Abstract
The increasing video content over the internet motivated the exploration of novel approaches in the video compression domain. Though neural network based architectures have already emerge as de-facto in the field of image compression and analytics, their application in video compression also result in promising outputs. Adaptive and efficient compression techniques are required for video transmission over varying bandwidth. Several deep learning based techniques and enhancements were proposed and experimented but they didn’t exhibit full optimal behavior and are not end to end trained and optimized. In the zest of a pure and end to end trainable compression technique, a deep learning based video compression architecture has been proposed comprises of frame autoencoder, flow autoencoder and motion extension network for the reconstruction of predicted frames. The video compression network has been designed incrementally and trained with random emission steps strategy. The proposed work results in significant improvement in visual perception quality measured in SSIM and PSNR when compared to some state-of-art techniques but in trade-off with frame reconstruction time sheet.
Highlights
The growing video content over the internet motivated the researchers to look for more proficient and efficient video compression techniques
Deep Learning is becoming a milestone in the field of both compression and analytics
Some deep learning based enhancements and improvements surpass the traditional techniques in both qualitative and quantitative measurements. These positive outcomes motivated the exploration of pure deep learning based video compression strategies which can be end to end trained and optimized
Summary
The growing video content over the internet motivated the researchers to look for more proficient and efficient video compression techniques. Deep learning based techniques are applied in various domain-specific applications including image and video compression too. The application of deep learning in image compression resulted in satisfactory results [1,2,3,4,5] These methods focused on producing the quantization based binary representation of the images exploring various techniques like transmission of a subset of the encoded representation, learning variable quantization, training multiple models etc. Some architecture resulted in superior performance in comparison to the traditional codecs, but with increased complexity and computation This led to the exploration of learning based more efficient and less complex video compression methods. The encoder and decoder networks comprise of recurrent ConvGRU based frames with varying degrees of compression quality.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
