Xiaodong Mu

Papers

Total Citations

H-Index

About

Xiaodong Mu is a rising researcher in computer vision and robotics, whose work focuses on advancing 3D scene understanding and multi-modal tracking. His most notable contribution is the development of the "3D Implicit Transporter" (2023, 15 citations), a novel method that achieves temporally consistent keypoint discovery in 3D space. This work addresses a critical gap in existing keypoint detection techniques, which often neglect temporal coherence across frames, thereby enabling more robust spatial alignment for visual and robotic tasks. Mu's approach leverages implicit neural representations to maintain keypoint consistency over time, offering significant advantages for applications in dynamic environments, such as autonomous navigation and manipulation. Additionally, his work on "IAMTrack" (2025, 4 citations) introduces interframe appearance and modality token propagation for RGBT tracking, enhancing multi-modal fusion and temporal modeling. While still early in his career, Mu's research demonstrates a clear trajectory toward solving fundamental challenges in temporal and spatial representation learning, with potential impacts on embodied AI and real-time perception systems. His innovative methods are paving the way for more reliable and consistent visual understanding in complex, time-varying scenarios.