Jiangyuan Liu
Papers
1
Total Citations
8
H-Index
1
About
Jiangyuan Liu is a leading researcher in computer vision and robotics, specializing in transparent object perception—a critical yet notoriously difficult problem for autonomous systems. Their work addresses the fundamental challenge of how machines can see and interact with transparent materials, which confound standard sensors due to their complex optical properties. Liu’s most influential paper, “Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion” (2025, 8 citations), introduces a novel framework that jointly tackles depth estimation and semantic segmentation using only monocular input. By iteratively fusing semantic and geometric cues, this approach achieves state-of-the-art accuracy without requiring specialized sensors or extra inputs, making it highly practical for real-world robotic applications. This work exemplifies Liu’s broader contribution: bridging the gap between perception and manipulation for challenging materials. With a growing citation record, Liu is establishing themselves as a key innovator in transparent object perception, laying the groundwork for more capable and reliable robotic systems in domains from manufacturing to healthcare.
Research Focus
Key Achievements
Top Papers
- 1