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:20260817T171538Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T163000
DTEND;TZID=Asia/Tokyo:20241203T174000
UID:siggraphasia_SIGGRAPH Asia 2024_sess110@linklings.com
SUMMARY:Path Guiding, Scattering
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nMARS: Multi-samp
 le Allocation through Russian roulette and Splitting\n\nMultiple importanc
 e sampling (MIS) is an indispensable tool in rendering that constructs rob
 ust sampling strategies by combining the respective strengths of individua
 l distributions. Its efficiency can be greatly improved by carefully selec
 ting the number of samples drawn from each distribution, but...\n\n\nJoshu
 a Meyer, Alexander Rath, and Ömercan Yazici (Saarland Informatics Campus) 
 and Philipp Slusallek (German Research Center for Artificial Intelligence,
  Saarland Informatics Campus)\n---------------------\nVolume Scattering Pr
 obability Guiding\n\nSimulating the light transport of volumetric effects 
 poses significant challenges and costs, especially in the presence of hete
 rogeneous volumes. Generating stochastic paths for volume rendering involv
 es multiple decisions, and previous works mainly focused on directional an
 d distance sampling, wher...\n\n\nKehan Xu (ETH Zürich); Sebastian Herholz
  (Intel Corporation); Marco Manzi and Marios Papas (DisneyResearch|Studios
 ); and Markus Gross (DisneyResearch|Studios, ETH Zürich)\n----------------
 -----\nEfficient Neural Path Guiding with 4D Modeling\n\nPrevious local gu
 iding methods used 3D data structures to model spatial radiance variations
  but struggled with additional dimensions in the path integral, such as te
 mporal changes in dynamic scenes. Extending these structures to higher dim
 ensions also proves inefficient due to the curse of dimension...\n\n\nHong
 hao Dong, Rui Su, Guoping Wang, and Sheng Li (Peking University)\n--------
 -------------\nNeuSmoke: Efficient Smoke Reconstruction and View Synthesis
  with Neural Transportation Fields\n\nNovel view synthesis of smoke scenes
  presents a challenging problem. Previous neural approaches have suffered 
 from inadequate quality and inefficient training. We introduce NeuSmoke, a
 n efficient framework for dynamic smoke reconstruction using neural transp
 ortation fields, enabling high-quality den...\n\n\nJiaxiong Qiu (TMCC, Col
 lege of Computer Science, Nankai University; Horizon Robotics); Ruihong Ce
 n (TMCC, College of Computer Science, Nankai University); Zhong Li (Apple)
 ; Han Yan (Nankai TMCC, College of Computer Science, Nankai University); a
 nd Ming-Ming Cheng and Bo Ren (TMCC, College of Computer Science, Nankai U
 niversity)\n---------------------\nDynamic Neural Radiosity with Multi-gri
 d Decomposition\n\nPrior approaches to the neural rendering of global illu
 mination typically rely on complex network architectures and training stra
 tegies to model the global effects. This often leads to impractically high
  overheads for both training and inference. The neural radiosity technique
  marks a significant ad...\n\n\nRui Su, Honghao Dong, Jierui Ren, Haojie J
 in, Yisong Chen, Guoping Wang, and Sheng Li (Peking University)\n---------
 ------------\nNeural Global Illumination via Superposed Deformable Feature
  Fields\n\nInteractive rendering of dynamic scenes with complex global ill
 umination has been a long-standing problem in computer graphics.\nRecent a
 dvances in neural rendering demonstrate new promising possibilities.\nHowe
 ver, while existing methods have achieved impressive results, complex rend
 ering effects (e....\n\n\nChuankun Zheng, Yuchi Huo, Hongxiang Huang, and 
 Hongtao Sheng (State Key Laboratory of CAD&CG, Zhejiang University); Junro
 ng Huang (City University of Hong Kong); Rui Tang and Hao Zhu (Manycore In
 c.); and Rui Wang and Hujun Bao (State Key Laboratory of CAD&CG, Zhejiang 
 University)\n\nRegistration Category: Full Access, Full Access Supporter\n
 \nLanguage Format: English Language\n\nSession Chair: Michael Wimmer (TU W
 ien, Technische Universität Wien (TU Wien))
END:VEVENT
END:VCALENDAR