Yue-Jiang Dong

Papers

Total Citations

H-Index

About

Yue-Jiang Dong is a researcher advancing the frontiers of self-supervised depth estimation and robotic perception. His work primarily addresses the critical challenge of overcoming the static-scene assumption in self-supervised monocular depth estimation—a fundamental limitation that hinders performance in dynamic real-world environments. Dong’s most impactful contribution, "PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation" (2024, 7 citations), introduces a novel framework that significantly improves depth perception for applications in autonomous driving and robotics. Complementing this, his "MAL: Motion-Aware Loss with Temporal and Distillation Hints for Self-Supervised Depth Estimation" (2024, 4 citations) further refines multi-frame depth estimation by incorporating motion-aware mechanisms. Beyond depth estimation, Dong has also contributed to robotic middleware efficiency with "ROS-SF" (2022, 2 citations), which enhances transparency in ROS message-passing systems. His research demonstrates a clear trajectory from foundational system improvements to cutting-edge self-supervised learning techniques, establishing him as an emerging voice in making robotic perception more robust and adaptable to complex, dynamic scenarios.