Xinli Xu

Papers

Total Citations

H-Index

About

Xinli Xu is an emerging researcher specializing in 3D perception and multi-sensor fusion for autonomous driving and robotics. His most recognized contribution, "FusionRCNN: LiDAR-Camera Fusion for Two-Stage 3D Object Detection" (2023), addresses one of the core challenges in autonomous systems: achieving accurate and reliable environmental perception by effectively combining complementary sensor modalities. Rather than relying solely on LiDAR point clouds — the dominant approach in prior two-stage detection frameworks — Xu's work introduces a principled method for integrating camera-based visual information with LiDAR data, enhancing the richness and accuracy of 3D object representations. This contribution has already garnered 55 citations since its publication, a notable achievement that underscores the timeliness and relevance of his research within a rapidly evolving field. By tackling the practical limitations of single-sensor pipelines, Xu's work advances the state of the art in perception systems that must operate safely in complex, real-world environments. His research speaks directly to the needs of the autonomous driving community and positions him as a promising voice in the intersection of deep learning, sensor fusion, and 3D scene understanding.