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.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 2	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 3

testf1		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 82	99.42 22	97.69 63	98.92 51	98.77 78	97.80 25	99.25 266	96.27 100	99.69 78	98.76 219

APD_test2		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 82	99.42 22	97.69 63	98.92 51	98.77 78	97.80 25	99.25 266	96.27 100	99.69 78	98.76 219

Effi-MVS+-dtu		96.81 151	96.09 186	98.99 10	96.90 323	98.69 4	96.42 156	98.09 240	95.86 146	95.15 294	95.54 322	94.26 177	99.81 36	94.06 218	98.51 283	98.47 250

APD_test1		97.95 58	97.68 85	98.75 31	99.60 17	98.60 5	97.21 113	99.08 59	96.57 108	98.07 140	98.38 118	96.22 115	99.14 284	94.71 195	99.31 195	98.52 245

RPSCF		97.87 74	97.51 106	98.95 14	99.15 85	98.43 6	97.56 92	99.06 63	96.19 125	98.48 90	98.70 85	94.72 161	99.24 270	94.37 206	99.33 190	99.17 148

FOURS1					99.59 18	98.20 7	99.03 7	99.25 31	98.96 18	98.87 56

TDRefinement		98.90 5	98.86 8	99.02 6	99.54 26	98.06 8	99.34 4	99.44 20	98.85 21	99.00 46	99.20 35	97.42 42	99.59 159	97.21 68	99.76 58	99.40 100

SR-MVS-dyc-post		98.14 39	97.84 66	99.02 6	98.81 127	98.05 9	97.55 93	98.86 116	97.77 54	98.20 122	98.07 161	96.60 93	99.76 61	95.49 142	99.20 208	99.26 132

RE-MVS-def			97.88 64		98.81 127	98.05 9	97.55 93	98.86 116	97.77 54	98.20 122	98.07 161	96.94 69		95.49 142	99.20 208	99.26 132

SR-MVS		98.00 51	97.66 87	99.01 8	98.77 135	97.93 11	97.38 105	98.83 129	97.32 84	98.06 141	97.85 187	96.65 88	99.77 56	95.00 179	99.11 222	99.32 115

MTAPA		98.14 39	97.84 66	99.06 3	99.44 38	97.90 12	97.25 109	98.73 151	97.69 63	97.90 157	97.96 176	95.81 130	99.82 34	96.13 106	99.61 98	99.45 85

UA-Net		98.88 7	98.76 13	99.22 2	99.11 94	97.89 13	99.47 3	99.32 25	99.08 10	97.87 162	99.67 2	96.47 100	99.92 5	97.88 42	99.98 2	99.85 3

mPP-MVS		97.91 69	97.53 104	99.04 4	99.22 68	97.87 14	97.74 80	98.78 143	96.04 133	97.10 200	97.73 200	96.53 95	99.78 47	95.16 167	99.50 139	99.46 81

CP-MVS		97.92 66	97.56 101	98.99 10	98.99 110	97.82 15	97.93 65	98.96 96	96.11 128	96.89 220	97.45 218	96.85 80	99.78 47	95.19 163	99.63 91	99.38 106

PMVS	89.60 17	96.71 159	96.97 138	95.95 233	99.51 30	97.81 16	97.42 104	97.49 276	97.93 50	95.95 269	98.58 96	96.88 77	96.91 391	89.59 316	99.36 177	93.12 396
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MP-MVS		97.64 96	97.18 126	99.00 9	99.32 55	97.77 17	97.49 99	98.73 151	96.27 119	95.59 284	97.75 197	96.30 110	99.78 47	93.70 233	99.48 146	99.45 85
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MSP-MVS		97.45 111	96.92 143	99.03 5	99.26 59	97.70 18	97.66 84	98.89 105	95.65 155	98.51 85	96.46 286	92.15 229	99.81 36	95.14 170	98.58 279	99.58 39
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
XVS		97.96 54	97.63 93	98.94 15	99.15 85	97.66 19	97.77 75	98.83 129	97.42 75	96.32 251	97.64 205	96.49 98	99.72 87	95.66 133	99.37 174	99.45 85

X-MVStestdata		92.86 304	90.83 331	98.94 15	99.15 85	97.66 19	97.77 75	98.83 129	97.42 75	96.32 251	36.50 406	96.49 98	99.72 87	95.66 133	99.37 174	99.45 85

PGM-MVS		97.88 73	97.52 105	98.96 13	99.20 77	97.62 21	97.09 120	99.06 63	95.45 165	97.55 172	97.94 179	97.11 55	99.78 47	94.77 191	99.46 151	99.48 76

ACMMP		98.05 48	97.75 80	98.93 18	99.23 65	97.60 22	98.09 57	98.96 96	95.75 152	97.91 156	98.06 166	96.89 75	99.76 61	95.32 157	99.57 108	99.43 96
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
HPM-MVS++		96.99 135	96.38 175	98.81 27	98.64 149	97.59 23	95.97 193	98.20 223	95.51 163	95.06 296	96.53 282	94.10 180	99.70 110	94.29 209	99.15 215	99.13 156

LS3D		97.77 86	97.50 108	98.57 47	96.24 337	97.58 24	98.45 31	98.85 120	98.58 28	97.51 175	97.94 179	95.74 133	99.63 144	95.19 163	98.97 236	98.51 246

ACMMPR		97.95 58	97.62 95	98.94 15	99.20 77	97.56 25	97.59 90	98.83 129	96.05 131	97.46 182	97.63 206	96.77 84	99.76 61	95.61 137	99.46 151	99.49 70

EGC-MVSNET		83.08 372	77.93 375	98.53 50	99.57 20	97.55 26	98.33 38	98.57 181	4.71 408	10.38 409	98.90 69	95.60 138	99.50 186	95.69 130	99.61 98	98.55 242

region2R		97.92 66	97.59 98	98.92 21	99.22 68	97.55 26	97.60 88	98.84 123	96.00 136	97.22 189	97.62 207	96.87 79	99.76 61	95.48 145	99.43 163	99.46 81

ACMM	93.33 11	98.05 48	97.79 73	98.85 24	99.15 85	97.55 26	96.68 146	98.83 129	95.21 174	98.36 104	98.13 153	98.13 18	99.62 149	96.04 110	99.54 121	99.39 104
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HFP-MVS		97.94 62	97.64 91	98.83 25	99.15 85	97.50 29	97.59 90	98.84 123	96.05 131	97.49 177	97.54 212	97.07 59	99.70 110	95.61 137	99.46 151	99.30 120

HPM-MVS_fast		98.32 30	98.13 40	98.88 23	99.54 26	97.48 30	98.35 35	99.03 75	95.88 144	97.88 159	98.22 145	98.15 16	99.74 76	96.50 90	99.62 92	99.42 97

HPM-MVS		98.11 43	97.83 69	98.92 21	99.42 41	97.46 31	98.57 20	99.05 67	95.43 168	97.41 184	97.50 216	97.98 19	99.79 44	95.58 140	99.57 108	99.50 62
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
XVG-OURS		97.12 129	96.74 152	98.26 70	98.99 110	97.45 32	93.82 305	99.05 67	95.19 176	98.32 111	97.70 202	95.22 149	98.41 360	94.27 210	98.13 300	98.93 193

MAR-MVS		94.21 269	93.03 289	97.76 109	96.94 321	97.44 33	96.97 126	97.15 286	87.89 338	92.00 368	92.73 369	92.14 230	99.12 288	83.92 374	97.51 330	96.73 361
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
XVG-OURS-SEG-HR		97.38 116	97.07 132	98.30 68	99.01 109	97.41 34	94.66 270	99.02 77	95.20 175	98.15 130	97.52 214	98.83 5	98.43 359	94.87 184	96.41 358	99.07 171

COLMAP_ROB	94.48 6	98.25 35	98.11 42	98.64 43	99.21 75	97.35 35	97.96 62	99.16 40	98.34 35	98.78 64	98.52 102	97.32 45	99.45 203	94.08 217	99.67 84	99.13 156
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
APD-MVS_3200maxsize		98.13 42	97.90 59	98.79 29	98.79 131	97.31 36	97.55 93	98.92 102	97.72 59	98.25 118	98.13 153	97.10 56	99.75 67	95.44 149	99.24 206	99.32 115

anonymousdsp		98.72 14	98.63 20	98.99 10	99.62 16	97.29 37	98.65 19	99.19 37	95.62 157	99.35 25	99.37 19	97.38 43	99.90 14	98.59 28	99.91 19	99.77 12

GST-MVS		97.82 81	97.49 109	98.81 27	99.23 65	97.25 38	97.16 114	98.79 139	95.96 138	97.53 173	97.40 222	96.93 71	99.77 56	95.04 176	99.35 182	99.42 97

ZNCC-MVS		97.92 66	97.62 95	98.83 25	99.32 55	97.24 39	97.45 100	98.84 123	95.76 150	96.93 217	97.43 220	97.26 50	99.79 44	96.06 107	99.53 125	99.45 85

DeepPCF-MVS	94.58 5	96.90 143	96.43 172	98.31 67	97.48 290	97.23 40	92.56 339	98.60 176	92.84 261	98.54 83	97.40 222	96.64 90	98.78 324	94.40 205	99.41 170	98.93 193

SteuartSystems-ACMMP		98.02 50	97.76 78	98.79 29	99.43 39	97.21 41	97.15 115	98.90 104	96.58 105	98.08 138	97.87 186	97.02 64	99.76 61	95.25 160	99.59 103	99.40 100
Skip Steuart: Steuart Systems R&D Blog.
LPG-MVS_test		97.94 62	97.67 86	98.74 34	99.15 85	97.02 42	97.09 120	99.02 77	95.15 178	98.34 107	98.23 142	97.91 21	99.70 110	94.41 203	99.73 67	99.50 62

LGP-MVS_train				98.74 34	99.15 85	97.02 42		99.02 77	95.15 178	98.34 107	98.23 142	97.91 21	99.70 110	94.41 203	99.73 67	99.50 62

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 37	99.71 9	96.99 44	99.69 2	99.57 14	99.02 15	99.62 12	99.36 21	98.53 9	99.52 181	98.58 29	99.95 5	99.66 30
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
FPMVS		89.92 343	88.63 351	93.82 321	98.37 185	96.94 45	91.58 359	93.34 353	88.00 336	90.32 381	97.10 246	70.87 385	91.13 405	71.91 403	96.16 366	93.39 395

XVG-ACMP-BASELINE		97.58 103	97.28 119	98.49 52	99.16 82	96.90 46	96.39 157	98.98 92	95.05 183	98.06 141	98.02 170	95.86 122	99.56 168	94.37 206	99.64 89	99.00 180

MP-MVS-pluss		97.69 92	97.36 114	98.70 38	99.50 33	96.84 47	95.38 232	98.99 89	92.45 270	98.11 133	98.31 124	97.25 51	99.77 56	96.60 86	99.62 92	99.48 76
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 72	97.63 93	98.67 40	99.35 51	96.84 47	96.36 162	98.79 139	95.07 182	97.88 159	98.35 120	97.24 52	99.72 87	96.05 109	99.58 105	99.45 85

PM-MVS		97.36 120	97.10 129	98.14 82	98.91 120	96.77 49	96.20 174	98.63 174	93.82 222	98.54 83	98.33 122	93.98 183	99.05 299	95.99 115	99.45 154	98.61 237

MIMVSNet1		98.51 23	98.45 29	98.67 40	99.72 8	96.71 50	98.76 12	98.89 105	98.49 31	99.38 22	99.14 46	95.44 143	99.84 30	96.47 91	99.80 51	99.47 79

ACMP	92.54 13	97.47 110	97.10 129	98.55 49	99.04 106	96.70 51	96.24 172	98.89 105	93.71 225	97.97 151	97.75 197	97.44 40	99.63 144	93.22 245	99.70 77	99.32 115
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CS-MVS		98.09 44	98.01 52	98.32 65	98.45 179	96.69 52	98.52 26	99.69 5	98.07 46	96.07 265	97.19 241	96.88 77	99.86 24	97.50 60	99.73 67	98.41 253

SMA-MVS		97.48 109	97.11 128	98.60 45	98.83 126	96.67 53	96.74 139	98.73 151	91.61 283	98.48 90	98.36 119	96.53 95	99.68 122	95.17 165	99.54 121	99.45 85
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
ITE_SJBPF				97.85 104	98.64 149	96.66 54		98.51 186	95.63 156	97.22 189	97.30 235	95.52 139	98.55 350	90.97 284	98.90 244	98.34 264

CPTT-MVS		96.69 160	96.08 187	98.49 52	98.89 121	96.64 55	97.25 109	98.77 144	92.89 260	96.01 268	97.13 243	92.23 228	99.67 128	92.24 258	99.34 185	99.17 148

OPM-MVS		97.54 105	97.25 120	98.41 59	99.11 94	96.61 56	95.24 243	98.46 189	94.58 201	98.10 135	98.07 161	97.09 58	99.39 225	95.16 167	99.44 155	99.21 140
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS_H		98.65 15	98.62 22	98.75 31	99.51 30	96.61 56	98.55 22	99.17 39	99.05 13	99.17 35	98.79 75	95.47 141	99.89 18	97.95 41	99.91 19	99.75 19

N_pmnet		95.18 226	94.23 263	98.06 88	97.85 238	96.55 58	92.49 340	91.63 371	89.34 315	98.09 136	97.41 221	90.33 260	99.06 298	91.58 273	99.31 195	98.56 240

PHI-MVS		96.96 139	96.53 167	98.25 73	97.48 290	96.50 59	96.76 138	98.85 120	93.52 231	96.19 261	96.85 262	95.94 120	99.42 210	93.79 229	99.43 163	98.83 210

jajsoiax		98.77 9	98.79 12	98.74 34	99.66 13	96.48 60	98.45 31	99.12 49	95.83 148	99.67 7	99.37 19	98.25 13	99.92 5	98.77 20	99.94 8	99.82 6

mvs_tets		98.90 5	98.94 6	98.75 31	99.69 10	96.48 60	98.54 23	99.22 32	96.23 122	99.71 4	99.48 10	98.77 7	99.93 3	98.89 17	99.95 5	99.84 5

pmmvs6		99.07 4	99.24 4	98.56 48	99.81 2	96.38 62	98.87 9	99.30 27	99.01 16	99.63 11	99.66 3	99.27 2	99.68 122	97.75 50	99.89 26	99.62 36

tt0805		97.44 112	97.56 101	97.11 163	99.55 23	96.36 63	98.66 18	95.66 320	98.31 36	97.09 205	95.45 325	97.17 54	98.50 354	98.67 25	97.45 334	96.48 367

OurMVSNet-221017-0		98.61 16	98.61 24	98.63 44	99.77 5	96.35 64	99.17 6	99.05 67	98.05 47	99.61 13	99.52 7	93.72 191	99.88 20	98.72 24	99.88 27	99.65 33

UniMVSNet_ETH3D		99.12 3	99.28 3	98.65 42	99.77 5	96.34 65	99.18 5	99.20 35	99.67 2	99.73 3	99.65 5	99.15 3	99.86 24	97.22 67	99.92 16	99.77 12

APD-MVS		97.00 134	96.53 167	98.41 59	98.55 164	96.31 66	96.32 165	98.77 144	92.96 259	97.44 183	97.58 211	95.84 123	99.74 76	91.96 263	99.35 182	99.19 145
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_djsdf		98.73 11	98.74 16	98.69 39	99.63 15	96.30 67	98.67 15	99.02 77	96.50 110	99.32 26	99.44 14	97.43 41	99.92 5	98.73 22	99.95 5	99.86 2

Gipuma		98.07 47	98.31 35	97.36 146	99.76 7	96.28 68	98.51 27	99.10 52	98.76 23	96.79 222	99.34 25	96.61 91	98.82 320	96.38 95	99.50 139	96.98 347
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DPE-MVS		97.64 96	97.35 115	98.50 51	98.85 125	96.18 69	95.21 245	98.99 89	95.84 147	98.78 64	98.08 159	96.84 81	99.81 36	93.98 223	99.57 108	99.52 58
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
AllTest		97.20 127	96.92 143	98.06 88	99.08 98	96.16 70	97.14 117	99.16 40	94.35 206	97.78 167	98.07 161	95.84 123	99.12 288	91.41 274	99.42 166	98.91 197

TestCases				98.06 88	99.08 98	96.16 70		99.16 40	94.35 206	97.78 167	98.07 161	95.84 123	99.12 288	91.41 274	99.42 166	98.91 197

DTE-MVSNet		98.79 8	98.86 8	98.59 46	99.55 23	96.12 72	98.48 30	99.10 52	99.36 4	99.29 28	99.06 52	97.27 48	99.93 3	97.71 52	99.91 19	99.70 26

h-mvs33		96.29 178	95.63 208	98.26 70	98.50 173	96.11 73	96.90 129	97.09 289	96.58 105	97.21 191	98.19 147	84.14 322	99.78 47	95.89 121	96.17 365	98.89 201

test_part2					99.03 107	96.07 74				98.08 138

APDe-MVS		98.14 39	98.03 50	98.47 54	98.72 139	96.04 75	98.07 58	99.10 52	95.96 138	98.59 80	98.69 86	96.94 69	99.81 36	96.64 84	99.58 105	99.57 46
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
F-COLMAP		95.30 221	94.38 260	98.05 92	98.64 149	96.04 75	95.61 219	98.66 168	89.00 321	93.22 346	96.40 290	92.90 207	99.35 241	87.45 348	97.53 329	98.77 218

CS-MVS-test		97.91 69	97.84 66	98.14 82	98.52 168	96.03 77	98.38 34	99.67 6	98.11 44	95.50 286	96.92 259	96.81 83	99.87 22	96.87 82	99.76 58	98.51 246

OMC-MVS		96.48 171	96.00 190	97.91 100	98.30 189	96.01 78	94.86 262	98.60 176	91.88 279	97.18 194	97.21 240	96.11 117	99.04 300	90.49 304	99.34 185	98.69 228

ZD-MVS					98.43 181	95.94 79		98.56 182	90.72 296	96.66 233	97.07 247	95.02 155	99.74 76	91.08 281	98.93 242

test_vis3_rt		97.04 132	96.98 137	97.23 157	98.44 180	95.88 80	96.82 133	99.67 6	90.30 303	99.27 29	99.33 27	94.04 181	96.03 397	97.14 72	97.83 312	99.78 11

TranMVSNet+NR-MVSNet		98.33 29	98.30 37	98.43 57	99.07 100	95.87 81	96.73 143	99.05 67	98.67 24	98.84 59	98.45 110	97.58 38	99.88 20	96.45 92	99.86 31	99.54 53

mvsmamba		98.16 37	98.06 47	98.44 55	99.53 28	95.87 81	98.70 13	98.94 99	97.71 61	98.85 57	99.10 48	91.35 245	99.83 32	98.47 30	99.90 24	99.64 35

UniMVSNet (Re)		97.83 78	97.65 88	98.35 64	98.80 129	95.86 83	95.92 199	99.04 74	97.51 72	98.22 121	97.81 192	94.68 164	99.78 47	97.14 72	99.75 65	99.41 99

UniMVSNet_NR-MVSNet		97.83 78	97.65 88	98.37 62	98.72 139	95.78 84	95.66 213	99.02 77	98.11 44	98.31 113	97.69 203	94.65 166	99.85 27	97.02 77	99.71 74	99.48 76

DU-MVS		97.79 84	97.60 97	98.36 63	98.73 137	95.78 84	95.65 215	98.87 113	97.57 67	98.31 113	97.83 188	94.69 162	99.85 27	97.02 77	99.71 74	99.46 81

PatchMatch-RL		94.61 255	93.81 275	97.02 174	98.19 203	95.72 86	93.66 310	97.23 282	88.17 334	94.94 301	95.62 320	91.43 242	98.57 347	87.36 349	97.68 322	96.76 360

DeepC-MVS	95.41 4	97.82 81	97.70 81	98.16 79	98.78 134	95.72 86	96.23 173	99.02 77	93.92 221	98.62 76	98.99 57	97.69 29	99.62 149	96.18 105	99.87 29	99.15 151
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		97.60 100	97.39 112	98.22 75	98.93 116	95.69 88	97.05 122	99.10 52	95.32 171	97.83 165	97.88 185	96.44 103	99.72 87	94.59 200	99.39 172	99.25 136

NCCC		96.52 169	95.99 191	98.10 85	97.81 247	95.68 89	95.00 257	98.20 223	95.39 169	95.40 289	96.36 292	93.81 188	99.45 203	93.55 236	98.42 289	99.17 148

PEN-MVS		98.75 10	98.85 10	98.44 55	99.58 19	95.67 90	98.45 31	99.15 44	99.33 5	99.30 27	99.00 55	97.27 48	99.92 5	97.64 56	99.92 16	99.75 19

nrg030		98.54 21	98.62 22	98.32 65	99.22 68	95.66 91	97.90 67	99.08 59	98.31 36	99.02 43	98.74 81	97.68 30	99.61 156	97.77 49	99.85 38	99.70 26

3Dnovator+	96.13 3	97.73 88	97.59 98	98.15 81	98.11 219	95.60 92	98.04 59	98.70 160	98.13 43	96.93 217	98.45 110	95.30 147	99.62 149	95.64 135	98.96 237	99.24 137

RRT_MVS		97.95 58	97.79 73	98.43 57	99.67 12	95.56 93	98.86 10	96.73 305	97.99 49	99.15 36	99.35 23	89.84 269	99.90 14	98.64 26	99.90 24	99.82 6

LF4IMVS		96.07 186	95.63 208	97.36 146	98.19 203	95.55 94	95.44 225	98.82 137	92.29 273	95.70 282	96.55 280	92.63 216	98.69 335	91.75 272	99.33 190	97.85 311

NR-MVSNet		97.96 54	97.86 65	98.26 70	98.73 137	95.54 95	98.14 54	98.73 151	97.79 53	99.42 20	97.83 188	94.40 174	99.78 47	95.91 120	99.76 58	99.46 81

CNVR-MVS		96.92 141	96.55 164	98.03 93	98.00 228	95.54 95	94.87 261	98.17 229	94.60 198	96.38 248	97.05 249	95.67 135	99.36 237	95.12 173	99.08 226	99.19 145

hse-mvs2		95.77 199	95.09 221	97.79 107	97.84 243	95.51 97	95.66 213	95.43 329	96.58 105	97.21 191	96.16 299	84.14 322	99.54 176	95.89 121	96.92 342	98.32 265

DVP-MVS		97.78 85	97.65 88	98.16 79	99.24 63	95.51 97	96.74 139	98.23 218	95.92 141	98.40 98	98.28 133	97.06 60	99.71 102	95.48 145	99.52 130	99.26 132
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					99.24 63	95.51 97	96.89 130	98.89 105	95.92 141	98.64 74	98.31 124	97.06 60

test_one_0601					99.05 105	95.50 100		98.87 113	97.21 88	98.03 145	98.30 128	96.93 71

test_0728_SECOND				98.25 73	99.23 65	95.49 101	96.74 139	98.89 105					99.75 67	95.48 145	99.52 130	99.53 56

PS-CasMVS		98.73 11	98.85 10	98.39 61	99.55 23	95.47 102	98.49 28	99.13 48	99.22 8	99.22 33	98.96 61	97.35 44	99.92 5	97.79 48	99.93 11	99.79 10

DVP-MVS++		97.96 54	97.90 59	98.12 84	97.75 263	95.40 103	99.03 7	98.89 105	96.62 101	98.62 76	98.30 128	96.97 67	99.75 67	95.70 128	99.25 203	99.21 140

IU-MVS					99.22 68	95.40 103		98.14 236	85.77 358	98.36 104				95.23 162	99.51 135	99.49 70

AUN-MVS		93.95 280	92.69 300	97.74 110	97.80 251	95.38 105	95.57 222	95.46 328	91.26 290	92.64 361	96.10 305	74.67 369	99.55 173	93.72 232	96.97 341	98.30 269

test_prior4						95.38 105	93.61 313

wuyk23d		93.25 299	95.20 215	87.40 386	96.07 349	95.38 105	97.04 123	94.97 335	95.33 170	99.70 6	98.11 157	98.14 17	91.94 404	77.76 395	99.68 82	74.89 404

SED-MVS		97.94 62	97.90 59	98.07 86	99.22 68	95.35 108	96.79 136	98.83 129	96.11 128	99.08 40	98.24 140	97.87 23	99.72 87	95.44 149	99.51 135	99.14 154

test_241102_ONE					99.22 68	95.35 108		98.83 129	96.04 133	99.08 40	98.13 153	97.87 23	99.33 246

MSC_two_6792asdad				98.22 75	97.75 263	95.34 110		98.16 233					99.75 67	95.87 123	99.51 135	99.57 46

No_MVS				98.22 75	97.75 263	95.34 110		98.16 233					99.75 67	95.87 123	99.51 135	99.57 46

MVS_111021_LR		96.82 150	96.55 164	97.62 119	98.27 194	95.34 110	93.81 307	98.33 208	94.59 200	96.56 240	96.63 277	96.61 91	98.73 329	94.80 187	99.34 185	98.78 215

OPU-MVS				97.64 118	98.01 224	95.27 113	96.79 136				97.35 231	96.97 67	98.51 353	91.21 280	99.25 203	99.14 154

CNLPA		95.04 233	94.47 256	96.75 192	97.81 247	95.25 114	94.12 293	97.89 252	94.41 204	94.57 307	95.69 316	90.30 263	98.35 366	86.72 355	98.76 260	96.64 362

TEST9					97.84 243	95.23 115	93.62 311	98.39 200	86.81 347	93.78 327	95.99 307	94.68 164	99.52 181

train_agg		95.46 214	94.66 242	97.88 102	97.84 243	95.23 115	93.62 311	98.39 200	87.04 343	93.78 327	95.99 307	94.58 168	99.52 181	91.76 271	98.90 244	98.89 201

TSAR-MVS + GP.		96.47 172	96.12 184	97.49 134	97.74 266	95.23 115	94.15 289	96.90 296	93.26 240	98.04 144	96.70 273	94.41 173	98.89 315	94.77 191	99.14 216	98.37 258

CP-MVSNet		98.42 26	98.46 27	98.30 68	99.46 36	95.22 118	98.27 44	98.84 123	99.05 13	99.01 44	98.65 91	95.37 144	99.90 14	97.57 57	99.91 19	99.77 12

ACMH+	93.58 10	98.23 36	98.31 35	97.98 97	99.39 46	95.22 118	97.55 93	99.20 35	98.21 41	99.25 31	98.51 104	98.21 14	99.40 221	94.79 188	99.72 71	99.32 115

Vis-MVSNet		98.27 33	98.34 34	98.07 86	99.33 53	95.21 120	98.04 59	99.46 18	97.32 84	97.82 166	99.11 47	96.75 85	99.86 24	97.84 45	99.36 177	99.15 151
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EC-MVSNet		97.90 71	97.94 58	97.79 107	98.66 148	95.14 121	98.31 39	99.66 8	97.57 67	95.95 269	97.01 253	96.99 66	99.82 34	97.66 55	99.64 89	98.39 256

SD-MVS		97.37 118	97.70 81	96.35 214	98.14 215	95.13 122	96.54 152	98.92 102	95.94 140	99.19 34	98.08 159	97.74 28	95.06 398	95.24 161	99.54 121	98.87 207
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
PLC	91.02 16	94.05 276	92.90 292	97.51 127	98.00 228	95.12 123	94.25 282	98.25 215	86.17 352	91.48 373	95.25 327	91.01 249	99.19 276	85.02 369	96.69 353	98.22 277
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_8					97.81 247	95.07 124	93.54 314	98.38 202	87.04 343	93.71 331	95.96 310	94.58 168	99.52 181

TSAR-MVS + MP.		97.42 114	97.23 122	98.00 95	99.38 48	95.00 125	97.63 87	98.20 223	93.00 254	98.16 128	98.06 166	95.89 121	99.72 87	95.67 132	99.10 224	99.28 127
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
agg_prior					97.80 251	94.96 126		98.36 204		93.49 339			99.53 178

CDPH-MVS		95.45 215	94.65 243	97.84 105	98.28 192	94.96 126	93.73 309	98.33 208	85.03 366	95.44 287	96.60 278	95.31 146	99.44 206	90.01 310	99.13 218	99.11 164

CSCG		97.40 115	97.30 117	97.69 115	98.95 112	94.83 128	97.28 108	98.99 89	96.35 118	98.13 132	95.95 311	95.99 119	99.66 134	94.36 208	99.73 67	98.59 238

PS-MVSNAJss		98.53 22	98.63 20	98.21 78	99.68 11	94.82 129	98.10 56	99.21 33	96.91 94	99.75 2	99.45 13	95.82 126	99.92 5	98.80 19	99.96 4	99.89 1

DP-MVS		97.87 74	97.89 62	97.81 106	98.62 155	94.82 129	97.13 118	98.79 139	98.98 17	98.74 70	98.49 105	95.80 131	99.49 191	95.04 176	99.44 155	99.11 164

save fliter					98.48 176	94.71 131	94.53 274	98.41 197	95.02 185

alignmvs		96.01 190	95.52 211	97.50 131	97.77 260	94.71 131	96.07 184	96.84 297	97.48 73	96.78 226	94.28 348	85.50 313	99.40 221	96.22 102	98.73 265	98.40 254

新几何1				97.25 155	98.29 190	94.70 133		97.73 262	77.98 396	94.83 303	96.67 275	92.08 233	99.45 203	88.17 337	98.65 273	97.61 326

plane_prior7					98.70 144	94.67 134

CMPMVS	73.10 23	92.74 306	91.39 318	96.77 191	93.57 397	94.67 134	94.21 286	97.67 265	80.36 389	93.61 335	96.60 278	82.85 331	97.35 385	84.86 370	98.78 258	98.29 272
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_fmvsmconf0.01_n		98.57 17	98.74 16	98.06 88	99.39 46	94.63 136	96.70 145	99.82 1	95.44 167	99.64 10	99.52 7	98.96 4	99.74 76	99.38 3	99.86 31	99.81 8

test_fmvsmconf0.1_n		98.41 27	98.54 25	98.03 93	99.16 82	94.61 137	96.18 175	99.73 3	95.05 183	99.60 14	99.34 25	98.68 8	99.72 87	99.21 7	99.85 38	99.76 17

test_fmvsmconf_n		98.30 32	98.41 32	97.99 96	98.94 115	94.60 138	96.00 190	99.64 12	94.99 186	99.43 19	99.18 39	98.51 10	99.71 102	99.13 10	99.84 40	99.67 28

pm-mvs1		98.47 24	98.67 18	97.86 103	99.52 29	94.58 139	98.28 42	99.00 86	97.57 67	99.27 29	99.22 34	98.32 12	99.50 186	97.09 74	99.75 65	99.50 62

GeoE		97.75 87	97.70 81	97.89 101	98.88 122	94.53 140	97.10 119	98.98 92	95.75 152	97.62 170	97.59 209	97.61 37	99.77 56	96.34 97	99.44 155	99.36 112

plane_prior3						94.51 141			95.29 173	96.16 262

TAPA-MVS	93.32 12	94.93 237	94.23 263	97.04 172	98.18 206	94.51 141	95.22 244	98.73 151	81.22 385	96.25 257	95.95 311	93.80 189	98.98 308	89.89 312	98.87 248	97.62 325
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.37 118	97.25 120	97.74 110	98.69 146	94.50 143	97.04 123	95.61 324	98.59 27	98.51 85	98.72 82	92.54 221	99.58 161	96.02 112	99.49 142	99.12 161

AdaColmap		95.11 230	94.62 247	96.58 201	97.33 305	94.45 144	94.92 259	98.08 241	93.15 250	93.98 325	95.53 323	94.34 175	99.10 294	85.69 360	98.61 276	96.20 372

sasdasda		97.23 125	97.21 124	97.30 149	97.65 277	94.39 145	97.84 70	99.05 67	97.42 75	96.68 230	93.85 353	97.63 35	99.33 246	96.29 98	98.47 285	98.18 281

Fast-Effi-MVS+-dtu		96.44 173	96.12 184	97.39 145	97.18 311	94.39 145	95.46 224	98.73 151	96.03 135	94.72 304	94.92 335	96.28 113	99.69 117	93.81 228	97.98 305	98.09 286

canonicalmvs		97.23 125	97.21 124	97.30 149	97.65 277	94.39 145	97.84 70	99.05 67	97.42 75	96.68 230	93.85 353	97.63 35	99.33 246	96.29 98	98.47 285	98.18 281

Anonymous20231211		98.55 20	98.76 13	97.94 99	98.79 131	94.37 148	98.84 11	99.15 44	99.37 3	99.67 7	99.43 15	95.61 137	99.72 87	98.12 34	99.86 31	99.73 22

plane_prior6					98.38 184	94.37 148						91.91 239

mvsany_test3		96.21 181	95.93 196	97.05 170	97.40 298	94.33 150	95.76 207	94.20 343	89.10 318	99.36 24	99.60 6	93.97 184	97.85 379	95.40 156	98.63 274	98.99 183

pmmvs-eth3d		96.49 170	96.18 183	97.42 142	98.25 196	94.29 151	94.77 266	98.07 245	89.81 311	97.97 151	98.33 122	93.11 201	99.08 296	95.46 148	99.84 40	98.89 201

HQP_MVS		96.66 162	96.33 178	97.68 116	98.70 144	94.29 151	96.50 153	98.75 148	96.36 116	96.16 262	96.77 269	91.91 239	99.46 199	92.59 254	99.20 208	99.28 127

plane_prior						94.29 151	95.42 227		94.31 208						98.93 242

Anonymous20240529		97.96 54	98.04 49	97.71 112	98.69 146	94.28 154	97.86 69	98.31 212	98.79 22	99.23 32	98.86 73	95.76 132	99.61 156	95.49 142	99.36 177	99.23 138

test_prior				97.46 137	97.79 256	94.26 155		98.42 196					99.34 244			98.79 214

v7n		98.73 11	98.99 5	97.95 98	99.64 14	94.20 156	98.67 15	99.14 47	99.08 10	99.42 20	99.23 33	96.53 95	99.91 13	99.27 5	99.93 11	99.73 22

DeepC-MVS_fast	94.34 7	96.74 154	96.51 169	97.44 139	97.69 270	94.15 157	96.02 188	98.43 193	93.17 249	97.30 186	97.38 228	95.48 140	99.28 260	93.74 230	99.34 185	98.88 205
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MCST-MVS		96.24 180	95.80 201	97.56 122	98.75 136	94.13 158	94.66 270	98.17 229	90.17 306	96.21 259	96.10 305	95.14 151	99.43 208	94.13 216	98.85 251	99.13 156

test12				97.46 137	97.61 281	94.07 159		97.78 260		93.57 337		93.31 198	99.42 210		98.78 258	98.89 201

test_0402		97.84 77	97.97 55	97.47 136	99.19 79	94.07 159	96.71 144	98.73 151	98.66 25	98.56 82	98.41 114	96.84 81	99.69 117	94.82 186	99.81 48	98.64 232

API-MVS		95.09 232	95.01 225	95.31 262	96.61 327	94.02 161	96.83 132	97.18 285	95.60 158	95.79 276	94.33 347	94.54 170	98.37 365	85.70 359	98.52 281	93.52 393

IS-MVSNet		96.93 140	96.68 155	97.70 113	99.25 62	94.00 162	98.57 20	96.74 303	98.36 34	98.14 131	97.98 175	88.23 288	99.71 102	93.10 248	99.72 71	99.38 106

DP-MVS Recon		95.55 208	95.13 219	96.80 188	98.51 170	93.99 163	94.60 272	98.69 161	90.20 305	95.78 278	96.21 298	92.73 212	98.98 308	90.58 300	98.86 250	97.42 335

test_fmvsm_n_1920		98.08 45	98.29 38	97.43 140	98.88 122	93.95 164	96.17 179	99.57 14	95.66 154	99.52 15	98.71 84	97.04 62	99.64 140	99.21 7	99.87 29	98.69 228

ETV-MVS		96.13 185	95.90 197	96.82 187	97.76 261	93.89 165	95.40 230	98.95 98	95.87 145	95.58 285	91.00 388	96.36 108	99.72 87	93.36 239	98.83 254	96.85 354

旧先验1					97.80 251	93.87 166		97.75 261			97.04 250	93.57 193			98.68 268	98.72 224

Anonymous202405211		96.34 177	95.98 192	97.43 140	98.25 196	93.85 167	96.74 139	94.41 341	97.72 59	98.37 101	98.03 169	87.15 301	99.53 178	94.06 218	99.07 228	98.92 196

UGNet		96.81 151	96.56 163	97.58 121	96.64 326	93.84 168	97.75 78	97.12 288	96.47 113	93.62 334	98.88 71	93.22 200	99.53 178	95.61 137	99.69 78	99.36 112
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
VPA-MVSNet		98.27 33	98.46 27	97.70 113	99.06 101	93.80 169	97.76 77	99.00 86	98.40 33	99.07 42	98.98 58	96.89 75	99.75 67	97.19 71	99.79 53	99.55 52

LCM-MVSNet-Re		97.33 121	97.33 116	97.32 148	98.13 218	93.79 170	96.99 125	99.65 9	96.74 99	99.47 17	98.93 64	96.91 74	99.84 30	90.11 308	99.06 231	98.32 265

EPP-MVSNet		96.84 146	96.58 161	97.65 117	99.18 80	93.78 171	98.68 14	96.34 308	97.91 51	97.30 186	98.06 166	88.46 285	99.85 27	93.85 227	99.40 171	99.32 115

NP-MVS					98.14 215	93.72 172					95.08 329

MGCFI-Net		97.20 127	97.23 122	97.08 168	97.68 271	93.71 173	97.79 73	99.09 57	97.40 80	96.59 237	93.96 350	97.67 31	99.35 241	96.43 93	98.50 284	98.17 283

GBi-Net		96.99 135	96.80 149	97.56 122	97.96 230	93.67 174	98.23 46	98.66 168	95.59 159	97.99 147	99.19 36	89.51 275	99.73 82	94.60 197	99.44 155	99.30 120

test1		96.99 135	96.80 149	97.56 122	97.96 230	93.67 174	98.23 46	98.66 168	95.59 159	97.99 147	99.19 36	89.51 275	99.73 82	94.60 197	99.44 155	99.30 120

FMVSNet1		97.95 58	98.08 44	97.56 122	99.14 92	93.67 174	98.23 46	98.66 168	97.41 79	99.00 46	99.19 36	95.47 141	99.73 82	95.83 125	99.76 58	99.30 120

MVS_111021_HR		96.73 156	96.54 166	97.27 152	98.35 187	93.66 177	93.42 317	98.36 204	94.74 192	96.58 238	96.76 271	96.54 94	98.99 306	94.87 184	99.27 201	99.15 151

3Dnovator	96.53 2	97.61 99	97.64 91	97.50 131	97.74 266	93.65 178	98.49 28	98.88 111	96.86 96	97.11 199	98.55 100	95.82 126	99.73 82	95.94 118	99.42 166	99.13 156

CDS-MVSNet		94.88 240	94.12 268	97.14 161	97.64 279	93.57 179	93.96 301	97.06 291	90.05 308	96.30 254	96.55 280	86.10 307	99.47 196	90.10 309	99.31 195	98.40 254
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ACMH	93.61 9	98.44 25	98.76 13	97.51 127	99.43 39	93.54 180	98.23 46	99.05 67	97.40 80	99.37 23	99.08 51	98.79 6	99.47 196	97.74 51	99.71 74	99.50 62
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		97.69 92	97.79 73	97.40 144	99.06 101	93.52 181	95.96 195	98.97 95	94.55 202	98.82 61	98.76 80	97.31 46	99.29 258	97.20 70	99.44 155	99.38 106

PCF-MVS	89.43 18	92.12 317	90.64 334	96.57 203	97.80 251	93.48 182	89.88 388	98.45 190	74.46 401	96.04 267	95.68 317	90.71 254	99.31 251	73.73 400	99.01 235	96.91 351
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
sd_testset		97.97 52	98.12 41	97.51 127	99.41 42	93.44 183	97.96 62	98.25 215	98.58 28	98.78 64	99.39 16	98.21 14	99.56 168	92.65 252	99.86 31	99.52 58

test_vis1_rt		94.03 277	93.65 277	95.17 269	95.76 362	93.42 184	93.97 300	98.33 208	84.68 370	93.17 348	95.89 313	92.53 223	94.79 399	93.50 237	94.97 379	97.31 339

TAMVS		95.49 210	94.94 226	97.16 159	98.31 188	93.41 185	95.07 252	96.82 299	91.09 292	97.51 175	97.82 191	89.96 266	99.42 210	88.42 333	99.44 155	98.64 232

TransMVSNet (Re)		98.38 28	98.67 18	97.51 127	99.51 30	93.39 186	98.20 51	98.87 113	98.23 40	99.48 16	99.27 30	98.47 11	99.55 173	96.52 89	99.53 125	99.60 37

MM		96.87 145	96.62 157	97.62 119	97.72 268	93.30 187	96.39 157	92.61 363	97.90 52	96.76 227	98.64 92	90.46 257	99.81 36	99.16 9	99.94 8	99.76 17

test_fmvsmvis_n_1920		98.08 45	98.47 26	96.93 178	99.03 107	93.29 188	96.32 165	99.65 9	95.59 159	99.71 4	99.01 54	97.66 33	99.60 158	99.44 2	99.83 43	97.90 307

Baseline_NR-MVSNet		97.72 90	97.79 73	97.50 131	99.56 21	93.29 188	95.44 225	98.86 116	98.20 42	98.37 101	99.24 32	94.69 162	99.55 173	95.98 116	99.79 53	99.65 33

VDDNet		96.98 138	96.84 146	97.41 143	99.40 45	93.26 190	97.94 64	95.31 331	99.26 7	98.39 100	99.18 39	87.85 295	99.62 149	95.13 172	99.09 225	99.35 114

test222					98.17 209	93.24 191	92.74 334	97.61 274	75.17 400	94.65 306	96.69 274	90.96 251			98.66 271	97.66 322

test_f		95.82 198	95.88 199	95.66 246	97.61 281	93.21 192	95.61 219	98.17 229	86.98 345	98.42 96	99.47 11	90.46 257	94.74 400	97.71 52	98.45 287	99.03 176

FC-MVSNet-test		98.16 37	98.37 33	97.56 122	99.49 34	93.10 193	98.35 35	99.21 33	98.43 32	98.89 54	98.83 74	94.30 176	99.81 36	97.87 43	99.91 19	99.77 12

MVP-Stereo		95.69 201	95.28 213	96.92 179	98.15 213	93.03 194	95.64 218	98.20 223	90.39 302	96.63 236	97.73 200	91.63 241	99.10 294	91.84 268	97.31 338	98.63 234
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EIA-MVS		96.04 188	95.77 203	96.85 184	97.80 251	92.98 195	96.12 181	99.16 40	94.65 196	93.77 329	91.69 382	95.68 134	99.67 128	94.18 213	98.85 251	97.91 306

FIs		97.93 65	98.07 45	97.48 135	99.38 48	92.95 196	98.03 61	99.11 50	98.04 48	98.62 76	98.66 88	93.75 190	99.78 47	97.23 66	99.84 40	99.73 22

Fast-Effi-MVS+		95.49 210	95.07 222	96.75 192	97.67 275	92.82 197	94.22 285	98.60 176	91.61 283	93.42 343	92.90 364	96.73 86	99.70 110	92.60 253	97.89 311	97.74 319

test_fmvs3		97.38 116	97.56 101	96.84 186	98.63 153	92.81 198	97.60 88	99.61 13	90.87 294	98.76 69	99.66 3	94.03 182	97.90 378	99.24 6	99.68 82	99.81 8

KD-MVS_self_test		97.86 76	98.07 45	97.25 155	99.22 68	92.81 198	97.55 93	98.94 99	97.10 90	98.85 57	98.88 71	95.03 154	99.67 128	97.39 64	99.65 87	99.26 132

PMMVS		92.39 310	91.08 325	96.30 218	93.12 399	92.81 198	90.58 379	95.96 315	79.17 393	91.85 370	92.27 374	90.29 264	98.66 340	89.85 313	96.68 354	97.43 334

dmvs_re		92.08 319	91.27 322	94.51 304	97.16 312	92.79 201	95.65 215	92.64 362	94.11 215	92.74 357	90.98 389	83.41 328	94.44 402	80.72 386	94.07 386	96.29 370

pmmvs4		94.82 242	94.19 266	96.70 195	97.42 297	92.75 202	92.09 353	96.76 301	86.80 348	95.73 281	97.22 239	89.28 278	98.89 315	93.28 243	99.14 216	98.46 252

fmvsm_l_conf0.5_n		97.68 94	97.81 71	97.27 152	98.92 118	92.71 203	95.89 201	99.41 24	93.36 236	99.00 46	98.44 112	96.46 102	99.65 136	99.09 11	99.76 58	99.45 85

DPM-MVS		93.68 286	92.77 299	96.42 211	97.91 234	92.54 204	91.17 370	97.47 278	84.99 368	93.08 350	94.74 337	89.90 267	99.00 304	87.54 345	98.09 302	97.72 320

CLD-MVS		95.47 213	95.07 222	96.69 196	98.27 194	92.53 205	91.36 363	98.67 166	91.22 291	95.78 278	94.12 349	95.65 136	98.98 308	90.81 289	99.72 71	98.57 239
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_s_conf0.1_n_a		97.80 83	98.01 52	97.18 158	99.17 81	92.51 206	96.57 150	99.15 44	93.68 228	98.89 54	99.30 28	96.42 104	99.37 234	99.03 13	99.83 43	99.66 30

fmvsm_s_conf0.5_n_a		97.65 95	97.83 69	97.13 162	98.80 129	92.51 206	96.25 171	99.06 63	93.67 229	98.64 74	99.00 55	96.23 114	99.36 237	98.99 15	99.80 51	99.53 56

HQP5-MVS						92.47 208

HQP-MVS		95.17 228	94.58 251	96.92 179	97.85 238	92.47 208	94.26 279	98.43 193	93.18 246	92.86 354	95.08 329	90.33 260	99.23 272	90.51 302	98.74 262	99.05 175

SixPastTwentyTwo		97.49 108	97.57 100	97.26 154	99.56 21	92.33 210	98.28 42	96.97 294	98.30 38	99.45 18	99.35 23	88.43 286	99.89 18	98.01 39	99.76 58	99.54 53

MVS_0304		96.62 164	96.40 174	97.28 151	97.91 234	92.30 211	96.47 155	89.74 390	97.52 71	95.38 290	98.63 93	92.76 210	99.81 36	99.28 4	99.93 11	99.75 19

fmvsm_l_conf0.5_n_a		97.60 100	97.76 78	97.11 163	98.92 118	92.28 212	95.83 204	99.32 25	93.22 242	98.91 53	98.49 105	96.31 109	99.64 140	99.07 12	99.76 58	99.40 100

EPNet		93.72 284	92.62 303	97.03 173	87.61 411	92.25 213	96.27 167	91.28 375	96.74 99	87.65 397	97.39 226	85.00 316	99.64 140	92.14 261	99.48 146	99.20 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpnnormal		97.72 90	97.97 55	96.94 177	99.26 59	92.23 214	97.83 72	98.45 190	98.25 39	99.13 38	98.66 88	96.65 88	99.69 117	93.92 225	99.62 92	98.91 197

SDMVSNet		97.97 52	98.26 39	97.11 163	99.41 42	92.21 215	96.92 128	98.60 176	98.58 28	98.78 64	99.39 16	97.80 25	99.62 149	94.98 182	99.86 31	99.52 58

XXY-MVS		97.54 105	97.70 81	97.07 169	99.46 36	92.21 215	97.22 112	99.00 86	94.93 189	98.58 81	98.92 65	97.31 46	99.41 219	94.44 201	99.43 163	99.59 38

ab-mvs		96.59 165	96.59 160	96.60 199	98.64 149	92.21 215	98.35 35	97.67 265	94.45 203	96.99 212	98.79 75	94.96 158	99.49 191	90.39 305	99.07 228	98.08 287

WR-MVS		96.90 143	96.81 148	97.16 159	98.56 163	92.20 218	94.33 278	98.12 238	97.34 83	98.20 122	97.33 233	92.81 208	99.75 67	94.79 188	99.81 48	99.54 53

Effi-MVS+		96.19 182	96.01 189	96.71 194	97.43 296	92.19 219	96.12 181	99.10 52	95.45 165	93.33 345	94.71 338	97.23 53	99.56 168	93.21 246	97.54 328	98.37 258

mvsany_test1		93.47 293	93.03 289	94.79 291	94.05 392	92.12 220	90.82 376	90.01 389	85.02 367	97.26 188	98.28 133	93.57 193	97.03 388	92.51 256	95.75 373	95.23 384

原ACMM1				96.58 201	98.16 211	92.12 220		98.15 235	85.90 356	93.49 339	96.43 287	92.47 225	99.38 228	87.66 342	98.62 275	98.23 276

lessismore_v0				97.05 170	99.36 50	92.12 220		84.07 403		98.77 68	98.98 58	85.36 314	99.74 76	97.34 65	99.37 174	99.30 120

casdiffmvs_mvg		97.83 78	98.11 42	97.00 175	98.57 161	92.10 223	95.97 193	99.18 38	97.67 66	99.00 46	98.48 109	97.64 34	99.50 186	96.96 79	99.54 121	99.40 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet-Vis-set		97.32 122	97.39 112	97.11 163	97.36 300	92.08 224	95.34 236	97.65 269	97.74 57	98.29 116	98.11 157	95.05 152	99.68 122	97.50 60	99.50 139	99.56 50

VNet		96.84 146	96.83 147	96.88 182	98.06 220	92.02 225	96.35 163	97.57 275	97.70 62	97.88 159	97.80 193	92.40 226	99.54 176	94.73 193	98.96 237	99.08 169

EI-MVSNet-UG-set		97.32 122	97.40 111	97.09 167	97.34 303	92.01 226	95.33 237	97.65 269	97.74 57	98.30 115	98.14 151	95.04 153	99.69 117	97.55 58	99.52 130	99.58 39

OpenMVS	94.22 8	95.48 212	95.20 215	96.32 216	97.16 312	91.96 227	97.74 80	98.84 123	87.26 340	94.36 313	98.01 172	93.95 185	99.67 128	90.70 297	98.75 261	97.35 338

FMVSNet2		96.72 157	96.67 156	96.87 183	97.96 230	91.88 228	97.15 115	98.06 246	95.59 159	98.50 87	98.62 94	89.51 275	99.65 136	94.99 181	99.60 101	99.07 171

MSDG		95.33 219	95.13 219	95.94 235	97.40 298	91.85 229	91.02 374	98.37 203	95.30 172	96.31 253	95.99 307	94.51 171	98.38 363	89.59 316	97.65 325	97.60 327

QAPM		95.88 195	95.57 210	96.80 188	97.90 236	91.84 230	98.18 53	98.73 151	88.41 329	96.42 246	98.13 153	94.73 160	99.75 67	88.72 328	98.94 240	98.81 212

HyFIR lowres test		93.72 284	92.65 301	96.91 181	98.93 116	91.81 231	91.23 369	98.52 184	82.69 378	96.46 245	96.52 284	80.38 343	99.90 14	90.36 306	98.79 257	99.03 176

test20.03		96.58 167	96.61 159	96.48 208	98.49 174	91.72 232	95.68 212	97.69 264	96.81 97	98.27 117	97.92 182	94.18 179	98.71 332	90.78 291	99.66 86	99.00 180

ambc				96.56 204	98.23 199	91.68 233	97.88 68	98.13 237		98.42 96	98.56 99	94.22 178	99.04 300	94.05 220	99.35 182	98.95 187

K. test v3		96.44 173	96.28 179	96.95 176	99.41 42	91.53 234	97.65 85	90.31 385	98.89 20	98.93 50	99.36 21	84.57 320	99.92 5	97.81 46	99.56 111	99.39 104

UnsupCasMVSNet_eth		95.91 194	95.73 204	96.44 209	98.48 176	91.52 235	95.31 239	98.45 190	95.76 150	97.48 179	97.54 212	89.53 274	98.69 335	94.43 202	94.61 383	99.13 156

LFMVS		95.32 220	94.88 232	96.62 198	98.03 221	91.47 236	97.65 85	90.72 381	99.11 9	97.89 158	98.31 124	79.20 346	99.48 194	93.91 226	99.12 221	98.93 193

fmvsm_s_conf0.5_n		97.62 98	97.89 62	96.80 188	98.79 131	91.44 237	96.14 180	99.06 63	94.19 211	98.82 61	98.98 58	96.22 115	99.38 228	98.98 16	99.86 31	99.58 39

fmvsm_s_conf0.1_n		97.73 88	98.02 51	96.85 184	99.09 97	91.43 238	96.37 161	99.11 50	94.19 211	99.01 44	99.25 31	96.30 110	99.38 228	99.00 14	99.88 27	99.73 22

test_fmvs2		96.38 176	96.45 171	96.16 224	97.85 238	91.30 239	96.81 134	99.45 19	89.24 317	98.49 88	99.38 18	88.68 282	97.62 383	98.83 18	99.32 192	99.57 46

PAPM_NR		94.61 255	94.17 267	95.96 231	98.36 186	91.23 240	95.93 198	97.95 248	92.98 255	93.42 343	94.43 346	90.53 255	98.38 363	87.60 343	96.29 362	98.27 273

OpenMVS_ROB	91.80 14	93.64 289	93.05 287	95.42 259	97.31 307	91.21 241	95.08 251	96.68 306	81.56 382	96.88 221	96.41 288	90.44 259	99.25 266	85.39 365	97.67 323	95.80 376

V42		97.04 132	97.16 127	96.68 197	98.59 159	91.05 242	96.33 164	98.36 204	94.60 198	97.99 147	98.30 128	93.32 197	99.62 149	97.40 63	99.53 125	99.38 106

casdiffmvs		97.50 107	97.81 71	96.56 204	98.51 170	91.04 243	95.83 204	99.09 57	97.23 87	98.33 110	98.30 128	97.03 63	99.37 234	96.58 88	99.38 173	99.28 127
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
JIA-IIPM		91.79 323	90.69 333	95.11 271	93.80 394	90.98 244	94.16 288	91.78 370	96.38 114	90.30 382	99.30 28	72.02 381	98.90 314	88.28 335	90.17 396	95.45 382

114514_t		93.96 278	93.22 286	96.19 222	99.06 101	90.97 245	95.99 191	98.94 99	73.88 402	93.43 342	96.93 257	92.38 227	99.37 234	89.09 323	99.28 199	98.25 275

1112_ss		94.12 272	93.42 281	96.23 219	98.59 159	90.85 246	94.24 283	98.85 120	85.49 359	92.97 352	94.94 333	86.01 308	99.64 140	91.78 270	97.92 308	98.20 279

CANet		95.86 196	95.65 207	96.49 207	96.41 334	90.82 247	94.36 277	98.41 197	94.94 187	92.62 363	96.73 272	92.68 213	99.71 102	95.12 173	99.60 101	98.94 189

Patchmtry		95.03 235	94.59 250	96.33 215	94.83 380	90.82 247	96.38 160	97.20 283	96.59 104	97.49 177	98.57 97	77.67 353	99.38 228	92.95 251	99.62 92	98.80 213

FMVSNet5		93.39 295	92.35 305	96.50 206	95.83 357	90.81 249	97.31 106	98.27 213	92.74 263	96.27 255	98.28 133	62.23 397	99.67 128	90.86 287	99.36 177	99.03 176

baseline		97.44 112	97.78 77	96.43 210	98.52 168	90.75 250	96.84 131	99.03 75	96.51 109	97.86 163	98.02 170	96.67 87	99.36 237	97.09 74	99.47 148	99.19 145

PVSNet_Blended_VisFu		95.95 192	95.80 201	96.42 211	99.28 57	90.62 251	95.31 239	99.08 59	88.40 330	96.97 215	98.17 150	92.11 231	99.78 47	93.64 234	99.21 207	98.86 208

testdata				95.70 245	98.16 211	90.58 252		97.72 263	80.38 388	95.62 283	97.02 251	92.06 234	98.98 308	89.06 325	98.52 281	97.54 330

VPNet		97.26 124	97.49 109	96.59 200	99.47 35	90.58 252	96.27 167	98.53 183	97.77 54	98.46 93	98.41 114	94.59 167	99.68 122	94.61 196	99.29 198	99.52 58

MSLP-MVS++		96.42 175	96.71 153	95.57 249	97.82 246	90.56 254	95.71 208	98.84 123	94.72 193	96.71 229	97.39 226	94.91 159	98.10 376	95.28 158	99.02 233	98.05 296

UnsupCasMVSNet_bld		94.72 248	94.26 262	96.08 227	98.62 155	90.54 255	93.38 319	98.05 247	90.30 303	97.02 210	96.80 268	89.54 272	99.16 282	88.44 332	96.18 364	98.56 240

FMVSNet3		95.26 223	94.94 226	96.22 221	96.53 331	90.06 256	95.99 191	97.66 267	94.11 215	97.99 147	97.91 183	80.22 344	99.63 144	94.60 197	99.44 155	98.96 186

CHOSEN 1792x2688		94.10 273	93.41 282	96.18 223	99.16 82	90.04 257	92.15 350	98.68 163	79.90 390	96.22 258	97.83 188	87.92 294	99.42 210	89.18 322	99.65 87	99.08 169

DELS-MVS		96.17 183	96.23 180	95.99 229	97.55 286	90.04 257	92.38 348	98.52 184	94.13 213	96.55 242	97.06 248	94.99 156	99.58 161	95.62 136	99.28 199	98.37 258
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
sss		94.22 267	93.72 276	95.74 242	97.71 269	89.95 259	93.84 304	96.98 293	88.38 331	93.75 330	95.74 315	87.94 290	98.89 315	91.02 283	98.10 301	98.37 258

test_vis1_n		95.67 203	95.89 198	95.03 276	98.18 206	89.89 260	96.94 127	99.28 29	88.25 333	98.20 122	98.92 65	86.69 305	97.19 386	97.70 54	98.82 255	98.00 301

CL-MVSNet_self_test		95.04 233	94.79 239	95.82 239	97.51 288	89.79 261	91.14 371	96.82 299	93.05 252	96.72 228	96.40 290	90.82 252	99.16 282	91.95 264	98.66 271	98.50 248

CANet_DTU		94.65 253	94.21 265	95.96 231	95.90 352	89.68 262	93.92 302	97.83 258	93.19 245	90.12 384	95.64 319	88.52 284	99.57 167	93.27 244	99.47 148	98.62 235

v10		97.55 104	97.97 55	96.31 217	98.60 157	89.64 263	97.44 101	99.02 77	96.60 103	98.72 72	99.16 43	93.48 195	99.72 87	98.76 21	99.92 16	99.58 39

ANet_high		98.31 31	98.94 6	96.41 213	99.33 53	89.64 263	97.92 66	99.56 16	99.27 6	99.66 9	99.50 9	97.67 31	99.83 32	97.55 58	99.98 2	99.77 12

test_yl		94.40 262	94.00 271	95.59 247	96.95 319	89.52 265	94.75 267	95.55 326	96.18 126	96.79 222	96.14 302	81.09 339	99.18 277	90.75 292	97.77 313	98.07 289

DCV-MVSNet		94.40 262	94.00 271	95.59 247	96.95 319	89.52 265	94.75 267	95.55 326	96.18 126	96.79 222	96.14 302	81.09 339	99.18 277	90.75 292	97.77 313	98.07 289

v8		97.60 100	98.06 47	96.23 219	98.71 142	89.44 267	97.43 103	98.82 137	97.29 86	98.74 70	99.10 48	93.86 186	99.68 122	98.61 27	99.94 8	99.56 50

Anonymous20231206		95.27 222	95.06 224	95.88 237	98.72 139	89.37 268	95.70 209	97.85 254	88.00 336	96.98 214	97.62 207	91.95 236	99.34 244	89.21 321	99.53 125	98.94 189

v1192		96.83 149	97.06 133	96.15 225	98.28 192	89.29 269	95.36 233	98.77 144	93.73 224	98.11 133	98.34 121	93.02 206	99.67 128	98.35 32	99.58 105	99.50 62

v1144		96.84 146	97.08 131	96.13 226	98.42 182	89.28 270	95.41 229	98.67 166	94.21 209	97.97 151	98.31 124	93.06 202	99.65 136	98.06 38	99.62 92	99.45 85

Vis-MVSNet (Re-imp)		95.11 230	94.85 233	95.87 238	99.12 93	89.17 271	97.54 98	94.92 336	96.50 110	96.58 238	97.27 236	83.64 326	99.48 194	88.42 333	99.67 84	98.97 185

new_pmnet		92.34 312	91.69 316	94.32 311	96.23 339	89.16 272	92.27 349	92.88 357	84.39 375	95.29 291	96.35 293	85.66 311	96.74 395	84.53 372	97.56 327	97.05 343

ET-MVSNet_ETH3D		91.12 330	89.67 342	95.47 256	96.41 334	89.15 273	91.54 361	90.23 386	89.07 319	86.78 401	92.84 366	69.39 389	99.44 206	94.16 214	96.61 355	97.82 313

iter_conf05_11		93.77 281	93.29 283	95.24 264	96.54 328	89.14 274	91.55 360	95.02 334	90.16 307	93.21 347	93.94 351	87.37 299	99.56 168	92.24 258	99.56 111	97.03 345

test_fmvs1_n		95.21 224	95.28 213	94.99 279	98.15 213	89.13 275	96.81 134	99.43 21	86.97 346	97.21 191	98.92 65	83.00 330	97.13 387	98.09 36	98.94 240	98.72 224

bld_raw_dy_0_64		95.16 229	95.16 218	95.15 270	96.54 328	89.06 276	96.63 149	99.54 17	89.68 313	98.72 72	94.50 344	88.64 283	99.38 228	92.24 258	99.93 11	97.03 345

v144192		96.69 160	96.90 145	96.03 228	98.25 196	88.92 277	95.49 223	98.77 144	93.05 252	98.09 136	98.29 132	92.51 224	99.70 110	98.11 35	99.56 111	99.47 79

Patchmatch-RL test		94.66 252	94.49 254	95.19 267	98.54 166	88.91 278	92.57 338	98.74 150	91.46 286	98.32 111	97.75 197	77.31 358	98.81 322	96.06 107	99.61 98	97.85 311

HY-MVS	91.43 15	92.58 308	91.81 313	94.90 284	96.49 332	88.87 279	97.31 106	94.62 338	85.92 355	90.50 379	96.84 263	85.05 315	99.40 221	83.77 377	95.78 371	96.43 368

Test_1112_low_res		93.53 292	92.86 293	95.54 253	98.60 157	88.86 280	92.75 332	98.69 161	82.66 379	92.65 360	96.92 259	84.75 318	99.56 168	90.94 285	97.76 315	98.19 280

PAPR		92.22 314	91.27 322	95.07 274	95.73 364	88.81 281	91.97 354	97.87 253	85.80 357	90.91 375	92.73 369	91.16 246	98.33 367	79.48 389	95.76 372	98.08 287

v1921920		96.72 157	96.96 140	95.99 229	98.21 200	88.79 282	95.42 227	98.79 139	93.22 242	98.19 126	98.26 138	92.68 213	99.70 110	98.34 33	99.55 118	99.49 70

v2v482		96.78 153	97.06 133	95.95 233	98.57 161	88.77 283	95.36 233	98.26 214	95.18 177	97.85 164	98.23 142	92.58 217	99.63 144	97.80 47	99.69 78	99.45 85

MDA-MVSNet-bldmvs		95.69 201	95.67 205	95.74 242	98.48 176	88.76 284	92.84 329	97.25 281	96.00 136	97.59 171	97.95 178	91.38 243	99.46 199	93.16 247	96.35 360	98.99 183

v1240		96.74 154	97.02 136	95.91 236	98.18 206	88.52 285	95.39 231	98.88 111	93.15 250	98.46 93	98.40 117	92.80 209	99.71 102	98.45 31	99.49 142	99.49 70

xiu_mvs_v1_base_debu		95.62 205	95.96 193	94.60 298	98.01 224	88.42 286	93.99 297	98.21 220	92.98 255	95.91 271	94.53 341	96.39 105	99.72 87	95.43 152	98.19 297	95.64 378

xiu_mvs_v1_base		95.62 205	95.96 193	94.60 298	98.01 224	88.42 286	93.99 297	98.21 220	92.98 255	95.91 271	94.53 341	96.39 105	99.72 87	95.43 152	98.19 297	95.64 378

xiu_mvs_v1_base_debi		95.62 205	95.96 193	94.60 298	98.01 224	88.42 286	93.99 297	98.21 220	92.98 255	95.91 271	94.53 341	96.39 105	99.72 87	95.43 152	98.19 297	95.64 378

pmmvs5		94.63 254	94.34 261	95.50 254	97.63 280	88.34 289	94.02 295	97.13 287	87.15 342	95.22 293	97.15 242	87.50 296	99.27 263	93.99 222	99.26 202	98.88 205

FE-MVS		92.95 303	92.22 307	95.11 271	97.21 310	88.33 290	98.54 23	93.66 349	89.91 310	96.21 259	98.14 151	70.33 387	99.50 186	87.79 339	98.24 296	97.51 331

thisisatest0530		92.71 307	91.76 315	95.56 251	98.42 182	88.23 291	96.03 187	87.35 397	94.04 218	96.56 240	95.47 324	64.03 395	99.77 56	94.78 190	99.11 222	98.68 231

MIMVSNet		93.42 294	92.86 293	95.10 273	98.17 209	88.19 292	98.13 55	93.69 346	92.07 274	95.04 299	98.21 146	80.95 341	99.03 303	81.42 384	98.06 303	98.07 289

Anonymous20240521		97.07 131	97.51 106	95.76 241	99.35 51	88.18 293	97.78 74	98.40 199	97.11 89	98.34 107	99.04 53	89.58 271	99.79 44	98.09 36	99.93 11	99.30 120

CR-MVSNet		93.29 298	92.79 296	94.78 292	95.44 369	88.15 294	96.18 175	97.20 283	84.94 369	94.10 318	98.57 97	77.67 353	99.39 225	95.17 165	95.81 368	96.81 358

RPMNet		94.68 251	94.60 248	94.90 284	95.44 369	88.15 294	96.18 175	98.86 116	97.43 74	94.10 318	98.49 105	79.40 345	99.76 61	95.69 130	95.81 368	96.81 358

EI-MVSNet		96.63 163	96.93 141	95.74 242	97.26 308	88.13 296	95.29 241	97.65 269	96.99 91	97.94 154	98.19 147	92.55 219	99.58 161	96.91 80	99.56 111	99.50 62

IterMVS-LS		96.92 141	97.29 118	95.79 240	98.51 170	88.13 296	95.10 248	98.66 168	96.99 91	98.46 93	98.68 87	92.55 219	99.74 76	96.91 80	99.79 53	99.50 62
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FA-MVS(test-final)		94.91 238	94.89 231	94.99 279	97.51 288	88.11 298	98.27 44	95.20 332	92.40 272	96.68 230	98.60 95	83.44 327	99.28 260	93.34 240	98.53 280	97.59 328

diffmvs		96.04 188	96.23 180	95.46 257	97.35 301	88.03 299	93.42 317	99.08 59	94.09 217	96.66 233	96.93 257	93.85 187	99.29 258	96.01 114	98.67 269	99.06 173
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvs1		94.51 260	94.60 248	94.26 314	95.91 351	87.92 300	95.35 235	99.02 77	86.56 350	96.79 222	98.52 102	82.64 332	97.00 390	97.87 43	98.71 266	97.88 309

TinyColmap		96.00 191	96.34 177	94.96 281	97.90 236	87.91 301	94.13 292	98.49 187	94.41 204	98.16 128	97.76 194	96.29 112	98.68 338	90.52 301	99.42 166	98.30 269

tttt0517		93.31 297	92.56 304	95.57 249	98.71 142	87.86 302	97.44 101	87.17 398	95.79 149	97.47 181	96.84 263	64.12 394	99.81 36	96.20 103	99.32 192	99.02 179

WTY-MVS		93.55 291	93.00 291	95.19 267	97.81 247	87.86 302	93.89 303	96.00 313	89.02 320	94.07 320	95.44 326	86.27 306	99.33 246	87.69 341	96.82 348	98.39 256

jason		94.39 264	94.04 270	95.41 261	98.29 190	87.85 304	92.74 334	96.75 302	85.38 363	95.29 291	96.15 300	88.21 289	99.65 136	94.24 211	99.34 185	98.74 221
jason: jason.
MVSFormer		96.14 184	96.36 176	95.49 255	97.68 271	87.81 305	98.67 15	99.02 77	96.50 110	94.48 311	96.15 300	86.90 302	99.92 5	98.73 22	99.13 218	98.74 221

lupinMVS		93.77 281	93.28 284	95.24 264	97.68 271	87.81 305	92.12 351	96.05 311	84.52 372	94.48 311	95.06 331	86.90 302	99.63 144	93.62 235	99.13 218	98.27 273

D2MVS		95.18 226	95.17 217	95.21 266	97.76 261	87.76 307	94.15 289	97.94 249	89.77 312	96.99 212	97.68 204	87.45 297	99.14 284	95.03 178	99.81 48	98.74 221

testgi		96.07 186	96.50 170	94.80 290	99.26 59	87.69 308	95.96 195	98.58 180	95.08 181	98.02 146	96.25 296	97.92 20	97.60 384	88.68 330	98.74 262	99.11 164

v148		96.58 167	96.97 138	95.42 259	98.63 153	87.57 309	95.09 249	97.90 251	95.91 143	98.24 119	97.96 176	93.42 196	99.39 225	96.04 110	99.52 130	99.29 126

BH-untuned		94.69 249	94.75 240	94.52 303	97.95 233	87.53 310	94.07 294	97.01 292	93.99 219	97.10 200	95.65 318	92.65 215	98.95 313	87.60 343	96.74 351	97.09 342

Patchmatch-test		93.60 290	93.25 285	94.63 296	96.14 347	87.47 311	96.04 186	94.50 340	93.57 230	96.47 244	96.97 254	76.50 361	98.61 344	90.67 298	98.41 290	97.81 315

iter_conf05		93.65 288	93.05 287	95.46 257	96.13 348	87.45 312	95.95 197	98.22 219	92.66 265	97.04 208	97.89 184	63.52 396	99.72 87	96.19 104	99.82 47	99.21 140

BH-RMVSNet		94.56 257	94.44 259	94.91 282	97.57 283	87.44 313	93.78 308	96.26 309	93.69 227	96.41 247	96.50 285	92.10 232	99.00 304	85.96 357	97.71 319	98.31 267

PVSNet_BlendedMVS		95.02 236	94.93 228	95.27 263	97.79 256	87.40 314	94.14 291	98.68 163	88.94 322	94.51 309	98.01 172	93.04 203	99.30 254	89.77 314	99.49 142	99.11 164

PVSNet_Blended		93.96 278	93.65 277	94.91 282	97.79 256	87.40 314	91.43 362	98.68 163	84.50 373	94.51 309	94.48 345	93.04 203	99.30 254	89.77 314	98.61 276	98.02 299

PatchT		93.75 283	93.57 279	94.29 313	95.05 377	87.32 316	96.05 185	92.98 356	97.54 70	94.25 314	98.72 82	75.79 366	99.24 270	95.92 119	95.81 368	96.32 369

GA-MVS		92.83 305	92.15 309	94.87 286	96.97 318	87.27 317	90.03 383	96.12 310	91.83 280	94.05 321	94.57 339	76.01 365	98.97 312	92.46 257	97.34 337	98.36 263

baseline1		93.14 301	92.64 302	94.62 297	97.34 303	87.20 318	96.67 148	93.02 355	94.71 194	96.51 243	95.83 314	81.64 334	98.60 346	90.00 311	88.06 400	98.07 289

patch_mono-2		96.59 165	96.93 141	95.55 252	98.88 122	87.12 319	94.47 275	99.30 27	94.12 214	96.65 235	98.41 114	94.98 157	99.87 22	95.81 127	99.78 56	99.66 30

MS-PatchMatch		94.83 241	94.91 230	94.57 301	96.81 324	87.10 320	94.23 284	97.34 280	88.74 325	97.14 196	97.11 245	91.94 237	98.23 372	92.99 249	97.92 308	98.37 258

cl____		94.73 244	94.64 244	95.01 277	95.85 356	87.00 321	91.33 365	98.08 241	93.34 237	97.10 200	97.33 233	84.01 325	99.30 254	95.14 170	99.56 111	98.71 227

DIV-MVS_self_test		94.73 244	94.64 244	95.01 277	95.86 355	87.00 321	91.33 365	98.08 241	93.34 237	97.10 200	97.34 232	84.02 324	99.31 251	95.15 169	99.55 118	98.72 224

MVS		90.02 339	89.20 346	92.47 357	94.71 381	86.90 323	95.86 202	96.74 303	64.72 404	90.62 376	92.77 367	92.54 221	98.39 362	79.30 390	95.56 375	92.12 397

test0.0.03 1		90.11 338	89.21 345	92.83 348	93.89 393	86.87 324	91.74 358	88.74 394	92.02 275	94.71 305	91.14 387	73.92 372	94.48 401	83.75 378	92.94 389	97.16 341

test_cas_vis1_n_1920		95.34 218	95.67 205	94.35 310	98.21 200	86.83 325	95.61 219	99.26 30	90.45 301	98.17 127	98.96 61	84.43 321	98.31 368	96.74 83	99.17 213	97.90 307

TR-MVS		92.54 309	92.20 308	93.57 327	96.49 332	86.66 326	93.51 315	94.73 337	89.96 309	94.95 300	93.87 352	90.24 265	98.61 344	81.18 385	94.88 380	95.45 382

MVS_Test		96.27 179	96.79 151	94.73 294	96.94 321	86.63 327	96.18 175	98.33 208	94.94 187	96.07 265	98.28 133	95.25 148	99.26 264	97.21 68	97.90 310	98.30 269

MVSTER		94.21 269	93.93 274	95.05 275	95.83 357	86.46 328	95.18 246	97.65 269	92.41 271	97.94 154	98.00 174	72.39 380	99.58 161	96.36 96	99.56 111	99.12 161

miper_lstm_enhance		94.81 243	94.80 238	94.85 287	96.16 343	86.45 329	91.14 371	98.20 223	93.49 232	97.03 209	97.37 230	84.97 317	99.26 264	95.28 158	99.56 111	98.83 210

c3_l		95.20 225	95.32 212	94.83 289	96.19 341	86.43 330	91.83 357	98.35 207	93.47 233	97.36 185	97.26 237	88.69 281	99.28 260	95.41 155	99.36 177	98.78 215

USDC		94.56 257	94.57 253	94.55 302	97.78 259	86.43 330	92.75 332	98.65 173	85.96 354	96.91 219	97.93 181	90.82 252	98.74 328	90.71 296	99.59 103	98.47 250

miper_ehance_all_eth		94.69 249	94.70 241	94.64 295	95.77 361	86.22 332	91.32 367	98.24 217	91.67 281	97.05 207	96.65 276	88.39 287	99.22 274	94.88 183	98.34 291	98.49 249

eth_miper_zixun_eth		94.89 239	94.93 228	94.75 293	95.99 350	86.12 333	91.35 364	98.49 187	93.40 234	97.12 198	97.25 238	86.87 304	99.35 241	95.08 175	98.82 255	98.78 215

cl22		93.25 299	92.84 295	94.46 306	94.30 386	86.00 334	91.09 373	96.64 307	90.74 295	95.79 276	96.31 294	78.24 350	98.77 325	94.15 215	98.34 291	98.62 235

MG-MVS		94.08 275	94.00 271	94.32 311	97.09 315	85.89 335	93.19 325	95.96 315	92.52 267	94.93 302	97.51 215	89.54 272	98.77 325	87.52 347	97.71 319	98.31 267

ADS-MVSNet2		91.47 328	90.51 336	94.36 309	95.51 367	85.63 336	95.05 254	95.70 319	83.46 376	92.69 358	96.84 263	79.15 347	99.41 219	85.66 361	90.52 394	98.04 297

cascas		91.89 322	91.35 319	93.51 328	94.27 387	85.60 337	88.86 393	98.61 175	79.32 392	92.16 367	91.44 384	89.22 279	98.12 375	90.80 290	97.47 333	96.82 357

IterMVS-SCA-FT		95.86 196	96.19 182	94.85 287	97.68 271	85.53 338	92.42 345	97.63 273	96.99 91	98.36 104	98.54 101	87.94 290	99.75 67	97.07 76	99.08 226	99.27 131

thisisatest0515		90.43 336	89.18 348	94.17 317	97.07 316	85.44 339	89.75 389	87.58 396	88.28 332	93.69 333	91.72 381	65.27 393	99.58 161	90.59 299	98.67 269	97.50 333

pmmvs3		90.00 340	88.90 350	93.32 330	94.20 390	85.34 340	91.25 368	92.56 364	78.59 394	93.82 326	95.17 328	67.36 392	98.69 335	89.08 324	98.03 304	95.92 373

BH-w/o		92.14 316	91.94 310	92.73 351	97.13 314	85.30 341	92.46 342	95.64 321	89.33 316	94.21 315	92.74 368	89.60 270	98.24 371	81.68 383	94.66 382	94.66 387

miper_enhance_ethall		93.14 301	92.78 298	94.20 315	93.65 395	85.29 342	89.97 384	97.85 254	85.05 365	96.15 264	94.56 340	85.74 310	99.14 284	93.74 230	98.34 291	98.17 283

DeepMVS_CX				77.17 388	90.94 407	85.28 343		74.08 411	52.51 405	80.87 406	88.03 399	75.25 368	70.63 408	59.23 408	84.94 403	75.62 403

MVE	73.61 22	86.48 370	85.92 369	88.18 384	96.23 339	85.28 343	81.78 402	75.79 408	86.01 353	82.53 404	91.88 379	92.74 211	87.47 407	71.42 404	94.86 381	91.78 398
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
1314		92.38 311	92.30 306	92.64 353	95.42 371	85.15 345	95.86 202	96.97 294	85.40 362	90.62 376	93.06 362	91.12 247	97.80 381	86.74 354	95.49 376	94.97 386

MDA-MVSNet_test_wron		94.73 244	94.83 236	94.42 307	97.48 290	85.15 345	90.28 382	95.87 317	92.52 267	97.48 179	97.76 194	91.92 238	99.17 281	93.32 241	96.80 350	98.94 189

YYNet1		94.73 244	94.84 234	94.41 308	97.47 294	85.09 347	90.29 381	95.85 318	92.52 267	97.53 173	97.76 194	91.97 235	99.18 277	93.31 242	96.86 345	98.95 187

PAPM		87.64 363	85.84 370	93.04 339	96.54 328	84.99 348	88.42 394	95.57 325	79.52 391	83.82 402	93.05 363	80.57 342	98.41 360	62.29 406	92.79 390	95.71 377

PS-MVSNAJ		94.10 273	94.47 256	93.00 342	97.35 301	84.88 349	91.86 356	97.84 256	91.96 277	94.17 316	92.50 373	95.82 126	99.71 102	91.27 277	97.48 331	94.40 389

test_vis1_n_1920		95.77 199	96.41 173	93.85 320	98.55 164	84.86 350	95.91 200	99.71 4	92.72 264	97.67 169	98.90 69	87.44 298	98.73 329	97.96 40	98.85 251	97.96 303

xiu_mvs_v2_base		94.22 267	94.63 246	92.99 343	97.32 306	84.84 351	92.12 351	97.84 256	91.96 277	94.17 316	93.43 355	96.07 118	99.71 102	91.27 277	97.48 331	94.42 388

IB-MVS	85.98 20	88.63 356	86.95 366	93.68 325	95.12 376	84.82 352	90.85 375	90.17 387	87.55 339	88.48 394	91.34 385	58.01 398	99.59 159	87.24 351	93.80 388	96.63 364
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
thres600view7		92.03 320	91.43 317	93.82 321	98.19 203	84.61 353	96.27 167	90.39 382	96.81 97	96.37 249	93.11 357	73.44 378	99.49 191	80.32 387	97.95 307	97.36 336

thres100view900		91.76 324	91.26 324	93.26 332	98.21 200	84.50 354	96.39 157	90.39 382	96.87 95	96.33 250	93.08 361	73.44 378	99.42 210	78.85 392	97.74 316	95.85 374

gg-mvs-nofinetune		88.28 359	86.96 365	92.23 361	92.84 402	84.44 355	98.19 52	74.60 409	99.08 10	87.01 400	99.47 11	56.93 400	98.23 372	78.91 391	95.61 374	94.01 391

tfpn200view9		91.55 326	91.00 326	93.21 336	98.02 222	84.35 356	95.70 209	90.79 379	96.26 120	95.90 274	92.13 377	73.62 375	99.42 210	78.85 392	97.74 316	95.85 374

thres400		91.68 325	91.00 326	93.71 324	98.02 222	84.35 356	95.70 209	90.79 379	96.26 120	95.90 274	92.13 377	73.62 375	99.42 210	78.85 392	97.74 316	97.36 336

testing3		89.72 346	88.26 355	94.10 318	97.66 276	84.30 358	94.80 263	88.25 395	94.66 195	95.07 295	92.51 372	41.15 413	99.43 208	91.81 269	98.44 288	98.55 242

GG-mvs-BLEND				90.60 372	91.00 406	84.21 359	98.23 46	72.63 412		82.76 403	84.11 404	56.14 403	96.79 393	72.20 402	92.09 393	90.78 401

dcpmvs_2		97.12 129	97.99 54	94.51 304	99.11 94	84.00 360	97.75 78	99.65 9	97.38 82	99.14 37	98.42 113	95.16 150	99.96 2	95.52 141	99.78 56	99.58 39

thres200		91.00 333	90.42 337	92.77 350	97.47 294	83.98 361	94.01 296	91.18 377	95.12 180	95.44 287	91.21 386	73.93 371	99.31 251	77.76 395	97.63 326	95.01 385

IterMVS		95.42 216	95.83 200	94.20 315	97.52 287	83.78 362	92.41 346	97.47 278	95.49 164	98.06 141	98.49 105	87.94 290	99.58 161	96.02 112	99.02 233	99.23 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DSMNet-mixed		92.19 315	91.83 312	93.25 333	96.18 342	83.68 363	96.27 167	93.68 348	76.97 399	92.54 364	99.18 39	89.20 280	98.55 350	83.88 375	98.60 278	97.51 331

ETVMVS		87.62 364	85.75 371	93.22 335	96.15 346	83.26 364	92.94 328	90.37 384	91.39 287	90.37 380	88.45 398	51.93 410	98.64 341	73.76 399	96.38 359	97.75 318

ECVR-MVS		94.37 265	94.48 255	94.05 319	98.95 112	83.10 365	98.31 39	82.48 406	96.20 123	98.23 120	99.16 43	81.18 338	99.66 134	95.95 117	99.83 43	99.38 106

testing222		87.35 366	85.50 373	92.93 346	95.79 359	82.83 366	92.40 347	90.10 388	92.80 262	88.87 392	89.02 397	48.34 411	98.70 333	75.40 398	96.74 351	97.27 340

baseline2		89.65 348	88.44 354	93.25 333	95.62 365	82.71 367	93.82 305	85.94 401	88.89 323	87.35 399	92.54 371	71.23 383	99.33 246	86.01 356	94.60 384	97.72 320

Syy-MVS		92.09 318	91.80 314	92.93 346	95.19 374	82.65 368	92.46 342	91.35 373	90.67 298	91.76 371	87.61 400	85.64 312	98.50 354	94.73 193	96.84 346	97.65 323

EPNet_dtu		91.39 329	90.75 332	93.31 331	90.48 408	82.61 369	94.80 263	92.88 357	93.39 235	81.74 405	94.90 336	81.36 337	99.11 291	88.28 335	98.87 248	98.21 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EU-MVSNet		94.25 266	94.47 256	93.60 326	98.14 215	82.60 370	97.24 111	92.72 360	85.08 364	98.48 90	98.94 63	82.59 333	98.76 327	97.47 62	99.53 125	99.44 95

ADS-MVSNet		90.95 334	90.26 338	93.04 339	95.51 367	82.37 371	95.05 254	93.41 352	83.46 376	92.69 358	96.84 263	79.15 347	98.70 333	85.66 361	90.52 394	98.04 297

ppachtmachnet_test		94.49 261	94.84 234	93.46 329	96.16 343	82.10 372	90.59 378	97.48 277	90.53 300	97.01 211	97.59 209	91.01 249	99.36 237	93.97 224	99.18 212	98.94 189

KD-MVS_2432*1600		88.93 353	87.74 358	92.49 355	88.04 409	81.99 373	89.63 390	95.62 322	91.35 288	95.06 296	93.11 357	56.58 401	98.63 342	85.19 366	95.07 377	96.85 354

miper_refine_blended		88.93 353	87.74 358	92.49 355	88.04 409	81.99 373	89.63 390	95.62 322	91.35 288	95.06 296	93.11 357	56.58 401	98.63 342	85.19 366	95.07 377	96.85 354

test1111		94.53 259	94.81 237	93.72 323	99.06 101	81.94 375	98.31 39	83.87 404	96.37 115	98.49 88	99.17 42	81.49 335	99.73 82	96.64 84	99.86 31	99.49 70

testing91		89.67 347	88.55 352	93.04 339	95.90 352	81.80 376	92.71 336	93.71 345	93.71 225	90.18 383	90.15 394	57.11 399	99.22 274	87.17 352	96.32 361	98.12 285

mvs_anonymous		95.36 217	96.07 188	93.21 336	96.29 336	81.56 377	94.60 272	97.66 267	93.30 239	96.95 216	98.91 68	93.03 205	99.38 228	96.60 86	97.30 339	98.69 228

testing11		88.93 353	87.63 361	92.80 349	95.87 354	81.49 378	92.48 341	91.54 372	91.62 282	88.27 395	90.24 392	55.12 408	99.11 291	87.30 350	96.28 363	97.81 315

SCA		93.38 296	93.52 280	92.96 344	96.24 337	81.40 379	93.24 323	94.00 344	91.58 285	94.57 307	96.97 254	87.94 290	99.42 210	89.47 318	97.66 324	98.06 293

our_test_3		94.20 271	94.58 251	93.07 338	96.16 343	81.20 380	90.42 380	96.84 297	90.72 296	97.14 196	97.13 243	90.47 256	99.11 291	94.04 221	98.25 295	98.91 197

CHOSEN 280x420		89.98 341	89.19 347	92.37 359	95.60 366	81.13 381	86.22 397	97.09 289	81.44 384	87.44 398	93.15 356	73.99 370	99.47 196	88.69 329	99.07 228	96.52 366

testing99		89.21 351	88.04 357	92.70 352	95.78 360	81.00 382	92.65 337	92.03 366	93.20 244	89.90 387	90.08 396	55.25 405	99.14 284	87.54 345	95.95 367	97.97 302

PMMVS2		93.66 287	94.07 269	92.45 358	97.57 283	80.67 383	86.46 396	96.00 313	93.99 219	97.10 200	97.38 228	89.90 267	97.82 380	88.76 327	99.47 148	98.86 208

WB-MVSnew		91.50 327	91.29 320	92.14 362	94.85 379	80.32 384	93.29 322	88.77 393	88.57 328	94.03 322	92.21 375	92.56 218	98.28 370	80.21 388	97.08 340	97.81 315

new-patchmatchnet		95.67 203	96.58 161	92.94 345	97.48 290	80.21 385	92.96 327	98.19 228	94.83 190	98.82 61	98.79 75	93.31 198	99.51 185	95.83 125	99.04 232	99.12 161

PatchmatchNet		91.98 321	91.87 311	92.30 360	94.60 383	79.71 386	95.12 247	93.59 351	89.52 314	93.61 335	97.02 251	77.94 351	99.18 277	90.84 288	94.57 385	98.01 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WAC-MVS						79.32 387								85.41 364

myMVS_eth3d		87.16 369	85.61 372	91.82 365	95.19 374	79.32 387	92.46 342	91.35 373	90.67 298	91.76 371	87.61 400	41.96 412	98.50 354	82.66 380	96.84 346	97.65 323

EPMVS		89.26 350	88.55 352	91.39 368	92.36 404	79.11 389	95.65 215	79.86 407	88.60 327	93.12 349	96.53 282	70.73 386	98.10 376	90.75 292	89.32 398	96.98 347

SSC-MVS		95.92 193	97.03 135	92.58 354	99.28 57	78.39 390	96.68 146	95.12 333	98.90 19	99.11 39	98.66 88	91.36 244	99.68 122	95.00 179	99.16 214	99.67 28

tpm		91.08 332	90.85 330	91.75 366	95.33 372	78.09 391	95.03 256	91.27 376	88.75 324	93.53 338	97.40 222	71.24 382	99.30 254	91.25 279	93.87 387	97.87 310

PVSNet	86.72 19	91.10 331	90.97 328	91.49 367	97.56 285	78.04 392	87.17 395	94.60 339	84.65 371	92.34 365	92.20 376	87.37 299	98.47 357	85.17 368	97.69 321	97.96 303

CostFormer		89.75 345	89.25 343	91.26 369	94.69 382	78.00 393	95.32 238	91.98 368	81.50 383	90.55 378	96.96 256	71.06 384	98.89 315	88.59 331	92.63 391	96.87 352

E-PMN		89.52 349	89.78 341	88.73 380	93.14 398	77.61 394	83.26 400	92.02 367	94.82 191	93.71 331	93.11 357	75.31 367	96.81 392	85.81 358	96.81 349	91.77 399

dmvs_testset		87.30 367	86.99 364	88.24 383	96.71 325	77.48 395	94.68 269	86.81 400	92.64 266	89.61 388	87.01 402	85.91 309	93.12 403	61.04 407	88.49 399	94.13 390

EMVS		89.06 352	89.22 344	88.61 381	93.00 400	77.34 396	82.91 401	90.92 378	94.64 197	92.63 362	91.81 380	76.30 363	97.02 389	83.83 376	96.90 344	91.48 400

tpm2		88.47 357	87.69 360	90.79 371	94.98 378	77.34 396	95.09 249	91.83 369	77.51 398	89.40 389	96.41 288	67.83 391	98.73 329	83.58 379	92.60 392	96.29 370

WB-MVS		95.50 209	96.62 157	92.11 363	99.21 75	77.26 398	96.12 181	95.40 330	98.62 26	98.84 59	98.26 138	91.08 248	99.50 186	93.37 238	98.70 267	99.58 39

test2506		89.86 344	89.16 349	91.97 364	98.95 112	76.83 399	98.54 23	61.07 413	96.20 123	97.07 206	99.16 43	55.19 407	99.69 117	96.43 93	99.83 43	99.38 106

tpmvs		90.79 335	90.87 329	90.57 373	92.75 403	76.30 400	95.79 206	93.64 350	91.04 293	91.91 369	96.26 295	77.19 359	98.86 319	89.38 320	89.85 397	96.56 365

tpm cat1		88.01 361	87.33 362	90.05 377	94.48 384	76.28 401	94.47 275	94.35 342	73.84 403	89.26 390	95.61 321	73.64 374	98.30 369	84.13 373	86.20 402	95.57 381

CVMVSNet		92.33 313	92.79 296	90.95 370	97.26 308	75.84 402	95.29 241	92.33 365	81.86 380	96.27 255	98.19 147	81.44 336	98.46 358	94.23 212	98.29 294	98.55 242

test-LLR		89.97 342	89.90 340	90.16 374	94.24 388	74.98 403	89.89 385	89.06 391	92.02 275	89.97 385	90.77 390	73.92 372	98.57 347	91.88 266	97.36 335	96.92 349

test-mter		87.92 362	87.17 363	90.16 374	94.24 388	74.98 403	89.89 385	89.06 391	86.44 351	89.97 385	90.77 390	54.96 409	98.57 347	91.88 266	97.36 335	96.92 349

PVSNet_0	81.89 21	84.49 371	83.21 374	88.34 382	95.76 362	74.97 405	83.49 399	92.70 361	78.47 395	87.94 396	86.90 403	83.38 329	96.63 396	73.44 401	66.86 407	93.40 394

UWE-MVS		87.57 365	86.72 367	90.13 376	95.21 373	73.56 406	91.94 355	83.78 405	88.73 326	93.00 351	92.87 365	55.22 406	99.25 266	81.74 382	97.96 306	97.59 328

MDTV_nov1_ep13			91.28 321		94.31 385	73.51 407	94.80 263	93.16 354	86.75 349	93.45 341	97.40 222	76.37 362	98.55 350	88.85 326	96.43 357

TESTMET0.1,1		87.20 368	86.57 368	89.07 379	93.62 396	72.84 408	89.89 385	87.01 399	85.46 361	89.12 391	90.20 393	56.00 404	97.72 382	90.91 286	96.92 342	96.64 362

tpmrst		90.31 337	90.61 335	89.41 378	94.06 391	72.37 409	95.06 253	93.69 346	88.01 335	92.32 366	96.86 261	77.45 355	98.82 320	91.04 282	87.01 401	97.04 344

gm-plane-assit					91.79 405	71.40 410			81.67 381		90.11 395		98.99 306	84.86 370

dp		88.08 360	88.05 356	88.16 385	92.85 401	68.81 411	94.17 287	92.88 357	85.47 360	91.38 374	96.14 302	68.87 390	98.81 322	86.88 353	83.80 404	96.87 352

MVS-HIRNet		88.40 358	90.20 339	82.99 387	97.01 317	60.04 412	93.11 326	85.61 402	84.45 374	88.72 393	99.09 50	84.72 319	98.23 372	82.52 381	96.59 356	90.69 402

MDTV_nov1_ep13_2view						57.28 413	94.89 260		80.59 387	94.02 323		78.66 349		85.50 363		97.82 313

tmp_tt		57.23 374	62.50 377	41.44 390	34.77 413	49.21 414	83.93 398	60.22 414	15.31 406	71.11 407	79.37 405	70.09 388	44.86 409	64.76 405	82.93 405	30.25 405

test_method		66.88 373	66.13 376	69.11 389	62.68 412	25.73 415	49.76 403	96.04 312	14.32 407	64.27 408	91.69 382	73.45 377	88.05 406	76.06 397	66.94 406	93.54 392

test123		12.59 376	15.49 379	3.87 391	6.07 414	2.55 416	90.75 377	2.59 416	2.52 409	5.20 411	13.02 408	4.96 414	1.85 411	5.20 409	9.09 408	7.23 406

testmvs		12.33 377	15.23 380	3.64 392	5.77 415	2.23 417	88.99 392	3.62 415	2.30 410	5.29 410	13.09 407	4.52 415	1.95 410	5.16 410	8.32 409	6.75 407

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

cdsmvs_eth3d_5k		24.22 375	32.30 378	0.00 393	0.00 416	0.00 418	0.00 404	98.10 239	0.00 411	0.00 412	95.06 331	97.54 39	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		7.98 378	10.65 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	95.82 126	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		7.91 379	10.55 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	94.94 333	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

PC_three_1452									87.24 341	98.37 101	97.44 219	97.00 65	96.78 394	92.01 262	99.25 203	99.21 140

eth-test2					0.00 416

eth-test					0.00 416

test_241102_TWO								98.83 129	96.11 128	98.62 76	98.24 140	96.92 73	99.72 87	95.44 149	99.49 142	99.49 70

9.14			96.69 154		98.53 167		96.02 188	98.98 92	93.23 241	97.18 194	97.46 217	96.47 100	99.62 149	92.99 249	99.32 192

test_0728_THIRD									96.62 101	98.40 98	98.28 133	97.10 56	99.71 102	95.70 128	99.62 92	99.58 39

GSMVS																98.06 293

sam_mvs1												77.80 352				98.06 293

sam_mvs												77.38 356

MTGPA								98.73 151

test_post1							94.98 258				10.37 410	76.21 364	99.04 300	89.47 318

test_post											10.87 409	76.83 360	99.07 297

patchmatchnet-post											96.84 263	77.36 357	99.42 210

MTMP							96.55 151	74.60 409

test9_res														91.29 276	98.89 247	99.00 180

agg_prior2														90.34 307	98.90 244	99.10 168

test_prior2							93.33 321		94.21 209	94.02 323	96.25 296	93.64 192		91.90 265	98.96 237

旧先验2							93.35 320		77.95 397	95.77 280			98.67 339	90.74 295

新几何2							93.43 316

无先验							93.20 324	97.91 250	80.78 386				99.40 221	87.71 340		97.94 305

原ACMM2							92.82 330

testdata2													99.46 199	87.84 338

segment_acmp												95.34 145

testdata1							92.77 331		93.78 223

plane_prior5								98.75 148					99.46 199	92.59 254	99.20 208	99.28 127

plane_prior4											96.77 269

plane_prior2							96.50 153		96.36 116

plane_prior1					98.49 174

n2								0.00 417

nn								0.00 417

door-mid								98.17 229

test11								98.08 241

door								97.81 259

HQP-NCC					97.85 238		94.26 279		93.18 246	92.86 354

ACMP_Plane					97.85 238		94.26 279		93.18 246	92.86 354

BP-MVS														90.51 302

HQP4-MVS										92.87 353			99.23 272			99.06 173

HQP3-MVS								98.43 193							98.74 262

HQP2-MVS												90.33 260

ACMMP++_ref															99.52 130

ACMMP++															99.55 118

Test By Simon												94.51 171

High-resolution multi-view benchmark