Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction

TL;DR

This paper introduces an implicit dual-domain convolutional network that effectively reduces compression artifacts in color images, handling various qualities with a single model, outperforming existing methods in both objective and subjective evaluations.

Contribution

The proposed IDCN employs an implicit dual-domain translation and a flexible version to handle diverse compression qualities and color images, addressing limitations of prior dual-domain CNN methods.

Findings

IDCN outperforms state-of-the-art methods in artifact reduction.

IDCN-f effectively handles a wide range of compression qualities.

The method demonstrates superior subjective and objective performance.

Abstract

Several dual-domain convolutional neural network-based methods show outstanding performance in reducing image compression artifacts. However, they suffer from handling color images because the compression processes for gray-scale and color images are completely different. Moreover, these methods train a specific model for each compression quality and require multiple models to achieve different compression qualities. To address these problems, we proposed an implicit dual-domain convolutional network (IDCN) with the pixel position labeling map and the quantization tables as inputs. Specifically, we proposed an extractor-corrector framework-based dual-domain correction unit (DCU) as the basic component to formulate the IDCN. A dense block was introduced to improve the performance of extractor in DRU. The implicit dual-domain translation allows the IDCN to handle color images with the discrete cosine transform (DCT)-domain priors. A flexible version of IDCN (IDCN-f) was developed to handle a wide range of compression qualities. Experiments for both objective and subjective evaluations on benchmark datasets show that IDCN is superior to the state-of-the-art methods and IDCN-f exhibits excellent abilities to handle a wide range of compression qualities with little performance sacrifice and demonstrates great potential for practical applications.