Event Temporal Upsampling through High Frame Rate Brightness Changes Estimation

Event cameras offer unique advantages such as high temporal resolution and low power consumption. However, under slow-motion or low-light scenarios, the resulting event streams are often sparse, limiting the performance of event-based vision algorithms. In this paper, we propose a novel temporal upsampling framework that enhances the temporal resolution of sparse events by estimating high-frame-rate brightness changes. Our method first reconstructs long-term brightness changes from sparse input events using a neural network, then optimizes short-term high-frame-rate brightness variations through a spatiotemporal smoothness and sparsity-constrained model. Following the generation principle of event cameras, new events are synthesized when estimated brightness changes exceed the firing threshold. To evaluate the effectiveness of our method, we construct a temporal upsampling dataset and introduce two event-based metrics to directly assess the quality of upsampled events. Extensive experiments demonstrate that our approach can generate denser and more informative events, significantly enhancing the performance of downstream tasks, including image reconstruction, optical flow estimation, and object detection in sparse conditions.