PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
SIAM review , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Model order reduction with snapshots from high-fidelity or one-shot solves accelerates 3D thermal topology optimization by up to 16x versus standard high-fidelity workflows and 1.54x versus one-shot alone.
citing papers explorer
-
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
-
Comparison of model order reduction techniques with one-shot procedure for topology optimization for thermal applications
Model order reduction with snapshots from high-fidelity or one-shot solves accelerates 3D thermal topology optimization by up to 16x versus standard high-fidelity workflows and 1.54x versus one-shot alone.