Attention-Guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
Abstract
We propose a deep learning system for attention-guided dual-layer image compression (AGDL). In the AGDL compression system, an image is encoded into two layers, a base layer and an attention-guided refinement layer. Unlike the existing ROI image compression methods that spend an extra bit budget equally on all pixels in ROI, AGDL employs a CNN module to predict those pixels on and near a saliency sketch within ROI that are critical to perceptual quality. Only the critical pixels are further sampled by compressive sensing (CS) to form a very compact refinement layer. Another novel CNN method is developed to jointly decode the two compression code layers for a much refined reconstruction, while strictly satisfying the transmitted CS constraints on perceptually critical pixels. Extensive experiments demonstrate that the proposed AGDL system advances the state of the art in perception-aware image compression.
Cite
Text
Zhang and Wu. "Attention-Guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01315Markdown
[Zhang and Wu. "Attention-Guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/zhang2021cvpr-attentionguided/) doi:10.1109/CVPR46437.2021.01315BibTeX
@inproceedings{zhang2021cvpr-attentionguided,
title = {{Attention-Guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton}},
author = {Zhang, Xi and Wu, Xiaolin},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2021},
pages = {13354-13364},
doi = {10.1109/CVPR46437.2021.01315},
url = {https://mlanthology.org/cvpr/2021/zhang2021cvpr-attentionguided/}
}