ROI-Based Deep Image Compression with Swin Transformers

Encoding the Region Of Interest (ROI) with better quality than the background has many applications including video conferencing systems, video surveillance and object-oriented vision tasks. In this paper, we propose a ROI-based image compression framework with Swin transformers as main building blo...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
Main Authors Li, Binglin, Liang, Jie, Fu, Haisheng, Han, Jingning
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.06.2023
Subjects
Image coding
Image segmentation
Learned image compression
Object detection
Object oriented modeling
region-of-interest
Signal processing
Swin transformers
Transformers
Video surveillance
Online AccessGet full text

Cover

More Information
Summary:Encoding the Region Of Interest (ROI) with better quality than the background has many applications including video conferencing systems, video surveillance and object-oriented vision tasks. In this paper, we propose a ROI-based image compression framework with Swin transformers as main building blocks for the autoencoder network. The binary ROI mask is integrated into different layers of the network to provide spatial information guidance. Based on the ROI mask, we can control the relative importance of the ROI and non-ROI by modifying the corresponding Lagrange multiplier λ for different regions. Experimental results show our model achieves higher ROI PSNR than other methods and modest average PSNR for human evaluation. When tested on models pre-trained with original images, it has superior object detection and instance segmentation performance on the COCO validation dataset.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10094674