11 Hits in 2.3 sec

ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving [article]

Xibin Song, Peng Wang, Dingfu Zhou, Rui Zhu, Chenye Guan, Yuchao Dai, Hao Su, Hongdong Li, Ruigang Yang
2018 arXiv   pre-print
In this paper, we contribute the first large-scale database suitable for 3D car instance understanding - ApolloCar3D.  ...  This task, while critical, is still under-researched in the computer vision community - partially owing to the lack of large scale and fully-annotated 3D car database suitable for autonomous driving research  ...  The authors gratefully acknowledge He Jiang from Baidu Research for car visualization using obtained poses.  ... 
arXiv:1811.12222v2 fatcat:3eu7nofbevbenkpdxddufya7w4

PerMO: Perceiving More at Once from a Single Image for Autonomous Driving [article]

Feixiang Lu, Zongdai Liu, Xibin Song, Dingfu Zhou, Wei Li, Hui Miao, Miao Liao, Liangjun Zhang, Bin Zhou, Ruigang Yang, Dinesh Manocha
2020 arXiv   pre-print
We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image for autonomous driving.  ...  We present a new part-based deformable vehicle model that is used for instance segmentation and automatically generate a dataset that contains dense correspondences between 2D images and 3D models.  ...  ApolloCar3D is a large-scale 3D instance car dataset built from real images captured in complex real-world driving scenes in multiple cities and targets 3D car understanding research in self-driving scenarios  ... 
arXiv:2007.08116v1 fatcat:ex4fbnzyjbckhmah2wnykury5q

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision [article]

Lei Ke, Shichao Li, Yanan Sun, Yu-Wing Tai, Chi-Keung Tang
2020 arXiv   pre-print
We present a novel end-to-end framework named as GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view.  ...  We evaluate GSNet on the largest multi-task ApolloCar3D benchmark and achieve state-of-the-art performance both quantitatively and qualitatively.  ...  scale of autonomous driving datasets.  ... 
arXiv:2007.13124v1 fatcat:nc23kh23dngz7ox5jp25sojd2i

Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset [article]

Liqiang Lin and Yilin Liu and Yue Hu and Xingguang Yan and Ke Xie and Hui Huang
2022 arXiv   pre-print
We present UrbanScene3D, a large-scale data platform for research of urban scene perception and reconstruction.  ...  The dataset also contains high-precision LiDAR scans and hundreds of image sets with different observation patterns, which provide a comprehensive benchmark to design and evaluate aerial path planning  ...  In this context, our released UrbanScene3D provides rich, large scale 3D urban scene building annotation data for outdoor instance segmentation research.  ... 
arXiv:2107.04286v2 fatcat:ikhnodq3tzfyrgno7ynjg3pgtm

Argoverse: 3D Tracking and Forecasting With Rich Maps

Ming-Fang Chang, Deva Ramanan, James Hays, John Lambert, Patsorn Sangkloy, Jagjeet Singh, Slawomir Bak, Andrew Hartnett, De Wang, Peter Carr, Simon Lucey
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1 : We introduce a dataset for 3D tracking and forecasting with rich maps for autonomous driving.  ...  We use 3D object tracking to "mine" for more than 300k interesting vehicle trajectories to create a trajectory forecasting benchmark.  ...  Patsorn Sangkloy is supported by a a Royal Thai Government Scholarship.  ... 
doi:10.1109/cvpr.2019.00895 dblp:conf/cvpr/ChangLSSBHW0LRH19 fatcat:i7fzdt2kkzhwhlo372acqmq2p4

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
2021 IEEE Access  
180 portant role for support in autonomous driving systems.  ...  However, recognizing a vehicle as a 2D BB is not always sufficient for perfect autonomous driving.  ... 
doi:10.1109/access.2021.3114399 fatcat:kvdwsslqxff3lkh27tsdsciqma

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association [article]

Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi
2021 arXiv   pre-print
We also show that our method generalizes to any class of semantic keypoints such as car and animal parts to provide a holistic perception framework that is well suited for urban mobility such as self-driving  ...  cars and delivery robots.  ...  We also thank our lab members and reviewers for their valuable comments.  ... 
arXiv:2103.02440v2 fatcat:utj3lczi7rbqri6ntt2um2quc4

An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots [article]

Marcos V. Conde
2021 arXiv   pre-print
Developing an AI able to drive a car without human intervention and a small robot to deliver packages in the city may seem like different problems, nevertheless from the point of view of perception and  ...  Autonomous robots are currently one of the most popular Artificial Intelligence problems, having experienced significant advances in the last decade, from Self-driving cars and humanoids to delivery robots  ...  Apollocar3d: A large 3d car instance understanding benchmark for autonomous driving.  ... 
arXiv:2112.05534v2 fatcat:3drhsxelvvdwvpsq5rvfpnukam

Argoverse: 3D Tracking and Forecasting with Rich Maps [article]

Ming-Fang Chang, John Lambert, Patsorn Sangkloy, Jagjeet Singh, Slawomir Bak, Andrew Hartnett, De Wang, Peter Carr, Simon Lucey, Deva Ramanan, James Hays
2019 arXiv   pre-print
Argoverse was collected by a fleet of autonomous vehicles in Pittsburgh and Miami.  ...  The Argoverse Motion Forecasting dataset includes more than 300,000 5-second tracked scenarios with a particular vehicle identified for trajectory forecasting.  ...  We thank our Argo AI colleagues for their invaluable assistance in supporting Argoverse. Patsorn Sangkloy is supported by a a Royal Thai Government Scholarship.  ... 
arXiv:1911.02620v1 fatcat:dnyuhwnk7vcwnpaa3n5gyibkau

A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning [article]

Xuan Di, Rongye Shi
2020 arXiv   pre-print
While reviewing the methodologies, we primarily focus on the following research questions: (1) What scalable driving policies are to control a large number of AVs in mixed traffic comprised of human drivers  ...  (3) How should the driving behavior of uncontrollable AVs be modeled in the environment? (4) How are the interactions between human drivers and autonomous vehicles characterized?  ...  Acknowledgments The authors would like to thank Data Science Institute from Columbia University for providing a seed grant for this research.  ... 
arXiv:2007.05156v1 fatcat:6pr3en5opfguje77wpa4dwr6pi

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
Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics.  ...  To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.  ...  Therefore, it is the preferred representation for many scene understanding related applications such as autonomous driving and robotics.  ... 
arXiv:1912.12033v2 fatcat:qiiyvvuulfccxaiihf2mu23k34