A Novel Dual Dense Connection Network for Video Super-resolution
This work addresses the problem of generating high-resolution videos from low-resolution inputs for applications in video enhancement, but it appears incremental as it builds on existing VSR methods with specific improvements.
The paper tackles video super-resolution by proposing a dual dense connection network that groups input frames into reference and temporal groups to avoid time information disorder, and introduces a new loss function to enhance convergence, achieving superior results on Vid4 and SPMCS-11 datasets compared to other advanced models.
Video super-resolution (VSR) refers to the reconstruction of high-resolution (HR) video from the corresponding low-resolution (LR) video. Recently, VSR has received increasing attention. In this paper, we propose a novel dual dense connection network that can generate high-quality super-resolution (SR) results. The input frames are creatively divided into reference frame, pre-temporal group and post-temporal group, representing information in different time periods. This grouping method provides accurate information of different time periods without causing time information disorder. Meanwhile, we produce a new loss function, which is beneficial to enhance the convergence ability of the model. Experiments show that our model is superior to other advanced models in Vid4 datasets and SPMCS-11 datasets.