9 papers
Hierarchy-GBP: Accelerating Factor Graph Inference via Abstraction and Recovery
Yuzhou Cheng, Tom Yates, Ignacio Alzugaray +3
Gaussian Belief Propagation (GBP) is a distributed inference algorithm that passes messages in graphical models, making it attractive for scalable spatial intelligence. However, we…
Rendering 3D Gaussians on a Graph Processor
Nicholas Fry, Ignacio Alzugaray, Mark Pupilli +2
We present the first implementation of a 3D Gaussian renderer on an Intelligence Processing Unit (IPU), comprising 1,472 independent tiles with only on-chip SRAM; constraints that…
Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
Tom Yates, Yuzhou Cheng, Ignacio Alzugaray +3
Belief Propagation (BP) is a powerful algorithm for distributed inference in probabilistic graphical models, however it quickly becomes infeasible for practical compute and memory…
Radiant Foam Rendering on a Graph Processor
Zulkhuu Tuya, Ignacio Alzugaray, Nicholas Fry +1
Many emerging many-core accelerators replace a single large device memory with hundreds to thousands of lightweight cores, each owning only a small local SRAM and exchanging data v…
KV-Tracker: Real-Time Pose Tracking with Transformers
Marwan Taher, Ignacio Alzugaray, Kirill Mazur +2
Multi-view 3D geometry networks offer a powerful prior but are prohibitively slow for real-time applications. We propose a novel way to adapt them for online use, enabling real-tim…
ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAM
Ignacio Alzugaray, Marwan Taher, Andrew J. Davison
We present a novel neural RGB-D Simultaneous Localization And Mapping (SLAM) system that learns an implicit map of the scene in real time. For the first time, we explore the use of…
PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation
Ignacio Alzugaray, Riku Murai, Andrew Davison
Images are the standard input for most computer vision algorithms. However, their processing often reduces to parallelizable operations applied locally and independently to individ…
Fit-NGP: Fitting Object Models to Neural Graphics Primitives
Marwan Taher, Ignacio Alzugaray, Andrew J. Davison
Accurate 3D object pose estimation is key to enabling many robotic applications that involve challenging object interactions. In this work, we show that the density field created b…
Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models
Ivan Kapelyukh, Yifei Ren, Ignacio Alzugaray +1
We introduce Dream2Real, a robotics framework which integrates vision-language models (VLMs) trained on 2D data into a 3D object rearrangement pipeline. This is achieved by the rob…