Spatial-Temporal Autoencoder with Attention Network for Video Compression

Sigger, Neetu and Al-Jawad, Naseer and Nguyen, Tuan (2022) Spatial-Temporal Autoencoder with Attention Network for Video Compression. In: International Conference on Image Analysis and Processing, May 23-27 2022, Italy.

[img] Text
Spatial_temporal_autoencoder.pdf

Download (499kB)
Official URL: https://dl.acm.org/doi/abs/10.1007/978-3-031-06433...

Abstract

Deep learning-based approaches are now state of the art in numerous tasks, including video compression, and are having a revolutionary influence in video processing. Recently, learned video compression methods exhibit a fast development trend with promising results. In this paper, taking advantage of the powerful non-linear representation ability of neural networks, we replace each standard component of video compression with a neural network. We propose a spatial-temporal video compression network (STVC) using the spatial-temporal priors with an attention module (STPA). On the one hand, joint spatial-temporal priors are used for generating latent representations and reconstructing compressed outputs because efficient temporal and spatial information representation plays a crucial role in video coding. On the other hand, we also added an efficient and effective Attention module such that the model pays more effort on restoring the artifact-rich areas. Moreover, we formalize the rate-distortion optimization into a single loss function, in which the network learns to leverage the Spatial-temporal redundancy presented in the frames and decreases the bit rate while maintaining visual quality in the decoded frames. The experiment results show that our approach delivers the state-of-the-art learning video compression performance in terms of MS-SSIM and PSNR.

Item Type: Conference or Workshop Item (Paper)
Additional Information: ICIAP 2022: 21st International Conference, Lecce, Italy, May 23–27, 2022, Proceedings, Part III May 2022
Uncontrolled Keywords: Video Compression ; Deep Learning ; Auto-Encoder ; Rate-Distortion Optimization ; Attention Mechanism
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: School of Computing
Depositing User: Neetu Sigger
Date Deposited: 20 Feb 2023 15:52
Last Modified: 20 Feb 2023 15:52
URI: http://bear.buckingham.ac.uk/id/eprint/584

Actions (login required)

View Item View Item