Related papers: Geometric Multi-Session Map Merging with Learned L…

Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D…

Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research, showcasing promising capabilities across various emerging benchmarks. LMMs specifically designed for this domain have demonstrated effective…

Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate…

Incorporating prior structure information into the visual state estimation could generally improve the localization performance. In this letter, we aim to address the paradox between accuracy and efficiency in coupling visual factors with…

Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and…

Federated learning allows clients to collaboratively train models on datasets that are acquired in different locations and that cannot be exchanged because of their size or regulations. Such collected data is increasingly non-independent…

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive…

Loop closure can effectively correct the accumulated error in robot localization, which plays a critical role in the long-term navigation of the robot. Traditional appearance-based methods rely on local features and are prone to failure in…

Multiple mobile robots play a significant role in various spatially distributed tasks.In unfamiliar and non-repetitive scenarios, reconstructing the global map is time-inefficient and sometimes unrealistic. Hence, research has focused on…

In the era of pre-trained models, image clustering task is usually addressed by two relevant stages: a) to produce features from pre-trained vision models; and b) to find clusters from the pre-trained features. However, these two stages are…

Accurate indoor localization remains challenging due to variations in wireless signal environments and limited data availability. This paper introduces MetaGraphLoc, a novel system leveraging sensor fusion, graph neural networks (GNNs), and…

This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport…

Relative pose estimation is crucial for various computer vision applications, including Robotic and Autonomous Driving. Current methods primarily depend on selecting and matching feature points prone to incorrect matches, leading to poor…

Deep metric learning applied to various applications has shown promising results in identification, retrieval and recognition. Existing methods often do not consider different granularity in visual similarity. However, in many domain…

Deep Metric Learning (DML) models often require strong local and global representations, however, effective integration of local and global features in DML model training is a challenge. DML models are often trained with specific loss…

The advancement of deep learning has driven notable progress in remote sensing semantic segmentation. Attention mechanisms, while enabling global modeling and utilizing contextual information, face challenges of high computational costs and…

Understanding the geometric and semantic structure of environments is essential for embodied navigation and reasoning. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics, and lack a native…

We present a novel approach for relocalization or place recognition, a fundamental problem to be solved in many robotics, automation, and AR applications. Rather than relying on often unstable appearance information, we consider a situation…

LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…

Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade…