Unsupervised Description of 3D Shapes by Superquadrics Using Deep Learning
- 6 May 2023
- book chapter
- Published by Springer Nature
- p. 95-107
Abstract
No abstract availableKeywords
This publication has 22 references indexed in Scilit:
- Convolutional neural networks on surfaces via seamless toric coversACM Transactions on Graphics, 2017
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017
- Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing2017
- Cyclical Learning Rates for Training Neural Networks2017
- Deep Learning 3D Shape Surfaces Using Geometry Images2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Equal-Distance Sampling of Supercllipse Models.1995
- Recovery of parametric models from range images: the case for superquadrics with global deformationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Human image understanding: Recent research and a theoryComputer Vision, Graphics, and Image Processing, 1985