https://github.com/jaliborc/re-draw

Redraw animation details using AI while retaining artistic control.
https://github.com/jaliborc/re-draw

anime neural-network research-paper

Last synced: about 1 month ago
JSON representation

Redraw animation details using AI while retaining artistic control.

• Host: GitHub
• URL: https://github.com/jaliborc/re-draw
• Owner: Jaliborc
• Created: 2023-09-29T22:59:18.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-05-28T16:16:33.000Z (8 months ago)
• Last Synced: 2024-05-29T07:25:04.627Z (8 months ago)
• Topics: anime, neural-network, research-paper
• Language: HTML
• Homepage: https://jaliborc.github.io/re-draw/
• Size: 20.8 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Re:Draw





Website • Paper • Explainer • Stress Test





![teaser](https://raw.githubusercontent.com/Jaliborc/re-draw/main/images/teaser/ABCDEFGH.webp)

**Re:Draw - Context Aware Translation as a Controllable Method for Artistic Production**  

[Joao Liborio Cardoso](https://www.jaliborc.com), [Francesco Banterle](http://www.banterle.com/francesco/), [Paolo Cignoni](https://vcg.isti.cnr.it/~cignoni/), [Michael Wimmer](https://www.cg.tuwien.ac.at/staff/MichaelWimmer)  

In Proceedings of the 33rd International Joint Conference on Artificial Intelligence

*We introduce context-aware translation, a novel method that combines the benefits of inpainting and image-to-image translation, respecting simultaneously the original input and contextual relevance -- where existing methods fall short. By doing so, our method opens new avenues for the controllable use of AI within artistic creation, from animation to digital art.*

*As an use case, we apply our method to redraw any hand-drawn animated character eyes based on any design specifications -- eyes serve as a focal point that captures viewer attention and conveys a range of emotions, however, the labor-intensive nature of traditional animation often leads to compromises in the complexity and consistency of eye design. Furthermore, we remove the need for production data for training and introduce a new character recognition method that surpasses existing work by not requiring fine-tuning to specific productions. This proposed use case could help maintain consistency throughout production and unlock bolder and more detailed design choices without the production cost drawbacks. A user study shows context-aware translation is preferred over existing work 95.16% of the time.*

## Citation

Please, do not forget to cite our work:

```bibtex

@misc{cardoso2024redraw,

	title={Re:Draw -- Context Aware Translation as a Controllable Method for Artistic Production}, 

	author={Jo\~ao Lib\'orio Cardoso and Francesco Banterle and Paolo Cignoni and Michael Wimmer},

	year={2024}, eprint={2401.03499}, archivePrefix={arXiv},

	primaryClass={cs.CV}

}

```