Intuitive Shape Editing in Latent Space

TL;DR

This paper introduces a novel autoencoder-based approach for intuitive and controllable shape editing in latent space by disentangling style and surface control points, ensuring predictable shape modifications.

Contribution

It proposes a Lipschitz constraint to create interpretable latent spaces, enabling independent manipulation of style and surface points for shape editing.

Findings

Outperforms state-of-the-art shape editing methods

Enables intuitive and predictable shape modifications

Supports unsupervised part segmentation

Abstract

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.