BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030502Z
LOCATION:Meeting Room S426+S427\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T104000
DTEND;TZID=Asia/Hong_Kong:20251216T114500
UID:siggraphasia_SIGGRAPH Asia 2025_sess118@linklings.com
SUMMARY:Sampling, Reconstruction & Variance Reduction
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nSZ Sequences: Binary-Constructed
  $(0, 2^q)$-Sequences\n\nLow-discrepancy sequences have seen widespread ad
 option in computer graphics thanks to the superior rates of convergence th
 at they provide.\nBecause rendering integrals often are comprised of produ
 cts of lower-dimensional integrals, recent work has focused on developing 
 sequences that are also well-d...\n\n\nAbdalla G. M. Ahmed (Shenzhen Unive
 rsity), Matt Pharr (NVIDIA), Victor Ostromoukhov (Université Claude Bernar
 d Lyon), and Hui Huang (Shenzhen University)\n---------------------\nStati
 stical Error Reduction for Monte Carlo Rendering\n\nDenoising is an import
 ant post-processing step in physically based Monte Carlo (MC) rendering. W
 hile neural networks are widely used in practice, statistical analysis has
  recently become a viable alternative for denoising. In this paper, we pre
 sent a general framework for statistics-based error redu...\n\n\nHiroyuki 
 Sakai, Christian Freude, Michael Wimmer, and David Hahn (Technische Univer
 sität Wien (TU Wien))\n---------------------\nJackknife Transmittance and 
 MIS Weight Estimation\n\nA core operation in Monte Carlo volume rendering 
 is transmittance estimation: Given a segment along a ray, the goal is to e
 stimate the fraction of light that will pass through this segment without 
 encountering absorption or out-scattering. A naive approach is to estimate
  optical depth τ using u...\n\n\nChristoph Peters (Delft University of Tec
 hnology)\n---------------------\nNonlinear Noise2Noise for Efficient Monte
  Carlo Denoiser Training\n\nThe Noise2Noise method allows for training mac
 hine learning-based denoisers with pairs of input and target images where 
 both the input and target can be noisy. This removes the need for training
  with clean target images, which can be difficult to obtain. However, Nois
 e2Noise training has a major lim...\n\n\nAndrew Tinits and Stephen Mann (U
 niversity of Waterloo)\n---------------------\nImperfect Image-Space Contr
 ol Variates for Monte Carlo Rendering\n\nWe present an image-space control
  variate technique to improve Monte Carlo~(MC) integration-based rendering
 . Our method selects spatially nearby pixel estimates as control variates 
 to exploit spatial coherence among pixel estimates in a rendered image wit
 hout requiring analytic modeling of the contr...\n\n\nChanu Yang and Bocha
 ng Moon (Gwangju Institute of Science and Technology)\n-------------------
 --\nDSCombiner: Double Shrinkage for Combining Biased and Unbiased Monte C
 arlo Renderings\n\nMonte Carlo rendering often faces a dilemma, namely, wh
 ether to choose an unbiased estimator or a biased one. Although different 
 integrators have been developed to address various scenarios, no single me
 thod can effectively manage all situations. Thus, finding a good approach 
 to combine different in...\n\n\nChenxi Zhou, Keheng Xu, Mufan Guo, Xianhao
  Yu, Zhimin Fan, Guihuan Feng, Yanwen Guo, and Jie Guo (Nanjing University
 )\n\nRegistration Category: Full Access, Full Access Supporter\n\nSession 
 Chair: Oliver Deussen (University of Konstanz)
END:VEVENT
END:VCALENDAR