Philipp Heise

Information Technology University, Technical University of Munich

Papers

Total Citations

H-Index

About

Philipp Heise is a leading researcher in computer vision and robotics, whose work focuses on real-time dense 3D reconstruction and visual odometry. His most influential contribution is the development of efficient, compositional approaches for direct visual odometry using RGB-D sensors, as detailed in his highly cited 2013 paper (49 citations). This work systematically evaluated photometric error minimization techniques for frame-to-frame motion estimation, demonstrating exceptional accuracy and robustness for real-time applications. Heise further advanced the field with his 2015 work on fast dense stereo correspondences using binary locality sensitive hashing (18 citations), addressing the critical challenge of handling high-resolution images in real-time—a bottleneck for many state-of-the-art algorithms. His research has significantly impacted autonomous navigation and 3D mapping, enabling practical, computationally efficient solutions for robotic systems. By bridging the gap between theoretical accuracy and real-world performance constraints, Heise’s contributions continue to influence modern visual SLAM and stereo vision systems, making his work essential reading for researchers developing robust, real-time perception algorithms.