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
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Detecting objects such as cars and pedestrians in 3D plays an indispensable role in autonomous driving. Existing approaches largely rely on expensive LiDAR sensors for accurate depth information. ...
In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation. ...
We are thankful for generous support by Zillow and SAP America Inc. We thank Gao Huang for helpful discussion. ...
arXiv:1906.06310v3
fatcat:wybv6cyqjrdexov66fkw42vudq
Rethinking Pseudo-LiDAR Representation
[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.
In this paper, we perform an in-depth investigation and observe that the efficacy of pseudo-LiDAR representation comes from the coordinate transformation, instead of data representation itself. ...
3D detection performance. ...
Introduction 3D object detection has received increasing attention from both industry and academia because of its wide applications in various fields such as autonomous driving and robotics. ...
arXiv:2008.04582v1
fatcat:k4spphwz45hjtpifiy3fx763de
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
[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
3D object detection is an essential task in autonomous driving. ...
At the time of submission our algorithm holds the highest entry on the KITTI 3D object detection leaderboard for stereo-image-based approaches. ...
We are thankful for generous support by Zillow and SAP America Inc. We thank Gao Huang for helpful discussion. ...
arXiv:1812.07179v6
fatcat:kxknnppa7nb63nfopj6n2zc7ge
Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud
[article]
2019
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
Following the pipeline of two-stage 3D detection algorithms, we detect 2D object proposals in the input image and extract a point cloud frustum from the pseudo-LiDAR for each proposal. ...
Then we can train a LiDAR-based 3D detection network with our pseudo-LiDAR end-to-end. ...
We show that, from only a single RGB image, the 3D bounding box detection for the car category can be very accurate, even for the challenging faraway objects (e.g., in the 6th row 1st column and 8th row ...
arXiv:1903.09847v4
fatcat:vwqdxubedzddnkeuos6eqqgsny
FPPN: Future Pseudo-LiDAR Frame Prediction for Autonomous Driving
[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.
LiDAR sensors are widely used in autonomous driving due to the reliable 3D spatial information. However, the data of LiDAR is sparse and the frequency of LiDAR is lower than that of cameras. ...
The future pseudo-LiDAR frame can be obtained by converting the predicted dense depth map into corresponding 3D point clouds. ...
.: Pseudo-lidar from visual depth estimation: Bridging the
gap in 3d object detection for autonomous driving. ...
arXiv:2112.04401v1
fatcat:ldy6xiv7zfctzk4adx5ikqqute
Pseudo-LiDAR Based Road 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.
Other Versions
Specifically, we exploit pseudo-LiDAR using depth estimation, and propose a feature fusion network where RGB and learned depth information are fused for improved road detection. ...
Road detection is a critically important task for self-driving cars. By employing LiDAR data, recent works have significantly improved the accuracy of road detection. ...
Pseudo-LiDAR Based Road Detection Libo Sun, Haokui Zhang, and Wei Yin Abstract-Road detection is a critically important task for self-driving cars. ...
arXiv:2107.13279v1
fatcat:452a5sbvd5e2rao7rc44e6rec4
Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?
[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.
In this paper, we dive deep into the pseudo Lidar representation and argue that the performance of 3D object detection is not fully dependent on the high precision stereo depth estimation. ...
We demonstrate that even for the unreliable depth estimation, with proper data processing and refining, it can achieve comparable 3D object detection accuracy. ...
INTRODUCTION T HREE -dimensional (3D) object detection is an essential vision task in scene perception and motion prediction of autonomous driving. ...
arXiv:2206.13858v1
fatcat:6fzpg4oax5hirghtk7tobofa2q
Is Pseudo-Lidar needed for Monocular 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.
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. ...
In this work, we propose an end-to-end, single stage, monocular 3D object detector, DD3D, that can benefit from depth pre-training like pseudo-lidar methods, but without their limitations. ...
We evaluate depth quality against the 3D detection accuracy of the PL detector, with results shown in Figure 5 . ...
arXiv:2108.06417v1
fatcat:bh6utkslwvcmvleslbdj5lmxr4
End-to-End Pseudo-LiDAR for Image-Based 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
Reliable and accurate 3D object detection is a necessity for safe autonomous driving. ...
PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. ...
We are thankful for generous support by Zillow and SAP America Inc. ...
arXiv:2004.03080v2
fatcat:67u6xcafufambnciirggtotfdy
PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
2020
Sensors
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.
LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10 Hz) and have been widely applied in the field of autonomous driving and unmanned aerial vehicle (UAV). ...
To the best of our knowledge, this is the first deep framework for Pseudo-LiDAR point cloud interpolation, which shows appealing applications in navigation systems equipped with LiDAR and cameras. ...
Recently, in 3D object detection [1] [2] [3] , 3D semantic segmentation [4] [5] [6] , and depth completion tasks [7] [8] [9] [10] , point clouds obtained by LiDAR have gained more and more attention ...
doi:10.3390/s20061573
pmid:32178238
fatcat:5ojkphujlffxrou3b7ixl54esy
PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
[article]
2019
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.
LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10Hz) and have been widely applied in the field of autonomous driving and UAV. ...
To the best of our knowledge, this is the first deep framework for Pseudo-LiDAR point cloud interpolation, which shows appealing applications in navigation systems equipped with LiDAR and cameras. ...
Recently, in 3D object detection [15] , [18] , 3D semantic segmentation [23] , [24] , and depth completion tasks [12] , [16] , [21] , point clouds obtained by LiDAR have gained more and more attention ...
arXiv:1909.07137v1
fatcat:36r3madncnf5fmz5orrj3mngsa
Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 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.
Other Versions
Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the ...
The source of the bias resides in an overlap between the KITTI3D object detection validation set and the training/validation sets used to train depth predictors feeding PL-based methods. ...
We also thank Xinzhu Ma, Wanli Ouyang and Garrick Brazil for sharing their detections and for helpful discussions. ...
arXiv:2012.05796v2
fatcat:elob3swa7vayld4zxuyg6q7zby
End-to-End Pseudo-LiDAR for Image-Based 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.
Reliable and accurate 3D object detection is a necessity for safe autonomous driving. ...
PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. ...
We are thankful for generous support by Zillow and SAP America Inc. ...
doi:10.1109/cvpr42600.2020.00592
dblp:conf/cvpr/QianG0YBHCWC20
fatcat:rrodzozyj5bzfkg73im6jzerlm
Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision
[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.
Pseudo-LiDAR point cloud interpolation is a novel and challenging task in the field of autonomous driving, which aims to address the frequency mismatching problem between camera and LiDAR. ...
point clouds in 3D space. ...
For these applications, the accurate and dense depth information is crucial for the obstacle avoidance [1] , object detection [2] , [3] , and 3D scene reconstruction tasks [4] . ...
arXiv:2006.11481v1
fatcat:flo4tivmvreennf74hytqk3jre
Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?
2021
Zenodo
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.
Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the ...
The source of the bias resides in an overlap between the KITTI3D object detection validation set and the training/validation sets used to train depth predictors feeding PL-based methods. ...
We also thank Xinzhu Ma, Wanli Ouyang and Garrick Brazil for sharing their detections and for helpful discussions. E. ...
doi:10.5281/zenodo.5795265
fatcat:j7taqyt22zbo5bhqlzwsv3xkye
« Previous
Showing results 1 — 15 out of 155 results