Research map / Image generation / Image restoration
Scalable Convolutional Neural Network for Image Compressed Sensing
Wuzhen Shi, Feng Jiang, Shaohui Liu, Debin Zhao
Check 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 |
|---|---|---|---|
| Replace CSNet's reconstruction network with SCSNet's hierarchical reconstruction network | CSNet · Set5, Set14, BSD100 average across seven sampling ratios | PSNR: 31.90 -> 32.40 | Improved |
| Replace CSNet's reconstruction network with SCSNet's hierarchical reconstruction network | CSNet · Set5, Set14, BSD100 average across seven sampling ratios | SSIM: 0.8445 -> 0.8507 | Improved |
| Use SCSNet instead of the strongest listed baseline, ISTA-Net+ | ISTA-Net+ · Set11, sampling ratio 0.5 | PSNR: 38.07 -> 39.01 | Improved |
| Use SCSNet instead of CSNet | CSNet · Set11, sampling ratio 0.1 | PSNR: 28.10 -> 28.48 | Improved |
| Use SCSNet instead of CSNet | CSNet · BSD68, sampling ratio 0.5 | PSNR: 34.89 -> 35.77 | Improved |
| Use SCSNet instead of CSNet | CSNet · BSD68, sampling ratio 0.1 | PSNR: 27.10 -> 27.28 | Improved |
| Order measurement bases with the greedy validation-set selection method instead of random selection (ablation) | SCSNet · Set5 and Set14, progressive sampling with the base layer | PSNR | Improved |
| Use one trained model and remove selected measurement bases for intermediate sampling ratios | SCSNet · Sampling ratios between trained layer ratios | PSNR | 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 1 of 1 shared result
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
- Self-supervised Scalable Deep Compressed Sensing (IJCV 2024 · similarity 0.90)
- Practical Compact Deep Compressed Sensing (TPAMI 2024 · similarity 0.89)
- ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing (CVPR 2018 · similarity 0.87)
- When to Use Convolutional Neural Networks for Inverse Problems (CVPR 2020 · similarity 0.87)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.86)
- Sequential Convolution and Runge-Kutta Residual Architecture for Image Compressed Sensing (ECCV 2020 · similarity 0.86)
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.
