No Detail Found!

Reviving Visuals: A Deep Learning Approach to Image Restoration and Enhancement

Author(s)
Syed Muhammad Daniyal Iqra University. Pakistan
Umer Hussain Qidwai FAST, NUCES, Pakistan
Faiza Latif Abbasi Iqra University , Pakistan
Abdul Khaliq Institute of Business Management.Country , Pakistan
Noman Bin Zahid Iqra University, Pakistan
Mohsin Mubeen Abbasi Iqra University, Pakistan
Abstract
In modern developments in image synthesis, neural networks are used to decode the random generation of latent code into high-quality images. These still cannot offer any easy way to alter to real image alteration. A type called model inversion tries to recover a latent code, which, when encoded back into an image, is similar to a target image. The approaches currently do not consider the possibility of picture modification on a semantic level in search of an accurate pixel. The study empowers an indomain constrained least squares inversion (CLSI) approach that mixes a domain-traversed encoder with a domain-regularized optimizer to circumvent this. The way enables the neural network to rely on its innate knowledge to perform both flexible editing and image reconstruction without the need for re-training by embedding the inverted code within the latent space within the network. In this research, the effect of different encoder structures, initial point of inversion, and parameter spaces on the quality versus semantic editability trade-off is explored. The paper reveals the details about how neural networks accumulate the semantic properties in latent spaces. Further, the research enhances the versatility of editing and enhancement of recent developments in image generation models. As far as we know, in-domain CLSI also has a significant potential to produce high-quality images and support semantic edits that will make sense (both of which will improve the realworld image edits).
Publication Details
Page(s) 14-20
DOI DOI not available
Published Journal: Journal of Information & Communication Technology (JICT), Volume: 19, Issue: 1, Year: 2025

Request the full text from PASTIC

Keywords
Image reconstruction, Semantic Image Editing, Latent Space Inversion, Constrained Least Squares Inversion (CLSI)
References
Rai D.,Rajput S. S. .2023 .A new face reconstruction technique for noisy low-resolution images using regression learning. ” Computers and Electrical Engineering, 107 : 108642.
Rai D.,Rajput S. S. .2023 .Low-light robust face image super-resolution via neuro-fuzzy inferencing-based locality-constrained representation. ” IEEE Transactions on Instrumentation and Measurement, 72 : 1-11.
Tai L.,Zhang L.,Zhou X.,Zhang S. .2023 .Research on image restoration processing based on Gaussian blur algorithm. in Proceedings of the 2023 3rd International Signal Processing, Communications and Engineering Management Conference (ISPCEM), : 384-389.
Li X.,Dong W.,Wu J.,Li L. .2023 .Superresolution image reconstruction: Selective milestones. ” IEEE Signal Processing Magazine, 40(5) : 54-66.
Atali G.,Kosal H. H.,Pekyaman M. .2023 .A new image restoration model associated with special elliptic quaternionic least-squares solutions based on LabVIEW,”. Journal of Computational and Applied Mathematics, 425 : 115071.
Daniyal S. M.,Masood A.,Ebrahim M.,Adil S. H.,Raza K. .2024 .An improved face recognition method based on convolutional neural network. ” Journal of Independent Studies and Research Computing, 22(1) : 103-110.
Qi P.,Zhang Z.,Feng X.,Lai P.,Zheng Y. .2024 .Asymmetric forward-inverse reinforcement framework for image reconstruction through scattering media,” Optics and Laser Technology. , 179 : 111222.
Zhai L.,Wang Y.,Cui S.,Zhou Y. .2023 .A comprehensive review of deep learning-based real-world image restoration,” IEEE Access. , 11 : 21049-21067.
Dhouioui M.,Frikha T.,Drira H.,Abid M. .2023 .A novel 3D face reconstruction model from a multi-image 2D set,”. in Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP), 5 : 745-753.
A. M. F. Goujon .2024 .Towards Trustworthy Deep Learning for Image Reconstruction. , 10667 : .
Hou X.,Shen L.,Ming Z. .2023 .Deep generative image priors for semantic face manipulation,” Pattern Recognition. , 139 : 109477.
Kamyab S.,Azimifar Z.,Sabzi R.,Fieguth P. .2022 .Deep learning methods for inverse problems,” PeerJ Computer Science. , 8 : e951.
Liu Y.,Qiao Y.,Hao Y.,Wang F.,Rashid S. F. .2021 .Single image super-resolution techniques based on deep learning: Status, applications. ” Journal of Image and Graphics, 9(3) : 74-86.
Zhang Z.,Yezzi A. J. .2022 .Formulating event-based image reconstruction as a linear inverse problem with deep regularization using optical flow. ” IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7) : 8372-8389.
Jiang J.,Wang C.,Liu X. .2021 .Deep learningbased face super-resolution: A survey,” ACM Computing Surveys (CSUR). , 55(1) : 1-36.
Usha S. G. A.,Maheswari P. U.,Bharathi K.,Jeevalakshmi V. .2025 .Next-generation image enhancement and restoration with artificial intelligence,” in Modern Intelligent Techniques for Image Processing. IGI Global Scientific Publishing, : 249-268.
Masood A.,Daniyal S. M.,Ibrahim H. .2025 .Enhancing skin cancer detection: A study on feature selection methods for image classification. International Journal of Innovations in Science and Technology, 7(1) : 272-285.
Anandhi A. Senthil,Jaiganesh M. .2025 .An enhanced image restoration using deep learning and transformer based contextual optimization algorithm,” Scientific Reports. , 15(1) : 10324.
Qayyum A.,Ilahi I.,Shamshad F.,Boussaid F.,Bennamoun M.,Qadir J. .2022 .Untrained neural network priors for inverse imaging problems: A survey,”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5) : 6511-6536.
Abbasi F. L.,Ebrahim M.,Abro A. A.,Daniyal S. M.,and I. Younus S. M. .2025 .CNN-based face detection focusing on diverse visual variations,” in Navigating Challenges of Object Detection Through Cognitive Computing. IGI Global Scientific Publishing, : 63-96.
Vendrow E.,Vendrow J. .2021 .Realistic face reconstruction from deep embeddings. NeurIPS 2021 Workshop on Privacy in Machine Learning, : .
Dong X.,Miao Z.,Shen J.,Jin Z.,Guo Z.,Teoh A. B. J. .2022 .Reconstruct face from features using a GAN generator as a distribution constraint. ” arXiv preprint arXiv:2206.04295, : .
Wan Z.,Zhang B.,Chen D.,Zhang P.,Wen F.,Liao J. .2022 .Old photo restoration via deep latent space translation. ” IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(2) : 2071-2087.
Wang T.,Zhang K.,Chen X.,Luo W.,Deng J.,Lu T. .2022 .“A survey of deep face restoration: Denoise, superresolution. ” arXiv preprint arXiv:2211.02831, : .
Daniyal S. M.,Hussain S. M. T.,Abbasi F. L.,Hussain D.,M. M. Abbasi D. .2024 .A hybrid deep learning model for precise epilepsy detection and seizure prediction,” Spectrum of Engineering Sciences. , 2(3) : 62-77.
Rastogi R.,Rawat V.,Kaushal S. . .Advancements in image restoration techniques: A comprehensive review. , : .
Daniyal S. M.,Amjad U.,Khaliq A.,Zahid N. B.,Abbasi F. L.,Hussain S. M. T. .2024 .Analyzing student's emotions in the classroom: A deep learning approach to facial expression recognition. International Journal of Artificial Intelligence & Mathematical Sciences, 3(1) : 11-19.
Wang Y.,Song W.,Fortino G.,Qi L. Z.,Zhang W.,Liotta A. .2019 .An experimental-based review of image enhancement and image restoration methods for underwater imaging. ” IEEE Access, 7 : 140233-140251.
0

Citations

0

Downloads

39

Views