Hybrid Rendering for Dynamic Scenes
Alexandr Kuznetsov, Stavros Diolatzis, Anton Sochenov, Anton Kaplanyan

TL;DR
This paper presents a hybrid rendering method that combines precomputation and neural networks to efficiently and accurately render global illumination in dynamic scenes with static backgrounds and moving elements.
Contribution
It introduces a novel approach that leverages precomputed light transport and neural networks to improve real-time global illumination rendering in dynamic scenes.
Findings
Reduces noise in global illumination rendering.
Achieves higher quality with minimal difference computation.
Efficiently handles dynamic scenes with static backgrounds.
Abstract
Despite significant advances in algorithms and hardware, global illumination continues to be a challenge in the real-time domain. Time constraints often force developers to either compromise on the quality of global illumination or disregard it altogether. We take advantage of a common setup in modern games: having a set of a level, which is a static scene with dynamic characters and lighting. We introduce a novel method for efficiently and accurately rendering global illumination in dynamic scenes. Our hybrid technique leverages precomputation and neural networks to capture the light transport of a static scene. Then, we introduce a method to compute the difference between the current scene and the static scene, which we already precomputed. By handling the bulk of the light transport through precomputation, our method only requires the rendering of a minimal difference, reducing the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputer Graphics and Visualization Techniques · 3D Shape Modeling and Analysis · Human Motion and Animation
