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:20250110T023313Z
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:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nFaceMap: Distortion-Driven Perceptual Facial Saliency Maps\n\nHumans a
 re uniquely sensitive to faces. Recognizing fine detail in faces plays an 
 important role in social cognition, identity; and it is key to human inter
 action. In this work, we present the first quantitative study of the relat
 ive importance of face regions to human observers. We created a datase...\
 n\n\nZhongshi Jiang, Kishore Venkateshan, Giljoo Nam, Meixu Chen, Romain B
 achy, Jean-Charles Bazin, and Alexandre Chapiro (Meta)\n------------------
 ---\nBoosting 3D Object Generation through PBR Materials\n\nAutomatic 3D c
 ontent creation has gained increasing attention recently, due to its poten
 tial in various applications such as video games, film industry, and AR/VR
 . \nRecent advancements in diffusion models and multimodal models have not
 ably improved the quality and efficiency of 3D object generation ...\n\n\n
 Yitong Wang (Fudan University, Shanghai Artificial Intelligence Laboratory
 ); Xudong Xu (Shanghai Artificial Intelligence Laboratory); Li Ma (Scanlin
 e VFX Studio); Haoran Wang (Shanghai Jiaotong University); and Bo Dai (Sha
 nghai Artificial Intelligence Laboratory)\n---------------------\nGPU Coro
 utines for Flexible Splitting and Scheduling of Rendering Tasks\n\nWe intr
 oduce coroutines into GPU kernel programming, providing an automated solut
 ion for flexible splitting and scheduling of rendering tasks. This approac
 h addresses a prevalent challenge in harnessing the power of modern GPUs f
 or complex, imbalanced graphics workloads like path tracing. Usually, t...
 \n\n\nShaokun Zheng, Xin Chen, and Zhong Shi (Tsinghua University); Ling-Q
 i Yan (University of California Santa Barbara); and Kun Xu (Tsinghua Unive
 rsity)\n---------------------\nEnhancing the Aesthetics of 3D Shapes via R
 eference-based Editing\n\nWhile there have been previous works that explor
 ed methods to enhance the aesthetics of images, the automated beautificati
 on 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 aes
 thetics of general 3D shapes. ...\n\n\nMinchan Chen and Manfred Lau (City 
 University of Hong Kong)\n---------------------\nProcedural Material Gener
 ation with Reinforcement Learning\n\nModern 3D content creation heavily re
 lies on procedural assets. In particular, procedural materials are ubiquit
 ous in the industry, but their manipulation remains challenging. Previous 
 work conditionally generates procedural graphs that match a given input im
 age. However, the parameter generation st...\n\n\nBeichen Li (MIT CSAIL, A
 dobe Research); Yiwei Hu, Paul Guerrero, and Milos Hasan (Adobe Research);
  Liang Shi (MIT CSAIL); Valentin Deschaintre (Adobe Research); and Wojciec
 h Matusik (MIT CSAIL)\n---------------------\nControlled Spectral Upliftin
 g for Indirect-Light-Metamerism\n\nSpectral rendering has received increas
 ing attention in recent years. Yet, solutions to define spectral reflectan
 ces are mostly limited to techniques which deterministically uplift existi
 ng RGB inputs. Only recently has uplifting enabled constraining a surface 
 appearance under direct illuminants. Ye...\n\n\nMark van de Ruit and Elmar
  Eisemann (Delft University of Technology)\n\nRegistration Category: Full 
 Access, Full Access Supporter\n\nLanguage Format: English Language\n\nSess
 ion Chair: Valentin Deschaintre (Adobe Research)
END:VEVENT
END:VCALENDAR