Skip to main navigation Skip to search Skip to main content

Deep convolutional network based image quality enhancement for low bit rate image compression

  • Chuanmin Jia
  • , Xiang Zhang
  • , Jian Zhang
  • , Shiqi Wang
  • , Siwei Ma

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this contribution, a novel image quality enhancement algorithm based on convolutional network is proposed for low bit rate image compression. Specifically, a downsample procedure is performed to generate lower resolution image for low bit rate compression. While the decoder side, upsample is to be performed firstly to the original resolution. Image quality is further enhanced by the proposed convolutional deep network. In particular, an optional image quality improvement network can be utilized for further enhancement after the first network. With the help of deep network, more detailed and high-frequency information can be recovered while maintaining the consistency of contour area, leading to better visual quality. Another benefit of this approach lies in that the proposed approach is fully compatible with all third-party image codec pipeline. Experimental result shows that the proposed scheme significantly outperforms JPEG in low bit rate image compression.

Original languageEnglish
Title of host publicationVCIP 2016 - 30th Anniversary of Visual Communication and Image Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509053162
DOIs
StatePublished - 4 Jan 2017
Externally publishedYes
Event2016 IEEE Visual Communication and Image Processing, VCIP 2016 - Chengdu, China
Duration: 27 Nov 201630 Nov 2016

Publication series

NameVCIP 2016 - 30th Anniversary of Visual Communication and Image Processing

Conference

Conference2016 IEEE Visual Communication and Image Processing, VCIP 2016
Country/TerritoryChina
CityChengdu
Period27/11/1630/11/16

Keywords

  • Deep Convolutional Network
  • Image Compression
  • Low Bit Rate

Fingerprint

Dive into the research topics of 'Deep convolutional network based image quality enhancement for low bit rate image compression'. Together they form a unique fingerprint.

Cite this