Disentangled Image Generation Through Structured Noise Injection

Yazeed Alharbi, Peter Wonka

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

46 Scopus citations

Abstract

We explore different design choices for injecting noise into generative adversarial networks (GANs) with the goal of disentangling the latent space. Instead of traditional approaches, we propose feeding multiple noise codes through separate fully-connected layers respectively. The aim is restricting the influence of each noise code to specific parts of the generated image. We show that disentanglement in the first layer of the generator network leads to disentanglement in the generated image. Through a grid-based structure, we achieve several aspects of disentanglement without complicating the network architecture and without requiring labels. We achieve spatial disentanglement, scale-space disentanglement, and disentanglement of the foreground object from the background style allowing fine-grained control over the generated images. Examples include changing facial expressions in face images, changing beak length in bird images, and changing car dimensions in car images. This empirically leads to better disentanglement scores than state-of-the-art methods on the FFHQ dataset.
Original languageEnglish (US)
Title of host publication2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
ISBN (Print)978-1-7281-7169-2
DOIs
StatePublished - 2020

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01

Fingerprint

Dive into the research topics of 'Disentangled Image Generation Through Structured Noise Injection'. Together they form a unique fingerprint.

Cite this