Copyright © 2026 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{194884,
        author = {Harshitha Vekanuru and Mohammad Abdul Muqeethh and Yannam Suryaprakash Reddy},
        title = {MaskOff-GAN: Intelligent Face Reconstruction Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6642-6649},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194884},
        abstract = {Deep learning-based face mask removal has drawn significant interest with its usage in facial recognition, healthcare, and security. In this paper, a new deep learning-based technique for reconstructing unmasked faces from masked faces is pre- sented. The technique utilizes Generative Adversarial Networks (GANs) for image-to-image translation to produce realistic un- masked face images with critical facial attributes such as identity and expression preserved. The model is trained using large-scale masked face datasets and learns to recover the occluded regions with high precision. State-of-the-art image inpainting techniques are also integrated to enhance the quality of reconstruction, with the results being natural and seamless. Experimental results indicate that the proposed model performs better than traditional techniques, with better reconstruction quality and fewer artifacts. The technique can be employed to enhance face recognition systems in scenarios where face masks are widely utilized.},
        keywords = {Face mask removal, deep learning, GANs, im- age inpainting, facial reconstruction, face recognition, occlusion recovery.},
        month = {March},
        }