Mikhail Li
Papers
1
Total Citations
3
H-Index
1
About
Mikhail Li’s research lies at the intersection of computer vision and robotics, with a particular focus on three-dimensional shape reconstruction. His most cited work, “Deep Neural Network Based Shape Reconstruction for Application in Robotics” (2019), addresses a fundamental challenge in the field: recovering 3D shape from 2D images using passive optical techniques. Li specifically advanced the Shape From Focus (SFF) method, which extracts depth information from a stack of images captured at different focus levels. By integrating deep neural networks into this classical framework, he demonstrated how learned representations can improve the accuracy and robustness of shape recovery—a critical capability for robotic manipulation, navigation, and object classification. While his citation count is still growing, Li’s contribution is notable for bridging traditional optics-based approaches with modern deep learning, offering a practical pathway for deploying 3D perception in resource-constrained robotic systems. His work serves as a stepping stone for researchers seeking to combine classical computer vision algorithms with data-driven models, and it highlights the ongoing importance of shape reconstruction as a core enabler for autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1