Local-Global Dynamic Filtering Network for Video Super-Resolution

Video super-resolution (VSR) has been greatly advanced by the use of deep learning techniques, but the challenge of handling motion variability has remained a bottleneck. Many previous methods have treated motions equally, leading to suboptimal alignment. In this article, we propose a Local-Global Dynamic Filtering Network (LGDFNet) to address this issue. LGDFNet uses a divide-and-conquer strategy to handle motion-varying features, where the overall feature is split into local features and assigned specialized sub-networks to align and fuse them from local to global. To align the features and adaptively aggregate several kernels for calibration, we propose the Self-Calibrated Dynamic Filtering (SCDF) module. Additionally, we introduce the Cross-Attention Feature Fusing (CAFF) module to capture long-range dependencies and fuse each feature. Our extensive experiments on different benchmark datasets demonstrate the effectiveness of LGDFNet, both subjectively and objectively.