Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.16133 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908893111648256 |
|---|---|
| author | Meng, Xiaoxu Chen, Zhongmin Yang, Bo Chen, Weikai Liu, Weixiao Gao, Lin |
| author_facet | Meng, Xiaoxu Chen, Zhongmin Yang, Bo Chen, Weikai Liu, Weixiao Gao, Lin |
| contents | Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16133 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives Meng, Xiaoxu Chen, Zhongmin Yang, Bo Chen, Weikai Liu, Weixiao Gao, Lin Computer Vision and Pattern Recognition Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives. |
| title | DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16133 |