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. Furthermore, realistic 3D objects can be easily generated by sampling the VSL's latent probabilistic manifold. We show that our generative model can be trained end-to-end from 2D images to perform single image 3D model retrieval. Experiments show, both quantitatively and qualitatively, the improved generalization of our proposed model over a range of tasks, performing better or comparable to various state-of-the-art alternatives.
@article{arxiv.1705.05994,
title = {Learning a Hierarchical Latent-Variable Model of 3D Shapes},
author = {Shikun Liu and C. Lee Giles and Alexander G. Ororbia},
journal= {arXiv preprint arXiv:1705.05994},
year = {2018}
}
Comments
Accepted as oral presentation at International Conference on 3D Vision (3DV), 2018