Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{172521,
        author = {Onkar Nigdikar and Manisha Darak and Harsh Patil and Aakash Patil and Aniket Margale},
        title = {Comprehensive Survey On Forensic Sketch Transformation To Realistic Image},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {42-45},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172521},
        abstract = {In this survey paper, we overview the recent advances of the sketch-to-photo transformation especially using deep learning techniques with basic concepts from computer vision and generative modeling. The paper includes details regarding how sketch to photo tasks is accomplished using various techniques like image translation as well as use of Generative Adversarial Networks (GANs) in this context. Transforming sketch drawing into clear and photo-realistic images to assist with crime solving has become important issue when it comes to identify criminals based on limited visual data. We will examine the main techniques used and also discuss their advantages, limitations and suitability for real world application. The purpose of this paper is to combine much of available experience and knowledgebase.},
        keywords = {Cycle Generative Adversarial Network (CycleGAN), Deep Convolutional Generative Adversarial Network (DCGAN), Generative Adversarial Network (GAN), Pix2Pix.},
        month = {January},
        }