Qiangeng(Charlie) Xu bio photo

Qiangeng(Charlie) Xu

Email LinkedIn Instagram Github

Mailing address

Powell Hall, Room 108
University of Southern California
3737 Watt Way, Los Angeles, U.S.
zip code: 90089

Publications

Overview

2022

  • Point-NeRF: Point-based Neural Radiance Fields
    Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, Ulrich Neumann
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022 Oral 🤩🤯🔥) [paper] [project site][code]
    bibtex
    @inproceedings{xu2022point,
         title={Point-NeRF: Point-based Neural Radiance Fields},
         author={Xu, Qiangeng and Xu, Zexiang and Philip, Julien and Bi, Sai and Shu, Zhixin and Sunkavalli, Kalyan and Neumann, Ulrich},
         booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
         pages={5438--5448},
         year={2022}
    }

     

  • Behind the Curtain: Learning Occluded Shapes for 3D Object Detection
    Qiangeng Xu, Yiqi Zhong, Ulrich Neumann
    Proceedings of the AAAI Conference on Artificial Intelligence 36 (AAAI-2022) [paper] [code]
    bibtex
    @article{xu2021behind,
         title={Behind the Curtain: Learning Occluded Shapes for 3D Object Detection},
         author={Xu, Qiangeng and Zhong, Yiqi and Neumann, Ulrich},
         booktitle={arXiv int arXiv:2112.02205},
         year={2021}
    }

2021

  • SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation
    Qiangeng Xu, Yin Zhou, Weiyue Wang, Charles R. Qi, Dragomir Anguelov
    International Conference on Computer Vision (ICCV 2021) [paper(+supplemental)]
    bibtex
    @inproceedings{xu2021spg,
         title={Grid-gcn for fast and scalable point cloud learning},
         author={Xu, Qiangeng and Zhou, Yin and Wang, Weiyue and Qi, Charles R. and Anguelov, Dragomir},
         booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
         year={2021}
    }

     

  • Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
    Cho-Ying Wu, Qiangeng Xu, Ulrich Neumann
    International Conference on 3D Vision 2021 (3DV 2021) [paper]
    bibtex
    @article{wu2021synergy,
         title={Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry},
         author={Wu, Cho-Ying and Xu, Qiangeng and Neumann, Ulrich},
         journal={arXiv preprint arXiv:2110.09772},
         year={2021}
    }

2020

  • Geometry-Aware Instance Segmentation with Disparity Maps
    Cho-Ying Wu, Xiaoyan Hu, Michael Happold, Qiangeng Xu, Ulrich Neumann
    IEEE Conference on Computer Vision and Pattern Recognition Workshop Scalability in Autonomous Driving (CVPRw 2020) [paper]
    bibtex
    inproceedings{wu2020Cvprw,
         title={Geometry-Aware Instance Segmentation with Disparity Maps},
         author={Wu, Cho-Ying and Hu, Xiaoyan and Happold, Michael and Xu, Qiangeng and Neumann, Ulrich},
         booktitle={CVPR Workshop on Scability in Autonomous Driving},
         year={2020}
    }

     

  • Grid-GCN for Fast and Scalable Point Cloud Learning
    Qiangeng Xu, Xudong Sun, Cho-ying Wu, Panqu Wang, Ulrich Neumann
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020) [paper] [supplementary] [code]
    bibtex
    @inproceedings{xu2020grid,
         title={Grid-gcn for fast and scalable point cloud learning},
         author={Xu, Qiangeng and Sun, Xudong and Wu, Cho-Ying and Wang, Panqu and Neumann, Ulrich},
         booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
         pages={5661--5670},
         year={2020}
    }

2019

  • DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
    Qiangeng Xu✴, Weiyue Wang✴, Duygu Ceylan, Radomir Mech, Ulrich Neumann
    Conference on neural information processing systems (NeurIPS) 2019 [paper] [appendix] [code]
    bibtex
    @incollection{NIPS2019_8340,
          title = {DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction},
          author = {Xu, Qiangeng and Wang, Weiyue and Ceylan, Duygu and Mech, Radomir and Neumann, Ulrich},
          booktitle = {Advances in Neural Information Processing Systems 32},
          editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
          pages = {492--502},
          year = {2019},
          publisher = {Curran Associates, Inc.},
          url = {http://papers.nips.cc/paper/8340-disn-deep-implicit-surface-network-for-high-quality-single-view-3d-reconstruction.pdf}
    }

     

  • Stochastic Dynamics for Video Infilling
    Qiangeng Xu, Hanwang Zhang, Weiyue Wang, Peter N. Belhumeur, Ulrich Neumann.
    CVPRw 2019
    Winter Conference on Applications of Computer Vision (WACV) 2020
    [paper] [project site]
    bibtex
    @inProceedings{xu2020sdvi,
          title={Stochastic Dynamics for Video Infilling},
          author={Qiangeng Xu, Hanwang Zhang, Weiyue Wang, Peter N. Belhumeur, Ulrich Neumann},
          booktitle={Winter Conference on Applications of Computer Vision},
          year={2020}
    }

     

  • Generative Cooperative Net for Image Generation and Data Augmentation
    Qiangeng Xu, Zengchang Qin, Tao Wan.
    The International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making (IUKM) 2019 [paper]
    bibtex
    @inproceedings{xu2019generative,
          title={Generative cooperative net for image generation and data augmentation},
          author={Xu, Qiangeng and Qin, Zengchang and Wan, Tao},
          booktitle={International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making},
          pages={284--294},
          year={2019},
          organization={Springer}
    }

2017

  • Dynamic Eye Movement Matching and Visualization Tool in Neuro Gesture
    Qiangeng Xu, John Kender.
    arXiv preprint arXiv:1712.09709 [paper]
    bibtex
    @misc{xu2017report,
          title={Report: Dynamic Eye Movement Matching and Visualization Tool in Neuro Gesture},
          author={Qiangeng Xu and John Kender},
          year={2017},
          eprint={1712.09709},
          archivePrefix={arXiv},
          primaryClass={cs.NE}
    }

Talk and Tutorials:

  • Reverse Rendering for 3D Scene Reconstruction [slides(284MB)] [pdf(18MB)]
    As a guest lecture of a graduate level course, CSCI 580 Computer Graphics at University of Southern California.