James Gardner

James Gardner

At PXLD I build tools that combine the real and the virtual while keeping real people and their performances at the centre. I am also completing my PhD at the University of York with William Smith.

Publications

  1. TAP-Out: Tracking Any Point in 360° via Outpainting

    Finlay G. C. Hudson, James A. D. Gardner, William A. P. Smith

    BMVC 2026 Project page Paper

  2. VENI: Variational Encoder for Natural Illumination

    Paul Walker, James A. D. Gardner, Andreea Ardelean, William A. P. Smith, Bernhard Egger

    CVPR 2026 Project page Paper Code

  3. TAPVid-360: Tracking Any Point in 360° from Narrow Field of View Video

    Finlay G. C. Hudson, James A. D. Gardner, William A. P. Smith

    NeurIPS 2025 Project page Paper Code Dataset

  5. RENI++: A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior

    James A. D. Gardner, Bernhard Egger, William A. P. Smith

    IEEE TPAMI Project page Paper Code

  7. Development of Modular Bio-Inspired Autonomous Underwater Vehicle for Close Subsea Asset Inspection

    Wael Gorma, Mark A. Post, James White, James Gardner, Yang Luo, Jongrae Kim, Paul D. Mitchell, Nils Morozs, Marvin Wright, Qing Xiao

    Applied Sciences 2021 Paper

News

  • Launched PXLD.
  • TAP-Out accepted to BMVC 2026.
  • RENI++ accepted to IEEE TPAMI.
  • VENI, a variational encoder for natural illumination, accepted to CVPR 2026.
  • TAPVid-360 accepted to NeurIPS 2025.
  • NeuraLaTeX, a machine learning library written in pure LaTeX, at SIGBOVIK 2025.
  • Started a research fellowship at York on video relighting and greenscreen compositing.
  • RENI accepted to NeurIPS 2022.
  • Summer research internship with Stephan Liwicki's group at Toshiba, Cambridge, on implicit neural representations for SLAM.

Education

  • PhD, Computer Vision and Machine Learning University of York, in progress
  • MEng, Electronic Engineering University of York, 2021