https://hackerpaper.kaipfister.de/p/2101.10997/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=37412262urn:hackerpapers:mention:2101.10997:37412262Wed, 06 Sep 2023 22:26:37 GMT<p>Yes, I think this is part of it -- when the model sees a new low-res image, it compares it to patterns that it has already seen to estimate what that location might look like at high-res. The other important part is that the model inputs many low-res images (up to 18, i.e. about three months of images) to produce each high-res image. If you were to down-sample an image by 2x via averaging, then offset the image by one pixel to the right and down-sample it, then repeat for two more offsets, then across the four down-sampled images, you should have enough information to reconstruct the original…</p><p><a href="https://hackerpaper.kaipfister.de/p/2101.10997/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV