Neural Render Proxies for Interactive and Differentiable Lighting

# Neural Render Proxies for Interactive and Differentiable Lighting Source: [https://studios.disneyresearch.com/2026/07/01/neural-render-proxies-for-interactive-and-differentiable-lighting/](https://studios.disneyresearch.com/2026/07/01/neural-render-proxies-for-interactive-and-differentiable-lighting/) ### In this work, we introduce a novel neural render proxy \(NRP\) that enables differentiable relighting of static scenes with fixed camera and materials at interactive rates\. **July 1, 2026** **Eurographics Symposium on Rendering \(EGSR\) \(2026\)** #### Authors Sergio Sancho \(ETH Zurich/DisneyResearch\|Studios\) Alexander Rath \(DisneyResearch\|Studios\) Marco Manzi \(DisneyResearch\|Studios\) Pascal Chang \(ETH Zurich/DisneyResearch\|Studios\) Amit H\. Bermano \(ETH Zurich/DisneyResearch\|Studios/Tel Aviv University\) Derek Nowrouzezahrai \(McGill University/Mila – Quebec AI Institute/CIFAR AI Chair\) Markus Gross \(DisneyResearch\|Studios/ETH Zurich\) Marios Papas \(DisneyResearch\|Studios\)  #### Neural Render Proxies for Interactive and Differentiable Lighting 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\.  ### Copyright Notice The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non\-commercial basis\. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically\. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author’s copyright\. These works may not be reposted without the explicit permission of the copyright holder\. ##### Research at Disney ##### Legal ##### MORE