Andreas Geiger

About

Andreas Geiger is a pioneering computer vision and robotics researcher whose work has fundamentally shaped the field of autonomous driving and 3D scene understanding. Best known as the creator of the **KITTI benchmark suite**, his 2012 paper introducing this dataset has accumulated an extraordinary 14,348 citations, making it one of the most influential works in computer vision history. The companion KITTI dataset paper (2013) has garnered an additional 9,681 citations, cementing his reputation as the architect of the standard evaluation framework against which autonomous driving perception systems are measured worldwide. Geiger's research spans dense 3D reconstruction, visual SLAM, sensor calibration, and omnidirectional image understanding. His StereoScan system demonstrated real-time dense reconstruction from stereo video, while his single-shot camera-LiDAR calibration method addressed a persistent bottleneck in robotic system setup. More recently, KITTI-360 (2022, 630 citations) extended his benchmark legacy toward holistic urban scene understanding across 2D and 3D modalities, bridging computer vision, graphics, and robotics communities. His contributions to fisheye and spherical imaging further demonstrate a commitment to perception systems that mirror real-world sensor deployments. Collectively, Geiger's work has provided the essential infrastructure upon which a generation of autonomous driving research has been built.

Research Focus

Key Achievements

Top Papers

1. 1
   Are we ready for autonomous driving? The KITTI vision benchmark suite

   14,348 citations · 2012
2. 2
   Vision meets robotics: The KITTI dataset

   9,681 citations · 2013
3. 3
   StereoScan: Dense 3d reconstruction in real-time

   1,102 citations · 2011
4. 4
   Automatic camera and range sensor calibration using a single shot

   640 citations · 2012
5. 5
   KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

   630 citations · 2022
6. 6
   SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images

   360 citations · 2018
7. 7
   Visual SLAM for autonomous ground vehicles

   159 citations · 2011
8. 8
   Robust Dense Mapping for Large-Scale Dynamic Environments

   147 citations · 2018
9. 9
   A generative model for 3D urban scene understanding from movable platforms

   57 citations · 2011
10. 10
    Direct visual odometry for a fisheye-stereo camera

    49 citations · 2017

Key Collaborators

Contact & Links