Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose CGS-Retinex, a new method to improve pictures taken in very dark conditions by better separating light and texture in images. They combine a continuous Gaussian splatting technique with Retinex theory to model illumination smoothly and avoid common visual artifacts. Their method also uses an implicit neural network to recover fine details like textures, guided by brightness and smoothness rules inspired by physics. Experiments show their approach reduces noise and overexposure while preserving color and detail more accurately than previous methods.
low-light image enhancementRetinex theoryGaussian splattingimplicit neural representationillumination modelingreflectanceimage artifactsbrightness consistencyimage reconstructionhigh-frequency details
Authors
Yuhan Chen, Yicui Shi, Guofa Li, Wenxuan Yu, Ying Fang, Guangrui Bai, Wenbo Chu, Keqiang Li
Abstract
Low-light image enhancement aims to recover clear images from low-illumination observations and is crucial for high-level downstream vision tasks. However, existing methods frequently encounter color distortion and structural artifacts when balancing global smooth illumination adjustment and local high-frequency detail recovery. To address these issues, we propose CGS-Retinex as the first low-light image enhancement framework based on explicit-implicit joint modeling. Our framework deeply integrates continuous Gaussian splatting with Retinex theory. Specifically, we represent the image grid as a continuous parameter field and propose a continuous Gaussian renderer to estimate the spatially continuous global illumination distribution. This approach fundamentally eliminates grid artifacts caused by discrete Gaussian sampling. Furthermore, we introduce an implicit neural representation to model reflectance independently. We leverage shallow high-frequency features to guide the network in accurately reconstructing degraded texture details. Within the Retinex framework, we incorporate physics-inspired brightness consistency constraints and illumination smoothness regularization to enable explicit illumination and implicit reflectance to maintain proper exposure and achieve high-fidelity recovery of high-frequency structures and colors. Extensive experiments demonstrate that CGS-Retinex significantly suppresses dark-region noise and overexposure while achieving exceptional high-frequency structural fidelity and color restoration by precisely decoupling illumination and texture. This work establishes a novel continuous physical representation paradigm for low-light image enhancement.