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:20260817T171532Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T144500
DTEND;TZID=Asia/Tokyo:20241206T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess149@linklings.com
SUMMARY:Enhancing, Saliency
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nBoosting 3D Obje
 ct Generation through PBR Materials\n\nAutomatic 3D content creation has g
 ained increasing attention recently, due to its potential in various appli
 cations such as video games, film industry, and AR/VR. \nRecent advancemen
 ts in diffusion models and multimodal models have notably improved the qua
 lity and efficiency of 3D object generation ...\n\n\nYitong Wang (Fudan Un
 iversity, Shanghai Artificial Intelligence Laboratory); Xudong Xu (Shangha
 i Artificial Intelligence Laboratory); Li Ma (Scanline VFX Studio); Haoran
  Wang (Shanghai Jiaotong University); and Bo Dai (Shanghai Artificial Inte
 lligence Laboratory)\n---------------------\nFaceMap: Distortion-Driven Pe
 rceptual Facial Saliency Maps\n\nHumans are uniquely sensitive to faces. R
 ecognizing fine detail in faces plays an important role in social cognitio
 n, identity; and it is key to human interaction. In this work, we present 
 the first quantitative study of the relative importance of face regions to
  human observers. We created a datase...\n\n\nZhongshi Jiang, Kishore Venk
 ateshan, Giljoo Nam, Meixu Chen, Romain Bachy, Jean-Charles Bazin, and Ale
 xandre Chapiro (Meta)\n---------------------\nEnhancing the Aesthetics of 
 3D Shapes via Reference-based Editing\n\nWhile there have been previous wo
 rks that explored methods to enhance the aesthetics of images, the automat
 ed beautification of 3D shapes has been limited to specific shapes such as
  3D face models. In this paper, we introduce a framework to automatically 
 enhance the aesthetics of general 3D shapes. ...\n\n\nMinchan Chen and Man
 fred Lau (City University of Hong Kong)\n---------------------\nControlled
  Spectral Uplifting for Indirect-Light-Metamerism\n\nSpectral rendering ha
 s received increasing attention in recent years. Yet, solutions to define 
 spectral reflectances are mostly limited to techniques which deterministic
 ally uplift existing RGB inputs. Only recently has uplifting enabled const
 raining a surface appearance under direct illuminants. Ye...\n\n\nMark van
  de Ruit and Elmar Eisemann (Delft University of Technology)\n------------
 ---------\nProcedural Material Generation with Reinforcement Learning\n\nM
 odern 3D content creation heavily relies on procedural assets. In particul
 ar, procedural materials are ubiquitous in the industry, but their manipul
 ation remains challenging. Previous work conditionally generates procedura
 l graphs that match a given input image. However, the parameter generation
  st...\n\n\nBeichen Li (MIT CSAIL, Adobe Research); Yiwei Hu, Paul Guerrer
 o, and Milos Hasan (Adobe Research); Liang Shi (MIT CSAIL); Valentin Desch
 aintre (Adobe Research); and Wojciech Matusik (MIT CSAIL)\n---------------
 ------\nGPU Coroutines for Flexible Splitting and Scheduling of Rendering 
 Tasks\n\nWe introduce coroutines into GPU kernel programming, providing an
  automated solution for flexible splitting and scheduling of rendering tas
 ks. This approach addresses a prevalent challenge in harnessing the power 
 of modern GPUs for complex, imbalanced graphics workloads like path tracin
 g. Usually, t...\n\n\nShaokun Zheng, Xin Chen, and Zhong Shi (Tsinghua Uni
 versity); Ling-Qi Yan (University of California Santa Barbara); and Kun Xu
  (Tsinghua University)\n\nRegistration Category: Full Access, Full Access 
 Supporter\n\nLanguage Format: English Language\n\nSession Chair: Valentin 
 Deschaintre (Adobe Research)
END:VEVENT
END:VCALENDAR