Abstract
Recent years have seen the emergence of the visual saliency-based image and video compression for low dynamic range (LDR) visual content. The high dynamic range (HDR) imaging is yet to follow such an approach for compression as the state-of-the-art visual saliency detection models are mainly concerned with LDR content. Although a few HDR saliency detection models have been proposed in the recent years, they lack the comprehensive validation. Current HDR image compression schemes do not differentiate salient and non-salient regions, which has been proved redundant in terms of the Human Visual System. In this paper, we propose a novel visual saliency guided layered compression scheme for HDR images. The proposed saliency detection model is robust and highly correlates with the ground truth saliency maps obtained from eye tracker. The results show a reduction of bit-rates up to 50% while retaining the same high visual quality in terms of HDR-Visual Difference Predictor (HDR-VDP) and the visual saliency-induced index for perceptual image quality assessment (VSI) metrics in the salient regions.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
