Re:Show HN: Neural Image Compression Demo
by tonic_section on Saturday September 12, 2020 @06:07AM
(#24451305)
Yes, the model is not lossless as this would require learning the PDF in the original input space.
However, the model does learn a conditional probability distribution over a lower-dimensional representation of the original image - this is unavoidable as entropy coding requires a distribution over discrete symbols. The GAN is almost auxiliary and not a central component of the model - in fact, you can get very good results without the GAN, but does seem to result in visually superior reconstructions.
However, the model does learn a conditional probability distribution over a lower-dimensional representation of the original image - this is unavoidable as entropy coding requires a distribution over discrete symbols. The GAN is almost auxiliary and not a central component of the model - in fact, you can get very good results without the GAN, but does seem to result in visually superior reconstructions.