Mykhailo Shvets

University of North Carolina at Chapel Hill

Papers

Total Citations

H-Index

About

Mykhailo Shvets is a researcher advancing the frontiers of computer vision and robotics, with key contributions in instance detection, depth prediction, and semantic segmentation. His work on "Target Driven Instance Detection" (2018, 17 citations) addresses a critical gap in object recognition: while general object detectors excel at broad categories, few systems are optimized for recognizing specific instances—a challenge essential for applications like household robotics. This paper laid groundwork for more precise, task-oriented detection systems. More recently, Shvets has tackled the limitations of single-view perception in "Joint Depth Prediction and Semantic Segmentation with Multi-View SAM" (2024, 10 citations). By leveraging multiple views—common in robotics—his approach overcomes the inherent constraints of monocular predictions, offering a practical middle ground between single-image methods and computationally heavy full 3D pipelines. This work highlights his focus on real-world deployability, balancing accuracy with efficiency. With a growing citation footprint, Shvets’ research is shaping how machines perceive and interact with their environments, making him a notable voice in the intersection of computer vision and autonomous systems.