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?
Also, can it run on Apple silicon?
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...
> Furthermore, by leveraging tools like MapAnything to generate metric points, ShapeR can even produce metric 3D shapes from monocular images without retraining.