Deep Homography for Efficient Stereo Image Compression
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1492-1501
Abstract
In this paper, we propose HESIC, an end-to-end trainable deep network for stereo image compression (SIC). To fully explore the mutual information across two stereo images, we use a deep regression model to estimate the homography matrix, i.e., H matrix. Then, the left image is spatially transformed by the H matrix, and only the residual information between the left and right images is encoded to save bitrates. A two-branch auto-encoder architecture is adopted in HESIC, corresponding to the left and right images, respectively. For entropy coding, we use two conditional stereo entropy models, i.e., Gaussian mixture model (GMM) based and context based entropy models, to fully explore the correlation between the two images to reduce the coding bit-rates. In decoding, a cross quality enhancement module is proposed to enhance the image quality based on inverse H matrix. Experimental results show that our HESIC outperforms state-of-the-art SIC methods on InStereo2K and KITTI datasets both quantitatively and qualitatively. Code is available at https://github.com/ywz978020607/HESIC.Keywords
This publication has 26 references indexed in Scilit:
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Overview of the High Efficiency Video Coding (HEVC) StandardIEEE Transactions on Circuits and Systems for Video Technology, 2012
- Constructing image panoramas using dual-homography warping2011
- Multiscale structural similarity for image quality assessment2004
- Stereo image compression using wavelet coefficients morphologyImage and Vision Computing, 2004
- Recognising panoramas2003
- Locally Optimized RANSAC2003
- Theoretical foundations of transform codingIEEE Signal Processing Magazine, 2001
- Object recognition from local scale-invariant features1999
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992