Role Overview
PhD research intern in 3D computer vision at Helsing's Spatial Intelligence Team. Focus on spatial perception, localisation, SLAM/VIO, and 3D reconstruction. Collaborate with a distributed European team to prototype and evaluate novel approaches under real-world constraints.
Responsibilities
- Survey and critically assess state-of-the-art research in geometric computer vision, feature matching, place recognition, and SLAM/VIO.
- Conceptualize how emerging techniques apply to localisation and reconstruction pipelines; discuss trade-offs.
- Evaluate algorithmic strengths and weaknesses for mission-critical use cases.
- Prototype and benchmark promising concepts against real-world conditions (illumination, viewpoint, season, sensor modality changes).
- Summarize findings in clear written reports and present to the team.
Requirements
- Currently pursuing a PhD in computer vision, machine learning, robotics, or closely related field.
- Demonstrated theoretical and practical experience in localisation, scene matching, SLAM, visual odometry, or 3D reconstruction.
- Proficient in Python and experienced with AI frameworks such as PyTorch.
- Experience with Rust or C++.
- Able to work reliably and independently; enjoy turning research ideas into working code.
Nice to Have
- Published paper at top-tier conference (CVPR, ICCV, ECCV, NeurIPS, ICLR, ICRA, IROS).
- Experience with learned feature matching, place recognition, VIO, or neural 3D representations (NeRF, Gaussian Splatting).
- Experience with model compression or domain adaptation for compute-constrained/edge deployment.
- Experience with simulators, emulators, or synthetic data generation for geometry/localisation tasks.