AI Paper Atlas

Research map / Detection and segmentation / CNN features

Deep Adaptive Unfolded Network via Spatial Morphology Stripping and Spectral Filtration for Pan-sharpening

Hebaixu Wang, Jiayi Ma

ICCV 2025 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 2 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
activate adaptive stage-exiting (ASE) with K=4 (ablation)DAPNet · GaoFen-2 reduced-scaleERGAS: 1.1140 -> 1.1118Improved
activate adaptive stage-exiting (ASE) with K=4 (ablation)DAPNet · GaoFen-2 reduced-scale full-scaleQNR: 0.9440 -> 0.9443Improved
increase unfolding stages from 1 to 4 (ablation)DAPNet · GaoFen-2 reduced-scaleERGAS: 1.2461 -> 1.1140Improved
increase unfolding stages from 4 to 10 (ablation)DAPNet · GaoFen-2 reduced-scaleERGAS: 1.1140 -> 1.0331Mixed
increase unfolding stages from 4 to 10 (ablation)DAPNet · GaoFen-2 reduced-scaleoverfitting patch proportion: 27.60% -> 33.46%Hurt
add phase consistency loss L_phase (ablation)DAPNet · GaoFen-2 L_phase ablation, stage 4, PSNR of Rxk o Sxk vs xkPSNR (dB): 37.5197 -> 39.3948Improved
adopt Lmorph, SFA and ASE modules together (ablation)DAPNet · GaoFen-2 reduced-scaleERGAS: 1.2078 -> 1.1118Improved
change ASE training criterion from PSNR to LPIPS (N=16) (ablation)ASE · GaoFen-2 reduced-scaleERGAS: 1.1118 -> 1.1663Hurt
use finer patch granularity in ASE (N=16 to N=64, PSNR criterion) (ablation)ASE · GaoFen-2 reduced-scaleERGAS: 1.1118 -> 1.0851Improved
use finer patch granularity in ASE (N=16 to N=64, PSNR criterion) (ablation)ASE · GaoFen-2 reduced-scaleoverfitting portion: 27.60% -> 44.31%Mixed
use pan-sharpened output rather than LRMS input for segmentationDAPNet · SegGF full-scalemIoU: 40.04 -> 45.18Improved
use DAPNet instead of DISPNetDAPNet · QuickBird reduced-scaleERGAS: 1.1164 -> 1.0177Improved

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