Ahhh, Sloot's digital coding system [1] is finally here ;).<p>[1] <a href="https://en.m.wikipedia.org/wiki/Sloot_Digital_Coding_System" rel="nofollow">https://en.m.wikipedia.org/wiki/Sloot_Digital_Coding_System</a>
How fast is this and how big is the decoder/encoder? The model weights are not accessible.<p>From the description, it looks like it's only being tested with 128x128 frames, which implies that the speed is very low.
> It can be observed that our model outperforms them at low bitrates<p>It can? Maybe I'm misunderstanding the graphs but it doesn't look like it to me?
Back in 2005 there was a collegue at my first job writing video format converters software. He was considered a genius and the stereo type of an introvert software developer. He claimed that one day an entire movie could be compressesed on a single floppydisk. Everybody laughed and thought he was weird. He might be right after all.
Here's the research behind this: <a href="https://arxiv.org/html/2402.08934v1" rel="nofollow">https://arxiv.org/html/2402.08934v1</a><p>As a casual non-scholar, non-AI person trying to parse this though, it's infuriatingly convoluted. I was expecting a table of "given source file X, we got file size Y with quality loss Z", but while quality (SSIM/LPIPS) is compared to standard codecs like H.264, for the life of me I can't find any measure of <i>how</i> efficient the compression is here.<p>Applying AI to image compression has been tried before though, with distinctly mediocre results: some may recall the Xerox debacle about 10 years, when it turned out copiers were helpfully "optimizing" images by replacing digits with others in invoices, architectural drawings, etc.<p><a href="https://www.theverge.com/2013/8/6/4594482/xerox-copiers-randomly-replacing-numbers-in-documents" rel="nofollow">https://www.theverge.com/2013/8/6/4594482/xerox-copiers-rand...</a>
It's important to remember that any compression gains must include the size of the decompressor which, I assume, will include an enormous diffusion model.
Does anyone remember the <a href="https://en.wikipedia.org/wiki/Sloot_Digital_Coding_System" rel="nofollow">https://en.wikipedia.org/wiki/Sloot_Digital_Coding_System</a>?