# Beyond Viewpoint Generalization: What Multi-View Demonstrations Offer and How to Synthesize Them for Robot Manipulation?

arXiv: https://arxiv.org/abs/2603.26757 · HTML: https://mlsanity.com/paper/2603.26757/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2026.

## Built on by (most cited first, 3 of 3)

- [From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model](https://mlsanity.com/paper/2607.05396/) (2026)
- [Selective Cross-View Consistency for World Action Models: Held-Out Viewpoint Robustness Without Test-Time Camera Information](https://mlsanity.com/paper/2608.21402/) (2026)
- [UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling](https://mlsanity.com/paper/2606.21501/) (2026)

## Abstract (arXiv)

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.