Related papers: Multi-task 3D building understanding with multi-mo…

The task of identifying and segmenting buildings within remote sensing imagery has perennially stood at the forefront of scholarly investigations. This manuscript accentuates the potency of harnessing diversified datasets in tandem with…

Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further…

This paper introduces a new Urban Point Cloud Dataset for Automatic Segmentation and Classification acquired by Mobile Laser Scanning (MLS). We describe how the dataset is obtained from acquisition to post-processing and labeling. This…

Segmentation architectures are typically benchmarked on single imaging modalities, obscuring deployment-relevant performance variations: an architecture optimal for one modality may underperform on another. We present a cross-modal…

3D instance segmentation is crucial for obtaining an understanding of a point cloud scene. This paper presents a novel neural network architecture for performing instance segmentation on 3D point clouds. We propose to jointly learn…

This technical report presents the 1st place winning solution for the Waymo Open Dataset 3D semantic segmentation challenge 2022. Our network, termed LidarMultiNet, unifies the major LiDAR perception tasks such as 3D semantic segmentation,…

Instance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up…

Fully convolutional networks (FCNs), including UNet and VNet, are widely-used network architectures for semantic segmentation in recent studies. However, conventional FCN is typically trained by the cross-entropy or Dice loss, which only…

LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a…

Mobile robots need to create high-definition 3D maps of the environment for applications such as remote surveillance and infrastructure mapping. Accurate semantic processing of the acquired 3D point cloud is critical for allowing the robot…

While massively scaling both data and models have become central in NLP and 2D vision, their benefits for 3D point cloud understanding remain limited. We study the initial step of scaling 3D point cloud understanding under a realistic…

In this work, we investigate multi-task learning as a way of pre-training models for classification tasks in digital pathology. It is motivated by the fact that many small and medium-size datasets have been released by the community over…

State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale datasets and well-defined category sets. Recent advances in multi-modal pre-training have demonstrated potential in learning 3D representations by…

Urban modeling from LiDAR point clouds is an important topic in computer vision, computer graphics, photogrammetry and remote sensing. 3D city models have found a wide range of applications in smart cities, autonomous navigation, urban…

A unified and versatile LiDAR segmentation model with strong robustness and generalizability is desirable for safe autonomous driving perception. This work presents M3Net, a one-of-a-kind framework for fulfilling multi-task, multi-dataset,…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

Satellite imagery has played an increasingly important role in post-disaster building damage assessment. Unfortunately, current methods still rely on manual visual interpretation, which is often time-consuming and can cause very low…

Building segmentation from aerial images and 3D laser scanning (LiDAR) is a challenging task due to the diversity of backgrounds, building textures, and image quality. While current research using different types of convolutional and…

The accurate segmentation of lesions in whole-body PET/CT imaging is es-sential for tumor characterization, treatment planning, and response assess-ment, yet current manual workflows are labor-intensive and prone to inter-observer…

Semantic 3D building models are widely available and used in numerous applications. Such 3D building models display rich semantics but no fa\c{c}ade openings, chiefly owing to their aerial acquisition techniques. Hence, refining models'…