SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.12384 · ICCV · 2023

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

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, largescale 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 twostage 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 endto-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. Codes are available at https://github.com/IRMVLab/RegFormer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.12384")
get_code_for_paper("2303.12384")
have("2303.12384")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.12384.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.12384.svg)](https://syntology.ai/paper/2303.12384)

Connect an agent — have() is free.