Related papers: Locating and Mitigating Gradient Conflicts in Poin…

Recent progress of semantic point clouds analysis is largely driven by synthetic data (e.g., the ModelNet and the ShapeNet), which are typically complete, well-aligned and noisy free. Therefore, representations of those ideal synthetic…

Most existing self-supervised learning (SSL) approaches for 3D point clouds are dominated by generative methods based on Masked Autoencoders (MAE). However, these generative methods have been proven to struggle to capture high-level…

The bottom-up saliency, an early stage of humans' visual attention, can be considered as a binary classification problem between center and surround classes. Discriminant power of features for the classification is measured as mutual…

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…

3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can…

Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets.…

Anomaly detection based on 3D point cloud data is an important research problem and receives more and more attention recently. Untrained anomaly detection based on only one sample is an emerging research problem motivated by real…

Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome…

Unsupervised Domain Adaptation (UDA) is crucial for reducing the need for extensive manual data annotation when training deep networks on point cloud data. A significant challenge of UDA lies in effectively bridging the domain gap. To…

In recent years, three-dimensional point clouds are used increasingly to document natural environments. Each dataset contains a diverse set of objects, at varying shapes and sizes, distributed throughout the data and intricately intertwined…

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success…

Semi-supervised learning addresses label scarcity and high annotation costs in medical image segmentation by exploiting the latent information in unlabeled data to enhance model performance. Traditional discriminative segmentation relies on…

An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point representation learning for autonomous driving datasets faces…

An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work. The proposed SPA method can register two point clouds effectively using only a small subset of salient points. It first applies…

Evaluating the performance of deep models in new scenarios has drawn increasing attention in recent years. However, while it is possible to collect data from new scenarios, the annotations are not always available. Existing DAOD methods…

Semi-Supervised Learning (SSL) and Unsupervised Domain Adaptation (UDA) enhance the model performance by exploiting information from labeled and unlabeled data. The clustering assumption has proven advantageous for learning with limited…

We propose DeepMapping, a novel registration framework using deep neural networks (DNNs) as auxiliary functions to align multiple point clouds from scratch to a globally consistent frame. We use DNNs to model the highly non-convex mapping…

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly…

Unsupervised domain adaptation for semantic segmentation (UDA-SS) aims to transfer knowledge from labeled source data to unlabeled target data. However, traditional UDA-SS methods assume that category settings between source and target…