Qingyang Xu

Papers

Total Citations

H-Index

About

Qingyang Xu is an emerging researcher whose work sits at the intersection of computer vision, deep learning, and autonomous systems. Their most recognized contribution to date is a 2025 paper on deep learning-based visual Simultaneous Localization and Mapping (SLAM) for indoor dynamic scenes — a technically demanding problem that challenges conventional SLAM systems, which typically assume static environments. By leveraging deep learning architectures, Xu's approach advances the robustness and accuracy of visual SLAM in real-world indoor settings where moving objects — such as people and furniture — can confound traditional geometric methods. This work addresses a critical bottleneck for applications in robotics, augmented reality, and autonomous navigation. Although the paper is in the early stages of accumulating citations, having gathered 4 citations shortly after its 2025 publication, the timeliness and practical relevance of the research suggest strong potential for broader impact. As interest in embodied AI and intelligent robotic systems continues to accelerate, Xu's focus on dynamic scene understanding positions them as a promising voice in next-generation perception and localization research.