BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190159Z
LOCATION:West Building\, Level 2\, Outside Room 219
DTSTART;TZID=America/Los_Angeles:20250810T090000
DTEND;TZID=America/Los_Angeles:20250810T173000
UID:siggraph_SIGGRAPH 2025_sess404_pos_281@linklings.com
SUMMARY:49. SAWNA: Space-Aware Text to Image Generation
DESCRIPTION:Ryugo Morita (Hosei University, EQUES Inc.); Sho Kuno (The Uni
 versity of Tokyo, EQUES Inc.); Ryunosuke Tanaka (EQUES Inc.); Rongzhi Li (
 The University of Tokyo, EQUES Inc.); and Hoang Dai Dinh and Issey Sukeda 
 (EQUES Inc.)\n\nSAWNA tackles layout-sensitive text-to-image generation by
  treating user-specified empty regions as first-class constraints. Boundin
 g-box masks are blurred and injected as mean-shifted, inert noise into the
  frozen Stable Diffusion latent, suppressing synthesis inside reserved are
 as while preserving diversity and quality elsewhere. This simple training-
 free modification supports workflows that require precise layout fidelity,
  including advertising (e.g., space for logos or headlines), UI design (e.
 g., button placement), and animation pre-production (e.g., speech bubbles,
  subtitles, or motion overlays).\nExperiments show that SAWNA outperforms 
 layout-aware baselines like GLIGEN and in-painting pipelines, both of whic
 h struggle to maintain truly empty regions without introducing artifacts o
 r incoherence. In contrast, SAWNA yields clean, editable space while produ
 cing semantically rich images across the remaining canvas.\nThis makes it 
 especially suitable for design-critical applications where reserved region
 s are integral to downstream compositing or storytelling.\n\nRegistration 
 Category: Full Conference, Experience\n\n
END:VEVENT
END:VCALENDAR
