Spectral Super-Resolution using Spatial-Spectral Residual Operator Networks

Seokhyun Chin

cs.CVSep 28, 2026

Spectral Super-Resolution using Spatial-Spectral Residual Operator Networks

Authors: Seokhyun Chin

Organizations: California Institute of Technology 1200 E California Boulevard, Pasadena, CA, USA

Abstract

Spectral super-resolution of multispectral satellite images can enable high temporal- and spatial-resolution hyperspectral satellite imagery at a modest cost, significantly increasing the applicability of hyperspectral remote sensing. This task is inherently ill-posed, making it well-suited for deep learning-based methods. In this study, the spectral super-resolution task is framed as an operator learning problem, and SSRON is proposed as a Deep Operator Network that effectively learns function-to-function mappings from downsampled spectra to continuous spectra. The model is trained to super-resolve Sentinel-2A-like multispectral imagery to EMIT images. Compared to baseline models, SSRON achieves superior performance across all metrics. The model also demonstrates zero-shot spectral super-resolution capability by predicting bands unseen during training. Furthermore, its continuous-output formulation suggests the potential to estimate spectra at finer wavelength intervals than the native sensor. These results suggest the potential of SSRON and establishes operator learning as a promising direction for spectral super-resolution.

Figures & tables

Panel of Figure 1 — Fig. 1 : Proposed architecture of SSRON. The framework consists of a branch network and trunk network, as shown in (a). The branch network encodes the MSI into a latent representation, and the trunk network encodes the spatial-spectral query positions. (b) shows the specific architecture of the branch network.

Scene no.	Granule ID (excluding common prefix)
1	20241214T150837_2434910_009
2	20241214T151321_2434910_033
3	20241215T094506_2435006_010
4	20241215T203042_2435013_020
5	20241216T071956_2435105_007
6	20241216T193914_2435113_006

TABLE I: Dataset specifications

Fig. 2: Normalized and downsampled SRF of the Sentinel 2A satellite

Model type	MAE $\downarrow$	RMSE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$
AWAN	0.01529	0.03476	50.92	0.9861
FNO	0.1690	0.2745	31.23	0.2516
Restormer	0.01606	0.03670	50.24	0.9845
SSRAN	0.01871	0.03999	49.29	0.9820
UNO	0.01498	0.03255	51.01	0.9865
SSRON	0.01183	0.02599	52.67	0.9889

TABLE II: Error metrics over testing dataset

Panel of Figure 5 — Fig. 3 : Per-band (a) MAE, (b) PSNR, (c) RMSE, and (d) 1-SSIM value comparison. FNO is excluded from the analysis due to extremely high errors. SSIM is reported as 1-SSIM and on a log scale for enhanced visibility.

% bands used	MAE $\downarrow$	RMSE $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$
100	0.01183	0.02599	52.67	0.9889
95	0.01422	0.04756	48.02	0.9764
90	0.01509	0.04836	47.50	0.9748
85	0.01701	0.05290	46.64	0.9730
80	0.01844	0.05638	46.10	0.9716
75	0.01946	0.05599	45.64	0.9707

TABLE III: Error metrics over testing dataset with reduced number of bands seen during training

Explore similar work

Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators
Sep 30, 2026Ji-Xuan He, Guohang Zhuang, Bo Junge +6Hyperspectral Image Super-Resolution Upsampling
Xi’an Jiaotong University · Hefei University of Technology · National University of Singapore +1
Correcting Spectra Outside the Backbone: A Model-Agnostic Rectifier for Hyperspectral Image Super-Resolution
Jan 29, 2026Ji-Xuan He, Guohang Zhuang, Bo Junge +5Hyperspectral Image Super-Resolution Signal Reconstruction
School of Computer Science and Technology, Xi’an Jiaotong University · School of Computer Science and Information Engineering, Hefei University of Technology
Is Zero-Shot Super-Resolution Possible in Operator Learning?
May 29, 2026Unique Subedi, Ambuj TewariGenerative Super-Resolution Probabilistic Operator Learning
Department of Statistics, University of Michigan

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators

Ji-Xuan He, Guohang Zhuang, Bo Junge, Tingyi Li+5

Xi’an Jiaotong University · Hefei University of Technology · National University of Singapore+1

Hyperspectral Image Super-Resolution Upsampling Signal Reconstruction Two-Level Spatial-Frequency Fusion Strategy Multi-Scale Convolution Omni

Open paper AskPDF arXiv

Achieving cross-sensor generalization and arbitrary-scale reconstruction with a single model remains challenging in hyperspectral super-resolution (HSR). Although recent methods support arbitrary-scale reconstruction, applying them to new sensors or scales beyond the training range often requires additional data and computation to maintain reconstruction quality. To address these challenges, we propose OmniHSR, which predicts band-shared spatial operators rather than spectral values. Cross-Spectral Mapping (CSM) resamples inputs with any number of bands to fixed reference positions and predicts local operators with Gaussian supports. Continuous Operator-Field Reconstruction (COFR) composes these operators into a continuous field and applies them to all original bands for arbitrary-scale reconstruction. Experiments demonstrate that operator prediction outperforms direct spectral-value prediction on all seven datasets. Trained solely on ARAD with only 0.538M parameters, OmniHSR outperforms all directly transferred baselines on six unseen datasets without target-domain training data or adaptation. Across twelve upsampling factors from

\times2

\times48

, it improves average PSNR on Pavia U and Chikusei by 0.55 dB over the strongest baseline. It also surpasses baselines trained from scratch or adapted on the target sensor and achieves up to

36\times

faster inference. Our code will be publicly released soon.

Abstract

Explore similar work

Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators

Correcting Spectra Outside the Backbone: A Model-Agnostic Rectifier for Hyperspectral Image Super-Resolution

Is Zero-Shot Super-Resolution Possible in Operator Learning?