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:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T144500
DTEND;TZID=Asia/Tokyo:20241205T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess134@linklings.com
SUMMARY:Diffusing Your Videos
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nStill-Moving: Cu
 stomized Video Generation without Customized Video Data\n\nCustomizing tex
 t-to-image (T2I) models has seen tremendous progress recently, particularl
 y in areas such as personalization, stylization, and conditional generatio
 n. However, expanding this progress to video generation is still in its in
 fancy, primarily due to the lack of customized video data. \nIn ...\n\n\nH
 ila Chefer (Google Research, Tel Aviv University); Shiran Zada, Roni Paiss
 , Ariel Ephrat, Omer Tov, and Michael Rubinstein (Google Research); Lior W
 olf (Tel Aviv University); Tali Dekel (Google Research, Weizmann Institute
  of Science); Tomer Michaeli (Google Research, Technion – Israel Institute
  of Technology); and Inbar Mosseri (Google Research)\n--------------------
 -\nFashion-VDM: Video Diffusion Model for Virtual Try-On\n\nWe present Fas
 hion-VDM, a video diffusion model (VDM) for generating virtual try-on vide
 os. Given an input garment image and person video, our method aims to gene
 rate a high-quality try-on video of the person wearing the given garment, 
 while preserving the person's identity and motion. Image-based v...\n\n\nJ
 ohanna Karras (Google Research, University of Washington); Yingwei Li and 
 Nan Liu (Google Research); Luyang Zhu (Google Research, University of Wash
 ington); Innfarn Yoo, Andreas Lugmayr, and Chris Lee (Google Research); an
 d Ira Kemelmacher-Shlizerman (Google Research, University of Washington)\n
 ---------------------\nLumiere: A Space-Time Diffusion Model for Video Gen
 eration\n\nWe introduce Lumiere -- a text-to-video diffusion model designe
 d for synthesizing videos that portray realistic, diverse and coherent mot
 ion -- a pivotal challenge in video synthesis. To this end, we introduce a
  Space-Time U-Net architecture that generates the entire temporal duration
  of the video a...\n\n\nOmer Bar-Tal (Google Research, Weizmann Institute 
 of Science); Hila Chefer (Google Research, Tel Aviv University); Omer Tov,
  Charles Herrmann, Roni Paiss, Shiran Zada, Ariel Ephrat, Junhwa Hur, Guan
 ghui Liu, Amit Raj, Yuanzhen Li, and Michael Rubinstein (Google Research);
  Tomer Michaeli (Google Research, Technion – Israel Institute of Technolog
 y); Oliver Wang and Deqing Sun (Google Research); Tali Dekel (Google Resea
 rch, Weizmann Institute of Science); and Inbar Mosseri (Google Research)\n
 ---------------------\nI2VEdit: First-Frame-Guided Video Editing via Image
 -to-Video Diffusion Models\n\nThe remarkable generative capabilities of di
 ffusion models have motivated extensive research in both image and video e
 diting. Compared to video editing which faces additional challenges in the
  time dimension, image editing has witnessed the development of more diver
 se, high-quality approaches and mo...\n\n\nWenqi Ouyang (S-Lab for Advance
 d Intelligence, Nanyang Technological University Singapore); Yi Dong (Nany
 ang Technological University (NTU)); Lei Yang and Jianlou Si (SenseTime); 
 and Xingang Pan (S-Lab for Advanced Intelligence, Nanyang Technological Un
 iversity Singapore)\n---------------------\nVidPanos: Generative Panoramic
  Videos from Casual Panning Videos\n\nStitching frames of a panning video 
 into a panoramic photograph is a well-understood problem for stationary sc
 enes. When objects are moving, however, a still panorama is not enough to 
 capture the scene. \nWe present a method for synthesizing a panoramic vide
 o from a casually-captured panning video, a...\n\n\nJingwei Ma (University
  of Washington); Erika Lu, Roni Paiss, and Shiran Zada (Google Deepmind); 
 Aleksander Holynski (University of California Berkeley, Google Deepmind); 
 Tali Dekel (Weizmann Institute of Science, Google Deepmind); Brian Curless
  (University of Washington, Google Deepmind); and Michael Rubinstein and F
 orrester Cole (Google Deepmind)\n---------------------\nTrailBlazer: Traje
 ctory Control for Diffusion-Based Video Generation\n\nLarge text-to-video 
 (T2V) models such as Sora have the potential to revolutionize visual effec
 ts and the creation of some types of movies. Current T2V models require te
 dious trial-and-error experimentation to achieve desired results, however.
  This motivates the search for methods to directly control...\n\n\nWan-Duo
  Kurt Ma (Victoria University of Wellington), J. P. Lewis (NVIDIA Research
 ), and W. Bastiaan Kleijn (Victoria University of Wellington)\n\nRegistrat
 ion Category: Full Access, Full Access Supporter\n\nLanguage Format: Engli
 sh Language\n\nSession Chair: Nanxuan Zhao (Adobe Research)
END:VEVENT
END:VCALENDAR