# WARPED: Synthesizing wrist-view observations from first-person human demonstrations to train robot visuomotor policies

- Source: arXiv cs.RO
- Published: 2026-10-22T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/dcnv5hwpwyskzlnsq94pia2uw
- Original: https://arxiv.org/abs/2604.10809

## Summary

WARPED is a framework that synthesizes realistic wrist-view observations and actions from human demonstration videos, enabling visuomotor policy training with only monocular RGB data. The system uses vision foundation models to initialize the interactive scene, employs a hand-object interaction pipeline to track the hand and manipulated object and retarget trajectories to a robotic end-effector, and finally uses Gaussian Splatting to synthesize photorealistic wrist-view observations for directly training policies.