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
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.
Yeah they confirm that at the bottom of the linked page
> Furthermore, by leveraging tools like MapAnything to generate metric points, ShapeR can even produce metric 3D shapes from monocular images without retraining.
KaiserPro|1 month ago
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...
lastdong|1 month ago
efskap|1 month ago
> Furthermore, by leveraging tools like MapAnything to generate metric points, ShapeR can even produce metric 3D shapes from monocular images without retraining.