# Compression Artifacts Removal Using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1605.00366 · HTML: https://mlsanity.com/paper/1605.00366/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2016.

## Built on by (most cited first, 13 of 13)

- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [NTIRE 2021 Challenge on Image Deblurring](https://mlsanity.com/paper/2104.14854/) (2021)
- [HST: Hierarchical Swin Transformer for Compressed Image Super-resolution](https://mlsanity.com/paper/2208.09885/) (2022)
- [Multi-modality Deep Restoration of Extremely Compressed Face Videos](https://mlsanity.com/paper/2107.05548/) (2021)
- [EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration](https://mlsanity.com/paper/2105.04872/) (2021)
- [End-to-end Transformer for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2210.13827/) (2022)
- [Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN](https://mlsanity.com/paper/2311.04263/) (2023)
- [Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement](https://mlsanity.com/paper/2202.00011/) (2022)
- [Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion](https://mlsanity.com/paper/2302.06096/) (2023)
- [JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer](https://mlsanity.com/paper/2308.09110/) (2023)
- [CISRNet: Compressed Image Super-Resolution Network](https://mlsanity.com/paper/2201.06045/) (2022)
- [A Unified Image Preprocessing Framework For Image Compression](https://mlsanity.com/paper/2208.07110/) (2022)
- [Convolutional Neural Network (CNN) to reduce construction loss in JPEG compression caused by Discrete Fourier Transform (DFT)](https://mlsanity.com/paper/2209.03475/) (2022)

## Abstract (arXiv)

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.