Dense Dual-Attention Network for Light Field Image Super-Resolution

Light field (LF) images can be used to improve the performance of image super-resolution (SR) because both angular and spatial information is available. It challenging incorporate distinctive from different views for LF SR. Moreover, long-term previous layers weakened as depth network increases. In this paper, we propose a dense dual-attention Specifically, design view attention module adaptively capture discriminative features across channel selectively focus on informative all channels. These two modules are fed branches stacked separately in chain structure adaptive fusion hierarchical distillation valid information. Meanwhile, connection fully exploit multi-level Extensive experiments demonstrate that our mechanism channels SR performance. Comparative results show advantage method over state-of-the-art methods public datasets.