Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Azizi, Amir | - |
dc.contributor.author | Charambous, Panayiotis | - |
dc.contributor.author | Chrysanthou, Yiorgos | - |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2024-07-27T18:31:28Z | - |
dc.date.available | 2024-07-27T18:31:28Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | WSCG 2024: full papers proceedings: 32. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 107-116. | cs_CZ |
dc.identifier.issn | 2464–4625 (online) | - |
dc.identifier.issn | 2464–4617 (print) | - |
dc.identifier.uri | http://hdl.handle.net/11025/57383 | - |
dc.format | 10 s. | cs_CZ |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | cs_CZ |
dc.publisher | Václav Skala - UNION Agency | cs_CZ |
dc.subject | zpracování obrazu | cs_CZ |
dc.subject | rekonstrukce obrazu | cs_CZ |
dc.subject | analýza hlavních komponent | cs_CZ |
dc.subject | konvoluční variační automatické kodéry | cs_CZ |
dc.title | Improving Image Reconstruction using Incremental PCA-Embedded Convolutional Variational Auto-Encoder | cs_CZ |
dc.type | conferenceObject | cs_CZ |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | Traditional image reconstruction methods often face challenges like noise, artifacts, and blurriness, requiring handcrafted algorithms for effective resolution. In contrast, deep learning techniques, notably Convolutional Neural Networks (CNNs) and Variational Autoencoders (VAEs), present more robust alternatives. This paper presents a novel and efficient approach for image reconstruction employing Convolutional Variational Autoen coders (CVAEs). We use Incremental Principal Component Analysis (IPCA) to enhance efficiency by discerning and capturing significant features within the latent space. This model is integrated into both the encoder and sampling stages of CVAEs, refining their capability to generate high-fidelity images. Our incremental strategy mitigates scalability issues associated with traditional PCA while preserving the model’s aptitude for identifying crucial image features. Experimental validation utilizing the MNIST dataset showcases noteworthy reductions in processing time and enhancements in image quality, underscoring the efficacy and potential applicability of our model for large-scale image generation tasks. | cs_CZ |
dc.subject.translated | image processing | cs_CZ |
dc.subject.translated | image reconstruction | cs_CZ |
dc.subject.translated | principal component analysis | cs_CZ |
dc.subject.translated | Convolutional Variational Auto-encoders | cs_CZ |
dc.type.status | Peer reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2024: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
A97-2024.pdf | Plný text | 10,53 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/57383
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.