Area ReSTIR: Resampling for Real-Time Defocus and Antialiasing

Recent advancements in spatiotemporal reservoir resampling (ReSTIR) leverage sample reuse from neighbors to efficiently evaluate the path integral. Like rasterization, ReSTIR methods implicitly assume a pinhole camera and evaluate the light arriving at a pixel through a single predetermined subpixel location at a time (e.g., the pixel center). This prevents efficient path reuse in and near pixels with high-frequency details.

We introduce Area ReSTIR, extending ReSTIR reservoirs to also integrate each pixel's 4D ray space, including 2D areas on the film and lens. We design novel subpixel-tracking temporal reuse and shift mappings that maximize resampling quality in such regions. This robustifies ReSTIR against high-frequency content, letting us importance sample subpixel and lens coordinates and efficiently render antialiasing and depth of field.

Source Code on GitHub

Comparisons to ReSTIR

Interactive Result Viewer

We provide an interactive comparison of our method (Area ReSTIR) and baselines for our test scenes. Click an scene thumbnail to see results for that scene.
Note that images have slight JPEG compression to reduce the size.

(We recommend using Chrome or Microsoft Edge for the best experience.)

Paper Video

High-quality version of the paper video (769 MB).

Video Summary

Chris Wyman's short summary of our Area ReSTIR method.

Project Publications