Research map / Image generation / Image restoration
ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use ReconNet with BM3D denoising instead of ReconNet intermediate output alone (ablation) | ReconNet · 11-image set, MR 0.10 | mean PSNR (dB): 22.68 -> 23.23 | Helped |
| Use ReconNet with BM3D denoising instead of ReconNet intermediate output alone (ablation) | ReconNet · 11-image set, MR 0.04 | mean PSNR (dB): 19.99 -> 20.44 | Helped |
| Use ReconNet with BM3D denoising instead of ReconNet intermediate output alone (ablation) | ReconNet · 11-image set, MR 0.01 | mean PSNR (dB): 17.27 -> 17.55 | Helped |
| Use ReconNet with BM3D denoising instead of ReconNet intermediate output alone (ablation) | ReconNet · 11-image set, MR 0.25 | mean PSNR (dB): 25.54 -> 25.92 | Helped |
| Replace iterative reconstruction with ReconNet | CS reconstruction on the 11-image set · MR 0.10, MR 0.04, and MR 0.01 | mean PSNR (dB): MR 0.10: 22.86 -> 23.23; MR 0.04: 18.40 -> 20.44; MR 0.01: 11.34 -> 17.55 | Helped |
| Use CNN-based non-iterative reconstruction rather than iterative TVAL3 | CS reconstruction of a 256 × 256 image · MR 0.25–0.01 | reconstruction time (seconds): ReconNet: 0.0213, 0.0195, 0.0192, 0.0244; TVAL3: 2.943, 3.223, 3.467, 7.790 | Helped |
| Use ReconNet rather than SDA | Non-iterative CS reconstruction · 11-image set, MR 0.10 and MR 0.04 | mean PSNR (dB): MR 0.10: 22.68 -> 23.23; MR 0.04: 20.21 -> 20.44 | Helped |
| Use ReconNet rather than SDA | Non-iterative CS reconstruction · 11-image set, MR 0.25 and MR 0.01 | mean PSNR (dB): MR 0.25: 24.55 -> 25.92; MR 0.01: 17.40 -> 17.55 | No clear effect |
Closest papers by meaning
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.87)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.85)
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.85)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.85)
- Block Image Compressive Sensing with Local and Global Information Interaction (AAAI 2024 · similarity 0.85)
- ReconFusion: 3D Reconstruction with Diffusion Priors (CVPR 2024 · similarity 0.84)
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.