Extreme Video Compression with Pre-trained Diffusion Models · HackerPapers discussions

Extreme Video Compression with Pre-trained Diffusion Models — mentioned by resolutebat

Tue, 20 Feb 2024 03:55:11 GMT

Here's the research behind this: https://arxiv.org/html/2402.08934v1 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 how efficient the compression is here. 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…

Paper and discussion history. A mention is not an endorsement.

Extreme Video Compression with Pre-trained Diffusion Models — mentioned by resolutebat

Tue, 20 Feb 2024 03:49:27 GMT

Direct link to HTML article: https://arxiv.org/html/2402.08934v1 Unfortunately it only contains still images with teeny thumbnails: https://arxiv.org/html/2402.08934v1/x2.png

Paper and discussion history. A mention is not an endorsement.

Extreme Video Compression with Pre-trained Diffusion Models — mentioned by yonixw

Mon, 19 Feb 2024 21:35:59 GMT

Googling gave me the article: https://www.arxiv.org/abs/2402.08934 Which have examples in it.

Paper and discussion history. A mention is not an endorsement.