Score-Based Turbo Message Passing for Plug-and-Play Compressive Imaging

• URL: http://arxiv.org/abs/2512.14435v1
• Date: Tue, 16 Dec 2025 14:24:12 GMT
• Title: Score-Based Turbo Message Passing for Plug-and-Play Compressive Imaging
• Authors: Chang Cai, Hao Jiang, Xiaojun Yuan, Ying-Jun Angela Zhang,
• Abstract summary: We devise an algorithm that integrates a score-based minimum mean-squared error (MMSE) denoiser for compressive image recovery.<n>The resulting algorithm, named score-based turbo message passing (STMP), combines the fast convergence of message passing with the power of score-based generative priors.
• Score: 45.77515171733844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Message-passing algorithms have been adapted for compressive imaging by incorporating various off-the-shelf image denoisers. However, these denoisers rely largely on generic or hand-crafted priors and often fall short in accurately capturing the complex statistical structure of natural images. As a result, traditional plug-and-play (PnP) methods often lead to suboptimal reconstruction, especially in highly underdetermined regimes. Recently, score-based generative models have emerged as a powerful framework for accurately characterizing sophisticated image distribution. Yet, their direct use for posterior sampling typically incurs prohibitive computational complexity. In this paper, by exploiting the close connection between score-based generative modeling and empirical Bayes denoising, we devise a message-passing framework that integrates a score-based minimum mean-squared error (MMSE) denoiser for compressive image recovery. The resulting algorithm, named score-based turbo message passing (STMP), combines the fast convergence of message passing with the expressive power of score-based generative priors. For practical systems with quantized measurements, we further propose quantized STMP (Q-STMP), which augments STMP with a component-wise MMSE dequantization module. We demonstrate that the asymptotic performance of STMP and Q-STMP can be accurately predicted by a set of state-evolution (SE) equations. Experiments on the FFHQ dataset demonstrate that STMP strikes a significantly better performance-complexity tradeoff compared with competing baselines, and that Q-STMP remains robust even under 1-bit quantization. Remarkably, both STMP and Q-STMP typically converge within 10 iterations.

Related papers

• Compressed BC-LISTA via Low-Rank Convolutional Decomposition [47.15001096567547]
  We study Sparse Signal Recovery (SSR) methods for multichannel imaging with compressed forward and backward operators.<n>We propose a Compressed Block-Convolutional (CBC) measurement model based on a low-rank Convolutional Network (CNN) decomposition.
  arXiv  Detail & Related papers  (2026-01-30T16:33:51Z)
• Matrix product state approach to lossy boson sampling and noisy IQP sampling [0.7066293026438526]
  We develop classical algorithms for lossy boson sampling and noisy instantaneous quantum-time sampling.<n>Our algorithm offers significantly improved control over the accuracy-efficiency trade-off.<n>It further extends the applicability of MPS simulation to broader classes of noisy quantum sampling models.
  arXiv  Detail & Related papers  (2025-10-28T07:23:10Z)
• Enhancing Generalization in Data-free Quantization via Mixup-class Prompting [8.107092196905157]
  Post-training quantization (PTQ) improves efficiency but struggles with limited calibration data, especially under privacy constraints.<n>Data-free quantization (DFQ) mitigates this by generating synthetic images using generative models such as generative adversarial networks (GANs) and text-conditioned latent diffusion models (LDMs)<n>We propose textbfmixup-class prompt, a mixup-based text prompting strategy that fuses multiple class labels at the text prompt level to generate diverse, robust synthetic data.
  arXiv  Detail & Related papers  (2025-07-29T16:00:20Z)
• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation [55.12070409045766]
  Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years.<n>Current PTQ methods for Vision Transformers (ViTs) still suffer from significant accuracy degradation, especially under low-bit quantization.
  arXiv  Detail & Related papers  (2025-06-13T07:57:38Z)
• Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery [24.60447255507278]
  Off-the-shelf image denoisers mostly rely on some generic or hand-crafted priors for denoising.<n>We devise a message passing framework that integrates a score-based minimum mean squared error (MMSE) denoiser for compressive image recovery.
  arXiv  Detail & Related papers  (2025-03-28T04:30:58Z)
• FD-LSCIC: Frequency Decomposition-based Learned Screen Content Image Compression [67.34466255300339]
  This paper addresses three key challenges in SC image compression: learning compact latent features, adapting quantization step sizes, and the lack of large SC datasets.<n>We introduce an adaptive quantization module that learns scaled uniform noise for each frequency component, enabling flexible control over quantization granularity.<n>We construct a large SC image compression dataset (SDU-SCICD10K), which includes over 10,000 images spanning basic SC images, computer-rendered images, and mixed NS and SC images from both PC and mobile platforms.
  arXiv  Detail & Related papers  (2025-02-21T03:15:16Z)
• A Novel Approach to Threshold Quantum Images by using Unsharp Measurements [0.8287206589886881]
  We propose a hybrid quantum approach to threshold and binarize a grayscale image through unsharp measurements. The proposed methodology uses peaks of the overlapping Gaussians and the distance between neighboring local minima as the variance. The obtained thresholds are used to binarize a grayscale image by using novel enhanced quantum image representation integrated with a threshold encoder.
  arXiv  Detail & Related papers  (2023-10-16T18:34:40Z)
• Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging [142.11622043078867]
  We propose a principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration. By plugging HST into DAUF, we establish the first Transformer-based deep unfolding method, Degradation-Aware Unfolding Half-Shuffle Transformer (DAUHST) for HSI reconstruction.
  arXiv  Detail & Related papers  (2022-05-20T11:37:44Z)
• Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction [138.04956118993934]
  We propose a novel Transformer-based method, coarse-to-fine sparse Transformer (CST) CST embedding HSI sparsity into deep learning for HSI reconstruction. In particular, CST uses our proposed spectra-aware screening mechanism (SASM) for coarse patch selecting. Then the selected patches are fed into our customized spectra-aggregation hashing multi-head self-attention (SAH-MSA) for fine pixel clustering and self-similarity capturing.
  arXiv  Detail & Related papers  (2022-03-09T16:17:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.