Hierarchy-GBP accelerates factor graph inference via coarse abstraction and recovery, SOTA BA runtimes
zhenjun_zhao · x · 2026-10-08
H-GBP speeds up Gaussian Belief Propagation by exploiting that GBP fixes local errors fast but global errors only slowly via long-range propagation. It first solves global errors on a coarse graph approximation (abstraction) and projects results back (recovery), then refines locally with GBP. The paper proves convergence to optimality via spectral radius analysis, shows much faster convergence on sparse linear graphs, markedly accelerates large-scale Pose Graph Optimization, and achieves state-of-the-art Bundle Adjustment runtimes across all tested scales. From Andrew Davison's group.
More from Embodied
- EvoMem-VLA adds state-evolution memory for long-horizon robot manipulation, hitting 80.7% on RMBench — zhenjun_zhao · 2026-10-08
- Clear Oakley Meta Vanguard smart glasses earn Z87 jobsite safety certification — armand_ruiz · 2026-10-08
- DeepMind's Raia Hadsell on continual learning, navigation and real-world robotics opportunities at RAAIS — nathanbenaich · 2026-10-08
- Robot fights got too dangerous, so organizers put swords on the bots — cixliv · 2026-10-08
- From single-task to full-workflow: why physical AI robots unlock a 10x larger market — Rewkang · 2026-10-08
- VibeBuddy is a $59 desk gadget that watches your coding agents and speaks up when they need you — juntao · 2026-10-08