Xujun Wei

Papers

Total Citations

H-Index

About

Xujun Wei is a researcher at the forefront of multi-modal perception and scene understanding, with a particular focus on advancing depth estimation through innovative fusion techniques. Their most influential work, "Multi-modal Scene Global Fusion Framework for Enhanced Depth Estimation" (2025), introduces a novel architecture that integrates disparate sensory data—such as RGB images and depth maps—to achieve more robust and accurate 3D scene reconstruction. This framework addresses critical challenges in autonomous navigation and augmented reality by leveraging global contextual cues, enabling systems to perceive depth in complex, dynamic environments. While early in its citation impact, this contribution has already garnered attention for its potential to redefine sensor fusion paradigms. Wei’s research bridges the gap between theoretical computer vision and practical deployment, emphasizing efficiency and scalability. Their work is particularly notable for its emphasis on global fusion over local feature aggregation, a departure that promises to enhance real-time performance in resource-constrained settings. As a rising voice in multi-modal learning, Xujun Wei continues to shape how machines interpret the physical world, with implications for robotics, autonomous driving, and immersive technologies.