Neural Phase Correlation framework generalizes image transformation analysis

Researchers have developed a novel framework called Neural Phase Correlation, which generalizes the traditional phase correlation method. This new approach learns a basis for transformations, enabling it to handle dense non-rigid deformations and unitary dynamics, unlike the original method which was limited to global translations. The framework has demonstrated strong performance on medical imaging benchmarks, matching or exceeding existing baselines in cardiac-MRI registration and echocardiography. Furthermore, it has been applied to quantum mechanics, successfully recovering eigenstates and energy levels of a quantum harmonic oscillator from observational data. AI

IMPACT This framework could advance image registration and potentially enable new approaches in quantum mechanics analysis.

RANK_REASON The cluster contains a research paper detailing a new computational framework.

Read on arXiv cs.CV →

• 1-D quantum harmonic oscillator
• AC/DC
• alphaXiv
• arXiv
• arXivLabs
• Camus
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hermite functions and uncertainty principles for the Fourier and the windowed Fourier transforms
• Hugging Face
• Influence Flower
• Neural Phase Correlation
• ScienceCast

• paper
• model release

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →