Guojun Dai — accepted AI-conference papers

2024

Boosting RGB-D Point Cloud Registration via Explicit Position-Aware Geometric Embedding

Wenhui Zhou, Luwei Ren, Junle Yu, Nian Qu, Guojun Dai

RA-L 2024

The goal of point cloud registration is to determine the rigid transformation between two unaligned point clouds, in which extracting reliable correspondences from overlapping regions is the key to success. Many recent methods have attempted to boost point cloud registration by using RGB-D data. The

Cited by 10 Source ↗code ↗Scholar ↗

2023

PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration

Junle Yu, Luwei Ren, Yu Zhang, Wenhui Zhou, Lili Lin, Guojun Dai

CVPR 2023poster

Learning distinctive point-wise features is critical for low-overlap point cloud registration. Recently, it has achieved huge success in incorporating Transformer into point cloud feature representation, which usually adopts a self-attention module to learn intra-point-cloud features first, then uti…

Cited by 59 Source ↗PDF ↗code ↗Scholar ↗