AI Paper Atlas

Research map / Image generation / Image restoration

Physical Degradation Model-Guided Interferometric Hyperspectral Reconstruction with Unfolding Transformer

Yuansheng Li, Yunhao Zou, Linwei Chen, Ying Fu

ICCV 2025 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 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 physical noise model (shot+read, standard) instead of Gaussian white noise (ablation)IHRUT-5 trained on synthetic data · Calibration (real)PSNR: 37.95 -> 38.82Improved
add pixel-wise stripe-pattern noise modeling over standard noise (ablation)IHRUT-5 · Calibration (real)PSNR: 38.82 -> 39.28Improved
add electronic gain e for parameter randomization (ablation)IHRUT-5 · Calibration (real)PSNR: 39.28 -> 39.46Improved
add relative response coefficient M to optical degradation (ablation)IHRUT-5 degradation model · Calibration (real)PSNR: 26.20 -> 33.96Improved
add SPE_0 to the data module (ablation)IHRUT-5 · Calibration (real)PSNR: 34.37 -> 38.73Improved
add SPE_k to the data module (ablation)IHRUT-5 · Calibration (real)PSNR: 38.73 -> 39.10Improved
add momentum branch (ablation)IHRUT-5 · Calibration (real)PSNR: 39.10 -> 39.12Improved
add cross-stage fusion in prior module (ablation)IHRUT-5 · Calibration (real)PSNR: 39.12 -> 39.35Improved
add SPE in the prior module (ablation)IHRUT-5 · Calibration (real)PSNR: 39.35 -> 39.46Improved
use SPE_k(SPE_0*delta+m) instead of channel-attention momentum branch (CA*delta+CA(m)) (ablation)IHRUT-5 data module · Calibration (real)PSNR: 38.31 -> 39.46Improved
use IHRUT-5 instead of MAUN-7 on real dataunfolding methods · Calibration (real)PSNR: 38.15 -> 39.46Improved
use IHRUT-7 instead of 5 stagesIHRUT · HSOD-BITPSNR: 44.25 -> 44.30No clear effect

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