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

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.

arXiv commentaccepted by IEEE Transactions on Circuits and Systems for Video Technology(T-CSVT)

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Multi-Scale Context Aggregation by Dilated Convolutions
• Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
• CAS-CNN: A Deep Convolutional Neural Network for Image Compression Artifact Suppression
• Compression Artifacts Removal Using Convolutional Neural Networks
• Residual Dense Network for Image Restoration
• S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction

Cited by in corpus (10)

• SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization
• Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal
• Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks
• FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment
• UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
• NTIRE 2020 Challenge on Image Demoireing: Methods and Results
• Image Demoireing with Learnable Bandpass Filters
• Concatenated Attention Neural Network for Image Restoration
• Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos
• Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton