PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters
This work addresses the lack of methods for 3D reconstruction from anime-style illustrations, which is important for creators in animation and gaming, though it is incremental as it builds on existing single-view reconstruction techniques.
The paper tackles the problem of reconstructing stylized 3D character heads from single-view anime portraits, addressing challenges like complex geometry and non-photorealistic shading, and reports that PAniC-3D significantly outperforms baseline methods on a new benchmark.
We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters. Our anime-style domain poses unique challenges to single-view reconstruction; compared to natural images of human heads, character portrait illustrations have hair and accessories with more complex and diverse geometry, and are shaded with non-photorealistic contour lines. In addition, there is a lack of both 3D model and portrait illustration data suitable to train and evaluate this ambiguous stylized reconstruction task. Facing these challenges, our proposed PAniC-3D architecture crosses the illustration-to-3D domain gap with a line-filling model, and represents sophisticated geometries with a volumetric radiance field. We train our system with two large new datasets (11.2k Vroid 3D models, 1k Vtuber portrait illustrations), and evaluate on a novel AnimeRecon benchmark of illustration-to-3D pairs. PAniC-3D significantly outperforms baseline methods, and provides data to establish the task of stylized reconstruction from portrait illustrations.