Yuzhou Cheng(程誉洲)

I am a second-year PhD student in the Dyson Robotics Lab at Imperial College London, under the supervision of Andrew Davison and Pedro Mediano. Previously, I received my BSc from CUHK-Shenzhen, supervised by Zhi-Quan Luo, and my MSc from UCL, supervised by Dimitrios Kanoulas.

How can robot vision lead to spatial intelligence? I explore this question through distributed inference frameworks and 3D representations.

Portrait of Yuzhou Cheng

Research

MLP Splatting preview
MLP Splatting: Object-Centric Neural Fields
Shinjeong Kim*, Yuzhou Cheng*, Xin Kong*, Paul H. J. Kelly, Andrew J. Davison
ECCV, 2026   (* equal contribution)
project page / arXiv

Object-centric neural primitives for photorealistic rendering and interactive scene editing.

Beliefs becoming progressively Gaussian along a factor-graph chain
Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
Tom Yates, Yuzhou Cheng, Ignacio Alzugaray, Danyal Akarca, Pedro A. M. Mediano, Andrew J. Davison
ICML, 2026
project page / arXiv

A theoretical account of when beliefs become Gaussian in sparse, loopy factor graphs.

LoGS visual localization preview
LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images
Yuzhou Cheng, Jianhao Jiao, Yue Wang, Dimitrios Kanoulas
ICRA, 2025
project page / arXiv / code

Few-shot visual localization using a compact 3D Gaussian Splatting map.