Dynamic Neural Network for Lossy-to-Lossless Image Coding - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2021

Dynamic Neural Network for Lossy-to-Lossless Image Coding


Lifting-based wavelet transform has been extensively used for efficient compression of various types of visual data. Generally, the performance of such coding schemes strongly depends on the lifting operators used, namely the prediction and update filters. Unlike conventional schemes based on linear filters, we propose, in this paper, to learn these operators by exploiting neural networks. More precisely, a classical Fully Connected Neural Network (FCNN) architecture is firstly employed to perform the prediction and update. Then, we propose to improve this FCNN-based Lifting Scheme (LS) in order to better take into account the input image to be encoded. Thus, a novel dynamical FCNN model is developed, making the learning process adaptive to the input image contents for which two adaptive learning techniques are proposed. While the first one resorts to an iterative algorithm where the computation of two kinds of variables is performed in an alternating manner, the second learning method aims to learn the model parameters directly through a reformulation of the loss function. Experimental results carried out on various test images show the benefits of the proposed approaches in the context of lossy and lossless image compression.
Fichier principal
Vignette du fichier
Accepted_IEEE_TIP_double_column_DFCN_LS.pdf (2.91 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03526618 , version 1 (14-01-2022)



Tassnim Dardouri, Mounir Kaaniche, Amel Benazza-Benyahia, Jean-Christophe Pesquet. Dynamic Neural Network for Lossy-to-Lossless Image Coding. IEEE Transactions on Image Processing, 2021, 31, pp.569-584. ⟨10.1109/TIP.2021.3132825⟩. ⟨hal-03526618⟩
70 View
186 Download



Gmail Mastodon Facebook X LinkedIn More