logoalt Hacker News

nicoyesterday at 3:37 PM2 repliesview on HN

Does this need depth data capture as well? The “casual captures” makes it seem like it only needs images, but apparently they are using depth data as well

Also, can it run on Apple silicon?


Replies

KaiserProyesterday at 6:35 PM

Nope, only needs depth for ground truth.

its designed to be run on top of a SLAM system that outputs a sparse point cloud.

on page 4 on the top right you can see how the point cloud is used to then feed into the object generator: https://cdn.jsdelivr.net/gh/facebookresearch/ShapeR@main/res...

lastdongyesterday at 5:57 PM

I think it does use depth data from parameters in docs: python infer_shape.py --input_pkl <sample.pkl> (possibly achievable using software like MapAnything). I believe CUDA only.

show 1 reply