DeepAI AI Chat
Log In Sign Up

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

10/18/2018
by   Bolun Zheng, et al.
10

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.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 7

page 9

09/15/2020

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...
09/27/2017

Fast Convolutional Sparse Coding in the Dual Domain

Convolutional sparse coding (CSC) is an important building block of many...
06/08/2018

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...
05/27/2018

DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images

JPEG is one of the widely used lossy compression methods. JPEG-compresse...
04/17/2020

Quantization Guided JPEG Artifact Correction

The JPEG image compression algorithm is the most popular method of image...
08/09/2022

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

Convolution neural network (CNN) based methods offer effective solutions...
08/09/2016

Deep Convolution Networks for Compression Artifacts Reduction

Lossy compression introduces complex compression artifacts, particularly...