TransGI : Real-Time Dynamic Global Illumination with Object-Centric Neural Transfer Model

Neural rendering algorithms have revolutionized computer graphics, yet their impact on real-time rendering under arbitrary lighting conditions remains limited due to strict latency constraints in practical applications. The key challenge lies in formulating a compact yet expressive material represen...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on visualization and computer graphics. - 1996. - PP(2025) vom: 22. Aug.
Auteur principal: Deng, Yijie (Auteur)
Autres auteurs: Han, Lei, Fang, Lu
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on visualization and computer graphics
Sujets:Journal Article
Description
Résumé:Neural rendering algorithms have revolutionized computer graphics, yet their impact on real-time rendering under arbitrary lighting conditions remains limited due to strict latency constraints in practical applications. The key challenge lies in formulating a compact yet expressive material representation. To address this, we propose TransGI, a novel neural rendering method for real-time, high-fidelity global illumination. It comprises an object-centric neural transfer model for material representation and a radiance-sharing lighting system for efficient illumination. Traditional BSDF representations and spatial neural material representations lack expressiveness, requiring thousands of ray evaluations to converge to noise-free colors. Conversely, realtime methods trade quality for efficiency by supporting only diffuse materials. In contrast, our object-centric neural transfer model achieves compactness and expressiveness through an MLPbased decoder and vertex-attached latent features, supporting glossy effects with low memory overhead. For dynamic, varying lighting conditions, we introduce local light probes capturing scene radiance, coupled with an across-probe radiance-sharing strategy for efficient probe generation. We implemented our method in a real-time rendering engine, combining compute shaders and CUDA-based neural networks. Experimental results demonstrate that our method achieves real-time performance of less than 10 ms to render a frame and significantly improved rendering quality compared to baseline methods
Description:Date Revised 22.08.2025
published: Print-Electronic
Citation Status Publisher
ISSN:1941-0506
DOI:10.1109/TVCG.2025.3596146