BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070312Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T101500
DTEND;TZID=Australia/Melbourne:20231215T111500
UID:siggraphasia_SIGGRAPH Asia 2023_sess135@linklings.com
SUMMARY:Text To Anything
DESCRIPTION:Technical Papers, TOG\n\nCLIP-Guided StyleGAN Inversion for Te
 xt-Driven Real Image Editing\n\nResearchers have recently begun exploring 
 the use of StyleGAN-based models for real image editing. One particularly 
 interesting application is using natural language descriptions to guide th
 e editing process. Existing approaches for editing images using language e
 ither resort to instance-level laten...\n\n\nAbdul Basit Anees and Ahmet C
 anberk Baykal (Koç University), Duygu Ceylan (Adobe Research), Erkut Erdem
  (Hacettepe University), and Aykut Erdem and Deniz Yuret (Koç University)\
 n---------------------\nRerender A Video: Zero-Shot Text-Guided Video-to-V
 ideo Translation\n\nLarge text-to-image diffusion models have exhibited im
 pressive proficiency in generating high-quality images. However, when appl
 ying these models to video domain, ensuring temporal consistency across vi
 deo frames remains a formidable challenge.\nThis paper proposes a novel ze
 ro-shot text-guided video...\n\n\nShuai Yang, Yifan Zhou, Ziwei Liu, and C
 hen Change Loy (Nanyang Technological University, Singapore)\n------------
 ---------\nText-Guided Synthesis of Eulerian Cinemagraphs\n\nWe introduce 
 Text2Cinemagraph,  a fully automated method for creating cinemagraphs from
  text descriptions - an especially challenging task when prompts feature i
 maginary elements and artistic styles, given the complexity of interpretin
 g the semantics and motions of these images. We focus on cinemagr...\n\n\n
 Aniruddha Mahapatra (Carnegie Mellon University); Aliaksandr Siarohin, Hsi
 n-Ying Lee, and Sergey Tulyakov (Snap Inc.); and Jun-Yan Zhu (Carnegie Mel
 lon University)\n---------------------\nFace0: Instantaneously Conditionin
 g a Text-to-Image Model on a Face\n\nWe present Face0, a novel way to inst
 antaneously condition a text-to-image generation model on a face, in sampl
 e time, without any optimization procedures such as fine-tuning or inversi
 ons. We augment a dataset of annotated images with embeddings of the inclu
 ded faces and train an image generation m...\n\n\nDani Valevski, Danny Lum
 en, Yossi Matias, and Yaniv Leviathan (Google Research)\n-----------------
 ----\nBreak-A-Scene: Extracting Multiple Concepts from a Single Image\n\nT
 ext-to-image model personalization aims to introduce a user-provided conce
 pt to the model, allowing its synthesis in diverse contexts. However, curr
 ent methods primarily focus on the case of learning a single concept from 
 multiple images with variations in backgrounds and poses, and struggle whe
 n a...\n\n\nOmri Avrahami (The Hebrew University of Jerusalem), Kfir Aberm
 an (Google Research), Ohad Fried (Reichman University), Daniel Cohen-Or (T
 el Aviv University), and Dani Lischinski (The Hebrew University of Jerusal
 em)\n\nRegistration Category: Full Access\n\nSession Chair: Chongyang Ma (
 ByteDance)
END:VEVENT
END:VCALENDAR