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:20251218T030402Z
LOCATION:Meeting Room S426+S427\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251215T131000
DTEND;TZID=Asia/Hong_Kong:20251215T141500
UID:siggraphasia_SIGGRAPH Asia 2025_sess106@linklings.com
SUMMARY:Global Illumination & Real-Time Rendering
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\nFrame-Free Representation of Pol
 arized Light for Resolving Stokes Vector Singularities\n\nStokes parameter
 s are the standard representation of polarized light intensity in Mueller 
 calculus and are widely used in polarization-aware computer graphics. Howe
 ver, their reliance on local frames--aligned with ray propagation directio
 ns--introduces a fundamental limitation: numerical discontinui...\n\n\nShi
 nyoung Yi (Korea Advanced Institute of Science and Technology (KAIST), Kyu
 ng Hee University) and Jiwoong Na, Seungmin Hwang, Inseung Hwang, and Min 
 H. Kim (Korea Advanced Institute of Science and Technology (KAIST))\n-----
 ----------------\nGS-ROR2: Bidirectional-guided 3DGS and SDF for Reflectiv
 e Object  Relighting and Reconstruction\n\n3D Gaussian Splatting (3DGS) ha
 s shown a powerful capability for novel view synthesis due to its detailed
  expressive ability and highly efficient rendering speed. Unfortunately, c
 reating relightable 3D assets and reconstructing faithful geometry with 3D
 GS is still problematic, particularly for refle...\n\n\nZuo-Liang Zhu (Nan
 kai University), Beibei Wang (Nanjing University), and Jian Yang (Nankai U
 niversity)\n---------------------\nNeLiF: Neural Lighting Function Generat
 ion for Real-Time Indoor Rendering\n\nRecent advances in neural rendering 
 have extensively explored modeling\nthe radiance fields with neural repres
 entations, while overlooking the under-\nlying mechanisms for producing va
 rious lighting effects, and consequently\nleading to limited adaptability 
 to dynamic scenes. These lighting effects,\nin...\n\n\nHongtao Sheng (Stat
 e Key Laboratory of CAD&CG, Zhejiang University); Yuchi Huo (State Key Lab
 oratory of CAD&CG, Zhejiang University; Zhejiang Lab); Chuankun Zheng, Gua
 ngzhi Han, and Bin Zang (State Key Laboratory of CAD&CG, Zhejiang Universi
 ty); Yifan Peng (The University of Hong Kong); Shi Li (State Key Laborator
 y of CAD&CG, Zhejiang University); Hao Zhu, Rui Tang, and Yiming Wu (Manyc
 ore Tech Inc.); and Rui Wang and Hujun Bao (State Key Laboratory of CAD&CG
 , Zhejiang University)\n---------------------\nReSTIR PG: Path Guiding wit
 h Spatiotemporally Resampled Paths\n\nWe present ReSTIR Path Guiding (ReST
 IR-PG), a real-time method that extracts guiding distributions from resamp
 led paths produced by ReSTIR and uses them to generate improved initial ca
 ndidates for the next frame. While ReSTIR significantly reduces variance t
 hrough spatiotemporal resampling, its effe...\n\n\nZHENG ZENG (University 
 of California Santa Barbara, NVIDIA); Markus Kettunen, Chris Wyman, and Li
 fan Wu (NVIDIA); Ravi Ramamoorthi (NVIDIA, University of California San Di
 ego); Ling-Qi Yan (Mohamed bin Zayed University of Artificial Intelligence
 ); and Daqi Lin (NVIDIA)\n---------------------\nSample Space Partitioning
  and Spatiotemporal Resampling for Specular Manifold Sampling\n\nCaustics 
 rendering remains a long-standing challenge in Monte Carlo rendering becau
 se high-energy specular paths occupy only a small region of path space, ma
 king them difficult to sample effectively. Recent work such as Specular Ma
 nifold Sampling (SMS) [Zeltner et al. 2020] can stochastically sample...\n
 \n\nPengpei Hong (University of Utah), Meng Duan (Nankai University), Beib
 ei Wang (Nanjing University), Cem Yuksel (University of Utah), and Tizian 
 Zeltner and Daqi Lin (NVIDIA)\n---------------------\nVertex Features for 
 Neural Global Illumination\n\nRecent research on learnable neural represen
 tations has been widely adopted in the field of 3D scene reconstruction an
 d neural rendering applications. However, traditional feature grid represe
 ntations often suffer from substantial memory footprint, posing a signific
 ant bottleneck for modern parallel...\n\n\nRui Su, Honghao Dong, Haojie Ji
 n, Yisong Chen, Guoping Wang, and Sheng Li (Peking University)\n\nRegistra
 tion Category: Full Access, Full Access Supporter\n\nSession Chair: Yuchi 
 Huo (Zhejiang University, Korea Advanced Institute of Science and Technolo
 gy)
END:VEVENT
END:VCALENDAR