Research map / Image generation / Image restoration
AdaCS: Adaptive Compressive Sensing With Restricted Isometry Property-Based Error-Clamping
Chenxi Qiu, Xuemei Hu
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 cascaded feature fusion between stages (ablation) | ACCSNet · Set5, rate 0.2 | PSNR: 36.70 -> 37.19 | Improved |
| add cascaded feature fusion between stages (ablation) | ACCSNet · BSDS500, rate 0.2 | PSNR: 32.28 -> 32.67 | Improved |
| add cascaded feature fusion between stages (ablation) | ACCSNet · Set5, rate 0.05 (stage 1) | PSNR: 30.01 -> 30.01 | No clear effect |
| add adaptive sampling module (ASM) (ablation) | ACCSNet · Set14 and BSD68, stages 2+ | PSNR: about 1dB improvement in PSNR | Improved |
| patch size 8 instead of 32 (ablation) | ACCSNet · General100, rate 0.2 | PSNR: 35.93 -> 37.23 | Improved |
| patch size 8 instead of 16 (ablation) | ACCSNet · Set14, rate 0.2 | PSNR: 32.76 -> 33.27 | Improved |
| patch size 8 instead of 16 (ablation) | ACCSNet · Set14, rate 0.1 | PSNR: 29.99 -> 30.00 | No clear effect |
| increase sampling scale factor alpha from 0.5 to 0.7 (ablation) | ACCSNet · BSDS500 average | SSIM: 0.8275 -> 0.8323 | Improved |
| increase sampling scale factor alpha from 0.7 to 0.8 (ablation) | ACCSNet · BSDS500 average | PSNR: 30.02 -> 29.72 | Hurt |
Closest papers by meaning
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.90)
- Sampling Innovation-Based Adaptive Compressive Sensing (CVPR 2025 · similarity 0.90)
- MB-RACS: Measurement-Bounds-Based Rate-Adaptive Image Compressed Sensing Network (TPAMI 2025 · similarity 0.87)
- Ground-Truth Free Meta-Learning for Deep Compressive Sampling (CVPR 2023 · similarity 0.85)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.85)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.83)
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.
