lxtGH / lxtGH/OMG-Seg

code of the interactive mode

Open
#63 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.4k
Forks
55
PR merge metrics
No merged PRs in 30d

Description

thanks for the great work!
For the interactive mode, the OMG-Seg paper mentions that the design of the prompt encoder follows SAM, but I can't find the corresponding code that adopts SAM's encoder to generate location queries. Could you tell me where the relevant code is? Also, does it only support using bbox as a prompt? since point prompts seem to be required to expand into bboxes.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Search the Python codebase for the interactive mode, prompt encoder, SAM, and location-query references. Determine where prompt encoding is implemented and whether point prompts are converted to bounding boxes. Done means documenting the relevant entry point and the supported prompt types.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.