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:20260417T190109Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250813T090000
DTEND;TZID=America/Los_Angeles:20250813T103000
UID:siggraph_SIGGRAPH 2025_sess127@linklings.com
SUMMARY:Monte-Carlo Rendering & Sampling
DESCRIPTION:Monte-Carlo Rendering & Sampling - Interactive Discussion\n\nA
 fter the summary presentations, attendees will participate in an interacti
 ve discussion. Outside the room will be a series of poster boards for auth
 ors to gather around with the audience. Authors are invited to bring any m
 aterial related to their paper that could instigate further conversation s
 uch...\n\n---------------------\nPractical Stylized Nonlinear Monte Carlo 
 Rendering\n\nWe present a practical method for rendering scenes with compl
 ex, recursive nonlinear stylization applied to physically based rendering.
  Our approach introduces nonlinear path filtering(NL-PF) and nonlinear neu
 ral radiance caching(NL-NRC), which reduce the exponential sampling cost o
 f stylized render...\n\n\nXiaochun Tong and Toshiya Hachisuka (University 
 of Waterloo)\n---------------------\nHistogram Stratification for Spatio-T
 emporal Reservoir Sampling\n\nThis paper introduces stratification into re
 sampled importance sampling (RIS) technique for real-time photorealistic r
 endering. It organizes sample candidates into local histograms and then em
 ploys Quasi Monte Carlo and antithetic patterns for efficient sampling. Th
 is low-overhead approach significa...\n\n\nCorentin Salaun and Martin Bali
 nt (Max Planck Institute for Informatics), Laurent Belcour and Eric Heitz 
 (Intel), and Gurprit Singh and Karol Myszkowski (Max Planck Institute for 
 Informatics)\n---------------------\nMultiple Importance Reweighting for P
 ath Guiding\n\nWe combine the estimates generated in each guiding iteratio
 n, leveraging the importance distributions from multiple guiding iteration
 s. We demonstrate that our path-level reweighting makes guiding algorithms
  less sensitive to noise and overfitting in distributions.\n\n\nZhimin Fan
 , Yiming Wang, and Chenxi Zhou (Nanjing University); Ling-Qi Yan (Universi
 ty of California Santa Barbara); and Yanwen Guo and Jie Guo (Nanjing Unive
 rsity)\n---------------------\nCorrect your balance heuristic: Optimizing 
 balance-style multiple importance sampling weights\n\nMultiple importance 
 sampling (MIS) is vital to most rendering algorithms. MIS computes a weigh
 ted sum of samples from different techniques to handle diverse scene types
  and lighting effects.\nWe propose a practical weight correction scheme th
 at yields better equal-time performance on bidirectional al...\n\n\nQingqi
 n Hua and Pascal Grittmann (Saarland University) and Philipp Slusallek (Sa
 arland University, DFKI)\n---------------------\nSobol' Sequences with Gua
 ranteed-Quality 2D Projections\n\nIn the context of quasi-Monte Carlo rend
 ering, we introduce a new Sobol' construction and demonstrate that particu
 lar pairs of polynomials of the form p and p^2+p+1 in Sobol'-based samplin
 g lead to (1, 2)-sequences. They can be combined to form high-dimensional 
 low discrepancy sequences with good 2D...\n\n\nNicolas Bonneel and David C
 oeurjolly (CNRS - LIRIS) and Jean-Claude Iehl and Victor Ostromoukhov (Uni
 versité Claude Bernard Lyon 1, CNRS - LIRIS)\n---------------------\nVecto
 r-Valued Monte Carlo Integration Using Ratio Control Variates\n\nVariance 
 reduction techniques are widely used to reduce the noise of Monte Carlo in
 tegration. However, these techniques are typically designed with the assum
 ption that the integrand is scalar-valued. To address this, we introduce r
 atio control variations, an estimator that leverages a ratio-based ap...\n
 \n\nHaolin Lu (UC San Diego, MPI for Informatics); Delio Vicini (Google In
 c.); and Wesley Chang and Tzu-Mao Li (UC San Diego)\n\nInterest Area: Rese
 arch & Education\n\nRecording: Livestreamed, Not Livestreamed, Recorded, N
 ot Recorded\n\nRegistration Category: Full Conference, Virtual Access, Wed
 nesday\n\nSession Chair: Delio Vicini (Google)
END:VEVENT
END:VCALENDAR