Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/aim-uofa/Framer
https://github.com/aim-uofa/Framer
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/aim-uofa/Framer
- Owner: aim-uofa
- Created: 2024-10-24T04:46:49.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2024-10-25T05:37:06.000Z (4 months ago)
- Last Synced: 2024-10-25T15:17:14.142Z (4 months ago)
- Size: 7.13 MB
- Stars: 54
- Watchers: 9
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Framer![]()
Framer: Interactive Frame Interpolation
[Wen Wang](https://github.com/encounter1997)1,2, [Qiuyu Wang](https://scholar.google.com/citations?user=VRsy9v8AAAAJ)2, [Kecheng Zheng](https://zkcys001.github.io)2, [Hao Ouyang](https://ken-ouyang.github.io/)2, [Zhekai Chen](https://github.com/Aziily)1, [Biao Gong](https://scholar.google.com/citations?user=BwdpTiQAAAAJ)2, [Hao Chen](https://scholar.google.com/citations?user=FaOqRpcAAAAJ)1,
[Yujun Shen](https://shenyujun.github.io)2, [Chunhua Shen](https://cshen.github.io/)11[Zhejiang University, China](https://www.zju.edu.cn/english/), 2[Ant Group](https://www.antgroup.com/en)
## 🔆 TL;DR
We propose Framer, a more controllable and interactive frame interpolation method that allows users to produce smoothly transitioning frames between two images by customizing the trajectory of selected keypoints, enhancing control and handling challenging cases.
### Main Claims
The proposed method, Framer, provides interactive frame interpolation, allowing users to customize transitions by tailoring the trajectories of selected keypoints.
This approach mitigates the ambiguity of image transformation, enabling much finer control of local motions and improving the model's ability to handle challenging cases (e.g., objects with differing shapes and styles).
Framer also includes an "autopilot" mode that automatically estimates keypoints and refines trajectories, simplifying the process and enabling motion-natural and temporally coherent results.### Methodology
This work utilizes a large-scale pre-trained image-to-video diffusion model (Stable Video Diffusion) as the base model. It introduces additional end-frame conditioning to facilitate video interpolation and incorporates a point trajectory controlling branch for user interaction.### Key Results
Framer outperforms existing frame interpolation methods in terms of visual quality and natural motion, particularly in cases involving complex motions and significant appearance changes.
Quantitative evaluation using FVD (Fréchet Video Distance) demonstrates superior performance compared to other methods.
User studies show a strong preference for Framer's output, highlighting its effectiveness in producing realistic and visually appealing results.## 💡 Changelog
- [x] Oct. 28, 2024. Huggingface Gradio Demo is now available [here](https://huggingface.co/spaces/wwen1997/Framer)!
- [x] Oct. 25, 2024. Launch the project page and upload the arXiv preprint.## Showcases
Note the videos are spatially compressed. We refer readers to the [project page](https://aim-uofa.github.io/Framer) for the original videos.
### 1. Video Interpolation with User-Interaction
Start Image
Input Trajectory & Interpolation Results
End Image
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
### 2. Image Morphing with User-Interaction
Start Image
Input Trajectory & Interpolation Results
End Image
![]()
![]()
![]()
![]()
![]()
![]()
### 3. Video Interpolation without User-Input Control
Start Image
Interpolation Results
End Image
![]()
![]()
![]()
![]()
![]()
![]()
### 4. Novel View Synthesis
Start Image
Interpolation Results
End Image
![]()
![]()
![]()
![]()
![]()
![]()
### 5. Cartoon and Sketch Interpolation
Start Image
Interpolation Results
End Image
![]()
![]()
![]()
![]()
![]()
![]()
### 6. Time-lapsing Video Generation.
Start Image
Interpolation Results
End Image
![]()
![]()
![]()
![]()
![]()
![]()
## 📖 Citation BibTeX
Please consider citing our paper if our code is useful:
```bib
@article{wang2024framer,
title={Framer: Interactive Video Interpolation},
author={Wang, Wen and Wang, Qiuyu and Zheng, Kecheng and Ouyang, Hao and Chen, Zhekai and Gong, Biao and Chen, Hao and Shen, Yujun and Shen, Chunhua},
journal={arXiv preprint https://arxiv.org/abs/2410.18978},
year={2024}
}
```## 🎫 License
For academic use, this project is licensed under [the 2-clause BSD License](LICENSE). For commercial use, please contact [C Shen](mailto:[email protected]).
## 😉 Acknowledgements
- Thanks to [SVD_Xtend](https://github.com/pixeli99/SVD_Xtend) for the wonderful work and codebase.
- Thanks to [DragAnything](https://github.com/showlab/DragAnything) for the wonderful work and codebase.