quoccuongle/Grounded-SAM-2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update README

Browse Source
This commit is contained in:
rentainhe
2024-08-06 03:08:06 +08:00
parent bb56590c47
commit 731955be0f
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -112,6 +112,9 @@ A simple pipeline visualization is as follows:
![Grounded SAM 2 Tracking Pipeline](./assets/grounded_sam2_tracking_pipeline_vis.png) ![Grounded SAM 2 Tracking Pipeline](./assets/grounded_sam2_tracking_pipeline_vis.png)
> [!NOTE]
> We noticed that the SAM 2 video predictor also supports mask prompts. Using the SAM 2 mask prediction results should be a more straightforward approach, and we will explore this implementation in future release.
### Grounded-SAM-2 Video Object Tracking Demo (with Grounding DINO 1.5 & 1.6) ### Grounded-SAM-2 Video Object Tracking Demo (with Grounding DINO 1.5 & 1.6)
We've also support video object tracking demo based on our stronger `Grounding DINO 1.5` model and `SAM 2`, you can try the following demo after applying the API keys for running `Grounding DINO 1.5`: We've also support video object tracking demo based on our stronger `Grounding DINO 1.5` model and `SAM 2`, you can try the following demo after applying the API keys for running `Grounding DINO 1.5`: