RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
This addresses noise reduction in real-time path tracing for graphics and rendering applications, representing a strong incremental improvement.
The paper tackles the problem of high noise in Monte-Carlo path tracing at low sample counts, which limits real-time use, by proposing an RL-based framework with neural networks for sampling and denoising, resulting in a 1.6x reduction in rendering time for equal quality compared to previous state-of-the-art.
Monte-Carlo path tracing is a powerful technique for realistic image synthesis but suffers from high levels of noise at low sample counts, limiting its use in real-time applications. To address this, we propose a framework with end-to-end training of a sampling importance network, a latent space encoder network, and a denoiser network. Our approach uses reinforcement learning to optimize the sampling importance network, thus avoiding explicit numerically approximated gradients. Our method does not aggregate the sampled values per pixel by averaging but keeps all sampled values which are then fed into the latent space encoder. The encoder replaces handcrafted spatiotemporal heuristics by learned representations in a latent space. Finally, a neural denoiser is trained to refine the output image. Our approach increases visual quality on several challenging datasets and reduces rendering times for equal quality by a factor of 1.6x compared to the previous state-of-the-art, making it a promising solution for real-time applications.