Intuitive Shape Editing in Latent Space
This addresses the challenge of interpretable shape manipulation for users in computer graphics and 3D modeling, though it is incremental as it builds on existing autoencoder frameworks.
The paper tackles the problem of unpredictable shape changes when editing autoencoder latent spaces by introducing a method that disentangles latent sub-spaces into style variables and control points, enabling intuitive shape editing with bounded output changes proportional to latent changes, and demonstrates competitive performance against state-of-the-art methods and applications in unsupervised part segmentation.
The use of autoencoders for shape editing or generation through latent space manipulation suffers from unpredictable changes in the output shape. Our autoencoder-based method enables intuitive shape editing in latent space by disentangling latent sub-spaces into style variables and control points on the surface that can be manipulated independently. The key idea is adding a Lipschitz-type constraint to the loss function, i.e. bounding the change of the output shape proportionally to the change in latent space, leading to interpretable latent space representations. The control points on the surface that are part of the latent code of an object can then be freely moved, allowing for intuitive shape editing directly in latent space. We evaluate our method by comparing to state-of-the-art data-driven shape editing methods. We further demonstrate the expressiveness of our learned latent space by leveraging it for unsupervised part segmentation.