CoFiI2P: coarse-to-fine correspondences-based image to point cloud registration

• Main Authors: Kang, Shuhao, Liao, Youqi, Li, Jianping, Liang, Fuxun, Li, Yuhao, Zou, Xianghong, Li, Fangning, Chen, Xieyuanli, Dong, Zhen, Yang, Bisheng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2025
• Subjects: Engineering; Coarse-to-fine correspondences; Transformer network
• Online Access: https://hdl.handle.net/10356/182367
• Institution: Nanyang Technological University

Image-to-point cloud (I2P) registration is a fundamental task for robots and autonomous vehicles to achieve cross-modality data fusion and localization. Current I2P registration methods primarily focus on estimating correspondences at the point or pixel level, often neglecting global alignment. As a result, I2P matching can easily converge to a local optimum if it lacks high-level guidance from global constraints. To improve the success rate and general robustness, this letter introduces CoFiI2P, a novel I2P registration network that extracts correspondences in a coarse-to-fine manner. First, the image and point cloud data are processed through a two-stream encoder-decoder network for hierarchical feature extraction. Second, a coarse-to-fine matching module is designed to leverage these features and establish robust feature correspondences. Specifically, in the coarse matching phase, a novel I2P transformer module is employed to capture both homogeneous and heterogeneous global information from the image and point cloud data. This enables the estimation of coarse super-point/super-pixel matching pairs with discriminative descriptors. In the fine matching module, point/pixel pairs are established with the guidance of super-point/super-pixel correspondences. Finally, based on matching pairs, the transformation matrix is estimated with the EPnP-RANSAC algorithm. Experiments conducted on the KITTI Odometry dataset demonstrate that CoFiI2P achieves impressive results, with a relative rotation error (RRE) of 1.14 degrees and a relative translation error (RTE) of 0.29 meters, while maintaining real-time speed. These results represent a significant improvement of 84% in RRE and 89% in RTE compared to the current state-of-the-art (SOTA) method. Additional experiments on the Nuscenes dataset confirm our method's generalizability.