Vesuvius Challenge

For what it&#x27;s worth, I worked with Dr. Seales while getting my undergrad degree. Happy to vouch that he and his team are great humans.<p>This is such a fascinating problem, and could have real benefits for society. Imagine uncovering ancient works that would otherwise be lost.

The images&#x2F;animations in this page are fantastic at visually explaining something quite complicated. I would not have been able to understand the difficulty without them.

Man, there&#x27;s probably a dozen different loosely-formed ideas floating in my head right now — kudos on the exciting presentation, you really make the problem seem interesting. I may just have to give this a shot, though I think the odds of me figuring it out are exceptionally low. Still, working on cutting-edge problems is motivating, even if they&#x27;re above my pay grade :)<p>You&#x27;ve nerd-sniped me good and proper. May the best team win!

One of the organizers here! Would love to welcome everyone&#x27;s questions, ideas, etc! :)

This was the outcome of <a href="https:&#x2F;&#x2F;nat.org&#x2F;puzzle" rel="nofollow">https:&#x2F;&#x2F;nat.org&#x2F;puzzle</a><p>HN discussion: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33735503" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33735503</a><p>Some did guess correctly that it was about decoding the Herculaneum papyri

Fantastic project. Amazing to think that there&#x27;s an entire first century library just waiting for the technology to be read.

I do a lot of brain image segmentation in my research using multiatlas image segmentation, which involves diffeomorphic image registration from multiple labeled atlases...but the amount of curling in on itself of these layered sheets seems a daunting problem for a fully automated pipeline.

Easter egg: if you click on the “days remaining” at the bottom of the page, it changes to Roman numerals :)

This needs to be solved ASAP. Chat-gpt needs more training data!<p>but seriously, way cool project.

Why has the team not tried to use terahertz tomography, if X rays gave such poor signal to noise ratio?

I guess this is the answer to this post from 3 months ago<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33735503" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33735503</a>

Reminds me of Kuzushiji recognition with ML, transcribing historical Japanese documents. Both are my favorite applications of ML: deciphering the past. This is really damn cool.