Research map / Image generation / Image restoration
Sequential Convolution and Runge-Kutta Residual Architecture for Image Compressed Sensing
Runkai Zheng, Yinqi Zhang, Daolang Huang, Qingliang Chen
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 SCM sequential convolutional sensing module (ablation) | CSNet+ · BSDS100 (1.5625%) | PSNR: 25.01 -> 25.31 | Improved |
| add SCM sequential convolutional sensing module (ablation) | CSNet+ · BSDS100 (50%) | PSNR: 36.62 -> 37.59 | Improved |
| add LRKB Runge-Kutta residual block (ablation) | CSNet+ · BSDS100 (1.5625%) | PSNR: 25.01 -> 25.49 | Improved |
| add LRKB Runge-Kutta residual block (ablation) | CSNet+ · BSDS100 (25%) | PSNR: 32.81 -> 32.43 | Hurt |
| add LRKB Runge-Kutta residual block (ablation) | CSNet+ · BSDS100 (12.5%) | PSNR: 30.11 -> 30.11 | No clear effect |
| add LRKB on top of SCM (ablation) | CSNet+ with SCM · BSDS100 (25%) | PSNR: 33.05 -> 33.43 | Improved |
| add SCM on top of LRKB (ablation) | CSNet+ with LRKB · BSDS100 (25%) | PSNR: 32.43 -> 33.43 | Improved |
| combine SCM and LRKB (RK-CCSNet) (ablation) | CSNet+ · BSDS100 (50%) | PSNR: 36.62 -> 37.92 | Improved |
| replace CSNet+ with RK-CCSNet | CSNet+ · BSDS100 (average) | PSNR: 29.87 -> 30.51 | Improved |
| replace CSNet+ with RK-CCSNet | CSNet+ · Set14 (average) | PSNR: 31.24 -> 32.21 | Improved |
Closest papers by meaning
- Practical Compact Deep Compressed Sensing (TPAMI 2024 · similarity 0.89)
- Global Sensing and Measurements Reuse for Image Compressed Sensing (CVPR 2022 · similarity 0.87)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.86)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.86)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.86)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.85)
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.
