Deep Wide-Activated Residual Network Based Joint Blocking and Color Bleeding Artifacts Reduction for 4:2:0 JPEG-Compressed Images

<div>Lossy image compression is ubiquitously used for</div><div>storage and transmission at lower rates. Among the existing</div><div>lossy image compression methods, the JPEG standard is the most widely used technique in the multimedia world. Over the years, numerous methods have been proposed to suppress the compression artifacts introduced in JPEG-compressed images. However, all current learning-based methods include deep convolutional neural networks (CNNs) that are manually-designed by researchers. The network design process requires extensive computational resources and expertise. Focusing on this issue, we investigate evolutionary search for finding the optimal residual block based architecture for artifact removal. We first define a residual network structure and its corresponding genotype representation used in the search. Then, we provide details</div><div>of the evolutionary algorithm and the multi-objective function</div><div>used to find the optimal residual block architecture. Finally, we present experimental results to indicate the effectiveness of our approach and compare performance with existing artifact removal networks. The proposed approach is scalable and portable to numerous low-level vision tasks.</div>

Download Full-text

A dual-residual network for JPEG compression artifacts reduction

Signal Image and Video Processing ◽

10.1007/s11760-020-01768-3 ◽

2020 ◽

Author(s):

Jianfei Li ◽

Dongsheng Li ◽

Chunxiao Chen ◽

Qiang Yan ◽

Xiong Lu

Keyword(s):

Jpeg Compression ◽

Residual Network ◽

Artifacts Reduction ◽

Compression Artifacts

Download Full-text

Evolutionary Algorithm Based Residual Block Search for Compression Artifact Removal

10.36227/techrxiv.13368698 ◽

2020 ◽

Author(s):

Rishil Shah

Keyword(s):

Image Compression ◽

Evolutionary Algorithm ◽

Evolutionary Search ◽

Residual Network ◽

Deep Convolutional Neural Networks ◽

Artifact Removal ◽

Compressed Images ◽

Block Based ◽

Residual Block ◽

Computational Resources

<div>Lossy image compression is ubiquitously used for</div><div>storage and transmission at lower rates. Among the existing</div><div>lossy image compression methods, the JPEG standard is the most widely used technique in the multimedia world. Over the years, numerous methods have been proposed to suppress the compression artifacts introduced in JPEG-compressed images. However, all current learning-based methods include deep convolutional neural networks (CNNs) that are manually-designed by researchers. The network design process requires extensive computational resources and expertise. Focusing on this issue, we investigate evolutionary search for finding the optimal residual block based architecture for artifact removal. We first define a residual network structure and its corresponding genotype representation used in the search. Then, we provide details</div><div>of the evolutionary algorithm and the multi-objective function</div><div>used to find the optimal residual block architecture. Finally, we present experimental results to indicate the effectiveness of our approach and compare performance with existing artifact removal networks. The proposed approach is scalable and portable to numerous low-level vision tasks.</div>

Download Full-text