DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916832056705024 |
|---|---|
| author | Kim, Young Hun Kim, Seungyeon Lee, Yonghyeon Park, Frank Chongwoo |
| author_facet | Kim, Young Hun Kim, Seungyeon Lee, Yonghyeon Park, Frank Chongwoo |
| contents | Partial-view 3D recognition -- reconstructing 3D geometry and identifying object instances from a few sparse RGB images -- is an exceptionally challenging yet practically essential task, particularly in cluttered, occluded real-world settings where full-view or reliable depth data are often unavailable. Existing methods, whether based on strong symmetry priors or supervised learning on curated datasets, fail to generalize to such scenarios. In this work, we introduce DreamGrasp, a framework that leverages the imagination capability of large-scale pre-trained image generative models to infer the unobserved parts of a scene. By combining coarse 3D reconstruction, instance segmentation via contrastive learning, and text-guided instance-wise refinement, DreamGrasp circumvents limitations of prior methods and enables robust 3D reconstruction in complex, multi-object environments. Our experiments show that DreamGrasp not only recovers accurate object geometry but also supports downstream tasks like sequential decluttering and target retrieval with high success rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05627 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation Kim, Young Hun Kim, Seungyeon Lee, Yonghyeon Park, Frank Chongwoo Robotics Computer Vision and Pattern Recognition Partial-view 3D recognition -- reconstructing 3D geometry and identifying object instances from a few sparse RGB images -- is an exceptionally challenging yet practically essential task, particularly in cluttered, occluded real-world settings where full-view or reliable depth data are often unavailable. Existing methods, whether based on strong symmetry priors or supervised learning on curated datasets, fail to generalize to such scenarios. In this work, we introduce DreamGrasp, a framework that leverages the imagination capability of large-scale pre-trained image generative models to infer the unobserved parts of a scene. By combining coarse 3D reconstruction, instance segmentation via contrastive learning, and text-guided instance-wise refinement, DreamGrasp circumvents limitations of prior methods and enables robust 3D reconstruction in complex, multi-object environments. Our experiments show that DreamGrasp not only recovers accurate object geometry but also supports downstream tasks like sequential decluttering and target retrieval with high success rates. |
| title | DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.05627 |