3D Reconstruction Scientist: SfM, SLAM & Dense Geometry

SpAItial AI; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

SpAItial AI in Greater London seeks a Research Scientist to advance 3D reconstruction methods that recover camera poses and geometry from real-world imagery. You will work with both classical multi-view geometry and state-of-the-art learned reconstructors, focusing on robustness and accuracy across diverse data.

The role demands a PhD in computer vision, deep knowledge of multi-view geometry, and hands-on experience with SfM/SLAM systems and deep learning frameworks.

Qualifications

• PhD in computer vision with a focus on 3D reconstruction.
• Deep understanding of multi-view geometry and camera models.
• Experience with SOTA deep reconstructors and deep MVS.
• Hands-on experience with SfM/SLAM systems (COLMAP, ORB-SLAM) and nonlinear least-squares solvers (Ceres).

Responsibilities

• Design camera pose estimators and 3D reconstructors.
• Build robust SfM and camera tracking pipelines for a variety of input imaging sensors.
• Develop bundle adjusters and nonlinear optimizers, including non-perspective camera formulations.
• Integrate and extend SOTA feed-forward reconstructors (VGGT, DA3, Pi3).
• Advance deep multi-view stereo, learned matching, and monocular depth methods for dense geometry.
• Build evaluation metrics for pose accuracy and reconstruction quality, and drive improvements against public & internal benchmarks.
• Scale reconstruction methods to large, diverse real-world datasets while keeping them reliable and efficient.
• Collaborate with researchers to bring reconstruction advances into production systems.

Skills

Python

PyTorch

Multi-view geometry

COLMAP

ORB-SLAM

Ceres Solver

Deep learning

Education

PhD in Computer Vision (3D reconstruction)

Tools

COLMAP

ORB-SLAM

Ceres

Job description

SpAItial AI in Greater London seeks a Research Scientist to advance 3D reconstruction methods that recover camera poses and geometry from real-world imagery. You will work with both classical multi-view geometry and state-of-the-art learned reconstructors, focusing on robustness and accuracy across diverse data.

The role demands a PhD in computer vision, deep knowledge of multi-view geometry, and hands-on experience with SfM/SLAM systems and deep learning frameworks.