Research map / Image generation / Image restoration
MB-RACS: Measurement-Bounds-Based Rate-Adaptive Image Compressed Sensing Network
Yujun Huang, Bin Chen, Naiqi Li, Baoyi An, Shu‐Tao Xia, Yaowei Wang
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 measurement-bounds-based rate-adaptive sampling instead of uniform sampling (ablation) | MB-RACS · 7 datasets average | PSNR: average improvement of 1.89 dB | Improved |
| set overall sparsity ratio from the sampling rate instead of fixed 0.15 (ablation) | MB-RACS · 7 datasets average | PSNR: average improvement of 0.72 dB | Improved |
| add decoder-side cross-iteration skip connections (ablation) | MB-RACS · 7 datasets average | PSNR: average improvement of 0.09 dB | Improved |
| increase sampling stages from 2 to 5 (ablation) | MB-RACS multi-stage · 7 datasets average | PSNR: 0.30 dB | Improved |
| increase sampling stages from 5 to 8 (ablation) | MB-RACS multi-stage · 7 datasets average | PSNR: 0.05 dB | Improved |
| increase sampling stages from 8 to 10 (ablation) | MB-RACS multi-stage · 7 datasets average | PSNR: 0.004 dB | No clear effect |
| add distribution ratio optimization (ablation) | MB-RACS multi-stage · 7 datasets average | PSNR: average improvement of 0.21 dB | Improved |
| use MB-RACS_ss instead of single-stage saliency-based CASNet | single-stage rate-adaptive CS · 7 datasets average | PSNR: 0.85dB/0.0182 | Improved |
| use measurement-bounds sampling instead of saliency-based sampling with ISTA-Net+ decoder | rate-adaptive sampling · 6 datasets | PSNR vs uniform: saliency-based declines of 3.62 dB; ours std 0.21 dB vs 1.57 dB | Improved |
| use MB-RACS_ss instead of OPINE-Net with uniform sampling | compressed sensing · 7 datasets average | PSNR/SSIM: 1.93dB/0.0175 | Improved |
| use MB-RACS_ss instead of CASNet_ss | CASNet · CBSD68 (sampling rate 0.01) | PSNR: 22.15 -> 23.81 | Improved |
Closest papers by meaning
- Sampling Innovation-Based Adaptive Compressive Sensing (CVPR 2025 · similarity 0.89)
- Practical Compact Deep Compressed Sensing (TPAMI 2024 · similarity 0.88)
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.88)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.87)
- Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing (NeurIPS 2026 · similarity 0.86)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · 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.
