Multi-Context Dual Hyper-Prior Neural Image Compression
This work addresses image compression for applications requiring high efficiency, representing an incremental improvement through hybrid methods.
The paper tackled the problem of limited receptive fields in convolutional transforms for deep image compression by proposing a Transformer-based nonlinear transform and a novel entropy model with dual hyperpriors and global context, achieving superior rate-distortion performance compared to state-of-the-art methods.
Transform and entropy models are the two core components in deep image compression neural networks. Most existing learning-based image compression methods utilize convolutional-based transform, which lacks the ability to model long-range dependencies, primarily due to the limited receptive field of the convolution operation. To address this limitation, we propose a Transformer-based nonlinear transform. This transform has the remarkable ability to efficiently capture both local and global information from the input image, leading to a more decorrelated latent representation. In addition, we introduce a novel entropy model that incorporates two different hyperpriors to model cross-channel and spatial dependencies of the latent representation. To further improve the entropy model, we add a global context that leverages distant relationships to predict the current latent more accurately. This global context employs a causal attention mechanism to extract long-range information in a content-dependent manner. Our experiments show that our proposed framework performs better than the state-of-the-art methods in terms of rate-distortion performance.