2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSS-IVC-DL.6
Paper Title A NEURAL NETWORK APPROACH FOR JOINT OPTIMIZATION OF PREDICTORS IN LIFTING-BASED IMAGE CODERS
Authors Tassnim Dardouri, Mounir Kaaniche, University Sorbonne Paris Nord, France; Amel Benazza-Benyahia, University of Carthage, SUP’COM, Tunisia; Jean-Christophe Pesquet, CentraleSupélec, France; Gabriel Dauphin, University Sorbonne Paris Nord, France
SessionSS-IVC-DL: Special Session: Optimized Image and Video Coding Using Deep Learning
LocationArea B
Session Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Time:Wednesday, 22 September, 08:00 - 09:30
Presentation Poster
Topic Special Sessions: Optimized image and video coding schemes using deep learning
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract The objective of this paper is to investigate techniques for learning Fully Connected Network (FCN) models in a lifting based image coding scheme. More precisely, based on a 2D non-separable lifting structure composed of three FCN-based prediction stages followed by an FCN-based update one, we first propose to resort to an Lp loss function, with p ∈ {1,2}, to learn the three FCN prediction models. While the latter are separately learned in the first approach, a novel joint learning approach is then developed by minimizing a weighted Lp loss function related to the global prediction error. Experimental results carried out on the standard Challenge LearnedImage Compression (CLIC) dataset, show the benefits of the proposed techniques in terms of rate-distortion performance.