Fader Networks: Manipulating Images by Sliding Attributes

Guillaume Lample (1, 2) , Neil Zeghidour (3, 4) , Nicolas Usunier (1) , Antoine Bordes (5) , Ludovic Denoyer (2) , Marc ' Aurelio Ranzato (1)

1 Facebook
2 SU - Sorbonne Université
3 CoML - Apprentissage machine et développement cognitif
4 LSCP - Laboratoire de sciences cognitives et psycholinguistique
5 FAIR - Facebook AI Research [Paris]

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Guillaume Lample, Neil Zeghidour, Nicolas Usunier, Antoine Bordes, Ludovic Denoyer, et al.. Fader Networks: Manipulating Images by Sliding Attributes. 31st Conference on Neural Information Processing Systems (NIPS 2017), Dec 2017, Long Beach, CA, United States. pp.5969-5978. ⟨hal-02275215⟩