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 81	99.42 21	97.69 63	98.92 50	98.77 79	97.80 25	99.25 262	96.27 98	99.69 77	98.76 219

APD_test2		98.57 17	98.45 29	98.93 18	99.79 3	98.78 2	97.69 81	99.42 21	97.69 63	98.92 50	98.77 79	97.80 25	99.25 262	96.27 98	99.69 77	98.76 219

Effi-MVS+-dtu		96.81 147	96.09 182	98.99 10	96.90 320	98.69 4	96.42 155	98.09 237	95.86 145	95.15 291	95.54 322	94.26 173	99.81 37	94.06 216	98.51 281	98.47 250

APD_test1		97.95 58	97.68 83	98.75 31	99.60 17	98.60 5	97.21 112	99.08 55	96.57 107	98.07 138	98.38 117	96.22 111	99.14 278	94.71 193	99.31 193	98.52 245

RPSCF		97.87 74	97.51 105	98.95 14	99.15 86	98.43 6	97.56 91	99.06 59	96.19 124	98.48 88	98.70 86	94.72 157	99.24 265	94.37 204	99.33 188	99.17 148

FOURS1					99.59 18	98.20 7	99.03 7	99.25 28	98.96 18	98.87 54

TDRefinement		98.90 5	98.86 8	99.02 6	99.54 26	98.06 8	99.34 4	99.44 19	98.85 21	99.00 46	99.20 35	97.42 40	99.59 159	97.21 67	99.76 59	99.40 100

SR-MVS-dyc-post		98.14 39	97.84 66	99.02 6	98.81 126	98.05 9	97.55 92	98.86 111	97.77 54	98.20 120	98.07 160	96.60 91	99.76 62	95.49 140	99.20 206	99.26 131

RE-MVS-def			97.88 64		98.81 126	98.05 9	97.55 92	98.86 111	97.77 54	98.20 120	98.07 160	96.94 67		95.49 140	99.20 206	99.26 131

SR-MVS		98.00 51	97.66 85	99.01 8	98.77 134	97.93 11	97.38 104	98.83 124	97.32 82	98.06 139	97.85 187	96.65 86	99.77 57	95.00 177	99.11 220	99.32 114

MTAPA		98.14 39	97.84 66	99.06 3	99.44 39	97.90 12	97.25 108	98.73 146	97.69 63	97.90 155	97.96 175	95.81 126	99.82 35	96.13 104	99.61 97	99.45 86

UA-Net		98.88 7	98.76 13	99.22 2	99.11 95	97.89 13	99.47 3	99.32 23	99.08 10	97.87 160	99.67 2	96.47 98	99.92 5	97.88 41	99.98 2	99.85 3

mPP-MVS		97.91 69	97.53 103	99.04 4	99.22 69	97.87 14	97.74 79	98.78 138	96.04 132	97.10 198	97.73 200	96.53 93	99.78 48	95.16 165	99.50 137	99.46 82

CP-MVS		97.92 66	97.56 100	98.99 10	98.99 111	97.82 15	97.93 66	98.96 91	96.11 127	96.89 218	97.45 218	96.85 78	99.78 48	95.19 161	99.63 90	99.38 105

PMVS	89.60 17	96.71 155	96.97 135	95.95 231	99.51 31	97.81 16	97.42 103	97.49 273	97.93 50	95.95 266	98.58 97	96.88 75	96.91 380	89.59 312	99.36 175	93.12 385
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MP-MVS		97.64 96	97.18 123	99.00 9	99.32 56	97.77 17	97.49 98	98.73 146	96.27 118	95.59 281	97.75 197	96.30 106	99.78 48	93.70 231	99.48 144	99.45 86
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MSP-MVS		97.45 110	96.92 140	99.03 5	99.26 60	97.70 18	97.66 83	98.89 100	95.65 154	98.51 83	96.46 286	92.15 224	99.81 37	95.14 168	98.58 277	99.58 40
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 91	98.94 15	99.15 86	97.66 19	97.77 74	98.83 124	97.42 75	96.32 248	97.64 205	96.49 96	99.72 88	95.66 131	99.37 172	99.45 86

X-MVStestdata		92.86 299	90.83 325	98.94 15	99.15 86	97.66 19	97.77 74	98.83 124	97.42 75	96.32 248	36.50 395	96.49 96	99.72 88	95.66 131	99.37 172	99.45 86

PGM-MVS		97.88 73	97.52 104	98.96 13	99.20 78	97.62 21	97.09 119	99.06 59	95.45 164	97.55 170	97.94 178	97.11 53	99.78 48	94.77 189	99.46 149	99.48 77

ACMMP		98.05 48	97.75 78	98.93 18	99.23 66	97.60 22	98.09 57	98.96 91	95.75 151	97.91 154	98.06 165	96.89 73	99.76 62	95.32 155	99.57 107	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++		96.99 132	96.38 171	98.81 27	98.64 148	97.59 23	95.97 192	98.20 219	95.51 162	95.06 293	96.53 282	94.10 176	99.70 112	94.29 207	99.15 213	99.13 156

LS3D		97.77 86	97.50 107	98.57 47	96.24 332	97.58 24	98.45 31	98.85 115	98.58 28	97.51 173	97.94 178	95.74 129	99.63 144	95.19 161	98.97 234	98.51 246

ACMMPR		97.95 58	97.62 93	98.94 15	99.20 78	97.56 25	97.59 89	98.83 124	96.05 130	97.46 180	97.63 206	96.77 82	99.76 62	95.61 135	99.46 149	99.49 71

EGC-MVSNET		83.08 360	77.93 363	98.53 50	99.57 20	97.55 26	98.33 38	98.57 177	4.71 397	10.38 398	98.90 70	95.60 134	99.50 185	95.69 128	99.61 97	98.55 242

region2R		97.92 66	97.59 97	98.92 21	99.22 69	97.55 26	97.60 87	98.84 118	96.00 135	97.22 187	97.62 207	96.87 77	99.76 62	95.48 143	99.43 161	99.46 82

ACMM	93.33 11	98.05 48	97.79 72	98.85 24	99.15 86	97.55 26	96.68 146	98.83 124	95.21 173	98.36 102	98.13 152	98.13 18	99.62 149	96.04 108	99.54 119	99.39 103
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HFP-MVS		97.94 62	97.64 89	98.83 25	99.15 86	97.50 29	97.59 89	98.84 118	96.05 130	97.49 175	97.54 212	97.07 57	99.70 112	95.61 135	99.46 149	99.30 119

HPM-MVS_fast		98.32 30	98.13 40	98.88 23	99.54 26	97.48 30	98.35 35	99.03 70	95.88 143	97.88 157	98.22 144	98.15 16	99.74 77	96.50 90	99.62 91	99.42 97

HPM-MVS		98.11 43	97.83 69	98.92 21	99.42 42	97.46 31	98.57 20	99.05 63	95.43 167	97.41 182	97.50 216	97.98 19	99.79 45	95.58 138	99.57 107	99.50 63
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
XVG-OURS		97.12 126	96.74 149	98.26 70	98.99 111	97.45 32	93.82 302	99.05 63	95.19 175	98.32 109	97.70 202	95.22 145	98.41 350	94.27 208	98.13 296	98.93 193

MAR-MVS		94.21 265	93.03 284	97.76 110	96.94 318	97.44 33	96.97 125	97.15 283	87.89 327	92.00 362	92.73 364	92.14 225	99.12 281	83.92 367	97.51 325	96.73 350
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		97.38 115	97.07 129	98.30 68	99.01 110	97.41 34	94.66 267	99.02 72	95.20 174	98.15 128	97.52 214	98.83 5	98.43 349	94.87 182	96.41 351	99.07 171

COLMAP_ROB	94.48 6	98.25 35	98.11 42	98.64 43	99.21 76	97.35 35	97.96 63	99.16 37	98.34 35	98.78 63	98.52 103	97.32 43	99.45 202	94.08 215	99.67 83	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	98.79 130	97.31 36	97.55 92	98.92 97	97.72 59	98.25 116	98.13 152	97.10 54	99.75 68	95.44 147	99.24 204	99.32 114

anonymousdsp		98.72 14	98.63 20	98.99 10	99.62 16	97.29 37	98.65 19	99.19 34	95.62 156	99.35 25	99.37 19	97.38 41	99.90 14	98.59 26	99.91 18	99.77 12

GST-MVS		97.82 81	97.49 108	98.81 27	99.23 66	97.25 38	97.16 113	98.79 134	95.96 137	97.53 171	97.40 222	96.93 69	99.77 57	95.04 174	99.35 180	99.42 97

ZNCC-MVS		97.92 66	97.62 93	98.83 25	99.32 56	97.24 39	97.45 99	98.84 118	95.76 149	96.93 215	97.43 220	97.26 48	99.79 45	96.06 105	99.53 123	99.45 86

DeepPCF-MVS	94.58 5	96.90 140	96.43 168	98.31 67	97.48 286	97.23 40	92.56 332	98.60 171	92.84 257	98.54 81	97.40 222	96.64 88	98.78 316	94.40 203	99.41 168	98.93 193

SteuartSystems-ACMMP		98.02 50	97.76 77	98.79 29	99.43 40	97.21 41	97.15 114	98.90 99	96.58 104	98.08 136	97.87 186	97.02 62	99.76 62	95.25 158	99.59 102	99.40 100
Skip Steuart: Steuart Systems R&D Blog.
LPG-MVS_test		97.94 62	97.67 84	98.74 34	99.15 86	97.02 42	97.09 119	99.02 72	95.15 177	98.34 105	98.23 141	97.91 21	99.70 112	94.41 201	99.73 66	99.50 63

LGP-MVS_train				98.74 34	99.15 86	97.02 42		99.02 72	95.15 177	98.34 105	98.23 141	97.91 21	99.70 112	94.41 201	99.73 66	99.50 63

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	99.52 180	98.58 27	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		89.92 337	88.63 345	93.82 317	98.37 184	96.94 45	91.58 349	93.34 348	88.00 325	90.32 374	97.10 246	70.87 379	91.13 394	71.91 392	96.16 356	93.39 384

XVG-ACMP-BASELINE		97.58 102	97.28 118	98.49 52	99.16 83	96.90 46	96.39 156	98.98 87	95.05 182	98.06 139	98.02 169	95.86 118	99.56 168	94.37 204	99.64 88	99.00 180

MP-MVS-pluss		97.69 92	97.36 113	98.70 38	99.50 34	96.84 47	95.38 229	98.99 84	92.45 265	98.11 131	98.31 123	97.25 49	99.77 57	96.60 86	99.62 91	99.48 77
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP_NAP		97.89 72	97.63 91	98.67 40	99.35 52	96.84 47	96.36 161	98.79 134	95.07 181	97.88 157	98.35 119	97.24 50	99.72 88	96.05 107	99.58 104	99.45 86

PM-MVS		97.36 119	97.10 126	98.14 82	98.91 119	96.77 49	96.20 173	98.63 169	93.82 222	98.54 81	98.33 121	93.98 179	99.05 291	95.99 113	99.45 152	98.61 237

MIMVSNet1		98.51 23	98.45 29	98.67 40	99.72 8	96.71 50	98.76 12	98.89 100	98.49 31	99.38 22	99.14 46	95.44 139	99.84 30	96.47 91	99.80 51	99.47 80

ACMP	92.54 13	97.47 109	97.10 126	98.55 49	99.04 107	96.70 51	96.24 171	98.89 100	93.71 225	97.97 149	97.75 197	97.44 38	99.63 144	93.22 243	99.70 76	99.32 114
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	98.45 178	96.69 52	98.52 26	99.69 5	98.07 46	96.07 262	97.19 241	96.88 75	99.86 24	97.50 59	99.73 66	98.41 253

SMA-MVS		97.48 108	97.11 125	98.60 45	98.83 125	96.67 53	96.74 139	98.73 146	91.61 277	98.48 88	98.36 118	96.53 93	99.68 124	95.17 163	99.54 119	99.45 86
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				97.85 105	98.64 148	96.66 54		98.51 182	95.63 155	97.22 187	97.30 235	95.52 135	98.55 340	90.97 280	98.90 242	98.34 264

CPTT-MVS		96.69 156	96.08 183	98.49 52	98.89 120	96.64 55	97.25 108	98.77 139	92.89 256	96.01 265	97.13 243	92.23 223	99.67 130	92.24 256	99.34 183	99.17 148

OPM-MVS		97.54 104	97.25 119	98.41 59	99.11 95	96.61 56	95.24 240	98.46 185	94.58 200	98.10 133	98.07 160	97.09 56	99.39 224	95.16 165	99.44 153	99.21 139
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 31	96.61 56	98.55 22	99.17 36	99.05 13	99.17 35	98.79 76	95.47 137	99.89 18	97.95 40	99.91 18	99.75 19

N_pmnet		95.18 222	94.23 258	98.06 88	97.85 237	96.55 58	92.49 333	91.63 365	89.34 306	98.09 134	97.41 221	90.33 255	99.06 290	91.58 269	99.31 193	98.56 240

PHI-MVS		96.96 136	96.53 163	98.25 73	97.48 286	96.50 59	96.76 138	98.85 115	93.52 230	96.19 258	96.85 262	95.94 116	99.42 209	93.79 227	99.43 161	98.83 210

jajsoiax		98.77 9	98.79 12	98.74 34	99.66 13	96.48 60	98.45 31	99.12 46	95.83 147	99.67 7	99.37 19	98.25 13	99.92 5	98.77 18	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 29	96.23 121	99.71 4	99.48 10	98.77 7	99.93 3	98.89 15	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 24	99.01 16	99.63 11	99.66 3	99.27 2	99.68 124	97.75 49	99.89 26	99.62 36

tt0805		97.44 111	97.56 100	97.11 162	99.55 23	96.36 63	98.66 18	95.66 317	98.31 36	97.09 203	95.45 325	97.17 52	98.50 344	98.67 23	97.45 329	96.48 356

OurMVSNet-221017-0		98.61 16	98.61 24	98.63 44	99.77 5	96.35 64	99.17 6	99.05 63	98.05 47	99.61 13	99.52 7	93.72 187	99.88 20	98.72 22	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 32	99.67 2	99.73 3	99.65 5	99.15 3	99.86 24	97.22 66	99.92 15	99.77 12

APD-MVS		97.00 131	96.53 163	98.41 59	98.55 163	96.31 66	96.32 164	98.77 139	92.96 255	97.44 181	97.58 211	95.84 119	99.74 77	91.96 259	99.35 180	99.19 144
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 72	96.50 109	99.32 26	99.44 14	97.43 39	99.92 5	98.73 20	99.95 5	99.86 2

Gipuma		98.07 47	98.31 35	97.36 147	99.76 7	96.28 68	98.51 27	99.10 49	98.76 23	96.79 221	99.34 25	96.61 89	98.82 312	96.38 94	99.50 137	96.98 336
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
DPE-MVS		97.64 96	97.35 114	98.50 51	98.85 124	96.18 69	95.21 242	98.99 84	95.84 146	98.78 63	98.08 158	96.84 79	99.81 37	93.98 221	99.57 107	99.52 59
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
AllTest		97.20 125	96.92 140	98.06 88	99.08 99	96.16 70	97.14 116	99.16 37	94.35 205	97.78 165	98.07 160	95.84 119	99.12 281	91.41 270	99.42 164	98.91 197

TestCases				98.06 88	99.08 99	96.16 70		99.16 37	94.35 205	97.78 165	98.07 160	95.84 119	99.12 281	91.41 270	99.42 164	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 49	99.36 4	99.29 28	99.06 52	97.27 46	99.93 3	97.71 51	99.91 18	99.70 26

h-mvs33		96.29 174	95.63 204	98.26 70	98.50 172	96.11 73	96.90 128	97.09 286	96.58 104	97.21 189	98.19 146	84.14 316	99.78 48	95.89 119	96.17 355	98.89 201

test_part2					99.03 108	96.07 74				98.08 136

APDe-MVS		98.14 39	98.03 50	98.47 54	98.72 138	96.04 75	98.07 58	99.10 49	95.96 137	98.59 78	98.69 87	96.94 67	99.81 37	96.64 84	99.58 104	99.57 47
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
F-COLMAP		95.30 217	94.38 255	98.05 92	98.64 148	96.04 75	95.61 216	98.66 163	89.00 312	93.22 342	96.40 290	92.90 203	99.35 239	87.45 343	97.53 324	98.77 218

CS-MVS-test		97.91 69	97.84 66	98.14 82	98.52 167	96.03 77	98.38 34	99.67 6	98.11 44	95.50 283	96.92 259	96.81 81	99.87 22	96.87 81	99.76 59	98.51 246

OMC-MVS		96.48 167	96.00 186	97.91 100	98.30 188	96.01 78	94.86 259	98.60 171	91.88 274	97.18 192	97.21 240	96.11 113	99.04 292	90.49 300	99.34 183	98.69 228

ZD-MVS					98.43 180	95.94 79		98.56 178	90.72 289	96.66 231	97.07 247	95.02 151	99.74 77	91.08 277	98.93 240

test_vis3_rt		97.04 129	96.98 134	97.23 156	98.44 179	95.88 80	96.82 132	99.67 6	90.30 296	99.27 29	99.33 27	94.04 177	96.03 386	97.14 71	97.83 307	99.78 11

TranMVSNet+NR-MVSNet		98.33 29	98.30 37	98.43 57	99.07 101	95.87 81	96.73 143	99.05 63	98.67 24	98.84 57	98.45 110	97.58 36	99.88 20	96.45 92	99.86 31	99.54 54

mvsmamba		98.16 37	98.06 47	98.44 55	99.53 29	95.87 81	98.70 13	98.94 94	97.71 61	98.85 55	99.10 48	91.35 240	99.83 33	98.47 28	99.90 24	99.64 35

UniMVSNet (Re)		97.83 78	97.65 86	98.35 64	98.80 128	95.86 83	95.92 198	99.04 69	97.51 72	98.22 119	97.81 192	94.68 160	99.78 48	97.14 71	99.75 64	99.41 99

UniMVSNet_NR-MVSNet		97.83 78	97.65 86	98.37 62	98.72 138	95.78 84	95.66 210	99.02 72	98.11 44	98.31 111	97.69 203	94.65 162	99.85 27	97.02 76	99.71 73	99.48 77

DU-MVS		97.79 84	97.60 96	98.36 63	98.73 136	95.78 84	95.65 212	98.87 108	97.57 67	98.31 111	97.83 188	94.69 158	99.85 27	97.02 76	99.71 73	99.46 82

PatchMatch-RL		94.61 250	93.81 271	97.02 171	98.19 202	95.72 86	93.66 307	97.23 279	88.17 323	94.94 298	95.62 320	91.43 237	98.57 337	87.36 344	97.68 317	96.76 349

DeepC-MVS	95.41 4	97.82 81	97.70 79	98.16 79	98.78 133	95.72 86	96.23 172	99.02 72	93.92 220	98.62 74	98.99 57	97.69 29	99.62 149	96.18 103	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	97.39 111	98.22 75	98.93 117	95.69 88	97.05 121	99.10 49	95.32 170	97.83 163	97.88 185	96.44 100	99.72 88	94.59 198	99.39 170	99.25 135

NCCC		96.52 165	95.99 187	98.10 85	97.81 246	95.68 89	95.00 254	98.20 219	95.39 168	95.40 286	96.36 292	93.81 184	99.45 202	93.55 234	98.42 285	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 41	99.33 5	99.30 27	99.00 55	97.27 46	99.92 5	97.64 55	99.92 15	99.75 19

nrg030		98.54 21	98.62 22	98.32 65	99.22 69	95.66 91	97.90 68	99.08 55	98.31 36	99.02 43	98.74 82	97.68 30	99.61 156	97.77 48	99.85 38	99.70 26

3Dnovator+	96.13 3	97.73 88	97.59 97	98.15 81	98.11 218	95.60 92	98.04 60	98.70 155	98.13 43	96.93 215	98.45 110	95.30 143	99.62 149	95.64 133	98.96 235	99.24 136

RRT_MVS		97.95 58	97.79 72	98.43 57	99.67 12	95.56 93	98.86 10	96.73 302	97.99 49	99.15 36	99.35 23	89.84 264	99.90 14	98.64 24	99.90 24	99.82 6

LF4IMVS		96.07 182	95.63 204	97.36 147	98.19 202	95.55 94	95.44 222	98.82 132	92.29 268	95.70 279	96.55 280	92.63 212	98.69 326	91.75 268	99.33 188	97.85 307

NR-MVSNet		97.96 54	97.86 65	98.26 70	98.73 136	95.54 95	98.14 54	98.73 146	97.79 53	99.42 20	97.83 188	94.40 170	99.78 48	95.91 118	99.76 59	99.46 82

CNVR-MVS		96.92 138	96.55 160	98.03 93	98.00 227	95.54 95	94.87 258	98.17 225	94.60 197	96.38 245	97.05 249	95.67 131	99.36 235	95.12 171	99.08 224	99.19 144

hse-mvs2		95.77 195	95.09 216	97.79 108	97.84 242	95.51 97	95.66 210	95.43 326	96.58 104	97.21 189	96.16 299	84.14 316	99.54 175	95.89 119	96.92 336	98.32 265

DVP-MVS		97.78 85	97.65 86	98.16 79	99.24 64	95.51 97	96.74 139	98.23 214	95.92 140	98.40 96	98.28 132	97.06 58	99.71 104	95.48 143	99.52 128	99.26 131
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 64	95.51 97	96.89 129	98.89 100	95.92 140	98.64 72	98.31 123	97.06 58

test_one_0601					99.05 106	95.50 100		98.87 108	97.21 86	98.03 143	98.30 127	96.93 69

test_0728_SECOND				98.25 73	99.23 66	95.49 101	96.74 139	98.89 100					99.75 68	95.48 143	99.52 128	99.53 57

PS-CasMVS		98.73 11	98.85 10	98.39 61	99.55 23	95.47 102	98.49 28	99.13 45	99.22 8	99.22 33	98.96 61	97.35 42	99.92 5	97.79 47	99.93 11	99.79 10

DVP-MVS++		97.96 54	97.90 59	98.12 84	97.75 262	95.40 103	99.03 7	98.89 100	96.62 99	98.62 74	98.30 127	96.97 65	99.75 68	95.70 126	99.25 201	99.21 139

IU-MVS					99.22 69	95.40 103		98.14 232	85.77 347	98.36 102				95.23 160	99.51 133	99.49 71

AUN-MVS		93.95 276	92.69 295	97.74 111	97.80 250	95.38 105	95.57 219	95.46 325	91.26 283	92.64 355	96.10 305	74.67 363	99.55 172	93.72 230	96.97 335	98.30 269

test_prior4						95.38 105	93.61 310

wuyk23d		93.25 294	95.20 211	87.40 375	96.07 343	95.38 105	97.04 122	94.97 331	95.33 169	99.70 6	98.11 156	98.14 17	91.94 393	77.76 386	99.68 81	74.89 393

SED-MVS		97.94 62	97.90 59	98.07 86	99.22 69	95.35 108	96.79 136	98.83 124	96.11 127	99.08 40	98.24 139	97.87 23	99.72 88	95.44 147	99.51 133	99.14 154

test_241102_ONE					99.22 69	95.35 108		98.83 124	96.04 132	99.08 40	98.13 152	97.87 23	99.33 243

MSC_two_6792asdad				98.22 75	97.75 262	95.34 110		98.16 229					99.75 68	95.87 121	99.51 133	99.57 47

No_MVS				98.22 75	97.75 262	95.34 110		98.16 229					99.75 68	95.87 121	99.51 133	99.57 47

MVS_111021_LR		96.82 146	96.55 160	97.62 120	98.27 193	95.34 110	93.81 304	98.33 204	94.59 199	96.56 237	96.63 277	96.61 89	98.73 321	94.80 185	99.34 183	98.78 215

OPU-MVS				97.64 119	98.01 223	95.27 113	96.79 136				97.35 231	96.97 65	98.51 343	91.21 276	99.25 201	99.14 154

CNLPA		95.04 228	94.47 251	96.75 189	97.81 246	95.25 114	94.12 290	97.89 249	94.41 203	94.57 304	95.69 316	90.30 258	98.35 356	86.72 348	98.76 258	96.64 351

TEST9					97.84 242	95.23 115	93.62 308	98.39 196	86.81 336	93.78 323	95.99 307	94.68 160	99.52 180

train_agg		95.46 210	94.66 237	97.88 103	97.84 242	95.23 115	93.62 308	98.39 196	87.04 332	93.78 323	95.99 307	94.58 164	99.52 180	91.76 267	98.90 242	98.89 201

TSAR-MVS + GP.		96.47 168	96.12 180	97.49 135	97.74 265	95.23 115	94.15 286	96.90 293	93.26 238	98.04 142	96.70 273	94.41 169	98.89 307	94.77 189	99.14 214	98.37 258

CP-MVSNet		98.42 26	98.46 27	98.30 68	99.46 37	95.22 118	98.27 44	98.84 118	99.05 13	99.01 44	98.65 92	95.37 140	99.90 14	97.57 56	99.91 18	99.77 12

ACMH+	93.58 10	98.23 36	98.31 35	97.98 97	99.39 47	95.22 118	97.55 92	99.20 32	98.21 41	99.25 31	98.51 105	98.21 14	99.40 220	94.79 186	99.72 70	99.32 114

Vis-MVSNet		98.27 33	98.34 34	98.07 86	99.33 54	95.21 120	98.04 60	99.46 17	97.32 82	97.82 164	99.11 47	96.75 83	99.86 24	97.84 44	99.36 175	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	97.79 108	98.66 147	95.14 121	98.31 39	99.66 8	97.57 67	95.95 266	97.01 253	96.99 64	99.82 35	97.66 54	99.64 88	98.39 256

SD-MVS		97.37 117	97.70 79	96.35 212	98.14 214	95.13 122	96.54 151	98.92 97	95.94 139	99.19 34	98.08 158	97.74 28	95.06 387	95.24 159	99.54 119	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	94.05 272	92.90 287	97.51 128	98.00 227	95.12 123	94.25 279	98.25 211	86.17 341	91.48 367	95.25 327	91.01 244	99.19 270	85.02 362	96.69 346	98.22 277
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_8					97.81 246	95.07 124	93.54 311	98.38 198	87.04 332	93.71 327	95.96 310	94.58 164	99.52 180

TSAR-MVS + MP.		97.42 113	97.23 121	98.00 95	99.38 49	95.00 125	97.63 86	98.20 219	93.00 250	98.16 126	98.06 165	95.89 117	99.72 88	95.67 130	99.10 222	99.28 126
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
agg_prior					97.80 250	94.96 126		98.36 200		93.49 335			99.53 177

CDPH-MVS		95.45 211	94.65 238	97.84 106	98.28 191	94.96 126	93.73 306	98.33 204	85.03 355	95.44 284	96.60 278	95.31 142	99.44 205	90.01 306	99.13 216	99.11 164

CSCG		97.40 114	97.30 116	97.69 116	98.95 113	94.83 128	97.28 107	98.99 84	96.35 117	98.13 130	95.95 311	95.99 115	99.66 136	94.36 206	99.73 66	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 30	96.91 92	99.75 2	99.45 13	95.82 122	99.92 5	98.80 17	99.96 4	99.89 1

DP-MVS		97.87 74	97.89 62	97.81 107	98.62 154	94.82 129	97.13 117	98.79 134	98.98 17	98.74 69	98.49 106	95.80 127	99.49 190	95.04 174	99.44 153	99.11 164

save fliter					98.48 175	94.71 131	94.53 271	98.41 193	95.02 184

alignmvs		96.01 186	95.52 207	97.50 132	97.77 259	94.71 131	96.07 183	96.84 294	97.48 73	96.78 225	94.28 347	85.50 307	99.40 220	96.22 100	98.73 263	98.40 254

新几何1				97.25 154	98.29 189	94.70 133		97.73 259	77.98 385	94.83 300	96.67 275	92.08 228	99.45 202	88.17 333	98.65 271	97.61 319

plane_prior7					98.70 143	94.67 134

CMPMVS	73.10 23	92.74 301	91.39 313	96.77 188	93.57 385	94.67 134	94.21 283	97.67 262	80.36 378	93.61 331	96.60 278	82.85 325	97.35 374	84.86 363	98.78 256	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 47	94.63 136	96.70 145	99.82 1	95.44 166	99.64 10	99.52 7	98.96 4	99.74 77	99.38 3	99.86 31	99.81 8

test_fmvsmconf0.1_n		98.41 27	98.54 25	98.03 93	99.16 83	94.61 137	96.18 174	99.73 3	95.05 182	99.60 14	99.34 25	98.68 8	99.72 88	99.21 7	99.85 38	99.76 17

test_fmvsmconf_n		98.30 32	98.41 32	97.99 96	98.94 116	94.60 138	96.00 189	99.64 12	94.99 185	99.43 19	99.18 39	98.51 10	99.71 104	99.13 10	99.84 40	99.67 28

pm-mvs1		98.47 24	98.67 18	97.86 104	99.52 30	94.58 139	98.28 42	99.00 81	97.57 67	99.27 29	99.22 34	98.32 12	99.50 185	97.09 73	99.75 64	99.50 63

GeoE		97.75 87	97.70 79	97.89 102	98.88 121	94.53 140	97.10 118	98.98 87	95.75 151	97.62 168	97.59 209	97.61 35	99.77 57	96.34 96	99.44 153	99.36 111

plane_prior3						94.51 141			95.29 172	96.16 259

TAPA-MVS	93.32 12	94.93 232	94.23 258	97.04 169	98.18 205	94.51 141	95.22 241	98.73 146	81.22 374	96.25 254	95.95 311	93.80 185	98.98 300	89.89 308	98.87 246	97.62 318
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
VDD-MVS		97.37 117	97.25 119	97.74 111	98.69 145	94.50 143	97.04 122	95.61 321	98.59 27	98.51 83	98.72 83	92.54 216	99.58 161	96.02 110	99.49 140	99.12 161

AdaColmap		95.11 225	94.62 242	96.58 198	97.33 301	94.45 144	94.92 256	98.08 238	93.15 246	93.98 321	95.53 323	94.34 171	99.10 286	85.69 353	98.61 274	96.20 361

Fast-Effi-MVS+-dtu		96.44 169	96.12 180	97.39 146	97.18 308	94.39 145	95.46 221	98.73 146	96.03 134	94.72 301	94.92 335	96.28 109	99.69 119	93.81 226	97.98 301	98.09 283

canonicalmvs		97.23 124	97.21 122	97.30 150	97.65 274	94.39 145	97.84 71	99.05 63	97.42 75	96.68 229	93.85 350	97.63 34	99.33 243	96.29 97	98.47 282	98.18 281

Anonymous20231211		98.55 20	98.76 13	97.94 99	98.79 130	94.37 147	98.84 11	99.15 41	99.37 3	99.67 7	99.43 15	95.61 133	99.72 88	98.12 33	99.86 31	99.73 22

plane_prior6					98.38 183	94.37 147						91.91 234

mvsany_test3		96.21 177	95.93 192	97.05 167	97.40 294	94.33 149	95.76 204	94.20 339	89.10 309	99.36 24	99.60 6	93.97 180	97.85 368	95.40 154	98.63 272	98.99 183

pmmvs-eth3d		96.49 166	96.18 179	97.42 143	98.25 195	94.29 150	94.77 263	98.07 242	89.81 303	97.97 149	98.33 121	93.11 197	99.08 288	95.46 146	99.84 40	98.89 201

HQP_MVS		96.66 158	96.33 174	97.68 117	98.70 143	94.29 150	96.50 152	98.75 143	96.36 115	96.16 259	96.77 269	91.91 234	99.46 198	92.59 252	99.20 206	99.28 126

plane_prior						94.29 150	95.42 224		94.31 207						98.93 240

Anonymous20240529		97.96 54	98.04 49	97.71 113	98.69 145	94.28 153	97.86 70	98.31 208	98.79 22	99.23 32	98.86 74	95.76 128	99.61 156	95.49 140	99.36 175	99.23 137

bld_raw_dy_0_64		97.69 92	97.61 95	97.91 100	99.54 26	94.27 154	98.06 59	98.60 171	96.60 101	98.79 62	98.95 63	89.62 265	99.84 30	98.43 30	99.91 18	99.62 36

test_prior				97.46 138	97.79 255	94.26 155		98.42 192					99.34 241			98.79 214

v7n		98.73 11	98.99 5	97.95 98	99.64 14	94.20 156	98.67 15	99.14 44	99.08 10	99.42 20	99.23 33	96.53 93	99.91 13	99.27 5	99.93 11	99.73 22

DeepC-MVS_fast	94.34 7	96.74 150	96.51 165	97.44 140	97.69 268	94.15 157	96.02 187	98.43 189	93.17 245	97.30 184	97.38 228	95.48 136	99.28 256	93.74 228	99.34 183	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		96.24 176	95.80 197	97.56 123	98.75 135	94.13 158	94.66 267	98.17 225	90.17 299	96.21 256	96.10 305	95.14 147	99.43 207	94.13 214	98.85 249	99.13 156

test12				97.46 138	97.61 277	94.07 159		97.78 257		93.57 333		93.31 194	99.42 209		98.78 256	98.89 201

test_0402		97.84 77	97.97 55	97.47 137	99.19 80	94.07 159	96.71 144	98.73 146	98.66 25	98.56 80	98.41 113	96.84 79	99.69 119	94.82 184	99.81 48	98.64 232

API-MVS		95.09 227	95.01 220	95.31 260	96.61 324	94.02 161	96.83 131	97.18 282	95.60 157	95.79 273	94.33 346	94.54 166	98.37 355	85.70 352	98.52 279	93.52 382

IS-MVSNet		96.93 137	96.68 152	97.70 114	99.25 63	94.00 162	98.57 20	96.74 300	98.36 34	98.14 129	97.98 174	88.23 283	99.71 104	93.10 246	99.72 70	99.38 105

DP-MVS Recon		95.55 204	95.13 214	96.80 185	98.51 169	93.99 163	94.60 269	98.69 156	90.20 298	95.78 275	96.21 298	92.73 208	98.98 300	90.58 296	98.86 248	97.42 327

test_fmvsm_n_1920		98.08 45	98.29 38	97.43 141	98.88 121	93.95 164	96.17 178	99.57 14	95.66 153	99.52 15	98.71 85	97.04 60	99.64 141	99.21 7	99.87 29	98.69 228

ETV-MVS		96.13 181	95.90 193	96.82 184	97.76 260	93.89 165	95.40 227	98.95 93	95.87 144	95.58 282	91.00 382	96.36 105	99.72 88	93.36 237	98.83 252	96.85 343

旧先验1					97.80 250	93.87 166		97.75 258			97.04 250	93.57 189			98.68 266	98.72 224

Anonymous202405211		96.34 173	95.98 188	97.43 141	98.25 195	93.85 167	96.74 139	94.41 337	97.72 59	98.37 99	98.03 168	87.15 295	99.53 177	94.06 216	99.07 226	98.92 196

UGNet		96.81 147	96.56 159	97.58 122	96.64 323	93.84 168	97.75 77	97.12 285	96.47 112	93.62 330	98.88 72	93.22 196	99.53 177	95.61 135	99.69 77	99.36 111
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	97.70 114	99.06 102	93.80 169	97.76 76	99.00 81	98.40 33	99.07 42	98.98 58	96.89 73	99.75 68	97.19 70	99.79 53	99.55 53

LCM-MVSNet-Re		97.33 120	97.33 115	97.32 149	98.13 217	93.79 170	96.99 124	99.65 9	96.74 97	99.47 17	98.93 65	96.91 72	99.84 30	90.11 304	99.06 229	98.32 265

EPP-MVSNet		96.84 142	96.58 157	97.65 118	99.18 81	93.78 171	98.68 14	96.34 305	97.91 51	97.30 184	98.06 165	88.46 280	99.85 27	93.85 225	99.40 169	99.32 114

NP-MVS					98.14 214	93.72 172					95.08 329

GBi-Net		96.99 132	96.80 146	97.56 123	97.96 229	93.67 173	98.23 46	98.66 163	95.59 158	97.99 145	99.19 36	89.51 271	99.73 83	94.60 195	99.44 153	99.30 119

test1		96.99 132	96.80 146	97.56 123	97.96 229	93.67 173	98.23 46	98.66 163	95.59 158	97.99 145	99.19 36	89.51 271	99.73 83	94.60 195	99.44 153	99.30 119

FMVSNet1		97.95 58	98.08 44	97.56 123	99.14 93	93.67 173	98.23 46	98.66 163	97.41 78	99.00 46	99.19 36	95.47 137	99.73 83	95.83 123	99.76 59	99.30 119

MVS_111021_HR		96.73 152	96.54 162	97.27 152	98.35 186	93.66 176	93.42 314	98.36 200	94.74 191	96.58 235	96.76 271	96.54 92	98.99 298	94.87 182	99.27 199	99.15 151

3Dnovator	96.53 2	97.61 99	97.64 89	97.50 132	97.74 265	93.65 177	98.49 28	98.88 106	96.86 94	97.11 197	98.55 101	95.82 122	99.73 83	95.94 116	99.42 164	99.13 156

CDS-MVSNet		94.88 235	94.12 263	97.14 160	97.64 275	93.57 178	93.96 298	97.06 288	90.05 300	96.30 251	96.55 280	86.10 301	99.47 195	90.10 305	99.31 193	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	97.51 128	99.43 40	93.54 179	98.23 46	99.05 63	97.40 79	99.37 23	99.08 51	98.79 6	99.47 195	97.74 50	99.71 73	99.50 63
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EG-PatchMatch MVS		97.69 92	97.79 72	97.40 145	99.06 102	93.52 180	95.96 194	98.97 90	94.55 201	98.82 59	98.76 81	97.31 44	99.29 254	97.20 69	99.44 153	99.38 105

PCF-MVS	89.43 18	92.12 312	90.64 328	96.57 200	97.80 250	93.48 181	89.88 377	98.45 186	74.46 390	96.04 264	95.68 317	90.71 249	99.31 247	73.73 389	99.01 233	96.91 340
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	97.51 128	99.41 43	93.44 182	97.96 63	98.25 211	98.58 28	98.78 63	99.39 16	98.21 14	99.56 168	92.65 250	99.86 31	99.52 59

test_vis1_rt		94.03 273	93.65 273	95.17 266	95.76 352	93.42 183	93.97 297	98.33 204	84.68 359	93.17 343	95.89 313	92.53 218	94.79 388	93.50 235	94.97 368	97.31 331

TAMVS		95.49 206	94.94 221	97.16 158	98.31 187	93.41 184	95.07 249	96.82 296	91.09 285	97.51 173	97.82 191	89.96 261	99.42 209	88.42 329	99.44 153	98.64 232

TransMVSNet (Re)		98.38 28	98.67 18	97.51 128	99.51 31	93.39 185	98.20 51	98.87 108	98.23 40	99.48 16	99.27 30	98.47 11	99.55 172	96.52 89	99.53 123	99.60 38

MM				97.62 120		93.30 186	96.39 156	92.61 358	97.90 52	96.76 226	98.64 93	90.46 252	99.81 37	99.16 9	99.94 8	99.76 17

test_fmvsmvis_n_1920		98.08 45	98.47 26	96.93 175	99.03 108	93.29 187	96.32 164	99.65 9	95.59 158	99.71 4	99.01 54	97.66 32	99.60 158	99.44 2	99.83 43	97.90 303

Baseline_NR-MVSNet		97.72 90	97.79 72	97.50 132	99.56 21	93.29 187	95.44 222	98.86 111	98.20 42	98.37 99	99.24 32	94.69 158	99.55 172	95.98 114	99.79 53	99.65 33

VDDNet		96.98 135	96.84 143	97.41 144	99.40 46	93.26 189	97.94 65	95.31 328	99.26 7	98.39 98	99.18 39	87.85 290	99.62 149	95.13 170	99.09 223	99.35 113

test222					98.17 208	93.24 190	92.74 329	97.61 271	75.17 389	94.65 303	96.69 274	90.96 246			98.66 269	97.66 315

test_f		95.82 194	95.88 195	95.66 244	97.61 277	93.21 191	95.61 216	98.17 225	86.98 334	98.42 94	99.47 11	90.46 252	94.74 389	97.71 51	98.45 283	99.03 176

FC-MVSNet-test		98.16 37	98.37 33	97.56 123	99.49 35	93.10 192	98.35 35	99.21 30	98.43 32	98.89 52	98.83 75	94.30 172	99.81 37	97.87 42	99.91 18	99.77 12

MVP-Stereo		95.69 197	95.28 209	96.92 176	98.15 212	93.03 193	95.64 215	98.20 219	90.39 295	96.63 234	97.73 200	91.63 236	99.10 286	91.84 264	97.31 333	98.63 234
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EIA-MVS		96.04 184	95.77 199	96.85 181	97.80 250	92.98 194	96.12 180	99.16 37	94.65 195	93.77 325	91.69 376	95.68 130	99.67 130	94.18 211	98.85 249	97.91 302

FIs		97.93 65	98.07 45	97.48 136	99.38 49	92.95 195	98.03 62	99.11 47	98.04 48	98.62 74	98.66 89	93.75 186	99.78 48	97.23 65	99.84 40	99.73 22

Fast-Effi-MVS+		95.49 206	95.07 217	96.75 189	97.67 272	92.82 196	94.22 282	98.60 171	91.61 277	93.42 339	92.90 360	96.73 84	99.70 112	92.60 251	97.89 306	97.74 312

test_fmvs3		97.38 115	97.56 100	96.84 183	98.63 152	92.81 197	97.60 87	99.61 13	90.87 287	98.76 68	99.66 3	94.03 178	97.90 367	99.24 6	99.68 81	99.81 8

KD-MVS_self_test		97.86 76	98.07 45	97.25 154	99.22 69	92.81 197	97.55 92	98.94 94	97.10 88	98.85 55	98.88 72	95.03 150	99.67 130	97.39 63	99.65 86	99.26 131

PMMVS		92.39 305	91.08 319	96.30 216	93.12 387	92.81 197	90.58 368	95.96 312	79.17 382	91.85 364	92.27 369	90.29 259	98.66 331	89.85 309	96.68 347	97.43 326

dmvs_re		92.08 314	91.27 316	94.51 300	97.16 309	92.79 200	95.65 212	92.64 357	94.11 214	92.74 351	90.98 383	83.41 322	94.44 391	80.72 378	94.07 375	96.29 359

pmmvs4		94.82 237	94.19 261	96.70 192	97.42 293	92.75 201	92.09 344	96.76 298	86.80 337	95.73 278	97.22 239	89.28 274	98.89 307	93.28 241	99.14 214	98.46 252

DPM-MVS		93.68 281	92.77 294	96.42 209	97.91 233	92.54 202	91.17 359	97.47 275	84.99 357	93.08 345	94.74 337	89.90 262	99.00 296	87.54 341	98.09 298	97.72 313

CLD-MVS		95.47 209	95.07 217	96.69 193	98.27 193	92.53 203	91.36 352	98.67 161	91.22 284	95.78 275	94.12 348	95.65 132	98.98 300	90.81 285	99.72 70	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	97.18 157	99.17 82	92.51 204	96.57 149	99.15 41	93.68 227	98.89 52	99.30 28	96.42 101	99.37 232	99.03 11	99.83 43	99.66 30

fmvsm_s_conf0.5_n_a		97.65 95	97.83 69	97.13 161	98.80 128	92.51 204	96.25 170	99.06 59	93.67 228	98.64 72	99.00 55	96.23 110	99.36 235	98.99 13	99.80 51	99.53 57

HQP5-MVS						92.47 206

HQP-MVS		95.17 224	94.58 246	96.92 176	97.85 237	92.47 206	94.26 276	98.43 189	93.18 242	92.86 348	95.08 329	90.33 255	99.23 267	90.51 298	98.74 260	99.05 175

SixPastTwentyTwo		97.49 107	97.57 99	97.26 153	99.56 21	92.33 208	98.28 42	96.97 291	98.30 38	99.45 18	99.35 23	88.43 281	99.89 18	98.01 38	99.76 59	99.54 54

MVS_0304		96.62 160	96.40 170	97.28 151	97.91 233	92.30 209	96.47 154	89.74 381	97.52 71	95.38 287	98.63 94	92.76 206	99.81 37	99.28 4	99.93 11	99.75 19

EPNet		93.72 279	92.62 298	97.03 170	87.61 399	92.25 210	96.27 166	91.28 368	96.74 97	87.65 386	97.39 226	85.00 310	99.64 141	92.14 257	99.48 144	99.20 143
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpnnormal		97.72 90	97.97 55	96.94 174	99.26 60	92.23 211	97.83 72	98.45 186	98.25 39	99.13 38	98.66 89	96.65 86	99.69 119	93.92 223	99.62 91	98.91 197

SDMVSNet		97.97 52	98.26 39	97.11 162	99.41 43	92.21 212	96.92 127	98.60 171	98.58 28	98.78 63	99.39 16	97.80 25	99.62 149	94.98 180	99.86 31	99.52 59

XXY-MVS		97.54 104	97.70 79	97.07 166	99.46 37	92.21 212	97.22 111	99.00 81	94.93 188	98.58 79	98.92 66	97.31 44	99.41 218	94.44 199	99.43 161	99.59 39

ab-mvs		96.59 161	96.59 156	96.60 196	98.64 148	92.21 212	98.35 35	97.67 262	94.45 202	96.99 210	98.79 76	94.96 154	99.49 190	90.39 301	99.07 226	98.08 284

WR-MVS		96.90 140	96.81 145	97.16 158	98.56 162	92.20 215	94.33 275	98.12 234	97.34 81	98.20 120	97.33 233	92.81 204	99.75 68	94.79 186	99.81 48	99.54 54

Effi-MVS+		96.19 178	96.01 185	96.71 191	97.43 292	92.19 216	96.12 180	99.10 49	95.45 164	93.33 341	94.71 338	97.23 51	99.56 168	93.21 244	97.54 323	98.37 258

mvsany_test1		93.47 288	93.03 284	94.79 287	94.05 380	92.12 217	90.82 365	90.01 380	85.02 356	97.26 186	98.28 132	93.57 189	97.03 377	92.51 254	95.75 362	95.23 373

原ACMM1				96.58 198	98.16 210	92.12 217		98.15 231	85.90 345	93.49 335	96.43 287	92.47 220	99.38 227	87.66 338	98.62 273	98.23 276

lessismore_v0				97.05 167	99.36 51	92.12 217		84.07 393		98.77 67	98.98 58	85.36 308	99.74 77	97.34 64	99.37 172	99.30 119

casdiffmvs_mvg		97.83 78	98.11 42	97.00 172	98.57 160	92.10 220	95.97 192	99.18 35	97.67 66	99.00 46	98.48 109	97.64 33	99.50 185	96.96 78	99.54 119	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		97.32 121	97.39 111	97.11 162	97.36 296	92.08 221	95.34 233	97.65 266	97.74 57	98.29 114	98.11 156	95.05 148	99.68 124	97.50 59	99.50 137	99.56 51

VNet		96.84 142	96.83 144	96.88 179	98.06 219	92.02 222	96.35 162	97.57 272	97.70 62	97.88 157	97.80 193	92.40 221	99.54 175	94.73 191	98.96 235	99.08 169

EI-MVSNet-UG-set		97.32 121	97.40 110	97.09 165	97.34 299	92.01 223	95.33 234	97.65 266	97.74 57	98.30 113	98.14 150	95.04 149	99.69 119	97.55 57	99.52 128	99.58 40

OpenMVS	94.22 8	95.48 208	95.20 211	96.32 214	97.16 309	91.96 224	97.74 79	98.84 118	87.26 329	94.36 310	98.01 171	93.95 181	99.67 130	90.70 293	98.75 259	97.35 330

FMVSNet2		96.72 153	96.67 153	96.87 180	97.96 229	91.88 225	97.15 114	98.06 243	95.59 158	98.50 85	98.62 95	89.51 271	99.65 138	94.99 179	99.60 100	99.07 171

MSDG		95.33 215	95.13 214	95.94 233	97.40 294	91.85 226	91.02 363	98.37 199	95.30 171	96.31 250	95.99 307	94.51 167	98.38 353	89.59 312	97.65 320	97.60 320

QAPM		95.88 191	95.57 206	96.80 185	97.90 235	91.84 227	98.18 53	98.73 146	88.41 318	96.42 243	98.13 152	94.73 156	99.75 68	88.72 324	98.94 238	98.81 212

HyFIR lowres test		93.72 279	92.65 296	96.91 178	98.93 117	91.81 228	91.23 358	98.52 180	82.69 367	96.46 242	96.52 284	80.38 337	99.90 14	90.36 302	98.79 255	99.03 176

test20.03		96.58 163	96.61 155	96.48 205	98.49 173	91.72 229	95.68 209	97.69 261	96.81 95	98.27 115	97.92 181	94.18 175	98.71 324	90.78 287	99.66 85	99.00 180

ambc				96.56 201	98.23 198	91.68 230	97.88 69	98.13 233		98.42 94	98.56 100	94.22 174	99.04 292	94.05 218	99.35 180	98.95 187

K. test v3		96.44 169	96.28 175	96.95 173	99.41 43	91.53 231	97.65 84	90.31 377	98.89 20	98.93 49	99.36 21	84.57 314	99.92 5	97.81 45	99.56 110	99.39 103

UnsupCasMVSNet_eth		95.91 190	95.73 200	96.44 206	98.48 175	91.52 232	95.31 236	98.45 186	95.76 149	97.48 177	97.54 212	89.53 270	98.69 326	94.43 200	94.61 372	99.13 156

LFMVS		95.32 216	94.88 227	96.62 195	98.03 220	91.47 233	97.65 84	90.72 374	99.11 9	97.89 156	98.31 123	79.20 340	99.48 193	93.91 224	99.12 219	98.93 193

fmvsm_s_conf0.5_n		97.62 98	97.89 62	96.80 185	98.79 130	91.44 234	96.14 179	99.06 59	94.19 210	98.82 59	98.98 58	96.22 111	99.38 227	98.98 14	99.86 31	99.58 40

fmvsm_s_conf0.1_n		97.73 88	98.02 51	96.85 181	99.09 98	91.43 235	96.37 160	99.11 47	94.19 210	99.01 44	99.25 31	96.30 106	99.38 227	99.00 12	99.88 27	99.73 22

test_fmvs2		96.38 172	96.45 167	96.16 222	97.85 237	91.30 236	96.81 133	99.45 18	89.24 308	98.49 86	99.38 18	88.68 278	97.62 372	98.83 16	99.32 190	99.57 47

PAPM_NR		94.61 250	94.17 262	95.96 229	98.36 185	91.23 237	95.93 197	97.95 245	92.98 251	93.42 339	94.43 345	90.53 250	98.38 353	87.60 339	96.29 353	98.27 273

OpenMVS_ROB	91.80 14	93.64 284	93.05 282	95.42 257	97.31 303	91.21 238	95.08 248	96.68 303	81.56 371	96.88 219	96.41 288	90.44 254	99.25 262	85.39 358	97.67 318	95.80 365

V42		97.04 129	97.16 124	96.68 194	98.59 158	91.05 239	96.33 163	98.36 200	94.60 197	97.99 145	98.30 127	93.32 193	99.62 149	97.40 62	99.53 123	99.38 105

casdiffmvs		97.50 106	97.81 71	96.56 201	98.51 169	91.04 240	95.83 202	99.09 54	97.23 85	98.33 108	98.30 127	97.03 61	99.37 232	96.58 88	99.38 171	99.28 126
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		91.79 318	90.69 327	95.11 267	93.80 382	90.98 241	94.16 285	91.78 364	96.38 113	90.30 375	99.30 28	72.02 375	98.90 306	88.28 331	90.17 385	95.45 371

114514_t		93.96 274	93.22 281	96.19 220	99.06 102	90.97 242	95.99 190	98.94 94	73.88 391	93.43 338	96.93 257	92.38 222	99.37 232	89.09 319	99.28 197	98.25 275

1112_ss		94.12 268	93.42 277	96.23 217	98.59 158	90.85 243	94.24 280	98.85 115	85.49 348	92.97 346	94.94 333	86.01 302	99.64 141	91.78 266	97.92 303	98.20 279

CANet		95.86 192	95.65 203	96.49 204	96.41 329	90.82 244	94.36 274	98.41 193	94.94 186	92.62 357	96.73 272	92.68 209	99.71 104	95.12 171	99.60 100	98.94 189

Patchmtry		95.03 230	94.59 245	96.33 213	94.83 368	90.82 244	96.38 159	97.20 280	96.59 103	97.49 175	98.57 98	77.67 347	99.38 227	92.95 249	99.62 91	98.80 213

FMVSNet5		93.39 290	92.35 300	96.50 203	95.83 349	90.81 246	97.31 105	98.27 209	92.74 258	96.27 252	98.28 132	62.23 392	99.67 130	90.86 283	99.36 175	99.03 176

baseline		97.44 111	97.78 76	96.43 207	98.52 167	90.75 247	96.84 130	99.03 70	96.51 108	97.86 161	98.02 169	96.67 85	99.36 235	97.09 73	99.47 146	99.19 144

PVSNet_Blended_VisFu		95.95 188	95.80 197	96.42 209	99.28 58	90.62 248	95.31 236	99.08 55	88.40 319	96.97 213	98.17 149	92.11 226	99.78 48	93.64 232	99.21 205	98.86 208

testdata				95.70 243	98.16 210	90.58 249		97.72 260	80.38 377	95.62 280	97.02 251	92.06 229	98.98 300	89.06 321	98.52 279	97.54 322

VPNet		97.26 123	97.49 108	96.59 197	99.47 36	90.58 249	96.27 166	98.53 179	97.77 54	98.46 91	98.41 113	94.59 163	99.68 124	94.61 194	99.29 196	99.52 59

MSLP-MVS++		96.42 171	96.71 150	95.57 247	97.82 245	90.56 251	95.71 205	98.84 118	94.72 192	96.71 228	97.39 226	94.91 155	98.10 365	95.28 156	99.02 231	98.05 293

UnsupCasMVSNet_bld		94.72 243	94.26 257	96.08 225	98.62 154	90.54 252	93.38 316	98.05 244	90.30 296	97.02 208	96.80 268	89.54 268	99.16 276	88.44 328	96.18 354	98.56 240

iter_conf_final		94.54 254	93.91 270	96.43 207	97.23 306	90.41 253	96.81 133	98.10 235	93.87 221	96.80 220	97.89 183	68.02 385	99.72 88	96.73 83	99.77 58	99.18 147

FMVSNet3		95.26 219	94.94 221	96.22 219	96.53 326	90.06 254	95.99 190	97.66 264	94.11 214	97.99 145	97.91 182	80.22 338	99.63 144	94.60 195	99.44 153	98.96 186

CHOSEN 1792x2688		94.10 269	93.41 278	96.18 221	99.16 83	90.04 255	92.15 341	98.68 158	79.90 379	96.22 255	97.83 188	87.92 289	99.42 209	89.18 318	99.65 86	99.08 169

DELS-MVS		96.17 179	96.23 176	95.99 227	97.55 282	90.04 255	92.38 339	98.52 180	94.13 212	96.55 239	97.06 248	94.99 152	99.58 161	95.62 134	99.28 197	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		94.22 263	93.72 272	95.74 240	97.71 267	89.95 257	93.84 301	96.98 290	88.38 320	93.75 326	95.74 315	87.94 285	98.89 307	91.02 279	98.10 297	98.37 258

test_vis1_n		95.67 199	95.89 194	95.03 272	98.18 205	89.89 258	96.94 126	99.28 26	88.25 322	98.20 120	98.92 66	86.69 299	97.19 375	97.70 53	98.82 253	98.00 298

CL-MVSNet_self_test		95.04 228	94.79 234	95.82 237	97.51 284	89.79 259	91.14 360	96.82 296	93.05 248	96.72 227	96.40 290	90.82 247	99.16 276	91.95 260	98.66 269	98.50 248

CANet_DTU		94.65 248	94.21 260	95.96 229	95.90 346	89.68 260	93.92 299	97.83 255	93.19 241	90.12 376	95.64 319	88.52 279	99.57 167	93.27 242	99.47 146	98.62 235

v10		97.55 103	97.97 55	96.31 215	98.60 156	89.64 261	97.44 100	99.02 72	96.60 101	98.72 71	99.16 43	93.48 191	99.72 88	98.76 19	99.92 15	99.58 40

ANet_high		98.31 31	98.94 6	96.41 211	99.33 54	89.64 261	97.92 67	99.56 16	99.27 6	99.66 9	99.50 9	97.67 31	99.83 33	97.55 57	99.98 2	99.77 12

test_yl		94.40 258	94.00 266	95.59 245	96.95 316	89.52 263	94.75 264	95.55 323	96.18 125	96.79 221	96.14 302	81.09 333	99.18 271	90.75 288	97.77 308	98.07 286

DCV-MVSNet		94.40 258	94.00 266	95.59 245	96.95 316	89.52 263	94.75 264	95.55 323	96.18 125	96.79 221	96.14 302	81.09 333	99.18 271	90.75 288	97.77 308	98.07 286

v8		97.60 100	98.06 47	96.23 217	98.71 141	89.44 265	97.43 102	98.82 132	97.29 84	98.74 69	99.10 48	93.86 182	99.68 124	98.61 25	99.94 8	99.56 51

Anonymous20231206		95.27 218	95.06 219	95.88 235	98.72 138	89.37 266	95.70 206	97.85 251	88.00 325	96.98 212	97.62 207	91.95 231	99.34 241	89.21 317	99.53 123	98.94 189

v1192		96.83 145	97.06 130	96.15 223	98.28 191	89.29 267	95.36 230	98.77 139	93.73 224	98.11 131	98.34 120	93.02 202	99.67 130	98.35 31	99.58 104	99.50 63

v1144		96.84 142	97.08 128	96.13 224	98.42 181	89.28 268	95.41 226	98.67 161	94.21 208	97.97 149	98.31 123	93.06 198	99.65 138	98.06 37	99.62 91	99.45 86

Vis-MVSNet (Re-imp)		95.11 225	94.85 228	95.87 236	99.12 94	89.17 269	97.54 97	94.92 332	96.50 109	96.58 235	97.27 236	83.64 320	99.48 193	88.42 329	99.67 83	98.97 185

new_pmnet		92.34 307	91.69 311	94.32 307	96.23 334	89.16 270	92.27 340	92.88 352	84.39 364	95.29 288	96.35 293	85.66 305	96.74 384	84.53 365	97.56 322	97.05 334

ET-MVSNet_ETH3D		91.12 324	89.67 336	95.47 254	96.41 329	89.15 271	91.54 350	90.23 378	89.07 310	86.78 390	92.84 361	69.39 383	99.44 205	94.16 212	96.61 348	97.82 309

test_fmvs1_n		95.21 220	95.28 209	94.99 275	98.15 212	89.13 272	96.81 133	99.43 20	86.97 335	97.21 189	98.92 66	83.00 324	97.13 376	98.09 35	98.94 238	98.72 224

v144192		96.69 156	96.90 142	96.03 226	98.25 195	88.92 273	95.49 220	98.77 139	93.05 248	98.09 134	98.29 131	92.51 219	99.70 112	98.11 34	99.56 110	99.47 80

Patchmatch-RL test		94.66 247	94.49 249	95.19 264	98.54 165	88.91 274	92.57 331	98.74 145	91.46 280	98.32 109	97.75 197	77.31 352	98.81 314	96.06 105	99.61 97	97.85 307

HY-MVS	91.43 15	92.58 303	91.81 308	94.90 280	96.49 327	88.87 275	97.31 105	94.62 334	85.92 344	90.50 373	96.84 263	85.05 309	99.40 220	83.77 370	95.78 360	96.43 357

Test_1112_low_res		93.53 287	92.86 288	95.54 251	98.60 156	88.86 276	92.75 327	98.69 156	82.66 368	92.65 354	96.92 259	84.75 312	99.56 168	90.94 281	97.76 310	98.19 280

PAPR		92.22 309	91.27 316	95.07 270	95.73 354	88.81 277	91.97 345	97.87 250	85.80 346	90.91 369	92.73 364	91.16 241	98.33 357	79.48 380	95.76 361	98.08 284

v1921920		96.72 153	96.96 137	95.99 227	98.21 199	88.79 278	95.42 224	98.79 134	93.22 240	98.19 124	98.26 137	92.68 209	99.70 112	98.34 32	99.55 116	99.49 71

v2v482		96.78 149	97.06 130	95.95 231	98.57 160	88.77 279	95.36 230	98.26 210	95.18 176	97.85 162	98.23 141	92.58 213	99.63 144	97.80 46	99.69 77	99.45 86

MDA-MVSNet-bldmvs		95.69 197	95.67 201	95.74 240	98.48 175	88.76 280	92.84 324	97.25 278	96.00 135	97.59 169	97.95 177	91.38 238	99.46 198	93.16 245	96.35 352	98.99 183

v1240		96.74 150	97.02 133	95.91 234	98.18 205	88.52 281	95.39 228	98.88 106	93.15 246	98.46 91	98.40 116	92.80 205	99.71 104	98.45 29	99.49 140	99.49 71

xiu_mvs_v1_base_debu		95.62 201	95.96 189	94.60 294	98.01 223	88.42 282	93.99 294	98.21 216	92.98 251	95.91 268	94.53 341	96.39 102	99.72 88	95.43 150	98.19 293	95.64 367

xiu_mvs_v1_base		95.62 201	95.96 189	94.60 294	98.01 223	88.42 282	93.99 294	98.21 216	92.98 251	95.91 268	94.53 341	96.39 102	99.72 88	95.43 150	98.19 293	95.64 367

xiu_mvs_v1_base_debi		95.62 201	95.96 189	94.60 294	98.01 223	88.42 282	93.99 294	98.21 216	92.98 251	95.91 268	94.53 341	96.39 102	99.72 88	95.43 150	98.19 293	95.64 367

pmmvs5		94.63 249	94.34 256	95.50 252	97.63 276	88.34 285	94.02 292	97.13 284	87.15 331	95.22 290	97.15 242	87.50 291	99.27 259	93.99 220	99.26 200	98.88 205

FE-MVS		92.95 298	92.22 302	95.11 267	97.21 307	88.33 286	98.54 23	93.66 344	89.91 302	96.21 256	98.14 150	70.33 381	99.50 185	87.79 335	98.24 292	97.51 323

thisisatest0530		92.71 302	91.76 310	95.56 249	98.42 181	88.23 287	96.03 186	87.35 387	94.04 217	96.56 237	95.47 324	64.03 390	99.77 57	94.78 188	99.11 220	98.68 231

MIMVSNet		93.42 289	92.86 288	95.10 269	98.17 208	88.19 288	98.13 55	93.69 341	92.07 269	95.04 296	98.21 145	80.95 335	99.03 295	81.42 376	98.06 299	98.07 286

Anonymous20240521		97.07 128	97.51 105	95.76 239	99.35 52	88.18 289	97.78 73	98.40 195	97.11 87	98.34 105	99.04 53	89.58 267	99.79 45	98.09 35	99.93 11	99.30 119

CR-MVSNet		93.29 293	92.79 291	94.78 288	95.44 359	88.15 290	96.18 174	97.20 280	84.94 358	94.10 315	98.57 98	77.67 347	99.39 224	95.17 163	95.81 357	96.81 347

RPMNet		94.68 246	94.60 243	94.90 280	95.44 359	88.15 290	96.18 174	98.86 111	97.43 74	94.10 315	98.49 106	79.40 339	99.76 62	95.69 128	95.81 357	96.81 347

EI-MVSNet		96.63 159	96.93 138	95.74 240	97.26 304	88.13 292	95.29 238	97.65 266	96.99 89	97.94 152	98.19 146	92.55 214	99.58 161	96.91 79	99.56 110	99.50 63

IterMVS-LS		96.92 138	97.29 117	95.79 238	98.51 169	88.13 292	95.10 245	98.66 163	96.99 89	98.46 91	98.68 88	92.55 214	99.74 77	96.91 79	99.79 53	99.50 63
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FA-MVS(test-final)		94.91 233	94.89 226	94.99 275	97.51 284	88.11 294	98.27 44	95.20 329	92.40 267	96.68 229	98.60 96	83.44 321	99.28 256	93.34 238	98.53 278	97.59 321

diffmvs		96.04 184	96.23 176	95.46 255	97.35 297	88.03 295	93.42 314	99.08 55	94.09 216	96.66 231	96.93 257	93.85 183	99.29 254	96.01 112	98.67 267	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		94.51 256	94.60 243	94.26 310	95.91 345	87.92 296	95.35 232	99.02 72	86.56 339	96.79 221	98.52 103	82.64 326	97.00 379	97.87 42	98.71 264	97.88 305

TinyColmap		96.00 187	96.34 173	94.96 277	97.90 235	87.91 297	94.13 289	98.49 183	94.41 203	98.16 126	97.76 194	96.29 108	98.68 329	90.52 297	99.42 164	98.30 269

tttt0517		93.31 292	92.56 299	95.57 247	98.71 141	87.86 298	97.44 100	87.17 388	95.79 148	97.47 179	96.84 263	64.12 389	99.81 37	96.20 101	99.32 190	99.02 179

WTY-MVS		93.55 286	93.00 286	95.19 264	97.81 246	87.86 298	93.89 300	96.00 310	89.02 311	94.07 317	95.44 326	86.27 300	99.33 243	87.69 337	96.82 342	98.39 256

jason		94.39 260	94.04 265	95.41 259	98.29 189	87.85 300	92.74 329	96.75 299	85.38 352	95.29 288	96.15 300	88.21 284	99.65 138	94.24 209	99.34 183	98.74 221
jason: jason.
MVSFormer		96.14 180	96.36 172	95.49 253	97.68 269	87.81 301	98.67 15	99.02 72	96.50 109	94.48 308	96.15 300	86.90 296	99.92 5	98.73 20	99.13 216	98.74 221

lupinMVS		93.77 277	93.28 279	95.24 262	97.68 269	87.81 301	92.12 342	96.05 308	84.52 361	94.48 308	95.06 331	86.90 296	99.63 144	93.62 233	99.13 216	98.27 273

D2MVS		95.18 222	95.17 213	95.21 263	97.76 260	87.76 303	94.15 286	97.94 246	89.77 304	96.99 210	97.68 204	87.45 292	99.14 278	95.03 176	99.81 48	98.74 221

testgi		96.07 182	96.50 166	94.80 286	99.26 60	87.69 304	95.96 194	98.58 176	95.08 180	98.02 144	96.25 296	97.92 20	97.60 373	88.68 326	98.74 260	99.11 164

v148		96.58 163	96.97 135	95.42 257	98.63 152	87.57 305	95.09 246	97.90 248	95.91 142	98.24 117	97.96 175	93.42 192	99.39 224	96.04 108	99.52 128	99.29 125

BH-untuned		94.69 244	94.75 235	94.52 299	97.95 232	87.53 306	94.07 291	97.01 289	93.99 218	97.10 198	95.65 318	92.65 211	98.95 305	87.60 339	96.74 345	97.09 333

Patchmatch-test		93.60 285	93.25 280	94.63 292	96.14 341	87.47 307	96.04 185	94.50 336	93.57 229	96.47 241	96.97 254	76.50 355	98.61 334	90.67 294	98.41 286	97.81 311

iter_conf05		93.65 283	93.05 282	95.46 255	96.13 342	87.45 308	95.95 196	98.22 215	92.66 260	97.04 206	97.89 183	63.52 391	99.72 88	96.19 102	99.82 47	99.21 139

BH-RMVSNet		94.56 252	94.44 254	94.91 278	97.57 279	87.44 309	93.78 305	96.26 306	93.69 226	96.41 244	96.50 285	92.10 227	99.00 296	85.96 350	97.71 314	98.31 267

PVSNet_BlendedMVS		95.02 231	94.93 223	95.27 261	97.79 255	87.40 310	94.14 288	98.68 158	88.94 313	94.51 306	98.01 171	93.04 199	99.30 250	89.77 310	99.49 140	99.11 164

PVSNet_Blended		93.96 274	93.65 273	94.91 278	97.79 255	87.40 310	91.43 351	98.68 158	84.50 362	94.51 306	94.48 344	93.04 199	99.30 250	89.77 310	98.61 274	98.02 296

PatchT		93.75 278	93.57 275	94.29 309	95.05 366	87.32 312	96.05 184	92.98 351	97.54 70	94.25 311	98.72 83	75.79 360	99.24 265	95.92 117	95.81 357	96.32 358

GA-MVS		92.83 300	92.15 304	94.87 282	96.97 315	87.27 313	90.03 372	96.12 307	91.83 275	94.05 318	94.57 339	76.01 359	98.97 304	92.46 255	97.34 332	98.36 263

baseline1		93.14 296	92.64 297	94.62 293	97.34 299	87.20 314	96.67 148	93.02 350	94.71 193	96.51 240	95.83 314	81.64 328	98.60 336	90.00 307	88.06 389	98.07 286

patch_mono-2		96.59 161	96.93 138	95.55 250	98.88 121	87.12 315	94.47 272	99.30 24	94.12 213	96.65 233	98.41 113	94.98 153	99.87 22	95.81 125	99.78 56	99.66 30

MS-PatchMatch		94.83 236	94.91 225	94.57 297	96.81 321	87.10 316	94.23 281	97.34 277	88.74 316	97.14 194	97.11 245	91.94 232	98.23 361	92.99 247	97.92 303	98.37 258

cl____		94.73 239	94.64 239	95.01 273	95.85 348	87.00 317	91.33 354	98.08 238	93.34 235	97.10 198	97.33 233	84.01 319	99.30 250	95.14 168	99.56 110	98.71 227

DIV-MVS_self_test		94.73 239	94.64 239	95.01 273	95.86 347	87.00 317	91.33 354	98.08 238	93.34 235	97.10 198	97.34 232	84.02 318	99.31 247	95.15 167	99.55 116	98.72 224

MVS		90.02 333	89.20 340	92.47 348	94.71 369	86.90 319	95.86 200	96.74 300	64.72 393	90.62 370	92.77 362	92.54 216	98.39 352	79.30 381	95.56 364	92.12 386

test0.0.03 1		90.11 332	89.21 339	92.83 341	93.89 381	86.87 320	91.74 348	88.74 384	92.02 270	94.71 302	91.14 381	73.92 366	94.48 390	83.75 371	92.94 378	97.16 332

test_cas_vis1_n_1920		95.34 214	95.67 201	94.35 306	98.21 199	86.83 321	95.61 216	99.26 27	90.45 294	98.17 125	98.96 61	84.43 315	98.31 358	96.74 82	99.17 211	97.90 303

TR-MVS		92.54 304	92.20 303	93.57 323	96.49 327	86.66 322	93.51 312	94.73 333	89.96 301	94.95 297	93.87 349	90.24 260	98.61 334	81.18 377	94.88 369	95.45 371

MVS_Test		96.27 175	96.79 148	94.73 290	96.94 318	86.63 323	96.18 174	98.33 204	94.94 186	96.07 262	98.28 132	95.25 144	99.26 260	97.21 67	97.90 305	98.30 269

MVSTER		94.21 265	93.93 269	95.05 271	95.83 349	86.46 324	95.18 243	97.65 266	92.41 266	97.94 152	98.00 173	72.39 374	99.58 161	96.36 95	99.56 110	99.12 161

miper_lstm_enhance		94.81 238	94.80 233	94.85 283	96.16 338	86.45 325	91.14 360	98.20 219	93.49 231	97.03 207	97.37 230	84.97 311	99.26 260	95.28 156	99.56 110	98.83 210

c3_l		95.20 221	95.32 208	94.83 285	96.19 336	86.43 326	91.83 347	98.35 203	93.47 232	97.36 183	97.26 237	88.69 277	99.28 256	95.41 153	99.36 175	98.78 215

USDC		94.56 252	94.57 248	94.55 298	97.78 258	86.43 326	92.75 327	98.65 168	85.96 343	96.91 217	97.93 180	90.82 247	98.74 320	90.71 292	99.59 102	98.47 250

miper_ehance_all_eth		94.69 244	94.70 236	94.64 291	95.77 351	86.22 328	91.32 356	98.24 213	91.67 276	97.05 205	96.65 276	88.39 282	99.22 269	94.88 181	98.34 287	98.49 249

eth_miper_zixun_eth		94.89 234	94.93 223	94.75 289	95.99 344	86.12 329	91.35 353	98.49 183	93.40 233	97.12 196	97.25 238	86.87 298	99.35 239	95.08 173	98.82 253	98.78 215

cl22		93.25 294	92.84 290	94.46 302	94.30 374	86.00 330	91.09 362	96.64 304	90.74 288	95.79 273	96.31 294	78.24 344	98.77 317	94.15 213	98.34 287	98.62 235

MG-MVS		94.08 271	94.00 266	94.32 307	97.09 312	85.89 331	93.19 321	95.96 312	92.52 262	94.93 299	97.51 215	89.54 268	98.77 317	87.52 342	97.71 314	98.31 267

ADS-MVSNet2		91.47 322	90.51 330	94.36 305	95.51 357	85.63 332	95.05 251	95.70 316	83.46 365	92.69 352	96.84 263	79.15 341	99.41 218	85.66 354	90.52 383	98.04 294

cascas		91.89 317	91.35 314	93.51 324	94.27 375	85.60 333	88.86 382	98.61 170	79.32 381	92.16 361	91.44 378	89.22 275	98.12 364	90.80 286	97.47 328	96.82 346

IterMVS-SCA-FT		95.86 192	96.19 178	94.85 283	97.68 269	85.53 334	92.42 337	97.63 270	96.99 89	98.36 102	98.54 102	87.94 285	99.75 68	97.07 75	99.08 224	99.27 130

thisisatest0515		90.43 330	89.18 342	94.17 313	97.07 313	85.44 335	89.75 378	87.58 386	88.28 321	93.69 329	91.72 375	65.27 388	99.58 161	90.59 295	98.67 267	97.50 325

pmmvs3		90.00 334	88.90 344	93.32 326	94.20 378	85.34 336	91.25 357	92.56 359	78.59 383	93.82 322	95.17 328	67.36 387	98.69 326	89.08 320	98.03 300	95.92 362

BH-w/o		92.14 311	91.94 305	92.73 343	97.13 311	85.30 337	92.46 334	95.64 318	89.33 307	94.21 312	92.74 363	89.60 266	98.24 360	81.68 375	94.66 371	94.66 376

miper_enhance_ethall		93.14 296	92.78 293	94.20 311	93.65 383	85.29 338	89.97 373	97.85 251	85.05 354	96.15 261	94.56 340	85.74 304	99.14 278	93.74 228	98.34 287	98.17 282

DeepMVS_CX				77.17 377	90.94 395	85.28 339		74.08 400	52.51 394	80.87 395	88.03 388	75.25 362	70.63 397	59.23 397	84.94 392	75.62 392

MVE	73.61 22	86.48 358	85.92 359	88.18 373	96.23 334	85.28 339	81.78 391	75.79 397	86.01 342	82.53 393	91.88 373	92.74 207	87.47 396	71.42 393	94.86 370	91.78 387
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
1314		92.38 306	92.30 301	92.64 344	95.42 361	85.15 341	95.86 200	96.97 291	85.40 351	90.62 370	93.06 358	91.12 242	97.80 370	86.74 347	95.49 365	94.97 375

MDA-MVSNet_test_wron		94.73 239	94.83 231	94.42 303	97.48 286	85.15 341	90.28 371	95.87 314	92.52 262	97.48 177	97.76 194	91.92 233	99.17 275	93.32 239	96.80 344	98.94 189

YYNet1		94.73 239	94.84 229	94.41 304	97.47 290	85.09 343	90.29 370	95.85 315	92.52 262	97.53 171	97.76 194	91.97 230	99.18 271	93.31 240	96.86 339	98.95 187

PAPM		87.64 354	85.84 360	93.04 334	96.54 325	84.99 344	88.42 383	95.57 322	79.52 380	83.82 391	93.05 359	80.57 336	98.41 350	62.29 395	92.79 379	95.71 366

PS-MVSNAJ		94.10 269	94.47 251	93.00 336	97.35 297	84.88 345	91.86 346	97.84 253	91.96 272	94.17 313	92.50 368	95.82 122	99.71 104	91.27 273	97.48 326	94.40 378

test_vis1_n_1920		95.77 195	96.41 169	93.85 316	98.55 163	84.86 346	95.91 199	99.71 4	92.72 259	97.67 167	98.90 70	87.44 293	98.73 321	97.96 39	98.85 249	97.96 299

xiu_mvs_v2_base		94.22 263	94.63 241	92.99 337	97.32 302	84.84 347	92.12 342	97.84 253	91.96 272	94.17 313	93.43 351	96.07 114	99.71 104	91.27 273	97.48 326	94.42 377

IB-MVS	85.98 20	88.63 347	86.95 357	93.68 321	95.12 365	84.82 348	90.85 364	90.17 379	87.55 328	88.48 384	91.34 379	58.01 393	99.59 159	87.24 345	93.80 377	96.63 353
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		92.03 315	91.43 312	93.82 317	98.19 202	84.61 349	96.27 166	90.39 375	96.81 95	96.37 246	93.11 353	73.44 372	99.49 190	80.32 379	97.95 302	97.36 328

thres100view900		91.76 319	91.26 318	93.26 328	98.21 199	84.50 350	96.39 156	90.39 375	96.87 93	96.33 247	93.08 357	73.44 372	99.42 209	78.85 383	97.74 311	95.85 363

gg-mvs-nofinetune		88.28 350	86.96 356	92.23 352	92.84 390	84.44 351	98.19 52	74.60 398	99.08 10	87.01 389	99.47 11	56.93 394	98.23 361	78.91 382	95.61 363	94.01 380

tfpn200view9		91.55 321	91.00 320	93.21 331	98.02 221	84.35 352	95.70 206	90.79 372	96.26 119	95.90 271	92.13 371	73.62 369	99.42 209	78.85 383	97.74 311	95.85 363

thres400		91.68 320	91.00 320	93.71 320	98.02 221	84.35 352	95.70 206	90.79 372	96.26 119	95.90 271	92.13 371	73.62 369	99.42 209	78.85 383	97.74 311	97.36 328

testing3		89.72 340	88.26 348	94.10 314	97.66 273	84.30 354	94.80 260	88.25 385	94.66 194	95.07 292	92.51 367	41.15 402	99.43 207	91.81 265	98.44 284	98.55 242

GG-mvs-BLEND				90.60 362	91.00 394	84.21 355	98.23 46	72.63 401		82.76 392	84.11 393	56.14 397	96.79 382	72.20 391	92.09 382	90.78 390

dcpmvs_2		97.12 126	97.99 54	94.51 300	99.11 95	84.00 356	97.75 77	99.65 9	97.38 80	99.14 37	98.42 112	95.16 146	99.96 2	95.52 139	99.78 56	99.58 40

thres200		91.00 327	90.42 331	92.77 342	97.47 290	83.98 357	94.01 293	91.18 370	95.12 179	95.44 284	91.21 380	73.93 365	99.31 247	77.76 386	97.63 321	95.01 374

IterMVS		95.42 212	95.83 196	94.20 311	97.52 283	83.78 358	92.41 338	97.47 275	95.49 163	98.06 139	98.49 106	87.94 285	99.58 161	96.02 110	99.02 231	99.23 137
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DSMNet-mixed		92.19 310	91.83 307	93.25 329	96.18 337	83.68 359	96.27 166	93.68 343	76.97 388	92.54 358	99.18 39	89.20 276	98.55 340	83.88 368	98.60 276	97.51 323

ECVR-MVS		94.37 261	94.48 250	94.05 315	98.95 113	83.10 360	98.31 39	82.48 395	96.20 122	98.23 118	99.16 43	81.18 332	99.66 136	95.95 115	99.83 43	99.38 105

baseline2		89.65 341	88.44 347	93.25 329	95.62 355	82.71 361	93.82 302	85.94 391	88.89 314	87.35 388	92.54 366	71.23 377	99.33 243	86.01 349	94.60 373	97.72 313

Syy-MVS		92.09 313	91.80 309	92.93 340	95.19 363	82.65 362	92.46 334	91.35 366	90.67 291	91.76 365	87.61 389	85.64 306	98.50 344	94.73 191	96.84 340	97.65 316

EPNet_dtu		91.39 323	90.75 326	93.31 327	90.48 396	82.61 363	94.80 260	92.88 352	93.39 234	81.74 394	94.90 336	81.36 331	99.11 284	88.28 331	98.87 246	98.21 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EU-MVSNet		94.25 262	94.47 251	93.60 322	98.14 214	82.60 364	97.24 110	92.72 355	85.08 353	98.48 88	98.94 64	82.59 327	98.76 319	97.47 61	99.53 123	99.44 95

ADS-MVSNet		90.95 328	90.26 332	93.04 334	95.51 357	82.37 365	95.05 251	93.41 347	83.46 365	92.69 352	96.84 263	79.15 341	98.70 325	85.66 354	90.52 383	98.04 294

ppachtmachnet_test		94.49 257	94.84 229	93.46 325	96.16 338	82.10 366	90.59 367	97.48 274	90.53 293	97.01 209	97.59 209	91.01 244	99.36 235	93.97 222	99.18 210	98.94 189

KD-MVS_2432*1600		88.93 345	87.74 350	92.49 346	88.04 397	81.99 367	89.63 379	95.62 319	91.35 281	95.06 293	93.11 353	56.58 395	98.63 332	85.19 359	95.07 366	96.85 343

miper_refine_blended		88.93 345	87.74 350	92.49 346	88.04 397	81.99 367	89.63 379	95.62 319	91.35 281	95.06 293	93.11 353	56.58 395	98.63 332	85.19 359	95.07 366	96.85 343

test1111		94.53 255	94.81 232	93.72 319	99.06 102	81.94 369	98.31 39	83.87 394	96.37 114	98.49 86	99.17 42	81.49 329	99.73 83	96.64 84	99.86 31	99.49 71

mvs_anonymous		95.36 213	96.07 184	93.21 331	96.29 331	81.56 370	94.60 269	97.66 264	93.30 237	96.95 214	98.91 69	93.03 201	99.38 227	96.60 86	97.30 334	98.69 228

SCA		93.38 291	93.52 276	92.96 338	96.24 332	81.40 371	93.24 319	94.00 340	91.58 279	94.57 304	96.97 254	87.94 285	99.42 209	89.47 314	97.66 319	98.06 290

our_test_3		94.20 267	94.58 246	93.07 333	96.16 338	81.20 372	90.42 369	96.84 294	90.72 289	97.14 194	97.13 243	90.47 251	99.11 284	94.04 219	98.25 291	98.91 197

CHOSEN 280x420		89.98 335	89.19 341	92.37 350	95.60 356	81.13 373	86.22 386	97.09 286	81.44 373	87.44 387	93.15 352	73.99 364	99.47 195	88.69 325	99.07 226	96.52 355

PMMVS2		93.66 282	94.07 264	92.45 349	97.57 279	80.67 374	86.46 385	96.00 310	93.99 218	97.10 198	97.38 228	89.90 262	97.82 369	88.76 323	99.47 146	98.86 208

new-patchmatchnet		95.67 199	96.58 157	92.94 339	97.48 286	80.21 375	92.96 323	98.19 224	94.83 189	98.82 59	98.79 76	93.31 194	99.51 184	95.83 123	99.04 230	99.12 161

PatchmatchNet		91.98 316	91.87 306	92.30 351	94.60 371	79.71 376	95.12 244	93.59 346	89.52 305	93.61 331	97.02 251	77.94 345	99.18 271	90.84 284	94.57 374	98.01 297
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WAC-MVS						79.32 377								85.41 357

myMVS_eth3d		87.16 357	85.61 361	91.82 355	95.19 363	79.32 377	92.46 334	91.35 366	90.67 291	91.76 365	87.61 389	41.96 401	98.50 344	82.66 373	96.84 340	97.65 316

EPMVS		89.26 343	88.55 346	91.39 358	92.36 392	79.11 379	95.65 212	79.86 396	88.60 317	93.12 344	96.53 282	70.73 380	98.10 365	90.75 288	89.32 387	96.98 336

SSC-MVS		95.92 189	97.03 132	92.58 345	99.28 58	78.39 380	96.68 146	95.12 330	98.90 19	99.11 39	98.66 89	91.36 239	99.68 124	95.00 177	99.16 212	99.67 28

tpm		91.08 326	90.85 324	91.75 356	95.33 362	78.09 381	95.03 253	91.27 369	88.75 315	93.53 334	97.40 222	71.24 376	99.30 250	91.25 275	93.87 376	97.87 306

PVSNet	86.72 19	91.10 325	90.97 322	91.49 357	97.56 281	78.04 382	87.17 384	94.60 335	84.65 360	92.34 359	92.20 370	87.37 294	98.47 347	85.17 361	97.69 316	97.96 299

CostFormer		89.75 339	89.25 337	91.26 359	94.69 370	78.00 383	95.32 235	91.98 362	81.50 372	90.55 372	96.96 256	71.06 378	98.89 307	88.59 327	92.63 380	96.87 341

E-PMN		89.52 342	89.78 335	88.73 369	93.14 386	77.61 384	83.26 389	92.02 361	94.82 190	93.71 327	93.11 353	75.31 361	96.81 381	85.81 351	96.81 343	91.77 388

dmvs_testset		87.30 355	86.99 355	88.24 372	96.71 322	77.48 385	94.68 266	86.81 390	92.64 261	89.61 379	87.01 391	85.91 303	93.12 392	61.04 396	88.49 388	94.13 379

EMVS		89.06 344	89.22 338	88.61 370	93.00 388	77.34 386	82.91 390	90.92 371	94.64 196	92.63 356	91.81 374	76.30 357	97.02 378	83.83 369	96.90 338	91.48 389

tpm2		88.47 348	87.69 352	90.79 361	94.98 367	77.34 386	95.09 246	91.83 363	77.51 387	89.40 380	96.41 288	67.83 386	98.73 321	83.58 372	92.60 381	96.29 359

WB-MVS		95.50 205	96.62 154	92.11 353	99.21 76	77.26 388	96.12 180	95.40 327	98.62 26	98.84 57	98.26 137	91.08 243	99.50 185	93.37 236	98.70 265	99.58 40

test2506		89.86 338	89.16 343	91.97 354	98.95 113	76.83 389	98.54 23	61.07 402	96.20 122	97.07 204	99.16 43	55.19 399	99.69 119	96.43 93	99.83 43	99.38 105

tpmvs		90.79 329	90.87 323	90.57 363	92.75 391	76.30 390	95.79 203	93.64 345	91.04 286	91.91 363	96.26 295	77.19 353	98.86 311	89.38 316	89.85 386	96.56 354

tpm cat1		88.01 352	87.33 353	90.05 366	94.48 372	76.28 391	94.47 272	94.35 338	73.84 392	89.26 381	95.61 321	73.64 368	98.30 359	84.13 366	86.20 391	95.57 370

CVMVSNet		92.33 308	92.79 291	90.95 360	97.26 304	75.84 392	95.29 238	92.33 360	81.86 369	96.27 252	98.19 146	81.44 330	98.46 348	94.23 210	98.29 290	98.55 242

test-LLR		89.97 336	89.90 334	90.16 364	94.24 376	74.98 393	89.89 374	89.06 382	92.02 270	89.97 377	90.77 384	73.92 366	98.57 337	91.88 262	97.36 330	96.92 338

test-mter		87.92 353	87.17 354	90.16 364	94.24 376	74.98 393	89.89 374	89.06 382	86.44 340	89.97 377	90.77 384	54.96 400	98.57 337	91.88 262	97.36 330	96.92 338

PVSNet_0	81.89 21	84.49 359	83.21 362	88.34 371	95.76 352	74.97 395	83.49 388	92.70 356	78.47 384	87.94 385	86.90 392	83.38 323	96.63 385	73.44 390	66.86 396	93.40 383

MDTV_nov1_ep13			91.28 315		94.31 373	73.51 396	94.80 260	93.16 349	86.75 338	93.45 337	97.40 222	76.37 356	98.55 340	88.85 322	96.43 350

TESTMET0.1,1		87.20 356	86.57 358	89.07 368	93.62 384	72.84 397	89.89 374	87.01 389	85.46 350	89.12 382	90.20 386	56.00 398	97.72 371	90.91 282	96.92 336	96.64 351

tpmrst		90.31 331	90.61 329	89.41 367	94.06 379	72.37 398	95.06 250	93.69 341	88.01 324	92.32 360	96.86 261	77.45 349	98.82 312	91.04 278	87.01 390	97.04 335

gm-plane-assit					91.79 393	71.40 399			81.67 370		90.11 387		98.99 298	84.86 363

dp		88.08 351	88.05 349	88.16 374	92.85 389	68.81 400	94.17 284	92.88 352	85.47 349	91.38 368	96.14 302	68.87 384	98.81 314	86.88 346	83.80 393	96.87 341

MVS-HIRNet		88.40 349	90.20 333	82.99 376	97.01 314	60.04 401	93.11 322	85.61 392	84.45 363	88.72 383	99.09 50	84.72 313	98.23 361	82.52 374	96.59 349	90.69 391

MDTV_nov1_ep13_2view						57.28 402	94.89 257		80.59 376	94.02 319		78.66 343		85.50 356		97.82 309

tmp_tt		57.23 362	62.50 365	41.44 379	34.77 401	49.21 403	83.93 387	60.22 403	15.31 395	71.11 396	79.37 394	70.09 382	44.86 398	64.76 394	82.93 394	30.25 394

test_method		66.88 361	66.13 364	69.11 378	62.68 400	25.73 404	49.76 392	96.04 309	14.32 396	64.27 397	91.69 376	73.45 371	88.05 395	76.06 388	66.94 395	93.54 381

test123		12.59 364	15.49 367	3.87 380	6.07 402	2.55 405	90.75 366	2.59 405	2.52 398	5.20 400	13.02 397	4.96 403	1.85 400	5.20 398	9.09 397	7.23 395

testmvs		12.33 365	15.23 368	3.64 381	5.77 403	2.23 406	88.99 381	3.62 404	2.30 399	5.29 399	13.09 396	4.52 404	1.95 399	5.16 399	8.32 398	6.75 396

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

cdsmvs_eth3d_5k		24.22 363	32.30 366	0.00 382	0.00 404	0.00 407	0.00 393	98.10 235	0.00 400	0.00 401	95.06 331	97.54 37	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		7.98 366	10.65 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	95.82 122	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		7.91 367	10.55 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	94.94 333	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

PC_three_1452									87.24 330	98.37 99	97.44 219	97.00 63	96.78 383	92.01 258	99.25 201	99.21 139

eth-test2					0.00 404

eth-test					0.00 404

test_241102_TWO								98.83 124	96.11 127	98.62 74	98.24 139	96.92 71	99.72 88	95.44 147	99.49 140	99.49 71

9.14			96.69 151		98.53 166		96.02 187	98.98 87	93.23 239	97.18 192	97.46 217	96.47 98	99.62 149	92.99 247	99.32 190

test_0728_THIRD									96.62 99	98.40 96	98.28 132	97.10 54	99.71 104	95.70 126	99.62 91	99.58 40

GSMVS																98.06 290

sam_mvs1												77.80 346				98.06 290

sam_mvs												77.38 350

MTGPA								98.73 146

test_post1							94.98 255				10.37 399	76.21 358	99.04 292	89.47 314

test_post											10.87 398	76.83 354	99.07 289

patchmatchnet-post											96.84 263	77.36 351	99.42 209

MTMP							96.55 150	74.60 398

test9_res														91.29 272	98.89 245	99.00 180

agg_prior2														90.34 303	98.90 242	99.10 168

test_prior2							93.33 318		94.21 208	94.02 319	96.25 296	93.64 188		91.90 261	98.96 235

旧先验2							93.35 317		77.95 386	95.77 277			98.67 330	90.74 291

新几何2							93.43 313

无先验							93.20 320	97.91 247	80.78 375				99.40 220	87.71 336		97.94 301

原ACMM2							92.82 325

testdata2													99.46 198	87.84 334

segment_acmp												95.34 141

testdata1							92.77 326		93.78 223

plane_prior5								98.75 143					99.46 198	92.59 252	99.20 206	99.28 126

plane_prior4											96.77 269

plane_prior2							96.50 152		96.36 115

plane_prior1					98.49 173

n2								0.00 406

nn								0.00 406

door-mid								98.17 225

test11								98.08 238

door								97.81 256

HQP-NCC					97.85 237		94.26 276		93.18 242	92.86 348

ACMP_Plane					97.85 237		94.26 276		93.18 242	92.86 348

BP-MVS														90.51 298

HQP4-MVS										92.87 347			99.23 267			99.06 173

HQP3-MVS								98.43 189							98.74 260

HQP2-MVS												90.33 255

ACMMP++_ref															99.52 128

ACMMP++															99.55 116

Test By Simon												94.51 167

High-resolution multi-view benchmark