Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908869909807104 |
|---|---|
| author | Dong, Xiaoyu Li, Jiahuan Cui, Ziteng Yokoya, Naoto |
| author_facet | Dong, Xiaoyu Li, Jiahuan Cui, Ziteng Yokoya, Naoto |
| contents | Cross-modal super-resolution (SR) on real-world misaligned data is challenging, as only unlabeled low-resolution (LR) source and high-resolution (HR) guide images with complex spatial misalignment are available. Previous methods either rely on fully simulated training data or adopt suboptimal alignment strategies that overlook cross-modal dependencies, limiting their performance in practice. To address these issues, we propose RobSelf, a self-supervised model that jointly optimizes a misalignment-aware feature translator and a content-aware reference filter online. The translator resolves unsupervised cross-modal and cross-resolution alignment via weakly-supervised, misalignment-aware translation, yielding an aligned guide feature. Guided by this feature, the filter performs reference-based discriminative self-enhancement on the source, enabling SR prediction with high resolution and high fidelity. Experiments on synthesized data and our collected real-world data demonstrate that RobSelf achieves state-of-the-art performance, outperforming existing self-supervised and supervised methods. Moreover, it achieves superior efficiency, up to 15.3$\times$ faster than prior self-supervised methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18822 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations Dong, Xiaoyu Li, Jiahuan Cui, Ziteng Yokoya, Naoto Computer Vision and Pattern Recognition Cross-modal super-resolution (SR) on real-world misaligned data is challenging, as only unlabeled low-resolution (LR) source and high-resolution (HR) guide images with complex spatial misalignment are available. Previous methods either rely on fully simulated training data or adopt suboptimal alignment strategies that overlook cross-modal dependencies, limiting their performance in practice. To address these issues, we propose RobSelf, a self-supervised model that jointly optimizes a misalignment-aware feature translator and a content-aware reference filter online. The translator resolves unsupervised cross-modal and cross-resolution alignment via weakly-supervised, misalignment-aware translation, yielding an aligned guide feature. Guided by this feature, the filter performs reference-based discriminative self-enhancement on the source, enabling SR prediction with high resolution and high fidelity. Experiments on synthesized data and our collected real-world data demonstrate that RobSelf achieves state-of-the-art performance, outperforming existing self-supervised and supervised methods. Moreover, it achieves superior efficiency, up to 15.3$\times$ faster than prior self-supervised methods. |
| title | Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.18822 |