Weiquan Liu
Papers
2
Total Citations
17
H-Index
2
About
Dr. Weiquan Liu is a leading researcher in computer vision and 3D scene understanding, with a focus on bridging the gap between 2D images and 3D point clouds. His major contributions center on developing robust cross-domain feature descriptors for 2D-3D matching, a critical challenge for applications like augmented reality, robotics, and autonomous navigation. His most influential work, "2D3D-MVPNet," introduces a novel framework that leverages multi-view projections of point clouds to learn discriminative descriptors, achieving 14 citations since 2022 and establishing a new benchmark for cross-modal correspondence. Earlier, he pioneered the use of hard triplet loss combined with spatial transformer networks to enhance descriptor learning, as demonstrated in his 2021 paper. Dr. Liu’s research directly addresses the fundamental problem of aligning disparate data modalities, enabling more accurate and efficient 3D reconstruction and localization. His innovative approaches have been recognized for their practical impact, offering scalable solutions for real-world systems that require seamless integration of 2D and 3D data.
Research Focus
Key Achievements
Top Papers
- 1
- 2