Skip to main content
placeholder image

Deep Stereo Image Compression via Bi-directional Coding

Conference Paper


Abstract


  • Existing learning-based stereo compression methods usually adopt a unidirectional approach to encoding one image independently and the other image conditioned upon the first. This paper proposes a novel bidirectional coding-based end-to-end stereo image compression network (BCSIC-Net). BCSIC-Net consists of a novel bidirectional contextual transform module which performs nonlinear transform conditioned upon the inter-view context in a latent space to reduce inter-view redundancy, and a bidirectional conditional entropy model that employs interview correspondence as a conditional prior to improve coding efficiency. Experimental results on the InStereo2K and KITTI datasets demonstrate that the proposed BCSIC-Net can effectively reduce the inter-view redundancy and out-performs state-of-the-art methods.

Publication Date


  • 2022

Citation


  • Lei, J., Liu, X., Peng, B., Jin, D., Li, W., & Gu, J. (2022). Deep Stereo Image Compression via Bi-directional Coding. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 2022-June (pp. 19637-19646). doi:10.1109/CVPR52688.2022.01905

Scopus Eid


  • 2-s2.0-85134981407

Web Of Science Accession Number


Start Page


  • 19637

End Page


  • 19646

Volume


  • 2022-June

Issue


Place Of Publication


Abstract


  • Existing learning-based stereo compression methods usually adopt a unidirectional approach to encoding one image independently and the other image conditioned upon the first. This paper proposes a novel bidirectional coding-based end-to-end stereo image compression network (BCSIC-Net). BCSIC-Net consists of a novel bidirectional contextual transform module which performs nonlinear transform conditioned upon the inter-view context in a latent space to reduce inter-view redundancy, and a bidirectional conditional entropy model that employs interview correspondence as a conditional prior to improve coding efficiency. Experimental results on the InStereo2K and KITTI datasets demonstrate that the proposed BCSIC-Net can effectively reduce the inter-view redundancy and out-performs state-of-the-art methods.

Publication Date


  • 2022

Citation


  • Lei, J., Liu, X., Peng, B., Jin, D., Li, W., & Gu, J. (2022). Deep Stereo Image Compression via Bi-directional Coding. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 2022-June (pp. 19637-19646). doi:10.1109/CVPR52688.2022.01905

Scopus Eid


  • 2-s2.0-85134981407

Web Of Science Accession Number


Start Page


  • 19637

End Page


  • 19646

Volume


  • 2022-June

Issue


Place Of Publication