2018 International Conference on 3D Vision (3DV) (2018)
Sep 5, 2018 to Sep 8, 2018
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.
image reconstruction, image representation, image retrieval, learning (artificial intelligence), probability, solid modelling
S. Liu, L. Giles and A. Ororbia, "Learning a Hierarchical Latent-Variable Model of 3D Shapes," 2018 International Conference on 3D Vision (3DV), Verona, Italy, 2018, pp. 542-551.