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 S421\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251217T170200
DTEND;TZID=Asia/Hong_Kong:20251217T171300
UID:siggraphasia_SIGGRAPH Asia 2025_sess143_papers_1817@linklings.com
SUMMARY:StyleSculptor: Zero-Shot Style-Controllable 3D Asset Generation wi
 th Texture-Geometry Dual Guidance
DESCRIPTION:Zefan Qu, Zhenwei Wang, Haoyuan Wang, Ke Xu, Gerhard Petrus HA
 NCKE, and Rynson. W. H. Lau (City University of Hong Kong)\n\nCreating 3D 
 assets that follow the texture and geometry style of existing ones is ofte
 n desirable or even inevitable in practical applications like video gaming
  and virtual reality. While impressive progress has been made in generatin
 g 3D objects from text or images, creating style-controllable 3D assets re
 mains a complex and challenging problem. In this work, we propose StyleScu
 lptor, a novel training-free approach for generating style-guided 3D asset
 s from a content image and one or more style images. Unlike previous works
 , StyleSculptor achieves style-guided 3D generation in a zero-shot manner,
  enabling fine-grained 3D style control that captures the texture, geometr
 y, or both styles of user-provided style images. At the core of StyleSculp
 tor is a novel Style Disentangled Attention (SD-Attn) module, which establ
 ishes a dynamic interaction between \why{the input content image and style
  image for style-guided 3D asset generation via a cross-3D attention mecha
 nism, enabling stable feature fusion and effective style-guided generation
 . To alleviate semantic content leakage, we also introduce a style-disenta
 ngled feature selection strategy within the SD-Attn module, which leverage
 s the variance of 3D feature patches to disentangle style- and content-sig
 nificant channels, allowing selective feature injection within the attenti
 on framework. With SD-Attn, the network can dynamically compute texture-, 
 geometry-, or both-guided features to steer the 3D generation process. Bui
 lt upon this, we further propose the Style Guided Control (SGC) mechanism,
  which enables exclusive geometry- or texture-only stylization, as well as
  adjustable style intensity control. StyleSculptor does not require prior 
 training and enables instant adaptation to any reference models while main
 taining strict user-specified style consistency. Extensive experiments dem
 onstrate that StyleSculptor outperforms existing baseline methods in produ
 cing high-fidelity 3D assets.\n\nRegistration Category: Full Access, Full 
 Access Supporter\n\nSession Chair: Young Min Kim (Seoul National Universit
 y)\n\n
END:VEVENT
END:VCALENDAR