Title: | SEL-CIE: Self-Supervised Learning Framework for CIE-XYZ Reconstruction from Non-Linear sRGB Images |
Authors: | Barzel, Shir Salhov, Moshe Lindenbaum, Ofir Averbuch, Amir |
Citation: | WSCG 2024: full papers proceedings: 32. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 13-22. |
Issue Date: | 2024 |
Publisher: | Václav Skala - UNION Agency |
Document type: | konferenční příspěvek conferenceObject |
URI: | http://hdl.handle.net/11025/57373 |
ISSN: | 2464–4625 (online) 2464–4617 (print) |
Keywords: | barevný prostor CIE-XYZ;sRGB;rekonstrukce obrazu;samokontrolované učení;nezpracovaný obraz;Macbeth ColorChecker |
Keywords in different language: | CIE-XYZ Color Space;sRGB;image reconstruction;Self-Supervised Learning;raw image;Macbeth ColorChecker |
Abstract in different language: | 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 |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | WSCG 2024: Full Papers Proceedings |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
A13-2024.pdf | Plný text | 6,35 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/57373
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.