Related papers: Hierarchical Point-based Active Learning for Semi-…

Autonomous driving can benefit from motion behavior comprehension when interacting with diverse traffic participants in highly dynamic environments. Recently, there has been a growing interest in estimating class-agnostic motion directly…

Automated semantic segmentation and object detection are of great importance in geospatial data analysis. However, supervised machine learning systems such as convolutional neural networks require large corpora of annotated training data.…

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo…

Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate in the 2D image space. Direct semantic segmentation of unstructured 3D point…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much…

Reliable 3D segmentation is critical for understanding complex scenes with dense layouts and multi-scale objects, as commonly seen in industrial environments. In such scenarios, heavy occlusion weakens geometric boundaries between objects,…

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of…

Point cloud semantic segmentation plays an essential role in autonomous driving, providing vital information about drivable surfaces and nearby objects that can aid higher level tasks such as path planning and collision avoidance. While…

3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However, densely labeling 3D point clouds to employ…

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…

Semantic segmentation metrics for 3D point clouds, such as mean Intersection over Union (mIoU) and Overall Accuracy (OA), present two key limitations in the context of aerial LiDAR data. First, they treat all misclassifications equally…

State of the art methods for semantic image segmentation are trained in a supervised fashion using a large corpus of fully labeled training images. However, gathering such a corpus is expensive, due to human annotation effort, in contrast…

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents…

Point cloud classification refers to the process of assigning semantic labels or categories to individual points within a point cloud data structure. Recent works have explored the extension of pre-trained CLIP to 3D recognition. In this…

Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are…

Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems. A wide variety of solutions using deep learning have been proposed for point…

To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. Our…

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…

The promotion of construction robots can solve the problem of human resource shortage and improve the quality of decoration. To help the construction robots obtain environmental information, we need to use 3D point cloud, which is widely…