3D Object Classification
27 papers with code • 3 benchmarks • 3 datasets
Image: Sedaghat et al
Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category.
We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion.
We adopt these graph based methods to 3D point clouds to introduce a generic vector representation of 3D graphs, we call graph 3D (G3D).