https://github.com/zhang-tao-whu/dvis_plus
https://github.com/zhang-tao-whu/dvis_plus
open-vocabulary video-instance-segmentation video-segmentation video-semantic-segmentation
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/zhang-tao-whu/dvis_plus
- Owner: zhang-tao-whu
- Created: 2023-11-14T10:55:11.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-07-04T03:34:51.000Z (10 months ago)
- Last Synced: 2024-12-26T10:06:26.973Z (4 months ago)
- Topics: open-vocabulary, video-instance-segmentation, video-segmentation, video-semantic-segmentation
- Language: Python
- Homepage:
- Size: 442 KB
- Stars: 97
- Watchers: 3
- Forks: 7
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Universal Video Segmentation Methods Based on DVIS
1. [DVIS++: Improved Decoupled Framework for Universal Video Segmentation](./DVIS_Plus/README.md)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-ovis-1?p=dvis-improved-decoupled-framework-for)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-1?p=dvis-improved-decoupled-framework-for)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-2?p=dvis-improved-decoupled-framework-for)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-3?p=dvis-improved-decoupled-framework-for)
[](https://paperswithcode.com/sota/video-semantic-segmentation-on-vspw?p=dvis-improved-decoupled-framework-for)
[](https://paperswithcode.com/sota/video-panoptic-segmentation-on-vipseg?p=dvis-improved-decoupled-framework-for)
2. [DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries](./DVIS_DAQ/README.md)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-ovis-1?p=dvis-daq-improving-video-segmentation-via)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-2?p=dvis-daq-improving-video-segmentation-via)
[](https://paperswithcode.com/sota/video-instance-segmentation-on-youtube-vis-1?p=dvis-daq-improving-video-segmentation-via)
## News
- DVIS-DAQ has been accepted by ECCV 2024. `2024.7.3`
- DVIS-DAQ achieves 57.1 AP on the OVIS dataset and also sets a new SOTA performance on YTVIS19/21 and VIPSeg. The code is released in this repository and [DAQ-VS](https://github.com/SkyworkAI/DAQ-VS). The paper is available at [DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries](https://arxiv.org/pdf/2404.00086.pdf) and the project page can be found in [project page](https://zhang-tao-whu.github.io/projects/DVIS_DAQ/).
- DVIS and DVIS++ achieved **1st place** in the VPS Track of the PVUW challenge at CVPR 2023. `2023.5.25`
- DVIS and DVIS++ achieved **1st place** in the VIS Track of the 5th LSVOS challenge at ICCV 2023. `2023.8.15`
## Citation
```BibTeX
@article{zhang2023dvis,
title={DVIS: Decoupled Video Instance Segmentation Framework},
author={Zhang, Tao and Tian, Xingye and Wu, Yu and Ji, Shunping and Wang, Xuebo and Zhang, Yuan and Wan, Pengfei},
journal={arXiv preprint arXiv:2306.03413},
year={2023}
}
@article{zhang2023dvisplus,
title={DVIS++: Improved Decoupled Framework for Universal Video Segmentation},
author={Tao Zhang and Xingye Tian and Yikang Zhou and Shunping Ji and Xuebo Wang and Xin Tao and Yuan Zhang and Pengfei Wan and Zhongyuan Wang and Yu Wu},
journal={arXiv preprint arXiv:2312.13305},
year={2023},
}
@article{dvisdaq,
title={DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries},
author={Yikang Zhou and Tao Zhang and Shunping Ji and Shuicheng Yan and Xiangtai Li},
journal={arXiv},
year={2024},
}
```