Deep Convolution Networks for Compression Artifacts Reduction

Abstract

Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restore sharpened images that are accompanied with ringing effects. Inspired by the success of deep convolutional networks (DCN) on superresolution, we formulate a compact and efficient network for seamless attenuation of different compression artifacts. To meet the speed requirement of real-world applications, we further accelerate the proposed baseline model by layer decomposition and joint use of large-stride convolutional and deconvolutional layers. This also leads to a more general CNN framework that has a close relationship with the conventional Multi-Layer Perceptron (MLP). Finally, the modified network achieves a speed up of 7.5 times with almost no performance loss compared to the baseline model. We also demonstrate that a deeper model can be effectively trained with features learned in a shallow network. Following a similar "easy to hard" idea, we systematically investigate three practical transfer settings and show the effectiveness of transfer learning in low-level vision problems. Our method shows superior performance than the state-of-the-art methods both on benchmark datasets and a real-world use case.

13 pages, 19 figures, an extension of our ICCV 2015 paper

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Rich feature hierarchies for accurate object detection and semantic segmentation
• DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

Cited by in corpus (12)

• A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
• One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
• S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction
• Recent Advances on HEVC Inter-frame Coding: From Optimization to Implementation and Beyond
• A New Convolutional Network-in-Network Structure and Its Applications in Skin Detection, Semantic Segmentation, and Artifact Reduction
• Compressing Weight-updates for Image Artifacts Removal Neural Networks
• Video Quality Enhancement Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients in MPEG I-frames
• Non-blind Image Restoration Based on Convolutional Neural Network
• Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution
• Neural Image Decompression: Learning to Render Better Image Previews
• Machine Learning based Post Processing Artifact Reduction in HEVC Intra Coding