Abstract
Large-scale manipulation demonstrations are essential for learning robust visuomotor policies, yet real-world data collection is expensive and difficult to scale. Simulation offers a promising alternative, but physical and visual discrepancies can limit the transferability of synthetic data, particularly for manipulation with soft grippers. We present PhyVisGen, a physically and visually high-fidelity framework for scalable robotic manipulation data generation. On the physical side, PhyVisGen introduces an arm-gripper coupling method based on the Incremental Potential Contact (IPC), enabling high-fidelity soft contact throughout complete manipulation trajectories. On the visual side, it combines real-scene reconstruction with real-time path tracing to generate visually realistic observations while preserving captured scene appearance. Quantitative evaluations demonstrate the physical and visual fidelity of PhyVisGen. Policies trained exclusively on synthetic manipulation demonstrations achieve 65-95% success across five real-robot tasks, without real-robot demonstration data or policy fine-tuning.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zheng, Y., Feng, Q., Wu, Y., Yang, B., Zhou, Y., Hu, B., Huang, K., Yang, G., & Wang, H. (2026). PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation. https://omanscience.com/en/articles/phyvisgen-physically-and-visually-high-fidelity-robotic-manipulation-data-generation
MLA 9
Zheng, Yu, et al. "PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation." https://omanscience.com/en/articles/phyvisgen-physically-and-visually-high-fidelity-robotic-manipulation-data-generation.
Chicago (author–date)
Zheng, Yu, Qiyu Feng, Yixin Wu, Baoquan Yang, Yixuan Zhou, Bingyang Hu, Kemeng Huang, Guansheng Yang, and Hesheng Wang. 2026. "PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation." https://omanscience.com/en/articles/phyvisgen-physically-and-visually-high-fidelity-robotic-manipulation-data-generation.
Harvard
Zheng, Y., Feng, Q., Wu, Y., Yang, B., Zhou, Y., Hu, B., Huang, K., Yang, G. and Wang, H. (2026) 'PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation', Available at: https://omanscience.com/en/articles/phyvisgen-physically-and-visually-high-fidelity-robotic-manipulation-data-generation.
Vancouver
Zheng Y, Feng Q, Wu Y, Yang B, Zhou Y, Hu B, et al. PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation. https://omanscience.com/en/articles/phyvisgen-physically-and-visually-high-fidelity-robotic-manipulation-data-generation
IEEE
Y. Zheng, Q. Feng, Y. Wu, B. Yang, Y. Zhou, B. Hu, K. Huang, G. Yang, and H. Wang, "PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation," https://omanscience.com/en/articles/phyvisgen-physically-and-visually-high-fidelity-robotic-manipulation-data-generation.