Related papers: Continual Learning for Image-Based Camera Localiza…

Image fusion aims to combine complementary information from multiple source images to generate more comprehensive scene representations. Existing methods primarily rely on the stacking and design of network architectures to enhance the…

Camera localization methods based on retrieval, local feature matching, and 3D structure-based pose estimation are accurate but require high storage, are slow, and are not privacy-preserving. A method based on scene landmark detection (SLD)…

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new…

Visual localization is a core component in many applications, including augmented reality (AR). Localization algorithms compute the camera pose of a query image w.r.t. a scene representation, which is typically built from images. This often…

Classical Visual Servoing (VS) rely on handcrafted visual features, which limit their generalizability. Recently, a number of approaches, some based on Deep Neural Networks, have been proposed to overcome this limitation by comparing…

Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model.…

The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the…

We propose a new method for estimating the relative pose between two images, where we jointly learn keypoint detection, description extraction, matching and robust pose estimation. While our architecture follows the traditional pipeline for…

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training…

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop…

We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data. Our method is based on invariant instance feature learning but is tailored for…

Image-based localization is a core component of many augmented/mixed reality (AR/MR) and autonomous robotic systems. Current localization systems rely on the persistent storage of 3D point clouds of the scene to enable camera pose…

Re-localizing a camera from a single image in a previously mapped area is vital for many computer vision applications in robotics and augmented/virtual reality. In this work, we address the problem of estimating the 6 DoF camera pose…

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…

Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, e.g., in the…

Visual localization, i.e., the problem of camera pose estimation, is a central component of applications such as autonomous robots and augmented reality systems. A dominant approach in the literature, shown to scale to large scenes and to…

Current research on visual place recognition mostly focuses on aggregating local visual features of an image into a single vector representation. Therefore, high-level information such as the geometric arrangement of the features is…

Current automatic vision systems face two major challenges: scalability and extreme variability of appearance. First, the computational time required to process an image typically scales linearly with the number of pixels in the image,…

Place recognition is an essential and challenging task in loop closing and global localization for robotics and autonomous driving applications. Benefiting from the recent advances in deep learning techniques, the performance of LiDAR place…