Realistic text replacement with non-uniform style conditioning

06/07/2020
by   Arseny Nerinovsky, et al.
0

In this work, we study the possibility of realistic text replacement, the goal of which is to replace text present in the image with user-supplied text. The replacement should be performed in a way that will not allow distinguishing the resulting image from the original one. We achieve this goal by developing a novel non-uniform style conditioning layer and apply it to an encoder-decoder ResNet based architecture. The resulting model is a single-stage model, with no post-processing. The proposed model achieves realistic text replacement and outperforms existing approaches on ICDAR MLT.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset