Apple releases Depth Pro, an AI model that rewrites the rules of 3D vision | Hacker News Reader

Apple releases Depth Pro, an AI model that rewrites the rules of 3D vision

venturebeat.com

112 pointsbentocorp20 comments

https://news.ycombinator.com/item?id=41738022

Title is such clickbait, it does not rewrite the rules of 3d vision, it is a marginal improvement on existing models, and does not work for video, only images. However, Apple open sourced the model weights, which is amazing for research.

Right, the title is so awful that i didn't even feel like reading the article.

I made it about a third of the way down. It doesn't get any better. Gave up when I hit the auto playing unrelated video that you can't scroll past. Do people really keep reading an article while a video about something else is playing on the top third of their screen? Totally nuts.

It's AI generated PR, perhaps the worst use of AI.

Intel open sourced Midas, too, which seems to have pretty similar result quality.

“The greatest model, just got better, introducing…” can I have a job now ?

What is the topology of the model like?

This article has a link to the live demo.

https://huggingface.co/spaces/akhaliq/depth-pro

For some pictures it outputs something reasonable, for others it's completely broken (black with colored noise in one area).

Just tried it on a "difficult" image (relatively low contrast photo of a small thin plant in front of a tree trunk with a distant fence in one corner) and it did a pretty good job, I think - https://imgur.com/a/Sqr6hR8 including the depth maps.

Mind you, it failed completely on my next test image - https://imgur.com/a/nFYtl77

This presumably is the same model that the Vision Pro Photos app uses to convert 2D photos to 3D.

Was this trained on iPhone photos since there is a decent amount of depth references within iPhone cameras? It’s interesting to see how clearly it understands depth of field. With that, how does it perform on F16 and above?

interesting. They claim 0.3 seconds on a consumer GPU; I thought that might scale to 30 seconds or so on CPU but gave up waiting after twelve minutes.

https://huggingface.co/spaces/akhaliq/depth-pro

Can I use this to generate accurate depth maps from 2-D images that I can then CNC or 3-D print?

No. You’ll want a photogrammetry or LIDAR app for that.

Maybe, if you're OK with printing just the front face of an object with its depth being roughly estimated.

You can of course do some great art with just a depth map manifested in a substance like marble:

https://en.wikipedia.org/wiki/Parthenon_Frieze

(Exaggerating a bit. Ancient Greek reliefs do have sculpted detail on the underside, e.g. the horse legs come slightly detached from the surface. So they are not 100% depth maps.)

Kinda, but you dont get the back.

Reply on news.ycombinator.com