BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030325Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251218T131000
DTEND;TZID=Asia/Hong_Kong:20251218T141500
UID:siggraphasia_SIGGRAPH Asia 2025_sess155@linklings.com
SUMMARY:Diffusion-Based Image Editing & Manipulation
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nIn-Context Brush: Zero-shot Cust
 omized Subject Insertion with Context-Aware Latent Space Manipulation\n\nR
 ecent advances in diffusion models have enhanced multimodal-guided visual 
 generation, enabling customized subject insertion that seamlessly "brushes
 " user-specified objects into a given image guided by textual prompts. How
 ever, existing methods often struggle to insert customized subjects with h
 igh...\n\n\nYu Xu, Fan Tang, You Wu, and Lin Gao (Institute of Computing T
 echnology, Chinese Academy of Sciences); Oliver Deussen (University of Kon
 stanz); Hongbin Yan (University of Chinese Academy of Sciences); Jintao Li
  and Juan Cao (Institute of Computing Technology, Chinese Academy of Scien
 ces); and Tong-Yee Lee (National Cheng-Kung University)\n-----------------
 ----\nBlobCtrl: Taming Controllable Blob for Element-level Image Editing\n
 \nAs user expectations for image editing continue to rise, the demand for 
 flexible, fine-grained manipulation of specific visual elements presents a
  challenge for current diffusion-based methods.\n\n    In this work, we pr
 esent BlobCtrl, a framework for element-level image editing based on a pro
 babilist...\n\n\nYaowei Li (Peking University); Lingen Li (Chinese Univers
 ity of Hong Kong); Zhaoyang Zhang, Xiaoyu Li, and Guangzhi Wang (Tencent);
  Hongxiang Li (The Hong Kong University of Science and Technology); Xiaodo
 ng Cun (GVC Lab, Great Bay University); Ying Shan (Tencent); and Yuexian Z
 ou (Peking University)\n---------------------\nThe Aging Multiverse: Gener
 ating Condition-Aware Facial Aging Tree via Training-Free Diffusion\n\nWe 
 introduce the Aging Multiverse, a framework for generating multiple plausi
 ble facial aging trajectories from a single image, each conditioned on ext
 ernal factors such as environment, health, and lifestyle. Unlike prior met
 hods that model aging as a single deterministic path, our approach creates
  ...\n\n\nBang Gong and Luchao Qi (University of North Carolina at Chapel 
 Hill (UNC)); Jiaye Wu (University of Maryland College Park); Zhicheng Fu, 
 Chunbo Song, and John Nicholson (Lenovo); and Roni Sengupta (University of
  North Carolina at Chapel Hill (UNC))\n---------------------\nDreamO: A Un
 ified Framework for Image Customization\n\nRecently, extensive research on
  image customization (e.g., identity, subject, style, background, etc.) de
 monstrates strong customization capabilities in large-scale generative mod
 els. However, most approaches are designed for specific tasks, restricting
  their generalizability to combine different ty...\n\n\nChong Mou (Bytedan
 ce, Peking University); Yanze Wu, Wenxu Wu, Zinan Guo, Pengze Zhang, Yufen
 g Cheng, Yiming Luo, Fei Ding, Shiwen Zhang, Xinghui Li, Mengtian Li, Ming
 cong Liu, Yunsheng Jiang, Shaojin Wu, and Songtao Zhao (Bytedance); Jian Z
 hang (Peking University); and Qian He and Xinglong Wu (Bytedance)\n-------
 --------------\nConsistEdit: Highly Consistent and Precise Training-free V
 isual Editing\n\nRecent advances in training-free attention control method
 s have enabled flexible and efficient text-guided editing capabilities for
  existing image and video generation models. However, current approaches s
 truggle to simultaneously deliver strong editing strength while preserving
  consistency with the...\n\n\nZixin Yin (Hong Kong University of Science a
 nd Technology); Ling-Hao Chen (Tsinghua University, International Digital 
 Economy Academy); Lionel Ni (Hong Kong University of Science and Technolog
 y, Guangzhou; Hong Kong University of Science and Technology); and Xili Da
 i (Hong Kong University of Science and Technology, Guangzhou)\n-----------
 ----------\nVoost: A Unified and Scalable Diffusion Transformer for Bidire
 ctional Virtual Try-On and Try-Off\n\nVirtual try-on aims to synthesize a 
 realistic image of a person wearing a target garment, but accurately model
 ing garment–body correspondence remains a persistent challenge, especially
  under pose and appearance variation.\nIn this paper, we propose Voost—a u
 nified and scalable framework t...\n\n\nSeungyong Lee (NXN LABS, Korea Adv
 anced Institute of Science and Technology (KAIST)) and Jeonggi Kwak (Unive
 rsity of British Columbia, Korea University)\n\nRegistration Category: Ful
 l Access, Full Access Supporter\n\nSession Chair: Ali Mahdavi-Amiri (Simon
  Fraser University, MARZ VFX)
END:VEVENT
END:VCALENDAR