Related papers: SaliencyI2PLoc: saliency-guided image-point cloud …
Aerial-ground localization is difficult due to large viewpoint and modality gaps between ground-level LiDAR and overhead imagery. We propose TransLocNet, a cross-modal attention framework that fuses LiDAR geometry with aerial semantic…
Cross-View Geo-Localisation is still a challenging task where additional modules, specific pre-processing or zooming strategies are necessary to determine accurate positions of images. Since different views have different geometries,…
Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. Due to the wide range of practical applications, the problem has been mainly focused on the vision and language case, e.g. text…
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open…
Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to…
Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature…
Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle…
This work explores attention models to weight the contribution of local convolutional representations for the instance search task. We present a retrieval framework based on bags of local convolutional features (BLCF) that benefits from…
In this work, we present a novel learning-based framework that combines the local accuracy of contrastive learning with the global consistency of geometric approaches, for robust non-rigid matching. We first observe that while contrastive…
This paper studies the problem of graph-level clustering, which is a novel yet challenging task. This problem is critical in a variety of real-world applications such as protein clustering and genome analysis in bioinformatics. Recent years…
To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting and object…
Conventional salient object detection models cannot differentiate the importance of different salient objects. Recently, two works have been proposed to detect saliency ranking by assigning different degrees of saliency to different…
In this paper, we propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. Existing fusion-based methods achieve remarkable performances by integrating information…
Along with the advancements in artificial intelligence technologies, image-to-point-cloud registration (I2P) techniques have made significant strides. Nevertheless, the dimensional differences in the features of points cloud…
Global visual localization in LiDAR-maps, crucial for autonomous driving applications, remains largely unexplored due to the challenging issue of bridging the cross-modal heterogeneity gap. Popular multi-modal learning approach Contrastive…
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds. Nevertheless, existing preeminent point cloud backbones usually incorporate…
Despite significant progress, image saliency detection still remains a challenging task in complex scenes and environments. Integrating multiple different but complementary cues, like RGB and Thermal (RGB-T), may be an effective way for…
This paper presents iMatcher, a fully differentiable framework for feature matching in point cloud registration. The proposed method leverages learned features to predict a geometrically consistent confidence matrix, incorporating both…
Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity.…
Improving instance-specific image goal navigation (InstanceImageNav), which locates the identical object in a real-world environment from a query image, is essential for robotic systems to assist users in finding desired objects. The…