Auto Encoder Driven Hybrid Pipelines for Image Deblurring using NAFNET

The project introduces an innovative solution to the persistent challenge of image blurring in the realm of Computer Vision. Leveraging the synergies between auto-encoder structures and Non-Linear Activation Free Networks (NAFNET), the proposed methodology aims to achieve superior image restoration results by effectively addressing diverse types of blur. This approach offers a holistic solution that combines the strengths of traditional methods and state-of-the-art deep learning techniques. Quantitative evaluation using metrics demonstrates the efficacy of the proposed methodology in achieving superior deblurring results compared to existing techniques. By pushing the boundaries alongside of image deblurring capabilities, the project contributes to the advancement of the field and holds promise for applications across various domains, including photography, medical imaging, and surveillance.