CVPR 2021 Open Access Repository

Autonomous Driving

Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment: Yizhou Wang,

Gaoang Wang,

Hung-Min Hsu,

Hui Liu,

Jenq-Neng Hwang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2021_CVPR, author = {Wang, Yizhou and Wang, Gaoang and Hsu, Hung-Min and Liu, Hui and Hwang, Jenq-Neng}, title = {Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2815-2824} }
Video Class Agnostic Segmentation Benchmark for Autonomous Driving: Mennatullah Siam,

Alex Kendall,

Martin Jagersand; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Siam_2021_CVPR, author = {Siam, Mennatullah and Kendall, Alex and Jagersand, Martin}, title = {Video Class Agnostic Segmentation Benchmark for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2825-2834} }
LCCNet: LiDAR and Camera Self-Calibration Using Cost Volume Network: Xudong Lv,

Boya Wang,

Ziwen Dou,

Dong Ye,

Shuo Wang; [pdf] [supp]
[bibtex]
@InProceedings{Lv_2021_CVPR, author = {Lv, Xudong and Wang, Boya and Dou, Ziwen and Ye, Dong and Wang, Shuo}, title = {LCCNet: LiDAR and Camera Self-Calibration Using Cost Volume Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2894-2901} }
Soft Cross Entropy Loss and Bottleneck Tri-Cost Volume for Efficient Stereo Depth Prediction: Tyler Nuanes,

Matt Elsey,

Aswin Sankaranarayanan,

John Shen; [pdf] [supp]
[bibtex]
@InProceedings{Nuanes_2021_CVPR, author = {Nuanes, Tyler and Elsey, Matt and Sankaranarayanan, Aswin and Shen, John}, title = {Soft Cross Entropy Loss and Bottleneck Tri-Cost Volume for Efficient Stereo Depth Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2846-2854} }
Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation: Francesco Barbato,

Marco Toldo,

Umberto Michieli,

Pietro Zanuttigh; [pdf] [arXiv]
[bibtex]
@InProceedings{Barbato_2021_CVPR, author = {Barbato, Francesco and Toldo, Marco and Michieli, Umberto and Zanuttigh, Pietro}, title = {Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2835-2845} }
Accurate 3D Object Detection Using Energy-Based Models: Fredrik K. Gustafsson,

Martin Danelljan,

Thomas B. Schon; [pdf] [arXiv]
[bibtex]
@InProceedings{Gustafsson_2021_CVPR, author = {Gustafsson, Fredrik K. and Danelljan, Martin and Schon, Thomas B.}, title = {Accurate 3D Object Detection Using Energy-Based Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2855-2864} }
RAD: Realtime and Accurate 3D Object Detection on Embedded Systems: Hamed H. Aghdam,

Elnaz J. Heravi,

Selameab S. Demilew,

Robert Laganiere; [pdf] [supp]
[bibtex]
@InProceedings{Aghdam_2021_CVPR, author = {Aghdam, Hamed H. and Heravi, Elnaz J. and Demilew, Selameab S. and Laganiere, Robert}, title = {RAD: Realtime and Accurate 3D Object Detection on Embedded Systems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2875-2883} }
Multi-Task Learning With Attention for End-to-End Autonomous Driving: Keishi Ishihara,

Anssi Kanervisto,

Jun Miura,

Ville Hautamaki; [pdf] [arXiv]
[bibtex]
@InProceedings{Ishihara_2021_CVPR, author = {Ishihara, Keishi and Kanervisto, Anssi and Miura, Jun and Hautamaki, Ville}, title = {Multi-Task Learning With Attention for End-to-End Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2902-2911} }
Occlusion Guided Scene Flow Estimation on 3D Point Clouds: Bojun Ouyang,

Dan Raviv; [pdf] [arXiv]
[bibtex]
@InProceedings{Ouyang_2021_CVPR, author = {Ouyang, Bojun and Raviv, Dan}, title = {Occlusion Guided Scene Flow Estimation on 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2805-2814} }
Semi-Synthesis: A Fast Way To Produce Effective Datasets for Stereo Matching: Ju He,

Enyu Zhou,

Liusheng Sun,

Fei Lei,

Chenyang Liu,

Wenxiu Sun; [pdf] [supp]
[bibtex]
@InProceedings{He_2021_CVPR, author = {He, Ju and Zhou, Enyu and Sun, Liusheng and Lei, Fei and Liu, Chenyang and Sun, Wenxiu}, title = {Semi-Synthesis: A Fast Way To Produce Effective Datasets for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2884-2893} }
MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting Through Multi-View Fusion of LiDAR Data: Ankit Laddha,

Shivam Gautam,

Stefan Palombo,

Shreyash Pandey,

Carlos Vallespi-Gonzalez; [pdf] [arXiv]
[bibtex]
@InProceedings{Laddha_2021_CVPR, author = {Laddha, Ankit and Gautam, Shivam and Palombo, Stefan and Pandey, Shreyash and Vallespi-Gonzalez, Carlos}, title = {MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting Through Multi-View Fusion of LiDAR Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {2865-2874} }