Thomas Walker

PhD Candidate in 3D Vision and Neural Graphics
University of Edinburgh & Generative AI Laboratory (GAIL)
T[DOT]M[DOT]WALKER[AT]ED.AC.UK
Google Scholar | GitHub | LinkedIn

About Me

Hello! I am a third-year Ph.D. candidate at the University of Edinburgh and a researcher at the Generative AI Laboratory (GAIL). My research spans differentiable rendering, 3D reconstruction, and 3D generative models. Before starting my PhD I studied Mathematics and Physics at the University of Durham, with a focus on the geometrical aspects of gauge field theories. Following this, I became fascinated by geometric deep learning, and came to the University Of Edinburgh to read Artifical Intelligence. Since then I've largely worked towards developing 3D reconstruction, from images and medical scanners such as CT/MRI. My current research focuses on equipping generative world models with persistent spatial memory.

I am currently looking for both collaborators and internships, so feel free to reach out!

Selected Publications

• 
  CrossSDF: Reconstruction Of Thin Structures From Cross Sections
  Thomas Walker, Salvatore Esposito, Daniel Rebain, Amir Vaxman, Arno Onken, Changjian Li, Oisin Mac Aodha. CVPR, 2025. [PDF]
• 
  Spatially Adaptive Hash Encodings For Neural Surface Reconstruction
  Thomas Walker, Octave Mariotti, Amir Vaxman, Hakan Bilen. WACV, 2025. [PDF]
• 
  Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fields
  Thomas Walker, Octave Mariotti, Amir Vaxman, Hakan Bilen. NeurIPS NeurReps Workshop, 2023. [PDF]
• 
  Spherical Feature Pyramid Networks
  Thomas Walker, Varun Anand, Pavlos Andreadis. arXiv, 2023. [PDF]