Papers
1
Total Citations
6
H-Index
1
About
Yonghu Zeng is a researcher advancing the field of computer vision, with a primary focus on self-supervised learning and efficient neural network architectures. His most notable contribution, "Self-supervised learning of monocular depth using quantized networks" (2021), addresses a critical challenge in autonomous systems: estimating 3D depth from single images without costly labeled data. By integrating network quantization—a technique that compresses models for faster, lower-power inference—Zeng’s work bridges the gap between high-accuracy depth perception and real-world deployment on resource-constrained devices like drones or mobile robots. This paper has garnered 6 citations, reflecting its relevance in the growing intersection of self-supervised learning and model efficiency. Zeng’s research is particularly impactful for applications in autonomous navigation, augmented reality, and robotics, where reliable depth estimation must operate under strict computational limits. His work stands out for its practical orientation, offering a pathway to deploy sophisticated vision models in edge environments. As the demand for efficient, label-free learning grows, Zeng’s contributions are poised to influence both academic research and industrial implementation, making him a rising voice in the drive toward scalable, self-supervised perception systems.
Research Focus
Key Achievements
Top Papers
- 1Self-supervised learning of monocular depth using quantized networks6 citations · 2021