Learning part-based templates from large collections of 3D shapes
DOI10.1145/2461912.2461933zbMATH Open1305.68249OpenAlexW2031760064MaRDI QIDQ5174709FDOQ5174709
Authors: Vladimir G. Kim, Wilmot Li, Niloy J. Mitra, Siddhartha Chaudhuri, Stephen Diverdi, Thomas Funkhouser 
Publication date: 18 February 2015
Published in: ACM Transactions on Graphics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1145/2461912.2461933
Recommendations
Nonnumerical algorithms (68W05) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Approximation algorithms (68W25) Computer-aided design (modeling of curves and surfaces) (65D17) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)
Cited In (12)
- Meta-representation of shape families
- EdgeNet: deep metric learning for 3D shapes
- Label transfer between images and 3D shapes via local correspondence encoding
- Iterative 3D shape classification by online metric learning
- Unsupervised 3D shape segmentation and co-segmentation via deep learning
- Jointly learning shape descriptors and their correspondence via deep triplet CNNs
- Structure-aware shape correspondence network for 3D shape synthesis
- Knowledge-based part correspondence
- Towards learning geometric shape parts
- Automatic extraction of generic focal features on 3D shapes via random forest regression analysis of geodesics-in-heat
- Functional map networks for analyzing and exploring large shape collections
- Diffusion pruning for rapidly and robustly selecting global correspondences using local isometry
This page was built for publication: Learning part-based templates from large collections of 3D shapes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5174709)
