/cae

Lossy Image Compression with Compressive Autoencoders

Primary LanguagePython

Lossy Image Compression with Compressive Autoencoders

See wiki for more details and further results.

Results

cae_32x32x32_zero_pad_bin model, after roughly 5.8 millions of optimization steps; left: original, right: reconstructed.

Resources

A smaller dataset (2,286 frames) that I have used in the Further results page of the wiki can be downloaded here.

A bigger dataset can be constructed by downloading frames using the scripts provided here. For the above results, I have randomly selected and downloaded 121,827 frames.

References

[1] https://arxiv.org/abs/1703.00395

[2] http://arxiv.org/abs/1511.06085