Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by atorodius on Friday June 26, 2020 @01:25PM
(#23654489)
Small text is indeed one of the fail cases, and more research needs to be done here (see also my other comment [1]). We mention this issue in the supplementary materials [2], and you can check out an example here at [3]
[1] https://news.ycombinator.com/item?id=23654161
[2] https://storage.googleapis.com/hific/data/appendixb/appendix...
[3] https://storage.googleapis.com/hific/userstudy/visualize.htm...
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by mmastrac on Friday June 26, 2020 @01:30PM
(#23654548)
This might be a good opportunity to lead to research on a "good faith watermark" for GAN-compressed images that may include hallucinated details.
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by gtoderici on Friday June 26, 2020 @01:32PM
(#23654570)
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 allow the user to determine whether the image is suitable for their use-case.
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by the8472 on Friday June 26, 2020 @02:24PM
(#23655220)
Is it possible to put the decoder into a feedback loop and search among multiple possible encodings that minimize the residual errors? Similar to trellis optimization in video codecs. http://akuvian.org/src/x264/trellis.txt
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by atorodius on Friday June 26, 2020 @02:26PM
(#23655251)
It would be possible - but by minimizing residual errors you end up in a similar regime as when minimizing MSE again, likely making reconstructions blurry!
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by AbrahamParangi on Friday June 26, 2020 @01:44PM
(#23654744)
You could use an OCR encoder and cat that to the feature vector. Great work by the way!
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi...
by atorodius on Friday June 26, 2020 @01:52PM
(#23654864)
Agreed! Alternatively, some semantic segmentation network could be used and a masked MSE loss. In this paper, we focussed on showing the crazy potential of GANs for compression - let's see what future work brings.
https://www.theregister.com/2013/08/06/xerox_copier_flaw_mea...