LL-GaussianImage: 用于零样本低光照增强的高效图像表示方法（基于二维高斯点撒）
LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting
AI总结：
LL-GaussianImage提出了一种基于二维高斯点撒的零样本无监督框架，直接在压缩域内实现低光照增强，通过语义引导的专家混合框架、多目标损失函数和两阶段优化提升效率和质量。
摘要：
二维高斯点撒（2DGS）是一种新兴的显式场景表示方法，由于其高保真度和高压缩比，具有显著的图像压缩潜力。然而，现有的低光照增强算法主要在像素域内操作。处理2DGS压缩图像需要繁琐的解压缩-增强-重新压缩流程，这会降低效率并引入二次退化。为了解决这些限制，我们提出了LL-GaussianImage，这是首个针对低光照增强的零样本无监督框架，直接在2DGS压缩表示域内进行处理。该框架提供了三个主要优势。首先，设计了一个语义引导的专家混合增强框架。通过渲染图像作为指导，动态自适应变换应用于2DGS的稀疏属性空间，从而实现压缩-增强而无需完全解压到像素网格。其次，建立了一个多目标协作损失函数系统，严格约束增强过程中的平滑度和保真度，抑制伪影同时提高视觉质量。第三，利用两阶段优化过程实现重建-增强。通过单尺度重建确保基础表示的准确性，并增强网络的鲁棒性。在保持高压缩比的同时实现了高质量的低光照图像增强。通过实验结果验证了该范式在压缩表示域内直接处理的可行性和优越性。
英文摘要：
2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios. However, existing low-light enhancement algorithms operate predominantly within the pixel domain. Processing 2DGS-compressed images necessitates a cumbersome decompression-enhancement-recompression pipeline, which compromises efficiency and introduces secondary degradation. To address these limitations, we propose LL-GaussianImage, the first zero-shot unsupervised framework designed for low-light enhancement directly within the 2DGS compressed representation domain. Three primary advantages are offered by this framework. First, a semantic-guided Mixture-of-Experts enhancement framework is designed. Dynamic adaptive transformations are applied to the sparse attribute space of 2DGS using rendered images as guidance to enable compression-as-enhancement without full decompression to a pixel grid. Second, a multi-objective collaborative loss function system is established to strictly constrain smoothness and fidelity during enhancement, suppressing artifacts while improving visual quality. Third, a two-stage optimization process is utilized to achieve reconstruction-as-enhancement. The accuracy of the base representation is ensured through single-scale reconstruction and network robustness is enhanced. High-quality enhancement of low-light images is achieved while high compression ratios are maintained. The feasibility and superiority of the paradigm for direct processing within the compressed representation domain are validated through experimental results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
