Adding new feature of image segmentation by using Grounded SAM2 #1977
Description
Search before asking
- I have searched the Supervision issues and found no similar feature requests.
Description
I would like to contribute a new example under the examples section that demonstrates image segmentation using Grounded SAM2. The example will allow users to segment parts of an image interactively using points, bounding boxes, or text prompts, providing flexibility for different annotation and exploration needs. This will serve as a practical reference for users looking to integrate Grounded SAM2 into real-world segmentation workflows.
and can you assign this to me under Hacktoberfest 2025
Use case
The proposed feature adds a new example script under the examples section to demonstrate how to perform image segmentation using Grounded SAM2. Unlike the current examples that may focus on single modes of input, this script will showcase a flexible way to generate segmentation masks using multiple types of inputs such as points, bounding boxes, and text prompts.
This use case is important because many real-world applications of segmentation require different input methods depending on the scenario (e.g., annotating objects by clicking on points, drawing a bounding box around regions, or providing a descriptive text prompt). Having a ready-to-use example will make it easier for researchers, developers, and practitioners to quickly experiment with Grounded SAM2 in diverse workflows, without needing to write additional boilerplate code.
By including this example, the project will provide a more comprehensive resource for users who want to explore practical segmentation use cases and speed up their adoption of the library in custom projects.
Additional
As i have already done a simple project it will be an easy task for me to contribute to supervision in this domain
and can you assign this to me under Hacktoberfest 2025
Are you willing to submit a PR?
- Yes I'd like to help by submitting a PR!