相关论文: GIDP: Learning a Good Initialization and Inducing …

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide…

Recent research has demonstrated the efficacy of pre-training graph neural networks (GNNs) to capture the transferable graph semantics and enhance the performance of various downstream tasks. However, the semantic knowledge learned from…

In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited…

Place recognition, an algorithm to recognize the re-visited places, plays the role of back-end optimization trigger in a full SLAM system. Many works equipped with deep learning tools, such as MLP, CNN, and transformer, have achieved great…

With the emerge of the Internet of Things (IoT), localization within indoor environments has become inevitable and has attracted a great deal of attention in recent years. Several efforts have been made to cope with the challenges of…

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to…

Prior research on self-supervised learning has led to considerable progress on image classification, but often with degraded transfer performance on object detection. The objective of this paper is to advance self-supervised pretrained…

A fundamental problem in supervised learning is to find a good set of features or distance measures. If the new set of features is of lower dimensionality and can be obtained by a simple transformation of the original data, they can make…

Many robotics applications require precise pose estimates despite operating in large and changing environments. This can be addressed by visual localization, using a pre-computed 3D model of the surroundings. The pose estimation then…

Deep learning has shown strong performance in geospatial prediction tasks, but the role of geolocation information in improving accuracy and generalizability remains underexamined. Recent work has introduced location encoders that aim to…

Person re-identification (reID) aims at retrieving a person from images captured by different cameras. For deep-learning-based reID methods, it has been proved that using local features together with global feature could help to give robust…

This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by…

The integration of a SLAM algorithm with place recognition technology empowers it with the ability to mitigate accumulated errors and to relocalize itself. However, existing methods for point cloud-based place recognition predominantly rely…

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the…

An efficient solution to semantic segmentation of large-scale indoor scene point clouds is proposed in this work. It is named GSIP (Green Segmentation of Indoor Point clouds) and its performance is evaluated on a representative large-scale…

Street-level geolocalization from images is crucial for a wide range of essential applications and services, such as navigation, location-based recommendations, and urban planning. With the growing popularity of social media data and…

Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made…

Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use image-level…

We introduce a discriminative multimodal descriptor based on a pair of sensor readings: a point cloud from a LiDAR and an image from an RGB camera. Our descriptor, named MinkLoc++, can be used for place recognition, re-localization and loop…

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…