AI Paper Atlas

Research map / Image generation / Super-resolution

PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution

Onkar Jadhav, Tim French, Matthew Rayson, Nicole L. Jones

ICML 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use POD basis instead of random orthonormal basis (ablation)PODiff-K40 · SST downscaling WA coast (2011 test)RMSE (C): 0.9987 -> 0.3923Improved
add diffusion on top of POD projection (ablation)POD-proj · SST downscaling WA coast (2011 test)RMSE (C): 0.7084 -> 0.3923Improved
increase POD latent dimension K from 10 to 20 (ablation)PODiff · SST downscaling WA coast (2011 test)RMSE (C): 0.7725 -> 0.5171Improved
increase POD latent dimension K from 20 to 40 (ablation)PODiff · SST downscaling WA coast (2011 test)RMSE (C): 0.5171 -> 0.3923Improved
diffuse in POD space instead of pixel spacePixelDiff · SST downscaling WA coast (2011 test)RMSE (C): 0.4118 -> 0.3923Improved
diffuse in POD space instead of pixel spacePixelDiff · SST downscaling WA coast (2011 test)peak GPU memory (GB): 12.5 GB -> 1.4 GBImproved
diffuse in POD space instead of pixel spacePixelDiff · SST downscaling WA coast (2011 test)training time: 48 h -> 3.8 hImproved
use PODiff instead of MC Dropout U-Net for uncertaintyMC Dropout U-Net · SST downscaling WA coast (2011 test), 20 test daysCRPS: 0.4821 -> 0.2889Improved
reduce U-Net capacity (C=128 to C=32) (ablation)U-Net · SST downscaling WA coast (2011 test)RMSE (C): 0.6788 -> 0.6819No clear effect
increase ensemble size from M=50 to M=100 (ablation)PODiff-K40 · SST downscaling WA coast (2011 test), 90% coverageempirical coverage: 0.899 -> 0.901No clear effect
increase ensemble size from M=100 to M=200 (ablation)PODiff-K40 · SST downscaling WA coast (2011 test), 90% coverageempirical coverage: 0.901 -> 0.902No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy