Variable Rate Deep Image Compression with Modulated Autoencoder
This addresses the need for flexible and adaptable image compression with reduced memory requirements, though it is incremental as it builds on existing autoencoder methods.
The paper tackles the problem of variable rate-distortion optimization in deep image compression by proposing modulated autoencoders (MAEs), which adapt a shared autoencoder's representations via a modulation network to achieve flexible bitrate control without performance degradation, achieving almost the same R-D performance as independent models with significantly fewer parameters.
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.