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:20251218T030657Z
LOCATION:Meeting Room S423+S424\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251215T172400
DTEND;TZID=Asia/Hong_Kong:20251215T173500
UID:siggraphasia_SIGGRAPH Asia 2025_sess113_papers_2105@linklings.com
SUMMARY:INF-3DP: Implicit Neural Fields for Collision-Free Multi-Axis 3D P
 rinting
DESCRIPTION:Jiasheng Qu, Zhuo Huang, Dezhao Guo, and Hailin Sun (Chinese U
 niversity of Hong Kong); Aoran Lyu (University of Manchester); Chengkai Da
 i (Centre for Perceptual and Interactive Intelligence (CPll) Limited); and
  Yeung Yam and Guoxin Fang (Chinese University of Hong Kong, Centre for Pe
 rceptual and Interactive Intelligence (CPII) Limited)\n\nWe introduce a ge
 neral, scalable computational framework for multi-axis 3D printing based o
 n implicit neural fields (INFs) that unifies all stages of toolpath genera
 tion and global collision-free motion planning. In our pipeline, input mod
 els are represented as signed distance fields, with fabrication objectives
 —such as support-free printing, surface finish quality, and extrusion cont
 rol—directly encoded in the optimization of an implicit guidance field. Th
 is unified approach enables toolpath optimization across both surface and 
 interior domains, allowing shell and infill paths to be generated via impl
 icit field interpolation. The printing sequence and multi-axis motion are 
 then jointly optimized over a continuous quaternion field. Our continuous 
 formulation constructs the evolving printing object as a time-varying SDF,
  supporting differentiable global collision handling throughout INF-based 
 motion planning. Compared to explicit-representation-based methods, INF-3D
 P achieves up to two orders of magnitude speedup and significantly reduces
  waypoint-to-surface error. We validate our framework on diverse, complex 
 models and demonstrate its efficiency with physical fabrication experiment
 s using a robot-assisted multi-axis system.\n\nRegistration Category: Full
  Access, Full Access Supporter\n\nSession Chair: Peng Song (Singapore Univ
 ersity of Technology and Design (SUTD))\n\n
END:VEVENT
END:VCALENDAR