A Joint Framework of GFP-GAN and Real-ESRGAN for Real-World Image Restoration

ba60f6118d1e33cbb5-7d12 20240121014731201 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Innovative Technology and Exploring Engineering IJITEE 22783075 10.35940/ijitee https://www.ijitee.org/ 01 30 2024 13 2 A Joint Framework of GFP-GAN and Real-ESRGAN for Real-World Image Restoration Department of Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Academic Block, Cumilla, Chittagong, Bangladesh. Mousumi Hasan https://orcid.org/0009-0006-7499-7669 Nusrat Jahan Nishat Department of Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Academic Block, Cumilla, Chittagong, Bangladesh. Tanjina Rahman Department of Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Academic Block, Cumilla, Chittagong, Bangladesh. Mujiba Shaima Department of Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Academic Block, Cumilla, Chittagong, Bangladesh. Quazi Saad ul Mosaher Department of Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Academic Block, Cumilla, Chittagong, Bangladesh. Mohd. Eftay Khyrul Alam Department of Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Academic Block, Cumilla, Chittagong, Bangladesh. In the current era of digitalization, the restoration of old photos holds profound significance as it allows us to preserve and revive cherished memories. However, the limitations imposed by various websites offering photo restoration services prompted our research endeavor in the field of image restoration. Our motive originated from the personal desire to restore old photos, which often face constraints and restrictions on existing platforms. As individuals, we often encounter old and faded photographs that require restoration to revive the emotions and moments captured within them. The limits of existing photo restoration services prompted us to conduct this research, with the ultimate goal of contributing to the field of image restoration. To address this issue, we propose a joint framework that combines the Real-ESRGAN and GFP-GAN methods. Our recommended joint structure has been thoroughly tested on a broad range of severely degraded image datasets, and it has shown its efficiency in preserving fine details, recovering colors, and reducing artifacts. The research not only addresses the personal motive for restoring old photos but also has wider applications in preserving memories, cultural artifacts, and historical records through an effective and adaptable solution. Our deep learning-based approach, which leverages the synergistic capabilities of Real-ESRGAN and GFP-GAN, holds immense potential for revitalizing images that have suffered from severe degradation. This proposed framework opens up new avenues for restoring the visual integrity of invaluable historical images, thereby preserving precious memories for generations to come. 01 30 2024 32 42 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true International Journal of Innovative Technology and Exploring Engineering (IJITEE) No, I did not receive. No conflicts of interest to the best of our knowledge. No, the article does not require ethical approval and consent to participate with evidence. Reference[3] Mousumi Hasan: Developed the initial research idea. Designed methodology and experimental approach. Drafting initial version of the paper and analysis the experimental results. Conducted data analyses . Nusrat Jahan Nishat:: As a second author she Actively participated in the research process, including data collection, analysis, and interpretation. Contributed to the review of relevant literature in the field. Tanjina Rahman: Offered insights into prior research that informs the current work. Assisted and wrote the literature review. Mujiba Shaima:Assisted in writing, data pre-processing, implementing and editing revised paper . Quazi Saad ul Mosaher: Collaborated with the authors to coordinate the manuscript preparation and result analysing and presenting. Mohd. Eftay Khyrul Alam: Created visual representations of data and assisted in analysis project. 10.35940/ijitee.B9792.13020124 https://www.ijitee.org/portfolio-item/B979213020124/