AI Paper Atlas

Research map / Image generation / Image restoration

OneHSI: A Unified Hyperspectral Foundation Model with Physical Consistency

Yufei WEN, Jingdan KANG, SHUXIN ZHONG, Yuting Zhang, Yutong Feng, Jintai Chen, Kaishun Wu

ECCV 2026 · 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 statistical (FiLM) modulation after spectral alignment (ablation)OneHSI · OHID-1OA: 91.65 -> 92.50Improved
use learnable wavelength reparameterization instead of CNN projection (ablation)OneHSI · OHID-1OA: 90.27 -> 92.50Improved
use learnable wavelength reparameterization instead of interpolation (ablation)OneHSI · OHID-1OA: 85.10 -> 92.50Improved
add domain-adversarial loss (ablation)OneHSI · OHID-1OA: 89.73 -> 92.50Improved
add expert balancing loss (ablation)OneHSI · OHID-1OA: 90.68 -> 92.50Improved
use scale-aware SEAT routing instead of generic MoE (top-2) (ablation)OneHSI · HeiPorSPECTRALOA: 94.55 -> 96.81Improved
generic MoE instead of dense network (ablation)OneHSI · OHID-1OA: 89.85 -> 90.80Improved
top-2 expert routing instead of top-1 (ablation)SEAT · OHID-1OA: 91.95 -> 92.50Improved
pretrain jointly on all four domains instead of sequentially / dropping one (ablation)OneHSI · downstream OAOAImproved
OneHSI vs HyperFree with identical pretraining data (frozen encoder) (ablation)OneHSI · OHID-1OA: 86.14 -> 90.65Improved
OneHSI on NPU detection vs SS-MambaOneHSI · NPUmAP: 78.33 vs 77.68No clear effect
fewer shots (1-shot) with OneHSI vs HyperFreeOneHSI · OHID-1 1-shotOA: 78.41 -> 80.76Improved

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