DEFENDING AGAINST NOISE BY CHARACTERIZING THE RATE-DISTORTION FUNCTIONS IN END-TO-END NOISY IMAGE COMPRESSION

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationIEEE International Conference on Image Processing - Proceedings (ICIP)
PublisherIEEE
Publication statusPublished - Sep 2021

Conference

Title28th IEEE International Conference on Image Processing (ICIP 2021)
LocationDenaʼina Civic and Convention Center
PlaceUnited States
CityAnchorage, Alaska
Period19 - 22 September 2021

Abstract

There has been an increasing consensus that precise understanding of the rate-distortion (RD) characteristics plays a critical role in image and video coding. In this paper, we explore the RD behaviors of end-to-end image compression in the real-world application scenario that the images could be corrupted by noise at different levels. With the RD behaviors that all images share, we develop a deep learning driven pre-analytical model which fully exploits the properties of RD functions and allows us to improve the quality with economized coding bits. The proposed approach does not require any prior knowledge of the noise level, and could effectively defend against the noise through the end-to-end compression. Extensive experimental results show that the proposed scheme offers the best promise in predicting RD behaviors, and naturally avoids the unnecessary bits consumption.

Research Area(s)

  • Rate-distortion function, end-to-end compression, noisy images

Bibliographic Note

Since this conference is yet to commence, the information for this record is subject to revision.

Citation Format(s)

DEFENDING AGAINST NOISE BY CHARACTERIZING THE RATE-DISTORTION FUNCTIONS IN END-TO-END NOISY IMAGE COMPRESSION. / Li, Binzhe; Wang, Shurun; Wang, Shiqi.

IEEE International Conference on Image Processing - Proceedings (ICIP). IEEE, 2021.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review