Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Erzar, Blaž | |
dc.contributor.author | Lesar, Žiga | |
dc.contributor.author | Marolt, Matija | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2023-10-17T15:32:52Z | |
dc.date.available | 2023-10-17T15:32:52Z | |
dc.date.issued | 2023 | |
dc.identifier.citation | WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 204-212. | en |
dc.identifier.isbn | 978-80-86943-32-9 | |
dc.identifier.issn | 2464–4617 (print) | |
dc.identifier.issn | 2464–4625 (CD/DVD) | |
dc.identifier.uri | http://hdl.handle.net/11025/54426 | |
dc.format | 9 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | en |
dc.rights | © Václav Skala - UNION Agency | en |
dc.subject | rozpoznávání obrazu | cs |
dc.subject | numerická interpolace | cs |
dc.subject | vícesíťová metoda | cs |
dc.subject | konvoluční neuronové sítě | cs |
dc.subject | automatický kodér | cs |
dc.title | Fast Incremental Image Reconstruction with CNN-enhanced Poisson Interpolation | en |
dc.type | konferenční příspěvek | cs |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | We present a novel image reconstruction method from scattered data based on multigrid relaxation of the Poisson equation and convolutional neural networks (CNN). We first formulate the image reconstruction problem as a Poisson equation with irregular boundary conditions, then propose a fast multigrid method for solving such an equation, and finally enhance the reconstructed image with a CNN to recover the details. The method works incrementally so that additional points can be added, and the amount of points does not affect the reconstruction speed. Furthermore, the multigrid and CNN techniques ensure that the output image resolution has only minor impact on the reconstruction speed. We evaluated the method on the CompCars dataset, where it achieves up to 40% error reduction compared to a reconstruction-only approach and 9% compared to a CNN-only approach. | en |
dc.subject.translated | image recognition | en |
dc.subject.translated | numerical interpolation | en |
dc.subject.translated | multigrid method | en |
dc.subject.translated | convolutional neural networks | en |
dc.subject.translated | autoencoder | en |
dc.identifier.doi | https://www.doi.org/10.24132/CSRN.3301.24 | |
dc.type.status | Peer-reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2023: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
F47-full.pdf | Plný text | 1,97 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/54426
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.