VIDEO UPSAMPLING OF CCTV FOOTAGES
Date
Journal Title
Journal ISSN
Volume Title
Publisher
I.O.E. Pulchowk Campus
Abstract
The idea of super resolution and image upsampling have taken the field of computer vision
by storm. New methods to upsample a grainy and low resolution videos are now the
new chase. Our research is focused on upsampling a CCTV video through the use of deep
learning techniques. Video superresolution often show sub-par results because they tend to
have more components to process than their image counterparts, namely temporal dimension
apart from the usual spatial dimension. In this research, we have studied these components
and developed a pipeline that effectively processes the spatio-temporal information through
optical flow, backed up by novel deep learning based VSR practices such as feature alignment,
aggregation and upsampling. We examined and improved the pipeline based on the
BasicVSR architecture and developed a model of our own by introducing residual in residual
dense blocks. The new model RD-BasicVSR, was successful in surpassing the results of
BasicVSR in both PSNR and SSIM metrics at same experimental settings.
Description
The idea of super resolution and image upsampling have taken the field of computer vision
by storm. New methods to upsample a grainy and low resolution videos are now the
new chase. Our research is focused on upsampling a CCTV video through the use of deep
learning techniques.