Sketch to Image using GAN


Authors : Sumit Gunjate; Tushar Nakhate; Tushar Kshirsagar; Yash Sapat

Volume/Issue : Volume 8 - 2023, Issue 1 - January

Google Scholar : https://bit.ly/3IIfn9N

Scribd : https://bit.ly/3Y1l7U6

DOI : https://doi.org/10.5281/zenodo.7588232

Abstract : With the development of the modern age and its technologies, people are discovering ways to improve, streamline, and de-stress their lives. A difficult issue in computer vision and graphics is the creation of realistic visuals from hand-drawn sketches. There are numerous uses for the technique of creating facial sketches from real images and its inverse. Due to the differences between a photo and a sketch, photo/sketch synthesis is still a difficult problem to solve. Existing methods either require precise edge maps or rely on retrieving previously taken pictures. In order to get around the shortcomings of current systems, the system proposed in this paper uses generative adversarial networks. A type of machine learning method is called a generative adversarial network (GAN). This algorithm pits two or more neural networks against one another inthe context of a zero-sum game. Here, we provide a generative adversarial network (GAN) method for creating convincing images. Recent GAN-based techniques for sketch-to-image translation issues have produced promising results. Our technology produces photos that are more lifelike than those made by other techniques. According to experimental findings, our technology can produce photographs that are both aesthetically pleasing and identity-Preserving using a variety of difficult data sets.

Keywords : Image Processing, Photo/Sketch Synthesis.

With the development of the modern age and its technologies, people are discovering ways to improve, streamline, and de-stress their lives. A difficult issue in computer vision and graphics is the creation of realistic visuals from hand-drawn sketches. There are numerous uses for the technique of creating facial sketches from real images and its inverse. Due to the differences between a photo and a sketch, photo/sketch synthesis is still a difficult problem to solve. Existing methods either require precise edge maps or rely on retrieving previously taken pictures. In order to get around the shortcomings of current systems, the system proposed in this paper uses generative adversarial networks. A type of machine learning method is called a generative adversarial network (GAN). This algorithm pits two or more neural networks against one another inthe context of a zero-sum game. Here, we provide a generative adversarial network (GAN) method for creating convincing images. Recent GAN-based techniques for sketch-to-image translation issues have produced promising results. Our technology produces photos that are more lifelike than those made by other techniques. According to experimental findings, our technology can produce photographs that are both aesthetically pleasing and identity-Preserving using a variety of difficult data sets.

Keywords : Image Processing, Photo/Sketch Synthesis.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe