• Supriya Madhukar Shilwant
• Dr.Satish N.Gujar

Face image restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, propose the modification of the GAN that leverages rich and diverse priors encapsulated in a pre trained face GAN for face restoration. This new GAN is incorporated into the face restoration process via spatial feature transform layers. Because of the powerful generative facial prior and delicate designs, this new GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require image-specific optimization at inference. With this new GAN we may achieve superior performance on both synthetic and real-world datasets. Image generation has attracted broad attention in recent years. Within these works, synthesizing a face from different angles while retaining identity is an important task, because of its wide range of industrial applications, such as video monitoring and face analysis. Recently, this task has been greatly advanced by a number of models of Generative Adversarial Networks. To tackle the task of face reconstruction, existing approaches typically apply predefined parameterized 3D models or Convolution Neural Network (CNN) to represent face. Despite exhibiting promising ability in describing faces, different head poses positioning has obvious deviation. In addition, the methods cannot describe complex expressions and facial postures. , Therefore, complex parametric fitting requires lots of precise data and detailed descriptions. Generative adversarial networks have recently demonstrated excellence in image editing which shows great potential in producing realistic images.

Image Processing, Deep Neural Networks

"Facial Blind Image Restoration Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.h538-h540, May 2022, Available :http://www.jetir.org/papers/JETIR2205872.pdf

"Facial Blind Image Restoration Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. pph538-h540, May 2022, Available at : http://www.jetir.org/papers/JETIR2205872.pdf