Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification
Onkar Jadhav, Tim French, Matthew Rayson +1
Diffusion models enable probabilistic super-resolution and conditional generation, but pixel-space methods are computationally expensive and learned latent spaces often lack interp…
cs.LG2026
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
Onkar Jadhav, Tim French, Matthew Rayson +1
Probabilistic super-resolution of high-dimensional spatial fields using diffusion models is often computationally prohibitive due to the cost of operating directly in pixel space.…