KrigSCD, a kriging-smoothed diffusion inpainting method, reconstructs 2D temperature fields from sparse masks and beats IDW, kriging, and plain diffusion on LPIPS at all tested coverage levels.
Nichol, 2021: Diffusion models beat gans on image synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Probabilistic Spatial Interpolation of Sparse Data using Diffusion Models
KrigSCD, a kriging-smoothed diffusion inpainting method, reconstructs 2D temperature fields from sparse masks and beats IDW, kriging, and plain diffusion on LPIPS at all tested coverage levels.