AI Paper Atlas

Research map / Image generation / Super-resolution

Hipandas: Hyperspectral Image Joint Denoising and Super-Resolution by Image Fusion with the Panchromatic Image

Shuang Xu, Zixiang Zhao, Haowen Bai, Chang Yu, Jiangjun Peng, Xiangyong Cao, Deyu Meng

ICCV 2025 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 4 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 GDN denoising loss (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10PSNR: 19.51 -> 40.61Improved
add super-resolution losses (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10PSNR: 31.49 -> 40.61Improved
add PAN high-frequency losses (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10PSNR: 33.32 -> 40.61Improved
add pretraining stage (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10PSNR: 35.94 -> 40.61Improved
add pretraining stage (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10ERGAS: 31.92 -> 8.50Improved
add low-rank modeling in GDN/GSRN (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10PSNR: 36.99 -> 40.61Improved
add fusion of PAN image (ablation)ZSHipandas · Hipandas ablation, i.i.d. Gaussian sigma=10PSNR: 33.76 -> 40.61Improved
jointly train with super-resolution (ablation)GDN denoising only · Denoising task, i.i.d. Gaussian sigma=10PSNR: 40.67 -> 41.68Improved
use joint ZSHipandas instead of best sequential pipelinePWTV+RPNN · Hipandas simulated, i.i.d. Gaussian sigma=10PSNR: 38.34 -> 40.61Improved
use joint ZSHipandas instead of best sequential pipelinePWTV+RPNN · Hipandas simulated, mixture noise p=0.55PSNR: 35.41 -> 36.61Improved
use joint ZSHipandas instead of best sequential pipelinePWTV+RPNN · Hipandas simulated, mixture noise p=0.55ERGAS: 194.38 -> 45.26Mixed

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