Research map / 3D vision / Face and shape
PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation
Hongyu Yan, Kunming Luo, Weiyu Li, Kaiyi Zhang, Yixun Liang, Jingwei Huang, Chunchao Guo, Ping Tan
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 |
|---|---|---|---|
| add 3D skeleton guidance to image-to-3D generation (ablation) | PoseMaster vs Hunyuan3D 2.1 · image-to-3D (Table 3) | MAE: 6.56 -> 4.82 | Improved |
| add 3D skeleton guidance to image-to-3D generation (ablation) | PoseMaster vs Hunyuan3D 2.1 · image-to-3D (Table 3) | ULIP-I: 0.154 -> 0.158 | No clear effect |
| use native 3D skeleton conditioning instead of 2D cascade (StdGen) on pose canonicalization | PoseMaster vs StdGen · VRoid canonicalization | MAE: 4.97 -> 4.59 | Improved |
| replace 2D canonicalization + 3D generator with unified model | PoseMaster vs Hunyuan3D 2.1 with StdGen A-pose input · VRoid canonicalization | MAE: 5.89 -> 4.59 | Improved |
| use PoseMaster with skeleton on arbitrary-pose stylization | PoseMaster vs Hunyuan3D 2.1 given target-pose image · arbitrary-pose stylization | MAE: 6.75 -> 5.28 | Improved |
| use dense interpolated skeleton point cloud with bone directions instead of sparse joints (ablation) | PoseMaster skeleton encoder · complex poses | qualitative | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StdGen — StdGEN: Semantic-Decomposed 3D Character Generation from Single Images (CVPR 2025) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (CVPR 2024 · similarity 0.89)
- Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles (NeurIPS 2025 · similarity 0.88)
- 3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images (CVPR 2024 · similarity 0.88)
- RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation (ICLR 2025 · similarity 0.87)
- SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons (CVPR 2025 · similarity 0.87)
- Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (NeurIPS 2026 · similarity 0.86)
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.
