News for hackers. Stuff that matters.
Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi... by deweller on Friday June 26, 2020 @11:41AM (#23653226)
This is really impressive. But it raises some questions for me.

What size library would be required to decode these type of images?

And would the decoding library be updated on a regular basis? Would the image change when decoding library is updated? Would images be tagged with a version of the library when encoded (HiFiC v1.0.2?)

Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi... by atorodius on Friday June 26, 2020 @12:11PM (#23653605)
Thanks for the kind words!

> What size library would be required to decode these type of images?

The model is 726MB. Keep in mind that this is a research project - further research needs to be done on how to get faster now that we know that this kind of results are possible!

> And would the decoding library be updated on a regular basis?

Only if you want even better reconstructions!

> Would the image change when decoding library is updated? Would images be tagged with a version of the library when encoded (HiFiC v1.0.2?)

Yes, some header would have to be added.

Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi... by pornel on Friday June 26, 2020 @03:37PM (#23656067)
I'm very curious how such thing could be standardized as an image format. With classic image formats there's an expectation one can write a spec and an independent implementation from scratch. "Take my X-MB large pre-trained model" is unprecedented.

Would it still be competitive with H.265 if the model was 10MB or 50MB in size? 0.7GB may be difficult for widespread adoption.

Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi... by gtoderici on Friday June 26, 2020 @05:36PM (#23657328)
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 they're still better.

I don't have any such model handy but perhaps it's 10x-20x smaller.

We don't claim that this (or even the previous work) is the way to go forward for images, but we hope to incentivize more researchers to look in this direction so that we can figure out how to deploy these kinds of methods since the results they produce are very compelling.

Re:Show HN: HiFiC – High-Fidelity Generative Image Compressi... by ache7 on Friday June 26, 2020 @12:06PM (#23653532)
And I also have questions about decompression speed and memory requirements.