Renjing Xu

Papers

Total Citations

H-Index

About

Renjing Xu is an emerging researcher specializing in event-based vision, 3D reconstruction, and neural implicit representations, with a particular focus on bridging the gap between neuromorphic sensing and modern deep learning frameworks. His notable work, "Physical Priors Augmented Event-Based 3D Reconstruction" (2024), demonstrates a sophisticated understanding of the unique challenges posed by event cameras — sensors that capture asynchronous, sparse data streams rather than conventional frame-based imagery. By integrating physical priors into neural radiance field (NeRF) pipelines, Xu addresses one of the field's most pressing limitations: the difficulty of reconstructing accurate 3D scenes from sparse, information-limited event streams. This contribution holds significant implications for robotics, where reliable 3D scene understanding is fundamental to navigation, manipulation, and perception tasks. With 9 citations accrued shortly after publication, his work is already attracting attention within the computer vision and robotics communities. Xu represents a new generation of researchers pushing the boundaries of event-based sensing technology, making previously intractable reconstruction problems tractable through principled, physics-informed deep learning approaches.