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.

reproduce_model		99.76 18	99.69 22	99.98 23	99.96 96	99.93 47	100.00 1	99.42 141	98.81 59	100.00 1	100.00 1	98.98 104	100.00 1	100.00 1	100.00 1	100.00 1

reproduce-ours		99.76 18	99.69 22	99.98 23	99.96 96	99.94 41	100.00 1	99.42 141	98.82 55	100.00 1	100.00 1	98.99 101	100.00 1	100.00 1	100.00 1	100.00 1

our_new_method		99.76 18	99.69 22	99.98 23	99.96 96	99.94 41	100.00 1	99.42 141	98.82 55	100.00 1	100.00 1	98.99 101	100.00 1	100.00 1	100.00 1	100.00 1

MM		99.63 54	99.52 64	99.94 66	99.99 49	99.82 89	100.00 1	99.97 17	99.11 8	100.00 1	100.00 1	96.65 211	100.00 1	100.00 1	99.97 116	100.00 1

test_fmvsmvis_n_1920		99.46 80	99.37 81	99.73 125	98.88 313	99.18 173	100.00 1	99.26 280	98.85 49	99.79 192	100.00 1	97.70 168	100.00 1	99.98 76	99.86 138	100.00 1

test_fmvsm_n_1920		99.55 69	99.49 69	99.73 125	99.85 120	99.19 171	100.00 1	99.41 190	98.87 47	100.00 1	100.00 1	97.34 188	100.00 1	99.98 76	99.90 131	100.00 1

test_vis1_n_1920		97.77 229	97.24 250	99.34 183	99.79 146	98.04 255	100.00 1	99.25 282	98.88 44	100.00 1	100.00 1	77.52 392	100.00 1	99.88 106	99.85 141	100.00 1

mvsany_test1		99.57 66	99.48 72	99.85 90	99.86 119	99.54 125	100.00 1	99.36 218	98.94 37	100.00 1	100.00 1	97.97 152	100.00 1	99.88 106	99.28 168	100.00 1

patch_mono-2		99.04 134	99.79 6	96.81 337	99.92 108	90.47 387	100.00 1	99.41 190	98.95 35	100.00 1	100.00 1	99.78 9	100.00 1	100.00 1	100.00 1	99.95 131

DVP-MVS++		99.81 11	99.75 14	100.00 1	100.00 1	99.99 5	100.00 1	99.42 141	98.79 63	100.00 1	100.00 1	99.54 30	100.00 1	100.00 1	100.00 1	100.00 1

MSC_two_6792asdad				100.00 1	100.00 1	100.00 1		99.42 141					100.00 1	100.00 1	100.00 1	100.00 1

PC_three_1452									98.80 60	100.00 1	100.00 1	99.54 30	100.00 1	100.00 1	100.00 1	100.00 1

No_MVS				100.00 1	100.00 1	100.00 1		99.42 141					100.00 1	100.00 1	100.00 1	100.00 1

SED-MVS		99.83 7	99.77 9	100.00 1	100.00 1	99.99 5	100.00 1	99.42 141	99.03 21	100.00 1	100.00 1	99.50 41	100.00 1	100.00 1	100.00 1	100.00 1

OPU-MVS				100.00 1	100.00 1	100.00 1	100.00 1				100.00 1	99.54 30	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								99.42 141	99.03 21	100.00 1	100.00 1	99.56 27	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					100.00 1	99.99 5		99.42 141	99.03 21	100.00 1	100.00 1	99.50 41	100.00 1

ZNCC-MVS		99.71 33	99.62 44	99.97 34	99.99 49	99.90 63	100.00 1	99.79 45	97.97 118	99.97 122	100.00 1	98.97 106	100.00 1	99.94 96	100.00 1	100.00 1

DVP-MVS		99.83 7	99.78 7	100.00 1	100.00 1	99.99 5	100.00 1	99.42 141	99.04 16	100.00 1	100.00 1	99.53 33	100.00 1	100.00 1	100.00 1	100.00 1
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									98.79 63	100.00 1	100.00 1	99.61 20	100.00 1	100.00 1	100.00 1	100.00 1

test_0728_SECOND				100.00 1	99.99 49	99.99 5	100.00 1	99.42 141					100.00 1	100.00 1	100.00 1	100.00 1

DPM-MVS		99.63 54	99.51 66	100.00 1	99.90 112	100.00 1	100.00 1	99.43 124	99.00 27	100.00 1	100.00 1	99.58 26	100.00 1	97.64 279	100.00 1	100.00 1

GST-MVS		99.64 51	99.53 62	99.95 54	100.00 1	99.86 82	100.00 1	99.79 45	97.72 138	99.95 154	100.00 1	98.39 143	100.00 1	99.96 88	99.99 103	100.00 1

test_yl		99.51 71	99.37 81	99.95 54	99.82 125	99.90 63	100.00 1	99.47 79	97.48 171	100.00 1	100.00 1	99.80 6	100.00 1	99.98 76	97.75 243	99.94 136

Anonymous20240529		96.93 269	96.22 286	99.05 207	99.79 146	97.30 292	99.16 382	99.47 79	88.51 392	98.69 268	100.00 1	83.50 372	100.00 1	99.83 116	97.02 258	99.83 201

Anonymous202405211		97.87 224	97.53 235	98.90 218	99.81 131	96.70 310	99.35 358	99.46 94	92.98 362	98.83 262	99.99 189	90.63 298	100.00 1	99.70 149	97.03 257	100.00 1

DCV-MVSNet		99.51 71	99.37 81	99.95 54	99.82 125	99.90 63	100.00 1	99.47 79	97.48 171	100.00 1	100.00 1	99.80 6	100.00 1	99.98 76	97.75 243	99.94 136

SMA-MVS		99.69 39	99.59 47	99.98 23	99.99 49	99.93 47	100.00 1	99.43 124	97.50 169	100.00 1	100.00 1	99.43 54	100.00 1	100.00 1	100.00 1	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
DPE-MVS		99.79 14	99.73 17	99.99 12	99.99 49	99.98 17	100.00 1	99.42 141	98.91 41	100.00 1	100.00 1	99.22 80	100.00 1	100.00 1	100.00 1	100.00 1
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
thres100view900		99.25 113	99.01 125	99.95 54	99.81 131	99.87 79	100.00 1	99.94 22	97.13 199	99.83 180	99.96 218	97.01 195	100.00 1	99.59 176	97.85 234	99.98 112

tfpn200view9		99.26 109	99.03 123	99.96 45	99.81 131	99.89 70	100.00 1	99.94 22	97.23 193	99.83 180	99.96 218	97.04 191	100.00 1	99.59 176	97.85 234	99.98 112

CANet_DTU		99.02 141	98.90 145	99.41 172	99.88 116	98.71 207	100.00 1	99.29 257	98.84 51	100.00 1	100.00 1	94.02 252	100.00 1	98.08 262	99.96 119	99.52 258

MVS_0304		99.72 29	99.65 34	99.93 70	99.99 49	99.79 93	100.00 1	99.91 35	99.17 6	100.00 1	100.00 1	97.84 161	100.00 1	100.00 1	99.95 121	100.00 1

MP-MVS-pluss		99.61 61	99.50 67	99.97 34	99.98 86	99.92 53	100.00 1	99.42 141	97.53 164	99.77 195	100.00 1	98.77 127	100.00 1	99.99 64	100.00 1	99.99 110
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
xiu_mvs_v1_base_debu		99.35 93	99.21 104	99.79 110	99.67 173	99.71 102	99.78 299	99.36 218	98.13 104	100.00 1	100.00 1	97.00 198	100.00 1	99.83 116	99.07 174	99.66 252

ACMMP_NAP		99.67 46	99.57 52	99.97 34	99.98 86	99.92 53	100.00 1	99.42 141	97.83 129	100.00 1	100.00 1	98.89 118	100.00 1	99.98 76	100.00 1	100.00 1

xiu_mvs_v2_base		99.51 71	99.41 75	99.82 97	99.70 160	99.73 100	99.92 273	99.40 194	98.15 102	100.00 1	100.00 1	98.50 140	100.00 1	99.85 112	99.13 172	99.74 243

xiu_mvs_v1_base		99.35 93	99.21 104	99.79 110	99.67 173	99.71 102	99.78 299	99.36 218	98.13 104	100.00 1	100.00 1	97.00 198	100.00 1	99.83 116	99.07 174	99.66 252

xiu_mvs_v1_base_debi		99.35 93	99.21 104	99.79 110	99.67 173	99.71 102	99.78 299	99.36 218	98.13 104	100.00 1	100.00 1	97.00 198	100.00 1	99.83 116	99.07 174	99.66 252

MTAPA		99.68 43	99.59 47	99.97 34	99.99 49	99.91 56	100.00 1	99.42 141	98.32 92	99.94 156	100.00 1	98.65 132	100.00 1	99.96 88	100.00 1	100.00 1

HFP-MVS		99.74 25	99.67 30	99.96 45	100.00 1	99.89 70	100.00 1	99.76 49	97.95 122	100.00 1	100.00 1	99.31 68	100.00 1	99.99 64	100.00 1	100.00 1

region2R		99.72 29	99.64 37	99.97 34	100.00 1	99.90 63	100.00 1	99.74 55	97.86 128	100.00 1	100.00 1	99.19 83	100.00 1	99.99 64	100.00 1	100.00 1

PS-MVSNAJ		99.64 51	99.57 52	99.85 90	99.78 149	99.81 90	99.95 263	99.42 141	98.38 84	100.00 1	100.00 1	98.75 128	100.00 1	99.88 106	99.99 103	99.74 243

HPM-MVS++		99.82 9	99.76 12	99.99 12	99.99 49	99.98 17	100.00 1	99.83 39	98.88 44	99.96 126	100.00 1	99.21 81	100.00 1	100.00 1	100.00 1	99.99 110

XVS		99.79 14	99.73 17	99.98 23	100.00 1	99.94 41	100.00 1	99.75 52	98.67 70	100.00 1	100.00 1	99.16 85	100.00 1	100.00 1	100.00 1	100.00 1

X-MVStestdata		97.04 263	96.06 292	99.98 23	100.00 1	99.94 41	100.00 1	99.75 52	98.67 70	100.00 1	66.97 424	99.16 85	100.00 1	100.00 1	100.00 1	100.00 1

旧先验2							100.00 1		98.11 108	100.00 1			100.00 1	99.67 160

新几何1				99.99 12	100.00 1	99.96 24		99.81 42	97.89 125	100.00 1	100.00 1	99.20 82	100.00 1	97.91 271	100.00 1	100.00 1

无先验							100.00 1	99.80 43	97.98 116				100.00 1	99.33 197		100.00 1

原ACMM1				99.93 70	100.00 1	99.80 92		99.66 63	98.18 99	100.00 1	100.00 1	99.43 54	100.00 1	99.50 188	100.00 1	100.00 1

testdata2													100.00 1	97.36 292

testdata				99.66 137	99.99 49	98.97 195		99.73 56	97.96 121	100.00 1	100.00 1	99.42 57	100.00 1	99.28 201	100.00 1	100.00 1

1314		99.38 89	99.19 108	99.96 45	98.88 313	99.89 70	99.24 368	99.93 30	98.88 44	98.79 265	100.00 1	97.02 194	100.00 1	100.00 1	100.00 1	100.00 1

LFMVS		97.42 246	96.62 267	99.81 102	99.80 142	99.50 133	99.16 382	99.56 70	94.48 324	100.00 1	100.00 1	79.35 387	100.00 1	99.89 104	97.37 252	99.94 136

VDD-MVS		96.58 284	95.99 295	98.34 252	99.52 230	95.33 329	99.18 376	99.38 209	96.64 243	99.77 195	100.00 1	72.51 404	100.00 1	100.00 1	96.94 260	99.70 248

VDDNet		96.39 296	95.55 318	98.90 218	99.27 275	97.45 283	99.15 384	99.92 34	91.28 375	99.98 117	100.00 1	73.55 400	100.00 1	99.85 112	96.98 259	99.24 262

MVS		99.22 117	98.96 133	99.98 23	99.00 300	99.95 32	99.24 368	99.94 22	98.14 103	98.88 255	100.00 1	95.63 227	100.00 1	99.85 112	100.00 1	100.00 1

SD-MVS		99.81 11	99.75 14	99.99 12	99.99 49	99.96 24	100.00 1	99.42 141	99.01 26	100.00 1	100.00 1	99.33 63	100.00 1	100.00 1	100.00 1	100.00 1
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
MSLP-MVS++		99.89 1	99.85 2	99.99 12	100.00 1	99.96 24	100.00 1	99.95 19	99.11 8	100.00 1	100.00 1	99.60 21	100.00 1	100.00 1	100.00 1	100.00 1

VNet		99.04 134	98.75 156	99.90 77	99.81 131	99.75 97	99.50 343	99.47 79	98.36 88	100.00 1	99.99 189	94.66 244	100.00 1	99.90 102	97.09 256	99.96 125

ACMMPR		99.74 25	99.67 30	99.96 45	100.00 1	99.89 70	100.00 1	99.76 49	97.95 122	100.00 1	100.00 1	99.29 74	100.00 1	99.99 64	100.00 1	100.00 1

thres600view7		99.24 116	99.00 127	99.95 54	99.81 131	99.87 79	100.00 1	99.94 22	97.13 199	99.83 180	99.96 218	97.01 195	100.00 1	99.54 184	97.77 242	99.97 119

MP-MVS		99.61 61	99.49 69	99.98 23	99.99 49	99.94 41	100.00 1	99.42 141	97.82 130	99.99 111	100.00 1	98.20 146	100.00 1	99.99 64	100.00 1	100.00 1
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
thres400		99.26 109	99.03 123	99.95 54	99.81 131	99.89 70	100.00 1	99.94 22	97.23 193	99.83 180	99.96 218	97.04 191	100.00 1	99.59 176	97.85 234	99.97 119

thres200		99.27 107	99.04 122	99.96 45	99.81 131	99.90 63	100.00 1	99.94 22	97.31 188	99.83 180	99.96 218	97.04 191	100.00 1	99.62 170	97.88 232	99.98 112

PGM-MVS		99.69 39	99.61 45	99.95 54	99.99 49	99.85 85	100.00 1	99.58 67	97.69 142	100.00 1	100.00 1	99.44 50	100.00 1	99.79 123	100.00 1	100.00 1

MCST-MVS		99.85 3	99.80 4	100.00 1	100.00 1	99.99 5	100.00 1	99.73 56	99.19 5	100.00 1	100.00 1	99.31 68	100.00 1	100.00 1	100.00 1	100.00 1

mPP-MVS		99.69 39	99.60 46	99.97 34	100.00 1	99.91 56	100.00 1	99.42 141	97.91 124	100.00 1	100.00 1	99.04 98	100.00 1	100.00 1	100.00 1	100.00 1

EPNet		99.62 59	99.69 22	99.42 171	99.99 49	98.37 228	100.00 1	99.89 37	98.83 53	100.00 1	100.00 1	98.97 106	100.00 1	99.90 102	99.61 162	99.89 168
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		99.85 3	99.80 4	100.00 1	100.00 1	99.99 5	100.00 1	99.77 48	99.07 11	100.00 1	100.00 1	99.39 61	100.00 1	100.00 1	100.00 1	100.00 1

NCCC		99.86 2	99.82 3	100.00 1	100.00 1	99.99 5	100.00 1	99.71 61	99.07 11	100.00 1	100.00 1	99.59 24	100.00 1	100.00 1	100.00 1	100.00 1

CP-MVS		99.67 46	99.58 49	99.95 54	100.00 1	99.84 87	100.00 1	99.42 141	97.77 135	100.00 1	100.00 1	99.07 92	100.00 1	100.00 1	100.00 1	100.00 1

DELS-MVS		99.62 59	99.56 57	99.82 97	99.92 108	99.45 142	100.00 1	99.78 47	98.92 39	99.73 200	100.00 1	97.70 168	100.00 1	99.93 98	100.00 1	100.00 1
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
CPTT-MVS		99.49 76	99.38 78	99.85 90	100.00 1	99.54 125	100.00 1	99.42 141	97.58 159	99.98 117	100.00 1	97.43 185	100.00 1	99.99 64	100.00 1	100.00 1

UGNet		98.41 202	98.11 210	99.31 190	99.54 219	98.55 217	99.18 376	100.00 1	98.64 73	99.79 192	99.04 345	87.61 338	100.00 1	99.30 200	99.89 132	99.40 261
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
sss		99.45 81	99.34 88	99.80 107	99.76 152	99.50 133	100.00 1	99.91 35	97.72 138	99.98 117	99.94 231	98.45 141	100.00 1	99.53 186	98.75 184	99.89 168

DP-MVS Recon		99.76 18	99.69 22	99.98 23	100.00 1	99.95 32	100.00 1	99.52 72	97.99 114	99.99 111	100.00 1	99.72 14	100.00 1	99.96 88	100.00 1	100.00 1

QAPM		98.99 147	98.66 165	99.96 45	99.01 296	99.87 79	99.88 283	99.93 30	97.99 114	98.68 269	100.00 1	93.17 264	100.00 1	99.32 198	100.00 1	100.00 1

PAPM_NR		99.74 25	99.66 33	99.99 12	100.00 1	99.96 24	100.00 1	99.47 79	97.87 127	100.00 1	100.00 1	99.60 21	100.00 1	100.00 1	100.00 1	100.00 1

PAPR		99.76 18	99.68 28	99.99 12	100.00 1	99.96 24	100.00 1	99.47 79	98.16 100	100.00 1	100.00 1	99.51 37	100.00 1	100.00 1	100.00 1	100.00 1

RPSCF		97.37 248	98.24 202	94.76 365	99.80 142	84.57 402	99.99 219	99.05 359	94.95 309	99.82 188	100.00 1	94.03 251	100.00 1	98.15 261	98.38 200	99.70 248

CSCG		99.28 106	99.35 86	99.05 207	99.99 49	97.15 298	100.00 1	99.47 79	97.44 175	99.42 218	100.00 1	97.83 163	100.00 1	99.99 64	100.00 1	100.00 1

API-MVS		99.72 29	99.70 21	99.79 110	99.97 90	99.37 152	99.96 257	99.94 22	98.48 79	100.00 1	100.00 1	98.92 115	100.00 1	100.00 1	100.00 1	100.00 1

ACMMP		99.65 49	99.57 52	99.89 79	99.99 49	99.66 110	99.75 308	99.73 56	98.16 100	99.75 198	100.00 1	98.90 117	100.00 1	99.96 88	99.88 134	100.00 1
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
CNLPA		99.72 29	99.65 34	99.91 74	99.97 90	99.72 101	100.00 1	99.47 79	98.43 82	99.88 173	100.00 1	99.14 88	100.00 1	99.97 86	100.00 1	100.00 1

PHI-MVS		99.50 74	99.39 77	99.82 97	100.00 1	99.45 142	100.00 1	99.94 22	96.38 260	100.00 1	100.00 1	98.18 147	100.00 1	100.00 1	100.00 1	100.00 1

PVSNet	94.91 18	99.30 104	99.25 97	99.44 166	100.00 1	98.32 234	100.00 1	99.86 38	98.04 111	100.00 1	100.00 1	96.10 220	100.00 1	99.55 181	99.73 150	100.00 1

PVSNet_0	93.57 19	96.41 292	95.74 309	98.41 247	99.84 121	95.22 331	100.00 1	100.00 1	98.08 109	97.55 334	99.78 267	84.40 364	100.00 1	100.00 1	81.99 397	100.00 1

DeepPCF-MVS	98.03 4	98.54 190	99.72 19	94.98 362	99.99 49	84.94 401	100.00 1	99.42 141	99.98 1	100.00 1	100.00 1	98.11 149	100.00 1	100.00 1	100.00 1	100.00 1

DeepC-MVS_fast	98.92 1	99.75 23	99.67 30	99.99 12	99.99 49	99.96 24	99.73 314	99.52 72	99.06 13	100.00 1	100.00 1	98.80 126	100.00 1	99.95 94	100.00 1	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
MG-MVS		99.75 23	99.68 28	99.97 34	100.00 1	99.91 56	99.98 245	99.47 79	99.09 10	100.00 1	100.00 1	98.59 136	100.00 1	99.95 94	100.00 1	100.00 1

AdaColmap		99.44 82	99.26 95	99.95 54	100.00 1	99.86 82	99.70 319	99.99 13	98.53 76	99.90 168	100.00 1	95.34 229	100.00 1	99.92 99	100.00 1	100.00 1

PLC	98.56 2	99.70 36	99.74 16	99.58 151	100.00 1	98.79 201	100.00 1	99.54 71	98.58 75	99.96 126	100.00 1	99.59 24	100.00 1	100.00 1	100.00 1	99.94 136
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MAR-MVS		99.49 76	99.36 84	99.89 79	99.97 90	99.66 110	99.74 309	99.95 19	97.89 125	100.00 1	100.00 1	96.71 210	100.00 1	100.00 1	100.00 1	100.00 1
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
3Dnovator+	95.58 15	99.03 136	98.71 162	99.96 45	98.99 303	99.89 70	100.00 1	99.51 76	98.96 32	98.32 293	100.00 1	92.78 270	100.00 1	99.87 109	100.00 1	100.00 1

3Dnovator	95.63 14	99.06 131	98.76 155	99.96 45	98.86 317	99.90 63	99.98 245	99.93 30	98.95 35	98.49 284	100.00 1	92.91 268	100.00 1	99.71 146	100.00 1	100.00 1

OpenMVS	95.20 17	98.76 167	98.41 188	99.78 115	98.89 312	99.81 90	99.99 219	99.76 49	98.02 112	98.02 311	100.00 1	91.44 286	100.00 1	99.63 169	99.97 116	99.55 256

UBG		99.36 92	99.27 91	99.63 140	99.63 190	99.01 188	100.00 1	99.43 124	96.99 209	100.00 1	99.92 236	99.69 17	99.99 98	99.74 137	98.06 222	99.88 181

fmvsm_l_conf0.5_n_a		99.63 54	99.55 59	99.86 87	99.83 124	99.58 119	100.00 1	99.36 218	98.98 30	100.00 1	100.00 1	97.85 159	99.99 98	100.00 1	99.94 124	100.00 1

fmvsm_l_conf0.5_n		99.63 54	99.56 57	99.86 87	99.81 131	99.59 117	100.00 1	99.36 218	98.98 30	100.00 1	100.00 1	97.92 155	99.99 98	100.00 1	99.95 121	100.00 1

fmvsm_s_conf0.5_n_a		99.32 100	99.15 113	99.81 102	99.80 142	99.47 141	100.00 1	99.35 229	98.22 95	100.00 1	100.00 1	95.21 234	99.99 98	99.96 88	99.86 138	99.98 112

fmvsm_s_conf0.5_n		99.21 118	99.01 125	99.83 95	99.84 121	99.53 127	100.00 1	99.38 209	98.29 94	100.00 1	100.00 1	93.62 257	99.99 98	99.99 64	99.93 127	99.98 112

test_fmvsmconf_n		99.56 67	99.46 74	99.86 87	99.68 165	99.58 119	100.00 1	99.31 247	98.92 39	99.88 173	100.00 1	97.35 187	99.99 98	99.98 76	99.99 103	100.00 1

test_cas_vis1_n_1920		98.63 180	98.25 199	99.77 118	99.69 161	99.32 155	100.00 1	99.31 247	98.84 51	99.96 126	100.00 1	87.42 340	99.99 98	99.14 208	99.86 138	100.00 1

test_vis1_n		96.69 279	95.81 303	99.32 188	99.14 281	97.98 258	99.97 251	98.98 371	98.45 81	100.00 1	100.00 1	66.44 410	99.99 98	99.78 129	99.57 164	100.00 1

h-mvs33		97.03 264	96.53 270	98.51 239	99.79 146	95.90 321	99.45 347	99.45 102	98.21 96	100.00 1	99.78 267	97.49 179	99.99 98	99.72 142	74.92 407	99.65 255

ZD-MVS					100.00 1	99.98 17		99.80 43	97.31 188	100.00 1	100.00 1	99.32 66	99.99 98	100.00 1	100.00 1

SR-MVS-dyc-post		99.63 54	99.52 64	99.97 34	99.99 49	99.91 56	100.00 1	99.42 141	97.62 150	100.00 1	100.00 1	98.65 132	99.99 98	99.99 64	100.00 1	100.00 1

SF-MVS		99.66 48	99.57 52	99.95 54	99.99 49	99.85 85	100.00 1	99.42 141	97.67 143	100.00 1	100.00 1	99.05 95	99.99 98	100.00 1	100.00 1	100.00 1

9.14			99.57 52		99.99 49		100.00 1	99.42 141	97.54 162	100.00 1	100.00 1	99.15 87	99.99 98	100.00 1	100.00 1

SR-MVS		99.68 43	99.58 49	99.98 23	100.00 1	99.95 32	100.00 1	99.64 64	97.59 158	100.00 1	100.00 1	98.99 101	99.99 98	100.00 1	100.00 1	100.00 1

TSAR-MVS + MP.		99.82 9	99.77 9	99.99 12	100.00 1	99.96 24	100.00 1	99.43 124	99.05 15	100.00 1	100.00 1	99.45 49	99.99 98	100.00 1	100.00 1	100.00 1
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APDe-MVS		99.84 6	99.78 7	99.99 12	100.00 1	99.98 17	100.00 1	99.44 116	99.06 13	100.00 1	100.00 1	99.56 27	99.99 98	100.00 1	100.00 1	100.00 1
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
APD-MVS_3200maxsize		99.65 49	99.55 59	99.97 34	99.99 49	99.91 56	100.00 1	99.48 78	97.54 162	100.00 1	100.00 1	98.97 106	99.99 98	99.98 76	100.00 1	100.00 1

CDPH-MVS		99.73 28	99.64 37	99.99 12	100.00 1	99.97 21	100.00 1	99.42 141	98.02 112	100.00 1	100.00 1	99.32 66	99.99 98	100.00 1	100.00 1	100.00 1

TSAR-MVS + GP.		99.61 61	99.69 22	99.35 182	99.99 49	98.06 253	100.00 1	99.36 218	99.83 2	100.00 1	100.00 1	98.95 110	99.99 98	100.00 1	99.11 173	100.00 1

SteuartSystems-ACMMP		99.78 16	99.71 20	99.98 23	99.76 152	99.95 32	100.00 1	99.42 141	98.69 68	100.00 1	100.00 1	99.52 36	99.99 98	100.00 1	100.00 1	100.00 1
Skip Steuart: Steuart Systems R&D Blog.
PVSNet_BlendedMVS		98.71 171	98.62 170	98.98 214	99.98 86	99.60 115	100.00 1	100.00 1	97.23 193	100.00 1	99.03 348	96.57 213	99.99 98	100.00 1	94.75 300	97.35 369

PVSNet_Blended		99.48 78	99.36 84	99.83 95	99.98 86	99.60 115	100.00 1	100.00 1	97.79 133	100.00 1	100.00 1	96.57 213	99.99 98	100.00 1	99.88 134	99.90 162

HY-MVS	96.53 9	99.50 74	99.35 86	99.96 45	99.81 131	99.93 47	99.64 326	100.00 1	97.97 118	99.84 177	99.85 252	98.94 112	99.99 98	99.86 110	98.23 213	99.95 131

PatchMatch-RL		99.02 141	98.78 153	99.74 122	99.99 49	99.29 158	100.00 1	100.00 1	98.38 84	99.89 171	99.81 261	93.14 266	99.99 98	97.85 273	99.98 113	99.95 131

F-COLMAP		99.64 51	99.64 37	99.67 134	99.99 49	99.07 179	100.00 1	99.44 116	98.30 93	99.90 168	100.00 1	99.18 84	99.99 98	99.91 101	100.00 1	99.94 136

testing91		99.18 120	99.10 117	99.41 172	99.60 201	98.43 220	100.00 1	99.43 124	96.76 227	99.82 188	99.92 236	99.05 95	99.98 123	99.62 170	97.67 247	99.81 215

testing99		99.18 120	99.10 117	99.41 172	99.60 201	98.43 220	100.00 1	99.43 124	96.76 227	99.84 177	99.92 236	99.06 93	99.98 123	99.62 170	97.67 247	99.81 215

test_8					100.00 1	99.91 56	100.00 1	99.42 141	97.70 140	100.00 1	100.00 1	99.51 37	99.98 123

MVS_Test		98.93 156	98.65 166	99.77 118	99.62 197	99.50 133	99.99 219	99.19 304	95.52 295	99.96 126	99.86 247	96.54 215	99.98 123	98.65 235	98.48 191	99.82 206

RPMNet		95.26 331	93.82 340	99.56 154	99.31 271	98.86 198	99.13 387	99.42 141	79.82 410	99.96 126	95.13 403	95.69 226	99.98 123	77.54 413	98.40 196	99.84 197

WTY-MVS		99.54 70	99.40 76	99.95 54	99.81 131	99.93 47	100.00 1	100.00 1	97.98 116	99.84 177	100.00 1	98.94 112	99.98 123	99.86 110	98.21 214	99.94 136

ab-mvs		98.42 200	98.02 219	99.61 143	99.71 158	99.00 191	99.10 390	99.64 64	96.70 236	99.04 248	99.81 261	90.64 297	99.98 123	99.64 166	97.93 229	99.84 197

testing11		99.26 109	99.19 108	99.46 163	99.64 188	98.61 213	100.00 1	99.43 124	96.94 212	99.92 163	99.94 231	99.43 54	99.97 130	99.67 160	97.79 241	99.82 206

sasdasda		99.03 136	98.73 158	99.94 66	99.75 154	99.95 32	100.00 1	99.30 251	97.64 147	100.00 1	100.00 1	95.22 232	99.97 130	99.76 132	96.90 261	99.91 151

FE-MVS		99.16 123	98.99 129	99.66 137	99.65 182	99.18 173	99.58 334	99.43 124	95.24 304	99.91 166	99.59 304	99.37 62	99.97 130	98.31 253	99.81 146	99.83 201

TEST9					100.00 1	99.95 32	100.00 1	99.42 141	97.65 145	100.00 1	100.00 1	99.53 33	99.97 130

train_agg		99.71 33	99.63 41	99.97 34	100.00 1	99.95 32	100.00 1	99.42 141	97.70 140	100.00 1	100.00 1	99.51 37	99.97 130	100.00 1	100.00 1	100.00 1

agg_prior					100.00 1	99.88 77		99.42 141		100.00 1			99.97 130

canonicalmvs		99.03 136	98.73 158	99.94 66	99.75 154	99.95 32	100.00 1	99.30 251	97.64 147	100.00 1	100.00 1	95.22 232	99.97 130	99.76 132	96.90 261	99.91 151

EI-MVSNet-UG-set		99.69 39	99.63 41	99.87 84	99.99 49	99.64 112	99.95 263	99.44 116	98.35 90	100.00 1	100.00 1	98.98 104	99.97 130	99.98 76	100.00 1	100.00 1

test_prior				99.90 77	100.00 1	99.75 97		99.73 56					99.97 130			100.00 1

test12				99.95 54	99.99 49	99.89 70		99.42 141		100.00 1		99.24 79	99.97 130		100.00 1	100.00 1

APD-MVS		99.68 43	99.58 49	99.97 34	99.99 49	99.96 24	100.00 1	99.42 141	97.53 164	100.00 1	100.00 1	99.27 77	99.97 130	100.00 1	100.00 1	100.00 1
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DP-MVS		98.86 161	98.54 177	99.81 102	99.97 90	99.45 142	99.52 341	99.40 194	94.35 328	98.36 289	100.00 1	96.13 219	99.97 130	99.12 211	100.00 1	100.00 1

LS3D		99.31 102	99.13 114	99.87 84	99.99 49	99.71 102	99.55 337	99.46 94	97.32 186	99.82 188	100.00 1	96.85 205	99.97 130	99.14 208	100.00 1	99.92 149

MGCFI-Net		99.01 143	98.70 164	99.93 70	99.74 156	99.94 41	100.00 1	99.29 257	97.60 157	100.00 1	100.00 1	95.10 236	99.96 143	99.74 137	96.85 263	99.91 151

fmvsm_s_conf0.1_n_a		98.71 171	98.36 195	99.78 115	99.09 286	99.42 146	100.00 1	99.26 280	97.42 177	100.00 1	100.00 1	89.78 310	99.96 143	99.82 121	99.85 141	99.97 119

fmvsm_s_conf0.1_n		98.77 166	98.42 187	99.82 97	99.47 249	99.52 130	100.00 1	99.27 273	97.53 164	100.00 1	100.00 1	89.73 312	99.96 143	99.84 115	99.93 127	99.97 119

test_fmvs1_n		97.43 245	96.86 258	99.15 203	99.68 165	97.48 282	99.99 219	98.98 371	98.82 55	100.00 1	100.00 1	74.85 399	99.96 143	99.67 160	99.70 153	100.00 1

test_fmvs1		98.37 205	98.04 217	99.34 183	99.84 121	98.07 251	100.00 1	99.00 368	98.85 49	100.00 1	100.00 1	85.11 361	99.96 143	99.69 156	99.88 134	100.00 1

FA-MVS(test-final)		99.00 144	98.75 156	99.73 125	99.63 190	99.43 145	99.83 289	99.43 124	95.84 285	99.52 210	99.37 325	97.84 161	99.96 143	97.63 280	99.68 154	99.79 235

CANet		99.40 85	99.24 100	99.89 79	99.99 49	99.76 96	100.00 1	99.73 56	98.40 83	99.78 194	100.00 1	95.28 230	99.96 143	100.00 1	99.99 103	99.96 125

MSP-MVS		99.81 11	99.77 9	99.94 66	100.00 1	99.86 82	100.00 1	99.42 141	98.87 47	100.00 1	100.00 1	99.65 19	99.96 143	100.00 1	100.00 1	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
RRT-MVS		98.75 169	98.52 180	99.44 166	99.65 182	98.57 216	99.90 277	99.08 344	96.51 251	99.96 126	99.95 225	92.59 276	99.96 143	99.60 174	99.45 167	99.81 215

EI-MVSNet-Vis-set		99.70 36	99.64 37	99.87 84	100.00 1	99.64 112	99.98 245	99.44 116	98.35 90	99.99 111	100.00 1	99.04 98	99.96 143	99.98 76	100.00 1	100.00 1

HPM-MVS_fast		99.60 64	99.49 69	99.91 74	99.99 49	99.78 94	100.00 1	99.42 141	97.09 201	100.00 1	100.00 1	98.95 110	99.96 143	99.98 76	100.00 1	100.00 1

HPM-MVS		99.59 65	99.50 67	99.89 79	100.00 1	99.70 106	100.00 1	99.42 141	97.46 173	100.00 1	100.00 1	98.60 135	99.96 143	99.99 64	100.00 1	100.00 1
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
BH-w/o		98.82 164	98.81 151	98.88 220	99.62 197	96.71 309	100.00 1	99.28 263	97.09 201	98.81 263	100.00 1	94.91 240	99.96 143	99.54 184	100.00 1	99.96 125

test_vis1_rt		93.10 351	92.93 352	93.58 375	99.63 190	85.07 400	99.99 219	93.71 421	97.49 170	90.96 393	97.10 395	60.40 412	99.95 156	99.24 204	97.90 231	95.72 397

AllTest		98.55 187	98.40 189	98.99 212	99.93 105	97.35 288	100.00 1	99.40 194	97.08 203	99.09 242	99.98 194	93.37 260	99.95 156	96.94 301	99.84 143	99.68 250

TestCases				98.99 212	99.93 105	97.35 288		99.40 194	97.08 203	99.09 242	99.98 194	93.37 260	99.95 156	96.94 301	99.84 143	99.68 250

CHOSEN 1792x2688		99.00 144	98.91 142	99.25 198	99.90 112	97.79 273	100.00 1	99.99 13	98.79 63	98.28 296	100.00 1	93.63 256	99.95 156	99.66 164	99.95 121	100.00 1

114514_t		99.39 86	99.25 97	99.81 102	99.97 90	99.48 140	100.00 1	99.42 141	95.53 293	100.00 1	100.00 1	98.37 144	99.95 156	99.97 86	100.00 1	100.00 1

PVSNet_Blended_VisFu		99.33 98	99.18 111	99.78 115	99.82 125	99.49 136	100.00 1	99.95 19	97.36 180	99.63 206	100.00 1	96.45 217	99.95 156	99.79 123	99.65 158	99.89 168

MVS_111021_LR		99.70 36	99.65 34	99.88 83	99.96 96	99.70 106	100.00 1	99.97 17	98.96 32	100.00 1	100.00 1	97.93 154	99.95 156	99.99 64	100.00 1	100.00 1

MVS_111021_HR		99.71 33	99.63 41	99.93 70	99.95 100	99.83 88	100.00 1	100.00 1	98.89 43	100.00 1	100.00 1	97.85 159	99.95 156	100.00 1	100.00 1	100.00 1

DeepC-MVS	97.84 5	99.00 144	98.80 152	99.60 145	99.93 105	99.03 184	100.00 1	99.40 194	98.61 74	99.33 228	100.00 1	92.23 280	99.95 156	99.74 137	99.96 119	99.83 201
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PCF-MVS	98.23 3	98.69 174	98.37 193	99.62 142	99.78 149	99.02 186	99.23 373	99.06 357	96.43 254	98.08 305	100.00 1	94.72 243	99.95 156	98.16 260	99.91 130	99.90 162
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MSDG		98.90 159	98.63 169	99.70 130	99.92 108	99.25 164	100.00 1	99.37 212	95.71 287	99.40 224	100.00 1	96.58 212	99.95 156	96.80 308	99.94 124	99.91 151

COLMAP_ROB	97.10 7	98.29 209	98.17 207	98.65 231	99.94 103	97.39 285	99.30 364	99.40 194	95.64 288	97.75 325	100.00 1	92.69 275	99.95 156	98.89 221	99.92 129	98.62 272
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
UWE-MVS		99.18 120	99.06 120	99.51 156	99.67 173	98.80 200	100.00 1	99.43 124	96.80 224	99.93 162	99.86 247	99.79 8	99.94 168	97.78 275	98.33 206	99.80 232

test_fmvsmconf0.1_n		99.25 113	99.05 121	99.82 97	98.92 309	99.55 122	100.00 1	99.23 291	98.91 41	99.75 198	99.97 203	94.79 242	99.94 168	99.94 96	99.99 103	99.97 119

UA-Net		99.06 131	98.83 148	99.74 122	99.52 230	99.40 148	99.08 393	99.45 102	97.64 147	99.83 180	100.00 1	95.80 223	99.94 168	98.35 251	99.80 148	99.88 181

XVG-OURS-SEG-HR		98.27 212	98.31 197	98.14 268	99.59 205	95.92 319	100.00 1	99.36 218	98.48 79	99.21 233	100.00 1	89.27 319	99.94 168	99.76 132	99.17 170	98.56 273

balanced_conf03		99.43 83	99.28 90	99.85 90	99.68 165	99.68 108	99.97 251	99.28 263	97.03 206	99.96 126	99.97 203	97.90 156	99.93 172	99.77 130	100.00 1	99.94 136

alignmvs		99.38 89	99.21 104	99.91 74	99.73 157	99.92 53	100.00 1	99.51 76	97.61 154	100.00 1	100.00 1	99.06 93	99.93 172	99.83 116	97.12 255	99.90 162

cascas		98.43 198	98.07 215	99.50 159	99.65 182	99.02 186	100.00 1	99.22 294	94.21 331	99.72 201	99.98 194	92.03 283	99.93 172	99.68 157	98.12 219	99.54 257

MVSMamba_PlusPlus		99.39 86	99.25 97	99.80 107	99.68 165	99.59 117	99.99 219	99.30 251	96.66 241	99.96 126	99.97 203	97.89 157	99.92 175	99.76 132	100.00 1	99.90 162

XVG-OURS		98.30 207	98.36 195	98.13 271	99.58 210	95.91 320	100.00 1	99.36 218	98.69 68	99.23 232	100.00 1	91.20 289	99.92 175	99.34 196	97.82 237	98.56 273

test_fmvsmconf0.01_n		98.60 182	98.24 202	99.67 134	96.90 385	99.21 169	99.99 219	99.04 362	98.80 60	99.57 208	99.96 218	90.12 304	99.91 177	99.89 104	99.89 132	99.90 162

APD_test1		93.07 352	94.14 338	89.85 383	99.18 279	72.49 411	99.76 306	98.90 378	92.86 366	96.35 359	99.94 231	75.56 397	99.91 177	86.73 395	97.98 224	97.15 374

diffmvs		98.96 151	98.73 158	99.63 140	99.54 219	99.16 175	100.00 1	99.18 311	97.33 185	99.96 126	100.00 1	94.60 245	99.91 177	99.66 164	98.33 206	99.82 206
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GDP-MVS		99.39 86	99.26 95	99.77 118	99.53 222	99.55 122	100.00 1	99.11 335	97.14 197	99.96 126	100.00 1	99.83 5	99.89 180	98.47 246	99.26 169	99.87 191

BP-MVS1		99.56 67	99.48 72	99.79 110	99.48 245	99.61 114	100.00 1	99.32 240	97.34 183	99.94 156	100.00 1	99.74 13	99.89 180	99.75 136	99.72 151	99.87 191

tpmvs		98.59 183	98.38 191	99.23 199	99.69 161	97.90 265	99.31 363	99.47 79	94.52 322	99.68 204	99.28 330	97.64 171	99.89 180	97.71 277	98.17 218	99.89 168

mvsmamba		99.05 133	98.98 130	99.27 196	99.57 214	98.10 249	100.00 1	99.28 263	95.92 279	99.96 126	99.97 203	96.73 209	99.89 180	99.72 142	99.65 158	99.81 215

Test_1112_low_res		98.83 163	98.60 173	99.51 156	99.69 161	98.75 203	99.99 219	99.14 324	96.81 223	98.84 260	99.06 342	97.45 182	99.89 180	98.66 233	97.75 243	99.89 168

1112_ss		98.91 157	98.71 162	99.51 156	99.69 161	98.75 203	99.99 219	99.15 319	96.82 222	98.84 260	100.00 1	97.45 182	99.89 180	98.66 233	97.75 243	99.89 168

IB-MVS	96.24 12	97.54 240	96.95 255	99.33 186	99.67 173	98.10 249	100.00 1	99.47 79	97.42 177	99.26 231	99.69 279	98.83 123	99.89 180	99.43 190	78.77 405	100.00 1
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
SDMVSNet		98.49 195	98.08 213	99.73 125	99.82 125	99.53 127	99.99 219	99.45 102	97.62 150	99.38 225	99.86 247	90.06 307	99.88 187	99.92 99	96.61 266	99.79 235

mamv4		98.95 154	99.11 116	98.46 242	99.68 165	95.67 326	99.14 386	99.27 273	96.43 254	99.94 156	99.97 203	97.79 164	99.88 187	99.77 130	100.00 1	99.84 197

testing222		99.14 125	98.94 138	99.73 125	99.67 173	99.51 131	100.00 1	99.43 124	96.90 218	99.99 111	99.90 241	98.55 138	99.86 189	98.85 223	97.18 254	99.81 215

dcpmvs_2		98.87 160	99.53 62	96.90 331	99.87 118	90.88 386	99.94 268	99.07 349	98.20 98	100.00 1	100.00 1	98.69 131	99.86 189	100.00 1	100.00 1	99.95 131

tpm cat1		98.05 219	97.76 227	98.92 217	99.50 239	97.10 301	99.77 304	99.30 251	90.20 386	99.72 201	98.71 367	97.71 167	99.86 189	96.75 312	98.20 215	99.81 215

tpmrst		98.98 150	98.93 140	99.14 204	99.61 199	97.74 274	99.52 341	99.36 218	96.05 276	99.98 117	99.64 292	99.04 98	99.86 189	98.94 218	98.19 216	99.82 206

MDTV_nov1_ep13			98.94 138		99.53 222	98.36 230	99.39 354	99.46 94	96.54 248	99.99 111	99.63 296	98.92 115	99.86 189	98.30 256	98.71 185

OMC-MVS		99.27 107	99.38 78	98.96 215	99.95 100	97.06 302	100.00 1	99.40 194	98.83 53	99.88 173	100.00 1	97.01 195	99.86 189	99.47 189	99.84 143	99.97 119

mmtdpeth		94.58 335	94.18 337	95.81 354	98.82 322	91.09 385	99.99 219	98.61 387	96.38 260	100.00 1	97.23 394	76.52 395	99.85 195	99.82 121	80.22 401	96.48 386

thisisatest0530		99.37 91	99.27 91	99.69 131	99.59 205	99.41 147	100.00 1	99.46 94	96.46 253	99.90 168	100.00 1	99.44 50	99.85 195	98.97 217	99.58 163	99.80 232

thisisatest0515		99.42 84	99.31 89	99.74 122	99.59 205	99.55 122	100.00 1	99.46 94	96.65 242	99.92 163	100.00 1	99.44 50	99.85 195	99.09 213	99.63 161	99.81 215

tttt0517		99.34 96	99.23 103	99.67 134	99.57 214	99.38 149	100.00 1	99.46 94	96.33 265	99.89 171	100.00 1	99.44 50	99.84 198	98.93 219	99.46 166	99.78 238

casdiffmvs		98.65 176	98.38 191	99.46 163	99.52 230	98.74 206	100.00 1	99.15 319	96.91 216	99.05 247	100.00 1	92.75 271	99.83 199	99.70 149	98.38 200	99.81 215
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		98.64 177	98.65 166	98.60 235	99.59 205	96.17 316	100.00 1	99.28 263	96.67 240	98.41 287	100.00 1	94.52 246	99.83 199	99.41 192	100.00 1	99.81 215

DeepMVS_CX				89.98 382	98.90 311	71.46 413		99.18 311	97.61 154	96.92 346	99.83 255	86.07 353	99.83 199	96.02 320	97.65 249	98.65 271

dp		98.72 170	98.61 171	99.03 210	99.53 222	97.39 285	99.45 347	99.39 207	95.62 290	99.94 156	99.52 315	98.83 123	99.82 202	96.77 311	98.42 195	99.89 168

BH-RMVSNet		98.46 196	98.08 213	99.59 147	99.61 199	99.19 171	100.00 1	99.28 263	97.06 205	98.95 251	100.00 1	88.99 322	99.82 202	98.83 226	100.00 1	99.77 239

PMMVS		99.12 126	98.97 132	99.58 151	99.57 214	98.98 193	100.00 1	99.30 251	97.14 197	99.96 126	100.00 1	96.53 216	99.82 202	99.70 149	98.49 190	99.94 136

kuosan		98.55 187	98.53 179	98.62 233	99.66 180	96.16 317	100.00 1	99.44 116	93.93 338	99.81 191	99.98 194	97.58 172	99.81 205	98.08 262	98.28 209	99.89 168

test2506		99.48 78	99.38 78	99.75 121	99.89 114	99.51 131	99.45 347	100.00 1	98.38 84	99.83 180	100.00 1	98.86 119	99.81 205	99.25 202	98.78 181	99.94 136

ECVR-MVS		98.43 198	98.14 208	99.32 188	99.89 114	98.21 242	99.46 345	100.00 1	98.38 84	99.47 216	100.00 1	87.91 333	99.80 207	99.35 195	98.78 181	99.94 136

test1111		98.42 200	98.12 209	99.29 191	99.88 116	98.15 244	99.46 345	100.00 1	98.36 88	99.42 218	100.00 1	87.91 333	99.79 208	99.31 199	98.78 181	99.94 136

EIA-MVS		99.26 109	99.19 108	99.45 165	99.63 190	98.75 203	100.00 1	99.27 273	96.93 213	99.95 154	100.00 1	97.47 181	99.79 208	99.74 137	99.72 151	99.82 206

ETV-MVS		99.34 96	99.24 100	99.64 139	99.58 210	99.33 154	100.00 1	99.25 282	97.57 160	99.96 126	100.00 1	97.44 184	99.79 208	99.70 149	99.65 158	99.81 215

TR-MVS		98.14 216	97.74 228	99.33 186	99.59 205	98.28 237	99.27 365	99.21 300	96.42 257	99.15 238	99.94 231	88.87 325	99.79 208	98.88 222	98.29 208	99.93 147

casdiffmvs_mvg		98.64 177	98.39 190	99.40 176	99.50 239	98.60 214	100.00 1	99.22 294	96.85 220	99.10 241	100.00 1	92.75 271	99.78 212	99.71 146	98.35 202	99.81 215
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sd_testset		97.81 227	97.48 236	98.79 226	99.82 125	96.80 307	99.32 360	99.45 102	97.62 150	99.38 225	99.86 247	85.56 359	99.77 213	99.72 142	96.61 266	99.79 235

Effi-MVS+		98.58 184	98.24 202	99.61 143	99.60 201	99.26 162	97.85 409	99.10 338	96.22 271	99.97 122	99.89 242	93.75 254	99.77 213	99.43 190	98.34 203	99.81 215

baseline1		98.91 157	98.61 171	99.81 102	99.71 158	99.77 95	99.78 299	99.44 116	97.51 168	98.81 263	99.99 189	98.25 145	99.76 215	98.60 241	95.41 276	99.89 168

lupinMVS		99.29 105	99.16 112	99.69 131	99.45 253	99.49 136	100.00 1	99.15 319	97.45 174	99.97 122	100.00 1	96.76 206	99.76 215	99.67 160	100.00 1	99.81 215

EPP-MVSNet		99.10 128	99.00 127	99.40 176	99.51 235	98.68 209	99.92 273	99.43 124	95.47 299	99.65 205	100.00 1	99.51 37	99.76 215	99.53 186	98.00 223	99.75 242

baseline		98.69 174	98.45 186	99.41 172	99.52 230	98.67 210	100.00 1	99.17 316	97.03 206	99.13 239	100.00 1	93.17 264	99.74 218	99.70 149	98.34 203	99.81 215

CostFormer		98.84 162	98.77 154	99.04 209	99.41 259	97.58 279	99.67 324	99.35 229	94.66 317	99.96 126	99.36 326	99.28 76	99.74 218	99.41 192	97.81 238	99.81 215

Fast-Effi-MVS+		98.40 203	98.02 219	99.55 155	99.63 190	99.06 181	100.00 1	99.15 319	95.07 306	99.42 218	99.95 225	93.26 263	99.73 220	97.44 287	98.24 212	99.87 191

jason		99.11 127	98.96 133	99.59 147	99.17 280	99.31 157	100.00 1	99.13 328	97.38 179	99.83 180	100.00 1	95.54 228	99.72 221	99.57 180	99.97 116	99.74 243
jason: jason.
EPMVS		99.25 113	99.13 114	99.60 145	99.60 201	99.20 170	99.60 332	100.00 1	96.93 213	99.92 163	99.36 326	99.05 95	99.71 222	98.77 228	98.94 178	99.90 162

SPE-MVS-test		99.31 102	99.27 91	99.43 169	99.99 49	98.77 202	100.00 1	99.19 304	97.24 192	99.96 126	100.00 1	97.56 176	99.70 223	99.68 157	99.81 146	99.82 206

Vis-MVSNet		98.52 192	98.25 199	99.34 183	99.68 165	98.55 217	99.68 323	99.41 190	97.34 183	99.94 156	100.00 1	90.38 303	99.70 223	99.03 215	98.84 179	99.76 241
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TAPA-MVS	96.40 10	97.64 233	97.37 242	98.45 244	99.94 103	95.70 325	100.00 1	99.40 194	97.65 145	99.53 209	100.00 1	99.31 68	99.66 225	80.48 408	100.00 1	100.00 1
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ETVMVS		99.16 123	98.98 130	99.69 131	99.67 173	99.56 121	100.00 1	99.45 102	96.36 262	99.98 117	99.95 225	98.65 132	99.64 226	99.11 212	97.63 250	99.88 181

CS-MVS		99.33 98	99.27 91	99.50 159	99.99 49	99.00 191	100.00 1	99.13 328	97.26 191	99.96 126	100.00 1	97.79 164	99.64 226	99.64 166	99.67 156	99.87 191

Fast-Effi-MVS+-dtu		98.38 204	98.56 176	97.82 296	99.58 210	94.44 354	100.00 1	99.16 317	96.75 229	99.51 211	99.63 296	95.03 238	99.60 228	97.71 277	99.67 156	99.42 260

PAPM		99.78 16	99.76 12	99.85 90	99.01 296	99.95 32	100.00 1	99.75 52	99.37 3	99.99 111	100.00 1	99.76 12	99.60 228	100.00 1	100.00 1	100.00 1

tt0805		96.52 285	96.23 285	97.40 306	99.30 274	93.55 362	99.32 360	99.45 102	96.75 229	97.88 318	99.99 189	79.99 385	99.59 230	97.39 291	95.98 269	99.06 267

GeoE		98.06 218	97.65 233	99.29 191	99.47 249	98.41 222	100.00 1	99.19 304	94.85 311	98.88 255	100.00 1	91.21 288	99.59 230	97.02 299	98.19 216	99.88 181

test_post1							99.32 360				88.24 416	99.33 63	99.59 230	98.31 253

test_post											89.05 414	99.49 43	99.59 230

ADS-MVSNet		98.70 173	98.51 182	99.28 194	99.51 235	98.39 225	99.24 368	99.44 116	95.52 295	99.96 126	99.70 276	97.57 174	99.58 234	97.11 297	98.54 187	99.88 181

Patchmatch-test		97.83 226	97.42 238	99.06 205	99.08 287	97.66 277	98.66 403	99.21 300	93.65 344	98.25 300	99.58 306	99.47 47	99.57 235	90.25 381	98.59 186	99.95 131

HQP4-MVS										99.17 234			99.57 235			97.77 275

HQP-MVS		97.73 230	97.85 224	97.39 307	99.07 288	94.82 338	100.00 1	99.40 194	99.04 16	99.17 234	99.97 203	88.61 328	99.57 235	99.79 123	95.58 270	97.77 275

CLD-MVS		97.64 233	97.74 228	97.36 309	99.01 296	94.76 346	100.00 1	99.34 235	99.30 4	99.00 249	99.97 203	87.49 339	99.57 235	99.96 88	95.58 270	97.75 288
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OPM-MVS		97.21 253	97.18 253	97.32 312	98.08 352	94.66 347	100.00 1	99.28 263	98.65 72	98.92 252	99.98 194	86.03 355	99.56 239	98.28 257	95.41 276	97.72 323
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LPG-MVS_test		97.31 250	97.32 244	97.28 315	98.85 318	94.60 350	100.00 1	99.37 212	97.35 181	98.85 258	99.98 194	86.66 347	99.56 239	99.55 181	95.26 282	97.70 331

LGP-MVS_train				97.28 315	98.85 318	94.60 350		99.37 212	97.35 181	98.85 258	99.98 194	86.66 347	99.56 239	99.55 181	95.26 282	97.70 331

ITE_SJBPF				96.84 335	98.96 306	93.49 363		98.12 394	98.12 107	98.35 290	99.97 203	84.45 363	99.56 239	95.63 327	95.25 284	97.49 362

ACMP	97.00 8	97.19 254	97.16 254	97.27 317	98.97 305	94.58 353	100.00 1	99.32 240	97.97 118	97.45 336	99.98 194	85.79 357	99.56 239	99.70 149	95.24 285	97.67 341
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HQP_MVS		97.71 232	97.82 226	97.37 308	99.00 300	94.80 341	100.00 1	99.40 194	99.00 27	99.08 244	99.97 203	88.58 330	99.55 244	99.79 123	95.57 274	97.76 277

plane_prior5								99.40 194					99.55 244	99.79 123	95.57 274	97.76 277

ACMM	97.17 6	97.37 248	97.40 240	97.29 314	99.01 296	94.64 349	100.00 1	99.25 282	98.07 110	98.44 286	99.98 194	87.38 341	99.55 244	99.25 202	95.19 288	97.69 335
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
patchmatchnet-post											97.79 389	99.41 59	99.54 247

SCA		98.30 207	97.98 221	99.23 199	99.41 259	98.25 239	99.99 219	99.45 102	96.91 216	99.76 197	99.58 306	89.65 314	99.54 247	98.31 253	98.79 180	99.91 151

XVG-ACMP-BASELINE		96.60 283	96.52 272	96.84 335	98.41 334	93.29 367	99.99 219	99.32 240	97.76 137	98.51 282	99.29 329	81.95 378	99.54 247	98.40 248	95.03 295	97.68 337

ACMH+	96.20 13	96.49 290	96.33 282	97.00 325	99.06 292	93.80 360	99.81 293	99.31 247	97.32 186	95.89 368	99.97 203	82.62 376	99.54 247	98.34 252	94.63 302	97.65 346

ACMH	96.25 11	96.77 273	96.62 267	97.21 318	98.96 306	94.43 355	99.64 326	99.33 237	97.43 176	96.55 357	99.97 203	83.52 371	99.54 247	99.07 214	95.13 292	97.66 342
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TDRefinement		91.93 357	90.48 365	96.27 348	81.60 421	92.65 374	99.10 390	97.61 409	93.96 337	93.77 383	99.85 252	80.03 383	99.53 252	97.82 274	70.59 411	96.63 385

JIA-IIPM		97.09 259	96.34 281	99.36 181	98.88 313	98.59 215	99.81 293	99.43 124	84.81 403	99.96 126	90.34 413	98.55 138	99.52 253	97.00 300	98.28 209	99.98 112

IS-MVSNet		99.08 129	98.91 142	99.59 147	99.65 182	99.38 149	99.78 299	99.24 287	96.70 236	99.51 211	100.00 1	98.44 142	99.52 253	98.47 246	98.39 198	99.88 181

dongtai		98.29 209	98.25 199	98.42 246	99.58 210	95.86 322	100.00 1	99.44 116	93.46 351	99.69 203	99.97 203	97.53 177	99.51 255	96.28 318	98.27 211	99.89 168

Effi-MVS+-dtu		98.51 194	98.86 147	97.47 305	99.77 151	94.21 357	100.00 1	98.94 373	97.61 154	99.91 166	98.75 366	95.89 221	99.51 255	99.36 194	99.48 165	98.68 270

PatchmatchNet		99.03 136	98.96 133	99.26 197	99.49 243	98.33 232	99.38 355	99.45 102	96.64 243	99.96 126	99.58 306	99.49 43	99.50 257	97.63 280	99.00 177	99.93 147
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		95.50 327	95.12 332	96.64 339	98.69 324	93.00 369	99.40 353	97.75 406	96.40 259	96.14 364	99.87 245	79.47 386	99.50 257	93.62 354	94.72 301	97.40 367

EC-MVSNet		99.19 119	99.09 119	99.48 162	99.42 257	99.07 179	100.00 1	99.21 300	96.95 211	99.96 126	100.00 1	96.88 204	99.48 259	99.64 166	99.79 149	99.88 181

LTVRE_ROB	95.29 16	96.32 300	96.10 290	96.99 326	98.55 329	93.88 359	99.45 347	99.28 263	94.50 323	96.46 358	99.52 315	84.86 362	99.48 259	97.26 295	95.03 295	97.59 356
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
AUN-MVS		96.26 303	95.67 315	98.06 278	99.68 165	95.60 327	99.82 292	99.42 141	96.78 226	99.88 173	99.80 264	94.84 241	99.47 261	97.48 286	73.29 409	99.12 265

D2MVS		97.63 236	97.83 225	97.05 322	98.83 320	94.60 350	100.00 1	99.82 40	96.89 219	98.28 296	99.03 348	94.05 250	99.47 261	98.58 243	94.97 298	97.09 375

tpm2		98.64 177	98.58 175	98.81 225	99.42 257	97.12 299	99.69 321	99.37 212	93.63 345	99.94 156	99.67 284	98.96 109	99.47 261	98.62 240	97.95 228	99.83 201

HyFIR lowres test		99.32 100	99.24 100	99.58 151	99.95 100	99.26 162	100.00 1	99.99 13	96.72 234	99.29 230	99.91 239	99.49 43	99.47 261	99.74 137	98.08 221	100.00 1

hse-mvs2		96.79 272	96.38 278	98.04 284	99.68 165	95.54 328	99.81 293	99.42 141	98.21 96	100.00 1	99.80 264	97.49 179	99.46 265	99.72 142	73.27 410	99.12 265

reproduce_monomvs		98.61 181	98.54 177	98.82 222	99.97 90	99.28 159	100.00 1	99.33 237	98.51 78	97.87 319	99.24 332	99.98 3	99.45 266	99.02 216	92.93 317	97.74 310

USDC		95.90 321	95.70 311	96.50 343	98.60 328	92.56 375	100.00 1	98.30 390	97.77 135	96.92 346	99.94 231	81.25 382	99.45 266	93.54 355	94.96 299	97.49 362

gm-plane-assit					99.52 230	97.26 294			95.86 282		100.00 1		99.43 268	98.76 229

MS-PatchMatch		95.66 325	95.87 301	95.05 358	97.80 361	89.25 391	98.88 399	99.30 251	96.35 263	96.86 349	99.01 350	81.35 381	99.43 268	93.30 357	99.98 113	96.46 387

CHOSEN 280x420		99.85 3	99.87 1	99.80 107	99.99 49	99.97 21	99.97 251	99.98 16	98.96 32	100.00 1	100.00 1	99.96 4	99.42 270	100.00 1	100.00 1	100.00 1

VPA-MVSNet		97.03 264	96.43 276	98.82 222	98.64 326	99.32 155	99.38 355	99.47 79	96.73 233	98.91 254	98.94 357	87.00 345	99.40 271	99.23 205	89.59 359	97.76 277

LF4IMVS		96.19 306	96.18 287	96.23 349	98.26 343	92.09 377	100.00 1	97.89 403	97.82 130	97.94 314	99.87 245	82.71 375	99.38 272	97.41 289	93.71 307	97.20 372

UniMVSNet_ETH3D		95.28 330	94.41 336	97.89 294	98.91 310	95.14 332	99.13 387	99.35 229	92.11 370	97.17 343	99.66 286	70.28 407	99.36 273	97.88 272	95.18 289	99.16 263

GA-MVS		97.72 231	97.27 248	99.06 205	99.24 278	97.93 264	100.00 1	99.24 287	95.80 286	98.99 250	99.64 292	89.77 311	99.36 273	95.12 336	97.62 251	99.89 168

XXY-MVS		97.14 258	96.63 266	98.67 230	98.65 325	98.92 196	99.54 339	99.29 257	95.57 292	97.63 328	99.83 255	87.79 337	99.35 275	98.39 249	92.95 316	97.75 288

test_fmvs2		95.17 333	95.23 329	95.01 359	98.95 308	88.99 393	99.99 219	97.77 405	97.79 133	98.58 275	99.70 276	73.36 401	99.34 276	95.88 321	95.03 295	96.70 383

GG-mvs-BLEND				99.59 147	99.54 219	99.49 136	99.17 381	99.52 72		99.96 126	99.68 283	100.00 1	99.33 277	99.71 146	99.99 103	99.96 125

dmvs_re		97.54 240	97.88 223	96.54 342	99.55 218	90.35 388	99.86 285	99.46 94	97.00 208	99.41 223	100.00 1	90.78 296	99.30 278	99.60 174	95.24 285	99.96 125

EPNet_dtu		98.53 191	98.23 205	99.43 169	99.92 108	99.01 188	99.96 257	99.47 79	98.80 60	99.96 126	99.96 218	98.56 137	99.30 278	87.78 393	99.68 154	100.00 1
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		98.24 213	98.22 206	98.32 254	99.13 282	95.79 323	99.53 340	99.12 334	95.20 305	99.96 126	99.36 326	97.58 172	99.28 280	97.41 289	96.67 264	99.88 181

baseline2		98.99 147	98.93 140	99.18 202	99.26 277	99.15 176	100.00 1	99.46 94	96.71 235	96.79 352	100.00 1	99.42 57	99.25 281	98.75 230	99.94 124	99.15 264

MonoMVSNet		98.55 187	98.64 168	98.26 258	98.21 346	95.76 324	99.94 268	99.16 317	96.23 268	99.47 216	99.24 332	96.75 208	99.22 282	99.61 173	99.17 170	99.81 215

gg-mvs-nofinetune		96.95 268	96.10 290	99.50 159	99.41 259	99.36 153	99.07 395	99.52 72	83.69 405	99.96 126	83.60 421	100.00 1	99.20 283	99.68 157	99.99 103	99.96 125

TAMVS		98.76 167	98.73 158	98.86 221	99.44 255	97.69 275	99.57 335	99.34 235	96.57 246	99.12 240	99.81 261	98.83 123	99.16 284	97.97 270	97.91 230	99.73 247

MVP-Stereo		96.51 287	96.48 274	96.60 341	95.65 396	94.25 356	98.84 400	98.16 392	95.85 284	95.23 371	99.04 345	92.54 278	99.13 285	92.98 359	99.98 113	96.43 388
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Vis-MVSNet (Re-imp)		98.99 147	98.89 146	99.29 191	99.64 188	98.89 197	99.98 245	99.31 247	96.74 231	99.48 213	100.00 1	98.11 149	99.10 286	98.39 249	98.34 203	99.89 168

EG-PatchMatch MVS		92.94 353	92.49 357	94.29 370	95.87 393	87.07 398	99.07 395	98.11 395	93.19 359	88.98 399	98.66 370	70.89 405	99.08 287	92.43 364	95.21 287	96.72 382

MVS-HIRNet		94.12 342	92.73 356	98.29 255	99.33 270	95.95 318	99.38 355	99.19 304	74.54 413	98.26 299	86.34 417	86.07 353	99.06 288	91.60 369	99.87 137	99.85 196

mvs_anonymous		98.80 165	98.60 173	99.38 180	99.57 214	99.24 166	100.00 1	99.21 300	95.87 280	98.92 252	99.82 258	96.39 218	99.03 289	99.13 210	98.50 189	99.88 181

TESTMET0.1,1		99.08 129	98.96 133	99.44 166	99.63 190	99.38 149	100.00 1	99.45 102	95.53 293	99.48 213	100.00 1	99.71 15	99.02 290	96.84 305	99.99 103	99.91 151

ttmdpeth		96.24 304	95.88 300	97.32 312	97.80 361	96.61 313	99.95 263	98.77 384	97.80 132	93.42 385	99.28 330	86.42 350	99.01 291	97.63 280	91.84 335	96.33 390

test-LLR		99.03 136	98.91 142	99.40 176	99.40 264	99.28 159	100.00 1	99.45 102	96.70 236	99.42 218	99.12 338	99.31 68	99.01 291	96.82 306	99.99 103	99.91 151

test-mter		98.96 151	98.82 149	99.40 176	99.40 264	99.28 159	100.00 1	99.45 102	95.44 303	99.42 218	99.12 338	99.70 16	99.01 291	96.82 306	99.99 103	99.91 151

tfpnnormal		96.36 297	95.69 314	98.37 250	98.55 329	98.71 207	99.69 321	99.45 102	93.16 360	96.69 356	99.71 273	88.44 332	98.99 294	94.17 346	91.38 344	97.41 366

Anonymous20231211		96.29 301	95.70 311	98.07 274	99.80 142	97.49 281	99.15 384	99.40 194	89.11 389	97.75 325	99.45 320	88.93 324	98.98 295	98.26 258	89.47 361	97.73 317

nrg030		97.64 233	97.27 248	98.75 228	98.34 336	99.53 127	100.00 1	99.22 294	96.21 272	98.27 298	99.95 225	94.40 247	98.98 295	99.23 205	89.78 358	97.75 288

mvs5depth		93.81 344	93.00 351	96.23 349	94.25 404	93.33 366	97.43 411	98.07 397	93.47 350	94.15 382	99.58 306	77.52 392	98.97 297	93.64 353	88.92 367	96.39 389

cl22		98.23 214	98.11 210	98.58 237	99.82 125	99.01 188	100.00 1	99.28 263	96.92 215	98.33 292	99.21 335	98.09 151	98.97 297	98.72 231	92.61 320	97.76 277

CVMVSNet		98.56 186	98.47 185	98.82 222	99.11 283	97.67 276	99.74 309	99.47 79	97.57 160	99.06 246	100.00 1	95.72 225	98.97 297	98.21 259	97.33 253	99.83 201

VPNet		96.41 292	95.76 308	98.33 253	98.61 327	98.30 236	99.48 344	99.45 102	96.98 210	98.87 257	99.88 244	81.57 379	98.93 300	99.22 207	87.82 376	97.76 277

v7n		96.06 317	95.42 327	97.99 288	97.58 371	97.35 288	99.86 285	99.11 335	92.81 367	97.91 317	99.49 317	90.99 294	98.92 301	92.51 362	88.49 372	97.70 331

jajsoiax		97.07 261	96.79 262	97.89 294	97.28 382	97.12 299	99.95 263	99.19 304	96.55 247	97.31 339	99.69 279	87.35 343	98.91 302	98.70 232	95.12 293	97.66 342

mvs_tets		97.00 267	96.69 264	97.94 290	97.41 381	97.27 293	99.60 332	99.18 311	96.51 251	97.35 338	99.69 279	86.53 349	98.91 302	98.84 224	95.09 294	97.65 346

CDS-MVSNet		98.96 151	98.95 137	99.01 211	99.48 245	98.36 230	99.93 271	99.37 212	96.79 225	99.31 229	99.83 255	99.77 11	98.91 302	98.07 264	97.98 224	99.77 239
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
FIs		97.95 223	97.73 230	98.62 233	98.53 331	99.24 166	100.00 1	99.43 124	96.74 231	97.87 319	99.82 258	95.27 231	98.89 305	98.78 227	93.07 314	97.74 310

v1192		96.18 307	95.49 321	98.26 258	98.01 354	98.15 244	99.99 219	99.08 344	93.36 354	98.54 278	98.97 355	89.47 317	98.89 305	91.15 372	90.82 349	97.75 288

UniMVSNet (Re)		97.29 252	96.85 259	98.59 236	98.49 332	99.13 177	100.00 1	99.42 141	96.52 250	98.24 302	98.90 360	94.93 239	98.89 305	97.54 284	87.61 377	97.75 288

EI-MVSNet		97.98 222	97.93 222	98.16 267	99.11 283	97.84 270	99.74 309	99.29 257	94.39 327	98.65 270	100.00 1	97.21 189	98.88 308	97.62 283	95.31 280	97.75 288

MVSTER		98.58 184	98.52 180	98.77 227	99.65 182	99.68 108	100.00 1	99.29 257	95.63 289	98.65 270	99.80 264	99.78 9	98.88 308	98.59 242	95.31 280	97.73 317

pm-mvs1		95.76 323	95.01 333	98.00 286	98.23 345	97.45 283	99.24 368	99.04 362	93.13 361	95.93 367	99.72 271	86.28 351	98.84 310	95.62 328	87.92 375	97.72 323

V42		96.65 280	96.16 289	98.11 273	98.17 350	98.23 240	99.99 219	99.09 343	93.97 336	98.74 267	99.05 344	91.09 291	98.82 311	95.46 330	89.90 356	97.27 371

CMPMVS	66.12 22	90.65 365	92.04 358	86.46 390	96.18 390	66.87 420	98.03 408	99.38 209	83.38 406	85.49 407	99.55 312	77.59 391	98.80 312	94.44 343	94.31 305	93.72 405
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PS-MVSNAJss		98.03 220	98.06 216	97.94 290	97.63 366	97.33 291	99.89 281	99.23 291	96.27 267	98.03 309	99.59 304	98.75 128	98.78 313	98.52 244	94.61 303	97.70 331

OurMVSNet-221017-0		96.14 313	95.98 296	96.62 340	97.49 376	93.44 364	99.92 273	98.16 392	95.86 282	97.65 327	99.95 225	85.71 358	98.78 313	94.93 338	94.18 306	97.64 349

OpenMVS_ROB	88.34 20	91.89 358	91.12 360	94.19 372	95.55 398	87.63 396	99.26 366	98.03 398	86.61 400	90.65 397	96.82 397	70.14 408	98.78 313	86.54 396	96.50 268	96.15 391

pmmvs6		93.64 345	92.87 353	95.94 353	97.47 378	91.41 382	98.92 397	99.02 365	87.84 396	95.01 373	99.61 302	77.24 394	98.77 316	94.33 344	86.41 386	97.63 350

v8		96.35 298	95.73 310	98.21 263	98.11 351	98.23 240	99.94 268	99.07 349	92.66 368	98.29 295	99.00 351	91.46 285	98.77 316	94.17 346	88.83 370	97.62 352

miper_enhance_ethall		98.33 206	98.27 198	98.51 239	99.66 180	99.04 183	100.00 1	99.22 294	97.53 164	98.51 282	99.38 324	99.49 43	98.75 318	98.02 266	92.61 320	97.76 277

EGC-MVSNET		79.46 380	74.04 388	95.72 355	96.00 392	92.73 372	99.09 392	99.04 362	5.08 425	16.72 425	98.71 367	73.03 402	98.74 319	82.05 405	96.64 265	95.69 398

v1921920		96.16 311	95.50 319	98.14 268	97.88 360	97.96 261	99.99 219	99.07 349	93.33 355	98.60 274	99.24 332	89.37 318	98.71 320	91.28 370	90.74 351	97.75 288

lessismore_v0				96.05 351	97.55 372	91.80 379		99.22 294		91.87 391	99.91 239	83.50 372	98.68 321	92.48 363	90.42 355	97.68 337

v2v482		96.70 278	96.18 287	98.27 256	98.04 353	98.39 225	100.00 1	99.13 328	94.19 333	98.58 275	99.08 341	90.48 301	98.67 322	95.69 325	90.44 354	97.75 288

v144192		96.40 295	95.81 303	98.17 266	97.89 359	98.11 247	99.99 219	99.06 357	93.39 353	98.75 266	99.09 340	90.43 302	98.66 323	93.10 358	90.55 353	97.75 288

cl____		97.54 240	97.32 244	98.18 264	99.47 249	98.14 246	100.00 1	99.10 338	94.16 334	97.60 332	99.63 296	97.52 178	98.65 324	96.47 313	91.97 333	97.76 277

v1144		96.51 287	95.97 297	98.13 271	97.98 356	98.04 255	99.99 219	99.08 344	93.51 349	98.62 273	98.98 352	90.98 295	98.62 325	93.79 352	90.79 350	97.74 310

WBMVS		98.19 215	98.10 212	98.47 241	99.63 190	99.03 184	100.00 1	99.32 240	95.46 300	98.39 288	99.40 323	99.69 17	98.61 326	98.64 236	92.39 325	97.76 277

v1240		95.96 319	95.25 328	98.07 274	97.91 358	97.87 269	99.96 257	99.07 349	93.24 358	98.64 272	98.96 356	88.98 323	98.61 326	89.58 386	90.92 348	97.75 288

v10		96.14 313	95.50 319	98.07 274	98.19 348	97.96 261	99.83 289	99.07 349	92.10 371	98.07 306	98.94 357	91.07 292	98.61 326	92.41 365	89.82 357	97.63 350

anonymousdsp		97.16 256	96.88 257	98.00 286	97.08 384	98.06 253	99.81 293	99.15 319	94.58 319	97.84 321	99.62 300	90.49 300	98.60 329	97.98 267	95.32 279	97.33 370

v148		96.29 301	95.84 302	97.63 299	97.74 363	96.53 314	100.00 1	99.07 349	93.52 348	98.01 312	99.42 322	91.22 287	98.60 329	96.37 317	87.22 380	97.75 288

MVSFormer		98.94 155	98.82 149	99.28 194	99.45 253	99.49 136	100.00 1	99.13 328	95.46 300	99.97 122	100.00 1	96.76 206	98.59 331	98.63 238	100.00 1	99.74 243

test_djsdf		97.55 239	97.38 241	98.07 274	97.50 374	97.99 257	100.00 1	99.13 328	95.46 300	98.47 285	99.85 252	92.01 284	98.59 331	98.63 238	95.36 278	97.62 352

test_0402		94.35 337	93.70 342	96.32 347	97.92 357	93.60 361	99.61 331	98.85 380	88.19 395	94.68 376	99.48 318	80.01 384	98.58 333	89.39 387	95.15 291	96.77 381

miper_ehance_all_eth		97.81 227	97.66 232	98.23 260	99.49 243	98.37 228	99.99 219	99.11 335	94.78 312	98.25 300	99.21 335	98.18 147	98.57 334	97.35 293	92.61 320	97.76 277

FC-MVSNet-test		97.84 225	97.63 234	98.45 244	98.30 341	99.05 182	100.00 1	99.43 124	96.63 245	97.61 331	99.82 258	95.19 235	98.57 334	98.64 236	93.05 315	97.73 317

WR-MVS		97.09 259	96.64 265	98.46 242	98.43 333	99.09 178	99.97 251	99.33 237	95.62 290	97.76 322	99.67 284	91.17 290	98.56 336	98.49 245	89.28 364	97.74 310

WR-MVS_H		96.73 275	96.32 283	97.95 289	98.26 343	97.88 267	99.72 316	99.43 124	95.06 307	96.99 345	98.68 369	93.02 267	98.53 337	97.43 288	88.33 373	97.43 365

ambc				88.45 385	86.84 417	70.76 414	97.79 410	98.02 400		90.91 394	95.14 402	38.69 420	98.51 338	94.97 337	84.23 390	96.09 394

eth_miper_zixun_eth		97.47 244	97.28 246	98.06 278	99.41 259	97.94 263	99.62 330	99.08 344	94.46 325	98.19 303	99.56 311	96.91 203	98.50 339	96.78 309	91.49 341	97.74 310

UniMVSNet_NR-MVSNet		97.16 256	96.80 260	98.22 261	98.38 335	98.41 222	100.00 1	99.45 102	96.14 274	97.76 322	99.64 292	95.05 237	98.50 339	97.98 267	86.84 381	97.75 288

DU-MVS		96.93 269	96.49 273	98.22 261	98.31 339	98.41 222	100.00 1	99.37 212	96.41 258	97.76 322	99.65 288	92.14 281	98.50 339	97.98 267	86.84 381	97.75 288

pmmvs4		97.17 255	96.80 260	98.27 256	97.68 365	98.64 212	100.00 1	99.18 311	94.22 330	98.55 277	99.71 273	93.67 255	98.47 342	95.66 326	92.57 323	97.71 330

pmmvs5		95.94 320	95.61 316	96.95 328	97.42 379	94.66 347	100.00 1	98.08 396	93.60 346	97.05 344	99.43 321	87.02 344	98.46 343	95.76 322	92.12 329	97.72 323

SixPastTwentyTwo		95.71 324	95.49 321	96.38 345	97.42 379	93.01 368	99.84 288	98.23 391	94.75 313	95.98 366	99.97 203	85.35 360	98.43 344	94.71 340	93.17 313	97.69 335

WB-MVSnew		97.02 266	97.24 250	96.37 346	99.44 255	97.36 287	100.00 1	99.43 124	96.12 275	99.35 227	99.89 242	93.60 258	98.42 345	88.91 392	98.39 198	93.33 407

NR-MVSNet		96.63 281	96.04 293	98.38 249	98.31 339	98.98 193	99.22 375	99.35 229	95.87 280	94.43 380	99.65 288	92.73 273	98.40 346	96.78 309	88.05 374	97.75 288

TransMVSNet (Re)		94.78 334	93.72 341	97.93 292	98.34 336	97.88 267	99.23 373	97.98 401	91.60 373	94.55 377	99.71 273	87.89 335	98.36 347	89.30 388	84.92 388	97.56 358

Baseline_NR-MVSNet		96.16 311	95.70 311	97.56 304	98.28 342	96.79 308	100.00 1	97.86 404	91.93 372	97.63 328	99.47 319	92.14 281	98.35 348	97.13 296	86.83 383	97.54 359

IterMVS-SCA-FT		96.72 277	96.42 277	97.62 301	99.40 264	96.83 306	99.99 219	99.14 324	94.65 318	97.55 334	99.72 271	89.65 314	98.31 349	95.62 328	92.05 330	97.73 317

DIV-MVS_self_test		97.52 243	97.35 243	98.05 282	99.46 252	98.11 247	100.00 1	99.10 338	94.21 331	97.62 330	99.63 296	97.65 170	98.29 350	96.47 313	91.98 332	97.76 277

IterMVS		96.76 274	96.46 275	97.63 299	99.41 259	96.89 304	99.99 219	99.13 328	94.74 315	97.59 333	99.66 286	89.63 316	98.28 351	95.71 324	92.31 327	97.72 323
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test_vis3_rt		79.61 379	78.19 384	83.86 393	88.68 416	69.56 415	99.81 293	82.19 429	86.78 399	68.57 417	84.51 420	25.06 426	98.26 352	89.18 390	78.94 404	83.75 417

MVStest1		94.27 338	93.30 347	97.19 319	98.83 320	97.18 297	99.93 271	98.79 383	86.80 398	84.88 410	99.04 345	94.32 249	98.25 353	90.55 377	86.57 385	96.12 393

c3_l		97.58 237	97.42 238	98.06 278	99.48 245	98.16 243	99.96 257	99.10 338	94.54 321	98.13 304	99.20 337	97.87 158	98.25 353	97.28 294	91.20 346	97.75 288

test0.0.03 1		98.12 217	98.03 218	98.39 248	99.11 283	98.07 251	100.00 1	99.93 30	96.70 236	96.91 348	99.95 225	99.31 68	98.19 355	91.93 366	98.44 193	98.91 268

CP-MVSNet		96.73 275	96.25 284	98.18 264	98.21 346	98.67 210	99.77 304	99.32 240	95.06 307	97.20 342	99.65 288	90.10 305	98.19 355	98.06 265	88.90 368	97.66 342

PS-CasMVS		96.34 299	95.78 307	98.03 285	98.18 349	98.27 238	99.71 317	99.32 240	94.75 313	96.82 351	99.65 288	86.98 346	98.15 357	97.74 276	88.85 369	97.66 342

our_test_3		96.51 287	96.35 280	96.98 327	97.61 368	95.05 333	99.98 245	99.01 367	94.68 316	96.77 354	99.06 342	95.87 222	98.14 358	91.81 367	92.37 326	97.75 288

new_pmnet		94.11 343	93.47 345	96.04 352	96.60 388	92.82 371	99.97 251	98.91 376	90.21 385	95.26 370	98.05 388	85.89 356	98.14 358	84.28 400	92.01 331	97.16 373

K. test v3		95.46 328	95.14 331	96.40 344	97.53 373	93.40 365	99.99 219	99.23 291	95.49 298	92.70 390	99.73 270	84.26 365	98.12 360	93.94 351	93.38 312	97.68 337

Patchmtry		96.81 271	96.37 279	98.14 268	99.31 271	98.55 217	98.91 398	99.00 368	90.45 382	97.92 316	98.98 352	96.94 201	98.12 360	94.27 345	91.53 340	97.75 288

FMVSNet3		97.30 251	96.95 255	98.37 250	99.65 182	99.25 164	99.71 317	99.28 263	94.23 329	98.53 279	98.91 359	93.30 262	98.11 362	95.31 332	93.60 308	97.73 317

N_pmnet		91.88 359	93.37 346	87.40 388	97.24 383	66.33 421	99.90 277	91.05 424	89.77 388	95.65 369	98.58 373	90.05 308	98.11 362	85.39 397	92.72 319	97.75 288

IterMVS-LS		97.56 238	97.44 237	97.92 293	99.38 268	97.90 265	99.89 281	99.10 338	94.41 326	98.32 293	99.54 314	97.21 189	98.11 362	97.50 285	91.62 338	97.75 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		98.02 221	97.71 231	98.93 216	99.31 271	98.86 198	99.13 387	99.00 368	96.53 249	99.96 126	98.98 352	96.94 201	98.10 365	91.18 371	98.40 196	99.84 197

FMVSNet2		96.22 305	95.60 317	98.06 278	99.53 222	98.33 232	99.45 347	99.27 273	93.71 340	98.03 309	98.84 362	84.23 366	98.10 365	93.97 350	93.40 311	97.73 317

ppachtmachnet_test		96.17 309	95.89 299	97.02 324	97.61 368	95.24 330	99.99 219	99.24 287	93.31 356	96.71 355	99.62 300	94.34 248	98.07 367	89.87 382	92.30 328	97.75 288

GBi-Net		96.07 315	95.80 305	96.89 332	99.53 222	94.87 335	99.18 376	99.27 273	93.71 340	98.53 279	98.81 363	84.23 366	98.07 367	95.31 332	93.60 308	97.72 323

test1		96.07 315	95.80 305	96.89 332	99.53 222	94.87 335	99.18 376	99.27 273	93.71 340	98.53 279	98.81 363	84.23 366	98.07 367	95.31 332	93.60 308	97.72 323

FMVSNet1		94.45 336	93.63 343	96.89 332	98.87 316	94.87 335	99.18 376	99.27 273	90.95 379	97.31 339	98.81 363	72.89 403	98.07 367	92.61 360	92.81 318	97.72 323

PatchT		95.90 321	94.95 335	98.75 228	99.03 294	98.39 225	99.08 393	99.32 240	85.52 401	99.96 126	94.99 405	97.94 153	98.05 371	80.20 409	98.47 192	99.81 215

TranMVSNet+NR-MVSNet		96.45 291	96.01 294	97.79 297	98.00 355	97.62 278	100.00 1	99.35 229	95.98 277	97.31 339	99.64 292	90.09 306	98.00 372	96.89 304	86.80 384	97.75 288

test_method		91.04 364	91.10 361	90.85 380	98.34 336	77.63 407	100.00 1	98.93 375	76.69 411	96.25 362	98.52 375	70.44 406	97.98 373	89.02 391	91.74 336	96.92 379

miper_lstm_enhance		97.40 247	97.28 246	97.75 298	99.48 245	97.52 280	100.00 1	99.07 349	94.08 335	98.01 312	99.61 302	97.38 186	97.98 373	96.44 316	91.47 343	97.76 277

ET-MVSNet_ETH3D		96.41 292	95.48 323	99.20 201	99.81 131	99.75 97	100.00 1	99.02 365	97.30 190	78.33 413	100.00 1	97.73 166	97.94 375	99.70 149	87.41 378	99.92 149

ADS-MVSNet2		98.28 211	98.51 182	97.62 301	99.51 235	95.03 334	99.24 368	99.41 190	95.52 295	99.96 126	99.70 276	97.57 174	97.94 375	97.11 297	98.54 187	99.88 181

PEN-MVS		96.01 318	95.48 323	97.58 303	97.74 363	97.26 294	99.90 277	99.29 257	94.55 320	96.79 352	99.55 312	87.38 341	97.84 377	96.92 303	87.24 379	97.65 346

Syy-MVS		96.17 309	96.57 269	95.00 360	99.50 239	87.37 397	100.00 1	99.57 68	96.23 268	98.07 306	100.00 1	92.41 279	97.81 378	85.34 398	97.96 226	99.82 206

myMVS_eth3d		98.52 192	98.51 182	98.53 238	99.50 239	97.98 258	100.00 1	99.57 68	96.23 268	98.07 306	100.00 1	99.09 91	97.81 378	96.17 319	97.96 226	99.82 206

testing3		98.44 197	98.37 193	98.65 231	99.51 235	98.32 234	100.00 1	99.62 66	96.43 254	97.93 315	99.99 189	99.11 89	97.81 378	94.88 339	97.80 239	99.82 206

testgi		96.18 307	95.93 298	96.93 330	98.98 304	94.20 358	100.00 1	99.07 349	97.16 196	96.06 365	99.86 247	84.08 369	97.79 381	90.38 380	97.80 239	98.81 269

testf1		84.40 376	84.79 378	83.23 394	95.71 394	58.71 427	98.79 401	97.75 406	81.58 407	84.94 408	98.07 386	45.33 418	97.73 382	77.09 415	83.85 391	93.24 408

APD_test2		84.40 376	84.79 378	83.23 394	95.71 394	58.71 427	98.79 401	97.75 406	81.58 407	84.94 408	98.07 386	45.33 418	97.73 382	77.09 415	83.85 391	93.24 408

MIMVSNet		97.06 262	96.73 263	98.05 282	99.38 268	96.64 312	98.47 405	99.35 229	93.41 352	99.48 213	98.53 374	89.66 313	97.70 384	94.16 348	98.11 220	99.80 232

LCM-MVSNet-Re		96.52 285	97.21 252	94.44 366	99.27 275	85.80 399	99.85 287	96.61 416	95.98 277	92.75 389	98.48 376	93.97 253	97.55 385	99.58 179	98.43 194	99.98 112

DTE-MVSNet		95.52 326	94.99 334	97.08 321	97.49 376	96.45 315	100.00 1	99.25 282	93.82 339	96.17 363	99.57 310	87.81 336	97.18 386	94.57 341	86.26 387	97.62 352

mvsany_test3		89.36 369	88.96 373	90.56 381	91.95 407	78.97 406	99.74 309	96.59 417	96.84 221	89.25 398	96.07 399	52.59 414	97.11 387	95.17 335	82.44 396	95.58 400

UnsupCasMVSNet_bld		89.50 368	88.00 374	93.99 373	95.30 399	88.86 394	98.52 404	99.28 263	85.50 402	87.80 403	94.11 407	61.63 411	96.96 388	90.63 375	79.26 402	96.15 391

Anonymous20240521		93.29 348	92.76 355	94.90 364	95.64 397	91.27 383	99.97 251	98.82 381	87.04 397	94.71 375	98.19 383	83.86 370	96.80 389	84.04 401	92.56 324	96.64 384

KD-MVS_2432*1600		94.15 340	93.08 349	97.35 310	99.53 222	97.83 271	99.63 328	99.19 304	92.88 364	96.29 360	97.68 390	98.84 121	96.70 390	89.73 383	63.92 414	97.53 360

miper_refine_blended		94.15 340	93.08 349	97.35 310	99.53 222	97.83 271	99.63 328	99.19 304	92.88 364	96.29 360	97.68 390	98.84 121	96.70 390	89.73 383	63.92 414	97.53 360

test_f		86.87 374	86.06 377	89.28 384	91.45 412	76.37 409	99.87 284	97.11 411	91.10 377	88.46 400	93.05 410	38.31 421	96.66 392	91.77 368	83.46 394	94.82 401

MDA-MVSNet_test_wron		92.61 354	91.09 362	97.19 319	96.71 387	97.26 294	100.00 1	99.14 324	88.61 391	67.90 419	98.32 382	89.03 321	96.57 393	90.47 379	89.59 359	97.74 310

UnsupCasMVSNet_eth		94.25 339	93.89 339	95.34 356	97.63 366	92.13 376	99.73 314	99.36 218	94.88 310	92.78 387	98.63 371	82.72 374	96.53 394	94.57 341	84.73 389	97.36 368

tmp_tt		75.80 385	74.26 387	80.43 398	52.91 430	53.67 429	87.42 417	97.98 401	61.80 417	67.04 420	100.00 1	76.43 396	96.40 395	96.47 313	28.26 422	91.23 412

Gipuma		84.73 375	83.50 380	88.40 386	97.50 374	82.21 404	88.87 415	99.05 359	65.81 415	85.71 406	90.49 412	53.70 413	96.31 396	78.64 411	91.74 336	86.67 414
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		92.44 355	90.92 363	97.03 323	96.20 389	97.06 302	99.99 219	99.14 324	88.21 394	67.93 418	98.43 379	88.63 327	96.28 397	90.64 374	89.08 366	97.74 310

EU-MVSNet		96.63 281	96.53 270	96.94 329	97.59 370	96.87 305	99.76 306	99.47 79	96.35 263	96.85 350	99.78 267	92.57 277	96.27 398	95.33 331	91.08 347	97.68 337

pmmvs-eth3d		91.73 360	90.67 364	94.92 363	91.63 410	92.71 373	99.90 277	98.54 388	91.19 376	88.08 401	95.50 401	79.31 388	96.13 399	90.55 377	81.32 400	95.91 396

PM-MVS		88.39 370	87.41 375	91.31 379	91.73 409	82.02 405	99.79 298	96.62 415	91.06 378	90.71 396	95.73 400	48.60 416	95.96 400	90.56 376	81.91 399	95.97 395

MDA-MVSNet-bldmvs		91.65 361	89.94 369	96.79 338	96.72 386	96.70 310	99.42 352	98.94 373	88.89 390	66.97 421	98.37 380	81.43 380	95.91 401	89.24 389	89.46 362	97.75 288

Patchmatch-RL test		93.49 346	93.63 343	93.05 377	91.78 408	83.41 403	98.21 407	96.95 413	91.58 374	91.05 392	97.64 392	99.40 60	95.83 402	94.11 349	81.95 398	99.91 151

Anonymous20231206		93.45 347	93.17 348	94.30 369	95.00 401	89.69 390	99.98 245	98.43 389	93.30 357	94.50 379	98.59 372	90.52 299	95.73 403	77.46 414	90.73 352	97.48 364

DSMNet-mixed		95.18 332	95.21 330	95.08 357	96.03 391	90.21 389	99.65 325	93.64 422	92.91 363	98.34 291	97.40 393	90.05 308	95.51 404	91.02 373	97.86 233	99.51 259

pmmvs3		90.62 366	89.36 372	94.40 367	90.53 415	91.49 381	100.00 1	96.73 414	84.21 404	93.65 384	96.65 398	82.56 377	94.83 405	82.28 404	77.62 406	96.89 380

KD-MVS_self_test		91.16 362	90.09 367	94.35 368	94.44 403	91.27 383	99.74 309	99.08 344	90.82 380	94.53 378	94.91 406	86.11 352	94.78 406	82.67 403	68.52 412	96.99 377

FMVSNet5		95.32 329	95.43 326	94.99 361	99.39 267	92.99 370	99.25 367	99.24 287	90.45 382	97.44 337	98.45 377	95.78 224	94.39 407	87.02 394	91.88 334	97.59 356

new-patchmatchnet		90.30 367	89.46 371	92.84 378	90.77 413	88.55 395	99.83 289	98.80 382	90.07 387	87.86 402	95.00 404	78.77 389	94.30 408	84.86 399	79.15 403	95.68 399

LCM-MVSNet		79.01 383	76.93 386	85.27 391	78.28 423	68.01 419	96.57 412	98.03 398	55.10 419	82.03 412	93.27 409	31.99 425	93.95 409	82.72 402	74.37 408	93.84 404

CL-MVSNet_self_test		91.07 363	90.35 366	93.24 376	93.27 405	89.16 392	99.55 337	99.25 282	92.34 369	95.23 371	97.05 396	88.86 326	93.59 410	80.67 407	66.95 413	96.96 378

MIMVSNet1		91.96 356	91.20 359	94.23 371	94.94 402	91.69 380	99.34 359	99.22 294	88.23 393	94.18 381	98.45 377	75.52 398	93.41 411	79.37 410	91.49 341	97.60 355

test20.03		93.11 350	92.85 354	93.88 374	95.19 400	91.83 378	100.00 1	98.87 379	93.68 343	92.76 388	98.88 361	89.20 320	92.71 412	77.88 412	89.19 365	97.09 375

test_fmvs3		87.19 373	87.02 376	87.71 387	92.69 406	76.64 408	99.96 257	97.27 410	93.55 347	90.82 395	94.03 408	38.00 422	92.19 413	93.49 356	83.35 395	94.32 402

dmvs_testset		93.27 349	95.48 323	86.65 389	98.74 323	68.42 418	99.92 273	98.91 376	96.19 273	93.28 386	100.00 1	91.06 293	91.67 414	89.64 385	91.54 339	99.86 195

PMMVS2		79.15 382	77.28 385	84.76 392	82.34 420	72.66 410	99.70 319	95.11 420	71.68 414	84.78 411	90.87 411	32.05 424	89.99 415	75.53 417	63.45 416	91.64 411

FPMVS		77.92 384	79.45 382	73.34 403	76.87 424	46.81 430	98.24 406	99.05 359	59.89 418	73.55 414	98.34 381	36.81 423	86.55 416	80.96 406	91.35 345	86.65 415

PMVS	60.66 23	65.98 390	65.05 391	68.75 406	55.06 429	38.40 431	88.19 416	96.98 412	48.30 423	44.82 424	88.52 415	12.22 429	86.49 417	67.58 418	83.79 393	81.35 419
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
WB-MVS		88.24 371	90.09 367	82.68 396	91.56 411	69.51 416	100.00 1	98.73 385	90.72 381	87.29 404	98.12 384	92.87 269	85.01 418	62.19 419	89.34 363	93.54 406

SSC-MVS		87.61 372	89.47 370	82.04 397	90.63 414	68.77 417	99.99 219	98.66 386	90.34 384	86.70 405	98.08 385	92.72 274	84.12 419	59.41 422	88.71 371	93.22 410

MVE	68.59 21	67.22 388	64.68 392	74.84 400	74.67 426	62.32 425	95.84 413	90.87 425	50.98 420	58.72 422	81.05 422	12.20 430	78.95 420	61.06 421	56.75 417	83.24 418
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		70.72 386	70.06 389	72.69 404	83.92 419	65.48 423	99.95 263	92.72 423	49.88 421	72.30 415	86.26 418	47.17 417	77.43 421	53.83 423	44.49 419	75.17 421

EMVS		69.88 387	69.09 390	72.24 405	84.70 418	65.82 422	99.96 257	87.08 428	49.82 422	71.51 416	84.74 419	49.30 415	75.32 422	50.97 424	43.71 420	75.59 420

test123		79.44 381	79.23 383	80.05 399	80.03 422	71.72 412	100.00 1	77.93 430	62.52 416	94.81 374	99.69 279	78.21 390	74.53 423	92.57 361	27.33 423	93.90 403

testmvs		80.17 378	81.95 381	74.80 401	58.54 428	59.58 426	100.00 1	87.14 427	76.09 412	99.61 207	100.00 1	67.06 409	74.19 424	98.84 224	50.30 418	90.64 413

ANet_high		66.05 389	63.44 393	73.88 402	61.14 427	63.45 424	95.68 414	87.18 426	79.93 409	47.35 423	80.68 423	22.35 427	72.33 425	61.24 420	35.42 421	85.88 416

wuyk23d		28.28 391	29.73 395	23.92 407	75.89 425	32.61 432	66.50 418	12.88 431	16.09 424	14.59 426	16.59 425	12.35 428	32.36 426	39.36 425	13.36 424	6.79 422

mmdepth		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.07 395	0.09 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.79 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		24.41 392	32.55 394	0.00 408	0.00 431	0.00 433	0.00 419	99.39 207	0.00 426	0.00 427	100.00 1	93.55 259	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		8.24 394	10.99 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	98.75 128	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		8.33 393	11.11 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.01 396	0.02 399	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.14 427	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						97.98 258								95.74 323

FOURS1					100.00 1	99.97 21	100.00 1	99.42 141	98.52 77	100.00 1

test_one_0601					100.00 1	99.99 5		99.42 141	98.72 67	100.00 1	100.00 1	99.60 21

eth-test2					0.00 431

eth-test					0.00 431

RE-MVS-def			99.55 59		99.99 49	99.91 56	100.00 1	99.42 141	97.62 150	100.00 1	100.00 1	98.94 112		99.99 64	100.00 1	100.00 1

IU-MVS					100.00 1	99.99 5		99.42 141	99.12 7	100.00 1				100.00 1	100.00 1	100.00 1

save fliter					99.99 49	99.93 47	100.00 1	99.42 141	98.93 38

test0726					100.00 1	99.99 5	100.00 1	99.42 141	99.04 16	100.00 1	100.00 1	99.53 33

GSMVS																99.91 151

test_part2					100.00 1	99.99 5				100.00 1

sam_mvs1												99.29 74				99.91 151

sam_mvs												99.33 63

MTGPA								99.42 141

MTMP							100.00 1	99.18 311

test9_res														100.00 1	100.00 1	100.00 1

agg_prior2														100.00 1	100.00 1	100.00 1

test_prior4						99.93 47	100.00 1

test_prior2							100.00 1		98.82 55	100.00 1	100.00 1	99.47 47		100.00 1	100.00 1

新几何2							100.00 1

旧先验1					99.99 49	99.88 77		99.82 40			100.00 1	99.27 77			100.00 1	100.00 1

原ACMM2							100.00 1

test222					99.99 49	99.90 63	100.00 1	99.69 62	97.66 144	100.00 1	100.00 1	99.30 73			100.00 1	100.00 1

segment_acmp												99.55 29

testdata1							100.00 1		98.77 66

plane_prior7					99.00 300	94.78 345

plane_prior6					99.06 292	94.80 341						88.58 330

plane_prior4											99.97 203

plane_prior3						94.79 344			99.03 21	99.08 244

plane_prior2							100.00 1		99.00 27

plane_prior1					99.02 295

plane_prior						94.80 341	100.00 1		99.03 21						95.58 270

n2								0.00 432

nn								0.00 432

door-mid								96.32 418

test11								99.42 141

door								96.13 419

HQP5-MVS						94.82 338

HQP-NCC					99.07 288		100.00 1		99.04 16	99.17 234

ACMP_Plane					99.07 288		100.00 1		99.04 16	99.17 234

BP-MVS														99.79 123

HQP3-MVS								99.40 194							95.58 270

HQP2-MVS												88.61 328

NP-MVS					99.07 288	94.81 340					99.97 203

MDTV_nov1_ep13_2view						99.24 166	99.56 336		96.31 266	99.96 126		98.86 119		98.92 220		99.89 168

ACMMP++_ref															94.58 304

ACMMP++															95.17 290

Test By Simon												99.10 90

High-resolution multi-view benchmark