Not sure how that would work out in practice. We kind of rushed with the experiments in any case - maybe we could let the methods train for longer. In the end the adversary might learn any regular patters that appear,…
Independently of this work, we have models which are competitive with HEVC while being significantly smaller (this is from previous work). They will not look nearly as good as what you see in the website demo, but…
What you suggest has already been done: train a neural network with the output of BPG or JPEG, and ask to reconstruct the input with just the decompressed pixels being available. It definitely is a valid approach but…
One of the things we discussed to address this is to have the ability to: a) turn off detail hallucination completely given the same bitstream; and b) store the median/maximum absolute error across the image (b) should…
On the standardization issue: the advantage of such a method that we presented is that as long as there exists a standard for model specification, we can encode every image with an arbitrary computational graph that can…
(coauthor here) We used an adversarial loss in addition to a perceptual loss and MSE. None of these work super-well when the others are not used. The adversarial loss "learns" what is a compressed image and tries to…
Not sure how that would work out in practice. We kind of rushed with the experiments in any case - maybe we could let the methods train for longer. In the end the adversary might learn any regular patters that appear,…
Independently of this work, we have models which are competitive with HEVC while being significantly smaller (this is from previous work). They will not look nearly as good as what you see in the website demo, but…
What you suggest has already been done: train a neural network with the output of BPG or JPEG, and ask to reconstruct the input with just the decompressed pixels being available. It definitely is a valid approach but…
One of the things we discussed to address this is to have the ability to: a) turn off detail hallucination completely given the same bitstream; and b) store the median/maximum absolute error across the image (b) should…
On the standardization issue: the advantage of such a method that we presented is that as long as there exists a standard for model specification, we can encode every image with an arbitrary computational graph that can…
(coauthor here) We used an adversarial loss in addition to a perceptual loss and MSE. None of these work super-well when the others are not used. The adversarial loss "learns" what is a compressed image and tries to…