Learned Variable-Rate Image Compression with Residual Divisive Normalization
This work addresses the implementation complexity of variable-rate image compression for applications requiring efficient storage and transmission, though it is incremental as it builds on existing GDN-based methods.
The paper tackles the problem of deep learning-based image compression requiring multiple networks for different bit rates by proposing a variable-rate framework with novel GDN-based residual sub-networks and a new objective function, achieving results that outperform standard codecs like BPG and state-of-the-art learning-based methods.
Recently it has been shown that deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rates, which increases the implementation complexity. In this paper, we propose a variable-rate image compression framework, which employs more Generalized Divisive Normalization (GDN) layers than previous GDN-based methods. Novel GDN-based residual sub-networks are also developed in the encoder and decoder networks. Our scheme also uses a stochastic rounding-based scalable quantization. To further improve the performance, we encode the residual between the input and the reconstructed image from the decoder network as an enhancement layer. To enable a single model to operate with different bit rates and to learn multi-rate image features, a new objective function is introduced. Experimental results show that the proposed framework trained with variable-rate objective function outperforms all standard codecs such as H.265/HEVC-based BPG and state-of-the-art learning-based variable-rate methods.