Hardware-Rasterized Ray-Based Gaussian Splatting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912434997952512 |
|---|---|
| author | Bulò, Samuel Rota Bartolovic, Nemanja Porzi, Lorenzo Kontschieder, Peter |
| author_facet | Bulò, Samuel Rota Bartolovic, Nemanja Porzi, Lorenzo Kontschieder, Peter |
| contents | We present a novel, hardware rasterized rendering approach for ray-based 3D Gaussian Splatting (RayGS), obtaining both fast and high-quality results for novel view synthesis. Our work contains a mathematically rigorous and geometrically intuitive derivation about how to efficiently estimate all relevant quantities for rendering RayGS models, structured with respect to standard hardware rasterization shaders. Our solution is the first enabling rendering RayGS models at sufficiently high frame rates to support quality-sensitive applications like Virtual and Mixed Reality. Our second contribution enables alias-free rendering for RayGS, by addressing MIP-related issues arising when rendering diverging scales during training and testing. We demonstrate significant performance gains, across different benchmark scenes, while retaining state-of-the-art appearance quality of RayGS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hardware-Rasterized Ray-Based Gaussian Splatting Bulò, Samuel Rota Bartolovic, Nemanja Porzi, Lorenzo Kontschieder, Peter Computer Vision and Pattern Recognition Graphics We present a novel, hardware rasterized rendering approach for ray-based 3D Gaussian Splatting (RayGS), obtaining both fast and high-quality results for novel view synthesis. Our work contains a mathematically rigorous and geometrically intuitive derivation about how to efficiently estimate all relevant quantities for rendering RayGS models, structured with respect to standard hardware rasterization shaders. Our solution is the first enabling rendering RayGS models at sufficiently high frame rates to support quality-sensitive applications like Virtual and Mixed Reality. Our second contribution enables alias-free rendering for RayGS, by addressing MIP-related issues arising when rendering diverging scales during training and testing. We demonstrate significant performance gains, across different benchmark scenes, while retaining state-of-the-art appearance quality of RayGS. |
| title | Hardware-Rasterized Ray-Based Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2503.18682 |