Deep Generative Models for Distribution-Preserving Lossy Compression
This addresses compression for applications requiring data fidelity and generative modeling, but it is incremental as it builds on existing extreme image compression and generative model techniques.
The paper tackles the problem of distribution-preserving lossy compression by optimizing the rate-distortion tradeoff with a constraint that reconstructed samples follow the training data distribution, achieving artifact-free reconstructions at low bitrates and perfect reconstruction at high bitrates.
We propose and study the problem of distribution-preserving lossy compression. Motivated by recent advances in extreme image compression which allow to maintain artifact-free reconstructions even at very low bitrates, we propose to optimize the rate-distortion tradeoff under the constraint that the reconstructed samples follow the distribution of the training data. The resulting compression system recovers both ends of the spectrum: On one hand, at zero bitrate it learns a generative model of the data, and at high enough bitrates it achieves perfect reconstruction. Furthermore, for intermediate bitrates it smoothly interpolates between learning a generative model of the training data and perfectly reconstructing the training samples. We study several methods to approximately solve the proposed optimization problem, including a novel combination of Wasserstein GAN and Wasserstein Autoencoder, and present an extensive theoretical and empirical characterization of the proposed compression systems.