Papers
10
Total Citations
203
H-Index
5
About
Rudolf Mester is a leading researcher in computer vision and robotics, with a focus on autonomous navigation, 3D scene understanding, and sensor-based perception. His most influential work, "Free Space Computation Using Stochastic Occupancy Grids and Dynamic Programming" (2008), has garnered 149 citations and introduced a novel probabilistic framework for real-time environment mapping—a foundational contribution for intelligent automotive and robotic systems. Mester has also pioneered view-based robot localization using spherical harmonics, developing illumination-invariant descriptors that enable robust self-localization from omnidirectional cameras, as demonstrated in his 2007 and 2008 papers. His "Optical Rails" concept (2008) offers a view-based method for autonomous track following, while his more recent work on RGB-D mapping and tracking in Plenoxel radiance fields (2024) pushes the boundaries of neural rendering for dense 3D reconstruction. Additionally, Mester has contributed to ground texture-based localization with compact binary descriptors (2020) and semantically guided depth estimation via SDNet (2019). With a career spanning over two decades, his research has consistently advanced practical, real-world applications in autonomous driving and mobile robotics, making him a respected figure in the field.
Research Focus
Key Achievements
Top Papers
- 1Free Space Computation Using Stochastic Occupancy Grids and Dynamic Programming149 citations · 2008
- 2Ground Texture Based Localization Using Compact Binary Descriptors11 citations · 2020
- 3
- 4
- 5RGB-D Mapping and Tracking in a Plenoxel Radiance Field7 citations · 2024
- 6Pattern Recognition5 citations · 2011
- 7
- 8SDNet: Semantically Guided Depth Estimation Network3 citations · 2019
- 9
- 10Optical Rails3 citations · 2008