Variable Rate Video Compression using a Hybrid Recurrent Convolutional Learning Framework

04/08/2020
by   Aishwarya Jadhav, et al.
0

In recent years, neural network-based image compression techniques have been able to outperform traditional codecs and have opened the gates for the development of learning-based video codecs. However, to take advantage of the high temporal correlation in videos, more sophisticated architectures need to be employed. This paper presents PredEncoder, a hybrid video compression framework based on the concept of predictive auto-encoding that models the temporal correlations between consecutive video frames using a prediction network which is then combined with a progressive encoder network to exploit the spatial redundancies. A variable-rate block encoding scheme has been proposed in the paper that leads to remarkably high quality to bit-rate ratios. By joint training and fine-tuning of this hybrid architecture, PredEncoder has been able to gain significant improvement over the MPEG-4 codec and has achieved bit-rate savings over the H.264 codec in the low to medium bit-rate range for HD videos and comparable results over most bit-rates for non-HD videos. This paper serves to demonstrate how neural architectures can be leveraged to perform at par with the highly optimized traditional methodologies in the video compression domain.

READ FULL TEXT
research
09/29/2020

Learning to Compress Videos without Computing Motion

With the development of higher resolution contents and displays, its sig...
research
05/28/2018

Block-optimized Variable Bit Rate Neural Image Compression

In this work, we propose an end-to-end block-based auto-encoder system f...
research
04/01/2019

Layered Image Compression using Scalable Auto-encoder

This paper presents a novel convolutional neural network (CNN) based ima...
research
04/07/2019

Image and Video Compression with Neural Networks: A Review

In recent years, the image and video coding technologies have advanced b...
research
08/02/2020

Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos

We propose a novel deep multi-modality neural network for restoring very...
research
09/20/2020

An enhanced performance for H.265/SHVC based on combined AEGBM3D filter and back-propagation neural network

This paper deals with the latest video coding standard H265 SHVC, a scal...
research
01/24/2023

Differentiable bit-rate estimation for neural-based video codec enhancement

Neural networks (NN) can improve standard video compression by pre- and ...

Please sign up or login with your details

Forgot password? Click here to reset