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:20250110T023309Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T130000
DTEND;TZID=Asia/Tokyo:20241203T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess105@linklings.com
SUMMARY:Make It Yours - Customizing Image Generation
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nMoA: Mixture-of-Attention for Subject-Context Disentanglement in Perso
 nalized Image Generation\n\nWe introduce a new architecture for personaliz
 ation of text-to-image diffusion models, coined Mixture-of-Attention (MoA)
 . Inspired by the Mixture-of-Experts mechanism utilized in large language 
 models (LLMs), MoA distributes the generation workload between two attenti
 on pathways: a personalized bran...\n\n\nKuan-Chieh Wang, Daniil Ostashev,
  Yuwei Fang, Sergey Tulyakov, and Kfir Aberman (Snap Inc.)\n--------------
 -------\nCustomizing Text-to-Image Models with a Single Image Pair\n\nArt 
 reinterpretation is the practice of creating a variation of a reference wo
 rk, making a paired artwork that exhibits a distinct artistic style. We as
 k if such an image pair can be used to customize a generative model to cap
 ture the demonstrated stylistic difference. We propose Pair Customization,
 ...\n\n\nMaxwell Jones, Sheng-Yu Wang, and Nupur Kumari (Carnegie Mellon U
 niversity); David Bau (Northeastern University); and Jun-Yan Zhu (Carnegie
  Mellon University)\n---------------------\nPALP: Prompt Aligned Personali
 zation of Text-to-Image Models\n\nContent creators often aim to create per
 sonalized images using personal subjects that go beyond the capabilities o
 f conventional text-to-image models. Additionally, they may want the resul
 ting image to encompass a specific location, style, ambiance, and more. Ex
 isting personalization methods may com...\n\n\nMoab Arar (Tel Aviv Univers
 ity), Andrey Voynov and Amir Hertz (Google Research), Omri Avrahami (Hebre
 w University of Jerusalem), Shlomi Fruchter and Yael Pritch (Google Resear
 ch), Daniel Cohen-Or (Tel Aviv University), and Ariel Shamir (Reichman Uni
 versity)\n---------------------\nReVersion: Diffusion-Based Relation Inver
 sion from Images\n\nDiffusion models gain increasing popularity for their 
 generative capabilities. Recently, there have been surging needs to genera
 te customized images by inverting diffusion models from exemplar images, a
 nd existing inversion methods mainly focus on capturing object appearances
  (i.e., the "look"). How...\n\n\nZiqi Huang, Tianxing Wu, Yuming Jiang, Ke
 lvin C.K. Chan, and Ziwei Liu (S-Lab for Advanced Intelligence, Nanyang Te
 chnological University Singapore)\n---------------------\nIdentity-Preserv
 ing Face Swapping via Dual Surrogate Generative Models\n\nIn this study, w
 e revisit the fundamental setting of face-swapping models and reveal that 
 only using implicit supervision for training leads to the difficulty of ad
 vanced methods to preserve the source identity. We propose a novel reverse
  pseudo-input generation approach to offer supplemental data f...\n\n\nZiy
 ao Huang and Fan Tang (Institute of Computing Technology, Chinese Academy 
 of Sciences); Yong Zhang (Tencent); Juan Cao, Chengyu Li, Sheng Tang, and 
 Jintao Li (Institute of Computing Technology, Chinese Academy of Sciences)
 ; and Tong-Yee Lee (National Cheng Kung University)\n---------------------
 \nCustomizing Text-to-Image Diffusion with Object Viewpoint Control\n\nMod
 el customization introduces new concepts to existing text-to-image models,
  enabling the generation of these new concepts/objects in novel contexts.\
 nHowever, such methods lack accurate camera view control with respect to t
 he new object, and users must resort to prompt engineering (e.g., adding "
 to...\n\n\nNupur Kumari and Grace Su (Carnegie Mellon Uniersity); Richard 
 Zhang, Taesung Park, and Eli Shechtman (Adobe Research); and Jun-Yan Zhu (
 Carnegie Mellon Uniersity)\n\nRegistration Category: Full Access, Full Acc
 ess Supporter\n\nLanguage Format: English Language\n\nSession Chair: Kfir 
 Aberman (Snap)
END:VEVENT
END:VCALENDAR