Learning Image and Video Compression Through Spatial-Temporal Energy Compaction
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10063-10072
Abstract
Compression has been an important research topic for many decades, to produce a significant impact on data transmission and storage. Recent advances have shown a great potential of learning based image and video compression. Inspired from related works, in this paper, we present an image compression architecture using a convolutional autoencoder, and then generalize image compression to video compression, by adding an interpolation loop into both encoder and decoder sides. Our basic idea is to realize spatial-temporal energy compaction in learning image and video compression. Thereby, we propose to add a spatial energy compaction-based penalty into loss function, to achieve higher image compression performance. Furthermore, based on temporal energy distribution, we propose to select the number of frames in one interpolation loop, adapting to the motion characteristics of video contents. Experimental results demonstrate that our proposed image compression outperforms the latest image compression standard with MS-SSIM quality metric, and provides higher performance compared with state-of-the-art learning compression methods at high bit rates, which benefits from our spatial energy compaction approach. Meanwhile, our proposed video compression approach with temporal energy compaction can significantly outperform MPEG-4, and is competitive with commonly used H.264. Both our image and video compression can produce more visually pleasant results than traditional standards.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Video Frame Interpolation via Adaptive Separable Convolution2017
- Full Resolution Image Compression with Recurrent Neural Networks2017
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Overview of the High Efficiency Video Coding (HEVC) StandardIEEE Transactions on Circuits and Systems for Video Technology, 2012
- Extracting and composing robust features with denoising autoencoders2008
- Overview of the H.264/AVC video coding standardIEEE Transactions on Circuits and Systems for Video Technology, 2003
- An overview of the JPEG 2000 still image compression standardSignal Processing: Image Communication, 2002
- Performance evaluation of subband coding and optimization of its filter coefficientsJournal of Visual Communication and Image Representation, 1991
- The JPEG still picture compression standardCommunications of the ACM, 1991
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948