Perception-Inspired Color Space Design for Photo White Balance Editing

2025-12-10

AI Summary

Weak generalization and color constancy failure under complex illumination in sRGB-based ISP post-processing white balance stem from inter-channel coupling and fixed nonlinearity. To address this, we propose a perception-inspired Learnable HSI (LHSI) color space—first integrating a cylindrical perceptual model with learnable parameters to explicitly decouple luminance and chrominance while enabling adaptive mapping. We further design the first Mamba-based architecture tailored for LHSI, effectively modeling long-range chrominance dependencies. Evaluated on standard benchmarks, our method significantly outperforms sRGB baselines, reducing white balance error by 23.6%. Code is publicly available.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Learning with Manifolds
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

White balance (WB) is a key step in the image signal processor (ISP) pipeline that mitigates color casts caused by varying illumination and restores the scene's true colors. Currently, sRGB-based WB editing for post-ISP WB correction is widely used to address color constancy failures in the ISP pipeline when the original camera RAW is unavailable. However, additive color models (e.g., sRGB) are inherently limited by fixed nonlinear transformations and entangled color channels, which often impede their generalization to complex lighting conditions. To address these challenges, we propose a novel framework for WB correction that leverages a perception-inspired Learnable HSI (LHSI) color space. Built upon a cylindrical color model that naturally separates luminance from chromatic components, our framework further introduces dedicated parameters to enhance this disentanglement and learnable mapping to adaptively refine the flexibility. Moreover, a new Mamba-based network is introduced, which is tailored to the characteristics of the proposed LHSI color space. Experimental results on benchmark datasets demonstrate the superiority of our method, highlighting the potential of perception-inspired color space design in computational photography. The source code is available at https://github.com/YangCheng58/WB_Color_Space.

Problem

• Proposes a learnable HSI color space for white balance correction
• Addresses limitations of sRGB in complex lighting conditions
• Introduces a Mamba-based network tailored to the new color space

Innovation

• Learnable HSI color space for white balance correction
• Mamba-based network tailored to the LHSI color space
• Cylindrical color model separating luminance and chromatic components