Publications

A raw colored video takes up around three times more memory size than its grayscale version. We can exploit this fact and send the grayscale version of a colored video along with a colorization model instead of the colored video to save bandwidth while transmission. In this paper, we tackle the problem of colorization of grayscale videos to reduce bandwidth usage. For this task, we use come colored keyframes as reference images from the colored version of the grayscale video. We propose a model that exracts keyframes from a colored video and trains a Fully Connected Network from scratch on these colored frames. Through the extractd keyframes we get a good knowledge of the colors that have been used in the video which helps us in colorizaing the grayscale version of the video efficiently.

Skills

R

90%

Statistics

100%

Photography

10%

Experience

 
 
 
 
 

CEO

GenCoin

Jan 2017 – Present California
Responsibilities include:

  • Analysing
  • Modelling
  • Deploying
 
 
 
 
 

Professor

University X

Jan 2016 – Dec 2016 California
Taught electronic engineering and researched semiconductor physics.

Recent Posts

Projects

Recent & Upcoming Talks

Popular Topics