Donghoon Lee

CV

LinkedIn

My background is computer vision and machine learning. I am interested in projects that tackles real-world problems with pragmatic solutions. I worked on building 3D object models using iPhone/iPad in Apple and improved Autopilot in Tesla. I published papers on a wide area of research topics during PhD such as image/video generation and editing, object detection/tracking/pose estimation/identification, compressive sensing, and cyber-physical systems. I received degrees in Electrical and Computer Engineering from Seoul National University (B.S. in 2011, M.S. in 2013, and Ph.D. in 2019). 

Employment

  • Dec 2022 - Dec 2023: Tesla, Autopilot Engineer, Palo Alto, CA
  • Aug 2019 - Dec 2022: Apple Inc., Computer vision and machine learning engineer, Cupertino, CA
  • Apr 2019 - Jul 2019: A. T. Kearney, Expert, Seoul, Korea
  • Jul 2018 - Dec 2018: Google Cloud AI, Student researcher, Sunnyvale, CA
  • Jan 2018 - Jun 2018: NVIDIA research, Intern, Santa Clara, CA

Publications

International Journal

International Conference

  • Donghoon Lee, Onur C. Hamsici, Shuo Feng, Prachee Sharma, Thorsten Gernoth, "DeepPRO: Deep Partial Point Cloud Registration of Objects", in Proc. of the IEEE International Conference on Computer Vision (ICCV), 2021.
  • Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang, "Inserting Videos into Videos",  in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  • Donghoon Lee, Sifei Liu, Jinwei Gu, Ming-Yu Liu, Ming-Hsuan Yang, and Jan Kautz, "Context-Aware Synthesis and Placement of Object Instances", Neural Information Processing Systems (NIPS), 2018.
  • Donghoon Lee, Sangdoo Yun, Sungjoon Choi, Hwiyeon Yoo, Ming-Hsuan Yang, and Songhwai Oh, "Unsupervised Holistic Image Generation from Key Local Patches", in Proc. of the European Conference on Computer Vision (ECCV), 2018.
  • Geonho Cha, Hwiyeon Yoo, Donghoon Lee, and Songhwai Oh, "Light-Weight Semantic Segmentation for Compound Images", in Proc. of the International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2017.
  • Hwiyeon Yoo, Donghoon Lee, Geonho Cha, and Songhwai Oh, "Estimating Objectness Using a Compound Eye Camera", in Proc. of the International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2017.
  • Donghoon Lee, Geonho Cha, Ming-Hsuan Yang, and Songhwai Oh, "Individualness and a Determinantal Point Process for Pedestrian Detection," in Proc. of the European Conference on Computer Vision (ECCV), 2016. (Supplementary material) [Software]
  • Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh, "Fast and Accurate Head Pose Estimation via Random Projection Forests," in Proc. of the IEEE International Conference on Computer Vision (ICCV), 2015. [Software]
  • Donghoon Lee and Songhwai Oh, "Understanding Human-Place Interaction from Tracking and Identification of Many Users," in Proc. of the IEEE International Conference on Cyber-Physical Systems, Networks, and Applications (CPSNA), 2013.
  • Sangseok Yoon, Hyeongseok Oh, Donghoon Lee, and Songhwai Oh, "Virtual Lock: A Smartphone Application for Personal Surveillance Using Camera Sensor Networks," in Proc. of the International Workshop on Cyber-Physical Systems, Networks, and Applications (CPSNA), 2011.

Preprints

  • Nuri Kim, Donghoon Lee, and Songhwai Oh, "“Learning Instance-Aware Object Detection Using Determinantal Point Processes", arXiv 2018.
  • Donghoon Lee, Ming-Hsuan Yang, and Songhwai Oh, "Generative Single Image Reflection Separation", arXiv 2018.

Domestic Journal

  • Nuri Kim, Donghoon Lee, and Songhwai Oh, "Searching Effective Network Parameters to Construct Convolutional Neural Networks for Object Detection," Journal of the Korean Institute of Information Scientists and Engineers, vol.44, no.7, 2017. (Best paper award)
  • Donghoon Lee and Songhwai Oh, "Head Pose Estimation Using Random Forests," Journal of the Korean Institute of Information Scientists and Engineers, vol.40, no.8, 2013.

Domestic Conference

  • Donghoon Lee and Songhwai Oh, "Object Recognition Using a Compound Eye Camera," Proc. of the Korea Institute of Military Science and Technology (KIMST), 2016.
  • Donghoon Lee, Geonho Cha, and Songhwai Oh, "Embedded Intelligent Systems Using Wireless Camera Sensor Networks," Proc. of the Korean Institute of Information Scientists and Engineers, vol.31, no.12, 2013.

Research Experiences