Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Paul H. J. Kelly

Paul H. J. Kelly

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Vision×2Graphics×1Distributed×1

Frequent co-authors

Ignacio Alzugaray2×
Andrew J. Davison2×
Nicholas Fry1×
Mark Pupilli1×
Shinjeong Kim1×
Callum Rhodes1×

Research Timeline

2026
PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

PixVOD proposes a fully parallelizable, pixel-distributed framework for visual odometry and depth estimation that performs computations directly on the sensor using Gaussian Belief Propagation.

Rendering 3D Gaussians on a Graph Processor

First implementation of a 3D Gaussian renderer on an Intelligence Processing Unit (IPU) with 1,472 independent tiles using only on-chip SRAM.

Highlighted terms show continued research focus across papers

Papers

cs.GRcs.CVcs.DCEmpiricalRecentJul 17, 2026

Rendering 3D Gaussians on a Graph Processor

Nicholas Fry, Ignacio Alzugaray, Mark Pupilli, Paul H. J. Kelly +1 more

First implementation of a 3D Gaussian renderer on an Intelligence Processing Unit (IPU) with 1,472 independent tiles using only on-chip SRAM.

View →
cs.CVRecentJun 2, 2026

PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

Shinjeong Kim, Ignacio Alzugaray, Callum Rhodes, Paul H. J. Kelly +1 more

PixVOD proposes a fully parallelizable, pixel-distributed framework for visual odometry and depth estimation that performs computations directly on the sensor using Gaussian Belief Propagation.

View →