Welcome!

I am a Senior Staff Computer Vision Scientist at NVIDIA Automotive, where I am working on computer vision and machine learning algorithms for driverless cars. I am leading a team focused on innovating and developing end-to-end and real-time machine learning models that are capable of consuming multiple images from multiple cameras and predict/detect both static and dynamic objects in a 3D world space. The models will enable autonomous vehicles “see” their surrounding in full 360 degree. Prior to NVIDIA, I was a research fellow at the Australian Centre of Robotic Vision. I secured my PhD in Computer Vision in 2014 from the University of Adelaide. In 2013, I was one of 200 young researchers worldwide invited to attend Heidelberg Laureate Forum. I was awarded a Google Australia PhD Fellowship in Computer Vision in 2012.

Research Interests

My researches range from low-level geometric vision (ie geometric fitting, 3D reconstruction, SLAM) to high-level semantic scene understanding (ie object detection, semantic segmentation). More recently, I am particularly interested in end-to-end 3D perception from multiple cameras. My favourite appplications include autonomous driving, indoor robotics.

My research has been published across top-tier computer vision, machine learning and robotic journals and conferences (TPAMI, CVPR, ICCV, ECCV, NIPS, ICRA), and has attracted more than 1000 citations (as of Dec 2020).

News

  • Dec 2020: Open Set Instance Segmentation Code is now online.
  • May 2020: Intersection Pose estimation for autonmous driving.
  • November 2018: 1 paper accepted to WACV18.
  • October 2018: Appointed as Associate Editor for IEEE Robotics and Automation Letters.
  • September 2018: 1 paper accepted to ACCV 2018.
  • July 2018: 2 papers accepted to ECCV 2018, 1 paper accepted to BMVC 2018 (oral).
  • June 2018: I am excited to join NVIDIA as a Senior Computer Vision Scientist.
  • We are organising a Real-World Challenges and New Benchmarks for Deep Learning in Robotic Vision workshop, in conjunction with CVPR 2018.
  • I am going to give a tutorial about Semantic Mapping at Robotic Vision Summer School 2018 (RVSS).
  • 1 paper accepted to Journal: Methods in Ecology and Evolution
  • 3 papers accepted to ICRA 2018