PENERAPAN MODEL ESRGAN UNTUK UPSCALING CITRA DAN VIDEO DIGITAL
##plugins.themes.academic_pro.article.main##
Abstract
Low-resolution images and videos remain a common problem in various digital applications due to limited visual quality. Conventional interpolation-based upscaling methods often produce blurry results and lead to the loss of important texture details. This study aims to apply the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) to improve the resolution of digital images and videos. The dataset used consists of low-resolution images and videos that are processed through preprocessing, model training, and testing stages using the Google Colab environment. The ESRGAN model is trained to generate high-resolution images while preserving visual details and structural information. Model performance is evaluated using the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and visual comparison between images before and after the upscaling process. The results show that ESRGAN significantly improves the quality of images and videos compared to conventional interpolation methods, both quantitatively and qualitatively. Therefore, the application of ESRGAN is considered effective for enhancing the resolution of digital images and videos and can be utilized in applications that require high visual quality.
##plugins.themes.academic_pro.article.details##
References
Brau, F., Rossolini, G., & Buttazzo, G. (n.d.). Video Deblurring by Sharpness Prior Detection and Edge Information.
Chen, Z., Zamfir, E., Zhang, K., Timofte, R., Lin, J., Zhao, K., Dou, Z., Wang, G., Lee, C., Chen, H., Chen, S., Park, G., Uddin, S. M. N., Orais, I., & Xu, K. (2024). NTIRE 2024 Challenge on Image Super-Resolution ( × 4 ): Methods and Results.
Faisal, M., Rahman, Shabir, F., & Ida. (2018). Design and Implementation of Plantation Commodities Price Information Broadcaster via Autoreply Short Message Service on Smartphone. Proceedings - 2nd East Indonesia Conference on Computer and Information Technology: Internet of Things for Industry, EIConCIT 2018, 212–217. https://doi.org/10.1109/EIConCIT.2018.8878575
Faisal, M., Rahman, T. K. A., Mulyadi, I., Aryasa, K., Irmawati, & Thamrin, M. (2024). A Novelty Decision-Making Based on Hybrid Indexing, Clustering, and Classification Methodologies: An Application to Map the Relevant Experts Against the Rural Problem. Decision Making: Applications in Management and Engineering, 7(2), 132–171. https://doi.org/10.31181/dmame7220241023
Hu, L., Hu, L., & Chen, M. (2024). Edge ‑ enhanced infrared image super ‑ resolution reconstruction model under transformer. Scientific Reports, 1–14. https://doi.org/10.1038/s41598-024-66302-8
Huang, J., Li, K., Jia, J., & Wang, X. (2025). Single Image Super-Resolution Through Image Pixel Information Clustering and Generative Adversarial Network. 8(5), 1044–1059. https://doi.org/10.26599/BDMA.2025.9020007
Li, F., Wu, Y., Li, A., Bai, H., Cong, R. M. I. N., & Zhao, Y. A. O. (2026). Enhanced Video Super-Resolution Network towards Compressed Data Enhanced Video Super-Resolution Network towards. 20(7). https://doi.org/10.1145/3651309
Maity, A., Pious, R., Lenka, S. K., Choudhary, V., & Lokhande, S. (2023). A Survey on Super Resolution for video Enhancement Using GAN.
Velagaleti, S. B., Mohite, S. S., Apare, R. S., Rao, A. L. N., Srivastava, A., Bansal, S., & Shrivastava, A. (2024). INTELLIGENT SYSTEMS AND APPLICATIONS IN ENGINEERING Image Super-Resolution with Deep Learning : Enhancing Visual Quality using SRCNN. 12, 479–486.
Wang, Y., Isobe, T., Lu, H., & Tai, Y. (2012). Compression-Aware Video Super-Resolution. 1, 2012–2021.