Research map / Image generation / Image restoration
Learning Memory Augmented Cascading Network for Compressed Sensing of Images
Jiwei Chen, Yubao Sun, Qingshan Liu, Rui Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add contextual memory module and reading gate (ablation) | C-Net (no CM) · Set11 (measurement rate 0.25) | PSNR (dB): +1.24 dB | Improved |
| add contextual memory module and reading gate (ablation) | C-Net (no CM) · Set11 (measurement rate 0.04) | PSNR (dB): +0.44 dB | Improved |
| add reading gate to the contextual memory (ablation) | MC-Net · Set11 (rates 0.25 and 0.04) | PSNR (dB) | Improved |
| add contextual memory module (without reading gate) (ablation) | C-Net · Set11 (rates 0.25 and 0.04) | PSNR (dB) | Improved |
| add more cascading stages (ablation) | MAC-Net · Set11 (measurement rate 0.25) | PSNR (dB): 22.01 -> 32.91 | Improved |
| add cascading stages beyond 8 (ablation) | MAC-Net · Set11 | PSNR (dB) | No clear effect |
| use MAC-Net instead of ISTA-Net+ | reconstruction network · Set11 (measurement rate 0.04) | PSNR (dB): 21.31 -> 24.22 | Improved |
| use MAC-Net instead of ISTA-Net+ | reconstruction network · BSD68 (measurement rate 0.04) | PSNR (dB): 22.17 -> 23.62 | Improved |
| use MAC-Net instead of ISTA-Net+ | reconstruction network · BSD68 (measurement rate 0.30) | PSNR (dB): 30.34 -> 30.28 | Hurt |
| use MAC-Net instead of SCGAN | reconstruction network · Set11 (measurement rate 0.01) | PSNR (dB): 18.43 -> 18.26 | Hurt |
| use MAC-Net instead of DAGAN | reconstruction network · MICCAI 2013 MRI (sampling rate 0.4) | PSNR (dB): 44.83 -> 54.35 | Improved |
| use MAC-Net instead of DAGAN | reconstruction network · MICCAI 2013 MRI (sampling rate 0.1) | PSNR (dB): 33.79 -> 35.94 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- ISTA-Net+ — ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing (CVPR 2018) · better on 7 of 8 shared results
- DAGAN — DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks (CVPR 2018) · better on 5 of 5 shared results
- ReconNet — ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements (CVPR 2016) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.85)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.85)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.84)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.84)
- Sampling Innovation-Based Adaptive Compressive Sensing (CVPR 2025 · similarity 0.84)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
