AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915858476957696 |
|---|---|
| author | Qiao, Xiaozhen Wang, Wenjia Zhao, Zhiyuan Sun, Jiacheng Luo, Ping Zhang, Hongyuan Li, Xuelong |
| author_facet | Qiao, Xiaozhen Wang, Wenjia Zhao, Zhiyuan Sun, Jiacheng Luo, Ping Zhang, Hongyuan Li, Xuelong |
| contents | Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and applicability in diverse real-world scenarios. In this work, we present AHAP (Reconstructing Arbitrary Humans from Arbitrary Perspectives), a feed-forward framework for reconstructing arbitrary humans from arbitrary camera perspectives without requiring camera calibration. Our core lies in the effective fusion of multi-view geometry to assist human association, reconstruction and localization. Specifically, we use a Cross-View Identity Association module through learnable person queries and soft assignment, supervised by contrastive learning to resolve cross-view human identity association. A Human Head fuses cross-view features and scene context for SMPL prediction, guided by cross-view reprojection losses to enforce body pose consistency. Additionally, multi-view geometry eliminates the depth ambiguity inherent in monocular methods, providing more precise 3D human localization through multi-view triangulation. Experiments on EgoHumans and EgoExo4D demonstrate that AHAP achieves competitive performance on both world-space human reconstruction and camera pose estimation, while being 180$\times$ faster than optimization-based approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23951 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors Qiao, Xiaozhen Wang, Wenjia Zhao, Zhiyuan Sun, Jiacheng Luo, Ping Zhang, Hongyuan Li, Xuelong Computer Vision and Pattern Recognition Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and applicability in diverse real-world scenarios. In this work, we present AHAP (Reconstructing Arbitrary Humans from Arbitrary Perspectives), a feed-forward framework for reconstructing arbitrary humans from arbitrary camera perspectives without requiring camera calibration. Our core lies in the effective fusion of multi-view geometry to assist human association, reconstruction and localization. Specifically, we use a Cross-View Identity Association module through learnable person queries and soft assignment, supervised by contrastive learning to resolve cross-view human identity association. A Human Head fuses cross-view features and scene context for SMPL prediction, guided by cross-view reprojection losses to enforce body pose consistency. Additionally, multi-view geometry eliminates the depth ambiguity inherent in monocular methods, providing more precise 3D human localization through multi-view triangulation. Experiments on EgoHumans and EgoExo4D demonstrate that AHAP achieves competitive performance on both world-space human reconstruction and camera pose estimation, while being 180$\times$ faster than optimization-based approaches. |
| title | AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23951 |