ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators
This work addresses shape generation for computer graphics and vision applications, offering an incremental improvement with a plug-and-play loss for existing models.
The paper tackles the problem of generating deformable shapes by introducing an unsupervised loss that enforces local rigidity preservation, resulting in improved performance over existing methods on benchmark datasets for human, animal, and bone shapes.
This paper introduces an unsupervised loss for training parametric deformation shape generators. The key idea is to enforce the preservation of local rigidity among the generated shapes. Our approach builds on an approximation of the as-rigid-as possible (or ARAP) deformation energy. We show how to develop the unsupervised loss via a spectral decomposition of the Hessian of the ARAP energy. Our loss nicely decouples pose and shape variations through a robust norm. The loss admits simple closed-form expressions. It is easy to train and can be plugged into any standard generation models, e.g., variational auto-encoder (VAE) and auto-decoder (AD). Experimental results show that our approach outperforms existing shape generation approaches considerably on public benchmark datasets of various shape categories such as human, animal and bone.