Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.22629 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914352399908864 |
|---|---|
| author | Jiang, Zeyu Li, Sihang Tan, Siqi Xu, Chenyang Zhang, Juexiao Galway-Witham, Julia Wang, Xue Williams, Scott A. Iovita, Radu Feng, Chen Zhang, Jing |
| author_facet | Jiang, Zeyu Li, Sihang Tan, Siqi Xu, Chenyang Zhang, Juexiao Galway-Witham, Julia Wang, Xue Williams, Scott A. Iovita, Radu Feng, Chen Zhang, Jing |
| contents | Most existing 3D assembly methods treat the problem as pure pose estimation, rearranging observed parts via rigid transformations. In contrast, human assembly naturally couples structural reasoning with holistic shape inference. Inspired by this intuition, we reformulate 3D assembly as a joint problem of assembly and generation. We show that these two processes are mutually reinforcing: assembly provides part-level structural priors for generation, while generation injects holistic shape context that resolves ambiguities in assembly. Unlike prior methods that cannot synthesize missing geometry, we propose CRAG, which simultaneously generates plausible complete shapes and predicts poses for input parts. Extensive experiments demonstrate state-of-the-art performance across in-the-wild objects with diverse geometries, varying part counts, and missing pieces. Our code and models will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22629 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CRAG: Can 3D Generative Models Help 3D Assembly? Jiang, Zeyu Li, Sihang Tan, Siqi Xu, Chenyang Zhang, Juexiao Galway-Witham, Julia Wang, Xue Williams, Scott A. Iovita, Radu Feng, Chen Zhang, Jing Computer Vision and Pattern Recognition Most existing 3D assembly methods treat the problem as pure pose estimation, rearranging observed parts via rigid transformations. In contrast, human assembly naturally couples structural reasoning with holistic shape inference. Inspired by this intuition, we reformulate 3D assembly as a joint problem of assembly and generation. We show that these two processes are mutually reinforcing: assembly provides part-level structural priors for generation, while generation injects holistic shape context that resolves ambiguities in assembly. Unlike prior methods that cannot synthesize missing geometry, we propose CRAG, which simultaneously generates plausible complete shapes and predicts poses for input parts. Extensive experiments demonstrate state-of-the-art performance across in-the-wild objects with diverse geometries, varying part counts, and missing pieces. Our code and models will be released. |
| title | CRAG: Can 3D Generative Models Help 3D Assembly? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.22629 |