.00 474	0.00 473	0.00 471

pcd_1.5k_mvsjas		7.60 442	10.13 445	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	91.20 170	0.00 475	0.00 474	0.00 473	0.00 471

sosnet-low-res		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

sosnet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uncertanet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

Regformer		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

ab-mvs-re		8.28 441	11.04 444	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	99.40 141	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uanet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 475	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

WAC-MVS						90.97 333								86.10 375

PC_three_1452									96.96 59	99.80 25	99.79 58	97.49 10	100.00 1	99.99 5	99.98 32	100.00 1

test_241102_TWO								98.43 151	97.27 46	99.80 25	99.94 4	97.18 21	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_THIRD									96.48 77	99.83 21	99.91 14	97.87 5	100.00 1	99.92 13	100.00 1	100.00 1

GSMVS																99.59 145

sam_mvs1												94.72 71				99.59 145

sam_mvs												94.25 91

MTGPA								98.28 199

test_post1							95.78 434				59.23 471	93.20 125	97.74 315	91.06 306

test_post											63.35 468	94.43 79	98.13 294

patchmatchnet-post											91.70 431	95.12 56	97.95 306

MTMP							99.87 124	96.49 402

test9_res														99.71 44	99.99 21	100.00 1

agg_prior2														99.48 59	100.00 1	100.00 1

test_prior4						98.05 77	99.94 84

test_prior2							99.95 67		95.78 99	99.73 44	99.76 67	96.00 37		99.78 31	100.00 1

旧先验2							99.46 253		94.21 159	99.85 17			99.95 80	96.96 188

新几何2							99.40 257

无先验							99.49 245	98.71 74	93.46 191				100.00 1	94.36 244		99.99 23

原ACMM2							99.90 108

testdata2													99.99 36	90.54 319

segment_acmp												96.68 29

testdata1							99.28 279		96.35 87

plane_prior5								97.87 249					98.37 275	97.79 162	89.55 307	94.52 319

plane_prior4											98.59 241

plane_prior3						91.64 321			96.63 72	93.01 279

plane_prior2							99.84 143		96.38 83

plane_prior						91.74 315	99.86 135		96.76 67						89.59 306

n2								0.00 480

nn								0.00 480

door-mid								89.69 464

test11								98.44 143

door								90.31 461

HQP5-MVS						91.85 311

BP-MVS														97.92 153

HQP4-MVS										93.37 274			98.39 269			94.53 317

HQP3-MVS								97.89 247							89.60 304

HQP2-MVS												80.65 322

MDTV_nov1_ep13_2view						96.26 162	96.11 428		91.89 264	98.06 161		94.40 81		94.30 247		99.67 125

ACMMP++_ref															87.04 340

ACMMP++															88.23 327

Test By Simon												92.82 136

High-resolution multi-view benchmark