You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Ops to convert N-dimensional segmentation masks to N-dimensional bounding boxes.
Motivation, pitch
Build upon #3960 to support the conversion of N-dimensional asks to bounding boxes.
Use cases:
I have 3D images (from medical imaging) and would like to convert segmentation masks (of tumors, aneurysms, etc.) to bounding boxes.
Sometimes different sources of data are stacked together, giving me 4D images (3D images, stacked along a new dimension to make the image source clear). I would also like to convert these segmentation masks to bounding boxes, although I will admit, I would compute bounding boxes in 3D and then stack those as well.
The text was updated successfully, but these errors were encountered:
RylanSchaeffer
changed the title
Ops to convert masks to boxes #3960
Ops to convert masks to bounding boxes #3960
Aug 31, 2021
RylanSchaeffer
changed the title
Ops to convert masks to bounding boxes #3960
Ops to convert masks to bounding boxes and back again
Aug 31, 2021
datumbox
changed the title
Ops to convert masks to bounding boxes and back again
Generalize masks_to_boxes op to support N-dimensional masks to bounding boxes conversion
Aug 31, 2021
🚀 The feature
Ops to convert N-dimensional segmentation masks to N-dimensional bounding boxes.
Motivation, pitch
Build upon #3960 to support the conversion of N-dimensional asks to bounding boxes.
Use cases:
I have 3D images (from medical imaging) and would like to convert segmentation masks (of tumors, aneurysms, etc.) to bounding boxes.
Sometimes different sources of data are stacked together, giving me 4D images (3D images, stacked along a new dimension to make the image source clear). I would also like to convert these segmentation masks to bounding boxes, although I will admit, I would compute bounding boxes in 3D and then stack those as well.
The text was updated successfully, but these errors were encountered: