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:20250110T023312Z
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:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nMARS: Multi-sample Allocation through Russian roulette and Splitting\n
 \nMultiple importance sampling (MIS) is an indispensable tool in rendering
  that constructs robust sampling strategies by combining the respective st
 rengths of individual distributions. Its efficiency can be greatly improve
 d by carefully selecting the number of samples drawn from each distributio
 n, but...\n\n\nJoshua Meyer, Alexander Rath, and Ömercan Yazici (Saarland 
 Informatics Campus) and Philipp Slusallek (German Research Center for Arti
 ficial Intelligence, Saarland Informatics Campus)\n---------------------\n
 Neural Global Illumination via Superposed Deformable Feature Fields\n\nInt
 eractive rendering of dynamic scenes with complex global illumination has 
 been a long-standing problem in computer graphics.\nRecent advances in neu
 ral rendering demonstrate new promising possibilities.\nHowever, while exi
 sting methods have achieved impressive results, complex rendering effects 
 (e....\n\n\nChuankun Zheng, Yuchi Huo, Hongxiang Huang, and Hongtao Sheng 
 (State Key Laboratory of CAD&CG, Zhejiang University); Junrong Huang (City
  University of Hong Kong); Rui Tang and Hao Zhu (Manycore Inc.); and Rui W
 ang and Hujun Bao (State Key Laboratory of CAD&CG, Zhejiang University)\n-
 --------------------\nEfficient Neural Path Guiding with 4D Modeling\n\nPr
 evious local guiding methods used 3D data structures to model spatial radi
 ance variations but struggled with additional dimensions in the path integ
 ral, such as temporal changes in dynamic scenes. Extending these structure
 s to higher dimensions also proves inefficient due to the curse of dimensi
 on...\n\n\nHonghao Dong, Rui Su, Guoping Wang, and Sheng Li (Peking Univer
 sity)\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 introd
 uce NeuSmoke, an efficient framework for dynamic smoke reconstruction usin
 g neural transportation fields, enabling high-quality den...\n\n\nJiaxiong
  Qiu (TMCC, College of Computer Science, Nankai University; Horizon Roboti
 cs); Ruihong Cen (TMCC, College of Computer Science, Nankai University); Z
 hong Li (Apple); Han Yan (Nankai TMCC, College of Computer Science, Nankai
  University); and Ming-Ming Cheng and Bo Ren (TMCC, College of Computer Sc
 ience, Nankai University)\n---------------------\nVolume Scattering Probab
 ility Guiding\n\nSimulating the light transport of volumetric effects pose
 s significant challenges and costs, especially in the presence of heteroge
 neous volumes. Generating stochastic paths for volume rendering involves m
 ultiple decisions, and previous works mainly focused on directional and di
 stance sampling, wher...\n\n\nKehan Xu (ETH Zürich); Sebastian Herholz (In
 tel Corporation); Marco Manzi and Marios Papas (DisneyResearch|Studios); a
 nd Markus Gross (DisneyResearch|Studios, ETH Zürich)\n--------------------
 -\nDynamic Neural Radiosity with Multi-grid Decomposition\n\nPrior approac
 hes to the neural rendering of global illumination typically rely on compl
 ex network architectures and training strategies to model the global effec
 ts. This often leads to impractically high overheads for both training and
  inference. The neural radiosity technique marks a significant ad...\n\n\n
 Rui Su, Honghao Dong, Jierui Ren, Haojie Jin, Yisong Chen, Guoping Wang, a
 nd Sheng Li (Peking University)\n\nRegistration Category: Full Access, Ful
 l Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: 
 Michael Wimmer (TU Wien)
END:VEVENT
END:VCALENDAR