AI Paper Atlas

Research map / Image generation / Super-resolution

GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution

Sirui Wang, Jiang He, Natàlia Blasco Andreo, Xiao Xiang Zhu

AAAI 2026 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 1 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
add PCA to the wavelet encoder (ablation)GEWDiff · Validation setPSNR: 15.788 -> 27.013Improved
add RWA to the encoder (ablation)GEWDiff · Validation setPSNR: 25.640 -> 27.013Improved
add edge-aware noise perturbation (ablation)GEWDiff · Validation setPSNR: 26.579 -> 27.013Improved
add mask conditioning (ablation)GEWDiff · Validation setSSIM: 0.6530 -> 0.6573 (PSNR 26.681 -> 27.013)No clear effect
use multi-level loss (pixel+perceptual+gradient) instead of a single term (ablation)GEWDiff · Validation setPSNR: 26.101 (pixel only) -> 27.013Improved
use perceptual loss only instead of full multi-level loss (ablation)GEWDiff · Validation setPSNR: 27.013 -> 21.664Hurt
add spectral fidelity enhancer (SFE) (ablation)GEWDiff · Validation setPSNR: 26.388 -> 27.013Improved
use 3D U-Net instead of 2D U-Net (ablation)GEWDiff · Validation setFID: 65.985 -> 30.110Improved
use more noise on edge (variant J) instead of default edge scheduler (ablation)GEWDiff · Validation setPSNR: 26.8713 vs 27.013No clear effect
use GEWDiff instead of SNLSR on SAM (MDAS sample 1)HSI SR · MDAS sample 1SAM: 7.8911 (SNLSR) vs 8.4283 (GEWDiff)Hurt
use GEWDiff instead of best baselineHSI SR · MDAS sample 1FID: 49.026 -> 44.464Improved
apply GEWDiff after HySure fusion on real EnMAP dataEnMAP+Sentinel-2 fusion · real-world applicationMetaIQA: 0.1997 -> 0.2029Improved

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