https://github.com/nvlabs/minvis

https://github.com/nvlabs/minvis

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/nvlabs/minvis
• Owner: NVlabs
• License: other
• Created: 2022-07-28T04:37:23.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-09-16T18:03:25.000Z (about 2 years ago)
• Last Synced: 2024-06-24T05:55:12.698Z (5 months ago)
• Language: Python
• Size: 149 KB
• Stars: 262
• Watchers: 5
• Forks: 23
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - NVlabs/MinVIS

README

        
# MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training

[De-An Huang](https://ai.stanford.edu/~dahuang/), [Zhiding Yu](https://chrisding.github.io/), [Anima Anandkumar](http://tensorlab.cms.caltech.edu/users/anima/)

[[`arXiv`](https://arxiv.org/abs/2208.02245)] [[`Project`]()] [[`BibTeX`](#CitingMinVIS)]



  



### Features

* Video instance segmentation by only training an image instance segmentation model.

* Support major video instance segmentation datasets: YouTubeVIS 2019/2021, Occluded VIS (OVIS).

### Qualitative Results on Occluded VIS

 

## Installation

See [installation instructions](INSTALL.md).

## Getting Started

See [Preparing Datasets for MinVIS](datasets/README.md).

See [Getting Started with MinVIS](GETTING_STARTED.md).

## Model Zoo

Trained models are available for download in the [MinVIS Model Zoo](MODEL_ZOO.md).

## License

The majority of MinVIS is made available under the [Nvidia Source Code License-NC](LICENSE). The trained models in the [MinVIS Model Zoo](MODEL_ZOO.md) are made available under the [CC BY-NC-SA 4.0 License](https://creativecommons.org/licenses/by-nc-sa/4.0/).

Portions of the project are available under separate license terms: Mask2Former is licensed under a [MIT License](https://github.com/facebookresearch/Mask2Former/blob/main/LICENSE). Swin-Transformer-Semantic-Segmentation is licensed under the [MIT License](https://github.com/SwinTransformer/Swin-Transformer-Semantic-Segmentation/blob/main/LICENSE), Deformable-DETR is licensed under the [Apache-2.0 License](https://github.com/fundamentalvision/Deformable-DETR/blob/main/LICENSE).

## Citing MinVIS

```BibTeX

@inproceedings{huang2022minvis,

  title={MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training},

  author={De-An Huang and Zhiding Yu and Anima Anandkumar},

  journal={NeurIPS},

  year={2022}

}

```

## Acknowledgement

This repo is largely based on Mask2Former (https://github.com/facebookresearch/Mask2Former).