Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910075115798528 |
|---|---|
| author | Xu, Peiyu Sun, Xin Mullia, Krishna Fei, Raymond Georgiev, Iliyan Zhao, Shuang |
| author_facet | Xu, Peiyu Sun, Xin Mullia, Krishna Fei, Raymond Georgiev, Iliyan Zhao, Shuang |
| contents | Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises.
We present a differentiable, sorting-free stochastic formulation for ray-traced 3DGS -- the first framework that uses stochastic ray tracing to both reconstruct and render standard and relightable 3DGS scenes. At its core is an unbiased Monte Carlo estimator for pixel-color gradients that evaluates only a small sampled subset of Gaussians per ray, bypassing the need for sorting. For standard 3DGS, our method matches the reconstruction quality and speed of rasterization-based 3DGS while substantially outperforming sorting-based ray tracing. For relightable 3DGS, the same stochastic estimator drives per-Gaussian shading with fully ray-traced shadow rays, delivering notably higher reconstruction fidelity than prior work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23637 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting Xu, Peiyu Sun, Xin Mullia, Krishna Fei, Raymond Georgiev, Iliyan Zhao, Shuang Computer Vision and Pattern Recognition Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced 3DGS -- the first framework that uses stochastic ray tracing to both reconstruct and render standard and relightable 3DGS scenes. At its core is an unbiased Monte Carlo estimator for pixel-color gradients that evaluates only a small sampled subset of Gaussians per ray, bypassing the need for sorting. For standard 3DGS, our method matches the reconstruction quality and speed of rasterization-based 3DGS while substantially outperforming sorting-based ray tracing. For relightable 3DGS, the same stochastic estimator drives per-Gaussian shading with fully ray-traced shadow rays, delivering notably higher reconstruction fidelity than prior work. |
| title | Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.23637 |