Dual-Path Hyperprior Informed Deep Unfolding Network for Image Compressive Sensing

• URL: http://arxiv.org/abs/2605.09566v1
• Date: Sun, 10 May 2026 14:28:37 GMT
• Title: Dual-Path Hyperprior Informed Deep Unfolding Network for Image Compressive Sensing
• Abstract summary: We propose a novel Dual-Path Hyperprior Informed Deep Unfolding Network (DPH-DUN)<n>It partitions measurements into double subsets to enable hyperprior-guided reconstruction via a dual-path architecture.<n>Extensive experiments demonstrate that the proposed DPH-DUN outperforms existing Compressive Sensing methods.
• Score: 20.76300063992605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Deep Unfolding Networks (DUNs) have significantly advanced Compressive Sensing (CS) by integrating iterative optimization with deep networks. However, existing DUNs still suffer from two challenges: 1) Reliance on a single measurement stream, which limits effective information interaction across distinct measurement subsets. 2) Uniform processing of all image regions, which overlooks varying reconstruction difficulties induced by diverse textures. To address these limitations, a novel Dual-Path Hyperprior Informed Deep Unfolding Network (DPH-DUN) is proposed, which partitions measurements into double subsets to enable hyperprior-guided reconstruction via a dual-path architecture. In the Deep Hyperprior Learning branch, a series of lightweight neural modules are designed to efficiently generate hyperprior knowledge of different domains, enabling collaborative guidance for the CS reconstruction. In the Hyperprior Informed Reconstruction branch, a deep unfolding framework with hyperprior guidance is constructed to iteratively refine reconstruction. Specifically, i) in the gradient descent step, a Hyperprior Informed Step Size Generation network is designed to dynamically generate spatially varying step maps, enabling adaptive fine-grained gradient updates. ii) In the proximal mapping step, two well-designed hyperprior informed attention mechanisms are introduced to dynamically focus on challenging regions via gradient-based hard and soft attentions, facilitating CS reconstruction accuracy. Extensive experiments demonstrate that the proposed DPH-DUN outperforms existing CS methods.

Related papers

• Current Injection Spiking Neural Network for Infrared and Visible Image Fusion [55.20584003351512]
  Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content.<n>We propose CIS-Fuse, a spiking network that performs cross-modal fusion directly at the membrane-potential level.<n>Experiments on four IVIF benchmarks and on downstream detection and segmentation show that CIS-Fuse achieves fusion quality on par with state-of-the-art ANN-based methods.
  arXiv  Detail & Related papers  (2026-07-22T08:10:02Z)
• Beyond Single Solution: Multi-Hypothesis Collaborative Deep Unfolding Network for Image Compressive Sensing [44.028998922506]
  Multi-Hypothesis Collaborative Deep Unfolding CS Network (MHC-DUN) is proposed.<n>It explicitly models and leverages multiple hypotheses by jointly optimizing across diverse solution spaces.<n> Experimental results reveal that the proposed CS method outperforms existing CS networks.
  arXiv  Detail & Related papers  (2026-06-02T13:50:56Z)
• Unrolled Neural Networks for Constrained Optimization [83.29547301151177]
  Our framework comprises two coupled neural networks that jointly approximate the saddle point of the Lagrangian.<n>We numerically evaluate the framework on mixed-integer quadratic programs and power allocation in wireless networks.
  arXiv  Detail & Related papers  (2026-01-24T03:12:41Z)
• UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing [77.10640210751981]
  UDPNet is a general framework that leverages depth-based priors from a large-scale pretrained depth estimation model DepthAnything V2.<n>Our proposed solution establishes a new benchmark for depth-aware dehazing across various scenarios.
  arXiv  Detail & Related papers  (2026-01-11T13:29:02Z)
• Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling [35.17811080742471]
  The deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS) This paper proposes a novel DUN for image compressed sensing (dubbed DUN-CSNet) to solve the above two issues. For the first issue, a novel content adaptive gradient descent network is proposed, in which a well-designed step size generation sub-network is developed. For the second issue, considering the fact that many similar patches exist in an image but have undergone a deformation, a novel deformation-invariant non-local proximal mapping network is developed.
  arXiv  Detail & Related papers  (2023-10-16T03:30:35Z)
• Deep Physics-Guided Unrolling Generalization for Compressed Sensing [8.780025933849751]
  Deep physics-engaged learning scheme achieves high-accuracy and interpretable image reconstruction. We find the intrinsic defect of this emerging paradigm, widely implemented by deep algorithm-unrolled networks. A novel deep $textbfP$hysics-guided untextbfR$olled recovery is proposed.
  arXiv  Detail & Related papers  (2023-07-18T03:37:10Z)
• HKNAS: Classification of Hyperspectral Imagery Based on Hyper Kernel Neural Architecture Search [104.45426861115972]
  We propose to directly generate structural parameters by utilizing the specifically designed hyper kernels. We obtain three kinds of networks to separately conduct pixel-level or image-level classifications with 1-D or 3-D convolutions. A series of experiments on six public datasets demonstrate that the proposed methods achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2023-04-23T17:27:40Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing [31.71861820004099]
  A novel fast hierarchical deep unfolding network (DUN) is proposed for image compressed sensing. The proposed FHDUN outperforms existing state-of-the-art CS methods, while maintaining fewer iterations.
  arXiv  Detail & Related papers  (2022-08-03T03:27:32Z)
• D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing [21.859168613393223]
  This paper develops a dual-domain optimization framework that combines the priors of (1) image- and (2) convolutional-coding-domains and offers generality to inverse imaging tasks.<n>We present a Dual-Domain Deep Convolutional Coding Network (D3C2-Net), which enjoys the ability to efficiently transmit high-capacity self-adaptive convolutional features across all its unfolded stages.
  arXiv  Detail & Related papers  (2022-07-27T14:52:32Z)
• HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging [41.91463343106411]
  Hyperspectral imaging is an essential imaging modality for a wide range of applications, especially in remote sensing, agriculture, and medicine. Inspired by existing hyperspectral cameras that are either slow, expensive, or bulky, reconstructing hyperspectral images (HSIs) from a low-budget snapshot measurement has drawn wide attention. Recent deep unfolding networks (DUNs) for spectral snapshot sensing (SCI) have achieved remarkable success. In this paper, we propose a novel Hyperspectral Explicable Reconstruction and Optimal Sampling deep Network for SCI, dubbed HerosNet, which includes several phases under the ISTA-unfolding framework.
  arXiv  Detail & Related papers  (2021-12-12T13:42:49Z)
• Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks [87.50632573601283]
  We present a novel method for multi-view depth estimation from a single video. Our method achieves temporally coherent depth estimation results by using a novel Epipolar Spatio-Temporal (EST) transformer. To reduce the computational cost, inspired by recent Mixture-of-Experts models, we design a compact hybrid network.
  arXiv  Detail & Related papers  (2020-11-26T04:04:21Z)

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.