LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment
This addresses a bottleneck for robotics applications like high-fidelity modeling and feature matching in low-light conditions, offering an incremental improvement over existing methods.
The paper tackles the problem of 3D Gaussian Splatting lacking color representation in low-light environments, proposing LLGS, an unsupervised multi-view system that enhances images and reconstructs scenes, outperforming state-of-the-art methods in experiments on real-world datasets.
3D Gaussian Splatting has shown remarkable capabilities in novel view rendering tasks and exhibits significant potential for multi-view optimization.However, the original 3D Gaussian Splatting lacks color representation for inputs in low-light environments. Simply using enhanced images as inputs would lead to issues with multi-view consistency, and current single-view enhancement systems rely on pre-trained data, lacking scene generalization. These problems limit the application of 3D Gaussian Splatting in low-light conditions in the field of robotics, including high-fidelity modeling and feature matching. To address these challenges, we propose an unsupervised multi-view stereoscopic system based on Gaussian Splatting, called Low-Light Gaussian Splatting (LLGS). This system aims to enhance images in low-light environments while reconstructing the scene. Our method introduces a decomposable Gaussian representation called M-Color, which separately characterizes color information for targeted enhancement. Furthermore, we propose an unsupervised optimization method with zero-knowledge priors, using direction-based enhancement to ensure multi-view consistency. Experiments conducted on real-world datasets demonstrate that our system outperforms state-of-the-art methods in both low-light enhancement and 3D Gaussian Splatting.