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:20250110T023313Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T150800
DTEND;TZID=Asia/Tokyo:20241206T151900
UID:siggraphasia_SIGGRAPH Asia 2024_sess149_papers_691@linklings.com
SUMMARY:Enhancing the Aesthetics of 3D Shapes via Reference-based Editing
DESCRIPTION:Technical Papers\n\nMinchan Chen and Manfred Lau (City Univers
 ity of Hong Kong)\n\nWhile there have been previous works that explored me
 thods to enhance the aesthetics of images, the automated beautification of
  3D shapes has been limited to specific shapes such as 3D face models. In 
 this paper, we introduce a framework to automatically enhance the aestheti
 cs of general 3D shapes. Our approach employs a reference-based beautifica
 tion strategy. We first performed data collection to gather the aesthetics
  ratings of various 3D shapes to create a 3D shape aesthetics dataset. The
 n we perform reference-based editing to edit the input shape and beautify 
 it by making it look more like some reference shape that is aesthetic. Spe
 cifically, we propose a reference-guided global deformation framework to c
 oherently deform the input shape such that its structural proportions will
  be closer to those of the reference shape. We then optionally transplant 
 some local aesthetic parts from the reference to the input to obtain the b
 eautified output shapes. Comparisons show that our reference-guided 3D def
 ormation algorithm outperforms existing techniques. Furthermore, quantitat
 ive and qualitative evaluations demonstrate that the performance of our ae
 sthetics enhancement framework is consistent with both human perception an
 d existing 3D shape aesthetics assessment.\n\nRegistration Category: Full 
 Access, Full Access Supporter\n\nLanguage Format: English Language\n\nSess
 ion Chair: Valentin Deschaintre (Adobe Research)
URL:https://asia.siggraph.org/2024/program/?id=papers_691&sess=sess149
END:VEVENT
END:VCALENDAR