A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
LiDAR-Based Real-Time Panoptic Segmentation via Spatiotemporal Sequential Data Fusion
2022
Remote Sensing
To improve the performance of LiDAR-based real-time panoptic segmentation, this study proposes a spatiotemporal sequential data fusion strategy that fused points in "thing classes" based on accurate data ...
Experiments on the publicly available dataset SemanticKITTI showed that our approach could achieve an effective balance between accuracy and efficiency, and it was also applicable to other point cloud ...
Point clouds of an indoor scene are usually acquired by RGB-D sensors and characterized by limited spatial coverage, dense data points, and evenly distributed point clouds. ...
doi:10.3390/rs14081775
fatcat:qe4mhwschjej3gib5vkgdc5kdy
Dynamic Convolution for 3D Point Cloud Instance Segmentation
[article]
2022
arXiv
pre-print
The representation capability of the network is greatly improved by gathering homogeneous points that have identical semantic categories and close votes for the geometric centroids. ...
We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. ...
FFig. 4 : 4 Fig. 4:The illustration of the weight generator and instance decoder. Homogenous points are clustered by exploring both category prediction and geometric distribution. ...
arXiv:2107.08392v3
fatcat:lv3cug4s75cmtpelta6jpxciku
Real-time Progressive 3D Semantic Segmentation for Indoor Scene
[article]
2019
arXiv
pre-print
In this paper, we propose an efficient yet robust technique for on-the-fly dense reconstruction and semantic segmentation of 3D indoor scenes. ...
The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. ...
While the results from these neural networks are impressive, they only take as input a small point cloud of a few thousand points. ...
arXiv:1804.00257v5
fatcat:b4tnakzyl5d7vogmmlycjizd54
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
[article]
2023
arXiv
pre-print
The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data. ...
This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs. ...
ACKNOWLEDGMENTS This project is funded in part by the Ministry of Education Singapore, under the Tier-1 scheme with project number RG18/22. ...
arXiv:2202.13589v3
fatcat:nu4zzmxh6ngjna7cshgyrw2fmm
Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
[article]
2020
arXiv
pre-print
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. ...
In this work, we propose a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage. ...
Methodology
Point Cloud Encoder Network We formally denote the input point cloud data as {X b } b=1···B with B individual shapes (e.g. shape segmentation) or room blocks (e.g. indoor point cloud segmentation ...
arXiv:2004.04091v1
fatcat:74rdfskoffepvbi5jouzny7jbe
Weakly Supervised Semantic Point Cloud Segmentation: Towards 10× Fewer Labels
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. ...
In this work, we propose a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage. ...
Methodology
Point Cloud Encoder Network We formally denote the input point cloud data as {X b } b=1•••B with B individual shapes (e.g. shape segmentation) or room blocks (e.g. indoor point cloud segmentation ...
doi:10.1109/cvpr42600.2020.01372
dblp:conf/cvpr/XuL20
fatcat:a3qzarozkng7zmpxd2meypyklq
Deep Learning-Based 3D Instance and Semantic Segmentation: A Review
2022
Journal on Artificial Intelligence
The process of segmenting point cloud data into several homogeneous areas with points in the same region having the same attributes is known as 3D segmentation. ...
However, due to the specific problems of processing point clouds with deep neural networks, deep learning on point clouds is still in its initial stages. ...
A group of point-based semantic segmentation networks has been suggested recently. ...
doi:10.32604/jai.2022.031235
fatcat:nsxfjoy4mnamfkrsu2mgsoums4
Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
2021
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this release, we demonstrate the effectiveness of the proposed modules with competitive segmentation results on S3DIS. The library will be made public through github. ...
Pooling and unpooling modules are defined on the vertex clusters gathered during decimation. ...
Semantic Segmentation The Stanford large-scale 3D Indoor Spaces (S3DIS) dataset [2] is a real-world dataset composed of dense 3D point clouds but sparse 3D meshes of 6 large-scale indoor areas. ...
doi:10.1109/cvpr46437.2021.01364
fatcat:ewihk6xf2vfqdawqksolqn3n6q
Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation
[article]
2023
arXiv
pre-print
Our LEAK approach is very general and can be seamlessly applied on top of any segmentation architecture; indeed, experimental results showed that it enables state-of-the-art performances on different architectures ...
First, classes are clustered into macro groups according to mutual prediction errors; then, the learning process is regularized by: (1) aligning class-conditional prototypical feature representation for ...
This variation is almost negligible considering the size of a general point cloud segmentation network (e.g., Cylinder3D architecture takes around 8 GB). ...
arXiv:2301.11145v2
fatcat:lpnqsm56azcubbj453sucng5be
Table of Contents
2020
IEEE Transactions on Network Science and Engineering
Van Mieghem 2755 Improving the Controllability of Complex Networks by Temporal Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ...
Guizani 2631 Defending Malicious Check-In Using Big Data Analysis of Indoor Positioning System: An Access Point Selection Approach. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ...
doi:10.1109/tnse.2020.3028672
fatcat:g2rcdwq7zvde5bgpmys3ppvgli
Towards Building and Civil Infrastructure Reconstruction from Point Clouds: A Review on Data and Key Techniques
2021
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Nowadays, point clouds acquired through laser scanning and stereo matching have deemed to be one of the best sources for mapping urban scenes. ...
The reconstruction of 3-D objects in a scene of man-made infrastructure and buildings is one of the core tasks using point clouds, which involves both the 3-D data acquisition and processing. ...
Segmentation of Point Clouds The segmentation of point clouds is the grouping of points into several homogeneous components of one or more common features [157] . ...
doi:10.1109/jstars.2021.3060568
fatcat:zjpzyfmibjeghcf35csjnwuseu
Xhaul: toward an integrated fronthaul/backhaul architecture in 5G networks
2015
IEEE wireless communications
A redesign of the fronthaul/ backhaul network segment is a key point for 5G networks since current transport networks cannot cope with the amount of bandwidth required for 5G. ...
The RAN may support different levels of centralization (fully or partially centralized, or fully distributed), different backhauling models (in-band, outof-band, licensed, point-to-point, point-tomultipoint ...
doi:10.1109/mwc.2015.7306535
fatcat:5oc3txqskrhi7k3bexwpihvsim
Automated Sustainable Multi-Object Segmentation and Recognition via Modified Sampling Consensus and Kernel Sliding Perceptron
2020
Symmetry
Firstly, after acquiring a depth image, the point cloud and the depth maps are extracted to obtain the planes. ...
Then, depth kernel descriptors (DKDES) over segmented objects are computed for single and multiple object scenarios separately. ...
Single-Object Segmentation Using Point Cloud After refining the segmentation of RGB-D images, 3D point clouds [28] were devised with images for the different phases of module recognition, namely, feature ...
doi:10.3390/sym12111928
fatcat:co3m74ku3zcexil22yetwstola
The Fusion Strategy of 2D and 3D Information Based on Deep Learning: A Review
2021
Remote Sensing
Recently, researchers have realized a number of achievements involving deep-learning-based neural networks for the tasks of segmentation and detection based on 2D images, 3D point clouds, etc. ...
However, there are no critical reviews focusing on the fusion strategies of 2D and 3D information integration based on various data for segmentation and detection, which are the basic tasks of computer ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/rs13204029
fatcat:onnjeqvwb5gsjcrhdaq6hiekru
PointInst3D: Segmenting 3D Instances by Points
[article]
2022
arXiv
pre-print
In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion. ...
The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes ...
This distance-based prior is hard to apply in 3D, however, as the distribution of high-quality samples in 3D point clouds is irregular and unpredictable. ...
arXiv:2204.11402v2
fatcat:natqepgj4zgjpknbjzfcxjmtnm
« Previous
Showing results 1 — 15 out of 1,701 results