BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205513Z
LOCATION:Room 408 A
DTSTART;TZID=America/Los_Angeles:20260722T090000
DTEND;TZID=America/Los_Angeles:20260722T103000
UID:siggraph_SIGGRAPH 2026_sess141@linklings.com
SUMMARY:Efficient Sampling: ReSTIR and More
DESCRIPTION:Spatio-Temporal Control Variates with ReSTIR for Real-Time Ren
 dering\n\nWe present ReSTCV, a real-time path tracing method that integrat
 es spatio-temporal control variates into ReSTIR. By improving sample reuse
  beyond single-sample estimation, our approach significantly reduces noise
 , especially chromatic noise under complex lighting, while maintaining eff
 iciency and re...\n\n\nZhong Shi and Cunhao Wu (CS Dept, Tsinghua Universi
 ty); Lifan Wu (NVIDIA); and Kun Xu (CS Dept, Tsinghua University)\n-------
 --------------\nToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal 
 Reservoir Resampling\n\nWe present a novel method for simulating time-of-f
 light imaging in complex, dynamic scenes. By reusing and correcting light 
 paths, our approach enables interactive performance and supports applicati
 ons such as shape reconstruction and navigation under practical real-time 
 constraints.\n\n\nJuhyeon Kim, Wojciech Jarosz, and Adithya Pediredla (Dar
 tmouth College)\n---------------------\nReSTIR BDPT: Bidirectional ReSTIR 
 Path Tracing with Caustics\n\nReSTIR accelerates path tracing by reusing s
 amples between pixels. However, existing methods are limited by the sampli
 ng quality of path tracing, making them inefficient for scenes with causti
 cs and hard-to-reach lights. We develop a ReSTIR variant incorporating bid
 irectional path tracing that signi...\n\n\nTrevor Hedstrom (University of 
 California San Diego); Markus Kettunen, Daqi Lin, and Chris Wyman (NVIDIA)
 ; Tzu-Mao Li (University of California San Diego); and Trevor Hedstrom\n--
 -------------------\nReal-Time Level-of-Detail rendering with ReSTIR\n\nWe
  propose a method to overcome a limitation in ReSTIR path tracing by intro
 ducing a surface point mapping to reuse samples across frames containing m
 eshes with different topologies and enabling real-time LoD rendering with 
 ReSTIR.\n\n\nYu-Chen Wang (University of California Irvine); Markus Kettun
 en, Daqi Lin, Chris Wyman, and Lifan Wu (NVIDIA); and Shuang Zhao (Univers
 ity of Illinois Urbana-Champaign)\n---------------------\nMulti-Layer Rese
 rvoir Splatting for Temporal Reuse under Disocclusion\n\nThis work address
 es disocclusion noise in ReSTIR by extending the framework to multiple scr
 een-space layers. This enables occluded samples in previous frames to cont
 ribute to the final image, improving temporal reuse in disoccluded regions
 . Depth ranges and active domains are introduced to reduce co...\n\n\nPeng
 pei Hong and Song Zhang (University of Utah); Daqi Lin, Markus Kettunen, a
 nd Chris Wyman (NVIDIA); and Cem Yuksel (University of Utah)\n------------
 ---------\nForget Superresolution, Sample Adaptively (when Path Tracing)\n
 \nWe introduce an end-to-end adaptive sampling and denoising pipeline for 
 sparse real-time path tracing. Our method trains stably despite discrete s
 ampling decisions and uses perceptual, tonemapping-aware optimization to p
 lace samples where they matter most. It samples fine structures, specular 
 highli...\n\n\nMartin Balint, Corentin Salaün, Hans-Peter Seidel, and Karo
 l Myszkowski (Max Planck Institute for Informatics)\n---------------------
 \nEfficient Sampling: ReSTIR and More - Interactive Discussion\n\nAfter th
 e summary presentations, attendees will participate in an interactive disc
 ussion. Outside the room will be a series of poster boards for authors to 
 gather around with the audience. Authors are invited to bring any material
  related to their paper that could instigate further conversation such...\
 n\n\nInterest Area: Research & Education\n\nKeyword: Artificial Intelligen
 ce/Machine Learning, Real-Time, Rendering\n\nRegistration Category: Full C
 onference Supporter, Full Conference\n\nSession Chair: Victor Ostromoukhov
  (Université Claude Bernard Lyon, CNRS - LIRIS)
END:VEVENT
END:VCALENDAR