Open Access Open Access  Restricted Access Subscription or Fee Access

Video Resolution Enhancement

Ajay Pratap Singh, Ashutosh Kumar Shukla, Muskan Pandey

Abstract


In this period of advanced correspondence, video has become a significant aspect of our everyday life. Additionally, video enhancement being a functioning exploration subject in PC vision has gotten more consideration in these ongoing years. Video enhancement manages the accompanying issue: Given an inferior quality info video, how might we make yield video more understood and better". There are essentially two strategies for video enhancement: 1-Spatial - based space video enhancement, 2-Transform - based area video enhancement. Spatial - put together area video enhancement works with respect to pixels. The essential restrictions of this model remember need of giving sufficient heartiness. The fundamental thought behind change-based video enhancement is that to improve the video by controlling the change coefficients. These strategies can't do all the upgrade of the image well overall, and it is hard to mechanize the image enhancement method. Aside from this, actualizing video enhancement utilizing these strategies costs high and is perplexing as well. Perform video enhancement utilizing a solitary image super resolution utilizing four diverse imaging procedures, in particular Super Resolution Convolutional Neural Network (SRCNN), Fast Super Resolution Convolutional Neural Network (FSRCNN), Super Resolution Generative Adversarial Networks (SRGAN), Fast Super Resolution Generative Adversarial Networks (FSRGAN).


Full Text:

PDF

References


Roumy, A.,Bevilacqua, M., Morel, M.L.A., Guillemot, C.: Low complexity single-image super-resolution based on nonnegative neighbour embedding. In: British Machine Vision Conference 2012.

Burger, H.C., Schuler, C.J., Harmeling, S: Image denoising neural networks compete with BM3D 2012.

Yeung, D.Y., Chang, H., Xiong, Y.: Computer Vision and Pattern Recognition 2004.

Cui, Z., Shan, S., Chang, H., Chen, X., Zhong, B.: Deep network cascade for image super- resolution In European Conference on Computer Vision 2014.

Dai, D., Van Gool, L., Timofte, R.: Jointly optimized regressors for image super-resolution, In: Eurographics 2015.

Han Katsaggelos, A.K. a soft edge smoothness prior for colored image SR IEEE Transactions on Image Processing 2009.

N., Kite, T.D., Geisler, Damera-Venkata, B.L., Bovik, W.S., Evans, A.C.: Image quality assessment based on a degradation model IEEE Transactions on Image Processing 2000.

Deng, J., Fei-Fei, Socher, R., Li, Dong, W., L.J., Li, K., L.: ImageNet: A large-scale hierarchical image database In IEEE Conference on CVPR 2009.

Denton, E., LeCun, Y., Zaremba, W., Fergus, R. Bruna, J Exploiting linear structure within CNN for efficient evaluation In: Advances in Neural IPS 2014.

Dong, C., Loy, C.C., He, K., Tang, X Learning a deep CNN for image SR European Conference on Computer Vision 2014.

Freedman, Fattal Image and video upscaling from local self-example ACM Transactions on Graphics 2011.

Freeman, W.T., Jones, T.R., Pasztor, E.C Example-based SR Computer Graphics and Applications 2002.

Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning lowlevel vision International Journal of Computer Vision 2000.


Refbacks

  • There are currently no refbacks.


eISSN: 2321–2837