HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes

3D Gaussian Splatting (3DGS) has shown promising results for Novel View Synthesis. However, while it is quite effective when based on high-quality images, its performance declines as image quality degrades, due to lack of resolution, motion blur, noise, compression artifacts, or other factors common in real-world data collection. While some solutions have been proposed for specific types of degradation, general techniques are still missing. To address the problem, we propose a robust HQGS that significantly enhances the 3DGS under various degradation scenarios. We first analyze that 3DGS lacks sufficient attention in some detailed regions in low-quality scenes, leading to the absence of Gaussian primitives in those areas and resulting in loss of detail in the rendered images. To address this issue, we focus on leveraging edge structural information to provide additional guidance for 3DGS, enhancing its robustness. First, we introduce an edgesemantic fusion guidance module that combines rich texture information from high-frequency edge-aware maps with semantic information from images. The fused features serve as prior guidance to capture detailed distribution across different regions, bringing more attention to areas with detailed edge information and allowing for a higher concentration of Gaussian primitives to be assigned to such areas. Additionally, we present a structural cosine similarity loss to complement pixel-level constraints, further improving the quality of the rendered images. Extensive experiments demonstrate that our method offers better robustness and achieves the best results across various degraded scenes. Source code and trained models are publicly available at: https://github.com/linxin0/HQGS . INTRODUCTION Novel view synthesis advanced significantly in recent years, with the introduction of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), benefiting applications such as augmented reality (AR) and virtual reality (VR) (Bian et al., 2016; Dawood, 2009; Farshid et al., 2018; Fassi et al., 2016) . Nevertheless, existing methods assume high-quality images captured with precise camera parameters. When faced with images of low resolution, with motion blur, compression artifacts, noise, or other degradations common in real-world imaging, they often struggle. Some