Despite recent success in incorporating learning into point cloud registration, many works
focus on learning feature descriptors and continue to rely on nearest-neighbor feature …

LiDAR-based place recognition (LPR) plays a pivotal role in autonomous driving, which
assists Simultaneous Localization and Mapping (SLAM) systems in reducing accumulated …

We introduce PREDATOR, a model for pairwise pointcloud registration with deep attention
to the overlap region. Different from previous work, our model is specifically designed to …

As a fundamental and critical task in various visual applications, image matching can identify
then correspond the same or similar structure/content from two or more images. Over the …

Removing outlier correspondences is one of the critical steps for successful feature-based
point cloud registration. Despite the increasing popularity of introducing deep learning …

Extracting robust and general 3D local features is key to downstream tasks such as point
cloud registration and reconstruction. Existing learning-based local descriptors are either …

Keypoint detection & descriptors are foundational technologies for computer vision tasks like
image matching, 3D reconstruction and visual odometry. Hand-engineered methods like …

Point cloud registration is the task of estimating the rigid transformation that aligns a pair of
point cloud fragments. We present an efficient and robust framework for pairwise registration …

Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR
point clouds are typically large-scale and complexly distributed, which makes the …

In this work we target the problem of estimating accurately localized correspondences
between a pair of images. We adopt the recent Neighbourhood Consensus Networks that …