Danni Wu

Papers

Total Citations

H-Index

About

Danni Wu is a leading researcher in autonomous driving perception, with a primary focus on LiDAR-based 3D scene understanding and multi-sensor fusion. Their most-cited work, the 2022 survey “Deep learning for LiDAR-only and LiDAR-fusion 3D perception,” has already garnered over 40 citations, establishing it as a key reference for researchers navigating the rapidly evolving landscape of point cloud deep learning. Wu’s contributions systematically map the state of the art in object detection, segmentation, and tracking using LiDAR alone or in combination with cameras and radar—critical for safe, robust autonomous systems. By synthesizing advances in sparse convolution, transformer architectures, and fusion strategies, Wu provides a clear taxonomy that helps both newcomers and experts identify promising research directions. Their work directly addresses the challenge of leveraging LiDAR’s precise geometric data alongside complementary sensor modalities, a core problem in robotics and self-driving cars. With this influential survey and ongoing work in perception, Danni Wu is shaping how the field approaches reliable environmental understanding for real-world deployment.