Rendering Anywhere You See: Renderability Field-guided Gaussian Splatting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908340005634048 |
|---|---|
| author | Jin, Xiaofeng Fang, Yan Frosi, Matteo Ge, Jianfei Xiao, Jiangjian Matteucci, Matteo |
| author_facet | Jin, Xiaofeng Fang, Yan Frosi, Matteo Ge, Jianfei Xiao, Jiangjian Matteucci, Matteo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19261 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rendering Anywhere You See: Renderability Field-guided Gaussian Splatting Jin, Xiaofeng Fang, Yan Frosi, Matteo Ge, Jianfei Xiao, Jiangjian Matteucci, Matteo Computer Vision and Pattern Recognition 65D18, 68U05 I.3.7; I.4.8 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. |
| title | Rendering Anywhere You See: Renderability Field-guided Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition 65D18, 68U05 I.3.7; I.4.8 |
| url | https://arxiv.org/abs/2504.19261 |