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

Add DINO-X arXiv link

Browse Source
This commit is contained in:
Ren Tianhe
2024-12-02 16:21:45 +08:00
committed by GitHub
parent 7262a579d7
commit 13d23efc55
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -4,7 +4,7 @@
[Tianhe Ren](https://rentainhe.github.io/), [Shuo Shen](https://github.com/ShuoShenDe) [Tianhe Ren](https://rentainhe.github.io/), [Shuo Shen](https://github.com/ShuoShenDe)
[[`SAM2 Paper`](https://arxiv.org/abs/2408.00714)] [[`Grounding DINO Paper`](https://arxiv.org/abs/2303.05499)] [[`Grounding DINO 1.5 Paper`](https://arxiv.org/abs/2405.10300)] [[`BibTeX`](#citation)] [[`SAM 2 Paper`](https://arxiv.org/abs/2408.00714)] [[`Grounding DINO Paper`](https://arxiv.org/abs/2303.05499)] [[`Grounding DINO 1.5 Paper`](https://arxiv.org/abs/2405.10300)] [[`DINO-X Paper`](https://arxiv.org/abs/2411.14347)] [[`BibTeX`](#citation)]
[![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)
@@ -13,8 +13,8 @@
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) 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) and [SAM 2](https://arxiv.org/abs/2408.00714).
In this repo, we've supported the following demo with **simple implementations**: In this repo, we've supported the following demo with **simple implementations**:
- **Ground and Segment Anything** with Grounding DINO, Grounding DINO 1.5 & 1.6 and SAM 2 - **Ground and Segment Anything** with Grounding DINO, Grounding DINO 1.5 & 1.6, DINO-X and SAM 2
- **Ground and Track Anything** with Grounding DINO, Grounding DINO 1.5 & 1.6 and SAM 2 - **Ground and Track Anything** with Grounding DINO, Grounding DINO 1.5 & 1.6, DINO-X and SAM 2
- **Detect, Segment and Track Visualization** based on the powerful [supervision](https://github.com/roboflow/supervision) library. - **Detect, Segment and Track Visualization** based on the powerful [supervision](https://github.com/roboflow/supervision) library.
Grounded SAM 2 does not introduce significant methodological changes compared to [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://arxiv.org/abs/2401.14159). Both approaches leverage the capabilities of open-world models to address complex visual tasks. Consequently, we try to **simplify the code implementation** in this repository, aiming to enhance user convenience. Grounded SAM 2 does not introduce significant methodological changes compared to [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://arxiv.org/abs/2401.14159). Both approaches leverage the capabilities of open-world models to address complex visual tasks. Consequently, we try to **simplify the code implementation** in this repository, aiming to enhance user convenience.