CVPR 2022 Open Access Repository

Autonomous Driving

Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning: Xinyu Luo,

Jiaming Zhang,

Kailun Yang,

Alina Roitberg,

Kunyu Peng,

Rainer Stiefelhagen; [pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2022_CVPR, author = {Luo, Xinyu and Zhang, Jiaming and Yang, Kailun and Roitberg, Alina and Peng, Kunyu and Stiefelhagen, Rainer}, title = {Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4429-4439} }
Reconstruct From Top View: A 3D Lane Detection Approach Based on Geometry Structure Prior: Chenguang Li,

Jia Shi,

Ya Wang,

Guangliang Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Chenguang and Shi, Jia and Wang, Ya and Cheng, Guangliang}, title = {Reconstruct From Top View: A 3D Lane Detection Approach Based on Geometry Structure Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4370-4379} }
PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems: Shu Hu,

Chun-Hao Liu,

Jayanta Dutta,

Ming-Ching Chang,

Siwei Lyu,

Naveen Ramakrishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2022_CVPR, author = {Hu, Shu and Liu, Chun-Hao and Dutta, Jayanta and Chang, Ming-Ching and Lyu, Siwei and Ramakrishnan, Naveen}, title = {PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4390-4398} }
H-Net: Unsupervised Attention-Based Stereo Depth Estimation Leveraging Epipolar Geometry: Baoru Huang,

Jian-Qing Zheng,

Stamatia Giannarou,

Daniel S. Elson; [pdf]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Baoru and Zheng, Jian-Qing and Giannarou, Stamatia and Elson, Daniel S.}, title = {H-Net: Unsupervised Attention-Based Stereo Depth Estimation Leveraging Epipolar Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4460-4467} }
TripletTrack: 3D Object Tracking Using Triplet Embeddings and LSTM: Nicola Marinello,

Marc Proesmans,

Luc Van Gool; [pdf]
[bibtex]
@InProceedings{Marinello_2022_CVPR, author = {Marinello, Nicola and Proesmans, Marc and Van Gool, Luc}, title = {TripletTrack: 3D Object Tracking Using Triplet Embeddings and LSTM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4500-4510} }
Anomaly Detection in Autonomous Driving: A Survey: Daniel Bogdoll,

Maximilian Nitsche,

J. Marius Zöllner; [pdf]
[bibtex]
@InProceedings{Bogdoll_2022_CVPR, author = {Bogdoll, Daniel and Nitsche, Maximilian and Z\"ollner, J. Marius}, title = {Anomaly Detection in Autonomous Driving: A Survey}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4488-4499} }
Multi-Modal 3D Human Pose Estimation With 2D Weak Supervision in Autonomous Driving: Jingxiao Zheng,

Xinwei Shi,

Alexander Gorban,

Junhua Mao,

Yang Song,

Charles R. Qi,

Ting Liu,

Visesh Chari,

Andre Cornman,

Yin Zhou,

Congcong Li,

Dragomir Anguelov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2022_CVPR, author = {Zheng, Jingxiao and Shi, Xinwei and Gorban, Alexander and Mao, Junhua and Song, Yang and Qi, Charles R. and Liu, Ting and Chari, Visesh and Cornman, Andre and Zhou, Yin and Li, Congcong and Anguelov, Dragomir}, title = {Multi-Modal 3D Human Pose Estimation With 2D Weak Supervision in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4478-4487} }
Raising Context Awareness in Motion Forecasting: Hédi Ben-Younes,

Éloi Zablocki,

Mickaël Chen,

Patrick Pérez,

Matthieu Cord; [pdf]
[bibtex]
@InProceedings{Ben-Younes_2022_CVPR, author = {Ben-Younes, H\'edi and Zablocki, \'Eloi and Chen, Micka\"el and P\'erez, Patrick and Cord, Matthieu}, title = {Raising Context Awareness in Motion Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4409-4418} }
CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving: Andreas Kloukiniotis,

Andreas Papandreou,

Christos Anagnostopoulos,

Aris Lalos,

Petros Kapsalas,

Duong-Van Nguyen,

Konstantinos Moustakas; [pdf]
[bibtex]
@InProceedings{Kloukiniotis_2022_CVPR, author = {Kloukiniotis, Andreas and Papandreou, Andreas and Anagnostopoulos, Christos and Lalos, Aris and Kapsalas, Petros and Nguyen, Duong-Van and Moustakas, Konstantinos}, title = {CarlaScenes: A Synthetic Dataset for Odometry in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4520-4528} }
K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways: Dong-Hee Paek,

Seung-Hyung Kong,

Kevin Tirta Wijaya; [pdf] [supp]
[bibtex]
@InProceedings{Paek_2022_CVPR, author = {Paek, Dong-Hee and Kong, Seung-Hyung and Wijaya, Kevin Tirta}, title = {K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4450-4459} }
Proposal-Free Lidar Panoptic Segmentation With Pillar-Level Affinity: Qi Chen,

Sourabh Vora; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Qi and Vora, Sourabh}, title = {Proposal-Free Lidar Panoptic Segmentation With Pillar-Level Affinity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4529-4536} }
Multi-Level Domain Adaptation for Lane Detection: Chenguang Li,

Boheng Zhang,

Jia Shi,

Guangliang Cheng; [pdf]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Chenguang and Zhang, Boheng and Shi, Jia and Cheng, Guangliang}, title = {Multi-Level Domain Adaptation for Lane Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4380-4389} }
Trust Your IMU: Consequences of Ignoring the IMU Drift: Marcus Valtonen Örnhag,

Patrik Persson,

Mårten Wadenbäck,

Kalle Åström,

Anders Heyden; [pdf]
[bibtex]
@InProceedings{Ornhag_2022_CVPR, author = {\"Ornhag, Marcus Valtonen and Persson, Patrik and Wadenb\"ack, M\r{a}rten and \r{A}str\"om, Kalle and Heyden, Anders}, title = {Trust Your IMU: Consequences of Ignoring the IMU Drift}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4468-4477} }
RoadSaW: A Large-Scale Dataset for Camera-Based Road Surface and Wetness Estimation: Kai Cordes,

Christoph Reinders,

Paul Hindricks,

Jonas Lammers,

Bodo Rosenhahn,

Hellward Broszio; [pdf]
[bibtex]
@InProceedings{Cordes_2022_CVPR, author = {Cordes, Kai and Reinders, Christoph and Hindricks, Paul and Lammers, Jonas and Rosenhahn, Bodo and Broszio, Hellward}, title = {RoadSaW: A Large-Scale Dataset for Camera-Based Road Surface and Wetness Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4440-4449} }
PointMotionNet: Point-Wise Motion Learning for Large-Scale LiDAR Point Clouds Sequences: Jun Wang,

Xiaolong Li,

Alan Sullivan,

Lynn Abbott,

Siheng Chen; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jun and Li, Xiaolong and Sullivan, Alan and Abbott, Lynn and Chen, Siheng}, title = {PointMotionNet: Point-Wise Motion Learning for Large-Scale LiDAR Point Clouds Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4419-4428} }
Performance Prediction for Semantic Segmentation by a Self-Supervised Image Reconstruction Decoder: Andreas Bär,

Marvin Klingner,

Jonas Löhdefink,

Fabian Hüger,

Peter Schlicht,

Tim Fingscheidt; [pdf] [supp]
[bibtex]
@InProceedings{Bar_2022_CVPR, author = {B\"ar, Andreas and Klingner, Marvin and L\"ohdefink, Jonas and H\"uger, Fabian and Schlicht, Peter and Fingscheidt, Tim}, title = {Performance Prediction for Semantic Segmentation by a Self-Supervised Image Reconstruction Decoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4399-4408} }
MUTR3D: A Multi-Camera Tracking Framework via 3D-to-2D Queries: Tianyuan Zhang,

Xuanyao Chen,

Yue Wang,

Yilun Wang,

Hang Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Tianyuan and Chen, Xuanyao and Wang, Yue and Wang, Yilun and Zhao, Hang}, title = {MUTR3D: A Multi-Camera Tracking Framework via 3D-to-2D Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4537-4546} }
Scene Representation in Bird's-Eye View From Surrounding Cameras With Transformers: Yun Zhao,

Yu Zhang,

Zhan Gong,

Hong Zhu; [pdf]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Yun and Zhang, Yu and Gong, Zhan and Zhu, Hong}, title = {Scene Representation in Bird's-Eye View From Surrounding Cameras With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {4511-4519} }