Photon-Driven Neural Path Guiding

TL;DR

This paper introduces a neural path guiding method that reconstructs high-quality importance sampling distributions from sparse data using an offline-trained neural network, significantly improving rendering efficiency in complex scenes.

Contribution

It presents a novel photon-driven neural path guiding approach that leverages scene partitioning and neural networks to enhance importance sampling in path tracing from limited samples.

Findings

Achieves better rendering quality than previous methods.

Generalizes well to unseen challenging scenes.

Efficiently reconstructs sampling distributions for any scene region.

Abstract

Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful variance-reduction techniques is path guiding, which can learn better distributions for importance sampling to reduce pixel noise. However, previous methods require a large number of path samples to achieve reliable path guiding. We present a novel neural path guiding approach that can reconstruct high-quality sampling distributions for path guiding from a sparse set of samples, using an offline trained neural network. We leverage photons traced from light sources as the input for sampling density reconstruction, which is highly effective for challenging scenes with strong global illumination. To fully make use of our deep neural network, we partition the scene space into an adaptive hierarchical grid, in which we apply our network to reconstruct high-quality sampling distributions for any local region in the scene. This allows for highly efficient path guiding for any path bounce at any location in path tracing. We demonstrate that our photon-driven neural path guiding method can generalize well on diverse challenging testing scenes that are not seen in training. Our approach achieves significantly better rendering results of testing scenes than previous state-of-the-art path guiding methods.