Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion
Pengpei Hong, Song Zhang, Daqi Lin, Markus Kettunen, Chris Wyman, Cem Yuksel
2026年份
摘要
ReSTIR [Bitterli et al. 2020] efficiently reduces path tracing noise by reusing samples spatiotemporally. Recent ReSTIR methods [Liu et al. 2025] improve temporal reuse from prior frame primary hits. But disocclusions still invalidate some pixel histories, degrading quality with spatially varying noise.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
相关 Paper
- Reservoir Splatting for Temporal Path Resampling and Motion BlurJeffrey Liu, Daqi Lin, Markus Kettunen, Chris Wyman 等SIGGRAPH 2025 · 被引用 4 次
- Spatio-Temporal Control Variates with ReSTIR for Real-Time RenderingZhong Shi, Cunhao Wu, Lifan Wu, Kun XuSIGGRAPH 2026
- Area ReSTIR: Resampling for Real-Time Defocus and AntialiasingSong Zhang, Daqi Lin, Markus Kettunen, Cem Yuksel 等SIGGRAPH 2024 · 被引用 16 次
- Real-Time Level-of-Detail rendering with ReSTIRYuchen Wang, Markus Kettunen, Daqi Lin, Chris Wyman 等SIGGRAPH 2026
- Spatiotemporal reservoir resampling for real-time ray tracing with dynamic direct lightingBenedikt Bitterli, Chris Wyman, Matt Pharr, Peter Shirley 等SIGGRAPH 2020 · 被引用 168 次
