Research map / Image generation / Image restoration
Multi-Scale Gradient-Guided Unrolling Architecture with Adaptive Mamba for Compressive Sensing
Le Yang, Hongping Gan
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 A-SSB into HDGF (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR: 31.40 -> 31.94 | Improved |
| add GCAB to A-SSB in FAPO (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR: 31.14 -> 31.94 | Improved |
| add VSSB to A-SSB in FAPO (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR: 31.22 -> 31.94 | Improved |
| add channel adaptive threshold shrinkage (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR: 31.44 -> 31.94 | Improved |
| use 128 sampling kernel instead of 32 (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR: 30.27 -> 31.94 | Improved |
| use 8 stages instead of 6 (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR / params: 31.56 -> 31.94 | Improved |
| use wider channels [32,64,128,256] instead of [32,48,64,128] (ablation) | MambaCS · Set11, CS rate 0.10 | PSNR: 31.23 -> 31.94 | Improved |
| replace CPP-Net with MambaCS | CS reconstruction · General100, CS rate 0.10 | PSNR: 33.16 -> 33.88 | Improved |
| replace CPP-Net with MambaCS | CS-MRI reconstruction · FastMRI avg | PSNR: 28.53 -> 28.61 | Improved |
| replace CPP-Net with MambaCS | CS reconstruction · LIVE29, CS rate 0.10 compute | GFLOPs: 153.47 -> 87.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CPP-Net — CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024) · better on 8 of 8 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
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.87)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.87)
- Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging (CVPR 2025 · similarity 0.87)
- Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging (AAAI 2025 · similarity 0.85)
- Unrolled denoising networks provably learn to perform optimal Bayesian inference (NeurIPS 2024 · similarity 0.85)
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.84)
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.
