Yunxuan Li
Papers
2
Total Citations
9
H-Index
2
About
Yunxuan Li’s research lies at the intersection of robotics, computer vision, and sensor perception, with a focus on enabling autonomous systems to perceive and interact with their environments more reliably. In his early work, Li tackled a classic challenge in RoboCup robotics: real-time ball recognition under dynamic lighting and motion. His 2016 paper introduced an efficient, look-up table-based method for arbitrary colored ball detection on humanoid soccer robots, significantly reducing false positives and computational overhead—a practical contribution that remains cited in robotics vision pipelines. More recently, Li has advanced the field of depth sensing. His 2022 work on unsupervised depth completion and denoising for RGB-D sensors addresses two persistent problems in consumer-grade depth cameras: missing data and sensor noise. By learning to fill gaps and smooth depth maps without requiring ground-truth labels, Li’s method offers a scalable solution for robotic manipulation, navigation, and 3D scene understanding. Though still early in his career, his work has already attracted citations from researchers in autonomous driving, service robotics, and augmented reality. Li’s trajectory—from real-time vision on resource-constrained robots to self-supervised depth enhancement—demonstrates a consistent drive to make perception algorithms both robust and practical for real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2Unsupervised Depth Completion and Denoising for RGB-D Sensors3 citations · 2022