“Neural Shape Diameter Function for Efficient Mesh Segmentation” by Roy
Conference:
Type(s):
Entry Number: 25
Title:
- Neural Shape Diameter Function for Efficient Mesh Segmentation
Session/Category Title: Posters: Geometry & Modeling
Presenter(s)/Author(s):
Abstract:
By leveraging a graph-based network architecture and message-passing mechanism, we revive the shape diameter function and express it as an unsupervised segmentation approach to achieve consistent object decompositions while avoiding resolution-dependent and computationally expensive raycasting with high-resolution meshes.
ACM Digital Library Publication:
Overview Page:
Submit a story:
If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org
