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:20250110T023312Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T135800
DTEND;TZID=Asia/Tokyo:20241205T140900
UID:siggraphasia_SIGGRAPH Asia 2024_sess130_papers_199@linklings.com
SUMMARY:SRIF: Semantic Shape Registration Empowered by Diffusion-based Ima
 ge Morphing and Flow Estimation
DESCRIPTION:Technical Papers\n\nMingze Sun (Tsinghua shenzhen internationa
 l graduate school); Chen Guo and Puhua Jiang (Tsinghua shenzhen internatio
 nal graduate school, Pengcheng Lab); and Shiwei Mao, Yurun Chen, and Ruqi 
 Huang (Tsinghua shenzhen international graduate school)\n\nIn this paper, 
 we propose \textbf{SRIF}, a novel \textbf{S}emantic shape \textbf{R}egistr
 ation framework based on diffusion-based \textbf{I}mage morphing and \text
 bf{F}low Estimation. \nMore concretely, given a pair of extrinsically alig
 ned shapes, we first render them from multi-views, and then we utilize an 
 image interpolation framework tailored for diffusion models to generate se
 quences of intermediate images between them. The images are later fed into
  a dynamic 3D Gaussian splatting framework, with which we reconstruct and 
 post-process for intermediate \emph{point clouds} respecting the image mor
 phing processing. In the end, tailored for the above, we propose a novel r
 egistration module to estimate continuous normalizing flow, which deforms 
 source shape consistently towards the target, with intermediate point clou
 ds as weak guidance. Our key insight is to leverage LVMs to \emph{associat
 e} shapes and therefore obtain much richer semantic information on the rel
 ationship between shapes than the ad-hoc independent semantic information 
 extraction. As consequence, \textbf{SRIF} achieves high-quality dense corr
 espondences on challenging shape pairs, but also delivers smooth, semantic
 ally\nmeaningful interpolation in between. Empirical evidence justifies th
 e effectiveness and superiority of our method as well as specific design c
 hoices. The code will be made public upon acceptance.\n\nRegistration Cate
 gory: Full Access, Full Access Supporter\n\nLanguage Format: English Langu
 age\n\nSession Chair: Noam Aigerman (University of Montreal)
URL:https://asia.siggraph.org/2024/program/?id=papers_199&sess=sess130
END:VEVENT
END:VCALENDAR