AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening

Junfeng Li, Wenyang Zhou, Xueheng Li, Xuanhua He, Jianhou Gan, Wenqi Ren

CVPR 2026 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 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
add average (global) token (ablation)MTRWKV with momentum · WorldView-IIPSNR: 42.0364 -> 42.1360Improved
add average (global) token (ablation)MTRWKV with momentum · GaoFen2PSNR: 47.5367 -> 47.6217Improved
add learnable register token (ablation)MTRWKV with momentum and average token · WorldView-IIPSNR: 42.1360 -> 42.2192Improved
add learnable register token (ablation)MTRWKV with momentum and average token · GaoFen2PSNR: 47.6217 -> 47.6681Improved
add semantic prototype tokens (ablation)MTRWKV with momentum and avg+learn tokens · WorldView-IIPSNR: 42.2192 -> 42.3750Improved
add semantic prototype tokens (ablation)MTRWKV with momentum and avg+learn tokens · GaoFen2PSNR: 47.6681 -> 47.8941Improved
add WKV momentum (ablation)MTRWKV with all tokens and prototype · WorldView-IIPSNR: 42.2800 -> 42.3750Improved
add WKV momentum (ablation)MTRWKV with all tokens and prototype · GaoFen2ERGAS: 0.5186 -> 0.5115Improved
add prototype learning without momentum (ablation)MTRWKV with all tokens · WorldView-IIPSNR: 42.2192 -> 42.2800No clear effect
use full method instead of strongest baseline SFINetMTRWKV · WorldView-IIPSNR: 41.7244 -> 42.3751Improved
use full method instead of strongest baseline SFINetMTRWKV · WorldView-IIIPSNR: 30.5971 -> 31.3113Improved
use full method instead of SFINetMTRWKV · GaoFen2SSIM: 0.9901 -> 0.9901No 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