AI Paper Atlas

Research map / Image generation / Image restoration

Laboring on less labors: RPCA Paradigm for Pan-sharpening

Honghui Xu, Chuangjie Fang, Yibin Wang, Jie Wu, Jianwei Zheng

ICCV 2025 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 11 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 NTNN (global low-rank modulation) to multi-scale broadcast CNN (ablation)RUN low-rank CNN · GaoFen-2PSNR: 46.6487 -> 46.9117Improved
add broadcast of multi-scale information in the low-rank CNN (ablation)RUN low-rank CNN · GaoFen-2PSNR: 46.4248 -> 46.6487Improved
replace simulated spatial degradation (one-round or two-round 3x3 convs) with sparse spatial offset component (ablation)RUN · GaoFen-2 (4x downsampling)PSNRImproved
increase unfolding stages beyond 3 or 4 (ablation)RUN · GF2 and WV3PSNRNo clear effect
use NTNN query with Swin keys/values in cross-attention versus self-attention or Swin alone (ablation)Low-rank Transformer · heat-map saliencysaliencyImproved
RUN versus strongest competitor on GaoFen-2RUN · GaoFen-2PSNR: 46.0123 -> 46.9117Improved
RUN versus strongest competitor on WorldView-3RUN · WorldView-3PSNR: 32.5571 -> 32.6064Improved

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