自动驾驶 - arXivDaily 专题

2210.01436 2022-10-05 cs.CV 57%

Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching

Yasuhiro Yao, Ryoichi Ishikawa, Shingo Ando, Kana Kurata, Naoki Ito, Jun Shimamura, Takeshi Oishi

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments 15 pages, 13 figures

Journal ref in IEEE Access, vol. 9, pp. 136674-136686, 2021

2210.00519 2022-10-04 cs.CV 57%

Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking

Yubo Cui, Jiayao Shan, Zuoxu Gu, Zhiheng Li, Zheng Fang

专题命中感知：BEV(abstract)；分类 cs.CV

Comments Accepted for publication at IEEE Robotics and Automation Letters (RAL)

2205.12519 2022-10-04 cs.CV 57%

Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset

Sushruth Nagesh, Asfiya Baig, Savitha Srinivasan, Akshay Rangesh, Mohan Trivedi

专题命中感知：autonomous driving(abstract)；分类 cs.CV

2209.12836 2022-09-27 cs.CV 57%

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps

Yue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong, Siheng Chen

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments 24 pages, 19 figures, Accepted by Neurips 2022

2209.12419 2022-09-27 cs.CV cs.LG 57%

Feature-based model selection for object detection from point cloud data

Kairi Tokuda, Ryoichi Shinkuma, Takehiro Sato, Eiji Oki

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments Submitted to IEICE Transactions on Communications

2209.11972 2022-09-27 cs.CV 57%

Ground then Navigate: Language-guided Navigation in Dynamic Scenes

Kanishk Jain, Varun Chhangani, Amogh Tiwari, K. Madhava Krishna, Vineet Gandhi

专题命中感知：autonomous driving(abstract)；分类 cs.CV

2207.02605 2022-09-27 cs.CV 57%

GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation

Haibo Qiu, Baosheng Yu, Dacheng Tao

专题命中感知：BEV(abstract)；分类 cs.CV

Comments Published in Transactions on Machine Learning Research (09/2022)

2011.11814 2022-09-22 cs.CV 57%

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

Felix Wimbauer, Nan Yang, Lukas von Stumberg, Niclas Zeller, Daniel Cremers

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments CVPR 2021, Project page with video can be found under https://vision.in.tum.de/research/monorec. 14 pages, 10 figures, 5 tables

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 6112-6122

2209.08608 2022-09-20 cs.RO 57%

HGI-SLAM: Loop Closure With Human and Geometric Importance Features

Shuhul Mujoo, Jerry Ng

专题命中感知：LiDAR(abstract)；分类 cs.RO

Comments 7 pages, 4 figures

2209.07419 2022-09-16 cs.CV 57%

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

Chaokang Jiang, Guangming Wang, Jinxing Wu, Yanzi Miao, Hesheng Wang

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments 7 pages, 4 figures; under review

2206.15407 2022-09-16 cs.LG cs.AI stat.ML 57%

Shifts 2.0: Extending The Dataset of Real Distributional Shifts

Andrey Malinin, Andreas Athanasopoulos, Muhamed Barakovic, Meritxell Bach Cuadra, Mark J. F. Gales, Cristina Granziera, Mara Graziani, Nikolay Kartashev, Konstantinos Kyriakopoulos, Po-Jui Lu, Nataliia Molchanova, Antonis Nikitakis, Vatsal Raina, Francesco La Rosa, Eli Sivena, Vasileios Tsarsitalidis, Efi Tsompopoulou, Elena Volf

专题命中感知：autonomous driving(abstract)；分类 cs.AI

2209.05588 2022-09-14 cs.CV 57%

CenterFormer: Center-based Transformer for 3D Object Detection

Zixiang Zhou, Xiangchen Zhao, Yu Wang, Panqu Wang, Hassan Foroosh

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments Accepted to ECCV 2022 (oral)

2208.02337 2022-09-14 cs.CV cs.MM cs.SD eess.AS 57%

Estimating Visual Information From Audio Through Manifold Learning

Fabrizio Pedersoli, Dryden Wiebe, Amin Banitalebi, Yong Zhang, George Tzanetakis, Kwang Moo Yi

专题命中感知：LiDAR(abstract)；分类 cs.CV

2112.00166 2022-09-13 cs.CV 57%

TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information

Suraj Kothawade, Saikat Ghosh, Sumit Shekhar, Yu Xiang, Rishabh Iyer

专题命中感知：self-driving(abstract)；分类 cs.CV

Comments To Appear In European Conference on Computer Vision (ECCV) 2022

2208.11903 2022-09-13 cs.RO 57%

Autonomous social robot navigation in unknown urban environments using semantic segmentation

Sophie Buckeridge, Pamela Carreno-Medrano, Akansel Cosgun, Elizabeth Croft, Wesley P. Chan

专题命中感知：LiDAR(abstract)；分类 cs.RO

2209.04203 2022-09-12 cs.CV 57%

An Indian Roads Dataset for Supported and Suspended Traffic Lights Detection

Sarita Gautam, Anuj Kumar

专题命中感知：self-driving(abstract)；分类 cs.CV

2209.04075 2022-09-12 cs.SD cs.AI eess.AS 57%

Improving the Environmental Perception of Autonomous Vehicles using Deep Learning-based Audio Classification

Finley Walden, Sagar Dasgupta, Mizanur Rahman, Mhafuzul Islam

专题命中感知：LiDAR(abstract)；分类 cs.AI

2205.15730 2022-09-07 cs.CV cs.LG 57%

Transformers for Multi-Object Tracking on Point Clouds

Felicia Ruppel, Florian Faion, Claudius Gläser, Klaus Dietmayer

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments Accepted for publication at the 2022 33rd IEEE Intelligent Vehicles Symposium (IV 2022), June 5-9, 2022, in Aachen, Germany

2111.12264 2022-09-07 cs.CV 57%

Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes

Yu Tian, Yuyuan Liu, Guansong Pang, Fengbei Liu, Yuanhong Chen, Gustavo Carneiro

专题命中感知：self-driving(abstract)；分类 cs.CV

Comments ECCV 2022 Oral

2207.08699 2022-09-05 cs.CV 57%

Semantic Novelty Detection via Relational Reasoning

Francesco Cappio Borlino, Silvia Bucci, Tatiana Tommasi

专题命中感知：autonomous driving(abstract)；分类 cs.CV

Comments Accepted at ECCV 2022

2205.05979 2022-09-05 cs.CV 57%

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

Xuesong Chen, Shaoshuai Shi, Benjin Zhu, Ka Chun Cheung, Hang Xu, Hongsheng Li

专题命中感知：autonomous driving(abstract)；分类 cs.CV

Comments Accepted by ECCV 2022

2209.00364 2022-09-02 cs.CV 57%

Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss

Yannik Blei, Nicolas Jourdan, Nils Gählert

专题命中感知：autonomous driving(abstract)；分类 cs.CV

Comments 5 pages, 3 Figures, eccv 2022 - Workshop on Uncertainty Quantification for Computer Vision

2208.13414 2022-08-30 cs.CV 57%

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

Peng Wu, Lipeng Gu, Xuefeng Yan, Haoran Xie, Fu Lee Wang, Gary Cheng, Mingqiang Wei

专题命中感知：LiDAR(abstract)；分类 cs.CV

Comments 18 pages, 9 figures

2208.10056 2022-08-29 cs.CV 57%

Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking

JunYoung Gwak, Silvio Savarese, Jeannette Bohg

专题命中感知：BEV(abstract)；分类 cs.CV

2205.07403 2022-08-29 cs.CV 57%

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Guangsheng Shi, Ruifeng Li, Chao Ma

专题命中感知：autonomous driving(abstract)；分类 cs.CV

Comments ECCV 2022

2208.11315 2022-08-25 cs.CV cs.LG 57%

Comparison of Object Detection Algorithms for Street-level Objects

Martinus Grady Naftali, Jason Sebastian Sulistyawan, Kelvin Julian

专题命中感知：self-driving(abstract)；分类 cs.CV

Comments 11 pages, 9 figures, 5 tables

2208.10976 2022-08-24 cs.CV 57%

Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking

Jinrong Yang, En Yu, Zeming Li, Xiaoping Li, Wenbing Tao

专题命中感知：LiDAR(abstract)；分类 cs.CV

2208.10773 2022-08-24 cs.CV cs.CR cs.LG 57%

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Svetlana Pavlitskaya, Nikolai Polley, Michael Weber, J. Marius Zöllner

专题命中感知：autonomous driving(abstract)；分类 cs.CV

Comments Accepted for publication at ECCV 2022 SAIAD workshop

2208.10035 2022-08-23 cs.CV 57%

A Simple Baseline for Multi-Camera 3D Object Detection

Yunpeng Zhang, Wenzhao Zheng, Zheng Zhu, Guan Huang, Jie Zhou, Jiwen Lu

专题命中感知：autonomous driving(abstract)；分类 cs.CV

2208.09480 2022-08-22 cs.CV 57%

Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion

Zian Wang, Wenzheng Chen, David Acuna, Jan Kautz, Sanja Fidler

专题命中感知：autonomous driving(abstract)；分类 cs.CV

Comments Webpage: https://nv-tlabs.github.io/outdoor-ar/

Journal ref ECCV 2022

1. 感知 6065 篇

Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching

Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking

Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps

Feature-based model selection for object detection from point cloud data

Ground then Navigate: Language-guided Navigation in Dynamic Scenes

GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

HGI-SLAM: Loop Closure With Human and Geometric Importance Features

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

Shifts 2.0: Extending The Dataset of Real Distributional Shifts

CenterFormer: Center-based Transformer for 3D Object Detection

Estimating Visual Information From Audio Through Manifold Learning

TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information

Autonomous social robot navigation in unknown urban environments using semantic segmentation

An Indian Roads Dataset for Supported and Suspended Traffic Lights Detection

Improving the Environmental Perception of Autonomous Vehicles using Deep Learning-based Audio Classification

Transformers for Multi-Object Tracking on Point Clouds

Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes

Semantic Novelty Detection via Relational Reasoning

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Comparison of Object Detection Algorithms for Street-level Objects

Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

A Simple Baseline for Multi-Camera 3D Object Detection

Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion