Intensity-Image Reconstruction Using Event Camera Data by Changing in LSTM Update

Event cameras offer many advantages, but their output is inherently ambiguous and needs to be converted into a more understandable output. One way to use the output of these cameras is to reconstruct the intensity. Various methods have been proposed for image reconstruction using event data, each attempting to improve image quality from specific aspects. In this study, we aim to increase image quality in a challenging condition when the number of events is very low or zero without retraining or changing the network structure during training. Another challenging situation is at the initial start-up moment which requires an initialization time. In this study, we used the potential of the E2VID model and increased the video quality without changing the trained model. Our method performs better than the E2VID method with an 11.9% improvement in the first 10 frames and a 2% improvement in entire videos in SSIM metric