[feature request] [discussion] mask utils in core
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
🚀 The feature
- Extracting bounding boxes from label map: https://github.com/pytorch/pytorch/issues/22378#issuecomment-881954924, https://github.com/pytorch/vision/issues/3960 - scatter_reduce now supports amin/amax, so can be done in batched regime
- Extracting label maps from RGB label maps (https://github.com/pytorch/pytorch/issues/5436)
- Conversion of RGB uint8 tensors to RGBA (or ARGB) uint32 tensor (https://github.com/pytorch/pytorch/issues/5436#issuecomment-920034956) for extracting "unique" labels faster
- Compression of masks (relevant for images with many objects / segments), e.g. RLE encoding / decoding as found in pycocotools.mask
Motivation, pitch
In detection/segmentation these utils are very frequent
Alternatives
No response
Additional context
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the linked PyTorch and PyTorch Vision discussions and the pycocotools.mask API. The requested scope covers bounding-box and label-map extraction, RGB-to-packed-label conversion, and mask compression, so completion first requires settling which utilities belong in torchvision and defining their expected behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100