# ToonOut: Fine-tuned Background-Removal for Anime Characters

arXiv: https://arxiv.org/abs/2509.06839 · HTML: https://mlsanity.com/paper/2509.06839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Boundary IoU: Improving Object-Centric Image Segmentation Evaluation](https://mlsanity.com/paper/2103.16562/) (2021)
- [CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement](https://mlsanity.com/paper/2005.02551/) (2020)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021)
- [Gradient-Induced Co-Saliency Detection](https://mlsanity.com/paper/2004.13364/) (2020)
- [On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression](https://mlsanity.com/paper/2008.07281/) (2020)
- [Multi-view Aggregation Network for Dichotomous Image Segmentation](https://mlsanity.com/paper/2404.07445/) (2024)

## Abstract (arXiv)

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.