Dylan Campbell


Picture of Dylan Campbell

Brian Anderson Building 115, Office B149


+61 2 6125 7779



I have broad research interests within computer vision, optimisation, machine learning, and robotics, with particular expertise in 3D vision and optimisation for deep learning. I have investigated problems of geometric sensor data alignment (including camera localisation, simultaneous localisation and mapping, structure from motion, and optical flow), 3D representations (including neural radiance fields), and differentiable optimisation layers (inserting constrained optimisation problems into deep learning systems). Current topics of interest include discovering and exploiting symmetries in data to share information across long-range physically-motivated connections, and optimisation in deep learning for training neural networks efficiently with respect to time and the quantity of data.


I am always looking for highly motivated students who are interested in conducting research with me. Students at ANU are encouraged to reach out to me about undergraduate or PhD research projects. Students outside of ANU who are interested in pursuing a PhD under my supervision should first visit my homepage and read the ANU application procedures before getting in contact.


I am a Lecturer in Computing at the Australian National University (ANU). Previously, I was a Research Fellow of the Visual Geometry Group at the University of Oxford, where I was supervised by Andrea Vedaldi and João Henriques. Prior to that, I was a Research Fellow of the Australian Centre for Robotic Vision at ANU, where I was supervised by Stephen Gould. I was awarded a PhD degree from ANU in 2018, conducting research on geometric vision problems at Data61/CSIRO and NICTA under the supervision of Lars Petersson, Laurent Kneip, and Hongdong Li, and received a BE in Mechatronic Engineering (Hons) from the University of New South Wales in 2012.

Activities & Awards

Workshop and Conference Organisation:

  • Co-organiser of and speaker at the tutorial on Deep Declarative Networks at ECCV 2020, organised by Itzik Ben-Shabat with Steve Gould, Steven Diamond, Brandon Amos, and Akshay Agrawal.
  • Co-organiser of the workshop on Deep Declarative Networks at CVPR 2020, with Steve Gould, Anoop Cherian, and Richard Hartley.
  • Co-organiser of the sixth Robotic Vision Summer School (RVSS 2020), with Rob Mahony, Dana Kulić, Katrina Tune, and Carol Taylor.
  • Co-organiser of the 2019 RoboVis Conference (poster chair), with Tat-Jun Chin, Yasir Latif, Thomas Rowntree, and Thuy Mai.

Conference and Journal Reviewer: I have regularly served as program committee member or reviewer for the following conferences and journals: Conference on Computer Vision and Pattern Recognition (CVPR), International Conference on Computer Vision (ICCV), European Conference on Computer Vision (ECCV), AAAI Conference on Artificial Intelligence (AAAI), Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Pattern Recognition (PR); Transactions on Image Processing (TIP), Image and Vision Computing (IMAVIS), International Journal of Computer Vision (IJCV), among others.

Supervision: I have co-supervised 7 PhD/DPhil students (3 now graduated), 3 MEng students, and 9 honours students from the Australian National University and the University of Oxford.


  • ENGN8501: Advanced Topics in Computer Vision (Semester 2, 2020) with Stephen Gould, Fatemeh Saleh and Yizhak Ben-Shabat
  • ENGN3213/6213: Digital Systems and Microprocessors (Semester 1, 2019) with Nicolo Malagutti
  • ENGN4528/6528: Computer Vision (Semester 1, 2019) with Hongdong Li

Guest lectures:

  • ENGN8536: Advanced Topics in Mechatronic Systems (Semester 2, 2020)
  • COMP4680/8650: Advanced Topics in Statistical Machine Learning (Semester 1, 2019)
  • ENGN4627: Robotics (Semester 2, 2018)
  • ENGN4528/6528: Computer Vision (Semester 1, 2018)


  • Marr Prize Honourable Mention. For: Dylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li, 2017, “Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence”, The 16th International Conference on Computer Vision (ICCV), Venice, Italy, IEEE.
  • 1st Prize IEEE Australia Council Postgraduate Student Paper Competition. For: Dylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li, 2018, “Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
  • Best Presentation Award at the 2022 Rank Prize Symposium on Neural Rendering
  • Outstanding Reviewer recipient (ECCV 2022)
  • Student Engineer of the Year (Engineers Australia 2013)
  • University Medal (University of New South Wales 2012)

You are on Aboriginal land.

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

bars search times arrow-up