Diffusion models have emerged as powerful tools for learning complex data distributions and solving inverse problems. However, most diffusion models rely on the Gaussian distribution, which does not accurately represent heavy-tailed data. In this work, we study diffusion-based reconstruction under Gaussian and symmetric α-stable fading channels, while also exploring the benefits of using possible temporal dependence in the channel. We consider two variants: pilot-based channel-only estimation and joint image-channel recovery for MIMO systems. Our approach is based on several standard and score-based diffusion models for both Gaussian and α-stable distributions. We refine these models by guiding the reverse diffusion process using the observation likelihood and show how a single trained diffusion model can be reused for the location-scale family of distributions without retraining. In blind MIMO recovery, separate diffusion models are used for the image and channel, and their estimates are combined through likelihood guidance. For each setting, we compare independent and temporal reconstruction, where information from previous observations is used to improve the estimation. We show that, under a time-dependent channel model, such a temporal reconstruction improves channel estimation and the quality of the reconstructed image. Finally, we show that, for the same heavy-tailed channel data, using an α-stable diffusion prior provides better channel estimation and image reconstruction than using a Gaussian diffusion prior.
Figures & tables
Fig. 1: Reconstruction loss versus ρ\lx@scalerel@objH for independent and temporal channel reconstruction. Top: Gaussian channels using DDPM. Bottom: α -stable channels using DLPM with α=1.7 .
Fig. 2: Image MS-SSIM and channel loss vs. SNR for independent and temporal joint channel–image MIMO reconstruction. Left: Gaussian channels using DDPM. Right: α -stable channels with α=1.7 using DLPM.
Fig. 3: Sent images and the corresponding independent and temporal joint MIMO reconstructions for ρ\lx@scalerel@objH=0.8 . Top: Gaussian channel using DDPM at SNR =10 dB. Bottom: α -stable channel using DLPM with α=1.7 at SNR =5 dB.
Fig. 4: Image MS-SSIM and channel loss vs. SNR for α -stable joint channel–image MIMO reconstruction using matched DLPM and mismatched DDPM for α=1.7 .
Fig. 5: Sent image on α -stable channel with joint MIMO reconstructions obtained using matched DLPM and mismatched Gaussian DDPM for α=1.7 and SNR =15 dB.
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
Fig. 6: Reconstruction loss versus ρ\lx@scalerel@objH for independent and temporal channel reconstruction. Top: Gaussian channels using the score-based model. Bottom: α -stable channels using LIM with α=1.7 . This corresponds to the channel-only experiment in Section V-A .
Fig. 7: Image MS-SSIM and channel loss vs. SNR for α -stable joint channel–image MIMO reconstruction using matched LIM and mismatched Gaussian score-based model for α=1.7 . This corresponds to the model-mismatch experiment in Section V-B .
Fig. 8: Sent image on α -stable channel with joint MIMO reconstructions obtained using matched LIM and mismatched Gaussian score-based model for α=1.7 and SNR =15 dB. These results correspond to the model-mismatch experiment in Section V-B .
Fig. 9: Image MS-SSIM and channel loss vs. SNR for independent and temporal joint channel–image MIMO reconstruction. Top: Gaussian channels using the score-based model. Bottom: α -stable channels with α=1.7 using LIM. This corresponds to the joint channel–image MIMO experiment in Section V-B .
Fig. 10: Sent images and the corresponding independent and temporal joint MIMO reconstructions. Top: Gaussian channel using the score-based model at SNR =10 dB with ρ\lx@scalerel@objH=0.4 . Bottom: α -stable channel using LIM with α=1.7 at SNR =10 dB with ρ\lx@scalerel@objH=0.8 . These results correspond to the joint channel–image MIMO experiment in Section V-B .
Accurate and low latency channel estimation is critical for modern MIMO systems, particularly under mobility, where channels exhibit structured sparsity and strong temporal correlation. This paper proposes a time-series conditioned diffusion framework for channel estimation that performs denoising in the angular domain. Starting from least squares (LS) observations, we train a diffusion denoiser whose conditioning information is encoded by a long short-term memory (LSTM) network over a short observation sequence, enabling the model to exploit temporal dynamics beyond per-snapshot estimation. To robustly balance observation fidelity and learned generative priors across a wide signal-to-noise ratio (SNR) range, we introduce a learnable SNR-gated late-fusion shortcut that injects the network input into the final decoding stage through a sigmoid gate with trainable center and scale. To reduce inference latency, we adopt deterministic denoising diffusion implicit model (DDIM) style reverse updates with SNR-adaptive truncation and step allocation, which significantly reduces the number of reverse diffusion steps at high SNR while maintaining strong performance in low SNR regimes. Simulations on time-evolving standardized channel models demonstrate that the proposed method achieves consistent performance gains over existing diffusion-based channel estimation baselines, while retaining low latency through SNR-adaptive inference.
Jixing Zhou, Xinming Huang
Worcester Polytechnic Institute Worcester, MA, USA
Solving severely ill-posed imaging inverse problems requires recovering image structures that are unobservable or weakly constrained by the measurements. Diffusion models provide expressive learned priors for inferring such missing information, while posterior sampling incorporates measurement consistency along the reverse process. Standard diffusion posterior samplers, however, rely on instantaneous measurement-aware estimates, without explicitly exploiting information carried by previous posterior corrections. We introduce Consecutive Posterior Fusion Denoising Diffusion Null-Space Models (CPF-DDNM), an inference-time strategy that fuses consecutive measurement-aware estimates to improve the diffusive recovery of unobservable image structures, without requiring retraining or additional denoiser evaluations. We instantiate this principle within DDNM, whose range/null-space decomposition reveals that consecutive fusion preserves the measurement-determined component while acting exclusively on the prior-driven null-space estimate. We thus provide a geometric interpretation of CPF-DDNM and a local error analysis that characterizes the optimal time-dependent fusion coefficient, including the extrapolative regime. Experiments on sparse-view and simulated low-dose computed tomography, as well as medical image super-resolution, show consistent improvements over DDNM and competitive performance against diffusion-based inverse solvers.
Elena Morotti, Davide Evangelista, Elena Loli Piccolomini
Department of Computer Science and Engineerin University of Bologna Bologna, 40126, Italy
In this work we propose a novel non-linear diffusion filtering approach for images based on their channel representation. To derive the diffusion update scheme we formulate a novel energy functional using a soft-histogram representation of image pixel neighborhoods obtained from the channel encoding. The resulting Euler-Lagrange equation yields a non-linear robust diffusion scheme with additional weighting terms stemming from the channel representation which steer the diffusion process. We apply this novel energy formulation to image reconstruction problems, showing good performance in the presence of mixtures of Gaussian and impulse-like noise, e.g. missing data. In denoising experiments of common scalar-valued images our approach performs competitive compared to other diffusion schemes as well as state-of-the-art denoising methods for the considered noise types.
Christian Heinemann, Freddie Åström, George Baravdish +3
IBG-2: Plant Sciences, Forschungszentrum Jülich, 52425 Jülich, Germany · Department of Electrical Engineering, Linköping University, SE-581 83 Linköping, Sweden · Department of Science and Technology, Linköping University, SE-601 74 Norrköping, Sweden