Generative Visual Manipulation on the Natural Image Manifold
This addresses the problem of realistic photo manipulation for users without artistic skills, offering a novel method to prevent unrealistic edits.
The paper tackles the challenge of realistic image manipulation by learning the natural image manifold using a generative adversarial network, enabling user-controlled edits that preserve realism and are applied in near-real time.
Realistic image manipulation is challenging because it requires modifying the image appearance in a user-controlled way, while preserving the realism of the result. Unless the user has considerable artistic skill, it is easy to "fall off" the manifold of natural images while editing. In this paper, we propose to learn the natural image manifold directly from data using a generative adversarial neural network. We then define a class of image editing operations, and constrain their output to lie on that learned manifold at all times. The model automatically adjusts the output keeping all edits as realistic as possible. All our manipulations are expressed in terms of constrained optimization and are applied in near-real time. We evaluate our algorithm on the task of realistic photo manipulation of shape and color. The presented method can further be used for changing one image to look like the other, as well as generating novel imagery from scratch based on user's scribbles.