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:20260817T171537Z
LOCATION:G510\, G Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T141000
DTEND;TZID=Asia/Tokyo:20241205T151000
UID:siggraphasia_SIGGRAPH Asia 2024_sess289@linklings.com
SUMMARY:Image Generation & Editing
DESCRIPTION:The Technical Communications program at SIGGRAPH Asia serves a
 s an invaluable platform for presenting cutting-edge work that may not nea
 tly align with the Technical Papers session. Attendees can expect to explo
 re fresh and thought-provoking ideas, glean practical insights from real-w
 orld production work, and discover innovative applications spanning variou
 s disciplines, from graphics and vision to AI and VR.\n\nDuring these sess
 ions, leading experts from academia and industry will present their latest
  findings, offering a glimpse into cutting-edge research and development. 
 From geometry and animation to virtual reality and machine learning, atten
 dees can expect to explore a diverse array of topics at the intersection o
 f graphics and other fields.\n\nUnder the overarching theme of Curious Min
 ds, attendees can delve into discussions surrounding innovation, interdisc
 iplinary discovery, and the role of education in shaping the future of tec
 hnology. Whether you’re a seasoned researcher or a curious enthusiast, the
  Technical Communications program promises to offer insights that spark cu
 riosity and inspire new perspectives.\n\nDiffOBI: Diffusion-based Image Ge
 neration of Oracle Bone Inscription Style Characters\n\nWe propose DiffOBI
 , a novel approach for generating images in the oracle bone inscription (O
 BI) style with unique pictographic features by using diffusion model.\n\n\
 nXiaoxuan Xie, Xusheng Du, and Minhao Li (Japan Advanced Institute of Scie
 nce and Technology (JAIST)); Xi Yang (Jilin University); and Haoran Xie (J
 apan Advanced Institute of Science and Technology (JAIST))\n--------------
 -------\nOrienText: Surface Oriented Textual Image Generation\n\nIntroduci
 ng OrienText: a GEN-AI method enhancing text alignment in images by levera
 ging surface normals, outperforming existing models for generating high-qu
 ality, accurately rendered text on oriented surfaces.\n\n\nShubham Singh P
 aliwal, Arushi Jain, Monika Sharma, Vikram Jamwal, and Lovekesh Vig (TCS R
 esearch)\n---------------------\nThe Secrets of Penalty Functions on Edge-
 preserving Image Smoothing\n\nWe study the influence of penalty functions 
 on the performance of the edge-preserving image smoothing from the shrinka
 ge rule perspective, and propose a simple optimization framework for edge-
 preserving image smoothing.\n\n\nXiqun Lu (Zhejiang University)\n---------
 ------------\nImproved Morphological Anti-Aliasing for Japanese Animation\
 n\nThis paper is about all the subtle changes made to MorphoLogical Anti-A
 liasing (MLAA) that make big differences when applied to Japanese Animatio
 n.\n\n\nTanguy Cesaratto, Alexandre Derouet-Jourdan, and Marc Salvati (OLM
  Digital, Inc.)\n---------------------\nCapturing Light with Robots: A Nov
 el Workflow for Reproducing Realistic Lens Flares\n\nThis research present
 s a motion control workflow designed to capture and replicate realistic le
 ns flares. To achieve accurate reproduction, it compares traditional image
  processing techniques with machine learning methods.\n\n\nVincent Maurer 
 (Filmakademie Baden-Württemberg)\n\nRegistration Category: Full Access, Fu
 ll Access Supporter\n\nLanguage Format: English Language\n\nSession Chair:
  Xi Yang (Jilin University)
END:VEVENT
END:VCALENDAR