Thomas Holzmann

Papers

Total Citations

H-Index

About

Thomas Holzmann is a computer vision researcher whose primary contributions lie in visual odometry and 3D reconstruction, particularly for challenging, poorly textured environments. His most cited work, "Direct Stereo Visual Odometry based on Lines" (2016), introduces a novel approach that leverages line features—rather than traditional point features—to estimate camera motion. To make this feasible, Holzmann developed a fast, IMU-assisted line segment detector and matcher that identifies vertical lines, using the patches around them for direct pose estimation. This work is especially impactful for robotics and autonomous navigation in indoor or industrial settings where texture is sparse. With 9 citations, this paper has influenced subsequent research in direct and semi-direct visual odometry methods. Holzmann’s contributions are notable for bridging the gap between feature-based and direct methods, offering a robust alternative for real-world deployment. His work demonstrates a clear focus on practical, real-time performance, making him a key figure in advancing visual SLAM for low-texture scenarios.