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:20260817T171539Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241204T130000
DTEND;TZID=Asia/Tokyo:20241204T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess116@linklings.com
SUMMARY:It's All About Change: Image Editing
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nDiffUHaul: A Tra
 ining-Free Method for Object Dragging in Images\n\nText-to-image diffusion
  models have proven effective for solving many image editing tasks.\n    H
 owever, the seemingly straightforward task of seamlessly relocating object
 s within a scene remains surprisingly challenging. Existing methods addres
 sing this problem often struggle to function reliably in...\n\n\nOmri Avra
 hami (Hebrew University of Jerusalem), Rinon Gal (Tel Aviv University), Ga
 l Chechik (NVIDIA), Ohad Fried (The Interdisciplinary Center Herzliya), Da
 ni Lischinski (Hebrew University of Jerusalem), and Arash Vahdat and Weili
  Nie (NVIDIA)\n---------------------\nInstantDrag: Improving Interactivity
  in Drag-based Image Editing\n\nDrag-based image editing has recently gain
 ed popularity for its interactivity and precision. However, despite the ab
 ility of text-to-image models to generate samples within a second, drag ed
 iting still lags behind due to the challenge of accurately reflecting user
  interaction while maintaining image...\n\n\nJoonghyuk Shin (Seoul Nationa
 l University), Daehyeon Choi (POSTECH), and Jaesik Park (Seoul National Un
 iversity)\n---------------------\nConsolidating Attention Features for Mul
 ti-view Image Editing\n\nLarge-scale text-to-image models enable a wide ra
 nge of image editing techniques, using text prompts or even spatial contro
 ls. However, applying these editing methods to multi-view images depicting
  a single scene leads to 3D-inconsistent results. In this work, we focus o
 n spatial control-based geome...\n\n\nOr Patashnik (Tel Aviv University); 
 Rinon Gal (Tel Aviv University, NVIDIA Research); Daniel Cohen-Or (Tel Avi
 v University); and Jun-Yan Zhu and Fernando De La Torre (Carnegie Mellon U
 niversity)\n---------------------\nTurboEdit: Text-Based Image Editing Usi
 ng Few-Step Diffusion Models\n\nDiffusion models have opened the path to a
  wide range of text-based image editing frameworks. However, these typical
 ly build on the multi-step nature of the diffusion backwards process, and 
 adapting them to distilled, fast-sampling methods has proven surprisingly 
 challenging. Here, we focus on a pop...\n\n\nGilad Deutch (Tel Aviv Univer
 sity); Rinon Gal (Tel Aviv University, NVIDIA Research); and Daniel Garibi
 , Or Patashnik, and Daniel Cohen-Or (Tel Aviv University)\n---------------
 ------\nGenerative Portrait Shadow Removal\n\nWe introduce a high-fidelity
  portrait shadow removal model that can effectively enhance the image of a
  portrait by predicting its appearance under disturbing shadows and highli
 ghts. Portrait shadow removal is a highly ill-posed problem where multiple
  plausible solutions can be found based on a singl...\n\n\nJae Shin Yoon, 
 Zhixin Shu, Mengwei Ren, Xuaner Zhang, Yannick Hold-Geoffroy, Krishna Kuma
 r Singh, and He Zhang (Adobe Inc.)\n---------------------\nContent-aware T
 ile Generation using Exterior Boundary Inpainting\n\nWe present a novel an
 d flexible learning-based method for generating tileable image sets.  Our 
 method goes beyond simple self-tiling, supporting sets of mutually tileabl
 e images that exhibit a high degree of diversity.  To promote diversity we
  decouple structure from content by foregoing explicit co...\n\n\nSam Sart
 or and Pieter Peers (College of William & Mary)\n\nRegistration Category: 
 Full Access, Full Access Supporter\n\nLanguage Format: English Language\n\
 nSession Chair: Dani Lischinski (Hebrew University of Jerusalem, Google)
END:VEVENT
END:VCALENDAR