Ben Kaye

Ben Kaye

Computer Vision PhD student at Visual Geometry Group, University of Oxford

I research learned 3D reconstruction, supervised by Andrea Vedaldi and Christian Rupprecht.

Contact me:emailbook a chat
ImageEngineering mastersImageOrganOxBuilt robust controllers for a surgical deviceRemy AICo-founder & CTOImageYC-backed robotics startup

publications

  1. DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction

    DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction

    Ben Kaye*, Tomas Jakab*, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi* equal contribution

    CVPR 2025 · Highlight

    Single-image 3D shape and pose recovery for deformable objects such as animals. By predicting paired posed and canonical point maps, deformation falls out as a difference. We train on synthetic data and get state-of-the-art results on real images.