Enhancement of Image Reconstruction in Orthogonal Frequency-Division Multiplexing (OFDM)-Based Communication System Using Conditional Diffusion Model of Generative AI
Abstract
:1. Introduction
- A CDM that addresses distorted OFDM-based images in wireless communication is introduced. While the existing diffusion models have only considered Gaussian noise in the diffusion process, the proposed model is designed to handle the image distortion that occurs in OFDM-based wireless communication. This adaptation allows the model to effectively account for varying levels of signal degradation, leading to improved reconstruction performance.
- The proposed CDM dynamically learns the variance during the training process, in contrast to diffusion models that learn through a fixed variance. This flexibility enables the model to optimally adjust to different modulation schemes and diverse SNR conditions, enhancing the overall training effectiveness and the rapidity of image reconstruction.
- A performance analysis is conducted on the proposed CDM under diverse modulation schemes and SNR conditions. From the simulation results, it is confirmed that the proposed CDM with learnable variance (CDM-LV) is effective in reconstructing OFDM-based images from received signals in highly deteriorated environments.
2. Problem Formulation
2.1. OFDM-Based Communication Systems
2.1.1. OFDM Systems for Image Transmission and Signal Processing
2.1.2. Distortion of the Received Signal
2.1.3. Diffusion Model for Image Reconstruction in OFDM
2.2. Diffusion Probabilistic Model
3. Conditional Diffusion Model for OFDM-Based Image Reconstruction
3.1. Conditional Diffusion and Reverse Processes
3.2. Learnable Variance in the Conditional Diffusion Model
Algorithm 1: Training algorithm in CDM-LV | ||
1 | for do | |
2 | Sample ( | |
3 | ||
4 | ||
5 | Compute | |
6 | Compute | |
7 | end for |
Algorithm 2: Sampling algorithm in the CDM-LV | ||
1 | Sample | |
2 | for do | |
3 | Compute , , using Equations (25)–(27) | |
4 | Sample | |
5 | end for | |
6 | return |
3.3. Performance Metrics
4. Simulation Results
4.1. Simulation Setup
4.2. Performance Evaluation
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Li, Y.; Cimini, L.J.; Sollenberger, N.R. Robust channel estimation for OFDM systems with rapid dispersive fading channels. IEEE Trans. Commun. 1998, 46, 902–915. [Google Scholar] [CrossRef]
- Wulich, D. Definition of efficient PAPR in OFDM. IEEE Commun. Lett. 2005, 9, 832–834. [Google Scholar] [CrossRef]
- Otsuka, H.; Tian, R.; Senda, K. Transmission performance of an OFDM-based higher-order modulation scheme in multipath fading channels. J. Sens. Actuator Netw. 2019, 8, 19. [Google Scholar] [CrossRef]
- Hagos, D.H.; Battle, R.; Rawat, D.B. Recent advances in generative AI and large language models: Current status, challenges, and perspectives. IEEE Trans. Artif. Intell. 2024, 5, 5873–5893. [Google Scholar] [CrossRef]
- Simion, A.-M.; Radu, Ș.; Florea, A.M. A review of generative adversarial networks for computer vision tasks. Electronics 2024, 13, 713. [Google Scholar] [CrossRef]
- Goyal, M.; Mahmoud, Q.H. A systematic review of synthetic data generation techniques using generative AI. Electronics 2024, 13, 3509. [Google Scholar] [CrossRef]
- Bengesi, S.; El-Sayed, H.; Sarker, M.K.; Houkpati, Y.; Irungu, J.; Oladunni, T. Advancements in generative AI: A comprehensive review of GANs, GPT, autoencoders, diffusion model, and transformers. IEEE Access 2024, 12, 69812–69837. [Google Scholar] [CrossRef]
- Goodfellow, I.J.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial networks. In Proceedings of the Advances in Neural Information Processing Systems 27 (NIPS 2014), Montreal, QC, Canada, 8–13 December 2014; pp. 2672–2680. [Google Scholar]
- Kingma, D.P.; Welling, M. An introduction to variational autoencoders. FNT Mach. Learn. 2019, 12, 307–392. [Google Scholar] [CrossRef]
- Kossale, Y.; Airaj, M.; Darouichi, A. Mode collapse in generative adversarial networks: An overview. In Proceedings of the 2022 8th International Conference on Optimization and Applications (ICOA), Genoa, Italy, 6–7 October 2022; pp. 1–6. [Google Scholar]
- Thanh-Tung, H.; Tran, T. Catastrophic forgetting and mode collapse in GANs. In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 19–24 July 2020; pp. 1–10. [Google Scholar]
- Daunhawer, I.; Sutter, T.M.; Chin-Cheong, K.; Palumbo, E.; Vogt, J.E. On the limitations of multimodal VAEs 2022. arXiv 2022, arXiv:2110.04121. [Google Scholar]
- Ho, J.; Jain, A.; Abbeel, P. Denoising diffusion probabilistic models. In Proceedings of the Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Virtual, 6–12 December 2020; Volume 33, pp. 6840–6851. [Google Scholar]
- Sengupta, U.; Jao, C.; Bernacchia, A.; Vakili, S.; Shiu, D. Generative diffusion models for radio wireless channel modelling and sampling. In Proceedings of the GLOBECOM 2023—2023 IEEE Global Communications Conference, Kuala Lumpur, Malaysia, 4–8 February 2023; pp. 4779–4784. [Google Scholar]
- Wu, T.; Chen, Z.; He, D.; Qian, L.; Xu, Y.; Tao, M.; Zhang, W. CDDM: Channel denoising diffusion models for wireless semantic communications. IEEE Trans. Wirel. Commum. 2024, 23, 11168–11183. [Google Scholar] [CrossRef]
- Kim, M.; Fritschek, R.; Schaefer, R.F. Learning end-to-end channel coding with diffusion models. In Proceedings of the WSA & SCC 2023; 26th International ITG Workshop on Smart Antennas and 13th Conference on Systems, Communications, and Coding, Braunschweig, Germany, 27 February 2023; pp. 1–6. [Google Scholar]
- Letafati, M.; Ali, S.; Latva-Aho, M. Conditional denoising diffusion probabilistic models for data reconstruction enhancement in wireless communications. IEEE Trans. Mach. Learn. Commun. Netw. 2025, 3, 133–146. [Google Scholar] [CrossRef]
- Merluzzi, M.; Borsos, T.; Rajatheva, N.; Benczúr, A.A.; Farhadi, H.; Yassine, T.; Müeck, M.D.; Barmpounakis, S.; Strinati, E.C.; Dampahalage, D.; et al. The hexa-X project vision on artificial intelligence and machine learning-driven communication and computation co-design for 6G. IEEE Access 2023, 11, 65620–65648. [Google Scholar] [CrossRef]
- Van Huynh, N.; Wang, J.; Du, H.; Hoang, D.T.; Niyato, D.; Nguyen, D.N.; Kim, D.I.; Letaief, K.B. Generative AI for physical layer communications: A survey. IEEE Trans. Cogn. Commun. Netw. 2024, 10, 706–728. [Google Scholar] [CrossRef]
- Sohl-Dickstein, J.; Weiss, E.; Maheswaranathan, N.; Ganguli, S. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning, PMLR, Lille, France, 6–11 July 2015; pp. 2256–2265. [Google Scholar]
- Lu, Y.-J.; Wang, Z.-Q.; Watanabe, S.; Richard, A.; Yu, C.; Tsao, Y. Conditional diffusion probabilistic model for speech enhancement. In Proceedings of the ICASSP 2022—2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 23–27 May 2022; pp. 7402–7406. [Google Scholar]
- Nichol, A.Q.; Dhariwal, P. Improved denoising diffusion probabilistic models. In Proceedings of the 38th International Conference on Machine Learning (ICML), Virtual, 18–24 July 2021; pp. 8162–8171. [Google Scholar]
Experimental Parameters | Values |
---|---|
Image dataset | CIFAR-10 () |
Training/test dataset | 50,000/10,000 images |
Signal point () | 256 |
Modulation scheme | -PSK (& -QAM ( |
SNR range | 0 dB–15 dB |
Multipath taps () | 4 |
Channel estimation | Least square (LS) |
Hyperparameter | Values |
---|---|
Neural architecture | U-Net [Channel dim: 128, depth multiplier: 1, 2, 3, 4, ResNet block: 2] |
Variance schedule ( | [, 0.035] |
Time step ( | 50 |
Batch size | 64 |
Learning rate | |
Dropout | 0.1 |
Weight ( |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kim, S.; Kim, J.; Sun, Y.; Seon, J.; Lee, S.; Hwang, B.; Kim, J.; Kim, K.; Kim, J. Enhancement of Image Reconstruction in Orthogonal Frequency-Division Multiplexing (OFDM)-Based Communication System Using Conditional Diffusion Model of Generative AI. Appl. Sci. 2025, 15, 3210. https://doi.org/10.3390/app15063210
Kim S, Kim J, Sun Y, Seon J, Lee S, Hwang B, Kim J, Kim K, Kim J. Enhancement of Image Reconstruction in Orthogonal Frequency-Division Multiplexing (OFDM)-Based Communication System Using Conditional Diffusion Model of Generative AI. Applied Sciences. 2025; 15(6):3210. https://doi.org/10.3390/app15063210
Chicago/Turabian StyleKim, Soohyun, Jinwook Kim, Youngghyu Sun, Joonho Seon, Seongwoo Lee, Byungsun Hwang, Jeongho Kim, Kyounghun Kim, and Jinyoung Kim. 2025. "Enhancement of Image Reconstruction in Orthogonal Frequency-Division Multiplexing (OFDM)-Based Communication System Using Conditional Diffusion Model of Generative AI" Applied Sciences 15, no. 6: 3210. https://doi.org/10.3390/app15063210
APA StyleKim, S., Kim, J., Sun, Y., Seon, J., Lee, S., Hwang, B., Kim, J., Kim, K., & Kim, J. (2025). Enhancement of Image Reconstruction in Orthogonal Frequency-Division Multiplexing (OFDM)-Based Communication System Using Conditional Diffusion Model of Generative AI. Applied Sciences, 15(6), 3210. https://doi.org/10.3390/app15063210