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:20260817T171530Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T150800
DTEND;TZID=Asia/Tokyo:20241203T151900
UID:siggraphasia_SIGGRAPH Asia 2024_sess108_papers_391@linklings.com
SUMMARY:ProcessPainter: Learning to draw from sequence data
DESCRIPTION:Yiren Song (National University of Singapore, Show Lab); Shiji
 e Huang, Chen Yao, and Hai Ci (National University of Singapore); Xiaojun 
 Ye (Zhejiang University); Jiaming Liu (Tiamat); Yuxuan Zhang (Shanghai Jia
 o Tong University); and Mike Zheng Shou (National University of Singapore)
 \n\nThe painting process of artists is inherently stepwise and varies sign
 ificantly among different painters and styles. Generating detailed, step-b
 y-step painting processes is essential for art education and research, yet
  remains largely underexplored. Traditional stroke-based rendering methods
  break down images into sequences of brushstrokes, yet they fall short of 
 replicating the authentic processes of artists, with limitations confined 
 to basic brushstroke modifications. Text-to-image models utilizing diffusi
 on processes generate images through iterative denoising, also diverge sub
 stantially from artists' painting process. To address these challenges, we
  introduce ProcessPainter, a text-to-video model that is initially pre-tra
 ined on synthetic data and subsequently fine-tuned with a select set of ar
 tists' painting sequences using the LoRA model. This approach successfully
  generates painting processes from text prompts for the first time. Furthe
 rmore, we introduce an Artwork Replication Network capable of accepting ar
 bitrary-frame input, which facilitates the controlled generation of painti
 ng processes, decomposing images into painting sequences, and completing s
 emi-finished artworks. This paper offers new perspectives and tools for ad
 vancing art education and image generation technology. Our code is availab
 le at: \url{https://github.com/nicolaus-huang/ProcessPainter}\n\nRegistrat
 ion Category: Full Access, Full Access Supporter\n\nLanguage Format: Engli
 sh Language\n\nSession Chair: I-Chao Shen (The University of Tokyo)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_391&sess=sess108
END:VEVENT
END:VCALENDAR