Learned Enhancement Filters for Image Coding for Machines

Jukka I. Ahonen, Ramin G. Youvalari, Nam Le, Honglei Zhang, Francesco Cricri, Hamed Rezazadegan Tavakoli, Miska M. Hannuksela, Esa Rahtu

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

Abstract

Machine-To-Machine (M2M) communication applications and use cases, such as object detection and instance segmentation, are becoming mainstream nowadays. As a consequence, majority of multimedia content is likely to be consumed by machines in the coming years. This opens up new challenges on efficient compression of this type of data. Two main directions are being explored in the literature, one being based on existing traditional codecs, such as the Versatile Video Coding (VVC) standard, that are optimized for human-Targeted use cases, and another based on end-To-end trained neural networks. However, traditional codecs have significant benefits in terms of interoperability, real-Time decoding, and availability of hardware implementations over end-To-end learned codecs. Therefore, in this paper, we propose learned post-processing filters that are targeted for enhancing the performance of machine vision tasks for images reconstructed by the VVC codec. The proposed enhancement filters provide significant improvements on the target tasks compared to VVC coded images. The conducted experiments show that the proposed post-processing filters provide about 45% and 49% Bjontegaard Delta Rate gains over VVC in instance segmentation and object detection tasks, respectively.

Original languageEnglish
Title of host publicationProceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021
PublisherIEEE
Pages235-239
Number of pages5
ISBN (Electronic)9781665437349
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in a conference publication
EventIEEE International Symposium on Multimedia: ISM - Virtual, Online, Italy
Duration: 29 Nov 20211 Dec 2021

Publication series

NameProceedings - 23rd IEEE International Symposium on Multimedia, ISM 2021

Conference

ConferenceIEEE International Symposium on Multimedia
Country/TerritoryItaly
CityVirtual, Online
Period29/11/211/12/21

Keywords

  • Image and video coding for machines
  • image compression
  • perceptual loss
  • post-processing filter
  • VVC

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Media Technology
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Learned Enhancement Filters for Image Coding for Machines'. Together they form a unique fingerprint.

Cite this