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:20250110T023311Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T144500
DTEND;TZID=Asia/Tokyo:20241203T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess108@linklings.com
SUMMARY:Design It All: Font, Paint, and Colors
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nProcessPainter: Learning to draw from sequence data\n\nThe painting pr
 ocess of artists is inherently stepwise and varies significantly among dif
 ferent painters and styles. Generating detailed, step-by-step painting pro
 cesses is essential for art education and research, yet remains largely un
 derexplored. Traditional stroke-based rendering methods break d...\n\n\nYi
 ren Song (National University of Singapore, Show Lab); Shijie Huang, Chen 
 Yao, and Hai Ci (National University of Singapore); Xiaojun Ye (Zhejiang U
 niversity); Jiaming Liu (Tiamat); Yuxuan Zhang (Shanghai Jiao Tong Univers
 ity); and Mike Zheng Shou (National University of Singapore)\n------------
 ---------\nHFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, 
 Faster Speed, and Higher Resolution\n\nThe challenge of automatically synt
 hesizing high-quality vector fonts, particularly for writing systems (e.g.
 , Chinese) consisting of huge amounts of complex glyphs, remains unsolved.
  Existing font synthesis techniques fall into two categories: 1) methods t
 hat directly generate vector glyphs, and 2)...\n\n\nHua Li (Wangxuan Insti
 tute of Computer Technology, Peking University) and Zhouhui Lian (Wangxuan
  Institute of Computer Technology, Peking University; State Key Laboratory
  of General Artificial Intelligence, Peking University)\n-----------------
 ----\nInverse Painting: Reconstructing The Painting Process\n\nGiven an in
 put painting, we reconstruct a time-lapse video of how it may be painted. 
  We formulate this as an autoregressive image generation problem, in which
  an initially blank "canvas'' is iteratively updated. The model learns fro
 m real artists by training on many painting videos.\nOur approach in...\n\
 n\nBowei Chen, Yifan Wang, Brian Curless, Ira Kemelmacher-Shlizerman, and 
 Steven M. Seitz (University of Washington)\n---------------------\nColorfu
 l Diffuse Intrinsic Image Decomposition in the Wild\n\nIntrinsic image dec
 omposition aims to separate the surface reflectance and the effects from t
 he illumination given a single photograph. Due to the complexity of the pr
 oblem, most prior works assume a single-color illumination and a Lambertia
 n world, which limits their use in illumination-aware image...\n\n\nChris 
 Careaga and Yağız Aksoy (Simon Fraser University)\n---------------------\n
 LVCD: Reference-based Lineart Video Colorization with Diffusion Models\n\n
 We propose the first video diffusion framework for reference-based lineart
  video colorization. Unlike previous works that rely solely on image gener
 ative models to colorize lineart frame by frame, our approach leverages a 
 large-scale pretrained video diffusion model to generate colorized animati
 on v...\n\n\nZhitong Huang (City University of Hong Kong); Mohan Zhang (We
 chat, Tencent Inc.); and Jing Liao (City University of Hong Kong)\n-------
 --------------\nSD-𝜋XL: Generating Low-Resolution Quantized Imagery via Sc
 ore Distillation\n\nLow-resolution quantized imagery, such as pixel art, i
 s seeing a revival in modern applications ranging from video game graphics
  to digital design and fabrication, where creativity is often bound by a l
 imited palette of elemental units. Despite their growing popularity, the a
 utomated generation of q...\n\n\nAlexandre Binninger and Olga Sorkine-Horn
 ung (ETH Zürich)\n\nRegistration Category: Full Access, Full Access Suppor
 ter\n\nLanguage Format: English Language\n\nSession Chair: I-Chao Shen (Th
 e University of Tokyo)
END:VEVENT
END:VCALENDAR