Title | ||
---|---|---|
Video Super-Resolution Reconstruction Based on Deep Learning and Spatio-Temporal Feature Self-Similarity |
Abstract | ||
---|---|---|
To address the problems in the existing video super-resolution methods, such as noise, over smooth and visual artifacts, which are caused by the reliance on limited external training or mismatch of internal similarity patch instances, this study proposes a novel video super-resolution reconstruction algorithm based on deep learning and spatio-temporal feature similarity (DLSS-VSR). The video super-resolution reconstruction mechanism with the joint internal and external constraints is established utilizing the complementary advantages of both external deep correlation mapping learning and internal spatio-temporal nonlocal self-similarity prior constraint. A deep learning model based on deep convolutional neural network is constructed to learn the nonlinear correlation mapping between low-resolution and high-resolution video frame patches. A novel spatio-temporal feature similarity calculation method is proposed, which considers both internal video spatio-temporal self-similarity and external clean nonlocal similarity. For the internal spatio-temporal feature self-similarity, we improve the accuracy and robustness of similarity matching by proposing a similarity measure strategy based on spatio-temporal moment feature similarity and structural similarity. The external nonlocal similarity prior constraint is learned by the patch group-based Gaussian mixture model. The time efficiency for spatio-temporal similarity matching is further improved based on saliency detection and region correlation judgment strategy, which achieves a better tradeoff between super-resolution accuracy and speed. Experimental results demonstrate that the DLSS-VSR algorithm achieves competitive super-resolution quality compared to other state-of-the-art algorithms in both subjective and objective evaluations. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TKDE.2020.3034261 | IEEE Transactions on Knowledge and Data Engineering |
Keywords | DocType | Volume |
Video super-resolution,deep learning,deep convolutional neural network,spatio-temporal nonlocal similarity,pseudo-Zernike moment | Journal | 34 |
Issue | ISSN | Citations |
9 | 1041-4347 | 1 |
PageRank | References | Authors |
0.36 | 28 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Meiyu Liang | 1 | 18 | 8.56 |
Junping Du | 2 | 789 | 91.80 |
Linghui Li | 3 | 1 | 0.36 |
Zhe Xue | 4 | 72 | 14.60 |
Xiaoxiao Wang | 5 | 1 | 0.36 |
Feifei Kou | 6 | 1 | 0.36 |
Xu Wang | 7 | 1 | 0.36 |