A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
[article]
2019
arXiv
pre-print
Preserved Fulltext
Other Versions
In this paper, we propose PointRCNN for 3D object detection from raw point cloud. ...
Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals ...
PointRCNN for Point Cloud 3D Detection In this section, we present our proposed two-stage detection framework, PointRCNN, for detecting 3D objects from irregular point cloud. ...
arXiv:1812.04244v2
fatcat:qadjesz2l5d6hjti6ehzzakcma
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose PointRCNN for 3D object detection from raw point cloud. ...
Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals ...
PointRCNN for Point Cloud 3D Detection In this section, we present our proposed two-stage detection framework, PointRCNN, for detecting 3D objects from irregular point cloud. ...
doi:10.1109/cvpr.2019.00086
dblp:conf/cvpr/ShiWL19
fatcat:zvpklt5f5bekdlaikvj6p2cbky
A Density-Aware PointRCNN for 3D Object Detection in Point Clouds
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2009.05307v1 fatcat:g4ew2q2xhvdrfadtvj5hj3idhy
We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. ...
An uncertainty-based sampling policy is proposed to deal with the distribution differences of different point clouds. ...
Conclusion We have presented DA-PointRCNN, an improved version of PointRCNN for 3D object detection from point clouds. ...
arXiv:2009.05307v2
fatcat:tysspeuk3nfdtiq5didlc6wx7q
TSF: Two-Stage Sequential Fusion for 3D Object Detection
2022
IEEE Sensors Journal
Preserved Fulltext
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.
However, it is surprisingly difficult to effectively design fusion location and fusion strategies for point cloud-based 3D object detection networks. ...
In the first stage of fusion, TSF generates the enhanced point cloud by combining the raw point cloud and semantic information of image instance segmentation. ...
We input the enhanced point cloud from the first fusion stage into PointRCNN [3] and fused the region proposals from PointRCNN with 2D detection boxes in C-D NMS. ...
doi:10.1109/jsen.2022.3175192
fatcat:fdjdftrsxjhy3jdmu7b2kv45xe
Robust 3D Object Detection in Cold Weather Conditions
[article]
2022
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
We address this issue in two steps: First, we present a gas exhaust data generation method based on 3D surface reconstruction and sampling which allows us to generate large sets of gas exhaust clouds from ...
Finally, we formulate a new training loss term that leverages the augmented point cloud to increase object detection robustness by penalizing predictions that include noise. ...
Twostage detectors generate proposals for objects in the point cloud and in a second stage refine them, resulting in slower but more accurate detections. ...
arXiv:2205.11925v1
fatcat:tf7ccp6pxzgf7b4djhnkw7wuxy
A LiDAR–Camera Fusion 3D Object Detection Algorithm
2022
Information
Preserved Fulltext
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.
Secondly, an attention-based fusion sub-network is designed to fuse the features extracted by the 2D backbone and the features extracted from 3D LiDAR point clouds by PointNet++. ...
This work proposes a deep neural network (namely FuDNN) for LiDAR–camera fusion 3D object detection. Firstly, a 2D backbone is designed to extract features from camera images. ...
For instance, MV3D [24] generated 3D object proposals from BEVs, which were projected to BEVs, FVs, and image views. ...
doi:10.3390/info13040169
fatcat:v5i43ryt7jewvo2oriof3jf6iy
Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection
2021
2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We propose a novel Detection Aware 3D Semantic Segmentation (DASS) framework that explicitly leverages localization features from an auxiliary 3D object detection task. ...
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 ...
We further investigate the yet unexplored problem of multitask learning of 3D semantic segmentation and 3D object detection from point clouds. ...
doi:10.1109/wacv48630.2021.00299
fatcat:hoiw4jog75em5ie3usfo2hpsg4
DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we put forward a novel density-oriented PointNet (DPointNet) for 3D object detection in point clouds, in which the density of points increases layer by layer. ...
In experiments for object detection, the DPointNet is applied to PointRCNN, and the results show that the model with the new operator can achieve better performance and higher speed than the baseline PointRCNN ...
The point clouds from LiDAR are adopted in many 3D detection methods, and the range information is much more accurate and stable than that of camera images. ...
arXiv:2102.03747v1
fatcat:qlvhl343czfarfrfyx4wqfjupa
Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We propose a novel Detection Aware 3D Semantic Segmentation (DASS) framework that explicitly leverages localization features from an auxiliary 3D object detection task. ...
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 ...
We further investigate the yet unexplored problem of multitask learning of 3D semantic segmentation and 3D object detection from point clouds. ...
arXiv:2009.10569v3
fatcat:q4ukkdnzkzcvpbn6l5luryw3vi
Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks. ...
Especially for outdoor scenes, the problem becomes more severe due to the sparseness of the point cloud and the complexity of urban scenes. ...
PROPOSED METHOD
Preliminaries Our method directly uses the original point cloud as input. We divide our detection goal into classify objects in the 3D scene and locate their 3D bounding boxes. ...
arXiv:2108.06649v1
fatcat:vvp2etajsff6xd5x33yoogtamm
Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2103.03977v2 fatcat:u7hztbadzng7lkjd7iblrrkdviOther Versions
From 2D to 3D object detection, the most difficult is to determine the distance from the ego-vehicle to objects. ...
This paper presents SLS-Fusion, a new approach to fuse data from 4-beam LiDAR and a stereo camera via a neural network for depth estimation to achieve better dense depth maps and thereby improves 3D object ...
Detecting and localizing objects in 3D from 2D is challenging. ...
arXiv:2103.03977v3
fatcat:5iahola2yjf7lmteq4s3jieteq
3D Object Detection from Point Cloud Based on Deep Learning
2022
Wireless Communications and Mobile Computing
Preserved Fulltext
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.
In order to study the modern 3D object detection algorithm based on deep learning, this paper studies the point-based 3D object detection algorithm, that is, a 3D object detection algorithm that uses multilayer ...
This paper proposes a method based on point RCNN. A three-stage 3D object detection algorithm improves the accuracy of the algorithm by fusing image information. ...
PointRCNN [18] proposes a new way of generating 3D proposal candidate frames from point clouds. ...
doi:10.1155/2022/6228797
fatcat:7lfq5ytfynhovgzxdt5dr6h3sa
PointPainting: Sequential Fusion for 3D Object Detection
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
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.
The appended (painted) point cloud can then be fed to any lidaronly method. ...
The painted version of PointRCNN represents a new state of the art on the KITTI leaderboard for the bird's-eye view detection task. ...
Acknowledgements We thank Donghyeon Won, Varun Bankiti and Venice Liong for help with the semantic segmentation model for nuScenes, and Holger Caesar for access to nuImages. ...
doi:10.1109/cvpr42600.2020.00466
dblp:conf/cvpr/VoraLHB20
fatcat:rwfqdmwgendaxlbf4rgrkeyc64
PointPainting: Sequential Fusion for 3D Object Detection
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The appended (painted) point cloud can then be fed to any lidar-only method. ...
The painted version of PointRCNN represents a new state of the art on the KITTI leaderboard for the bird's-eye view detection task. ...
Acknowledgements We thank Donghyeon Won, Varun Bankiti and Venice Liong for help with the semantic segmentation model for nuScenes, and Holger Caesar for access to nuImages. ...
arXiv:1911.10150v2
fatcat:vr7v6my26bbpbkjl7egkhqekty
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving
[article]
2022
arXiv
pre-print
Preserved Fulltext
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.
Other Versions
Our results show that sensor placement is non-negligible in 3D point cloud-based object detection, which will contribute up to 10% performance discrepancy in terms of average precision in challenging 3D ...
To this end, we introduce an easy-to-compute information-theoretic surrogate metric to quantitatively and fast evaluate LiDAR placement for 3D detection of different types of objects. ...
Pointr- cnn: 3d object proposal generation and detection from point cloud. ...
arXiv:2105.00373v4
fatcat:xqwxkpbmrrcp3ecsewptsit3li
« Previous
Showing results 1 — 15 out of 352 results