cs.GRNov 12, 2026

Neural Render Proxies for Interactive and Differentiable Lighting

Authors: Sergio Sancho, Alexander Rath, Marco Manzi, Pascal Chang, Amit H. Bermano, Derek Nowrouzezahrai, Markus Gross, Marios Papas

Organizations: ETH Zurich, Switzerland · DisneyResearch|Studios, Switzerland · Tel Aviv University, Israel · McGill University, Canada · 

Abstract

Within the CG animation production pipeline, the challenges artists tackle in Lighting can be immense. Even minor adjustments require re-rendering massive scenes with slow offline renderers; global illumination has to be sampled and complex shaders have to be evaluated, leading to iteration times of minutes to hours per frame. To accelerate this process, we introduce a novel neural render proxy (NRP) that enables differentiable relighting of static scenes with fixed camera and materials at interactive rates. Our main insight is the decoupling of traditional rendering into path sampling and emission computation. From a single, light-agnostic render pass, we collect light transport data in the form of path samples. This enables rapidly sampling lighting conditions on the fly, and training a scene-specific lightweight neural network that learns how light is transported from any scene location to any image pixel. This approach is compatible with non-differentiable production renderers, induces minimal memory requirements during inference, and scales only with resolution and the number of light sources and parameters, but independently of scene and appearance complexity. Our evaluation demonstrates interactive frame rates for relighting (~30-60 Hz) while closely approximating the visual fidelity of ground-truth path tracing. In addition, the differentiable NRP enables fast, gradient-based inverse workflows, allowing artists to efficiently solve for lighting parameters from intuitive image-space edits or generative targets.

Figures & tables

Explore similar work

CardsList
  1. 8DNA: 8D Neural Asset Light Transport by Distribution Learning

    Apr 28, 2026Liwen Wu, Haolin Lu, Bing Xu +2Neural RenderingPhysically Based Rendering

  2. DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Rendering

    Sep 25, 2026Kai-Chen Tung, Qi Wu, David Bauer +3Neural RenderingDiffusion Model Caching

  3. Floating Radiance Networks

    Aug 6, 2026Krzysztof Byrski, Rafał Tobiasz, Grzegorz Wilczyński +5Neural RenderingNovel View Synthesis