Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation
This work addresses the challenge of flexible rate control in deep learning-based image compression, which is incremental by building on existing learned methods to enable continuous adaptation without performance loss.
The paper tackles the problem of continuous rate adaptation in learned image compression, proposing the Asymmetric Gained Variational Autoencoder (AG-VAE) framework that achieves comparable quantitative performance with state-of-the-art methods and better qualitative performance than classical codecs.
With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of rate-distortion performance. However, continuous rate adaptation remains an open question. Some learned image compression methods use multiple networks for multiple rates, while others use one single model at the expense of computational complexity increase and performance degradation. In this paper, we propose a continuously rate adjustable learned image compression framework, Asymmetric Gained Variational Autoencoder (AG-VAE). AG-VAE utilizes a pair of gain units to achieve discrete rate adaptation in one single model with a negligible additional computation. Then, by using exponential interpolation, continuous rate adaptation is achieved without compromising performance. Besides, we propose the asymmetric Gaussian entropy model for more accurate entropy estimation. Exhaustive experiments show that our method achieves comparable quantitative performance with SOTA learned image compression methods and better qualitative performance than classical image codecs. In the ablation study, we confirm the usefulness and superiority of gain units and the asymmetric Gaussian entropy model.