Research map / Image generation / Image restoration
FourierPET: Deep Fourier-based Unrolled Network for Low-count PET Reconstruction
Zheng Zhang, Hao Tang, Yingying Hu, Zhanli Hu, Jing Qin
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 SCM replacing conv x-update (ablation) | unrolled ADMM baseline · In-House (1% count) | PSNR: 33.15 -> 34.62 | Improved |
| add APCM replacing conv z-update (ablation) | unrolled ADMM baseline · In-House (1% count) | PSNR: 33.15 -> 34.05 | Improved |
| combine SCM and APCM (ablation) | unrolled ADMM baseline · UDPET DRF-100 (1% count) | PSNR: 25.95 -> 27.98 | Improved |
| add A^T back-projection in SCM (ablation) | SCM · In-House (1% count) | PSNR: 22.55 -> 35.19 | Improved |
| add SSFNO in SCM (ablation) | SCM · In-House (1% count) | PSNR: 33.69 -> 35.19 | Improved |
| add spatial module in SCM (ablation) | SCM · In-House (1% count) | PSNR: 34.43 -> 35.19 | Improved |
| add amplitude branch to phase-only APCM (ablation) | APCM · In-House (1% count) | PSNR: 33.95 -> 34.05 | Improved |
| add amplitude branch to phase-only APCM (ablation) | APCM · In-House (1% count) | SSIM: 0.968 -> 0.967 | Hurt |
| add phase branch to amplitude-only APCM (ablation) | APCM · In-House (1% count) | SSIM: 0.958 -> 0.967 | Improved |
| use FourierPET vs best baselines with fewer params | FourierPET · In-House (1% count) | PSNR: 34.95 (LCPR-Net) -> 35.19 with 0.44M params | Improved |
Closest papers by meaning
- Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting (NeurIPS 2024 · similarity 0.83)
- Efficient Noise Calculation in Deep Learning-based MRI Reconstructions (ICML 2025 · similarity 0.82)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.82)
- Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging (CVPR 2025 · similarity 0.81)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.81)
- Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification (AAAI 2025 · similarity 0.81)
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.
