Full metadata record
| DC pole | Hodnota | Jazyk |
|---|---|---|
| dc.contributor.author | Le Clerc, François | |
| dc.contributor.author | Sun, Hao | |
| dc.contributor.editor | Skala, Václav | |
| dc.date.accessioned | 2020-07-27T07:54:30Z | |
| dc.date.available | 2020-07-27T07:54:30Z | |
| dc.date.issued | 2020 | |
| dc.identifier.citation | WSCG 2020: full papers proceedings: 28th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 1-10. | en |
| dc.identifier.isbn | 978-80-86943-35-0 | |
| dc.identifier.issn | 2464–4617 (print) | |
| dc.identifier.issn | 2464–4625 (CD-ROM) | |
| dc.identifier.uri | http://wscg.zcu.cz/WSCG2020/2020-CSRN-3001.pdf | |
| dc.identifier.uri | http://hdl.handle.net/11025/38445 | |
| dc.format | 10 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.language.iso | en | en |
| dc.publisher | Václav Skala - UNION Agency | cs |
| dc.relation.ispartofseries | WSCG 2020: full papers proceedings | en |
| dc.rights | © Václav Skala - UNION Agency | cs |
| dc.subject | geometrické hluboké učení | cs |
| dc.subject | konvoluční neuronové sítě | cs |
| dc.subject | přizpůsobení tvaru | cs |
| dc.subject | 3D mřížka | cs |
| dc.title | Memory-Friendly Deep Mesh Registration | en |
| dc.type | conferenceObject | en |
| dc.type | konferenční příspěvek | cs |
| dc.rights.access | openAccess | en |
| dc.type.version | publishedVersion | en |
| dc.description.abstract-translated | Processing 3D meshes using convolutional neural networks requires convolutions to operate on features sampled on non-Euclidean manifolds. To this purpose, spatial-domain approaches applicable to meshes with different topologies locally map feature values in vertex neighborhoods to Euclidean ’patches’ that provide consistent inputs to the convolution filters around all mesh vertices. This generalization of the convolution operator significantly increases the memory footprint of convolutional layers and sets a practical limit to network depths on the available GPU hardware. We propose a memory-optimized convolution scheme that mitigates the issue and allows more convolutional layers to be included in a network for a given memory budget. The experimental evaluation of mesh registration accuracy on datasets of human face and body scans shows that deeper networks bring substantial performance improvements and demonstrate the benefits of our scheme. Our results outperform the state of art. | en |
| dc.subject.translated | geometric deep learning | en |
| dc.subject.translated | convolutional neural networks | en |
| dc.subject.translated | shape matching | en |
| dc.subject.translated | 3D mesh | en |
| dc.identifier.doi | https://doi.org/10.24132/CSRN.2020.3001.1 | |
| dc.type.status | Peer-reviewed | en |
| Vyskytuje se v kolekcích: | WSCG 2020: Full Papers Proceedings | |
Soubory připojené k záznamu:
| Soubor | Popis | Velikost | Formát | |
|---|---|---|---|---|
| E29.pdf | Plný text | 5,59 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/38445Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.