SpatialLM, a 1B model capable of spatial identification, using 3d point cloud data. The video demo is amazing.
SpatialLM: Large Language Model for Spatial Understanding
The demo looks pretty impressive, but it's a prerecorded demo we know nothing about. SO many AI companies have been lying about their benchmarks.
Apparently they have code. I haven’t tried it yet though.
Looks impressive and it's truly open-source.
However, I see it requires CUDA. Could it run anyway:
I think the bigger bottleneck is SLAM, running that is intensive, it wont directly run on video, and SLAM is tough i guess, reading the repo doesn't give any clues of it being able to run on CPU inference.
Now build a robot / autonomous (remote controlled) car / robo vacuum with that.
Isn't that basically a variant of photogrametry but enhanced by AI so as to need fewer photos?
