Fast event image filling method and system based on lightweight generative adversarial network

Abstract

The invention discloses a fast event image filling method and system based on a lightweight generative adversarial network. The fast event image filling method based on the lightweight generative adversarial network comprises the following steps: constructing the lightweight generative adversarial network; obtaining training data, wherein the training data comprises a plurality of pairs of matchedloss event images and non-loss event images; optimizing the lightweight generative adversarial network by using the training data to obtain optimal network parameters; and obtaining a loss event image to be filled, and inputting the loss event image to be filled into the lightweight generative adversarial network based on the optimal network parameters to obtain a filled event image output by thelightweight generative adversarial network. According to the rapid event image filling method and system based on the lightweight generative adversarial network, the sparse characteristic of the event image is fully utilized, and the authenticity and fineness of an image filling structure are improved.

Description

technical field [0001] The present application belongs to the technical field of image processing, and specifically relates to a method and system for fast event image filling based on a lightweight generative confrontation network. Background technique [0002] Event-based Camera (Event-based Camera, or simply Event Camera, abbreviated as EB. Sometimes also called DVS (Dynamic Vision Sensor, dynamic vision sensor)) is a new type of sensor. Unlike traditional cameras that capture a complete image, event cameras capture "events", which can be simply understood as "changes in pixel brightness", that is, the output of event cameras is the change in pixel brightness. [0003] Currently, event cameras are capable of generating sparse event streams and capturing high-speed motion information, however, as the temporal resolution increases, the spatial resolution decreases dramatically. Although Generative Adversarial Networks have achieved remarkable results in traditional image i...

AI Technical Summary

Problems solved by technology

[0003] Currently, event cameras are capable of generating sparse event streams and capturing high-speed motion information, however, as temporal resolution increases, spatial resolution decreases dramatically

Although generative adversarial networks have achieved remarkable results in traditional image restoration, using them directly for event filling will bury the fast response characteristics of event cameras, and the sparsity of event streams is not fully utilized

Images