Spaces:
Running
Running
| title: DeepContourFlow | |
| emoji: 🪢 | |
| colorFrom: pink | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 6.18.0 | |
| python_version: '3.13' | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: DCF is an unsupervised & 1-shot 2D segmentation method | |
| # Deep ContourFlow — interactive demo | |
| **Training-free** image segmentation: a circular contour is *evolved* into the | |
| boundary of the main object, guided only by the multi-scale features of a frozen | |
| VGG16. No training, no labels, no annotated dataset. | |
| Upload an image, tweak a couple of sliders, and watch the contour converge. | |
| - 📄 Paper: [arXiv:2407.10696](https://arxiv.org/abs/2407.10696) | |
| - 💻 Code: [github.com/antoinehabis/Deep-ContourFlow](https://github.com/antoinehabis/Deep-ContourFlow) | |
| Built with [Gradio](https://gradio.app). Configuration reference: | |
| https://huggingface.co/docs/hub/spaces-config-reference | |