Rendering Anywhere You See: Renderability Field-guided Gaussian Splatting
This addresses scene view synthesis for applications like virtual reality and robotics, but it appears incremental as it builds on existing Gaussian splatting techniques.
The paper tackles the problem of scene view synthesis in non-uniformly observed environments by proposing a renderability field-guided Gaussian splatting method, which improves rendering stability and outperforms existing approaches in experiments.
Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360° views of a car, scene view synthesis handles entire environments where non-uniform observations pose unique challenges for stable rendering quality. To address this issue, we propose a novel approach: renderability field-guided gaussian splatting (RF-GS). This method quantifies input inhomogeneity through a renderability field, guiding pseudo-view sampling to enhanced visual consistency. To ensure the quality of wide-baseline pseudo-views, we train an image restoration model to map point projections to visible-light styles. Additionally, our validated hybrid data optimization strategy effectively fuses information of pseudo-view angles and source view textures. Comparative experiments on simulated and real-world data show that our method outperforms existing approaches in rendering stability.