EUVIMEDEUVIMED entdecken
Crossref

Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms

H. Yu, M. Własiuk, M. Chwesiuk, J. Park, R. Chmielewski, P. Dębski, K. Rembelska, N. Kang

Computer Graphics Forum · 05.08.2026

DOI: 10.1111/cgf.70537 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 05.08.2026. Verfasst von H. Yu und 7 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Research Foundation of Korea, Korea Institute for Advancement of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Research Foundation of Korea
  • Korea Institute for Advancement of Technology

Zitieren

APA

Yu, H., Własiuk, M., Chwesiuk, M., Park, J., Chmielewski, R., Dębski, P., Rembelska, K., & Kang, N. (2026). Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms. Computer Graphics Forum. https://doi.org/10.1111/cgf.70537

Vancouver

Yu H, Własiuk M, Chwesiuk M, Park J, Chmielewski R, Dębski P, et al. Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms. Computer Graphics Forum. 2026. doi:10.1111/cgf.70537

BibTeX
@article{Yu2026,
  author = {Yu, H. and Własiuk, M. and Chwesiuk, M. and Park, J. and Chmielewski, R. and Dębski, P. and Rembelska, K. and Kang, N.},
  title = {Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70537}
}
Kostenlos starten →