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:20260817T171536Z
LOCATION:Hall B5 (1)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T130000
DTEND;TZID=Asia/Tokyo:20241205T131100
UID:siggraphasia_SIGGRAPH Asia 2024_sess130_papers_635@linklings.com
SUMMARY:SpaceMesh: A Continuous Representation for Learning Manifold Surfa
 ce Meshes
DESCRIPTION:Tianchang Shen (University of Toronto, NVIDIA Research) and Zh
 aoshuo Li, Marc Law, Matan Atzmon, Sanja Fidler, James Lucas, Jun Gao, and
  Nicholas Sharp (NVIDIA Research)\n\nMeshes are ubiquitous in visual compu
 ting and simulation, yet most existing machine learning techniques represe
 nt meshes only indirectly, e.g. as the level set of a scalar field, or def
 ormation of a template, or as a disordered triangle soup lacking local str
 ucture. This work presents a scheme to directly generate manifold, polygon
 al meshes of arbitrary connectivity as the output of a neural network. Our
  key innovation is to define a continuous latent connectivity space at eac
 h mesh vertex, which implies the discrete mesh. In particular, our vertex 
 embeddings generate cyclic neighbor relationships in a halfedge mesh repre
 sentation, which gives a guarantee of edge-manifoldness and the ability to
  represent general polygonal meshes. This representation is well-suited to
  machine learning and stochastic optimization, without restriction on conn
 ectivity or topology. We first explore the basic properties of this repres
 entation, then use it to fit distributions of meshes from large datasets. 
 The resulting models generate diverse meshes with tessellation structure l
 earned from the dataset population, with concise details and high-quality 
 mesh elements. In applications, this approach not only yields high-quality
  outputs from generative models, but also enables directly learning challe
 nging geometry processing tasks such as mesh repair.\n\nRegistration Categ
 ory: Full Access, Full Access Supporter\n\nLanguage Format: English Langua
 ge\n\nSession Chair: Noam Aigerman (University of Montreal, Mila)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_635&sess=sess130
END:VEVENT
END:VCALENDAR