Paper Detail
Songen Gu, Yuhang Zheng, Weize Li, Yupeng Zheng, Yating Feng, Xiang Li, Yilun Chen, Pengfei Li, Wenchao Ding
Recently, end-to-end robotic manipulation models have gained significant attention for their generalizability and scalability. However, they often suffer from limited robustness to camera viewpoint changes when training with a fixed camera. In this paper, we propose VistaBot, a novel framework that integrates feed-forward geometric models with video diffusion models to achieve view-robust closed-loop manipulation without requiring camera calibration at test time. Our approach consists of three key components: 4D geometry estimation, view synthesis latent extraction, and latent action learning. VistaBot is integrated into both action-chunking (ACT) and diffusion-based ($π_0$) policies and evaluated across simulation and real-world tasks. We further introduce the View Generalization Score (VGS) as a new metric for comprehensive evaluation of cross-view generalization. Results show that VistaBot improves VGS by 2.79$\times$ and 2.63$\times$ over ACT and $π_0$, respectively, while also achieving high-quality novel view synthesis. Our contributions include a geometry-aware synthesis model, a latent action planner, a new benchmark metric, and extensive validation across diverse environments. The code and models will be made publicly available.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{gu2026vistabot,
title = {VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis},
author = {Songen Gu and Yuhang Zheng and Weize Li and Yupeng Zheng and Yating Feng and Xiang Li and Yilun Chen and Pengfei Li and Wenchao Ding},
year = {2026},
abstract = {Recently, end-to-end robotic manipulation models have gained significant attention for their generalizability and scalability. However, they often suffer from limited robustness to camera viewpoint changes when training with a fixed camera. In this paper, we propose VistaBot, a novel framework that integrates feed-forward geometric models with video diffusion models to achieve view-robust closed-loop manipulation without requiring camera calibration at test time. Our approach consists of three k},
url = {https://arxiv.org/abs/2604.21914},
keywords = {cs.RO},
eprint = {2604.21914},
archiveprefix = {arXiv},
}
{}