Related papers: HDD-Net: Hybrid Detector Descriptor with Mutual In…

Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We…

Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first…

Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in…

For relocalization in large-scale point clouds, we propose the first approach that unifies global place recognition and local 6DoF pose refinement. To this end, we design a Siamese network that jointly learns 3D local feature detection and…

We develop methods for detector learning which exploit joint training over both weak and strong labels and which transfer learned perceptual representations from strongly-labeled auxiliary tasks. Previous methods for weak-label learning…

Learning a fast and discriminative patch descriptor is a challenging topic in computer vision. Recently, many existing works focus on training various descriptor learning networks by minimizing a triplet loss (or its variants), which is…

A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D feature descriptors, little attention has been drawn to the…

In this paper, we present a novel approach that exploits the information within the descriptor space to propose keypoint locations. Detect then describe, or detect and describe jointly are two typical strategies for extracting local…

3D landmark detection is a critical task in medical image analysis, and accurately detecting anatomical landmarks is essential for subsequent medical imaging tasks. However, mainstream deep learning methods in this field struggle to…

Performing accurate localization while maintaining the low-level communication bandwidth is an essential challenge of multi-robot simultaneous localization and mapping (MR-SLAM). In this paper, we tackle this problem by generating a compact…

Modifications on triplet loss that rescale the back-propagated gradients of special pairs have made significant progress on local descriptor learning. However, current gradient modulation strategies are mainly static so that they would…

The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks…

Triplet loss is widely used for learning local descriptors from image patch. However, triplet loss only minimizes the Euclidean distance between matching descriptors and maximizes that between the non-matching descriptors, which neglects…

Classical Visual Simultaneous Localization and Mapping (VSLAM) algorithms can be easily induced to fail when either the robot's motion or the environment is too challenging. The use of Deep Neural Networks to enhance VSLAM algorithms has…

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Recent advancements in keypoint detection and descriptor extraction have shown impressive performance in local feature learning tasks. However, existing methods generally exhibit suboptimal performance under extreme conditions such as…

Visual localization to compute 6DoF camera pose from a given image has wide applications such as in robotics, virtual reality, augmented reality, etc. Two kinds of descriptors are important for the visual localization. One is global…

Depth from defocus (DfD) and stereo matching are two most studied passive depth sensing schemes. The techniques are essentially complementary: DfD can robustly handle repetitive textures that are problematic for stereo matching whereas…

Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted methods are used to…

The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.…