Pose-Aware Diffusion for 3D Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917452597690368 |
|---|---|
| author | Zhou, Zihan Chen, Luxi Zhou, Jingzhi Wan, Yuhao Zhao, Min Fan, Baoyu Li, Chongxuan |
| author_facet | Zhou, Zihan Chen, Luxi Zhou, Jingzhi Wan, Yuhao Zhao, Min Fan, Baoyu Li, Chongxuan |
| contents | Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rotate paradigms. To this end, we introduce Pose-Aware Diffusion (PAD), a novel end-to-end diffusion framework that synthesizes 3D geometry directly within the observation space. By unprojecting monocular depth into a partial point cloud and explicitly injecting it as a 3D geometric anchor, PAD abandons canonical assumptions to enforce rigorous spatial supervision. This native generation intrinsically resolves pose ambiguity, producing high-fidelity pose-aligned assets. Extensive experiments demonstrate that PAD achieves superior geometric alignment and image-to-3D correspondence compared to state-of-the-art methods. Additionally, PAD naturally extends to compositional 3D scene reconstruction via a simple union of independently generated objects, highlighting its robust ability to preserve precise spatial layouts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00345 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pose-Aware Diffusion for 3D Generation Zhou, Zihan Chen, Luxi Zhou, Jingzhi Wan, Yuhao Zhao, Min Fan, Baoyu Li, Chongxuan Computer Vision and Pattern Recognition Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rotate paradigms. To this end, we introduce Pose-Aware Diffusion (PAD), a novel end-to-end diffusion framework that synthesizes 3D geometry directly within the observation space. By unprojecting monocular depth into a partial point cloud and explicitly injecting it as a 3D geometric anchor, PAD abandons canonical assumptions to enforce rigorous spatial supervision. This native generation intrinsically resolves pose ambiguity, producing high-fidelity pose-aligned assets. Extensive experiments demonstrate that PAD achieves superior geometric alignment and image-to-3D correspondence compared to state-of-the-art methods. Additionally, PAD naturally extends to compositional 3D scene reconstruction via a simple union of independently generated objects, highlighting its robust ability to preserve precise spatial layouts. |
| title | Pose-Aware Diffusion for 3D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.00345 |