Work

Neural Photo Editing With Introspective Adversarial Networks

Year: 2017

Type: conference-paper

Abstract: We present the Neural Photo Editor, an interface for exploring the latent space of generative image models and making large, semantically coherent changes to existing images. Our interface is powered by the Introspective Adversarial Network, a hybridization of the Generative Adversarial Network and the Variational Autoencoder designed for use in the editor. Our model makes use of a novel computational block based on dilated convolutions, and Orthogonal Regularization, a novel weight regularization method. We validate our model on CelebA, SVHN, and ImageNet, and produce samples and reconstructions with high visual fidelity.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.807637

Authors: Brock, Andrew, Lim, Theodore, Ritchie, James, Weston, Nick

Institutions: Heriot-Watt University, Renishaw (Ireland), Renishaw (United Kingdom)

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: European Commission, Horizon 2020 Framework Programme

Award: Breaking Educational Barriers with Contextualised, Pervasive and Gameful Learning (BEACONING)