Sabina Umirzakova
Papers
2
Total Citations
14
H-Index
2
About
Sabina Umirzakova is a rising researcher in computer vision, whose work is rapidly gaining traction for its innovative approach to monocular depth estimation (MDE)—a fundamental challenge with applications spanning autonomous driving, robotics, and augmented reality. Her most cited papers, including "Iterative contextual and adaptive strategies for enhanced monocular depth estimation" (8 citations) and "Breaking New Ground in Monocular Depth Estimation with Dynamic Iterative Refinement and Scale Consistency" (6 citations), introduce dynamic, iterative refinement frameworks that tackle the persistent problem of scale ambiguity in dynamic scenes. By integrating contextual and adaptive strategies, Umirzakova’s methods achieve unprecedented accuracy in predicting depth from single images, directly addressing the limitations of traditional approaches when faced with moving objects. Her work not only advances the theoretical underpinnings of MDE but also offers practical solutions for real-world deployment in safety-critical systems. With her publications already garnering attention in 2025, Umirzakova is establishing herself as a key contributor to next-generation depth perception technologies, promising to enhance the reliability and robustness of visual AI systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2