The purpose of this project is to provide a practical alternative that approximates the underlying solution by learning-based methods. Several models based on deep Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) provide state-of-the art performance in learning, to enhance perceptual image quality from a large collection of paired or unpaired data. Hence, an attempt to address these challenges is done by designing a RAPID UNDERWATER IMAGE ENHANCEMENT model and analyzing its feasibility for real-time applications.
- Enhances the given underwater image into clear image in millisecons
- uses FUIGAN Model
- Generates Graphs for Better Visualization
- Simple UI for using the Model
Md Jahidul Islam https://github.com/xahidbuffon/FUnIE-GAN