BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030653Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T164000
DTEND;TZID=Asia/Hong_Kong:20251216T165100
UID:siggraphasia_SIGGRAPH Asia 2025_sess129_papers_1086@linklings.com
SUMMARY:AutoSketch: VLM-assisted Style-Aware Vector Sketch Completion
DESCRIPTION:Hsiao-Yuan Chin (National Taiwan University), I-Chao Shen (The
  University of Tokyo), Yi-Ting Chiu (National Taiwan University), Ariel Sh
 amir (Reichman University), and Bing-Yu Chen (National Taiwan University)\
 n\nSketches are an important medium of expression and recently many works 
 concentrate on automatic sketch creations. One such ability very useful fo
 r amateurs is text-based completion of a partial sketch to create a comple
 x scene, while preserving the style of the partial sketch. Existing method
 s focus solely on generating sketch that match the content in the input pr
 ompt in a predefined style, ignoring the styles of the input partial sketc
 hes, e.g., the global abstraction level and local stroke styles. To addres
 s this challenge, we introduce AutoSketch, a style-aware vector sketch com
 pletion method that accommodates diverse sketch styles and supports iterat
 ive sketch completion. AutoSketch completes the input sketch in a style-co
 nsistent manner using a two-stage method. In the first stage, we initially
  optimize the strokes to match an input prompt augmented by style descript
 ions extracted from a vision-language model (VLM). Such style descriptions
  lead to non-photorealistic guidance images which enable more content to b
 e depicted through new strokes. In the second stage, we utilize the VLM to
  adjust the strokes from the previous stage to adhere to the style present
  in the input partial sketch through an iterative style adjustment process
 . In each iteration, the VLM identifies a list of style differences betwee
 n the input sketch and the strokes generated in the previous stage, transl
 ating these differences into adjustment codes to modify the strokes. We co
 mpare our method with existing methods using various sketch styles and pro
 mpts, perform extensive ablation studies and qualitative and quantitative 
 evaluations, and demonstrate that AutoSketch can support diverse sketching
  scenarios.\n\nRegistration Category: Full Access, Full Access Supporter\n
 \nSession Chair: Zeyu Wang (The Hong Kong University of Science and Techno
 logy (Guangzhou), The Hong Kong University of Science and Technology)\n\n
END:VEVENT
END:VCALENDAR