A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential
for robot autonomy. For visual SLAM algorithms, though the theoretical framework has been …

Existing methods detect the keypoints in a non-differentiable way, therefore they can not
directly optimize the position of keypoints through back-propagation. To address this issue …

Compared to feature point detection and description, detecting and matching line segments
offer additional challenges. Yet, line features represent a promising complement to points for …

Image keypoints and descriptors play a crucial role in many visual measurement tasks. In
recent years, deep neural networks have been widely used to improve the performance of …

Monocular Re-Localization (MRL) is an essential component in autonomous applications,
estimating 6 degree-of-freedom ego poses wrt the scene map using monocular images …

Motion coherence is an important clue for distinguishing true correspondences from false
ones. Modeling motion coherence on sparse putative correspondences is challenging due …

Multi-modal registration is a required step for many image-guided procedures, especially
ultrasound-guided interventions that require anatomical context. While a number of such …

We propose a novel learned keypoint detection method to increase the number of correct
matches for the task of non-rigid image correspondence. By leveraging true …

The image matching task, which aims to find the correspondence between elements across
images, is a fundamental component for many computer vision applications. In visual …

This paper proposes a keypoint regressor (KeyReg), which consists of multi-layer random
forest (MRF) regressor and single random forest (SRF) classifier modules. To increase the …