TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

88 pointsby qwertygnuover 1 year ago

7 comments

Chironoover 1 year ago
Nice paper. I particularly like how they talk through the ideas they tried that <i>didn’t</i> work, and the process they used to land on the final results. A lot of ML papers present the finished result as if it appeared from nowhere without trial and error, perhaps with some ablations in the appendix and I wish more papers followed this one in talking about the dead ends along the way.
评论 #39098833 未加载
buildbotover 1 year ago
Very interesting work! More details here: <a href="https:&#x2F;&#x2F;depth-anything.github.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;depth-anything.github.io&#x2F;</a><p>It seems better overall and per parameter than current work, with relative and absolute measurement.<p>Is there any research people are aware of that provides sub-mm level models? For 3D modeling purposes? Or is &quot;classic&quot; photogrammetry still the best option there?
MostlyStableover 1 year ago
In grad school I was using stereo video cameras to measure fish. I wonder if a model like this could do it accurately from frame grabs from a single feed now. And of course an AI to identify fish, even if was just which sections of video had&#x2F;did not have fish, not even doing the species level ID, would have saved a ton of time.<p>We had a whole workshop on various monitoring technologies and the take home from the various video tools is that having highly trained grad students and&#x2F;or techs watch and analyze the video is extremely slow and expensive.<p>I haven&#x27;t worked with video in a while now, but I wonder if any labs are doing more automated identification these days. It feels like the kind of problem that is probably completely solvable if the right tech gets applied.
评论 #39098496 未加载
评论 #39099101 未加载
评论 #39097237 未加载
评论 #39098518 未加载
ClassyJacketover 1 year ago
Can someone explain the meaning of labelled vs unlabelled in this context? What kind of information would the labels carry?<p>Did they have depth maps for all 62 million images or not?
评论 #39097066 未加载
xnxover 1 year ago
Very cool to see TikTok sharing its research.
nicollegahover 1 year ago
any information on the inference speed of this vs midas?
leobgover 1 year ago
Impressive demo.<p>Any FSD startup that put their money on LiDAR is even more screwed now.
评论 #39095410 未加载
评论 #39095835 未加载