Iaroslav Melekhov
Papers
1
Total Citations
23
H-Index
1
About
Iaroslav Melekhov is a leading researcher in computer vision and robotics, with a primary focus on visual localization—the task of determining a camera’s position and orientation from a single image. His most influential work, “HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer” (2024), has already garnered 23 citations, underscoring its timely impact. Melekhov’s major contribution lies in advancing deep neural network approaches for single-image RGB localization, moving beyond traditional feature-based methods that match local descriptors to pre-built 3D models. By integrating hierarchical scene coordinate classification with transformer architectures, he has significantly improved the accuracy and robustness of localization in challenging environments. His research bridges the gap between classical geometric techniques and modern learning-based paradigms, offering scalable solutions for augmented reality, autonomous navigation, and drone guidance. Melekhov’s work is widely recognized for its practical relevance, and he continues to shape the field through innovative architectures that push the boundaries of what is achievable with end-to-end learned localization.
Research Focus
Key Achievements
Top Papers
- 1