Related papers: GLACE: Global Local Accelerated Coordinate Encodin…

Anomaly Detection involves identifying deviations from normal data distributions and is critical in fields such as medical diagnostics and industrial defect detection. Traditional AD methods typically require the availability of normal…

We present our work on scalable, GPU-accelerated algorithms for diffeomorphic image registration. The associated software package is termed CLAIRE. Image registration is a non-linear inverse problem. It is about computing a spatial mapping…

Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of…

The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor…

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…

Reconstructing 3D scenes from unconstrained image collections poses significant challenges due to variations in appearance. In this paper, we propose Scalable Micro-macro Wavelet-based Gaussian Splatting (SMW-GS), a novel method that…

Cross-view geo-localization (CVGL) aims to establish spatial correspondences between images captured from significantly different viewpoints and constitutes a fundamental technique for visual localization in GNSS-denied environments.…

Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications, especially in scene understanding areas. However, most existing methods operate on fully annotated data while manually preparing…

Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in…

Existing methods of 3D cross-modal retrieval heavily lean on category distribution priors within the training set, which diminishes their efficacy when tasked with unseen categories under open-set environments. To tackle this problem, we…

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level…

Monocular Semantic Scene Completion (MSSC) aims to predict the voxel-wise occupancy and semantic category from a single-view RGB image. Existing methods adopt a single-stage framework that aims to simultaneously achieve visible region…

We propose an end-to-end solution to address the problem of object localisation in partial scenes, where we aim to estimate the position of an object in an unknown area given only a partial 3D scan of the scene. We propose a novel scene…

Scene graphs enhance 3D mapping capabilities in robotics by understanding the relationships between different spatial elements, such as rooms and objects. Recent research extends scene graphs to hierarchical layers, adding and leveraging…

Recovering high-quality 3D scenes from a single RGB image is a challenging task in computer graphics. Current methods often struggle with domain-specific limitations or low-quality object generation. To address these, we propose CAST…

This article introduces a novel method for object-level relocalization of robotic systems. It determines the pose of a camera sensor by robustly associating the object detections in the current frame with 3D objects in a lightweight…

Visual retrieval tasks such as image retrieval and person re-identification (Re-ID) aim at effectively and thoroughly searching images with similar content or the same identity. After obtaining retrieved examples, re-ranking is a widely…

Recently, with the prevalence of large-scale image dataset, the co-occurrence information among classes becomes rich, calling for a new way to exploit it to facilitate inference. In this paper, we propose Obj-GloVe, a generic scene-based…

As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…

We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos. Unlike conventional methods encoding motion and appearance patterns individually, our method puts particular…