Related papers: Rethinking Task and Metrics of Instance Segmentati…
This paper addresses the challenge of 3D instance segmentation by simultaneously leveraging 3D geometric and multi-view image information. Many previous works have applied deep learning techniques to 3D point clouds for instance…
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt convolutions for feature extraction. However, as affected by the inherent receptive field, convolution based feature…
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…
Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique…
This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local…
Point cloud segmentation (PCS) is to classify each point in point clouds. The task enables robots to parse their 3D surroundings and run autonomously. According to different point cloud representations, existing PCS models can be roughly…
Designing metrics for evaluating instance segmentation revolves around comprehensively considering object detection and segmentation accuracy. However, other important properties, such as sensitivity, continuity, and equality, are…
Point-cloud semantic segmentation underpins a wide range of critical applications. Although recent deep architectures and large-scale datasets have driven impressive closed-set performance, these models struggle to recognize or properly…
Instance segmentation is an important problem in computer vision, with applications in autonomous driving, drone navigation and robotic manipulation. However, most existing methods are not real-time, complicating their deployment in…
3D point cloud segmentation remains challenging for structureless and textureless regions. We present a new unified point-based framework for 3D point cloud segmentation that effectively optimizes pixel-level features, geometrical…
Instance segmentation in point clouds is one of the most fine-grained ways to understand the 3D scene. Due to its close relationship to semantic segmentation, many works approach these two tasks simultaneously and leverage the benefits of…
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,…
Existing state-of-the-art 3D point cloud understanding methods merely perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework that simultaneously solves the downstream high-level…
Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to…
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…
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…
We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization of 3D point clouds can be efficiently captured by a…
Point cloud segmentation is crucial for robotic visual perception and environmental understanding, enabling applications such as robotic navigation and 3D reconstruction. However, handling the sparse and unordered nature of point cloud data…
The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Recent state-of-the-art methods have relatively complex architectures such as…
Autonomous driving is a safety-critical application, and it is therefore a top priority that the accompanying assistance systems are able to provide precise information about the surrounding environment of the vehicle. Tasks such as 3D…