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:20260817T171536Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T130000
DTEND;TZID=Asia/Tokyo:20241205T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess131@linklings.com
SUMMARY:Sampling and Light Transport
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nHierarchical Lig
 ht Sampling with Accurate Spherical Gaussian Lighting\n\nImportance sampli
 ng using a light tree (i.e., a hierarchy of light clusters) has been widel
 y used for many-light rendering. This technique samples a light source by 
 stochastically traversing the tree according to the importance of each nod
 e. While this importance should be close to the illumination ...\n\n\nYusu
 ke Tokuyoshi, Sho Ikeda, Paritosh Kulkarni, and Takahiro Harada (Advanced 
 Micro Devices, Inc.)\n---------------------\nBSDF importance sampling usin
 g a diffusion model\n\nMany real-world materials feature complex BSDFs (Bi
 directional Scattering Distribution Functions) that require significant st
 orage, making the use of neural networks to represent BSDFs appealing. Pre
 vious neural sampling methods, primarily using analytical lobe mixtures an
 d normalizing flows, often ...\n\n\nZiyang Fu, Yash Belhe, Haolin Lu, Liwe
 n Wu, Bing Xu, and Tzu-Mao Li (University of California San Diego)\n------
 ---------------\nDARTS: Diffusion Approximated Residual Time Sampling for 
 Time-of-flight Rendering in Homogeneous Scattering Media\n\nTime-of-flight
  (ToF) devices have greatly propelled the advancement of various multi-mod
 al perception applications. However, achieving accurate rendering of time-
 resolved information remains a challenge, particularly in scenes involving
  complex geometries, diverse materials and participating media. ...\n\n\nQ
 ianyue He, Dongyu Du, Haitian Jiang, and Xin Jin (Tsinghua Shenzhen Intern
 ational Graduate School)\n---------------------\nNeural Product Importance
  Sampling via Warp Composition\n\nAchieving high efficiency in modern phot
 orealistic rendering methods hinges on using Monte Carlo sampling distribu
 tions that closely approximate the illumination integral estimated for eve
 ry pixel. Samples are typically generated from a set of simple distributio
 ns, each targeting a different factor ...\n\n\nJoey Litalien (McGill Unive
 rsity) and Miloš Hašan, Fujun Luan, Krishna Mullia, and Iliyan Georgiev (A
 dobe Research)\n---------------------\nManifold Sampling for Differentiabl
 e Uncertainty in Radiance Fields\n\nRadiance fields are powerful and, henc
 e, popular models for representing the appearance of complex scenes. Yet, 
 constructing them based on image observations gives rise to ambiguities an
 d uncertainties. We propose a versatile approach for learning Gaussian rad
 iance fields with explicit and fine-grai...\n\n\nLinjie Lyu (Max Planck In
 stitute for Informatics), Ayush Tewari (MIT CSAIL), Marc Habermann (Max Pl
 anck Institute for Informatics), Shunsuke Saito and Michael Zollhöfer (Met
 a Codec Avatars Lab), and Thomas Leimkühler and Christian Theobalt (Max Pl
 anck Institute for Informatics)\n---------------------\nA Generalized Ray 
 Formulation For Wave-Optical Light Transport\n\nRay optics is the foundati
 on of modern path tracing and sampling algorithms for computer graphics; c
 rucially, it allows high-performance implementations based on ray tracing.
  However, many applications of interest in computer graphics and computati
 onal optics demand a more precise understanding of l...\n\n\nShlomi Steinb
 erg (University of Waterloo); Ravi Ramamoorthi (NVIDIA, University of Cali
 fornia San Diego); Benedikt Bitterli and Eugene d'Eon (NVIDIA); Ling-Qi Ya
 n (University of California Santa Barbara); and Matt Pharr (NVIDIA)\n\nReg
 istration Category: Full Access, Full Access Supporter\n\nLanguage Format:
  English Language\n\nSession Chair: Seungyong Lee (POSTECH)
END:VEVENT
END:VCALENDAR