Toward Real-World Super Resolution With Adaptive Self-Similarity Mining
Lists
Only you see this
Abstract
Despite efforts to construct super-resolution (SR) training datasets with a wide range of degradation scenarios, existing supervised methods based on these datasets still struggle to consistently offer promising results due to the diversity of real-world degradation scenarios and the inherent complexity of model learning. Our work explores a new route: integrating the sample-adaptive property learned through image intrinsic self-similarity and the universal knowledge acquired from large-scale data. We achieve this by uniting internal learning and external learning by an unrolled optimization process. With the merits of both, the tuned fully-supervised SR models can be augmented to broadly handle the real-world degradation in a plug-and-play style. Furthermore, to promote the efficiency of combining internal/external learning, we apply an attention-based weight-updating method to guide the mining of self-similarity, and various data augmentations are adopted while applying the exponential moving average strategy. We conduct extensive experiments on real-world degraded images and our approach outperforms other methods in both qualitative and quantitative comparisons. Our project is available at: https://github.com/ZahraFan/AdaSSR/.
BibTeX
@article{fan2024toward,
author = {Zejia Fan and Wenhan Yang and Zongming Guo and Jiaying Liu},
title = {{Toward Real-World Super Resolution With Adaptive Self-Similarity Mining}},
journal = {IEEE Trans. Image Process.},
year = {2024},
url = {https://openreview.net/forum?id=J44CCyi5Sh},
}Loading related content...