Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications

• URL: http://arxiv.org/abs/2606.00078v1
• Date: Fri, 22 May 2026 12:35:05 GMT
• Title: Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications
• Abstract summary: We present a flow-based generative framework for learning subsampling masks for compressed sensing applications.<n>For image reconstruction, our method demonstrated state-of-the-art performance, achieving Peak Signal-to-Noise Ratio of 25.17 dB at the subsampling rate of 5%.<n>Results highlight the effectiveness of task-conditioning within generative flow models and reveal a promising direction for representation learning strategies.
• Score: 6.687252358900529
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Numerous modern applications in signal processing and medical imaging necessitate acquiring high-dimensional signals under tight resource constraints. Traditional sampling theory suggests that accurate signal reconstruction requires a number of measurements proportional to the signal's ambient dimension, a requirement often too expensive or impractical. Compressed sensing challenges this notion by demonstrating that sparse signals can be recovered with fewer measurements, provided the measurement operator meets certain conditions. This proof-of-concept study presents a task-aware flow-based generative framework -- a reformulation of the conventional Flow Matching training paradigm with a flow model trained to optimize subsampling in compressed sensing applications. We establish the fundamental feasibility of the proposed framework of learning subsampling masks that substantially enhance the performance of compressed sensing for image classification, image reconstruction, and MRI acceleration. For the image reconstruction task, our method demonstrated state-of-the-art performance, achieving Peak Signal-to-Noise Ratio of 25.17 dB at the subsampling rate of 5\% on the CelebA dataset and 29.24 dB when reconstructing $8\times$ accelerated MRI measurements (fastMRI dataset) with the minimal computational overhead. These results highlight the effectiveness of task-conditioning within generative flow models and reveal a promising direction for representation learning strategies. Overall, the proposed framework offers a unified, flexible approach to designing data- and task-driven sensing schemes that can be potentially adapted to a broad range of inverse problems.

Related papers

• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance [52.705112811734566]
  A novel diffusion-based framework is introduced for solving inverse problems using a piecewise guidance scheme.<n>The proposed method is problem-agnostic and readily adaptable to a variety of inverse problems.<n>The framework achieves a reduction in inference time of (25%) for inpainting with both random and center masks, and (23%) and (24%) for (4times) and (8times) super-resolution tasks.
  arXiv  Detail & Related papers  (2025-07-22T19:35:14Z)
• Active MRI Acquisition with Diffusion Guided Bayesian Experimental Design [1.3142127084199051]
  Key challenge in maximizing the benefits of Magnetic Resonance Imaging (MRI) in clinical settings is to accelerate acquisition times without significantly degrading image quality.<n>This objective requires a balance between under-sampling the raw k-space measurements for faster acquisitions and gathering sufficient raw information for high-fidelity image reconstruction and analysis tasks.<n>We propose to use sequential Bayesian experimental design (BED) to provide an adaptive and task-dependent selection of the most informative measurements.
  arXiv  Detail & Related papers  (2025-06-19T11:48:30Z)
• Efficient MRI Parallel Imaging Reconstruction by K-Space Rendering via Generalized Implicit Neural Representation [16.63720411275398]
  This study presents a generalized implicit neural representation (INR)-based framework for MRI PI reconstruction.<n>The proposed method overcomes limitations by leveraging prior knowledge of voxel-specific features.<n>Experiments on publicly available MRI datasets demonstrate the superior performance of the proposed method.
  arXiv  Detail & Related papers  (2023-09-12T09:07:03Z)
• Towards performant and reliable undersampled MR reconstruction via diffusion model sampling [67.73698021297022]
  DiffuseRecon is a novel diffusion model-based MR reconstruction method. It guides the generation process based on the observed signals. It does not require additional training on specific acceleration factors.
  arXiv  Detail & Related papers  (2022-03-08T02:25:38Z)
• Single-pass Object-adaptive Data Undersampling and Reconstruction for MRI [6.599344783327054]
  We propose a data-driven sampler using a convolutional neural network, MNet, to provide object-specific sampling patterns adaptive to each scanned object. The network observes very limited low-frequency k-space data for each object and rapidly predicts the desired undersampling pattern. Experimental results on the fastMRI knee dataset demonstrate the ability of the proposed learned undersampling network to generate object-specific masks at fourfold and eightfold acceleration.
  arXiv  Detail & Related papers  (2021-11-17T16:06:06Z)
• Deep Unfolded Recovery of Sub-Nyquist Sampled Ultrasound Image [94.42139459221784]
  We propose a reconstruction method from sub-Nyquist samples in the time and spatial domain, that is based on unfolding the ISTA algorithm. Our method allows reducing the number of array elements, sampling rate, and computational time while ensuring high quality imaging performance.
  arXiv  Detail & Related papers  (2021-03-01T19:19:38Z)
• Neural BRDF Representation and Importance Sampling [79.84316447473873]
  We present a compact neural network-based representation of reflectance BRDF data. We encode BRDFs as lightweight networks, and propose a training scheme with adaptive angular sampling. We evaluate encoding results on isotropic and anisotropic BRDFs from multiple real-world datasets.
  arXiv  Detail & Related papers  (2021-02-11T12:00:24Z)
• LoRD-Net: Unfolded Deep Detection Network with Low-Resolution Receivers [104.01415343139901]
  We propose a deep detector entitled LoRD-Net for recovering information symbols from one-bit measurements. LoRD-Net has a task-based architecture dedicated to recovering the underlying signal of interest. We evaluate the proposed receiver architecture for one-bit signal recovery in wireless communications.
  arXiv  Detail & Related papers  (2021-02-05T04:26:05Z)
• Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI [30.838990115880197]
  Compressed sensing (CS) MRI relies on adequate undersampling of the k-space to accelerate the acquisition without compromising image quality. We propose joint learning of both task-adaptive k-space sampling and a subsequent model-based proximal-gradient recovery network. The proposed combination of a highly flexible sampling model and a model-based (sampling-adaptive) image reconstruction network facilitates exploration and efficient training, yielding improved MR image quality.
  arXiv  Detail & Related papers  (2020-04-22T12:50:03Z)

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.