Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling

• URL: http://arxiv.org/abs/2310.10033v1
• Date: Mon, 16 Oct 2023 03:30:35 GMT
• Title: Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling
• Authors: Wenxue Cui, Xiaopeng Fan, Jian Zhang, Debin Zhao
• Abstract summary: 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.
• Score: 35.17811080742471
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inspired by certain optimization solvers, the deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS). However, there still exist the following two issues: 1) In existing DUNs, most hyperparameters are usually content independent, which greatly limits their adaptability for different input contents. 2) In each iteration, a plain convolutional neural network is usually adopted, which weakens the perception of wider context prior and therefore depresses the expressive ability. In this paper, inspired by the traditional Proximal Gradient Descent (PGD) algorithm, a novel DUN for image compressed sensing (dubbed DUN-CSNet) is proposed to solve the above two issues. Specifically, 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 to dynamically allocate the corresponding step sizes for different textures of input image by generating a content-aware step size map, realizing a content-adaptive gradient updating. 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, which can adaptively build the long-range dependencies between the nonlocal patches by deformation-invariant non-local modeling, leading to a wider perception on context priors. Extensive experiments manifest that the proposed DUN-CSNet outperforms existing state-of-the-art CS methods by large margins.

Related papers

• Unleashing Network Potentials for Semantic Scene Completion [50.95486458217653]
  This paper proposes a novel SSC framework - Adrial Modality Modulation Network (AMMNet) AMMNet introduces two core modules: a cross-modal modulation enabling the interdependence of gradient flows between modalities, and a customized adversarial training scheme leveraging dynamic gradient competition. Extensive experimental results demonstrate that AMMNet outperforms state-of-the-art SSC methods by a large margin.
  arXiv  Detail & Related papers  (2024-03-12T11:48:49Z)
• Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks [53.67497327319569]
  We introduce a novel neural rendering technique to solve image-to-3D from a single view. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
  arXiv  Detail & Related papers  (2023-12-24T08:42:37Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• 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 [9.014593915305069]
  Deep unfolding networks (DUNs) have achieved impressive success in compressive sensing (CS) By unfolding the proposed framework into deep neural networks, we further design a novel Dual-Domain Deep Convolutional Coding Network (D3C2-Net) Experiments on natural and MR images demonstrate that our D3C2-Net achieves higher performance and better accuracy-complexity trade-offs than other state-of-the-arts.
  arXiv  Detail & Related papers  (2022-07-27T14:52:32Z)
• Image Compressed Sensing Using Non-local Neural Network [43.51101614942895]
  In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed. In the proposed NL-CSNet, two non-localworks are constructed for utilizing the non-local self-similarity priors. In the subnetwork of multi-scale feature domain, the affinities between the dense feature representations are explored.
  arXiv  Detail & Related papers  (2021-12-07T14:06:12Z)
• Dynamic Proximal Unrolling Network for Compressive Sensing Imaging [29.00266254916676]
  We present a dynamic proximal unrolling network (dubbed DPUNet), which can handle a variety of measurement matrices via one single model without retraining. Specifically, DPUNet can exploit both embedded physical model via gradient descent and imposing image prior with learned dynamic proximal mapping. Experimental results demonstrate that the proposed DPUNet can effectively handle multiple CSI modalities under varying sampling ratios and noise levels with only one model.
  arXiv  Detail & Related papers  (2021-07-23T03:04:44Z)
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation [97.74059510314554]
  Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering from large domain gaps. We propose a novel Dual Soft-Paste (DSP) method in this paper.
  arXiv  Detail & Related papers  (2021-07-20T16:22:40Z)
• Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction [94.25865526414717]
  This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos. We propose Bilevel Online Adaptation, which divides the optimization process of overall multi-objective into two steps of weight probe and weight update in a training. We demonstrate that BOA leads to state-of-the-art results on two human mesh reconstruction benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T15:47:58Z)

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.