Learning-based lossless light field compression - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Learning-based lossless light field compression

Abstract

We propose a learning-based method for lossless light field compression. The approach consists of two steps: first, the view to be compressed is synthesized based on previously decoded views; then, the synthesized view is used as a context to predict probabilities of the residual signal for adaptive arithmetic coding. We leverage recent advances in deep-learning based view synthesis and generative modeling. Specifically, we evaluate two strategies for entropy modeling: a fully parallel probability estimation, where all pixel probabilities are estimated simultaneously; and a partially auto-regressive estimation, in which groups of pixels are predicted sequentially. Our results show that the latter approach provides the best coding gains compared to the state of the art, while keeping the computational complexity competitive
Fichier principal
Vignette du fichier
MMSP2021.pdf (230.99 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03298954 , version 1 (23-08-2021)

Identifiers

Cite

Milan Stepanov, M. Umair Mukati, Giuseppe Valenzise, Søren Forchhammer, Frédéric Dufaux. Learning-based lossless light field compression. IEEE International Workshop on Multimedia Signal Processing (MMSP'2021), Oct 2021, Tampere, Finland. pp.1-6, ⟨10.1109/MMSP53017.2021.9733637⟩. ⟨hal-03298954⟩
78 View
165 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More