_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI Apple's Cubify Anything: Scaling Indoor 3D Object Detection
Carrok wrote 2 hours 15 min ago:
I really want an app I can scan my whole house with the camera/lidar
combo on my phone, and export it into Blender, where I can then
rearrange furniture and stuff. Apps like Scaniverse get you pretty
close, but everything is one mesh, would be great to be able to slide
the couch around the space without having the manually cut it out of
the mesh.
tuna74 wrote 30 min ago:
Yeah, how hard can it be :)
Carrok wrote 13 min ago:
These days? Doesn't seem that hard honestly.
totetsu wrote 10 hours 36 min ago:
Is this so your smart speaker can better report whats in your house
back to apple?
pzo wrote 11 hours 13 min ago:
They overcomplicate by using 3-4 different (sub) license in one
project:
in README:
Licenses
- The sample code is released under Apple Sample Code License.
- The data is released under CC-by-NC-ND.
- The models are released under Apple ML Research Model Terms of Use.
Acknowledgements
- We use and acknowledge contributions from multiple open-source
projects in
ACKNOWLEDGEMENTS."
then having in github license button "Copyright (C) 2025 Apple Inc. All
Rights Reserved."
in repo file
LICENSE
LICENSE_MODEL
why making it so confusing and elaborate? Its so useless to even use by
3rd party devs for making apps and releasing on their platform. So then
just make it one license with the most strict restrictions you can make
AGPL and/or CC-by-NC-ND .
guipsp wrote 7 hours 20 min ago:
It complicated, but it's not overcomplicated. CC is not adequate for
code and I belive that none of the code is GPL so your suggestion
regarding AGPL is strange.
generalizations wrote 5 hours 39 min ago:
Why isn't CC-by-NC-ND adequate for code? Kinda makes sense IMO and
the summary looks useful?
> CC-BY-NC-ND is a type of Creative Commons license that allows
others to use a work non-commercially, but they cannot modify it or
create derivative works. This means the original work can be
shared, but it must remain unchanged and cannot be used for
commercial purposes.
Notwithstanding it's only applied to the data in this case, it sure
looks like a useful license for code.
tpmoney wrote 4 hours 26 min ago:
> Why isn't CC-by-NC-ND adequate for code? Kinda makes sense IMO
and the summary looks useful?
Because the Creative Commons folks themselves say itâs not
because it doesnât cover a number of software specific edge
cases.
brookst wrote 8 hours 54 min ago:
They could have transformed it from insane to sublime by slapping a
highly restrictive license on the readme itself. Seriously missed
opportunity.
Svip wrote 14 hours 47 min ago:
Will it work on a picture of a Power Mac G4 Cube[0]? Whenever I see
"cube" and "apple" together (which, in fairness, is rare), I think of
the Cube.
[0]
URI [1]: https://en.wikipedia.org/wiki/Power_Mac_G4_Cube
callumprentice wrote 16 hours 9 min ago:
I keep meaning to get back to my suite of equirectangular image
functions - viewers, editors, authoring etc. and this reminded me to
resurrect the Viewer. [1] Not quite right I think because the source
image issn't 2x1 aspect ratio.
They can look really nice: both in the real world - [2] or
the virtual world:
URI [1]: https://equinaut.surge.sh/?eqr=https://raw.githubusercontent.c...
URI [2]: https://equinaut.surge.sh/?eqr=https://upload.wikimedia.org/wi...
URI [3]: https://equinaut.surge.sh/?eqr=https://live.staticflickr.com/6...
pablogancharov wrote 21 hours 7 min ago:
In case anyone is interested in rendering USDZ scans in Three.js, I
created a demo:
URI [1]: https://usdz-threejs-viewer.vercel.app/
mhuffman wrote 18 hours 46 min ago:
Very nice and smooth! Do you have source for your demo?
callumprentice wrote 16 hours 17 min ago:
There is one in the Three.JS example suite with source:
URI [1]: https://threejs.org/examples/webgl_loader_usdz.html
fidotron wrote 21 hours 19 min ago:
The accuracy of the results don't seem that great. For example, looking
at the pictures on the wall in their sample, or the beams in the
ceiling.
It's possible it's some artifact of the processing resolution, but I
think most people that have worked with NNs for AR input will be
surprised that this is not considered disappointing.
ellisv wrote 6 hours 49 min ago:
> The accuracy of the results don't seem that great. For example,
looking at the pictures on the wall in their sample, or the beams in
the ceiling.
Do you mean the accuracy of the classification or the precision of
the lidar scans?
In my experience the lidar precision on the iPhones is decent but not
great, so the texture mapping can look a bit off at times.
I'd love to have these bounding boxes on my scans though.
fidotron wrote 5 hours 33 min ago:
I mean the accuracy with which it's locating the bounds. What is
extra curious is it obviously supports rotated cubes, yet it often
doesn't use them when it should, leading to overstating the bounds,
as if it's over enthusiastically trying to put things aligned to
some inferred axis.
This is obviously an attempt at the general case to apply cubes to
anything, but what is disappointing is the performance on boxy
objects is lower than I've seen on private NNs used for AR and CV
for years (ironically enough on iPads), using just rgb and no
depth.
I half think the exercise here was to establish if transformers
were the way to go for this, and on the strength of that the answer
would be probably not.
syntaxing wrote 21 hours 27 min ago:
Surprised this isnât in coreML. Seems useful for the Vision Pro or
something
hokumguru wrote 16 hours 47 min ago:
Might see it at WWDC this year?
desertmonad wrote 21 hours 59 min ago:
Looks promising but the license,
Attribution-NonCommercial-NoDerivatives is pretty limiting..
huxley wrote 20 hours 17 min ago:
Thatâs just for the data, isnât it, the code is Apple Sample Code
License which I seem to recall is an MIT type license
pzo wrote 11 hours 12 min ago:
"models are released under Apple ML Research Model Terms of Use."
DIR <- back to front page