Research map / Label-efficient and robust learning / Self-supervised and contrastive
IntraTomo: Self-Supervised Learning-Based Tomography via Sinogram Synthesis and Prediction
Guangming Zang, Ramzi Idoughi, Rui Li, Peter Wonka, Wolfgang Heidrich
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 Fourier feature projection layer (ablation) | IntraTomo sinogram prediction · PET phantom limited angle | PSNR: 6.38 dB PSNR improvement | Improved |
| use Swish activation instead of ReLU (ablation) | IntraTomo MLP · Shepp-Logan sparse view (5 projections) | PSNR: 0.52 dB | Improved |
| add geometry refinement (TV + non-local means) (ablation) | IntraTomo · Sparse view average | PSNR: 24.53 -> 27.13 | Improved |
| add geometry refinement (TV + non-local means) (ablation) | IntraTomo · Limited angle average | PSNR: 25.53 -> 26.74 | Improved |
| add geometry refinement (TV + non-local means) (ablation) | IntraTomo · Covid-19 sparse view | PSNR: 24.54 -> 27.19 | Improved |
| add geometry refinement (TV + non-local means) (ablation) | IntraTomo · Pepper limited angle | PSNR: 25.82 -> 28.40 | Improved |
Closest papers by meaning
- Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT (ECCV 2026 · similarity 0.87)
- Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning (ICML 2022 · similarity 0.87)
- Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion (CVPR 2018 · similarity 0.86)
- QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction (CVPR 2024 · similarity 0.86)
- Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction (AAAI 2025 · similarity 0.86)
- Improving Robustness of Deep-Learning-Based Image Reconstruction (ICML 2020 · 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.
