Revealing Shadows: Low-Light Image Enhancement Using Self-Calibrated Illumination
Farzaneh Koohestani, Nader Karimi, Shadrokh Samavi

TL;DR
This paper introduces a novel low-light image enhancement technique using Self-Calibrated Illumination (SCI), which improves visibility and detail preservation without requiring paired training images, suitable for various real-world applications.
Contribution
The paper develops a new low-light enhancement method based on SCI that enhances illumination in varied color spaces, preserving color integrity and eliminating the need for paired images.
Findings
Effective enhancement of low-light images with preserved color fidelity
No requirement for paired training images
Improved visibility and detail in dark images
Abstract
In digital imaging, enhancing visual content in poorly lit environments is a significant challenge, as images often suffer from inadequate brightness, hidden details, and an overall reduction in quality. This issue is especially critical in applications like nighttime surveillance, astrophotography, and low-light videography, where clear and detailed visual information is crucial. Our research addresses this problem by enhancing the illumination aspect of dark images. We have advanced past techniques by using varied color spaces to extract the illumination component, enhance it, and then recombine it with the other components of the image. By employing the Self-Calibrated Illumination (SCI) method, a strategy initially developed for RGB images, we effectively intensify and clarify details that are typically lost in low-light conditions. This method of selective illumination enhancement…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Advanced Vision and Imaging · Color Science and Applications
