From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields

TL;DR

This paper introduces Gaussian Photon Fields, a learnable continuous representation for photon mapping that enables efficient multi-view rendering with photon-level accuracy by reusing photon information across views.

Contribution

It proposes a novel Gaussian Photon Field representation that encodes photon distributions as learnable anisotropic 3D Gaussians, significantly improving rendering efficiency.

Findings

Achieves photon-level accuracy in complex light transport scenes.

Reduces computational cost by orders of magnitude compared to traditional methods.

Enables differentiable radiance evaluation without repeated photon tracing.

Abstract

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.