SEL-CIE: Knowledge-Guided Self-Supervised Learning Framework for CIE-XYZ Reconstruction from Non-Linear sRGB Images

TL;DR

This paper introduces SEL-CIE, a self-supervised learning framework that reconstructs CIE-XYZ images from non-linear sRGB images, reducing the need for large paired datasets and improving accuracy in color-critical applications.

Contribution

The paper presents a novel SSL-based framework for CIE-XYZ reconstruction that outperforms existing methods and minimizes reliance on extensive paired data.

Findings

Outperforms existing CIE-XYZ reconstruction methods

Reduces dependence on large paired datasets

Effective in color-critical computer vision tasks

Abstract

Modern cameras typically offer two types of image states: a minimally processed linear raw RGB image representing 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 computer 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.