Learning a Hierarchical Latent-Variable Model of 3D Shapes

17 May 2017Shikun LiuC. Lee GilesAlexander G. Ororbia II

We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hierarchical representation of objects... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
3D Object Recognition ModelNet40 Variational Shape Learner Accuracy 84.5% # 3