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.

Bolt3D: Generating 3D Scenes in Seconds

290 pointsby jasondavies2 months ago

11 comments

bhouston2 months ago
It doesn&#x27;t seem to work that well. Once you move off the primary camera axis, like rotate around, you notice that there are many regions with only sparse resolution and there are gaps everywhere. It is totally unusable for anything.<p>Sure, it solves for the primary view, but this is claiming it is a 3D scene reconstruction&#x2F;inference technique and in that claim it only sort of works.<p>For example: <a href="https:&#x2F;&#x2F;i.postimg.cc&#x2F;43tj36jv&#x2F;Screenshot-2025-03-20-at-8-52-48-AM.png" rel="nofollow">https:&#x2F;&#x2F;i.postimg.cc&#x2F;43tj36jv&#x2F;Screenshot-2025-03-20-at-8-52-...</a>
评论 #43423251 未加载
burgerone2 months ago
What&#x27;s the use case for putting AI into everything? Pretty much every AI product so far has been and still is subject to hallucinations and inaccuracies and on top of that it&#x27;s hugely computing intensive. Sure, it&#x27;s the best we have right now and it allows us to do things that were previously next to impossible with manual programming work, but it&#x27;s far from being something that&#x27;s actually viable. And what would be the use case for turning a picture into an approximated 3d mesh that is only really complete from one angle? LIDAR does a stunningly accurate job at that already, reproducibly (although granted that this cannot retroactively be applied to existing photos).
评论 #43430054 未加载
评论 #43443914 未加载
scyzoryk_xyz2 months ago
I’m imagining this approach being combined down the line with your typical photogrammetry approach for reinforcing quality.
diggan2 months ago
Show. Us. The. Wireframes!<p>Every single time a new &quot;Generate 3D&quot; thing appears, they never show the wireframes of the objects&#x2F;scenes up front, always you need to download and inspect things yourself. How is this not standard practice already?<p>Not displaying the wireframes at all, or even offer sample files so we could at least see it ourselves, just makes it look like you already know that the generated results are unusable...
评论 #43418974 未加载
评论 #43418938 未加载
评论 #43418939 未加载
评论 #43421640 未加载
评论 #43418944 未加载
评论 #43421287 未加载
slowtrek2 months ago
Is anything like this available locally yet?
评论 #43418797 未加载
noduerme2 months ago
I&#x27;m very unclear as to what is supposed to be happening locally here, but as soon as the demo finishes loading, it crashes firefox on my phone.
评论 #43421340 未加载
antonkar2 months ago
We’ll hopefully convert an LLM into a 3D haunted house and finally democratize AI interpretability by having millions of gamers walking in them
oplane2 months ago
Can 3D generation happen for terrain views on a map ?
flykespice2 months ago
Good good, now show me the topology
marianaenhn2 months ago
ok, thx
tmilard2 months ago
Impressed with Bolt3D AI model ! - Speed of the 3D generation, - Accurate 3D mesh deduction. It&#x27;s a wonderfull chock.<p>I agree, this is the way forward: - &quot;some photos&quot; as imput. - Convenient, a camera is in every pocket (Smartphone).<p>On WE, I have been trying for years to generate 3D from photos.My tool now works well, but there is still this big problem of the time it takes to &quot;recreate&quot; the 3D mesh from photos. I remind that photos are in ... 2D.Not convenient. Here is an example of my Tool&#x27;s generation : <a href="https:&#x2F;&#x2F;free-visit.net&#x2F;fr&#x2F;demo01" rel="nofollow">https:&#x2F;&#x2F;free-visit.net&#x2F;fr&#x2F;demo01</a><p>Here, Bolt3d takes away the 4 hours combersome work into a automatic process. Wahoo !<p>So Bravo to the Bolt3d team of researchers.