CrosSeR: Collaborative Learning for Generalizable Cross-Device Image Super-Resolution via Amplitude Spectrum Sharing
Authors:
- Yue YangYYYue Yang
- Yunqiu XuYXYunqiu Xu
- Anran LiALAnran Li
- Saiyu QiSQSaiyu Qi
- Fan MaFMFan Ma
Preprint
- 13 April 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Recent advances in image super-resolution (SR) have enabled high-fidelity reconstruction, yet existing models still underperform on real-world devices due to a distribution gap between public training datasets and personal images. In this study, we investigate a practical yet under-explored scenario, cross-device image SR, where a shared SR model is federatively constructed across multiple devices and endowed with generalization capacity to unseen devices. This new task brings two key challenges: 1) effectively learning from the limited data on individual devices, and 2) developing a generic SR model capable of robustly generalizing to unseen devices. To address these issues, we propose CrosSeR, a novel collaborative learning SR framework. Specifically, an amplitude-mixed curation strategy is first introduced to enrich data diversity on each device. This involves extracting the amplitude and phase spectra of images in the frequency domain, and combining the device’s own phase with amplitude sampled from other devices to enlarge both diversity and scale. The amplitude spectra are globally shared across devices as they do not reveal visual content but contribute to appearance variations. Furthermore, we devise a bi-level joint learning scheme comprising within-device training and cross-device adaptation. This scheme leverages both original and augmented samples to guide the transition from device-specific to device-invariant representation learning. By ensembling the device-specific models, CrosSeR ultimately develops a generic image SR model that effectively generalizes to arbitrary unseen devices. Extensive experiments on two real-world SR benchmarks demonstrate the effectiveness of CrosSeR in achieving both high-quality image reconstruction and strong generalization performance.Keywords
This publication has 17 references indexed in Scilit:
- Deep blind super-resolution for hyperspectral imagesPattern Recognition, 2024
- Cross-contrast mutual fusion network for joint MRI reconstruction and super-resolutionPattern Recognition, 2024
- Learning From Multi-Perception Features for Real-Word Image Super-ResolutionIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Pyramid Attention Network for Image RestorationInternational Journal of Computer Vision, 2023
- Dual Circle Contrastive Learning-Based Blind Image Super-ResolutionIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Single image super-resolution based on directional variance attention networkPattern Recognition, 2022
- Multi-attention augmented network for single image super-resolutionPattern Recognition, 2022
- Wide Weighted Attention Multi-Scale Network for Accurate MR Image Super-ResolutionIEEE Transactions on Circuits and Systems for Video Technology, 2021
- Deep Edge Guided Recurrent Residual Learning for Image Super-ResolutionIEEE Transactions on Image Processing, 2017
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004