Filters








39 Hits in 2.1 sec

GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving [article]

Buyu Li, Wanli Ouyang, Lu Sheng, Xingyu Zeng, Xiaogang Wang
<span title="2019-03-27">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving.  ...  Leveraging the off-the-shelf 2D object detector, we propose an artful approach to efficiently obtain a coarse cuboid for each predicted 2D box.  ...  This paper proposes an efficient framework based on 3D guidance and using the surface feature for refinement (GS3D) to detect complete 3D object content using only monocular RGB image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.10955v2">arXiv:1903.10955v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2juo4w7mqzbjlkh2av2raarsyu">fatcat:2juo4w7mqzbjlkh2av2raarsyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907174428/https://arxiv.org/pdf/1903.10955v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/78/80/78808bd9c712b959344df278398860e038368347.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.10955v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Reinforced Axial Refinement Network for Monocular 3D Object Detection [article]

Lijie Liu, Chufan Wu, Jiwen Lu, Lingxi Xie, Jie Zhou, Qi Tian
<span title="2020-08-31">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image.  ...  To improve the efficiency of sampling, we propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step.  ...  However, these methods require the CAD model of the objects for fine correction and cannot be used in autonomous driving directly.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.13748v1">arXiv:2008.13748v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5eorvtrt3fgtzmyhetqkxmbr4a">fatcat:5eorvtrt3fgtzmyhetqkxmbr4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902084350/https://arxiv.org/pdf/2008.13748v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.13748v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving [article]

Peixuan Li, Huaici Zhao, Pengfei Liu, Feidao Cao
<span title="2020-01-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose an efficient and accurate monocular 3D detection framework in single shot.  ...  Training our method only uses the 3D properties of the object without the need for external networks or supervision data.  ...  Introduction 3D object detection is an essential component of scene perception and motion prediction in autonomous driving [2, 10] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03343v1">arXiv:2001.03343v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v34dca7k4vat3hp57yjfzt5d5y">fatcat:v34dca7k4vat3hp57yjfzt5d5y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321103511/https://arxiv.org/pdf/2001.03343v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03343v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training [article]

Peixuan Li
<span title="2020-09-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net.  ...  And also, to the best of our knowledge, this is the first time that semi-supervised learning is applied in monocular 3D objects detection.  ...  Introduction This work focuses on 3D object detection using only monocular RGB image for autonomous driving. 3D object detection plays an essential role in serving autonomous vehicle perception and robotic  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.00764v1">arXiv:2009.00764v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b7pxmgowrngbvnvqql3ymstxbm">fatcat:b7pxmgowrngbvnvqql3ymstxbm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200909013126/https://arxiv.org/pdf/2009.00764v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.00764v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

3D Object Detection for Autonomous Driving: A Survey [article]

Rui Qian, Xin Lai, Xirong Li
<span title="2021-06-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Autonomous driving is regarded as one of the most promising remedies to shield human beings from severe crashes.  ...  To this end, 3D object detection serves as the core basis of such perception system especially for the sake of path planning, motion prediction, collision avoidance, etc.  ...  (Data from Google trends by searching key word: "3d object detection autonomous driving".)  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10823v1">arXiv:2106.10823v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eo4jyjwxezbcjo57qgzkqe5kbq">fatcat:eo4jyjwxezbcjo57qgzkqe5kbq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210623084323/https://arxiv.org/pdf/2106.10823v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ef/d0/efd0281156c9206d3eca01c34db745ad65db903e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10823v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection

Seong-heum Kim, Youngbae Hwang
<span title="2021-02-22">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikdpfme5h5egvnwtvvtjrnntyy" style="color: black;">Electronics</a> </i> &nbsp;
In addition, we discuss the effectiveness of the detection models on their baseline benchmarks. Finally, we explore several directions for future research on monocular 3D object detection.  ...  Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized.  ...  Acknowledgments: The first author sincerely appreciates Min-ho Lee and Hoo-kyeong Lee at KETI for valuable discussion. Conflicts of Interest: The authors declare no conflict of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10040517">doi:10.3390/electronics10040517</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rziqhrkefvelpg3vgb6qxfprte">fatcat:rziqhrkefvelpg3vgb6qxfprte</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210313074208/https://res.mdpi.com/d_attachment/electronics/electronics-10-00517/article_deploy/electronics-10-00517-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/07/6b/076b052fe9aa43e1f8619cc9e8aab29966a32f6d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10040517"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation [article]

Yingjie Cai, Buyu Li, Zeyu Jiao, Hongsheng Li, Xingyu Zeng, Xiaogang Wang
<span title="2021-06-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Compared to the widely-used 3D bounding box proposals, it is shown to be a better representation for 3D detection.  ...  Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images.  ...  Introduction 3D object detection is an important computer vision task since it is an essential component of autonomous driving and robot perception to avoid collisions with surrounding objects.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.01619v2">arXiv:2002.01619v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fxjuql7ja5gmxgdnamlip72nru">fatcat:fxjuql7ja5gmxgdnamlip72nru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210612031429/https://arxiv.org/pdf/2002.01619v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/76/dc76f532fa0918ab4282805c04d6ef10a549f8bf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.01619v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

Yingjie Cai, Buyu Li, Zeyu Jiao, Hongsheng Li, Xingyu Zeng, Xiaogang Wang
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
Compared to the widely-used 3D bounding box proposals, it is shown to be a better representation for 3D detection.  ...  Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images.  ...  Introduction 3D object detection is an important computer vision task since it is an essential component of autonomous driving and robot perception to avoid collisions with surrounding objects.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.6618">doi:10.1609/aaai.v34i07.6618</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bhjoz3tntjadtalwyi5a4dcazm">fatcat:bhjoz3tntjadtalwyi5a4dcazm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103160716/https://aaai.org/ojs/index.php/AAAI/article/download/6618/6472" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7f/cf/7fcfd9c510b807125ad9b7f96869e2566770ca54.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.6618"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation [article]

Zechen Liu, Zizhang Wu, Roland Tóth
<span title="2020-02-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving.  ...  Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables  ...  Our proposed SMOKE 3D detection framework achieves promising accuracy and efficiency, which can be further extended and used on autonomous vehicles and in robotic navigation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.10111v1">arXiv:2002.10111v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pytrnbnepbcdrdgyqzapnznlm4">fatcat:pytrnbnepbcdrdgyqzapnznlm4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321180216/https://arxiv.org/pdf/2002.10111v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.10111v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time [article]

Xichuan Zhou, Yicong Peng, Chunqiao Long, Fengbo Ren, Cong Shi
<span title="2020-06-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The MoNet3D algorithm is a novel and effective framework that can predict the 3D position of each object in a monocular image and draw a 3D bounding box for each object.  ...  Monocular multi-object detection and localization in 3D space has been proven to be a challenging task.  ...  Embedded devices are often used in the field of autonomous driving, so there are very high requirements for energy efficiency.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16007v1">arXiv:2006.16007v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/icbn75qefjfxxl777ahs7vyf4e">fatcat:icbn75qefjfxxl777ahs7vyf4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200703202713/https://arxiv.org/pdf/2006.16007v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4a/78/4a78be95eed8ae1a297e7900e9b560be73dd065d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16007v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Comprehensive Review on 3D Object Detection and 6D Pose Estimation with Deep Learning

Sabera Hoque, MD. Yasir Arafat, Shuxiang Xu, Ananda Maiti, Yuchen Wei
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Li [139] has come 970 up with an idea called GS3D, a 3DOD method based on an RGB (single) image in autonomous driving.  ...  180 portant role for support in autonomous driving systems.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3114399">doi:10.1109/access.2021.3114399</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kvdwsslqxff3lkh27tsdsciqma">fatcat:kvdwsslqxff3lkh27tsdsciqma</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210930191317/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09543652.pdf?tp=&amp;arnumber=9543652&amp;isnumber=6514899&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9f/7c/9f7cbc96e6b884961248693479258186ad82ef57.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3114399"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies [article]

Yu Huang, Yue Chen
<span title="2020-07-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Due to the limited space, we focus the analysis on several key areas, i.e. 2D and 3D object detection in perception, depth estimation from cameras, multiple sensor fusion on the data, feature and task  ...  This is a survey of autonomous driving technologies with deep learning methods.  ...  Besides, there are special objects for autonomous driving to detect/classify, i.e. lane and road markings, traffic sign and traffic light.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.06091v3">arXiv:2006.06091v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nhdgivmtrzcarp463xzqvnxlwq">fatcat:nhdgivmtrzcarp463xzqvnxlwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710071048/https://arxiv.org/ftp/arxiv/papers/2006/2006.06091.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ea/69/ea691e79e5986f5d62bde9604bf651d046c95458.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.06091v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

3D Bounding Box Estimation for Autonomous Vehicles by Cascaded Geometric Constraints and Depurated 2D Detections Using 3D Results [article]

Jiaojiao Fang, Lingtao Zhou, Guizhong Liu
<span title="2019-09-01">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
3D object detection is one of the most important tasks in 3D vision perceptual system of autonomous vehicles.  ...  In this paper, we propose a novel two stage 3D object detection method aimed at get the optimal solution of object location in 3D space based on regressing two additional 3D object properties by a deep  ...  object detection by the data collected from autonomous driving scenarios, such as KITTI dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.01867v1">arXiv:1909.01867v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3f75hm47abeq5hhttjpucykvlu">fatcat:3f75hm47abeq5hhttjpucykvlu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824035026/https://arxiv.org/ftp/arxiv/papers/1909/1909.01867.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/da/87/da8735f83657a3077ee82d085364eba8cc3064c4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.01867v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR [article]

Ziyue Feng, Longlong Jing, Peng Yin, Yingli Tian, Bing Li
<span title="2021-11-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With the accurate dense depth prediction, our model outperforms the state-of-the-art sparse-LiDAR-based method (Pseudo-LiDAR++) by more than 68% for the downstream task monocular 3D object detection on  ...  Then, an efficient feed-forward refine network is further designed to correct the errors in these initial depth maps in pseudo-3D space with real-time performance.  ...  Introduction Obtaining the 3D location of objects is an essential task for autonomous robots.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.09628v4">arXiv:2109.09628v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jtm7rogh2nffpc6t237vmwh3ba">fatcat:jtm7rogh2nffpc6t237vmwh3ba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211103155211/https://arxiv.org/pdf/2109.09628v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/37/fd/37fdcc53cdfcd0a93d1122b66f21490ebc365ced.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.09628v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving [article]

Jean Marie Uwabeza Vianney, Shubhra Aich, Bingbing Liu
<span title="2019-11-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we strive for solving the ambiguities arisen by the astoundingly high density of raw PseudoLiDAR for monocular 3D object detection for autonomous driving.  ...  Without much computational overhead, we propose a supervised and an unsupervised sparsification scheme of PseudoLiDAR prior to 3D detection.  ...  nostic sparsifications demonstrate the necessity of data orchestration alongside architectural enhancement, especially for generated data like PseudoLiDAR.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.09712v1">arXiv:1911.09712v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hkujln2w35awbjgcram6cx6a6a">fatcat:hkujln2w35awbjgcram6cx6a6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200909012544/https://arxiv.org/pdf/1911.09712v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b4/92/b4924d967c13036cb77403986edb2bc08d86673f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.09712v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 39 results