# A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation

## TL;DR

This paper introduces a unified BEV-based model that jointly learns 3D local features and overlap estimation to improve pairwise point cloud registration, especially in scenes with small overlaps, achieving state-of-the-art results.

## Contribution

The paper proposes a novel BEV-based neural network that simultaneously estimates overlap regions and extracts features for registration, enhancing robustness in low-overlap scenarios.

## Key findings

- Outperforms existing methods in overlap estimation accuracy.
- Achieves top registration performance on KITTI and Apollo-SouthBay datasets.
- Significantly improves registration in scenes with small overlaps.

## Abstract

Pairwise point cloud registration is a critical task for many applications, which heavily depends on finding correct correspondences from the two point clouds. However, the low overlap between input point clouds causes the registration to fail easily, leading to mistaken overlapping and mismatched correspondences, especially in scenes where non-overlapping regions contain similar structures. In this paper, we present a unified bird's-eye view (BEV) model for jointly learning of 3D local features and overlap estimation to fulfill pairwise registration and loop closure. Feature description is performed by a sparse UNet-like network based on BEV representation, and 3D keypoints are extracted by a detection head for 2D locations, and a regression head for heights. For overlap detection, a cross-attention module is applied for interacting contextual information of input point clouds, followed by a classification head to estimate the overlapping region. We evaluate our unified model extensively on the KITTI dataset and Apollo-SouthBay dataset. The experiments demonstrate that our method significantly outperforms existing methods on overlap estimation, especially in scenes with small overlaps. It also achieves top registration performance on both datasets in terms of translation and rotation errors.