DSIC: Deep Stereo Image Compression
arXiv:1908.03631
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.
arXiv commentAccepted at International Conference on Computer Vision 2019
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Variational image compression with a scale hyperprior
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Joint Autoregressive and Hierarchical Priors for Learned Image Compression
- Density Modeling of Images using a Generalized Normalization Transformation
- End-to-End Learning of Geometry and Context for Deep Stereo Regression
- Context-adaptive Entropy Model for End-to-end Optimized Image Compression
- Self-Supervised Learning for Stereo Matching with Self-Improving Ability
- Neural Video Compression using Spatio-Temporal Priors