I work on 3D vision and robotics data infrastructure at NVIDIA Isaac, with interests in scalable camera geometry, Structure-from-Motion, neural reconstruction, and spatial data pipelines for embodied AI systems.
- CUDA-accelerated Structure-from-Motion and camera-pose estimation
- Robotics data infrastructure for reconstruction and simulation
- Neural reconstruction and real-world-to-simulation pipelines
- 3D vision, visual localization, and mapping systems
- pyCuSFM — CUDA-accelerated Structure-from-Motion framework for Python
- Isaac Neural Reconstruction — NVIDIA Isaac reconstruction workflow
- Personal website — profile, background, and selected projects
My PhD research at Shanghai Jiao Tong University focused on autonomous-driving perception and localization, including fisheye cameras, visual SLAM, semantic localization, and simulation-based learning.
- Website: jingruiyu.github.io
- GitHub: github.com/JingruiYu
- LinkedIn: Jingrui Yu
- ORCID: 0000-0001-5544-6155