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

Lü, Fan; Chen, Guang; Liu, Yinlong; Zhang, Lijun; Qu, Sanqing; Liu, Shu; Gu, Rongqi

doi:10.1109/iccv48922.2021.01571

Cited by 89 publications

(28 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further compare to three RANSAC-free methods in Tab. 5(bottom): FMR [16], DGR [7] and HRegNet [21]. Our method outperforms all the baselines by large margin.…”

Section: Outdoor Benchmark: Kitti Odometrymentioning

confidence: 99%

See 1 more Smart Citation

Geometric Transformer for Fast and Robust Point Cloud Registration

Zheng¹,

Yu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios, showing great potential in registration. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invariant to rigid transformation. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Our method improves the inlier ratio by 17%∼30% and the registration recall by over 7% on the challenging 3DLoMatch benchmark. The code and models will be released at https://github. com/qinzheng93/GeoTransformer.

show abstract

“…We further compare to three RANSAC-free methods in Tab. 5(bottom): FMR [16], DGR [7] and HRegNet [21]. Our method outperforms all the baselines by large margin.…”

Section: Outdoor Benchmark: Kitti Odometrymentioning

confidence: 99%

“…Following [4,8,15,21,39], we compute the mean RRE and the mean RTE only for the correctly registered point cloud pairs in KITTI.…”

Section: B2 Kittimentioning

confidence: 99%

Geometric Transformer for Fast and Robust Point Cloud Registration

Zheng¹,

Yu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Various such descriptor have been suggested, e.g. [10,18,20]. Fully Convolutional Geometric Features (FCGF) [10] are based on sparse convolutions over a voxelized represen-tation of the point cloud.…”

Section: Related Workmentioning

confidence: 99%

“…One approach for producing a harder benchmark is to replace the LiDAR dataset. In [20], for example, they use the more challenging NuScenes [6] dataset. However, framepairs are still selected with a simple heuristic: scans separated by one second.…”

Section: Introductionmentioning

confidence: 99%

Stress-Testing LiDAR Registration

Drory¹,

Avidan²,

Giryes³

2022

Preprint

View full text Add to dashboard Cite

Point cloud registration (PCR) is an important task in many fields including autonomous driving with LiDAR sensors. PCR algorithms have improved significantly in recent years, by combining deep-learned features with robust estimation methods. These algorithms succeed in scenarios such as indoor scenes and object models registration. However, testing in the automotive LiDAR setting, which presents its own challenges, has been limited. The standard benchmark for this setting, KITTI-10m, has essentially been saturated by recent algorithms: many of them achieve nearperfect recall.In this work, we stress-test recent PCR techniques with LiDAR data. We propose a method for selecting balanced registration sets, which are challenging sets of frame-pairs from LiDAR datasets. They contain a balanced representation of the different relative motions that appear in a dataset, i.e. small and large rotations, small and large offsets in space and time, and various combinations of these. We perform a thorough comparison of accuracy and runtime on these benchmarks. Perhaps unexpectedly, we find that the fastest and simultaneously most accurate approach is a version of advanced RANSAC. We further improve results with a novel pre-filtering method.Full code is available 1 .

show abstract

“…Anyhow, they are usually considered as a coarse registration to provide an initial guess for fine registration. In hybrid models [10], [11], they assemble different registration modules to achieve a coarse-tofine result. In contrast to feature matching-based registrations, global feature registrations are more direct.…”

Section: Introductionmentioning

confidence: 99%

Indirect Point Cloud Registration: Aligning Distance Fields using a Pseudo Third Point Ses

Yuan¹,

Nüchter²

2022

Preprint

View full text Add to dashboard Cite

In recent years, implicit functions have drawn attention in the field of 3D reconstruction and have successfully been applied with Deep Learning. However, for incremental reconstruction, implicit function-based registrations have been rarely explored. Inspired by the high precision of deep learning global feature registration, we propose to combine this with distance fields. We generalize the algorithm to a non-Deep Learning setting while retaining the accuracy. Our algorithm is more accurate than conventional models while, without any training, it achieves a competitive performance and faster speed, compared to Deep Learning-based registration models. The implementation is available on github 1 for the research community.

show abstract

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

Cited by 89 publications

References 24 publications

Geometric Transformer for Fast and Robust Point Cloud Registration

Geometric Transformer for Fast and Robust Point Cloud Registration

Stress-Testing LiDAR Registration

Indirect Point Cloud Registration: Aligning Distance Fields using a Pseudo Third Point Ses

Contact Info

Product

Resources

About