Research map / Video / Video segmentation and tracking
Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging
Zongliang Wu, Chengshuai Yang, Xiongfei Su, 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 |
|---|---|---|---|
| use Two-Stage ADMM instead of GAP | FFDNet PnP · Mid-scale color Bayer | PSNR: 32.03 -> 32.45 | Improved |
| add online network updating | Two-Stage ADMM-FFDNet · Mid-scale color Bayer | PSNR: 32.45 -> 32.70 | Improved |
| add deep demosaicing network (DDNet) (ablation) | Two-Stage ADMM-FFDNet (online) · Mid-scale color Bayer | PSNR: 32.70 -> 32.89 | Improved |
| use closed-form demosaicing instead of DDNet (ablation) | Two-Stage ADMM-FFDNet · Mid-scale color Bayer | PSNR: 32.83 -> 28.72 | Hurt |
| reuse updated network parameters across sequential measurements (ablation) | Two-Stage ADMM-FFDNet-DDNet (online) · Mid-scale color Bayer | PSNR: 32.89 -> 32.95 | Improved |
| add online updating to FastDVDNet | Two-Stage ADMM-FastDVDNet-DDNet · Mid-scale color Bayer | PSNR: 34.93 -> 34.90 | No clear effect |
| add online updating to FastDVDNet denoiser | GAP-FastDVDNet · Grayscale benchmark | PSNR: 32.35 -> 32.56 | Improved |
| use FastDVDNet two-stage with DDNet instead of FFDNet | Two-Stage ADMM · Mid-scale color Bayer | PSNR: 32.95 -> 34.93 | Improved |
| update network once instead of 3 or 5 times per measurement (ablation) | online FFDNet · Beauty first measurement | PSNR | Improved |
| use deep-learning PnP instead of DeSCI | GAP-FastDVDNet (online-reuse) · Grayscale benchmark | PSNR: 32.65 -> 32.56 | Mixed |
Closest papers by meaning
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (TPAMI 2021 · similarity 0.95)
- Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging (CVPR 2020 · similarity 0.94)
- TFPnP: Tuning-free Plug-and-Play Proximal Algorithms with Applications to Inverse Imaging Problems (JMLR 2022 · similarity 0.90)
- PnP-Flow: Plug-and-Play Image Restoration with Flow Matching (ICLR 2025 · similarity 0.89)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.88)
- Plug-and-Play image restoration with Stochastic deNOising REgularization (ICML 2024 · similarity 0.88)
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.
