Related papers: Text to Point Cloud Localization with Relation-Enh…

Unlike its image based counterpart, point cloud based retrieval for place recognition has remained as an unexplored and unsolved problem. This is largely due to the difficulty in extracting local feature descriptors from a point cloud that…

Fusion-based place recognition is an emerging technique jointly utilizing multi-modal perception data, to recognize previously visited places in GPS-denied scenarios for robots and autonomous vehicles. Recent fusion-based place recognition…

In this paper, we propose one novel model for point cloud semantic segmentation, which exploits both the local and global structures within the point cloud based on the contextual point representations. Specifically, we enrich each point…

Text augmentation is an effective technique for addressing the problem of insufficient data in natural language processing. However, existing text augmentation methods tend to focus on few-shot scenarios and usually perform poorly on large…

We present Point-TTA, a novel test-time adaptation framework for point cloud registration (PCR) that improves the generalization and the performance of registration models. While learning-based approaches have achieved impressive progress,…

3D point cloud is an efficient and flexible representation of 3D structures. Recently, neural networks operating on point clouds have shown superior performance on 3D understanding tasks such as shape classification and part segmentation.…

Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud completion methods are built on rotation-variant frameworks trained with data in canonical poses,…

A robot operating in a real-world environment needs to perform reasoning over a variety of sensor modalities such as vision, language and motion trajectories. However, it is extremely challenging to manually design features relating such…

Recent machine learning-based multi-object tracking (MOT) frameworks are becoming popular for 3-D point clouds. Most traditional tracking approaches use filters (e.g., Kalman filter or particle filter) to predict object locations in a time…

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…

Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments.…

Localization is a key requirement for mobile robot autonomy and human-robot interaction. Vision-based localization is accurate and flexible, however, it incurs a high computational burden which limits its application on many…

Image to point cloud global localization is crucial for robot navigation in GNSS-denied environments and has become increasingly important for multi-robot map fusion and urban asset management. The modality gap between images and point…

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as…

We present Point-BERT, a new paradigm for learning Transformers to generalize the concept of BERT to 3D point cloud. Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers. Specifically, we…

The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a…

Remarkable performance from Transformer networks in Natural Language Processing promote the development of these models in dealing with computer vision tasks such as image recognition and segmentation. In this paper, we introduce a novel…

We propose an end-to-end trainable approach for multi-instance pose estimation, called POET (POse Estimation Transformer). Combining a convolutional neural network with a transformer encoder-decoder architecture, we formulate multiinstance…

This paper proposes a voxel-based approach for creating a digital twin of an urban environment that is capable of efficiently managing smart spaces. The paper explains the registration and localization procedure of the point cloud dataset,…

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is…