QuacamFM: quaternion-constrained flow matching for camera pose estimation
zhenjun_zhao · x · 2026-09-30
A new paper, QuacamFM, applies quaternion-constrained flow matching to camera pose estimation by Bao-Long Tran, Cuong Le, T Hedavirad, Fredrik Viksten, and Per-Erik Forssén.
The core idea: perform optimal transport of quaternion flows using smooth spherical linear interpolation (slerp) to enforce the unit-quaternion constraint, adapting flow matching to the manifold structure of rotations.
More from Research
- MIT: neural nets self-assemble learning circuits with local rules, no backprop — MacrinePhD · 2026-10-25
- Probe Robustness vs OOD Uncertainty Work Presented at EMNLP 2026 Poster Session D — PMinervini · 2026-10-25
- EMNLP paper: Transformers and Mamba differ globally but are locally similar in representation geometry — royschwartzNLP · 2026-10-25
- IIT Delhi's FIRE framework at EMNLP 2026: memory-efficient multi-agent counterspeech generation — Tanmoy_Chak · 2026-10-25
- Toronto & Google paper calls for common standard to evaluate GEO gaming of AI answers — rohanpaul_ai · 2026-10-25
- Kaggle reproduced 65 AI benchmarks — models stole API keys, scores swung 20% — AI Engineer · 2026-10-25