Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2025

Abstract

Low-Light Image Enhancement (LLIE) is a crucial computer vision task that aims to restore detailed visual information from corrupted low-light images. Many existing LLIE methods are based on standard RGB (sRGB) space, which often produce color bias and brightness artifacts due to inherent high color sensitivity in sRGB. While converting the images using Hue, Saturation and Value (HSV) color space helps resolve the brightness issue, it introduces significant red and black noise artifacts. To address this issue, we propose a new color space for LLIE, namely Horizontal/Vertical-Intensity (HVI), defined by polarized HS maps and learnable inten sity. The former enforces small distances for red coordinates to remove the red artifacts, while the latter compresses the low-light regions to remove the black artifacts. To fully lever age the chromatic and intensity information, a novel Color and Intensity Decoupling Network (CIDNet) is further in troduced to learn accurate photometric mapping function under different lighting conditions in the HVI space. Com prehensive results from benchmark and ablation experiments show that the proposed HVI color space with CIDNet out performs the state-of-the-art methods on 10 datasets. The code is available at https://github.com/Fediory/HVI-CIDNet.

Keywords

HVI color space, image processing, low-light enhancement

Discipline

Graphics and Human Computer Interfaces | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025: June 11-15, Nashville

First Page

5678

Last Page

5687

ISBN

9798331543648

Identifier

10.1109/CVPR52734.2025.00533

Publisher

IEEE Computer Society

City or Country

Nashville

Additional URL

https://doi.org/10.1109/CVPR52734.2025.00533

Download

Share

COinS