Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.26757 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918413498056704 |
|---|---|
| author | Cai, Boyang Liang, Qiwei Li, Jiawei Weng, Shihang Zhang, Zhaoxin Lin, Tao Chen, Xiangyu Zhang, Wenjie Mao, Jiaqi Xu, Weisheng Yang, Bin Liang, Jiaming Cai, Junhao Xu, Renjing |
| author_facet | Cai, Boyang Liang, Qiwei Li, Jiawei Weng, Shihang Zhang, Zhaoxin Lin, Tao Chen, Xiangyu Zhang, Wenjie Mao, Jiaqi Xu, Weisheng Yang, Bin Liang, Jiaming Cai, Junhao Xu, Renjing |
| contents | Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling behavior, and underlying mechanisms of multi-view data for robot manipulation. Controlled experiments show that, under both fixed and randomized backgrounds, multi-view demonstrations consistently improve single-view policy success and generalization. Performance varies non-monotonically with view coverage, revealing effective regimes rather than a simple "more is better" trend. Notably, multi-view data breaks the scaling limitation of single-view datasets and continues to raise performance ceilings after saturation. Mechanistic analysis shows that multi-view learning promotes manipulation-relevant visual representations, better aligns the action head with the learned feature distribution, and reduces overfitting. Motivated by the importance of multi-view data and its scarcity in large-scale robotic datasets, as well as the difficulty of collecting additional viewpoints in real world settings, we propose RoboNVS, a geometry-aware self-supervised framework that synthesizes novel-view videos from monocular inputs. The generated data consistently improves downstream policies in both simulation and real-world environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26757 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation? Cai, Boyang Liang, Qiwei Li, Jiawei Weng, Shihang Zhang, Zhaoxin Lin, Tao Chen, Xiangyu Zhang, Wenjie Mao, Jiaqi Xu, Weisheng Yang, Bin Liang, Jiaming Cai, Junhao Xu, Renjing Robotics Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling behavior, and underlying mechanisms of multi-view data for robot manipulation. Controlled experiments show that, under both fixed and randomized backgrounds, multi-view demonstrations consistently improve single-view policy success and generalization. Performance varies non-monotonically with view coverage, revealing effective regimes rather than a simple "more is better" trend. Notably, multi-view data breaks the scaling limitation of single-view datasets and continues to raise performance ceilings after saturation. Mechanistic analysis shows that multi-view learning promotes manipulation-relevant visual representations, better aligns the action head with the learned feature distribution, and reduces overfitting. Motivated by the importance of multi-view data and its scarcity in large-scale robotic datasets, as well as the difficulty of collecting additional viewpoints in real world settings, we propose RoboNVS, a geometry-aware self-supervised framework that synthesizes novel-view videos from monocular inputs. The generated data consistently improves downstream policies in both simulation and real-world environments. |
| title | Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation? |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.26757 |