Deep Photon Mapping

TL;DR

This paper introduces a novel deep learning-based photon density estimation method for particle-based rendering, significantly reducing the number of photons needed for high-quality global illumination effects like caustics.

Contribution

It presents the first deep neural network for photon density estimation in particle-based rendering, enabling high-quality results with fewer photons and easy integration into existing photon mapping techniques.

Findings

Achieves high-quality caustics with an order of magnitude fewer photons.

Easily integrates into existing photon mapping methods by swapping kernel estimators.

Demonstrates improved photon density estimation accuracy over traditional methods.

Abstract

Recently, deep learning-based denoising approaches have led to dramatic improvements in low sample-count Monte Carlo rendering. These approaches are aimed at path tracing, which is not ideal for simulating challenging light transport effects like caustics, where photon mapping is the method of choice. However, photon mapping requires very large numbers of traced photons to achieve high-quality reconstructions. In this paper, we develop the first deep learning-based method for particle-based rendering, and specifically focus on photon density estimation, the core of all particle-based methods. We train a novel deep neural network to predict a kernel function to aggregate photon contributions at shading points. Our network encodes individual photons into per-photon features, aggregates them in the neighborhood of a shading point to construct a photon local context vector, and infers a kernel function from the per-photon and photon local context features. This network is easy to incorporate in many previous photon mapping methods (by simply swapping the kernel density estimator) and can produce high-quality reconstructions of complex global illumination effects like caustics with an order of magnitude fewer photons compared to previous photon mapping methods.