• Anantha Sree Skanda S N
• Abhilash B.S
• Akash Deep
• Amrit Kumar Bhuwania

Convolutional neural networks (CNN) are a special type of deep neural networks (DNN).They have so far been successfully applied to image super-resolution (SR) as well as other image restoration tasks. Consecutive frames are motion compensated and used as input to a CNN that provides super-resolved video frames as output. We investigate different options for combining the video frames within one CNN architecture. 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. We show that by using images to pre-train our model, a relatively small video database is sufficient for the training of our model to achieve and even improve upon the current state-of-the-art. We compare our proposed approach to current video as well as image SR algorithms.

Bi-cubic Interpolation; Convolutional neural net; Motion Compensation; Flownet; Multi-Frame systems; Spatio-Temporal networks

"Video Super Resolution Using Deep Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 5, page no.879-882, May-2018, Available :http://www.jetir.org/papers/JETIR1805161.pdf

"Video Super Resolution Using Deep Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 5, page no. pp879-882, May-2018, Available at : http://www.jetir.org/papers/JETIR1805161.pdf