Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384261720> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4384261720 abstract "Despite the impressive performance obtained by recent single-image hand modeling techniques, they lack the capability to capture sufficient details of the 3D hand mesh. This deficiency greatly limits their applications when high-fidelity hand modeling is required, e.g., personalized hand modeling. To address this problem, we design a frequency split network to generate 3D hand mesh using different frequency bands in a coarse-to-fine manner. To capture high-frequency personalized details, we transform the 3D mesh into the frequency domain, and propose a novel frequency decomposition loss to supervise each frequency component. By leveraging such a coarse-to-fine scheme, hand details that correspond to the higher frequency domain can be preserved. In addition, the proposed network is scalable, and can stop the inference at any resolution level to accommodate different hardware with varying computational powers. To quantitatively evaluate the performance of our method in terms of recovering personalized shape details, we introduce a new evaluation metric named Mean Signal-to-Noise Ratio (MSNR) to measure the signal-to-noise ratio of each mesh frequency component. Extensive experiments demonstrate that our approach generates fine-grained details for high-fidelity 3D hand reconstruction, and our evaluation metric is more effective for measuring mesh details compared with traditional metrics." @default.
- W4384261720 created "2023-07-14" @default.
- W4384261720 creator A5024925731 @default.
- W4384261720 creator A5047400466 @default.
- W4384261720 creator A5055403026 @default.
- W4384261720 creator A5068376674 @default.
- W4384261720 creator A5071710737 @default.
- W4384261720 creator A5084634014 @default.
- W4384261720 creator A5085245110 @default.
- W4384261720 date "2023-07-08" @default.
- W4384261720 modified "2023-10-16" @default.
- W4384261720 title "High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition" @default.
- W4384261720 doi "https://doi.org/10.48550/arxiv.2307.05541" @default.
- W4384261720 hasPublicationYear "2023" @default.
- W4384261720 type Work @default.
- W4384261720 citedByCount "0" @default.
- W4384261720 crossrefType "posted-content" @default.
- W4384261720 hasAuthorship W4384261720A5024925731 @default.
- W4384261720 hasAuthorship W4384261720A5047400466 @default.
- W4384261720 hasAuthorship W4384261720A5055403026 @default.
- W4384261720 hasAuthorship W4384261720A5068376674 @default.
- W4384261720 hasAuthorship W4384261720A5071710737 @default.
- W4384261720 hasAuthorship W4384261720A5084634014 @default.
- W4384261720 hasAuthorship W4384261720A5085245110 @default.
- W4384261720 hasBestOaLocation W43842617201 @default.
- W4384261720 hasConcept C113364801 @default.
- W4384261720 hasConcept C113775141 @default.
- W4384261720 hasConcept C11413529 @default.
- W4384261720 hasConcept C121332964 @default.
- W4384261720 hasConcept C121684516 @default.
- W4384261720 hasConcept C132525143 @default.
- W4384261720 hasConcept C154945302 @default.
- W4384261720 hasConcept C162324750 @default.
- W4384261720 hasConcept C168167062 @default.
- W4384261720 hasConcept C176217482 @default.
- W4384261720 hasConcept C19118579 @default.
- W4384261720 hasConcept C21547014 @default.
- W4384261720 hasConcept C24890656 @default.
- W4384261720 hasConcept C2776214188 @default.
- W4384261720 hasConcept C2776459999 @default.
- W4384261720 hasConcept C31487907 @default.
- W4384261720 hasConcept C31972630 @default.
- W4384261720 hasConcept C41008148 @default.
- W4384261720 hasConcept C48044578 @default.
- W4384261720 hasConcept C76155785 @default.
- W4384261720 hasConcept C77088390 @default.
- W4384261720 hasConcept C80444323 @default.
- W4384261720 hasConcept C97355855 @default.
- W4384261720 hasConceptScore W4384261720C113364801 @default.
- W4384261720 hasConceptScore W4384261720C113775141 @default.
- W4384261720 hasConceptScore W4384261720C11413529 @default.
- W4384261720 hasConceptScore W4384261720C121332964 @default.
- W4384261720 hasConceptScore W4384261720C121684516 @default.
- W4384261720 hasConceptScore W4384261720C132525143 @default.
- W4384261720 hasConceptScore W4384261720C154945302 @default.
- W4384261720 hasConceptScore W4384261720C162324750 @default.
- W4384261720 hasConceptScore W4384261720C168167062 @default.
- W4384261720 hasConceptScore W4384261720C176217482 @default.
- W4384261720 hasConceptScore W4384261720C19118579 @default.
- W4384261720 hasConceptScore W4384261720C21547014 @default.
- W4384261720 hasConceptScore W4384261720C24890656 @default.
- W4384261720 hasConceptScore W4384261720C2776214188 @default.
- W4384261720 hasConceptScore W4384261720C2776459999 @default.
- W4384261720 hasConceptScore W4384261720C31487907 @default.
- W4384261720 hasConceptScore W4384261720C31972630 @default.
- W4384261720 hasConceptScore W4384261720C41008148 @default.
- W4384261720 hasConceptScore W4384261720C48044578 @default.
- W4384261720 hasConceptScore W4384261720C76155785 @default.
- W4384261720 hasConceptScore W4384261720C77088390 @default.
- W4384261720 hasConceptScore W4384261720C80444323 @default.
- W4384261720 hasConceptScore W4384261720C97355855 @default.
- W4384261720 hasLocation W43842617201 @default.
- W4384261720 hasOpenAccess W4384261720 @default.
- W4384261720 hasPrimaryLocation W43842617201 @default.
- W4384261720 hasRelatedWork W12463128 @default.
- W4384261720 hasRelatedWork W2062515146 @default.
- W4384261720 hasRelatedWork W2079850795 @default.
- W4384261720 hasRelatedWork W2170445277 @default.
- W4384261720 hasRelatedWork W2607045699 @default.
- W4384261720 hasRelatedWork W2756016502 @default.
- W4384261720 hasRelatedWork W2952631742 @default.
- W4384261720 hasRelatedWork W3136652852 @default.
- W4384261720 hasRelatedWork W4287687954 @default.
- W4384261720 hasRelatedWork W1954515982 @default.
- W4384261720 isParatext "false" @default.
- W4384261720 isRetracted "false" @default.
- W4384261720 workType "article" @default.