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:20250110T023309Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241203T144500
DTEND;TZID=Asia/Tokyo:20241203T145600
UID:siggraphasia_SIGGRAPH Asia 2024_sess108_papers_1187@linklings.com
SUMMARY:HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Fas
 ter Speed, and Higher Resolution
DESCRIPTION:Technical Papers\n\nHua Li (Wangxuan Institute of Computer Tec
 hnology, Peking University) and Zhouhui Lian (Wangxuan Institute of Comput
 er Technology, Peking University; State Key Laboratory of General Artifici
 al Intelligence, Peking University)\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) methods that initially synthes
 ize glyph images and then vectorize them. However, the first category ofte
 n fails to construct complete and correct shapes for complex glyphs, while
  the latter struggles to efficiently synthesize high-resolution (i.e., 102
 4 × 1024 or higher) glyph images while preserving local details. In this p
 aper, we introduce HFH-Font, a few-shot font synthesis method capable of e
 fficiently generating high-resolution glyph images that can be converted i
 nto high-quality vector glyphs. More specifically, our method employs a di
 ffusion model-based generative framework with component-aware conditioning
  to learn different levels of style information adaptable to varying input
  reference sizes. We also design a distillation module based on Score Dist
 illation Sampling for 1-step fast inference, and a style-guided super-reso
 lution module to refine and upscale low-resolution synthesis results. Exte
 nsive experiments, including a user study with professional font designers
 , have been conducted to demonstrate that our method significantly outperf
 orms existing font synthesis approaches. Experimental results show that ou
 r method produces high-fidelity, high-resolution raster images which can b
 e vectorized into high-quality vector fonts. Using our method, for the fir
 st time, large-scale Chinese vector fonts of a quality comparable to those
  manually created by professional font designers can be automatically gene
 rated.\n\nRegistration Category: Full Access, Full Access Supporter\n\nLan
 guage Format: English Language\n\nSession Chair: I-Chao Shen (The Universi
 ty of Tokyo)
URL:https://asia.siggraph.org/2024/program/?id=papers_1187&sess=sess108
END:VEVENT
END:VCALENDAR