Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
This addresses the problem of efficient, perception-aware image compression for applications like media storage and transmission, representing an incremental improvement over existing ROI methods.
The paper tackles image compression by introducing an attention-guided dual-layer system that selectively refines only critical pixels near saliency sketches, achieving state-of-the-art perceptual quality with a compact refinement layer.
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 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.