Workshop on Autonomous Driving
Training Strategies for Vision Transformers for Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Singh_2023_CVPR, author = {Singh, Apoorv}, title = {Training Strategies for Vision Transformers for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {110-118} }
MobileDeRainGAN: An Efficient Semi-Supervised Approach to Single Image Rain Removal for Task-Driven Applications-
[pdf]
[supp]
[bibtex]@InProceedings{Swaminathan_2023_CVPR, author = {Swaminathan, Ruphan and Korupolu, Pradyot}, title = {MobileDeRainGAN: An Efficient Semi-Supervised Approach to Single Image Rain Removal for Task-Driven Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {192-201} }
Ultra-Sonic Sensor Based Object Detection for Autonomous Vehicles-
[pdf]
[bibtex]@InProceedings{Nesti_2023_CVPR, author = {Nesti, Tommaso and Boddana, Santhosh and Yaman, Burhaneddin}, title = {Ultra-Sonic Sensor Based Object Detection for Autonomous Vehicles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {210-218} }
HazardNet: Road Debris Detection by Augmentation of Synthetic Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Choe_2023_CVPR, author = {Choe, Tae Eun and Wu, Jane and Lin, Xiaolin and Kwon, Karen and Park, Minwoo}, title = {HazardNet: Road Debris Detection by Augmentation of Synthetic Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {161-171} }
TorchSparse++: Efficient Point Cloud Engine-
[pdf]
[bibtex]@InProceedings{Tang_2023_CVPR, author = {Tang, Haotian and Yang, Shang and Liu, Zhijian and Hong, Ke and Yu, Zhongming and Li, Xiuyu and Dai, Guohao and Wang, Yu and Han, Song}, title = {TorchSparse++: Efficient Point Cloud Engine}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {202-209} }
Improvements to Image Reconstruction-Based Performance Prediction for Semantic Segmentation in Highly Automated Driving-
[pdf]
[supp]
[bibtex]@InProceedings{Bar_2023_CVPR, author = {B\"ar, Andreas and Kusuma, Daniel and Fingscheidt, Tim}, title = {Improvements to Image Reconstruction-Based Performance Prediction for Semantic Segmentation in Highly Automated Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {219-229} }
RadarGNN: Transformation Invariant Graph Neural Network for Radar-Based Perception-
[pdf]
[arXiv]
[bibtex]@InProceedings{Fent_2023_CVPR, author = {Fent, Felix and Bauerschmidt, Philipp and Lienkamp, Markus}, title = {RadarGNN: Transformation Invariant Graph Neural Network for Radar-Based Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {182-191} }
EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation-
[pdf]
[bibtex]@InProceedings{Shi_2023_CVPR, author = {Shi, Yunxiao and Cai, Hong and Ansari, Amin and Porikli, Fatih}, title = {EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {119-129} }
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Xuanyao and Zhang, Tianyuan and Wang, Yue and Wang, Yilun and Zhao, Hang}, title = {FUTR3D: A Unified Sensor Fusion Framework for 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {172-181} }
Joint Camera and LiDAR Risk Analysis-
[pdf]
[supp]
[bibtex]@InProceedings{Zendel_2023_CVPR, author = {Zendel, Oliver and Huemer, Johannes and Murschitz, Markus and Dominguez, Gustavo Fernandez and Lobe, Amadeus}, title = {Joint Camera and LiDAR Risk Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {88-97} }
LiDAR-Based Localization on Highways Using Raw Data and Pole-Like Object Features-
[pdf]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Sheng-Cheng and Lu, Victor and Wang, Chieh-Chih and Lin, Wen-Chieh}, title = {LiDAR-Based Localization on Highways Using Raw Data and Pole-Like Object Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {230-237} }
MotionTrack: End-to-End Transformer-Based Multi-Object Tracking With LiDAR-Camera Fusion-
[pdf]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ce and Zhang, Chengjie and Guo, Yiluan and Chen, Lingji and Happold, Michael}, title = {MotionTrack: End-to-End Transformer-Based Multi-Object Tracking With LiDAR-Camera Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {151-160} }
Exploiting the Complementarity of 2D and 3D Networks To Address Domain-Shift in 3D Semantic Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cardace_2023_CVPR, author = {Cardace, Adriano and Ramirez, Pierluigi Zama and Salti, Samuele and Di Stefano, Luigi}, title = {Exploiting the Complementarity of 2D and 3D Networks To Address Domain-Shift in 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {98-109} }
DPPD: Deformable Polar Polygon Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yang and Andrienko, Oles and Zhao, Yonglei and Park, Minwoo and Pham, Trung}, title = {DPPD: Deformable Polar Polygon Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {78-87} }
Improving Rare Classes on nuScenes LiDAR Segmentation Through Targeted Domain Adaptation-
[pdf]
[bibtex]@InProceedings{Rajendran_2023_CVPR, author = {Rajendran, Vickram and Tang, Chuck and van Paasschen, Frits}, title = {Improving Rare Classes on nuScenes LiDAR Segmentation Through Targeted Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {130-139} }
Does Image Anonymization Impact Computer Vision Training?-
[pdf]
[supp]
[bibtex]@InProceedings{Hukkelas_2023_CVPR, author = {Hukkel\r{a}s, H\r{a}kon and Lindseth, Frank}, title = {Does Image Anonymization Impact Computer Vision Training?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {140-150} }