Fringe projection profilometry (FPP) is a high-precision structured-light sensing technique for 3D surface reconstruction, yet its practical deployment is often constrained by complex calibration procedures, sensitivity to environmental conditions, and the high cost of physical experimentation. At the same time, robotics research increasingly relies on simulation platforms such as NVIDIA Isaac Sim for scalable development and validation, but accurate virtual representations of optical metrology sensors such as FPP are not currently available. In this work, we present VIRTUS-FPP, the first end-to-end virtual sensor modeling framework for fringe projection profilometry implemented in NVIDIA Isaac Sim, enabling physically grounded simulation of the complete FPP pipeline, including structured light projection, image formation, calibration, and 3D reconstruction, without dependence on pre-calibrated physical systems. The framework leverages an inverse camera model for projector representation, ensuring geometric and photometric fidelity consistent with structured-light principles. By bridging optical metrology and robotics simulation, VIRTUS-FPP enables high-fidelity synthetic data generation, systematic evaluation of sensing pipelines, and digital twin replication of real-world FPP systems. Experimental results demonstrate sub-millimeter reconstruction accuracy and strong correspondence between simulated and physical measurements, highlighting the framework's effectiveness and its potential to advance perception-driven robotics, simulation-to-reality transfer, and scalable optical sensor design.

翻译：条纹投影轮廓术（FPP）是一种用于三维表面重建的高精度结构光传感技术，但其实际部署常受限于复杂的标定流程、对环境条件的敏感性以及物理实验的高昂成本。与此同时，机器人研究日益依赖诸如NVIDIA Isaac Sim等仿真平台进行可扩展的开发与验证，然而目前尚缺乏如FPP这类光学计量传感器的精确虚拟表征。本文提出VIRTUS-FPP——首个在NVIDIA Isaac Sim中实现的端到端条纹投影轮廓术虚拟传感器建模框架，无需依赖预标定的物理系统即可实现完整FPP流程（包括结构光投影、图像形成、标定及三维重建）的物理真实性仿真。该框架采用逆相机模型进行投影仪表征，确保符合结构光原理的几何与光度保真度。通过桥接光学计量学与机器人仿真，VIRTUS-FPP能够实现高保真合成数据生成、传感流程的系统性评估以及真实FPP系统的数字孪生复制。实验结果表明，该框架达到了亚毫米级重建精度，且仿真结果与物理测量值高度一致，充分验证了其有效性及其在推动感知驱动型机器人、仿真到现实迁移以及可扩展光学传感器设计方面的潜力。