Variable Rate Deep Image Compression with Modulated Autoencoder

TL;DR

This paper introduces modulated autoencoders that adapt a shared deep image compression model to different rate-distortion tradeoffs, achieving near-independent model performance with fewer parameters.

Contribution

It proposes a novel modulated autoencoder framework for variable rate image compression, improving flexibility and efficiency over traditional fixed-rate models.

Findings

Achieves comparable R-D performance to independent models

Uses significantly fewer parameters

Effectively navigates the R-D operational curve

Abstract

Variable rate is a requirement for flexible and adaptable image and video compression. However, deep image compression methods are optimized for a single fixed rate-distortion tradeoff. While this can be addressed by training multiple models for different tradeoffs, the memory requirements increase proportionally to the number of models. Scaling the bottleneck representation of a shared autoencoder can provide variable rate compression with a single shared autoencoder. However, the R-D performance using this simple mechanism degrades in low bitrates, and also shrinks the effective range of bit rates. Addressing these limitations, we formulate the problem of variable rate-distortion optimization for deep image compression, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific rate-distortion tradeoff via a modulation network. Jointly training this modulated autoencoder and modulation network provides an effective way to navigate the R-D operational curve. Our experiments show that the proposed method can achieve almost the same R-D performance of independent models with significantly fewer parameters.