Shaoshuai SHI Ph.D. Student The Chinese University of Hong Kong Email: shaoshuaics [at] gmail [dot] com [Google Scholar]   [GitHub]   [CV]

About Me

I am currently a Ph.D. student in Multimedia Lab (MMLab), The Chinese University of Hong Kong (CUHK), supervised by Prof. Xiaogang Wang and Prof. Hongsheng Li. Before that, I received my bachelor’s degree from the Computer Science Honor Class of Harbin Institute Technology (HIT) in July 2017. I am about to graduate in the summer of 2021.

My research interests focus on computer vision and deep learning, especially the 3D scene understanding and object detection on the autonomous driving scenarios.

News

• Two papers got accepted by ICCV 2021.
• I am awarded the World Artificial Intelligence Conference (WAIC) Rising Star Award, see the news from WAIC.
• Two papers got accepted by CVPR 2021.
• I am awarded Google PhD Fellowship 2020, see the news from Google AI Blog.
• Highly optimized PyTorch codebase OpenPCDet for LiDAR-based 3D scene understanding is released, including the implementation of PV-RCNN, the 1st place method in the KITTI 3D detection leaderboard.
• We win the 1st place among all LiDAR-only methods on 3D Detection, 3D Tracking, Domain Adaptation three tracks of the Waymo Open Dataset challenge. See the official blog post from Waymo.
• Two papers with one oral got accepted by CVPR 2020.
• Our Part-A^2 net got accepted by T-PAMI 2020, code is available at PartA2-Net.
• One paper got accepted by ICRA 2020.
• One paper got accepted by CVPR 2019.
• One paper got accepted by ICLR 2019.
• One paper got accepted by ECCV 2018.

Codebase

OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Cloud OpenPCDet Development Team June 2020 [Code]   [Bibtex]

@misc{openpcdet2020,
    title={OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Clouds},
    author={OpenPCDet Development Team},
    howpublished = {\url{https://github.com/open-mmlab/OpenPCDet}},
    year={2020}
}

Publications

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection Jihan Yang*, Shaoshuai Shi*, Zhe Wang, Hongsheng Li, Xiaojuan Qi (*co-first authors) IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [PDF]   [Bibtex]   [Code]

@inproceedings{yang2021st3d,
  title={ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection},
  author={Yang, Jihan and Shi, Shaoshuai and Wang, Zhe and Li, Hongsheng and Qi, Xiaojuan},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2021}
}

Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds Bowen Cheng, Lu Sheng, Shaoshuai Shi, Ming Yang, Dong Xu IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [PDF]   [Bibtex]   [Code]

@inproceedings{cheng2021back,
  title={Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds},
  author={Cheng, Bowen and Sheng, Lu and Shi, Shaoshuai and Yang, Ming and Xu, Dong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={8963--8972},
  year={2021}
}

PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection Shaoshuai Shi, Li Jiang, Jiajun Deng, Zhe Wang, Chaoxu Guo, Jianping Shi, Xiaogang Wang, Hongsheng Li Technical report, arXiv:2102.00463 [PDF]   [Bibtex]

@article{shi2021pv,
  title={PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection},
  author={Shi, Shaoshuai and Jiang, Li and Deng, Jiajun and Wang, Zhe and Guo, Chaoxu and Shi, Jianping and Wang, Xiaogang and Li, Hongsheng},
  journal={arXiv preprint arXiv:2102.00463},
  year={2021}
}

Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection Jiajun Deng, Shaoshuai Shi, Peiwei Li, Wengang Zhou, Yanyong Zhang, Houqiang Li AAAI Conference on Artificial Intelligence (AAAI), 2021 [PDF]   [Bibtex]   [Code]

@article{deng2020voxel,
  title={Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection},
  author={Deng, Jiajun and Shi, Shaoshuai and Li, Peiwei and Zhou, Wengang and Zhang, Yanyong and Li, Houqiang},
  journal={arXiv preprint arXiv:2012.15712},
  year={2020}
}

The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Adaptation of Waymo Open Dataset Challenges Shaoshuai Shi, Chaoxu Guo, Jihan Yang, Hongsheng Li Technical report of top-performing LiDAR-only solutions to Waymo Open Dataset Challenges at Workshop of CVPR 2020. [PDF]   [Bibtex]   [Code]   Ranked 1st place among all LiDAR-only methods on 3D Detection, 3D Tracking, Domain Adaptation three tracks of the Waymo Open Dataset challenge.

@article{shi2020pvwaymo,
  title={PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection/3D Tracking/Domain Adaptation of Waymo Open Dataset Challenges},
  author={Shi, Shaoshuai and Guo, Chaoxu and Yang, Jihan and Li, Hongsheng},
  journal={arXiv preprint arXiv:2008.12599},
  year={2020}
}

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection Shaoshuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [PDF]   [Bibtex]   [Code]   Ranked 1st place on KITTI 3D object detection benchmark (Car, Nov-16 2019).

@inproceedings{shi2020pv,
  title={Pv-rcnn: Point-voxel feature set abstraction for 3d object detection},
  author={Shi, Shaoshuai and Guo, Chaoxu and Jiang, Li and Wang, Zhe and Shi, Jianping and Wang, Xiaogang and Li, Hongsheng},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10529--10538},
  year={2020}
}

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral Presentation, 2020. [PDF]   [Bibtex]   [Code]   Ranked 1st place on ScanNet 3D Semantic instance benchmark (Nov-16 2019).

@inproceedings{jiang2020pointgroup,
  title={PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation},
  author={Jiang, Li and Zhao, Hengshuang and Shi, Shaoshuai and Liu, Shu and Fu, Chi-Wing and Jia, Jiaya},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4867--4876},
  year={2020}
}

From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network Shaoshuai Shi, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), accepted. [PDF]   [Bibtex]   [Code]   Ranked 1st place on KITTI 3D object detection benchmark (Car, July-9 2019).

@article{shi2020part,
    title={From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network},
    author={Shi, Shaoshuai and Wang, Zhe and Shi, Jianping and Wang, Xiaogang and Li, Hongsheng},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    publisher={IEEE},
    year={2020}
}

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud Shaoshuai Shi, Xiaogang Wang, Hongsheng Li IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [PDF]   [Bibtex]   [Code]   The top-10 cited papers among all CVPR-2019 papers (March, 2021), refer to here.

@inproceedings{shi2019pointrcnn,
  title={PointRCNN: 3d Object Proposal Generation and Detection from Point Cloud},
  author={Shi, Shaoshuai and Wang, Xiaogang and Li, Hongsheng},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={770--779},
  year={2019}
}

SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud Hongwei Yi, Shaoshuai Shi, Mingyu Ding, Jiankai Sun, Kui Xu, Hui Zhou, Zhe Wang, Sheng Li, Guoping Wang International Conference on Robotics and Automation (ICRA), 2020. [PDF]   [Bibtex]

@article{yi2020segvoxelnet,
  title={SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud},
  author={Yi, Hongwei and Shi, Shaoshuai and Ding, Mingyu and Sun, Jiankai and Xu, Kui and Zhou, Hui and Wang, Zhe and Li, Sheng and Wang, Guoping},
  journal={arXiv preprint  arXiv:2002.05316},
  year={2020}
}

Feature Intertwiner for Object Detection Hongyang Li, Bo Dai, Shaoshuai Shi, Wanli Ouyang, Xiaogang Wang International Conference on Learning Representation (ICLR), 2019. [PDF]   [Bibtex]

@inproceedings{li2018feature,
    title={Feature Intertwiner for Object Detection},
    author={Hongyang Li and Bo Dai and Shaoshuai Shi and Wanli Ouyang and Xiaogang Wang},
    booktitle={International Conference on Learning Representations},
    year={2019},
    url={https://openreview.net/forum?id=SyxZJn05YX},
}

GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction Li Jiang, Shaoshuai Shi, Xiaojuan Qi, Jiaya Jia European Conference on Computer Vision (ECCV), Oral Presentation, 2018. [PDF]   [Bibtex]

@inproceedings{jiang2018gal,
    title={Gal: Geometric adversarial loss for single-view 3d-object reconstruction},
    author={Jiang, Li and Shi, Shaoshuai and Qi, Xiaojuan and Jia, Jiaya},
    booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
    pages={802--816},
    year={2018}
}

FP-DNN: An automated framework for mapping deep neural networks onto FPGAs with RTL-HLS hybrid templates Yijin Guan, Hao Liang, Ningyi Xu, Wenqiang Wang, Shaoshuai Shi, Xi Chen, Guangyu Sun, Wei Zhang, Jason Cong IEEE Field-Programmable Custom Computing Machines (FCCM), 2017. [PDF]   [Bibtex]

@inproceedings{guan2017fp,
    title={FP-DNN: An automated framework for mapping deep neural networks onto FPGAs with RTL-HLS hybrid templates},
    author={Guan, Yijin and Liang, Hao and Xu, Ningyi and Wang, Wenqiang and Shi, Shaoshuai and Chen, Xi and Sun, Guangyu and Zhang, Wei and Cong, Jason},
    booktitle={2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)},
    pages={152--159},
    year={2017},
    organization={IEEE}
}

Invited Talks

• [2020-06-24] VALSE Webinar: Deep Learning on Point Clouds for 3D Object Detection. [Link (Chinese)]
• [2020-06-16] PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Challenges of Waymo Open Dataset Challenges. [Link]

Education & Experiences

• [Aug 2017 ~ Exp. 2021] PhD student in computer vision and deep learning at The Chinese University of Hong Kong.
• [July 2016 ~ July 2017] Research intern at the System Group of Microsoft Research Asia (MSRA), Beijing, China.
• [Aug 2013 ~ July 2017] Bachelor degree at Harbin Institute Technology, major in Computer Science and Technology.

Honors & Awards

• World Artificial Intelligence Conference (WAIC) Rising Star Award, 2021.
• Google PhD Fellowship in machine perception (10 selected world-wide), 2020.
• Hong Kong PhD Fellowship (The highest scholarship for PhD students in Hong Kong), 2017-2021
• National Scholarship, 2014, 2015, 2016
• Silver Prize of China Collegiate Programming Contest (CCPC 2015), 2015
• Second Prize of China Undergraduate Mathematical Contest in Modeling (CUMCM 2015), 2015
• Gold Prize of China Collegiate Programming Contest (CCPC) of Northeast Area, 2015
• First Prize of Mathematical Modeling Contest of Northeast Area, 2015
• First Class Scholarship of HIT (six times at each semester), 2014-2016