Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration

About

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale registration methods are rarely explored. Challenges mainly arise from the huge point number, complex distribution, and outliers of outdoor LiDAR scans. In addition, most existing registration works generally adopt a two-stage paradigm: They first find correspondences by extracting discriminative local features and then leverage estimators (eg. RANSAC) to filter outliers, which are highly dependent on well-designed descriptors and post-processing choices. To address these problems, we propose an end-to-end transformer network (RegFormer) for large-scale point cloud alignment without any further post-processing. Specifically, a projection-aware hierarchical transformer is proposed to capture long-range dependencies and filter outliers by extracting point features globally. Our transformer has linear complexity, which guarantees high efficiency even for large-scale scenes. Furthermore, to effectively reduce mismatches, a bijective association transformer is designed for regressing the initial transformation. Extensive experiments on KITTI and NuScenes datasets demonstrate that our RegFormer achieves competitive performance in terms of both accuracy and efficiency.

Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Marc Pollefeys, Hesheng Wang• 2023

Related benchmarks

TaskDatasetResultRank
Cross-modal registrationVoD sequence 19
RYE0.731
14
Cross-modal registrationVoD sequence 03
RYE0.628
14
Open-loop RegistrationVoD sequence 03
RTE (m)0.398
14
Cross-modal registrationVoD sequence 02
RYE0.805
14
Open-loop RegistrationVoD sequence 02
RTE (m)0.431
14
Cross-modal registrationVoD sequence 01
RYE1.224
14
Open-loop RegistrationVoD sequence 01
RTE (m)0.819
14
Open-loop RegistrationVoD sequence 04
RTE (m)0.554
14
Open-loop RegistrationVoD sequence 14
RTE (m)0.619
14
Open-loop RegistrationVoD sequence 19
RTE (m)0.817
14
Showing 10 of 24 rows

Other info

Follow for update