Related papers: Coarse-to-Fine Monocular Re-Localization in OpenSt…
Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework…
The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service…
Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations. Inspired by the non-contrastive SSL approach (SimSiam), we introduce a novel framework SIMSAM to…
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM…
In this work, we propose a simultaneous localization and mapping (SLAM) system using a monocular camera and Ultra-wideband (UWB) sensors. Our system, referred to as VRSLAM, is a multi-stage framework that leverages the strengths and…
Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics, the same can currently not be said for capturing global…
Open-vocabulary image semantic segmentation (OVS) seeks to segment images into semantic regions across an open set of categories. Existing OVS methods commonly depend on foundational vision-language models and utilize similarity computation…
Downsampling and path planning are essential in robotics and autonomous systems, as they enhance computational efficiency and enable effective navigation in complex environments. However, current downsampling methods often fail to preserve…
In this paper, we address monocular depth estimation with deep neural networks. To enable training of deep monocular estimation models with various sources of datasets, state-of-the-art methods adopt image-level normalization strategies to…
This paper presents a system for autonomous semantic exploration and dense semantic target mapping of a complex unknown environment using a ground robot equipped with a LiDAR-panoramic camera suite. Existing approaches often struggle to…
Incremental open-vocabulary 3D instance-semantic mapping is essential for autonomous agents operating in complex everyday environments. However, it remains challenging due to the need for robust instance segmentation, real-time processing,…
Deep Learning based techniques have been adopted with precision to solve a lot of standard computer vision problems, some of which are image classification, object detection and segmentation. Despite the widespread success of these…
The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level…
In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise…
Robust cross-seasonal localization is one of the major challenges in long-term visual navigation of autonomous vehicles. In this paper, we exploit recent advances in semantic segmentation of images, i.e., where each pixel is assigned a…
This paper introduces a cost effective localization system combining monocular visual odometry , augmented reality (AR) poses, and integrated INS-GPS data. We address monocular VO scale factor issues using AR poses and enhance accuracy with…
The recent years have witnessed the remarkable development for open-vocabulary semantic segmentation (OVSS) using visual-language foundation models, yet still suffer from following fundamental challenges: (1) insufficient cross-modal…
In the context of robotic underwater operations, the visual degradations induced by the medium properties make difficult the exclusive use of cameras for localization purpose. Hence, most localization methods are based on expensive…
Standard semantic instance segmentation provides useful, but inherently 2D information from a single image. To enable 3D analysis, one usually integrates absolute monocular depth estimation with instance segmentation. However, monocular…
Currently, GPS is by far the most popular global localization method. However, it is not always reliable or accurate in all environments. SLAM methods enable local state estimation but provide no means of registering the local map to a…