Low-complexity ℓ∞-compression of light field images with a deep-decompression stage

M. Umair Mukati, Xi Zhang, Xiaolin Wu, Søren Forchhammer

Abstract

Highlights•Existing LF compression methods are computationally heavy for commodity hardware.•An efficient hybrid solution: DPCM encoder merged with learning-based decompression.•Achieves high-fidelity and high-quality LFs by deep decompression.•The proposed approach offers:•Lightweight high-fidelity near-lossless LF encoding scheme.•High pixel-level accuracy and simultaneous high PSNR performance.
BibTeX
@article{mukati2024low,
  author = {M. Umair Mukati and Xi Zhang and Xiaolin Wu and Søren Forchhammer},
  title = {{Low-complexity ℓ∞-compression of light field images with a deep-decompression stage}},
  journal = {J. Vis. Commun. Image Represent.},
  year = {2024},
  doi = {10.1016/j.jvcir.2024.104072},
}

Loading related content...

Figure