2025/04/27 by Xiaofeng Jin, Yan Fang, Jin, Xiaofeng +9 · 1 citation
Computer Science · #3D rendering #65D18 #68U05 #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaussian #Generative Adversarial Networks and Image Synthesis #I.3.7 #I.4.8 #Image-based modeling and rendering #Point (geometry) #Real-time rendering #Rendering (computer graphics) #Tiled rendering #View synthesis
paper · pdf · doi:10.48550/arxiv.2504.19261
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/04/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.