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

by   Bolun Zheng, et al.

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 (DRU) 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.


page 1

page 2

page 4

page 5

page 7

page 9


JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer

JPEG compression adopts the quantization of Discrete Cosine Transform (D...

Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal

Lossy compression brings artifacts into the compressed image and degrade...

Fast Convolutional Sparse Coding in the Dual Domain

Convolutional sparse coding (CSC) is an important building block of many...

DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal

JPEG is one of the most commonly used standards among lossy image compre...

Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression

Echo cancellation and noise reduction are essential for full-duplex comm...

OL-DN: Online learning based dual-domain network for HEVC intra frame quality enhancement

Convolution neural network (CNN) based methods offer effective solutions...

Deep Convolution Networks for Compression Artifacts Reduction

Lossy compression introduces complex compression artifacts, particularly...

Please sign up or login with your details

Forgot password? Click here to reset