Guardado en:
Detalles Bibliográficos
Autores principales: 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
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