pose_and_shape_evaluation icon indicating copy to clipboard operation
pose_and_shape_evaluation copied to clipboard
verified publisher icon roym899

Improve automatically generated visualization

Open roym899 opened this issue 2 years ago • 0 comments

Currently a single view per dataset is autogenerated with prediction on top of point cloud. Better to generate three separate figures: prediction, ground-truth, and masked RGB-D, as shown below. Camera view has to be adjusted to automatically focus object of interest.

Possibly auto crop like this

roym899 avatar Jan 05 '23 13:01 roym899