papers AI Learner
The Github is limit! Click to go to the new site.

Automatic Video Colorization using 3D Conditional Generative Adversarial Networks

2019-05-08
Panagiotis Kouzouglidis, Giorgos Sfikas, Christophoros Nikou

Abstract

In this work, we present a method for automatic colorization of grayscale videos. The core of the method is a Generative Adversarial Network that is trained and tested on sequences of frames in a sliding window manner. Network convolutional and deconvolutional layers are three-dimensional, with frame height, width and time as the dimensions taken into account. Multiple chrominance estimates per frame are aggregated and combined with available luminance information to recreate a colored sequence. Colorization trials are run succesfully on a dataset of old black-and-white films. The usefulness of our method is also validated with numerical results, computed with a newly proposed metric that measures colorization consistency over a frame sequence.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.03023

PDF

http://arxiv.org/pdf/1905.03023


Similar Posts

Comments