FuRA: Fully Random Access Light Field Image Compression - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

FuRA: Fully Random Access Light Field Image Compression

Abstract

Light fields are typically represented by multi-view images, and enable post-capture actions such as refocusing and perspective shift. To compress a light field image, its view images are typically converted into a pseudo video sequence (PVS) and the generated PVS is compressed using a video codec. However, when using the inter-coding tool of a video codec to exploit the redundancy among view images, the possibility to randomly access any view image is lost. On the other hand, when video codecs independently encode view images using the intra-coding tool, random access to view images is enabled, however, at the expense of a significant drop in the compression efficiency. To address this trade-off, we propose to use neural representations to represent 4D light fields. For each light field, a multi-layer perceptron (MLP) is trained to map the light field four dimensions to the color space, thus enabling random access even to pixels. To achieve higher compression efficiency, neural network compression techniques are deployed. The proposed method outperforms the compression efficiency of HEVC intercoding, while providing random access to view images and even pixel values.
Fichier principal
Vignette du fichier
EUVIP22__FuRA__Fully_Random_Access_Light_Field_Image_Coding-2.pdf (5.34 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03758898 , version 1 (23-08-2022)

Identifiers

  • HAL Id : hal-03758898 , version 1

Cite

Hadi Amirpour, Christine Guillemot, Christian Timmerer. FuRA: Fully Random Access Light Field Image Compression. European Workshop on Video and Image Processing, Sep 2022, Lisbo, Portugal. pp.1-6. ⟨hal-03758898⟩
85 View
45 Download

Share

Gmail Facebook Twitter LinkedIn More