Dzmitry Tsishkou

Papers

Total Citations

H-Index

About

Dzmitry Tsishkou is a leading researcher in computer vision and robotics, with a primary focus on visual localization and autonomous navigation. His work bridges the gap between deep learning and real-world deployment, particularly for autonomous vehicles. Tsishkou’s major contribution is the development of uncertainty-aware pose regression, exemplified by his highly cited work on **CoordiNet** (2022, 41 citations), which directly predicts 3D camera pose from a single image while quantifying prediction confidence—a critical feature for safe autonomous driving. He further advanced the field with **LENS** (2021, 17 citations), where he pioneered the use of Neural Radiance Fields (NeRF) for synthetic data augmentation to improve robot relocalization accuracy. Earlier in his career, Tsishkou addressed foundational challenges in **monocular vision obstacle detection** (2008, 5 citations), proposing a sensor-efficient navigation solution for unknown environments. His research is notable for its practical impact, enabling reliable, cost-effective localization systems that reduce reliance on expensive multi-sensor setups. Tsishkou’s work continues to influence the development of robust, uncertainty-aware perception systems for next-generation autonomous vehicles.