Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
This work addresses a practical issue in image processing for applications requiring robust color image quality enhancement, though it is incremental as it builds on existing dual-domain methods.
The paper tackled the problem of reducing compression artifacts in color images by proposing an implicit dual-domain convolutional network (IDCN) that handles a wide range of compression qualities with a single model, achieving superior performance over state-of-the-art methods in objective and subjective evaluations.
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.