Christos Sakaridis

About

Christos Sakaridis is a leading researcher at the forefront of robust perception for autonomous systems, with key contributions spanning semantic segmentation, sensor calibration, and neural scene representation. His work on condition-invariant semantic segmentation (2025, 12 citations) tackles the critical challenge of adapting deep networks to varying visual conditions—such as weather, lighting, and time of day—enabling reliable scene understanding for autonomous cars and robots in real-world environments. This research has garnered significant attention for its practical impact on domain adaptation. Sakaridis also pioneered novel sensor fusion techniques, including the L2E method (2023, 14 citations), which achieves 6-DoF extrinsic calibration between lidars and event cameras, a vital step for integrating neuromorphic vision into low-power, low-latency robotics. His work on Radar Fields (2024, 11 citations) introduces frequency-space neural scene representations for FMCW radar, advancing neural reconstruction for outdoor autonomous navigation. With a growing citation record and a focus on bridging simulation and reality, Sakaridis is shaping the future of robust, multi-modal perception for autonomous vehicles and intelligent robots.

Research Focus

Key Achievements

Top Papers

1. 1
   L2E: Lasers to Events for 6-DoF Extrinsic Calibration of Lidars and Event Cameras

   14 citations · 2023
2. 2
   Condition-Invariant Semantic Segmentation

   12 citations · 2025
3. 3
   Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar

   11 citations · 2024
4. 4
   Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding

   5 citations · 2024
5. 5
   Condition-Invariant Semantic Segmentation

   2 citations · 2023

Key Collaborators

Contact & Links