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

03/22/2023
by   Jiuming Liu, et al.
0

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 state-of-the-art performance in terms of both accuracy and efficiency.

READ FULL TEXT

page 1

page 3

page 8

research
07/26/2021

HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration

Point cloud registration is a fundamental problem in 3D computer vision....
research
09/01/2023

Robust Point Cloud Processing through Positional Embedding

End-to-end trained per-point embeddings are an essential ingredient of a...
research
03/28/2022

REGTR: End-to-end Point Cloud Correspondences with Transformers

Despite recent success in incorporating learning into point cloud regist...
research
04/08/2021

DeepI2P: Image-to-Point Cloud Registration via Deep Classification

This paper presents DeepI2P: a novel approach for cross-modality registr...
research
07/09/2022

Learning to Register Unbalanced Point Pairs

Recent 3D registration methods can effectively handle large-scale or par...
research
02/13/2022

LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling

Compared with traditional task-irrelevant downsampling methods, task-ori...
research
05/23/2019

Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes

Outlier feature matches and loop-closures that survived front-end data a...

Please sign up or login with your details

Forgot password? Click here to reset