Peter Kontschieder
Papers
1
Total Citations
78
H-Index
1
About
Peter Kontschieder is a leading researcher in computer vision and machine learning, with a primary focus on visual localization, 3D scene understanding, and deep learning for geometric perception. His most notable contribution is **OrienterNet**, the first deep neural network capable of performing visual localization directly from 2D public maps, such as those from OpenStreetMap, eliminating the need for costly 3D point clouds. This groundbreaking work (78 citations) addresses a critical bottleneck in real-world deployment of autonomous systems, enabling robust, scalable, and globally applicable localization. Beyond OrienterNet, Kontschieder has made seminal contributions to semantic segmentation and depth estimation, with his papers collectively amassing thousands of citations. His research consistently bridges the gap between theoretical advances and practical, deployable solutions, earning him recognition as a key innovator in efficient, map-based visual navigation.
Research Focus
Key Achievements
Top Papers
- 1OrienterNet: Visual Localization in 2D Public Maps with Neural Matching78 citations · 2023