Abstract
In this paper we tackle the problem of stereo image compression, and leverage the fact that the two images have overlapping fields of view to further compress the representations. Our approach leverages state-of-the-art single-image compression autoencoders and enhances the compression with novel parametric skip functions to feed fully differentiable, disparity-warped features at all levels to the encoder/decoder of the second image. Moreover, we model the probabilistic dependence between the image codes using a conditional entropy model. Our experiments show an impressive 30 – 50% reduction in the second image bitrate at low bitrates compared to deep single-image compression, and a 10 – 20% reduction at higher bitrates.
Authors
Jerry Liu, Shenlong Wang, Raquel Urtasun
Conference
ICCV 2019
Full Paper
Uber ATG
Related articles
Interested in joining Uber Eng?
Click here
Products
Company
