Mirrors/Track-Anything
1
0
Fork 0
mirror of https://github.com/gaomingqi/Track-Anything.git synced 2025-12-16 08:27:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix mapper color

Browse Source
This commit is contained in:
gaomingqi
2023-04-19 20:00:25 +08:00
parent 5c8fb53563 45f5897a47
commit eaa9ab1597
3 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@@ -2,7 +2,7 @@
<!-- [![](https://img.shields.io/badge/arxiv-23xx.xxxxx-red.svg?style=flat-square)](linkUrl) &nbsp; [![](https://img.shields.io/badge/:hugs:-Open_in_Spaces-informational.svg?style=flat-square)](linkUrl) &nbsp; [![](https://img.shields.io/badge/contributors-SUSTech_VIP_Lab-important.svg?style=flat-square)](https://zhengfenglab.com/) -->
***Track-Anything*** is a flexible and interactive tool for video object tracking and segmentation. It is developed upon [Segment Anything](https://github.com/facebookresearch/segment-anything) and [XMem](https://github.com/hkchengrex/XMem), can specify anything to track and segment via user clicks only. During tracking, users can flexibly change the objects they wanna track or correct the region of interest if there are any ambiguities. These characteristics enable ***Track-Anything*** to be suitable for:
***Track-Anything*** is a flexible and interactive tool for video object tracking and segmentation. It is developed upon [Segment Anything](https://github.com/facebookresearch/segment-anything), can specify anything to track and segment via user clicks only. During tracking, users can flexibly change the objects they wanna track or correct the region of interest if there are any ambiguities. These characteristics enable ***Track-Anything*** to be suitable for:
- Video object tracking and segmentation with shot changes.
- Visualized development and data annnotation for video object tracking and segmentation.
- Object-centric downstream video tasks, such as video inpainting and editing.
@@ -11,17 +11,17 @@
https://user-images.githubusercontent.com/28050374/232842703-8395af24-b13e-4b8e-aafb-e94b61e6c449.MP4
### Video Object Tracking and Segmentation with Shot Changes
### Multiple Object Tracking and Segmentation (with [XMem](https://github.com/hkchengrex/XMem))
one gif/video
https://user-images.githubusercontent.com/39208339/233035206-0a151004-6461-4deb-b782-d1dbfe691493.mp4
### Video Object Tracking and Segmentation with Shot Changes (with [XMem](https://github.com/hkchengrex/XMem))
https://user-images.githubusercontent.com/30309970/232848349-f5e29e71-2ea4-4529-ac9a-94b9ca1e7055.mp4
### Video Inpainting (with [E2FGVI](https://github.com/MCG-NKU/E2FGVI))
![image](./assets/inpainting.gif)
### Video Editing
one gif/video
https://user-images.githubusercontent.com/28050374/232959816-07f2826f-d267-4dda-8ae5-a5132173b8f4.mp4
## Get Started
#### Linux
@@ -44,6 +44,6 @@ pip install madgrad
python app.py --device cuda:0 --sam_model_type vit_h --port 12212
```
## Acknowledgement
## Acknowledgements
The project is based on [Segment Anything](https://github.com/facebookresearch/segment-anything) and [XMem](https://github.com/hkchengrex/XMem). Thanks for the authors for their efforts.
The project is based on [Segment Anything](https://github.com/facebookresearch/segment-anything), [XMem](https://github.com/hkchengrex/XMem), and [E2FGVI](https://github.com/MCG-NKU/E2FGVI). Thanks for the authors for their efforts.

6
app.py
View File

@@ -193,9 +193,9 @@ xmem_checkpoint = download_checkpoint(xmem_checkpoint_url, folder, xmem_checkpoi
# args, defined in track_anything.py
args = parse_augment()
args.port = 12212
args.device = "cuda:4"
args.mask_save = True
# args.port = 12212
# args.device = "cuda:4"
# args.mask_save = True
model = TrackingAnything(SAM_checkpoint, xmem_checkpoint, args)

BIN
assets/qingming.mp4 Normal file
View File

Binary file not shown.