LucidDream: Controlled Temporally-Consistent DeepDream on Videos

11/27/2019
by   Joel Ruben Antony Moniz, et al.
13

In this work, we aim to propose a set of techniques to improve the controllability and aesthetic appeal when DeepDream, which uses a pre-trained neural network to modify images by hallucinating objects into them, is applied to videos. In particular, we demonstrate a simple modification that improves control over the class of object that DeepDream is induced to hallucinate. We also show that the flickering artifacts which frequently appear when DeepDream is applied on videos can be mitigated by the use of an additional temporal consistency loss term.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset