Research map / 3D vision / Face and shape
PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters
Shuhong Chen, Kevin Zhang, Yichun Shi, Heng Wang, Yiheng Zhu, Guoxian Song, Sizhe An, Janus Kristjansson, Xiao Yang, Matthias Zwicker
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use PAniC-3D instead of PixelNerf | single-view reconstruction on AnimeRecon · AnimeRecon, front | CLIP: 91.07 -> 94.66 | Improved |
| Use PAniC-3D instead of PixelNerf | single-view reconstruction on AnimeRecon · AnimeRecon, geometry | CD: 1.45 -> 1.33 | Improved |
| Use PAniC-3D line removal instead of Telea inpainting | illustration-to-render translation · AnimeRecon | LPIPS: 23.91 -> 18.26 | Improved |
| Add feature pooling to distribute information along triplane axes (ablation) | PAniC-3D reconstruction · AnimeRecon | F-1@5: 35.26 -> 37.73 | Improved |
| Add a multi-layer triplane (ablation) | PAniC-3D reconstruction · AnimeRecon | F-1@5: 34.55 -> 37.73 | Improved |
| Add side/back-view reconstruction losses (ablation) | PAniC-3D reconstruction · AnimeRecon | F-1@10: 58.67 -> 65.50 | Improved |
| Add side/back-view reconstruction losses (ablation) | PAniC-3D reconstruction · AnimeRecon | CD: 1.56 -> 1.33 | Improved |
| Add 2.5D supervision (ablation) | PAniC-3D reconstruction · AnimeRecon | LPIPS: 20.76 -> 19.37 | Improved |
| Add 2.5D supervision (ablation) | PAniC-3D reconstruction · AnimeRecon | F-1@5: 36.42 -> 37.73 | Improved |
Closest papers by meaning
- StdGEN: Semantic-Decomposed 3D Character Generation from Single Images (CVPR 2025 · similarity 0.87)
- 3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images (CVPR 2024 · similarity 0.87)
- CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models (CVPR 2025 · similarity 0.87)
- FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video (CVPR 2025 · similarity 0.85)
- Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters (CVPR 2025 · similarity 0.85)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
