ToonOut: Fine-tuned Background-Removal for Anime Characters
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911142959382528 |
|---|---|
| author | Muratori, Matteo Seytre, Joël |
| author_facet | Muratori, Matteo Seytre, Joël |
| contents | While state-of-the-art background removal models excel at realistic imagery, they frequently underperform in specialized domains such as anime-style content, where complex features like hair and transparency present unique challenges. To address this limitation, we collected and annotated a custom dataset of 1,228 high-quality anime images of characters and objects, and fine-tuned the open-sourced BiRefNet model on this dataset. This resulted in marked improvements in background removal accuracy for anime-style images, increasing from 95.3% to 99.5% for our newly introduced Pixel Accuracy metric. We are open-sourcing the code, the fine-tuned model weights, as well as the dataset at: https://github.com/MatteoKartoon/BiRefNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06839 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ToonOut: Fine-tuned Background-Removal for Anime Characters Muratori, Matteo Seytre, Joël Computer Vision and Pattern Recognition Machine Learning While state-of-the-art background removal models excel at realistic imagery, they frequently underperform in specialized domains such as anime-style content, where complex features like hair and transparency present unique challenges. To address this limitation, we collected and annotated a custom dataset of 1,228 high-quality anime images of characters and objects, and fine-tuned the open-sourced BiRefNet model on this dataset. This resulted in marked improvements in background removal accuracy for anime-style images, increasing from 95.3% to 99.5% for our newly introduced Pixel Accuracy metric. We are open-sourcing the code, the fine-tuned model weights, as well as the dataset at: https://github.com/MatteoKartoon/BiRefNet. |
| title | ToonOut: Fine-tuned Background-Removal for Anime Characters |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.06839 |