Yuan, JunPingWang, ChenSun, QiGuo, JieBei, JiaZhang, YanGuo, YanwenChristie, MarcHan, Ping-HsuanLin, Shih-SyunPietroni, NicoSchneider, TeseoTsai, Hsin-RueyWang, Yu-ShuenZhang, Eugene2025-10-072025-10-072025978-3-03868-295-0https://doi.org/10.2312/pg.20251292https://diglib.eg.org/handle/10.2312/pg20251292In the context of hardware-accelerated real-time ray tracing, existing spatiotemporal resampling techniques are still constrained by screen-space dependencies, which may lead to reuse failures. To address this issue, we propose a world-space resampling method based on a hybrid spatial structure that combines uniform grids and octrees. This persistent structure, which remains unchanged with respect to camera motion, can efficiently partition scenes while preserving geometric details. Our method begins with generating initial light samples, then remaps these samples to the spatial structure. Spatial reuse occurs entirely within individual spatial nodes. For direct illumination, we determine the spatial node of each shading point and select the world-space reservoir from that node to obtain a light sample. For indirect illumination, we trace a BRDF ray and use the world-space reservoir within the spatial node at the hit point to improve the NEE. This unified approach enables joint sample reuse for both direct and indirect illumination. Our experiments show that the proposed method achieves 20-70% reduction in RelMSE compared to screen-space ReSTIR and previous world-space methods under equal-time comparison, with 2× faster convergence rates and superior temporal stability under rapid camera motion.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Rendering;Ray tracingComputing methodologies → RenderingRay tracing10.2312/pg.2025129212 pages