Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!
| Date | Stars |
|---|---|
| 2026-07-24 | 488 |
| 2026-07-25 | 488 |
| 2026-07-28 | 488 |
| 2026-07-30 | 488 |
| 2026-08-06 | 488 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion (MiVOS) [Ho Kei Cheng](https://hkchengrex.github.io/), Yu-Wing Tai, Chi-Keung Tang CVPR 2021 [[arXiv]](https://arxiv.org/abs/2103.07941) [[Paper PDF]](https://arxiv.org/pdf/2103.07941.pdf) [[Project Page]](https://hkchengrex.github.io/MiVOS/) [[Demo]](https://hkchengrex.github.io/MiVOS/video.html#partb) [[Papers with Code]](https://paperswithcode.com/task/interactive-video-object-segmentation) [[Supplementary Material]](docs/supplementary.pdf) ## Newer: check out our new work [Cutie](https://github.com/hkchengrex/Cutie). It also includes an interactive GUI! ## New: see the [STCN branch](https://github.com/hkchengrex/MiVOS/tree/MiVOS-STCN) for a better and faster version.    <sub><sup>Credit (left to right): DAVIS 2017, [Academy of Historical Fencing](https://youtu.be/966ulgwEcyc), [Modern History TV](https://youtu.be/e_D1ZQ7Hu0g)</sup></sub> We manage the project using three different repositories (which are actually in the paper title). This is the main repo, see also [Mask-Propagation](https://github.com/hkchengrex/Mask-Propagation) and [Scribble-to-Mask](https://github.com/hkchengrex/Scribble-to-Mask). ## Overall structure and capabilities | | [MiVOS](https://github.com/hkchengrex/MiVOS) | [Mask-Propagation](https://github.com/hkchengrex/Mask-Propagation)| [Scribble-to-Mask](https://github.com/hkchengrex/Scribble-to-Mask) | | ------------- |:-------------:|:-----:|:-----:| | DAVIS/YouTube semi-supervised evaluation | :x: | :heavy_check_mark: | :x: | | DAVIS interactive evaluation | :heavy_check_mark: | :x: | :x: | | User interaction GUI tool | :heavy_check_mark: | :x: | :x: | | Dense Correspondences | :x: | :heavy_check_mark: | :x: | | Train propagation module | :x: | :heavy_check_mark: | :x: | | Train S2M (interaction) module | :x: | :x: | :heavy_check_mark: | | Train fusion module | :heavy_check_mark: | :x: | :x: | | Generate more synthetic data | :heavy_check_mark: | :x: | :x: | ## Framework  ## Requirements We used these packages/versions in the development of this project. It is likely that higher versions of the same package will also work. This is not an exhaustive list -- other common python packages (e.g. pillow) are expected and not listed. - PyTorch `1.7.1` - torchvision `0.8.2` - OpenCV `4.2.0` - Cython - progressbar - davis-interactive (<https://github.com/albertomontesg/davis-interactive>) - PyQt5 for GUI - networkx `2.4` for DAVIS - gitpython for training - gdown for downloading pretrained models Refer to the official [PyTorch guide]((<https://pytorch.org/>)) for installing PyTorch/torchvision. The rest can be installed by: `pip install PyQt5 davisinteractive progressbar2 opencv-python networkx gitpython gdown Cython` ## Quick start ### GUI 1. `python download_model.py` to get all the required models. 2. `python interactive_gui.py --video <path to video>` or `python interactive_gui.py --images <path to a folder of images>`. A video has been prepared for you at `example/example.mp4`. 3. If you need to label more than one object, additionally specify `--num_objects <number_of_objects>`. See all the argument options with `python interactive_gui.py --help`. 4. There are instructions in the GUI. You can also watch the [demo videos](https://hkchengrex.github.io/MiVOS/video.html#partb) for some ideas. ### DAVIS Interactive VOS See `eval_interactive_davis.py`. If you have downloaded the datasets and pretrained models using our script, you only need to specify the output path, i.e., `python eval_interactive_davis.py --output [somewhere]`. ### DAVIS/YouTube Semi-supervised VOS Go to this repo: [Mask-Propagation](https://github.com/hkchengrex/Mask-Propagation). ## Main Results ### [DAVIS/YouTube semi-supervised results](https://github.com/
Excerpt of 12,888 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8ce319932869388a, topic:deep-learning, topic:pytorch
matched fp:8ce319932869388a, topic:computer-vision