Haibing Ren

Papers

Total Citations

H-Index

About

Haibing Ren is a researcher in computer vision and robotics, with a primary focus on 3D point cloud processing and registration. His work addresses fundamental challenges in spatial perception, particularly in scenarios involving large rotations and small overlaps between scans—conditions that often defeat conventional registration algorithms. Ren’s most cited paper, "PCAOT: A Manhattan Point Cloud Registration Method Towards Large Rotation and Small Overlap" (2018, 9 citations), introduces a robust registration technique tailored for Manhattan-world scenes, significantly advancing the reliability of robot mapping and localization under difficult conditions. In earlier work, "SDTP: a robust method for interest point detection on 3D range images" (2014, 6 citations), he developed a novel detector for identifying salient structures in range data, improving the performance of downstream applications such as object recognition and scene reconstruction. Though his citation counts are modest, Ren’s contributions are technically impactful, offering practical solutions to persistent problems in autonomous navigation and 3D vision. His research is especially valuable for engineers and scientists working on real-world robotic systems where sensor data is noisy, sparse, or poorly aligned.