Research map / Optimization / Optimizers
Beyond Single Solution: Multi-Hypothesis Deep Unfolding Network for Image Compressive Sensing
Wenxue Cui, Hualin Li, Yuhang Qin, Yifu Xu, Xiaopeng Fan, Debin Zhao
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 AlphaNet spatially varying step sizes (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.06 -> 36.27 | Improved |
| add MHCB (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.10 -> 36.27 | Improved |
| add diversity and data composite loss (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.17 -> 36.27 | Improved |
| add spatial attention in MHCB (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.14 -> 36.27 | Improved |
| add channel attention in MHCB (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.22 -> 36.27 | Improved |
| add data fidelity loss (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.22 -> 36.27 | Improved |
| add diversity regularizer (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.24 -> 36.27 | Improved |
| increase hypotheses from 1 to 16 (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.42 -> 36.72 | Improved |
| increase hypotheses from 16 to 32 (ablation) | MHC-DUN · Set11 avg PSNR | PSNR: 36.72 -> 36.74 | No clear effect |
| share parameters across stages (MHC-DUN*) | MHC-DUN · Set11 avg PSNR | PSNR: 33.91 -> 33.85 | No clear effect |
| MHC-DUN vs USB-Net | MHC-DUN · Set11 avg PSNR | PSNR: 33.46 -> 33.91 | Improved |
| MHC-DUN vs USB-Net | MHC-DUN · Urban100 avg PSNR | PSNR: 30.86 -> 31.90 | Improved |
Closest papers by meaning
- Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing (CVPR 2025 · similarity 0.91)
- CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing (CVPR 2024 · similarity 0.89)
- HUNet: Homotopy Unfolding Network for Image Compressive Sensing (CVPR 2025 · similarity 0.89)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.89)
- Dual Prior Unfolding for Snapshot Compressive Imaging (CVPR 2024 · similarity 0.87)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.86)
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.
