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
2024-12-09 11:35:16 +08:00
parent 53dcb96024
commit dd4c5141b7
1 changed files with 14 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README.md
View File

@@ -8,7 +8,7 @@
[![Video Name](./assets/grounded_sam_2_intro.jpg)](https://github.com/user-attachments/assets/f0fb0022-779a-49fb-8f46-3a18a8b4e893) [![Video Name](./assets/grounded_sam_2_intro.jpg)](https://github.com/user-attachments/assets/f0fb0022-779a-49fb-8f46-3a18a8b4e893)
**🔥 Project Highlight** ## Highlights
Grounded SAM 2 is a foundation model pipeline towards grounding and track anything in Videos with [Grounding DINO](https://arxiv.org/abs/2303.05499), [Grounding DINO 1.5](https://arxiv.org/abs/2405.10300), [Florence-2](https://arxiv.org/abs/2311.06242), [DINO-X](https://arxiv.org/abs/2411.14347) and [SAM 2](https://arxiv.org/abs/2408.00714). Grounded SAM 2 is a foundation model pipeline towards grounding and track anything in Videos with [Grounding DINO](https://arxiv.org/abs/2303.05499), [Grounding DINO 1.5](https://arxiv.org/abs/2405.10300), [Florence-2](https://arxiv.org/abs/2311.06242), [DINO-X](https://arxiv.org/abs/2411.14347) and [SAM 2](https://arxiv.org/abs/2408.00714).
@@ -21,13 +21,19 @@ Grounded SAM 2 does not introduce significant methodological changes compared to
## Latest updates ## Latest updates
- `2024/12/02`: Support **DINO-X with SAM 2** demos (including object segmentation and tracking), please install the latest version of `dds-cloudapi-sdk==0.3.3` and refer to [Grounded SAM 2 (with DINO-X)](#grounded-sam-2-image-demo-with-dino-x) and [Grounded SAM 2 Video (with DINO-X)](#grounded-sam-2-video-object-tracking-demo-with-custom-video-input-with-dino-x) for more details. - **2024.12.02**: Support **DINO-X with SAM 2** demos (including object segmentation and tracking), please install the latest version of `dds-cloudapi-sdk==0.3.3` and refer to [Grounded SAM 2 (with DINO-X)](#grounded-sam-2-image-demo-with-dino-x) and [Grounded SAM 2 Video (with DINO-X)](#grounded-sam-2-video-object-tracking-demo-with-custom-video-input-with-dino-x) for more details.
- `2024/10/24`: Support [SAHI (Slicing Aided Hyper Inference)](https://docs.ultralytics.com/guides/sahi-tiled-inference/) on Grounded SAM 2 (with Grounding DINO 1.5) which may be helpful for inferencing high resolution image with dense small objects (e.g. **4K** images).
- `2024/10/10`: Support `SAM-2.1` models, if you want to use `SAM 2.1` model, you need to update to the latest code and reinstall SAM 2 follow [SAM 2.1 Installation](https://github.com/facebookresearch/sam2?tab=readme-ov-file#latest-updates). - **2024.10.24**: Support [SAHI (Slicing Aided Hyper Inference)](https://docs.ultralytics.com/guides/sahi-tiled-inference/) on Grounded SAM 2 (with Grounding DINO 1.5) which may be helpful for inferencing high resolution image with dense small objects (e.g. **4K** images).
- `2024/08/31`: Support `dump json results` in Grounded SAM 2 Image Demos (with Grounding DINO).
- `2024/08/20`: Support **Florence-2 SAM 2 Image Demo** which includes `dense region caption`, `object detection`, `phrase grounding`, and cascaded auto-label pipeline `caption + phrase grounding`. - **2024.10.10**: Support `SAM-2.1` models, if you want to use `SAM 2.1` model, you need to update to the latest code and reinstall SAM 2 follow [SAM 2.1 Installation](https://github.com/facebookresearch/sam2?tab=readme-ov-file#latest-updates).
- `2024/08/09`: Support **Ground and Track New Object** throughout the whole videos. This feature is still under development now. Credits to [Shuo Shen](https://github.com/ShuoShenDe).
- `2024/08/07`: Support **Custom Video Inputs**, users need only submit their video file (e.g. `.mp4` file) with specific text prompts to get an impressive demo videos. - **2024.08.31**: Support `dump json results` in Grounded SAM 2 Image Demos (with Grounding DINO).
- **2024.08.20**: Support **Florence-2 SAM 2 Image Demo** which includes `dense region caption`, `object detection`, `phrase grounding`, and cascaded auto-label pipeline `caption + phrase grounding`.
- **2024.08.09**: Support **Ground and Track New Object** throughout the whole videos. This feature is still under development now. Credits to [Shuo Shen](https://github.com/ShuoShenDe).
- **2024.08.07**: Support **Custom Video Inputs**, users need only submit their video file (e.g. `.mp4` file) with specific text prompts to get an impressive demo videos.
## Contents ## Contents
- [Installation](#installation) - [Installation](#installation)