Split-AE: an autoencoder-based disentanglement framework for 3D shape-to-shape feature transfer

Sneha Saha, Leandro Minku, Xin Yao, Bernard Sendhoff, Stefan Menzel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Downloads (Pure)

Abstract

Recent advancements in machine learning comprise generative models such as autoencoders (AE) for learning and compressing 3D data to generate low-dimensional latent representations of 3D shapes. Learning latent representations that disentangle the underlying factors of variations in 3D shapes is an intuitive way to achieve generalization in generative models. However, it remains an open problem to learn a generative model of 3D shapes such that the latent variables are disentangled and represent different interpretable aspects of 3D shapes. In this paper, we propose Split-AE, which is an autoencoder-based architecture for partitioning the latent space into two sets, named as content and style codes. The content code represents global features of 3D shapes to differentiate between semantic categories of shapes, while style code represents distinct visual features to differentiate between shape categories having similar semantic meaning. We present qualitative and quantitative experiments to verify feature disentanglement using our Split-AE. Further, we demonstrate that, given a source shape as an initial shape and a target shape as a style reference, the trained Split-AE combines the content of a source and style of a target shape to generate a novel augmented shape, that possesses the distinct features of the target shape category yet maintains the similarity of the global features with the source shape. We conduct a qualitative study showing that the augmented shapes exhibit a realistic interpretable mixture of content and style features across different shape classes with similar semantic meaning.
Original languageEnglish
Title of host publication2022 International Joint Conference on Neural Networks (IJCNN)
PublisherIEEE
Publication statusAccepted/In press - 26 Apr 2022
Event2022 International Joint Conference on Neural Networks (IJCNN) - University of Padua, Padua, Italy
Duration: 18 Jul 202223 Jul 2022

Conference

Conference2022 International Joint Conference on Neural Networks (IJCNN)
Abbreviated titleIJCNN 2022
Country/TerritoryItaly
CityPadua
Period18/07/2223/07/22

Bibliographical note

Not yet published as of 12/05/2022.

Fingerprint

Dive into the research topics of 'Split-AE: an autoencoder-based disentanglement framework for 3D shape-to-shape feature transfer'. Together they form a unique fingerprint.

Cite this