Fader Networks: Generating Image Variations by Sliding Attribute Values
neural information processing systems, pp. 5963-5972, 2017.
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. ...More
Full Text (Upload PDF)
PPT (Upload PPT)