Fang‐Lue Zhang
Papers
3
Total Citations
12
H-Index
2
About
Fang-Lue Zhang is a leading researcher in computer vision and robotics, with a core focus on self-supervised depth estimation and 3D scene understanding. His major contributions lie in advancing monocular depth perception under challenging real-world conditions, particularly by addressing the limitations of static-scene assumptions in dynamic environments. His 2024 paper, "PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation," has already garnered 7 citations, showcasing its impact on autonomous driving and robotics by enabling robust depth estimation in dynamic scenes. Zhang further refined this domain with "MAL: Motion-Aware Loss with Temporal and Distillation Hints for Self-Supervised Depth Estimation" (4 citations), which introduces innovative loss functions to handle motion-induced ambiguities. In 2025, he expanded into robotic manipulation with "Occlusion Avoidance for Robotic Manipulators Using Rigid Gaussian Splatting" (1 citation), a lightweight learning-based solution that overcomes line-of-sight occlusions in automated environments. His work consistently bridges theoretical advances with practical robotic applications, earning recognition for its efficiency and real-world deployability. Zhang’s research is essential reading for students and engineers working on autonomous systems, offering scalable solutions for depth perception and occlusion handling in dynamic, unlabeled environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3