A ReSTIR GI Method Using the Sample-Space Filtering

In real-time ray tracing applications, only a small number of samples per pixel can be traced, limited by the computational power of the hardware. Maximizing the rendering quality with a low sampling rate is an important problem for real-time ray tracing. Reservoir-based spatiotemporal importance resampling with multi-bounce global illumination (ReSTIR GI) improves the rendering quality of a low sampling rate. However, the noise introduced by Monte Carlo sampling still exists. We propose a lightweight and efficient sample-space filtering method applied to ReSTIR GI that filters the sample distribution before resampling, thus reducing the noise in the final rendering result. Compared to the original ReSTIR GI, our method achieves a smaller mean squared error (MSE) of 1.1 \(\times \) to 5.6 \(\times \) and a higher peak signal-to-noise ratio (PSNR) of 1.1 \(\times \) at the cost of an average increase in rendering time of 12%.