Unsupervised Geometric Disentanglement via CFAN-VAE

Norman Joseph Tatro, Stefan C Schonsheck, Rongjie Lai

Keywords: geometric deep learning, generative models

TL;DR: We introduce a generative model for surfaces, CFAN-VAE, that learns disjoint latent spaces for intrinsic (shape) and extrinsic (pose) geometry in an unsupervised manner.

Abstract: Geometric disentanglement, the separation of latent codes for intrinsic (i.e. identity) and extrinsic (i.e. pose) geometry, is a prominent task for generative models of non-Euclidean data such as 3D deformable models. It provides greater interpretability of the latent space, and leads to more control in generation. This work introduces a mesh feature, the conformal factor and normal feature (CFAN), for use in mesh convolutional autoencoders. We further propose CFAN-VAE, a novel architecture that disentangles identity and pose using the CFAN feature. Requiring no label information on the identity or pose during training, CFAN-VAE achieves geometric disentanglement in an unsupervised way. Our comprehensive experiments, including reconstruction, interpolation, generation, and identity/pose transfer, demonstrate CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement.