AI Paper Atlas

Research map / Image generation / Image restoration

Spatial-Spectral Residuals Informed Diffusion Neural Operator for Pan-sharpening

Jiahan Huang, Ran Ran, Junming Hou, Zihao Chen, Xiaofeng Cong, Junling Li, Liang-Jian Deng

CVPR 2026 · Image generation › Image restoration · approach: Pansharpening and spectral fusion

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 pixel-wise spatial and spectral consistency residuals as denoiser inputs (ablation)SRINO · WV3 (reduced resolution)PSNR: 39.013 -> 39.305Improved
add spatial consistency residual only (ablation)SRINO · WV3 (reduced resolution)PSNR: 39.013 -> 39.177Improved
add spectral consistency residual only (ablation)SRINO · WV3 (reduced resolution)PSNR: 39.013 -> 39.124Improved
add spatial residual on top of spectral residual (both) (ablation)SRINO · WV3 (reduced resolution)SAM: 2.945 -> 2.869Improved
use residual-informed inputs instead of gradient-guided strategy (ablation)SRINO · WV3 (reduced resolution)PSNR, SAM, ERGAS, Q8Improved
vary gradient guidance weight alpha (1, 10, 100) in gradient-guided baseline (ablation)gradient-guided strategy · WV3 (reduced resolution)PSNR, SAM, ERGAS, Q8No clear effect
use Galerkin-type neural operator backbone instead of CNN (ablation)SRINO denoiser · WV3 (reduced resolution)PSNR, SAM, Q8, ERGASImproved
use Galerkin-type neural operator backbone instead of FNO (ablation)SRINO denoiser · WV3 (reduced resolution)PSNR, SAM, Q8, ERGASImproved
replace attention-based diffusion denoiser with Galerkin neural operatorPanDiff-style attention denoiser · efficiency (FLOPs, memory, inference time)FLOPs, memory, inference timeImproved
SRINO vs ADWM on spatial distortionWV3 full resolution · WV3 (full resolution)Ds: 0.029 (ADWM) vs 0.032 (SRINO)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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