Related papers: HGL: Hierarchical Geometry Learning for Test-time …

In 3D point cloud understanding, the core challenge lies in accurately capturing discriminative features within complex neighborhoods, which directly affects the execution precision of downstream tasks such as embodied AI and autonomous…

Large 2D vision-language models (2D-LLMs) have gained significant attention by bridging Large Language Models (LLMs) with images using a simple projector. Inspired by their success, large 3D point cloud-language models (3D-LLMs) also…

Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…

3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This can significantly hinder the…

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate…

Point clouds, as a form of Lagrangian representation, allow for powerful and flexible applications in a large number of computational disciplines. We propose a novel deep-learning method to learn stable and temporally coherent feature…

Generating high-quality pseudo-labels on the cloud is crucial for cloud-edge object detection, especially in dynamic traffic monitoring where data distributions evolve. Existing methods often assume reliable cloud models, neglecting…

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model…

Recent self-supervised pre-training methods on Heterogeneous Information Networks (HINs) have shown promising competitiveness over traditional semi-supervised Heterogeneous Graph Neural Networks (HGNNs). Unfortunately, their performance…

Recently, the fundamental problem of unsupervised domain adaptation (UDA) on 3D point clouds has been motivated by a wide variety of applications in robotics, virtual reality, and scene understanding, to name a few. The point cloud data…

Point cloud registration aims to provide estimated transformations to align point clouds, which plays a crucial role in pose estimation of various navigation systems, such as surgical guidance systems and autonomous vehicles. Despite the…

The integration of GNSS data into portable devices has led to the generation of vast amounts of trajectory data, which is crucial for applications such as map-matching. To tackle the limitations of rule-based methods, recent works in deep…

This technical report presents the implementation details of the winning solution for the ICRA 2025 GOOSE 3D Semantic Segmentation Challenge. This challenge focuses on semantic segmentation of 3D point clouds from diverse unstructured…

Hyperbolic spaces allow for more efficient modeling of complex, hierarchical structures, which is particularly beneficial in tasks involving multi-modal data. Although hyperbolic geometries have been proven effective for language-image…

The recently introduced coder based on region-adaptive hierarchical transform (RAHT) for the compression of point clouds attributes, was shown to have a performance competitive with the state-of-the-art, while being much less complex. In…

Learning semantic representations from point sets of 3D object shapes is often challenged by significant geometric variations, primarily due to differences in data acquisition methods. Typically, training data is generated using point…

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many…

In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this…

The main challenge in domain generalization (DG) is to handle the distribution shift problem that lies between the training and test data. Recent studies suggest that test-time training (TTT), which adapts the learned model with test data,…

Test-time adaptation (TTA) refers to adapting a classifier for the test data when the probability distribution of the test data slightly differs from that of the training data of the model. To the best of our knowledge, most of the existing…