Fader Networks: Manipulating Images by Sliding Attributes

TL;DR

Fader Networks introduce a novel encoder-decoder model that disentangles image content and attributes in latent space, enabling smooth, realistic attribute manipulation through continuous sliders, simplifying training and scaling to multiple attributes.

Contribution

The paper presents a new architecture for image attribute manipulation that simplifies training and scales efficiently to multiple attributes by disentangling features in latent space.

Findings

Model can generate realistic images with varied attributes.

Continuous attribute control allows smooth modifications.

Preserves image naturalness while changing attributes.

Abstract

This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. As a result, after training, our model can generate different realistic versions of an input image by varying the attribute values. By using continuous attribute values, we can choose how much a specific attribute is perceivable in the generated image. This property could allow for applications where users can modify an image using sliding knobs, like faders on a mixing console, to change the facial expression of a portrait, or to update the color of some objects. Compared to the state-of-the-art which mostly relies on training adversarial networks in pixel space by altering attribute values at train time, our approach results in much simpler training schemes and nicely scales to multiple attributes. We present evidence that our model can significantly change the perceived value of the attributes while preserving the naturalness of images.