Skip to main content
Search

# Image Inpainting

2 related articles

Subscribe to updates
  1. Anthropic

    Ménard's Claude Science agent team filled a third of the unobserved sky to produce the first complete UV all-sky map

    Working with Claude Science, Brice Ménard orchestrated a team of AI agents to gather public UV and multi-wavelength data from GALEX, Swift, FIMS/SPEAR, TD-1, Planck and Gaia, cross-calibrate and merge the surveys, inpaint roughly one third of the sky never observed in UV using learned multi-wavelength relations, and add UV estimates for more than 100 million individual stars, yielding the first complete UV map of the sky; in held-out tests the model estimated hidden UV data to within about 10% of real measurements.

  2. Integrating image inpainting into an ensemble score filter to track surface quasi-geostrophic dynamics under partial observations

    The work develops an ensemble score filter (EnSF) that integrates image inpainting to address data assimilation with partial observations: at each filtering step a training-free diffusion model estimates the observed states by incorporating likelihood information into the score function, and image inpainting methods then predict the unobserved state variables, with performance demonstrated by tracking Surface Quasi-Geostrophic (SQG) model dynamics across a variety of scenarios as a proof of concept.

You’re all caught up