Unsupervised Geometric Disentanglement for Surfaces via CFAN-VAE
This work addresses the problem of interpretable and controllable generation for 3D mesh data, providing an incremental improvement in unsupervised disentanglement methods.
The paper tackles unsupervised geometric disentanglement for 3D deformable surfaces by introducing CFAN-VAE, a novel architecture using conformal factor and normal features, achieving state-of-the-art performance in tasks like reconstruction and identity/pose transfer.
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 unsupervisedway. Our comprehensive experiments, including reconstruction, interpolation, generation, and identity/pose transfer, demonstrate CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement. We also successfully detect a level of geometric disentanglement in mesh convolutional autoencoders that encode xyz-coordinates directly by registering its latent space to that of CFAN-VAE.