Achieving Excellence in Exploration and Exploitation by Matching Appropriate Resources

Image super-resolution (SR) is widely used in remote sensing because it can effectively increase image details. Neural networks have shown remarkable performance in recent years, benefitting from their end-to-end training. However, remote sensing images contain a variety of degradation factors. Neural networks lack flexibility in dealing with these complex issues compared with reconstruction-based approaches. Traditional neural network methods can not take advantage of prior knowledge and lack interpretability. To develop a flexible, accurate, and interpretable algorithm for remote sensing SR, we proposed an effective SR network called YSRNet. It is performed by unfolding a traditional optimization process into a learnable network. Combining conventional reconstruction-based methods and neural networks can significantly improve the algorithm's performance. Since the gradient features of remote sensing images contain valuable information, the total variation (TV) constraints and the deep prior constraints are introduced into the objective function for image SR. Furthermore, we propose an enhanced version called YSRNet+, which can apply attention weights to different prior terms and channels. Compared with the YSRNet, the YSRNet+ enables networks to focus more on useful prior information and improve the interpretability of networks. Experiments on three remote sensing datasets are performed to evaluate the algorithm's effectiveness. The experimental results demonstrate that the proposed algorithm performs better than some state-of-the-art neural network algorithms, especially in the scenario of the multi-degradation factors.

show abstract

“…The structure of the Res-block is shown in Eq. (13). Each residual block connects the input to the output using a skip connection.…”

Section: B Unfolding Network Frameworkmentioning

confidence: 99%

“…R EMOTE sensing images are widely used in target recognition and detection [1]- [6], land classification [7]- [12], resource exploration [13], etc. However, due to remote sensing images mostly covering a large area of the ground, the image resolution is usually low, degrading real-world applications' performance.…”

Section: Introductionmentioning

confidence: 99%

Double Prior Network for Multidegradation Remote Sensing Image Super-Resolution

Shi

Gao

Chen

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The exploration-exploitation model for innovation is well known-there is basic and applied research [3]. According to Guttman and Lang in the third TMN article, the managing of this research balance is not easy in organizations.…”

Section: Tmn Articlesmentioning

confidence: 99%