Projects

  1. summary image

    GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

    Abhinav Kumar, Garrick Brazil, Xiaoming Liu

    Modern 3D object detectors have immensely benefited from the end-to-end learning idea. However, most of them use a post-processing algorithm called Non-Maximal Suppression (NMS) only during inference. While there were attempts to include NMS in the training pipeline for tasks such as 2D object detection, they have been less widely ...

    Continue reading

    Keywords: 3D Object Detection

  2. summary image

    Kinematic 3D Object Detection in Monocular Video

    Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu, Bernt Schiele

    Perceiving the physical world in 3D is fundamental for selfdriving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not been thoroughly utilized in modern 3D object detectors. In this work, we propose a novel method for monocular video-based ...

    Continue reading

    Keywords: 3D Object Detection, Video

  3. summary image

    The Edge of Depth: Explicit Constraints between Segmentation and Depth

    Shengjie Zhu, Garrick Brazil, Xiaoming Liu

    In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsupervised monocular depth estimation, constraints from semantic segmentation has been explored implicitly such as sharing and transforming features. In contrast, we propose to explicitly ...

    Continue reading

    Keywords: Depth Prediction

  4. summary image

    M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

    Garrick Brazil, Xiaoming Liu

    Understanding the world in 3D is a critical component of urban autonomous driving. Generally, the combination of expensive LiDAR sensors and stereo RGB imaging has been paramount for successful 3D object detection algorithms, whereas monocular image-only methods experience drastically reduced performance. We propose to reduce the gap by reformulating the ...

    Continue reading

    Keywords: 3D Object Detection

  5. summary image

    Pedestrian Detection with Autoregressive Network Phases

    Garrick Brazil, Xiaoming Liu

    We present an autoregressive pedestrian detection framework with cascaded phases designed to progressively improve precision. The proposed framework utilizes a novel lightweight stackable decoder-encoder module which uses convolutional re-sampling layers to improve features while maintaining efficient memory and runtime cost. Unlike previous cascaded detection systems, our proposed framework is designed ...

    Continue reading

    Keywords: Pedestrian Detection

  6. summary image

    Illuminating Pedestrians via Simultaneous Detection & Segmentation

    Garrick Brazil, Xi Yin, Xiaoming Liu

    Pedestrian detection is a critical problem in computer vision with significant impact on safety in urban autonomous driving. In this work, we explore how semantic segmentation can be used to boost pedestrian detection accuracy while having little to no impact on network efficiency. We propose a segmentation infusion network to ...

    Continue reading

    Keywords: Pedestrian Detection, Semantic Segmentation

Publications

2021

  • GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
    Abhinav Kumar, Garrick Brazil, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2021), Nashville, TN, Jun. 2021
    Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code | Video
  • @inproceedings{ groomed-nms-grouped-mathematically-differentiable-nms-for-monocular-3d-object-detection,
      author = { Abhinav Kumar and Garrick Brazil and Xiaoming Liu },
      title = { GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Nashville, TN },
      month = { June },
      year = { 2021 },
    }

2020

  • Kinematic 3D Object Detection in Monocular Video
    Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu, Bernt Schiele
    In Proceeding of European Conference on Computer Vision (ECCV 2020), Virtual, Aug. 2020
    Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code | Video
  • @inproceedings{ kinematic-3d-object-detection-in-monocular-video,
      author = { Garrick Brazil and Gerard Pons-Moll and Xiaoming Liu and Bernt Schiele },
      title = { Kinematic 3D Object Detection in Monocular Video },
      booktitle = { In Proceeding of European Conference on Computer Vision },
      address = { Virtual },
      month = { August },
      year = { 2020 },
    }
  • The Edge of Depth: Explicit Constraints between Segmentation and Depth
    Shengjie Zhu, Garrick Brazil, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2020), Seattle, WA, Jun. 2020
    Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code | Video
  • @inproceedings{ the-edge-of-depth-explicit-constraints-between-segmentation-and-depth,
      author = { Shengjie Zhu and Garrick Brazil and Xiaoming Liu },
      title = { The Edge of Depth: Explicit Constraints between Segmentation and Depth },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Seattle, WA },
      month = { June },
      year = { 2020 },
    }

2019

  • M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
    Garrick Brazil, Xiaoming Liu
    In Proceeding of International Conference on Computer Vision (ICCV 2019), Seoul, South Korea, Oct. 2019 (Oral presentation)
    Bibtex | PDF | arXiv | Project Webpage | Code | Video
  • @inproceedings{ m3d-rpn-monocular-3d-region-proposal-network-for-object-detection,
      author = { Garrick Brazil and Xiaoming Liu },
      title = { M3D-RPN: Monocular 3D Region Proposal Network for Object Detection },
      booktitle = { In Proceeding of International Conference on Computer Vision },
      address = { Seoul, South Korea },
      month = { October },
      year = { 2019 },
    }
  • Pedestrian Detection with Autoregressive Network Phases
    Garrick Brazil, Xiaoming Liu
    In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, Jun. 2019
    Bibtex | PDF | arXiv | Poster | Project Webpage | Code
  • @inproceedings{ pedestrian-detection-with-autoregressive-network-phases,
      author = { Garrick Brazil and Xiaoming Liu },
      title = { Pedestrian Detection with Autoregressive Network Phases },
      booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
      address = { Long Beach, CA },
      month = { June },
      year = { 2019 },
    }
  • Recurrent Flow-Guided Semantic Forecasting
    Adam M. Terwilliger, Garrick Brazil, Xiaoming Liu
    Proc. IEEE Winter Conference on Application of Computer Vision (WACV 2019), Hawaii, Jan. 2019
    Bibtex | PDF | arXiv | Poster | Project Webpage | Code
  • @inproceedings{ recurrent-flow-guided-semantic-forecasting,
      author = { Adam M. Terwilliger and Garrick Brazil and Xiaoming Liu },
      title = { Recurrent Flow-Guided Semantic Forecasting },
      booktitle = { Proc. IEEE Winter Conference on Application of Computer Vision },
      address = { Hawaii },
      month = { January },
      year = { 2019 },
    }

2017

  • Illuminating Pedestrians via Simultaneous Detection & Segmentation
    Garrick Brazil, Xi Yin, Xiaoming Liu
    In Proceeding of International Conference on Computer Vision (ICCV 2017), Venice, Italy, Oct. 2017
    Bibtex | PDF | arXiv | Poster | Project Webpage | Code
  • @inproceedings{ illuminating-pedestrians-via-simultaneous-detection-segmentation,
      author = { Garrick Brazil and Xi Yin and Xiaoming Liu },
      title = { Illuminating Pedestrians via Simultaneous Detection & Segmentation },
      booktitle = { In Proceeding of International Conference on Computer Vision },
      address = { Venice, Italy },
      month = { October },
      year = { 2017 },
    }