1. 

   SeaBird: Segmentation in Bird’s View with Dice Loss Improves Monocular 3D Detection of Large Objects

   Abhinav Kumar, Yuliang Guo, Xinyu Huang, Liu Ren and Xiaoming Liu

   Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects ...

   Continue reading

   Keywords: 3D Object Detection, Image Segmentation

2. 

   DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

   Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami, Xiaoming Liu

   Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D translations in the projective manifold. Even then, all monocular 3D detectors use vanilla blocks to obtain the 3D coordinates, a task for which the ...

   Continue reading

   Keywords: 3D Object Detection

3. 

   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

2025

• CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector
  Abhinav Kumar, Yuliang Guo, Zhihao Zhang, Xinyu Huang, Liu Ren, Xiaoming Liu
  In Proceeding of International Conference on Computer Vision (ICCV 2025), Honolulu, Hawaii, Oct. 2025
  Bibtex
@inproceedings{ charm3r-towards-unseen-camera-height-robust-monocular-3d-detector,
  author = { Abhinav Kumar and Yuliang Guo and Zhihao Zhang and Xinyu Huang and Liu Ren and Xiaoming Liu },
  title = { CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector },
  booktitle = { In Proceeding of International Conference on Computer Vision },
  address = { Honolulu, Hawaii },
  month = { October },
  year = { 2025 },
}
• RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection
  Yunfei Long, Abhinav Kumar, Xiaoming Liu, Daniel Morris
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN, Jun. 2025
  Bibtex | arXiv
@inproceedings{ riccardo-radar-hit-prediction-and-convolution-for-camera-radar-3d-object-detection,
  author = { Yunfei Long and Abhinav Kumar and Xiaoming Liu and Daniel Morris },
  title = { RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Nashville, TN },
  month = { June },
  year = { 2025 },
}

2024

• RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry
  Shengjie Zhu*, Girish Chandar Ganesan*, Abhinav Kumar, Xiaoming Liu
  In Proceeding of European Conference on Computer Vision (ECCV 2024), Milan, Italy, Oct. 2024
  Bibtex | PDF | arXiv
@inproceedings{ replay-remove-projective-lidar-depthmap-artifacts-via-exploiting-epipolar-geometry,
  author = { Shengjie Zhu* and Girish Chandar Ganesan* and Abhinav Kumar and Xiaoming Liu },
  title = { RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry },
  booktitle = { In Proceeding of European Conference on Computer Vision },
  address = { Milan, Italy },
  month = { October },
  year = { 2024 },
}
• SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
  Abhinav Kumar, Yuliang Guo, Xinyu Huang, Liu Ren, Xiaoming Liu
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, Jun. 2024
  Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code
@inproceedings{ seabird-segmentation-in-birds-view-with-dice-loss-improves-monocular-3d-detection-of-large-objects,
  author = { Abhinav Kumar and Yuliang Guo and Xinyu Huang and Liu Ren and Xiaoming Liu },
  title = { SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Seattle, WA },
  month = { June },
  year = { 2024 },
}

2023

• PrObeD: Proactive Object Detection Wrapper
  Vishal Asnani, Abhinav Kumar, Suya You, Xiaoming Liu
  In Proceeding of Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, Dec. 2023
  Bibtex | PDF | arXiv | Supplemental | Code
@inproceedings{ probed-proactive-object-detection-wrapper,
  author = { Vishal Asnani and Abhinav Kumar and Suya You and Xiaoming Liu },
  title = { PrObeD: Proactive Object Detection Wrapper },
  booktitle = { In Proceeding of Thirty-seventh Conference on Neural Information Processing Systems },
  address = { New Orleans, LA },
  month = { December },
  year = { 2023 },
}
• Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
  Shengjie Zhu, Abhinav Kumar, Masa Hu, Xiaoming Liu
  In Proceeding of Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, Dec. 2023
  Bibtex | arXiv | Code | Video
@inproceedings{ tame-a-wild-camera-in-the-wild-monocular-camera-calibration,
  author = { Shengjie Zhu and Abhinav Kumar and Masa Hu and Xiaoming Liu },
  title = { Tame a Wild Camera: In-the-Wild Monocular Camera Calibration },
  booktitle = { In Proceeding of Thirty-seventh Conference on Neural Information Processing Systems },
  address = { New Orleans, LA },
  month = { December },
  year = { 2023 },
}
• RADIANT: RADar Image Association NeTwork for 3D Object Detection
  Yunfei Long, Abhinav Kumar, Daniel Morris, Xiaoming Liu, Marcos Paul Gerardo Castro, Punarjay Chakravarty
  In Proceeding of Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), Washington, D.C., Feb. 2023
  Bibtex | PDF
@inproceedings{ radiant-radar-image-association-network-for-3d-object-detection,
  author = { Yunfei Long and Abhinav Kumar and Daniel Morris and Xiaoming Liu and Marcos Paul Gerardo Castro and Punarjay Chakravarty },
  title = { RADIANT: RADar Image Association NeTwork for 3D Object Detection },
  booktitle = { In Proceeding of Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI) },
  address = { Washington, D.C. },
  month = { February },
  year = { 2023 },
}

2022

• DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
  Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami, Xiaoming Liu
  In Proceeding of European Conference on Computer Vision (ECCV 2022), Tel-Aviv, Israel, Oct. 2022
  Bibtex | PDF | arXiv | Supplemental | Project Webpage | Code
@inproceedings{ deviant-depth-equivariant-network-for-monocular-3d-object-detection,
  author = { Abhinav Kumar and Garrick Brazil and Enrique Corona and Armin Parchami and Xiaoming Liu },
  title = { DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection },
  booktitle = { In Proceeding of European Conference on Computer Vision },
  address = { Tel-Aviv, Israel },
  month = { October },
  year = { 2022 },
}

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

• LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood
  Abhinav Kumar*, Tim K. Marks*, Wenxuan Mou*, Ye Wang, Michael Jones, Anoop Cherian, Toshiaki Koike-Akino, Xiaoming Liu, Chen Feng
  In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2020), Seattle, WA, Jun. 2020
  Bibtex | PDF | arXiv | Supplemental | Code | Video | Dataset
@inproceedings{ luvli-face-alignment-estimating-landmarks-location-uncertainty-and-visibility-likelihood,
  author = { Abhinav Kumar* and Tim K. Marks* and Wenxuan Mou* and Ye Wang and Michael Jones and Anoop Cherian and Toshiaki Koike-Akino and Xiaoming Liu and Chen Feng },
  title = { LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood },
  booktitle = { In Proceeding of IEEE Computer Vision and Pattern Recognition },
  address = { Seattle, WA },
  month = { June },
  year = { 2020 },
}

2019

• UGLLI Face Alignment:Estimating Uncertainty with Gaussian Log-Likelihood Loss
  Abhinav Kumar*, Tim K.Marks*, Wenxuan Mou*, Chen Feng, Xiaoming Liu
  In Proceeding of International Conference on Computer Vision Workshops (ICCVW 2019), Seoul, Korea, Oct. 2019 (Best Oral Presentation)
  Bibtex | PDF | Poster
@inproceedings{ uglli-face-alignmentestimating-uncertainty-with-gaussian-log-likelihood-loss,
  author = { Abhinav Kumar* and Tim K.Marks* and Wenxuan Mou* and Chen Feng and Xiaoming Liu },
  title = { UGLLI Face Alignment:Estimating Uncertainty with Gaussian Log-Likelihood Loss },
  booktitle = { In Proceeding of International Conference on Computer Vision Workshops },
  address = { Seoul, Korea },
  month = { October },
  year = { 2019 },
}