Client-Side Real-Time Inference untuk Efisiensi Bandwidth: Komparasi Lightweight Super-Resolution ESPCN dan FSRCNN Berbasis Browser pada Web Retail
DOI:
https://doi.org/10.47065/bulletincsr.v6i5.1263Keywords:
Lightweight Super-Resolution; Bandwidth Efficiency; Client-Side Inference; ESPCN; FSRCNN; Web PerformanceAbstract
Indonesia's rapidly expanding e-commerce industry demands high-quality product imagery, yet directly distributing high-resolution images imposes a significant bandwidth burden particularly on fluctuating mobile network infrastructures. Prior research on client-side visual processing has focused on video streaming, while Lightweight Super-Resolution (LSR) architecture development has been conducted exclusively in native computing environments leaving an empirical gap in browser-based LSR deployment for retail web platforms. This study bridges that gap by implementing and comparing two LSR architectures ESPCN and FSRCNN executed directly within the browser using TensorFlow.js with WebGL acceleration on the CV Citra Wyrus Sakti retail web platform. Evaluation was conducted on 28 industrial product image samples across three dimensions: bandwidth efficiency, cross-device inference time, and visual restoration quality. Results demonstrate that this approach reduces average bandwidth consumption by 50.1%, directly translating to a Lighthouse Performance score increase from 79 to 99 and a Largest Contentful Paint (LCP) reduction from 3.8 seconds to 0.8 seconds. ESPCN proved 1.84× faster than FSRCNN on laptops and 1.52× faster on mobile devices, while also outperforming in restoring edge sharpness and texture detail without excessive smoothing artifacts. The main contribution of this study is twofold: it provides one of the first empirical comparisons of client-side LSR inference on real-world e-commerce product imagery, and it delivers a reusable browser-based deployment framework combining TensorFlow.js, WebGL acceleration, and an HR–LR preprocessing pipeline that Indonesian retail platforms can adopt without native-side infrastructure changes. ESPCN is recommended as the optimal architecture for balancing bandwidth efficiency with e-commerce visual aesthetics within browser environments.
Downloads
References
P. Putra Dharma, M. S. Purwanegara, and S. A. Wibowo, “Proposed Marketing Strategy to Increase Brand Loyalty: Study Case of Lazada Indonesia,” International Journal of Current Science Research and Review, vol. 7, no. 7, pp. 4701–4716, 2024, doi: 10.47191/ijcsrr/v7-i7-15.
W. A. Social and Meltwater, “Digital 2024: Indonesia,” DataReportal, 2024. [Online]. Available: https://wearesocial.com/id/wp-content/uploads/sites/19/2024/02/Digital_2024_Indonesia.pdf
M. G. Mokobombang and N. Kusumawati, “Impact of Product Description, Product Photo, Rating, and Review on Purchase Intention in E-Commerce,” Journal of Consumer Studies and Applied Marketing, vol. 1, no. 2, pp. 137–147, 2023, doi: 10.58229/jcsam.v1i2.100.
Y. Yang, Q. Yang, and X. Liu, “Seeing the Feel, Willing to Buy: How Visual–Tactile Cues Shape Consumer Purchase Intention in E-Commerce Platforms,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 21, no. 3, p. 84, Mar. 2026, doi: 10.3390/jtaer21030084.
B. Dornauer and M. Felderer, “Web Image Formats: Assessment of Their Real-World-Usage and Performance Across Popular Web Browsers,” in Product-Focused Software Process Improvement, vol. 14483, R. Kadgien, A. Jedlitschka, A. Janes, V. Lenarduzzi, and X. Li, Eds., Cham: Springer, 2024, pp. 132–147. doi: 10.1007/978-3-031-49266-2_9.
K. Król and W. Sroka, “Internet in the Middle of Nowhere: Performance of Geoportals in Rural Areas According to Core Web Vitals,” ISPRS Int. J. Geoinf., vol. 12, no. 12, p. 484, Nov. 2023, doi: 10.3390/ijgi12120484.
Patrick Welay, Caroline Herfisia Parlina, Ivena Julia Armelinda, and Jadiaman Parhusip, “The Distribution Of Average Mobile Network Speeds In Indonesia Based On Ookla Data,” Informatika: Jurnal Teknik Informatika dan Multimedia, vol. 4, no. 2, pp. 24–29, Dec. 2024, doi: 10.51903/informatika.v4i2.825.
N. Salsi Anugrah, H. Adilah, D. P. Panggabean, and R. P. Laksana, “Analisis Kecepatan Internet Seluler Di Indonesia Berdasarkan Regional,” Journal of Data Analytics, Information, and Computer Science, vol. 2, no. 2, pp. 155–158, Apr. 2025, doi: 10.70248/jdaics.v2i2.1821.
V. I. Ungureanu, P. Negirla, and A. Korodi, “Image-Compression Techniques: Classical and Region-of-Interest-Based Approaches Presented in Recent Papers,” Sensors, vol. 24, no. 3, p. 791, 2024, doi: 10.3390/s24030791.
A. Liu, Y. Liu, J. Gu, Y. Qiao, and C. Dong, “Blind Image Super-Resolution: A Survey and Beyond,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 5, pp. 5461–5480, 2023, doi: 10.1109/TPAMI.2022.3203009.
J. Guo et al., “AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, pp. 1582–1592. doi: 10.1109/CVPRW59228.2023.00160.
Z. Li et al., “Blueprint Separable Residual Network for Efficient Image Super-Resolution,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022, pp. 832–842. doi: 10.1109/CVPRW56347.2022.00099.
H. A. Goh, C. C. Ho, and F. S. Abas, “Front-end deep learning web apps development and deployment: a review,” Applied Intelligence, vol. 53, no. 12, pp. 15923–15945, 2023, doi: 10.1007/s10489-022-04278-6.
Q. Wang et al., “Anatomizing Deep Learning Inference in Web Browsers,” ACM Transactions on Software Engineering and Methodology, vol. 34, no. 2, 2025, doi: 10.1145/3688843.
J. Yang, Y. Jiang, and S. Wang, “Enhancement or Super-Resolution: Learning-Based Adaptive Video Streaming with Client-Side Video Processing,” in IEEE International Conference on Communications (ICC), 2022, pp. 739–744. doi: 10.1109/ICC45855.2022.9839262.
B. B. Moser, F. Raue, S. Frolov, S. Palacio, J. Hees, and A. Dengel, “Hitchhiker’s Guide to Super-Resolution: Introduction and Recent Advances,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 8, pp. 9862–9882, Aug. 2023, doi: 10.1109/TPAMI.2023.3243794.
J. Li et al., “A Systematic Survey of Deep Learning-Based Single-Image Super-Resolution,” ACM Comput. Surv., vol. 56, no. 10, pp. 1–40, Oct. 2024, doi: 10.1145/3659100.
M. Saeed Rad, T. Yu, C. Musat, H. Kemal Ekenel, B. Bozorgtabar, and J.-P. Thiran, “Benefiting from Bicubically Down-Sampled Images for Learning Real-World Image Super-Resolution,” in Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 1589–1598. doi: 10.1109/WACV48630.2021.00163.
M. Haverbeke, Eloquent JavaScript: A Modern Introduction to Programming, 4th ed. No Starch Press, 2022. [Online]. Available: https://eloquentjavascript.net
T. Jing, C. Liu, and Y. Chen, “A Lightweight Single-Image Super-Resolution Method Based on the Parallel Connection of Convolution and Swin Transformer Blocks,” Applied Sciences, vol. 15, no. 4, p. 1806, 2025, doi: 10.3390/app15041806.
A. Ignatov, R. Timofte, M. Denna, and A. A. R. Younes, “Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021, pp. 2525–2534. doi: 10.1109/CVPRW53098.2021.00286.
P. Walton and B. Pollard, “Optimize Largest Contentful Paint,” Web Dev. Accessed: Jul. 12, 2026. [Online]. Available: https://web.dev/articles/optimize-lcp
W. Zhou and Z. Wang, “Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity,” in Proceedings of the 30th ACM International Conference on Multimedia (MM), 2022, pp. 934–942. doi: 10.1145/3503161.3547899.
B. Möller, L. Görnhardt, and T. Fingscheidt, “A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only,” Procedia Comput. Sci., vol. 264, pp. 299–308, 2025, doi: 10.1016/j.procs.2025.07.141.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Client-Side Real-Time Inference untuk Efisiensi Bandwidth: Komparasi Lightweight Super-Resolution ESPCN dan FSRCNN Berbasis Browser pada Web Retail
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 Muhammad Nur, Carudin Carudin, Faizal Kurnia Ramdhana
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
