Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Barzel, Shir | |
dc.contributor.author | Salhov, Moshe | |
dc.contributor.author | Lindenbaum, Ofir | |
dc.contributor.author | Averbuch, Amir | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2024-07-24T19:16:58Z | - |
dc.date.available | 2024-07-24T19:16:58Z | - |
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. 13-22. | en |
dc.identifier.issn | 2464–4625 (online) | |
dc.identifier.issn | 2464–4617 (print) | |
dc.identifier.uri | http://hdl.handle.net/11025/57373 | |
dc.format | 10 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 | cs_CZ |
dc.subject | barevný prostor CIE-XYZ | cs |
dc.subject | sRGB | cs |
dc.subject | rekonstrukce obrazu | cs |
dc.subject | samokontrolované učení | cs |
dc.subject | nezpracovaný obraz | cs |
dc.subject | Macbeth ColorChecker | cs |
dc.title | SEL-CIE: Self-Supervised Learning Framework for CIE-XYZ Reconstruction from Non-Linear sRGB Images | en |
dc.type | konferenční příspěvek | cs |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | Modern cameras typically offer two types of image states: a minimally processed linear raw RGB image repre senting the raw sensor data, and a highly-processed non-linear image state, such as the sRGB state. The CIE-XYZ color space is a device-independent linear space used as part of the camera pipeline and can be helpful for com puter vision tasks, such as image deblurring, dehazing, and color recognition tasks in medical applications, where color accuracy is important. However, images are usually saved in non-linear states, and achieving CIE-XYZ color images using conventional methods is not always possible. To tackle this issue, classical methodologies have been developed that focus on reversing the acquisition pipeline. More recently, supervised learning has been employed, using paired CIE-XYZ and sRGB representations of identical images. However, obtaining a large-scale dataset of CIE-XYZ and sRGB pairs can be challenging. To overcome this limitation and mitigate the reliance on large amounts of paired data, self-supervised learning (SSL) can be utilized as a substitute for relying solely on paired data. This paper proposes a framework for using SSL methods alongside paired data to reconstruct CIE-XYZ images and re-render sRGB images, outperforming existing approaches. The proposed framework is applied to the sRGB2XYZ dataset | en |
dc.subject.translated | CIE-XYZ Color Space | en |
dc.subject.translated | sRGB | en |
dc.subject.translated | image reconstruction | en |
dc.subject.translated | Self-Supervised Learning | en |
dc.subject.translated | raw image | en |
dc.subject.translated | Macbeth ColorChecker | en |
dc.identifier.doi | https://doi.org/10.24132/10.24132/CSRN.3401.2 | |
dc.type.status | Peer reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2024: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
A13-2024.pdf | Plný text | 6,35 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/57373
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.