Torsten Sattler

Torsten Sattler leads spatial AI research, combining 3D computer vision and machine learning for robust visual localization.

Professional profile

Torsten Sattler is a senior researcher at the Czech Institute of Informatics, Robotics and Cybernetics (CIIRC) at the Czech Technical University in Prague, where he leads the Spatial Intelligence group. His work sits at the intersection of 3D computer vision and machine learning, with a clear goal in mind: making technologies like 3D reconstruction and visual localization more robust and reliable. He is particularly interested in how a deeper understanding of scenes can strengthen 3D vision systems, while also using 3D vision techniques to improve how machine‑learning models are trained.

His research interests span a wide range of topics, including large‑scale and real‑time image‑based localization, 3D mapping and reconstruction, neural scene representations and neural rendering, learning local visual features, and camera calibration. These methods are applied to real‑world challenges such as self‑driving cars, autonomous robots, and augmented and virtual reality systems.

More recently, Sattler’s work has focused on making localization and mapping algorithms “smarter” by integrating higher‑level scene understanding into the process. The goal is to build systems that are not only more accurate, but also more reliable when deployed in complex, real‑world environments.