Filters








7,066 Hits in 7.4 sec

A Hierarchical Graph Network for 3D Object Detection on Point Clouds

Jintai Chen, Biwen Lei, Qingyu Song, Haochao Ying, Danny Z. Chen, Jian Wu
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose a new graph convolution (GConv) based hierarchical graph network (HGNet) for 3D object detection, which processes raw point clouds directly to predict 3D bounding boxes.  ...  3D object detection on point clouds finds many applications.  ...  In this paper, we propose a novel Hierarchical Graph Network (HGNet) for 3D object detection on point clouds, based on graph convolutions (GConvs).  ... 
doi:10.1109/cvpr42600.2020.00047 dblp:conf/cvpr/ChenLSYCW20 fatcat:6imh4oabfjdqrdwkddb6sxljqy

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

Yifei Shi, Angel X. Chang, Zhelun Wu, Manolis Savva, Kai Xu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud.  ...  We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.  ...  Acknowledgements We are grateful to Thomas Funkhouser and Shuran Song for the valuable discussion.  ... 
doi:10.1109/cvpr.2019.00187 dblp:conf/cvpr/ShiCWS019 fatcat:t4f7rkbsyzfmrdoyc76kcn4pcu

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction [article]

Yifei Shi, Angel Xuan Chang, Zhelun Wu, Manolis Savva, Kai Xu
2019 arXiv   pre-print
We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud.  ...  We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.  ...  Acknowledgements We are grateful to Thomas Funkhouser and Shuran Song for the valuable discussion.  ... 
arXiv:1903.03757v2 fatcat:rd24h3i2ircbhdah5rmefy7dni

Deep Learning for 3D Point Clouds: A Survey [article]

Yulan Guo, Hanyun Wang, Qingyong Hu, Hao Liu, Li Liu, Mohammed Bennamoun
2020 arXiv   pre-print
It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation.  ...  However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks.  ...  [125] proposed a graph neural network Point-GNN to detect 3D objects from lidar point clouds.  ... 
arXiv:1912.12033v2 fatcat:qiiyvvuulfccxaiihf2mu23k34

Deep Learning on Point Clouds and Its Application: A Survey

Weiping Liu, Jia Sun, Wanyi Li, Ting Hu, Peng Wang
2019 Sensors  
The applications related to point cloud feature learning, including 3D object classification, semantic segmentation, and 3D object detection, are introduced, and the datasets and evaluation metrics are  ...  Point cloud is a widely used 3D data form, which can be produced by depth sensors, such as Light Detection and Ranging (LIDAR) and RGB-D cameras.  ...  Acknowledgments: The authors own many thanks to the anonymous reviewers for their instructive comments. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s19194188 fatcat:s64jm5t5xbhzjk7jxgrodehucu

Deep Learning for 3D Point Cloud Understanding: A Survey [article]

Haoming Lu, Humphrey Shi
2021 arXiv   pre-print
While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points.  ...  To demonstrate the latest progress of deep learning for 3D point cloud understanding, this paper summarizes recent remarkable research contributions in this area from several different directions (classification  ...  Graph neural networks have also been introduced to 3D object detection for its ability to accommodate intrinsic characteristics of point clouds like sparsity.  ... 
arXiv:2009.08920v2 fatcat:qiuhs6v345bpffzjk2nvhgbfvq

SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds [article]

Qingdong He, Zhengning Wang, Hao Zeng, Yi Zeng, Yijun Liu
2021 arXiv   pre-print
Accurate 3D object detection from point clouds has become a crucial component in autonomous driving.  ...  Experiments on KITTI detection benchmark demonstrate the efficiency of extending the graph representation to 3D object detection and the proposed SVGA-Net can achieve decent detection accuracy.  ...  Graph neural network for 3d object detection in a point cloud.  ... 
arXiv:2006.04043v2 fatcat:p4jzhx74pnclpdgkh4uo7hrbwy

Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review [article]

Ying Li, Lingfei Ma, Zilong Zhong, Fei Liu, Dongpu Cao, Jonathan Li, Michael A. Chapman
2020 arXiv   pre-print
However, automated processing uneven, unstructured, noisy, and massive 3D point clouds is a challenging and tedious task.  ...  Although several published research papers focus on specific topics in computer vision for autonomous vehicles, to date, no general survey on deep learning applied in LiDAR point clouds for autonomous  ...  Besides, we also would like to thank anonymous reviewers for their insightful comments and suggestions.  ... 
arXiv:2005.09830v1 fatcat:zrja5sgtsvgulpnp7p7t4kxq54

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [article]

Yanan Zhang, Di Huang, Yunhong Wang
2020 arXiv   pre-print
LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects.  ...  On the other hand, a graph neural network module is designed, which comprehensively captures relations among points through a local-global attention mechanism as well as multi-scale graph based context  ...  features for 3D object detection, which proves a promising way.  ... 
arXiv:2012.10412v3 fatcat:sku7ehn5xrbzxlpxsn6fm7ue7i

Review: Deep Learning on 3D Point Clouds

Saifullahi Aminu Bello, Shangshu Yu, Cheng Wang, Jibril Muhmmad Adam, Jonathan Li
2020 Remote Sensing  
A point cloud is a set of points defined in a 3D metric space.  ...  Point clouds have become one of the most significant data formats for 3D representation and are gaining increased popularity as a result of the increased availability of acquisition devices, as well as  ...  Most current object detection relies on 2D detection for region proposal; few works are available on detecting objects directly with point clouds.  ... 
doi:10.3390/rs12111729 fatcat:hitwxgdfp5avrdaqrjxlialwou

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points [article]

Liang Pan, Chee-Meng Chew, Gim Hee Lee
2019 arXiv   pre-print
Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently  ...  exploiting multi-scale edge features in point clouds.  ...  [28] introduced the feature pyramid network for object detection.  ... 
arXiv:1907.09798v2 fatcat:gpyul44syfdbxfznbjmewjpdfa

3D Point Cloud Processing and Learning for Autonomous Driving [article]

Siheng Chen and Baoan Liu and Chen Feng and Carlos Vallespi-Gonzalez and Carl Wellington
2020 arXiv   pre-print
We present a review of 3D point cloud processing and learning for autonomous driving.  ...  As one of the most important sensors in autonomous vehicles, light detection and ranging (LiDAR) sensors collect 3D point clouds that precisely record the external surfaces of objects and scenes.  ...  Inspired by the success of graph neural networks in social network analysis, numerous recent research incorporate graph neural networks to handle a 3D point cloud.  ... 
arXiv:2003.00601v1 fatcat:w3sxkiupo5avhlbrstugqkohqy

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis [article]

Ben Fei, Weidong Yang, Wenming Chen, Zhijun Li, Yikang Li, Tao Ma, Xing Hu, Lipeng Ma
2022 arXiv   pre-print
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision.  ...  Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc.  ...  The 3D object detection relies on complete point clouds to keep state-of-the-art (SOTA) performance.  ... 
arXiv:2203.03311v2 fatcat:e2kvryolufearetp4ujlw2gwwy

LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks

Hang Zhou, Dongdong Chen, Jing Liao, Kejiang Chen, Xiaoyi Dong, Kunlin Liu, Weiming Zhang, Gang Hua, Nenghai Yu
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To overcome these shortcomings, this paper proposes a novel label guided adversarial network (LG-GAN) for real-time flexible targeted point cloud attack.  ...  Deep neural networks have made tremendous progress in 3D point-cloud recognition.  ...  Input points Graph Discriminator D To help generate a more realistic adversarial point cloud, we further leverage a graph discriminator network D for adversarial learning.  ... 
doi:10.1109/cvpr42600.2020.01037 dblp:conf/cvpr/ZhouC0CDLZ0Y20 fatcat:j2leifzi2vhjvovv6hesskbfi4

Learning to Segment 3D Point Clouds in 2D Image Space

Yecheng Lyu, Xinming Huang, Ziming Zhang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
With the help of the Delaunay triangulation for graph construction from point clouds and a multi-scale U-Net for segmentation, we manage to demonstrate the state-of-the-art performance on ShapeNet and  ...  such point clouds into a 2D image space so that traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation.  ...  Spectral SpecTN point cloud onto a 2D image space. Network Architectures. Network operations are the key to hierarchically learn the local context and perform semantic segmentation on point clouds.  ... 
doi:10.1109/cvpr42600.2020.01227 dblp:conf/cvpr/Lyu0Z20 fatcat:hf3jonjdnngtpeo7xuqv3y27ty
« Previous Showing results 1 — 15 out of 7,066 results