Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.14412 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917344748503040 |
|---|---|
| author | Yang, Zhiqi Yin, Shan Liang, Jingze Deng, Liang-Jian |
| author_facet | Yang, Zhiqi Yin, Shan Liang, Jingze Deng, Liang-Jian |
| contents | Pansharpening aims to fuse a high-resolution panchromatic (PAN) image and a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. Recent deep models have achieved strong performance, yet they typically rely on large-scale pretraining and often generalize poorly to unseen real-world image pairs.Prior zero-shot approaches improve real-scene generalization but require per-image optimization, hindering weight reuse, and the above methods are usually limited to a fixed scale.To address this issue, we propose G-ZAP, a generalizable zero-shot framework for arbitrary-scale pansharpening, designed to handle cross-resolution, cross-scene, and cross-sensor generalization.G-ZAP adopts a feature-based implicit neural representation (INR) fusion network as the backbone and introduces a multi-scale, semi-supervised training scheme to enable robust generalization.Extensive experiments on multiple real-world datasets show that G-ZAP achieves state-of-the-art results under PAN-scale fusion in both visual quality and quantitative metrics.Notably, G-ZAP supports weight reuse across image pairs while maintaining competitiveness with per-pair retraining, demonstrating strong potential for efficient real-world deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14412 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | G-ZAP: A Generalizable Zero-Shot Framework for Arbitrary-Scale Pansharpening Yang, Zhiqi Yin, Shan Liang, Jingze Deng, Liang-Jian Computer Vision and Pattern Recognition Pansharpening aims to fuse a high-resolution panchromatic (PAN) image and a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. Recent deep models have achieved strong performance, yet they typically rely on large-scale pretraining and often generalize poorly to unseen real-world image pairs.Prior zero-shot approaches improve real-scene generalization but require per-image optimization, hindering weight reuse, and the above methods are usually limited to a fixed scale.To address this issue, we propose G-ZAP, a generalizable zero-shot framework for arbitrary-scale pansharpening, designed to handle cross-resolution, cross-scene, and cross-sensor generalization.G-ZAP adopts a feature-based implicit neural representation (INR) fusion network as the backbone and introduces a multi-scale, semi-supervised training scheme to enable robust generalization.Extensive experiments on multiple real-world datasets show that G-ZAP achieves state-of-the-art results under PAN-scale fusion in both visual quality and quantitative metrics.Notably, G-ZAP supports weight reuse across image pairs while maintaining competitiveness with per-pair retraining, demonstrating strong potential for efficient real-world deployment. |
| title | G-ZAP: A Generalizable Zero-Shot Framework for Arbitrary-Scale Pansharpening |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14412 |