mlsanityData to 14 Oct 2026

Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing

arXiv 2306.16060 ↗First posted 28 Jun 2023cs.CV eess.IVcited by 15

Not on the map. Why?

Abstract (arXiv)

Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance. Each stage in DUN corresponds to one iteration in optimization. At the test time, all the sampling images generally need to be processed by all stages, which comes at a price of computation burden and is also unnecessary for the images whose contents are easier to restore. In this paper, we focus on CS reconstruction and propose a novel Dynamic Path-Controllable Deep Unfolding Network (DPC-DUN). DPC-DUN with our designed path-controllable selector can dynamically select a rapid and appropriate route for each image and is slimmable by regulating different performance-complexity tradeoffs. Extensive experiments show that our DPC-DUN is highly flexible and can provide excellent performance and dynamic adjustment to get a suitable tradeoff, thus addressing the main requirements to become appealing in practice. Codes are available at https://github.com/songjiechong/DPC-DUN.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 28 of its 67 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

28 of 67 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Squeeze-and-Excitation Networkscited by 4,789
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  5. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  6. 2021Dynamic Neural Networks: A Surveycited by 408
  7. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 332
  8. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 195
  9. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 189
  10. 2019Variable Rate Deep Image Compression With a Conditional Autoencodercited by 114
  11. 2021Dynamic Slimmable Networkcited by 83
  12. 2018Denoising Prior Driven Deep Neural Network for Image Restorationcited by 80
16 more
  1. 2021Towards Flexible Blind JPEG Artifacts Removalcited by 76
  2. 2014From Denoising to Compressed Sensingcited by 68
  3. 2020AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensingcited by 68
  4. 2019Path-Restore: Learning Network Path Selection for Image Restorationcited by 40
  5. 2014Group-based Sparse Representation for Image Restorationcited by 39
  6. 2016Non-Local Color Image Denoising with Convolutional Neural Networkscited by 39
  7. 2021ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensingcited by 39
  8. 2021Memory-Augmented Deep Unfolding Network for Compressive Sensingcited by 38
  9. 2021COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensingcited by 32
  10. 2018Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networkscited by 31
  11. 2021Dynamic Resolution Networkcited by 31
  12. 2021Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imagingcited by 31
  13. 2021Toward Interactive Modulation for Photo-Realistic Image Restorationcited by 15
  14. 2014Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimizationcited by 13
  15. 2022TransCL: Transformer Makes Strong and Flexible Compressive Learningcited by 8
  16. 2020Learned Variable-Rate Multi-Frequency Image Compression using Modulated Generalized Octave Convolutioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 5; 2026: 3.

15 papers.

Sort:

By area: