Compression Artifacts Removal Using Convolutional Neural Networks
This work improves image quality for applications like photography and video streaming, though it is incremental as it builds on existing CNN techniques.
The paper tackled JPEG compression artifact reduction by training large, deep convolutional neural networks, achieving significantly better reconstruction quality than previous smaller networks and other state-of-the-art methods.
This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three different objectives, generalization with respect to training dataset size, and generalization with respect to JPEG quality level.