Triangle Splatting for Real-Time Radiance Field Rendering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913858042462208 |
|---|---|
| author | Held, Jan Vandeghen, Renaud Deliege, Adrien Hamdi, Abdullah Giancola, Silvio Cioppa, Anthony Vedaldi, Andrea Ghanem, Bernard Tagliasacchi, Andrea Van Droogenbroeck, Marc |
| author_facet | Held, Jan Vandeghen, Renaud Deliege, Adrien Hamdi, Abdullah Giancola, Silvio Cioppa, Anthony Vedaldi, Andrea Ghanem, Bernard Tagliasacchi, Andrea Van Droogenbroeck, Marc |
| contents | The field of computer graphics was revolutionized by models such as Neural Radiance Fields and 3D Gaussian Splatting, displacing triangles as the dominant representation for photogrammetry. In this paper, we argue for a triangle comeback. We develop a differentiable renderer that directly optimizes triangles via end-to-end gradients. We achieve this by rendering each triangle as differentiable splats, combining the efficiency of triangles with the adaptive density of representations based on independent primitives. Compared to popular 2D and 3D Gaussian Splatting methods, our approach achieves higher visual fidelity, faster convergence, and increased rendering throughput. On the Mip-NeRF360 dataset, our method outperforms concurrent non-volumetric primitives in visual fidelity and achieves higher perceptual quality than the state-of-the-art Zip-NeRF on indoor scenes. Triangles are simple, compatible with standard graphics stacks and GPU hardware, and highly efficient: for the \textit{Garden} scene, we achieve over 2,400 FPS at 1280x720 resolution using an off-the-shelf mesh renderer. These results highlight the efficiency and effectiveness of triangle-based representations for high-quality novel view synthesis. Triangles bring us closer to mesh-based optimization by combining classical computer graphics with modern differentiable rendering frameworks. The project page is https://trianglesplatting.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19175 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Triangle Splatting for Real-Time Radiance Field Rendering Held, Jan Vandeghen, Renaud Deliege, Adrien Hamdi, Abdullah Giancola, Silvio Cioppa, Anthony Vedaldi, Andrea Ghanem, Bernard Tagliasacchi, Andrea Van Droogenbroeck, Marc Computer Vision and Pattern Recognition The field of computer graphics was revolutionized by models such as Neural Radiance Fields and 3D Gaussian Splatting, displacing triangles as the dominant representation for photogrammetry. In this paper, we argue for a triangle comeback. We develop a differentiable renderer that directly optimizes triangles via end-to-end gradients. We achieve this by rendering each triangle as differentiable splats, combining the efficiency of triangles with the adaptive density of representations based on independent primitives. Compared to popular 2D and 3D Gaussian Splatting methods, our approach achieves higher visual fidelity, faster convergence, and increased rendering throughput. On the Mip-NeRF360 dataset, our method outperforms concurrent non-volumetric primitives in visual fidelity and achieves higher perceptual quality than the state-of-the-art Zip-NeRF on indoor scenes. Triangles are simple, compatible with standard graphics stacks and GPU hardware, and highly efficient: for the \textit{Garden} scene, we achieve over 2,400 FPS at 1280x720 resolution using an off-the-shelf mesh renderer. These results highlight the efficiency and effectiveness of triangle-based representations for high-quality novel view synthesis. Triangles bring us closer to mesh-based optimization by combining classical computer graphics with modern differentiable rendering frameworks. The project page is https://trianglesplatting.github.io/ |
| title | Triangle Splatting for Real-Time Radiance Field Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.19175 |