Convolutional Autoencoders for Lossy Light Field Compression

Expansion and reduction of a neural network’s width has well known properties in terms of the entropy of the propagating information. When carefully stacked on top of one another, an encoder network and a decoder network produce an autoencoder, often used in compression. Using this architecture, we develop an efficient method of encoding and decoding 4D Light Field data, with a substantial compression factor at a minimal loss in quality. Our best results managed to achieve a compression of 48.6x, with a PSNR of 29.46 dB and a SSIM of 0.8104. Computations of the encoder and decoder can be run in real time, with average computation times of 1.62s and 1.81s respectively, and the entire network occupies a reasonable 584MB by today’s storage standards.

Bibtex

@misc{valtchev2020convAutoencoders,
  author = {Valtchev, Svetozar Zarko and Wu, Jianhong},
  title = {Convolutional Autoencoders for Lossy Light Field Compression},
  publisher = {arXiv},
  year = {2020},
  url = {https://arxiv.org/abs/2008.00027},
  doi = {10.48550/ARXIV.2008.00027},
}