Research map / 3D vision / Depth and stereo
Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging
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 PnP-FFDNet instead of GAP-TV | SCI reconstruction · Six benchmark datasets (average) | PSNR (dB): 26.73 -> 29.70 | Helped |
| Use PnP-FFDNet instead of GAP-TV | SCI reconstruction · Six benchmark datasets (average) | Run time (min): 0.07 -> {{\bf 0.05} (GPU) | Helped |
| Use DeSCI (GAP-WNNM) instead of PnP-FFDNet | SCI reconstruction · Six benchmark datasets (average) | PSNR (dB): 29.70 -> 32.65 | Helped |
| Use PnP-WNNM-FFDNet instead of DeSCI (GAP-WNNM) | SCI reconstruction · Six benchmark datasets (average) | Run time (min): 103.0 -> 17.9 | Helped |
| Use PnP-WNNM-FFDNet instead of PnP-FFDNet | SCI reconstruction · Six benchmark datasets (average) | PSNR (dB): 29.70 -> 31.72 | Helped |
| Use PnP-WNNM-FFDNet instead of PnP-FFDNet | SCI reconstruction · Six benchmark datasets (average) | Run time (min): {{\bf 0.05} (GPU) -> 17.9 | Hurt |
| Replace PnP-FFDNet with PnP-VBM4D | SCI reconstruction · Six benchmark datasets (average) | PSNR (dB): 29.70 -> 27.68 | Hurt |
| Use PnP-WNNM-TV instead of PnP-FFDNet | SCI reconstruction · Six benchmark datasets (average) | PSNR (dB): 29.70 -> 32.14 | Helped |
| Use PnP-WNNM-VBM4D instead of PnP-FFDNet | SCI reconstruction · Six benchmark datasets (average) | PSNR (dB): 29.70 -> 29.66 | No clear effect |
| Use PnP-FFDNet instead of GAP-TV | Real SCI reconstruction · chopperwheel (256×256×14) | Run time (second): 11.6 -> 2.7 | Helped |
| Use PnP-FFDNet instead of GAP-TV | Real SCI reconstruction · labs (484×248×10) | Run time (second): 36.9 -> 4.5 | Helped |
| Use PnP-FFDNet instead of GAP-TV | Real SCI reconstruction · hammer color (512×512×22) | Run time (second): 94.5 -> 12.6 | Helped |
Closest papers by meaning
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.89)
- Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.86)
- Dual Prior Unfolding for Snapshot Compressive Imaging (CVPR 2024 · similarity 0.86)
- DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model (CVPR 2024 · similarity 0.86)
- Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging (CVPR 2025 · similarity 0.85)
- PnP-Flow: Plug-and-Play Image Restoration with Flow Matching (ICLR 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.