Michał Własiuk
Research Subjects
Michał Własiuk has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hyeonseung Yu
Samsung Advanced Institute of Technology, Samsung Electronics, Suwon, South Korea
1 shared publication - J. Park
Samsung Electronics Republic of Korea
1 shared publication K. Rembelska
Samsung R&D Institute Poland Poland
1 shared publication- Michał Chwesiuk
West Pomeranian University of Technology, Szczecin
1 shared publication - Nahyup Kang
Samsung Electronics Republic of Korea
1 shared publication - P. DęBski
Samsung R&D Institute Poland Poland
1 shared publication
Latest Publications
- 5 August 2026
- Published by Wiley in Computer Graphics Forum
- p. e70537
Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms
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.
- 5 August 2026
- Published by Wiley in Computer Graphics Forum
- p. e70537
Locality‐aware Training for Online Radiance Caching in Path Tracing on Mobile Platforms
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.
- Open Access
- 9 February 2026
- Published by Elsevier in Data in Brief
- Vol. 65, 112566
Structured light 3D scanner simulation dataset
- 9 February 2026
- Published by Elsevier in Data in Brief
- Vol. 65, 112566
Open AccessStructured light 3D scanner simulation dataset