Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2512.12459 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918388984446976 |
|---|---|
| author | Tao, Jiachen Planche, Benjamin Nguyen, Van Nguyen Wu, Junyi Liu, Yuchun Wang, Haoxuan Gao, Zhongpai Zhang, Gengyu Zheng, Meng Wang, Feiran Choudhuri, Anwesa Zhao, Zhenghao Kang, Weitai Chen, Terrence Yan, Yan Wu, Ziyan |
| author_facet | Tao, Jiachen Planche, Benjamin Nguyen, Van Nguyen Wu, Junyi Liu, Yuchun Wang, Haoxuan Gao, Zhongpai Zhang, Gengyu Zheng, Meng Wang, Feiran Choudhuri, Anwesa Zhao, Zhenghao Kang, Weitai Chen, Terrence Yan, Yan Wu, Ziyan |
| contents | Accurately modeling light transport is essential for realistic image synthesis. Photon mapping provides physically grounded estimates of complex global illumination effects such as caustics and specular-diffuse interactions, yet its per-view radiance estimation remains computationally inefficient when rendering multiple views of the same scene. The inefficiency arises from independent photon tracing and stochastic kernel estimation at each viewpoint, leading to inevitable redundant computation. To accelerate multi-view rendering, we reformulate photon mapping as a continuous and reusable radiance function. Specifically, we introduce the Gaussian Photon Field (GPF), a learnable representation that encodes photon distributions as anisotropic 3D Gaussian primitives parameterized by position, rotation, scale, and spectrum. GPF is initialized from physically traced photons in the first SPPM iteration and optimized using multi-view supervision of final radiance, distilling photon-based light transport into a continuous field. Once trained, the field enables differentiable radiance evaluation along camera rays without repeated photon tracing or iterative refinement. Extensive experiments on scenes with complex light transport, such as caustics and specular-diffuse interactions, demonstrate that GPF attains photon-level accuracy while reducing computation by orders of magnitude, unifying the physical rigor of photon-based rendering with the efficiency of neural scene representations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_12459 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields Tao, Jiachen Planche, Benjamin Nguyen, Van Nguyen Wu, Junyi Liu, Yuchun Wang, Haoxuan Gao, Zhongpai Zhang, Gengyu Zheng, Meng Wang, Feiran Choudhuri, Anwesa Zhao, Zhenghao Kang, Weitai Chen, Terrence Yan, Yan Wu, Ziyan Computer Vision and Pattern Recognition Graphics Accurately modeling light transport is essential for realistic image synthesis. Photon mapping provides physically grounded estimates of complex global illumination effects such as caustics and specular-diffuse interactions, yet its per-view radiance estimation remains computationally inefficient when rendering multiple views of the same scene. The inefficiency arises from independent photon tracing and stochastic kernel estimation at each viewpoint, leading to inevitable redundant computation. To accelerate multi-view rendering, we reformulate photon mapping as a continuous and reusable radiance function. Specifically, we introduce the Gaussian Photon Field (GPF), a learnable representation that encodes photon distributions as anisotropic 3D Gaussian primitives parameterized by position, rotation, scale, and spectrum. GPF is initialized from physically traced photons in the first SPPM iteration and optimized using multi-view supervision of final radiance, distilling photon-based light transport into a continuous field. Once trained, the field enables differentiable radiance evaluation along camera rays without repeated photon tracing or iterative refinement. Extensive experiments on scenes with complex light transport, such as caustics and specular-diffuse interactions, demonstrate that GPF attains photon-level accuracy while reducing computation by orders of magnitude, unifying the physical rigor of photon-based rendering with the efficiency of neural scene representations. |
| title | From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2512.12459 |