BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171531Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T090000
DTEND;TZID=Asia/Tokyo:20241205T101000
UID:siggraphasia_SIGGRAPH Asia 2024_sess125@linklings.com
SUMMARY:(Don't) Make Some Noise: Denoising
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nA Statistical Ap
 proach to Monte Carlo Denoising\n\nThe stochastic nature of modern Monte C
 arlo (MC) rendering methods inevitably produces noise in rendered images f
 or a practical number of samples per pixel. The problem of denoising these
  images has been widely studied, with most recent methods relying on data-
 driven, pretrained neural networks. In ...\n\n\nHiroyuki Sakai and Christi
 an Freude (Technical University of Vienna), Thomas Auzinger (Institute of 
 Science and Technology Austria), and David Hahn and Michael Wimmer (Techni
 cal University of Vienna)\n---------------------\nOnline Neural Denoising 
 with Cross-Regression for Interactive Rendering\n\nGenerating a rendered i
 mage sequence through Monte Carlo ray tracing is an appealing option when 
 one aims to accurately simulate various lighting effects. Unfortunately, i
 nteractive rendering scenarios limit the allowable sample size for such sa
 mpling-based light transport algorithms, resulting in a...\n\n\nHajin Choi
  (Gwangju Institute of Science and Technology); Seokpyo Hong (Samsung Adva
 nced Institute of Technology); Inwoo Ha (Samsung Advanced Institute of Tec
 hnology, KAIST); Nahyup Kang (Samsung Advanced Institute of Technology); a
 nd Bochang Moon (Gwangju Institute of Science and Technology)\n-----------
 ----------\nFiltering-Based Reconstruction for Gradient-Domain Rendering\n
 \nGradient-domain rendering methods reconstruct color images based on the 
 Poisson equation with gradients from correlated sampling. The relatively l
 ow variance in the gradient estimation facilitates convergence but the ine
 vitable noises make the solving process prone to unpleasant spiky artifact
 s.\n\nWe...\n\n\nDifei Yan and Shaokun Zheng (Tsinghua University), Ling-Q
 i Yan (University of California Santa Barbara), and Kun Xu (Tsinghua Unive
 rsity)\n---------------------\nSpatiotemporal Bilateral Gradient Filtering
  for Inverse Rendering\n\nIn inverse rendering, gradient-based methods, wh
 ich have seen great progress in the recent years, are typically used in co
 njunction with the Adam optimizer. While Adam usually improves convergence
  by temporally filtering gradients over previous iterations to reduce nois
 e, it is not tailored to inver...\n\n\nWesley Chang, Xuanda Yang, Yash Bel
 he, Ravi Ramamoorthi, and Tzu-Mao Li (University of California San Diego)\
 n---------------------\nNeural Kernel Regression for Consistent Monte Carl
 o Denoising\n\nUnbiased Monte Carlo path tracing that is extensively used 
 in realistic rendering produces undesirable noise, especially with low sam
 ples per pixel (spp). Recently, several methods have coped with this probl
 em by importing unbiased noisy images and auxiliary features to neural net
 works to either pre...\n\n\nQi Wang (State Key Laboratory of CAD&CG, Zheji
 ang University); Pengju Qiao (Institute of Software Chinese Academy of Sci
 ences; State Key Laboratory of CAD&CG, Zhejiang University); Yuchi Huo (St
 ate Key Laboratory of CAD&CG, Zhejiang University; Zhejiang University); S
 hiji Zhai (Institute of Computing Technology, Chinese Academy of Sciences)
 ; Zixuan Xie (Institute of Computing Technology, Chinese Academy of Scienc
 es; Zhejiang Lab); Rengan Xie (State Key Laboratory of CAD&CG, Zhejiang Un
 iversity); Wei Hua (Zhejiang Lab); Hujun Bao (State Key Laboratory of CAD&
 CG, Zhejiang University; Zhejiang University); and Tao Liu (Shanghai Marit
 ime University, College of Transport & Communications)\n\nRegistration Cat
 egory: Full Access, Full Access Supporter\n\nLanguage Format: English Lang
 uage\n\nSession Chair: Wenzel Jakob (École Polytechnique Féderale de Lausa
 nne (EPFL), NVIDIA)
END:VEVENT
END:VCALENDAR