Research map / Image generation / Image restoration
Breaking Measurement Barriers: From Compressed Sensing to Deep Reconstruction
Gang Qu, Ping Wang, Siming Zheng, Xin Yuan
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 AKCS sensing model (ablation) | MEUNet · Set11 (SR=10%) | PSNR (dB): 32.35 -> 32.90 | Improved |
| add AKCS sensing model (ablation) | MEUNet · Set11 (SR=10%) | SSIM: 0.9194 -> 0.9270 | Improved |
| add ResBlock in conv-Transformer block (ablation) | MEUNet · Set11 (SR=10%) | PSNR (dB): 32.63 -> 32.90 | Improved |
| add transposed attention (TA) (ablation) | MEUNet · Set11 (SR=10%) | PSNR (dB): 32.42 -> 32.90 | Improved |
| add measurement-aware cross-attention (MACA) (ablation) | MEUNet · Set11 (SR=10%) | PSNR (dB): 32.79 -> 32.90 | Improved |
| add MACA (ablation) | MEUNet · Set11 (SR=10%) | SSIM: 0.9262 -> 0.9270 | Improved |
| add ResBlock (ablation) | MEUNet · Set11 (SR=10%) | SSIM: 0.9239 -> 0.9270 | Improved |
| add TA (ablation) | MEUNet · Set11 (SR=10%) | SSIM: 0.9205 -> 0.9270 | Improved |
| use MEUNet instead of ProxUnroll | ProxUnroll · Set11 (SR=10%) | PSNR (dB): 32.55 -> 32.90 | Improved |
| use MEUNet instead of ProxUnroll | ProxUnroll · Set11 (SR=50%) | PSNR (dB): 41.97 -> 42.39 | Improved |
| use MEUNet instead of ProxUnroll | ProxUnroll · CBSD68 (SR=50%) | PSNR (dB): 39.23 -> 39.65 | Improved |
| use MEUNet instead of ProxUnroll | ProxUnroll · CBSD68 (SR=10%) | PSNR (dB): 29.43 -> 29.56 | Improved |
Closest papers by meaning
- Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing (CVPR 2025 · similarity 0.87)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.87)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.87)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.86)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.86)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · 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.
