Jinding Liu
Papers
1
Total Citations
1
H-Index
1
About
Jinding Liu is a researcher specializing in computer vision and deep learning, with a particular focus on monocular depth estimation and efficient neural network architectures. His most notable contribution is the development of LightNet, a lightweight monocular depth estimation framework that introduces high-level guidance and channel re-alignment optimization techniques. This work, presented at ChinaMM 2025, addresses the critical challenge of balancing accuracy and computational efficiency in depth perception tasks, making it suitable for real-time applications on resource-constrained devices. While his citation count is currently modest, with one citation for this flagship paper, Liu's research demonstrates significant potential for impact in autonomous driving, robotics, and augmented reality. His approach to channel re-alignment optimization represents an innovative method for improving feature representation without substantially increasing model complexity. As an emerging researcher, Jinding Liu is establishing himself in the competitive field of efficient deep learning, with his work on LightNet laying a foundation for future advancements in lightweight computer vision systems that can operate effectively in real-world, low-power environments.
Research Focus
Key Achievements
Top Papers
- 1