Diffusion Model-Enhanced Environment Reconstruction in ISAC
- 26 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1588-1592
Abstract
Recently, environment reconstruction (ER) in integrated sensing and communication (ISAC) systems has emerged as a promising approach for achieving high-resolution environmental perception. However, the initial results obtained from ISAC systems are coarse and often unsatisfactory due to the high sparsity of the point clouds and significant noise variance. To address this problem, we propose a noise–sparsity-aware diffusion model (NSADM) post-processing framework. Leveraging the powerful data recovery capabilities of diffusion models, the proposed scheme exploits spatial features and the additive nature of noise to enhance point cloud density and denoise the initial input. Simulation results demonstrate that the proposed method significantly outperforms existing model-based and deep learning-based approaches in terms of Chamfer distance and root mean square error.Keywords
All Related Versions
Funding Information
- La Trobe University Start-Up Package (325011150)
- La Trobe University Research Project – SCMES CaRE and Beyond Scheme (401310405)
- European Union’s Horizon 2020 Research and Innovation Program under MSCA (101105732 (DDComRad))
- Australian Research Council’s Discovery Projects (DP240101019)
This publication has 13 references indexed in Scilit:
- ISAC Imaging by Channel State Information Using Ray Tracing for Next Generation 6GIEEE Journal of Selected Topics in Electromagnetics, Antennas and Propagation, 2025
- Deep-Learning-Based Multinode ISAC 4D Environmental Reconstruction With Uplink–Downlink CooperationIEEE Internet of Things Journal, 2024
- Environment Reconstruction Based on Multi-User Selection and Multi-Modal Fusion in ISACIEEE Transactions on Wireless Communications, 2024
- Learning-Based Predictive Beamforming for Integrated Sensing and Communication in Vehicular NetworksIEEE Journal on Selected Areas in Communications, 2022
- A Survey on Fundamental Limits of Integrated Sensing and CommunicationIEEE Communications Surveys & Tutorials, 2022
- The Cramér–Rao Bound for Signal Parameter Estimation From Quantized Data [Lecture Notes]IEEE Signal Processing Magazine, 2021
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- All-Digital Self-Interference Cancellation Technique for Full-Duplex SystemsIEEE Transactions on Wireless Communications, 2015
- Radar detection probabilities and their calculationIEEE Transactions on Aerospace and Electronic Systems, 1995