We introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models. Current professional workflows require tedious manual segmentation and the artistic ``hallucination'' of occluded regions to enable motion. Our approach overcomes this by decomposing a single image into fully inpainted, semantically distinct layers with inferred drawing orders. To address the scarcity of training data, we introduce a scalable engine that bootstraps high-quality supervision from commercial Live2D models, capturing pixel-perfect semantics and hidden geometry. Our methodology couples a diffusion-based Body Part Consistency Module, which enforces global geometric coherence, with a pixel-level pseudo-depth inference mechanism. This combination resolves the intricate stratification of anime characters, e.g., interleaving hair strands, allowing for dynamic layer reconstruction. We demonstrate that our approach yields high-fidelity, manipulatable models suitable for professional, real-time animation applications.
@article{arxiv.2602.03749,
title = {See-through: Single-image Layer Decomposition for Anime Characters},
author = {Jian Lin and Chengze Li and Haoyun Qin and Kwun Wang Chan and Yanghua Jin and Hanyuan Liu and Stephen Chun Wang Choy and Xueting Liu},
journal= {arXiv preprint arXiv:2602.03749},
year = {2026}
}