jiawen-zhu / HQTrack

Tracking Anything in High Quality
MIT License
745 stars 65 forks source link
object-segmentation object-tracking tracking-anything

Tracking Anything in High Quality

Technical Report:

:wave:Welcome everyone to contribute and collaborate on HQTrack repository!

Tracking Anything in High Quality (HQTrack) is a framework for high performance video object tracking and segmentation. It mainly consists of a Video Multi-Object Segmenter (VMOS) and a Mask Refiner (MR), can track multiple target objects at the same time and output accurate object masks.

:beer: HQTrack obtains runner-up in the Visual Object Tracking and Segmentaion (VOTS2023) challenge.

:calendar:TODO

:loudspeaker:News

:fire:Demo

We also provide a demo script, which supports box and point prompts as inputs. This is a pure python script that allows the user to test arbitrary videos.

:snake:Pipeline

image

:bookmark_tabs:Intallation

:car:Run HQTrack

Download VMOS model from Google Driver or Baidu Driver and put it under

/path/to/HQTrack/result/default_InternT_MSDeAOTL_V2/YTB_DAV_VIP/ckpt/

Download HQ-SAM_h and put it under

/path/to/HQTrack/segment_anything_hq/pretrained_model/

:dolphin:Training

Stage 1

In stage 1, we pre-train VMOS on synthetic video sequences generated from static image datasets. We refer readers to AFB-URR for preparing the pre-train datasets. The Static dataset should be put in

/path/to/HQTrack/datasets/

Stage 2

In stage 2, video multi-object segmentation datasets are employed for training, e.g., DAVIS and YoutubeVOS.

:book: Citation

If you find HQTrack useful for you, please consider citing :mega:

@misc{hqtrack,
      title={Tracking Anything in High Quality}, 
      Author = {Jiawen Zhu and Zhenyu Chen and Zeqi Hao and Shijie Chang and Lu Zhang and Dong Wang and Huchuan Lu and Bin Luo and Jun-Yan He and Jin-Peng Lan and Hanyuan Chen and Chenyang Li},
      Title = {Tracking Anything in High Quality},
      Year = {2023},
      Eprint = {arXiv:2307.13974},
      PrimaryClass={cs.CV}
}

:hearts: Acknowledgment

This project is based on DeAOT, HQ-SAM, and SAM. Thanks for these excellent works.

:email:Contact

If you have any question, feel free to email jiawen@mail.dlut.edu.cn. ^_^