English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the wide application of stereo images in various fields, the research onstereo image compression (SIC) attracts extensive attention from academia andindustry. The core of SIC is to fully explore the mutual information betweenthe left and right images and reduce redundancy between views as much aspossible. In this paper, we propose DispSIC, an end-to-end trainable deepneural network, in which we jointly train a stereo matching model to assist inthe image compression task. Based on the stereo matching results (i.e.disparity), the right image can be easily warped to the left view, and only theresiduals between the left and right views are encoded for the left image. Athree-branch auto-encoder architecture is adopted in DispSIC, which encodes theright image, the disparity map and the residuals respectively. During training,the whole network can learn how to adaptively allocate bitrates to these threeparts, achieving better rate-distortion performance at the cost of a lowerdisparity map bitrates. Moreover, we propose a conditional entropy model withaligned cross-view priors for SIC, which takes the warped latents of the rightimage as priors to improve the accuracy of the probability estimation for theleft image. Experimental results demonstrate that our proposed method achievessuperior performance compared to other existing SIC methods on the KITTI andInStereo2K datasets both quantitatively and qualitatively.

Disparity-based Stereo Image Compression with Aligned Cross-View Priors