Generating robust and reliable correspondences across images is a fundamental task for a
diversity of applications. To capture context at both global and local granularity, we propose …

State estimation of dynamical systems in real-time is a fundamental task in signal
processing. For systems that are well-represented by a fully known linear Gaussian state …

Matching local features across images is a fundamental problem in computer vision.
Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching …

Deep learning based localization and mapping has recently attracted significant attention.
Instead of creating hand-designed algorithms through exploitation of physical models or …

Visual Localization is one of the key enabling technologies for autonomous driving and
augmented reality. High quality datasets with accurate 6 Degree-of-Freedom (DoF) …

Scene coordinates regression (SCR) ie predicting 3D coordinates for every pixel of a given
image has recently shown promising potential. However existing methods remain limited to …

Deep-learning-based localization and mapping approaches have recently emerged as a
new research direction and receive significant attention from both industry and academia …

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 …

Visual localization is of great importance in robotics and computer vision. Recently, scene
coordinate regression based methods have shown good performance in visual localization …

In this work, we seek to predict camera poses across scenes with a multi-task learning
manner, where we view the localization of each scene as a new task. We propose OFVL …