$\mathbf{D^3}$: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images
This addresses image quality restoration for JPEG-compressed images, offering a fast and high-performance solution that is incremental in combining deep learning with domain-specific knowledge.
The paper tackles the problem of removing artifacts from JPEG-compressed images by proposing a Deep Dual-Domain (D^3) model, which achieves around 1 dB higher PSNR and is 30 times faster than the latest deep model.
In this paper, we design a Deep Dual-Domain ($\mathbf{D^3}$) based fast restoration model to remove artifacts of JPEG compressed images. It leverages the large learning capacity of deep networks, as well as the problem-specific expertise that was hardly incorporated in the past design of deep architectures. For the latter, we take into consideration both the prior knowledge of the JPEG compression scheme, and the successful practice of the sparsity-based dual-domain approach. We further design the One-Step Sparse Inference (1-SI) module, as an efficient and light-weighted feed-forward approximation of sparse coding. Extensive experiments verify the superiority of the proposed $D^3$ model over several state-of-the-art methods. Specifically, our best model is capable of outperforming the latest deep model for around 1 dB in PSNR, and is 30 times faster.