LL-GaussianMap: Zero-shot Low-Light Image Enhancement via 2D Gaussian Splatting Guided Gain Maps

TL;DR

LL-GaussianMap introduces an unsupervised low-light image enhancement method that leverages 2D Gaussian Splatting for structural preservation and artifact suppression, achieving high-quality results with minimal storage.

Contribution

This work is the first to incorporate 2D Gaussian Splatting into low-light image enhancement, formulating the task as gain map generation guided by explicit scene representations.

Findings

Outperforms existing methods in enhancement quality

Uses significantly less storage space

Effectively preserves edges and reduces artifacts

Abstract

Significant progress has been made in low-light image enhancement with respect to visual quality. However, most existing methods primarily operate in the pixel domain or rely on implicit feature representations. As a result, the intrinsic geometric structural priors of images are often neglected. 2D Gaussian Splatting (2DGS) has emerged as a prominent explicit scene representation technique characterized by superior structural fitting capabilities and high rendering efficiency. Despite these advantages, the utilization of 2DGS in low-level vision tasks remains unexplored. To bridge this gap, LL-GaussianMap is proposed as the first unsupervised framework incorporating 2DGS into low-light image enhancement. Distinct from conventional methodologies, the enhancement task is formulated as a gain map generation process guided by 2DGS primitives. The proposed method comprises two primary stages. First, high-fidelity structural reconstruction is executed utilizing 2DGS. Then, data-driven enhancement dictionary coefficients are rendered via the rasterization mechanism of Gaussian splatting through an innovative unified enhancement module. This design effectively incorporates the structural perception capabilities of 2DGS into gain map generation, thereby preserving edges and suppressing artifacts during enhancement. Additionally, the reliance on paired data is circumvented through unsupervised learning. Experimental results demonstrate that LL-GaussianMap achieves superior enhancement performance with an extremely low storage footprint, highlighting the effectiveness of explicit Gaussian representations for image enhancement.