EvSTVSR: Event Guided Space-Time Video Super-Resolution

Introducing event cameras into video super-resolution (VSR) shows great promise. In practice, however, integrating event data as a new modality necessitates a laborious model architecture design. This not only consumes substantial time and effort but also disregards valuable insights from successful existing VSR models. Furthermore, the resourceintensive process of retraining these newly designed models exacerbates the challenge. In this paper, inspired by the recent success of parameterefficient tuning in reducing the number of trainable parameters of a pretrained model for downstream tasks, we introduce the Event AdapTER (EATER) for VSR. EATER efficiently utilizes knowledge of VSR models at the feature level through two lightweight and trainable components: the event-adapted alignment (EAA) unit and the event-adapted fusion (EAF) unit. The EAA unit aligns multiple frames based on the event stream in a coarse-to-fine manner, while the EAF unit efficiently fuses frames with the event stream through a multi-scale design. Thanks to both units, EATER outperforms the full fine-tuning approach with parameter efficiency, as demonstrated by comprehensive experiments.