Published August 30, 2026 | Version CC-BY-NC-ND 4.0
Journal article Open

PixelBoost 8 – Pixel Quality with 8X Highlights Boosting Enhancement

Authors/Creators

  • 1. Department of Mechanical Engineering, Bharati Vidyapeeth's College of Engineering for Women, Pune (Maharashtra), India.

Contributors

Contact person:

  • 1. Department of Computer Science & Business Systems, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune (Maharashtra), India.
  • 2. Department of Mechanical Engineering, Bharati Vidyapeeth's College of Engineering for Women, Pune (Maharashtra), India.
  • 3. Department of Information Technology, Bharati Vidyapeeth's College of Engineering for Women, Pune (Maharashtra), India.
  • 4. Department of Instrumentation Engineering, Bharati Vidyapeeth College of Engineering, Navi Mumbai (Maharashtra), India.
  • 5. Basic Science and Engineering Department, SCTR's Pune Institute of Computer Technology, Pune (Maharashtra), India.
  • 6. Bharati Vidyapeeth (Deemed to be University) College of Nursing, Sangli (Maharashtra), India.

Description

Abstract: In recent years, deep learning has become a fundamental technology across a wide array of scientific and industrial fields, largely fuelled by advances in computational capabilities. One area that has experienced substantial progress is face hallucination—the task of improving the resolution of facial images. This process is critical to various computer vision applications, including facial recognition, feature extraction, and identity verification. Recently, deep generative models, particularly Generative Adversarial Networks (GANs), have led the field. Although these models have produced remarkable results, there is still a pressing need to further improve both accuracy and output quality. In order to address these problems, we propose a new GAN-based face hallucination method. This method is primarily based on the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN). We present a personalised adaptation of ESRGAN that employs the VGG16 architecture with a compact pre-trained version. This method balances output image quality and computational efficiency. Experiments show that our approach is effective. The improved model obtains a maximum peak signal-to-noise ratio (PSNR) of 30.30. The Learned Perceptual Image Patch Similarity (LPIPS) score is 0.0817, whereas the Structural Similarity Index Measure (SSIM) is 0.8757. The results surpass many state-of-the-art methods available today. These enhancements have a significant impact and importance.

Files

A479816011026.pdf

Files (699.1 kB)

Name Size Download all
md5:ccc2e63418ae0e0973581aa81a0c09b0
699.1 kB Preview Download

Additional details

Identifiers

DOI
10.35940/ijeat.A4798.15060826
EISSN
2249-8958

Dates

Accepted
2026-08-15
Manuscript received on 07 July 2026 | First Revised Manuscript received on 01 August 2026 | Second Manuscript Accepted on 08 August 2026 | Manuscript Accepted on 15 August 2026 | Manuscript published on 30 August 2026.

References

  • (2022). Low-resolution face recognition based on feature-mapping face hallucination. Computers and Electrical Engineering 101. DOI: 10.1016/j.compeleceng.2022.108136
  • Aakerberg, A., Nasrollahi, K. & Moeslund, T. B. (2021). Real-world super-resolution of face images from surveillance cameras. IET Image Processing 16(8), pp. 1234-1245. DOI: 10.1049/ipr2.12359
  • Grm, K., Scheirer, W. J. & Struc, V. (2020). Face Hallucination Using Cascaded Super-Resolution and Identity Priors. IEEE Transactions on Image Processing 29(1), pp. 2150-2165. DOI: 10.1109/TIP.2019.2945835
  • Wang, Z., She, Q. & Ward, T. E. (2021). Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy. ACM Computing Surveys 54(2). DOI: 10.1145/3439723
  • Tustison, N. J., Avants, B. B. & Gee, J. C. (2019). Learning imagebased spatial transformations via convolutional neural networks: A review. Magnetic Resonance Imaging 64, pp. 142-153. DOI: 10.1016 /j.mri.2019.05.037
  • (2023). ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks - Technical Documentation and Model Overview. ESRGAN ReadTheDocs. https://esrgan.readthedocs.io/en/latest/index.html
  • Zhu, Z., Lei, Y., Qin, Y. & Zhu, C. (2023). IRE: Improved Image Super-Resolution Based on Real-ESRGAN. IEEE Access 99, p. 1. DOI: 10.1109/ACCESS.2023.3256086
  • Choi, Y. & Park, H. (2023). Improving ESRGAN with an additional image quality loss. Multimedia Tools & Applications 82(2), p. 3123. DOI: 10.1007/s11042-022-13452-4
  • Tomar, A. S., Arya, K. & Rajput, S. S. (2024). Learning face superresolution through identity features and distilling facial prior knowledge—Expert Systems with Applications 202. DOI: 10.1016/j.eswa.2024.125625
  • Bashir, S. M., Wang, Y., Khan, M. & Niu, Y. (2021). A comprehensive review of deep learning-based single image super-resolution. PeerJ Computer Science 7. DOI: 10.7717/peerj-cs.621
  • Zhang, W., Zhao, W., Li, J., Zhuang, P., Sun, H., Xu, Y. & Li, C. (2024). CVANet: Cascaded Visual Attention Network for Single Image Super-Resolution. Neural Networks 170, pp. 622-634. DOI: 10.1016/j.neunet.2023.11.049
  • Zhu, Y., Zhang, Y. & Yuille, A. L. (2014). Single Image SuperResolution Using Deformable Patches. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2917-2924. DOI: 10.1109/CVPR.2014.373, works remain significant, see the declaration
  • Anwar, S., Khan, S. & Barnes, N. (2020). A Deep Journey into Superresolution: A Survey. ACM Computing Surveys 53(3). DOI: 10.1145/3390462
  • Yu, X., Fernando, B., Hartley, R. & Porikli, F. (2020). Semantic Face Hallucination: Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes. IEEE Transactions on Pattern Analysis and Machine Intelligence 42(11), pp. 2926-2943. DOI: 10.1109/TPAMI.2019.2916881
  • Rana, M. S., Nibali, A. & He, Z. (2022). Selection of object detections using overlap map predictions. Neural Computing and Applications 34. DOI: 10.1007/s00521-022-07469-x
  • Hu, X., Fan, Z., Jia, X., Li, Z., Zhang, X., Qi, L. & Xuan, Z. (2021). Towards effective learning for face super-resolution with shape and pose perturbations—Knowledge-Based Systems 220. DOI: 10.1016/j.knosys.2021.106938
  • Dastmalchi, H. & Aghaeinia, H. (2022). Super-resolution of very lowresolution face images with a wavelet-integrated, identity-preserving adversarial network. Image and Vision Computing 107. DOI: 10.1016/j.image.2022.116755
  • (2020). Facial Image Synthesis and Super-Resolution with Stacked Generative Adversarial Network. Neurocomputing 402, pp. 359-365. DOI: 10.1016/j.neucom.2020.03.107
  • Arabboev, M., Begmatov, S., Rikhsivoev, M., Nosirov, K. & Saydiakbarov, S. (2021). A comprehensive review of image superresolution metrics: classical and AI-based approaches. Acta IMEKO 13(1). DOI: 10.21014/actaimeko.v13i1.1679
  • (2021). Py-Feat: Python Facial Expression Analysis Toolbox. PMC10751270. DOI: 10.3389/fnins.2021.635019
  • He, K., Pu, N., Lao, M. & Lew, M. S. (2023). Few-shot and metalearning methods for image understanding: a survey. International Journal of Multimedia Information Retrieval 12. DOI: 10.1007/s13735-023-00279-4
  • Lopes, A., Santos, F. P., Oliveira, D. d., Schiezaro, M. & Pedrini, H. (2024). Computer Vision Model Compression Techniques for Embedded Systems: A Survey. Computers & Graphics 123. DOI: 10.1016/j.cag.2024.104015
  • Zhang, Z., Shi, Y., Zhou, X., Kan, H. & Wen, J. (2020). Shuffle block SRGAN for face image super-resolution reconstruction. Measurement and Control 53(78), pp. 1429-1439. DOI: 10.1177/0020294020944969
  • Mishra, A., Lee, B. & Lee, B. (2025). PixelBoost: Leveraging Brownian Motion for Realistic-Image Super-Resolution. IEEE Transactions on Multimedia 99, pp. 1-13. DOI: 10.1109/TMM.2025.3623517
  • Zhang, Y., Tian, Y., Kong, Y., Zhong, B. & Fu, Y. (2018). Residual Dense Network for Image Super-Resolution. arXiv preprint arXiv:1802.08797. DOI: 10.48550/arXiv.1802.08797
  • Li, M., Zhang, Z., Yu, J. & Chen, C. (2020). Learning Face Image Super-Resolution Through Facial Semantic Attribute Transformation and Self-Attentive Structure Enhancement. IEEE Transactions on Multimedia 99, p. 1. DOI: 10.1109/TMM.2020.2984092
  • Musunuri, Y. R. & Kwon, O. (2021). Deep residual dense network for Single Image Super-Resolution. Electronics 10(5). DOI: 10.3390/electronics10050555
  • Fan, Z., Hu, X., Chen, C., Wang, X. & Peng, S. (2020). Facial image super-resolution guided by adaptive geometric features. EURASIP Journal on Wireless Communications and Networking 2020. DOI: 10.1186/s13638-020-01760-y
  • (2021). Improved Face Image Super-Resolution Model Based on Generative Adversarial Network. MDPI 11(5). DOI: 10.3390/23134331
  • (2022). Deep Learning for Face Super-Resolution: A Techniques Review. APSIPA Transactions on Signal and Information Processing 11(1), pp. 1-15. DOI: 10.1561/116.20240045
  • Johnson, J., Alahi, A. & Fei-Fei, L. (2016). Perceptual Losses for RealTime Style Transfer and Super-Resolution. arXiv preprint arXiv:1603.08155. DOI: 10.1007/978-3-319-46475-6_43
  • Georgopoulos, M., Oldfield, J., Nicolaou, M. A., Panagakis, Y. & Pantic, M. (2021). Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer. International Journal of Computer Vision 129. DOI: 10.1007/s11263-021-01448-w
  • (2020). Facial image super-resolution guided by adaptive geometric features. Journal on Wireless Communications and Networking. DOI: 10.1186/s13638-020-01760-y
  • Joze, H. R., Zharkov, I., Powell, K., Ringler, C., Liang, L., Roulston, A., Lutz, M. & Pradeep, V. (2020). ImagePairs: Realistic Super Resolution Dataset via Beam Splitter Camera Rig. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. DOI: 10.1109/CVPRW50498.2020.00267
  • Tejy, A. R., Halder, S. S., Shandeelya, A. P. & Pankajakshany, V. (2020). Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution. arXiv preprint. https://arxiv.org/pdf/2005.07502
  • Liu, Y., Liu, Y. & Liu, Y. (2017). Tensor Super-Resolution with Generative Adversarial Nets. IEEE Transactions on Image Processing 26(1), pp. 1-12. DOI: 10.1109/TIP.2016.2610190
  • Liu, Y., Sun, D., Wang, F., Lim, K. P., Chiew, T. K. & Lai, Y. (2022). Improved Face Image Super-Resolution Model Based on Generative Adversarial Network. IEEE Transactions on Circuits and Systems for Video Technology 32(1), pp. 1-14. DOI: 10.1109/TCSVT.2021.3071234
  • Kim, D., Kim, M., Kwon, G. & Kim, D. (2019). Progressive Face Super-Resolution via Attention to Facial Landmark. arXiv preprint arXiv:1908.08239. DOI: 10.48550/arXiv.1908.08239
  • Eugenesiow. (2026). Dataset Card for Div2k. Hugging Face. https://huggingface.co/datasets/eugenesiow/Div2k
  • Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Loy, C. C., Qiao, Y. & Tang, X. (2018). ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. ECCVW 2018. DOI: 10.1109/ICCVW.2018.00135
  • (2021). Synchronizing billion-scale automata. Information Sciences 574, pp. 162-175. DOI: 10.1016/j.ins.2021.05.072
  • (2024). Peak signal-to-noise ratio. Wikipedia. https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio
  • Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J. & Aila, T. (2020). Training Generative Adversarial Networks with Limited Data. arXiv preprint arXiv:2006.06676. DOI: 10.48550/arXiv.2006.06676
  • He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778. DOI: 10.1109/CVPR.2016.90
  • (2024). Learned Perceptual Image Patch Similarity (LPIPS). PyTorchMetrics 0.8.0 documentation. https://torchmetrics.readthedocs.io/en/v0.8.0/image/learned_perceptual _image_patch_similarity.html