# No Pixel Left Behind: Filling Gaps in Anime Colorization

arXiv: https://arxiv.org/abs/2609.00800 · HTML: https://mlsanity.com/paper/2609.00800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 94 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ToonCrafter: Generative Cartoon Interpolation](https://mlsanity.com/paper/2405.17933/) (2024)
- [Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems](https://mlsanity.com/paper/2204.07666/) (2022)
- [User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks](https://mlsanity.com/paper/1808.03240/) (2018)
- [Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN](https://mlsanity.com/paper/1706.03319/) (2017)
- [Designing Participatory AI: Creative Professionals' Worries and Expectations about Generative AI](https://mlsanity.com/paper/2303.08931/) (2023)
- [Exploring Challenges and Opportunities to Support Designers in Learning to Co-create with AI-based Manufacturing Design Tools](https://mlsanity.com/paper/2303.00192/) (2023)
- [Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressure](https://mlsanity.com/paper/2306.07458/) (2023)
- [Generative AI for Cel-Animation: A Survey](https://mlsanity.com/paper/2501.06250/) (2025)
- [MangaNinja: Line Art Colorization with Precise Reference Following](https://mlsanity.com/paper/2501.08332/) (2025)
- [APISR: Anime Production Inspired Real-World Anime Super-Resolution](https://mlsanity.com/paper/2403.01598/) (2024)
- [Learning Inclusion Matching for Animation Paint Bucket Colorization](https://mlsanity.com/paper/2403.18342/) (2024)
- ["An Adapt-or-Die Type of Situation": Perception, Adoption, and Use of Text-To-Image-Generation AI by Game Industry Professionals](https://mlsanity.com/paper/2302.12601/) (2023)
- [Collaborative human-AI trust (CHAI-T): A process framework for active management of trust in human-AI collaboration](https://mlsanity.com/paper/2404.01615/) (2024)
- [Understanding User Perceptions, Collaborative Experience and User Engagement in Different Human-AI Interaction Designs for Co-Creative Systems](https://mlsanity.com/paper/2204.13217/) (2022)
- [AniFaceDrawing: Anime Portrait Exploration during Your Sketching](https://mlsanity.com/paper/2306.07476/) (2023)
- [Image Referenced Sketch Colorization Based on Animation Creation Workflow](https://mlsanity.com/paper/2502.19937/) (2025)
- [A Systematic Review of Human-AI Co-Creativity](https://mlsanity.com/paper/2506.21333/) (2025)
- [A Practical Style Transfer Pipeline for 3D Animation: Insights from Production R&D](https://mlsanity.com/paper/2410.24123/) (2024)
- [Understanding Collaboration between Professional Designers and Decision-making AI: A Case Study in the Workplace](https://mlsanity.com/paper/2509.24718/) (2025)
- [Sketch Animation: State-of-the-art Report](https://mlsanity.com/paper/2510.10218/) (2025)

## Abstract (arXiv)

Animation production workflows often involve digital colorization of line art, where small unpainted regions ("gaps") frequently occur and remain an underexplored challenge. We conducted a formative study in Japanese animation (anime) pipelines and found that while the paint bucket tool is widely used for base coloring, tiny enclosed areas are frequently overlooked, resulting in time-consuming manual detection and filling. We introduce GapFill, a tool grounded in professional practices that reduces the effort of gap detection, zooming, and color selection. Our deep-learning method suggests appropriate fill colors by referencing surrounding regions, leveraging the flat-color nature of anime-style images. In a user study with 13 professional colorists, our system improved performance and usability in gap-filling tasks over conventional methods. The study also suggested that prediction accuracy alone is not the primary factor for usability, that appropriate colors can be contextually ambiguous, and that GapFill can complement existing tools depending on users' trust in new AI-powered assistance.