Research map / Image generation / Image restoration
Practical Compact Deep Compressed Sensing
Bin Chen, Jian Zhang
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 transmission augmenting (31-channel auxiliary variable across stages) (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): +0.58dB PSNR | Improved |
| enable ratio scalability with cropped Gaussian matrix (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): -0.31dB PSNR | Hurt |
| make sampling matrix learnable (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): +1.97dB PSNR | Improved |
| replace residual blocks with Swin-Conv blocks (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): +0.26dB PSNR, -0.26M params | Improved |
| add spatial downscaling r=2 in Swin-Conv blocks (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): -0.06dB PSNR, more than 2x speed | Mixed |
| train on larger WED dataset instead of Train400 (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): +0.23dB PSNR | Improved |
| use Charbonnier loss (ablation) | PGD-unrolled baseline · Set11 | PSNR (dB): +0.07dB PSNR | Improved |
| add deep filtering network to sampling operator (ablation) | PC-CNN · Set11 CS ratio 10% (PC-CNN ablation) | PSNR (dB): 30.42 -> 31.23 | Improved |
| add D-branch (global DCT) to G-branch sampling (ablation) | PC-CNN · Set11 CS ratio 10% (PC-CNN ablation) | PSNR (dB): 29.97 -> 30.42 | Improved |
| add random permutation to G-branch (ablation) | PC-CNN · Set11 CS ratio 10% (PC-CNN ablation) | PSNR (dB): 29.31 -> 30.42 | Improved |
| add G-branch to D-branch (ablation) | PC-CNN · Set11 CS ratio 10% (PC-CNN ablation) | PSNR (dB): 29.43 -> 30.42 | Improved |
| increase stage number K from 10 to 20 (ablation) | PC-CNN · Set11 CS ratio 10% (PC-CNN ablation) | PSNR (dB): 31.06 -> 31.39 | 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.
- ISTA-Net++ — ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing (CVPR 2018) · better on 3 of 3 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
- ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing (CVPR 2018 · similarity 0.91)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.90)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.89)
- Deep Compressed Sensing (ICML 2019 · similarity 0.89)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.89)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.88)
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.
