Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms
- 5 August 2026
- journal article
- research article
- Published by Wiley in Computer Graphics Forum
- p. e70537
Abstract
Real‐time path tracing for global illumination has recently become feasible on high‐performance desktop GPUs, but achieving similar performance on mobile platforms remains a significant challenge due to computational limitations. As mobile devices begin to integrate ray tracing capabilities, new methods are required to bridge the performance gap and enable advanced rendering techniques on constrained hardware. In this paper, we present Mobile Radiance Caching (MobileRC), an online trainable radiance caching approach based on a plenoxel representation, designed to accelerate path tracing on mobile devices. Unlike neural network‐based radiance caching methods, which rely on matrix multiplication accelerators unavailable on current mobile GPUs, MobileRC uses a voxel‐based representation where each voxel stores spherical harmonic coefficients to represent angular dependencies, making it more suitable for mobile hardware. Specifically, we exploit the localized interaction between learnable plenoxel weights and training samples, designing a mobile‐friendly training method. While our approach incurs a mild loss in cache quality compared to neural methods optimized for high‐end GPUs, it significantly improves image quality while reducing rendering time, achieving interactive frame rates for full HD images in room‐sized scenes on mobile hardware.Keywords
Funding Information
- National Research Foundation of Korea (RS‐2023‐00221186)
- Korea Institute for Advancement of Technology (RS‐2024‐00418086)
This publication has 29 references indexed in Scilit:
- Neural Two‐Level Monte Carlo Real‐Time RenderingComputer Graphics Forum, 2025
- Real‐time Neural Rendering of Dynamic Light FieldsComputer Graphics Forum, 2024
- MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures2023
- Real-Time Neural Light Field on Mobile Devices2023
- Neural Precomputed Radiance TransferComputer Graphics Forum, 2022
- Advances in Neural RenderingComputer Graphics Forum, 2022
- Online Path Sampling Control with Progressive Spatio-temporal FilteringSN Computer Science, 2020
- The State of the Art in Interactive Global IlluminationComputer Graphics Forum, 2012
- Radiance Caching for Efficient Global Illumination ComputationIEEE Transactions on Visualization and Computer Graphics, 2005
- The irradiance volumeIEEE Computer Graphics and Applications, 1998