UGC approved journal IJNRD Research Journal

An International Open Access Journal |   ISSN: 2456-4184  

Call For Paper

Issue: February 2021

Volume 6 | Issue 2

Submit Paper Online

Click Here For more Details

For Authors

Forms / Download

Editorial Board

Subscribe IJNRD

Visitor Counter

Published Paper Details
Paper Title: Video Restoration using Convolution Neural Network
Authors Name: Sushant Deshmukh , Rajesh Patil
Author Reg. ID:
Published Paper Id: IJNRD1807014
Published In: Volume 3 Issue 7, July-2018
Abstract: Neural networks have shown very promising results in a large number of research areas. With the introduction of convolution neural networks, they have been widely used in image processing. In this paper we implement Convolution Neural Network for video restoration. This is achieved by introducing higher frequency details using pre trained networks. Most of the research aims at improving video quality by increasing PSNR, but sometimes due to this the videos may become aesthetically less satisfying. While large image databases are available to train deep neural networks, it is more challenging to create a large video database of sufficient quality to train neural nets for video restoration. The dataset used for training the model is from DIV2K - bicubic downscaling x4 competition.Video restoration remains a challenging problem despite being a very active area of research. Even with huge strides made with single-image super-resolution, multi-frame techniques, which utilize multiple frames in improving the quality of a given frame, we have yet to fully take advantage of the power of deep learning.
Keywords: Neural Networks, Video Restoration
Cite Article: "Video Restoration using Convolution Neural Network", International Journal of Novel Research and Development (, ISSN:2456-4184, Vol.3, Issue 7, page no.78-80, July-2018, Available :
Downloads: 00041488
Share Article:

Click Here to Download This Article

Article Preview

ISSN Details

DOI (A digital object identifier)

Providing A digital object identifier by DOI

Conference Proposal

Open Access License Policy

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Creative Commons License This material is Open Knowledge This material is Open Data This material is Open Content

Important Details

Social Media