Research map / 3D vision / 3D generation
Improving 2D Diffusion Models for 3D Medical Imaging with Inter‑Slice Consistent Stochasticity
Chenhe Du, Qing Wu, Xuanyu Tian, Jingyi Yu, Hongjiang Wei, Yuyao Zhang
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 ISCS slerp-correlated noise | DDS · SVCT 30 views (axial) | PSNR: 34.76 -> 36.97 | Improved |
| add ISCS slerp-correlated noise | DDNM · LACT 0-100 deg (axial) | PSNR: 28.40 -> 30.89 | Improved |
| add ISCS slerp-correlated noise | DDS · MRI SR 5x (axial) | PSNR: 39.32 -> 40.33 | Improved |
| add ISCS slerp-correlated noise | DDNM · SVCT 30 views | inter-slice difference gap |Delta|: 0.009342 -> 0.001785 | Improved |
| add TV regularization instead of ISCS (ablation) | DDS · SVCT 30 views (axial) | PSNR: 36.97 -> 36.26 | Hurt |
| add TV regularization instead of ISCS (ablation) | DDS · LACT 0-100 deg (coronal) | PSNR: 32.90 -> 33.33 | Improved |
| use identical noise across slices (BCS) instead of slerp noise (ablation) | ISCS · SVCT, CT volumes | visual quality | Hurt |
| vary angle between slerp anchors from 30 to 175 degrees (ablation) | ISCS · SVCT 30 views (axial) | PSNR: 36.84 -> 36.90 | No clear effect |
Closest papers by meaning
- DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction (NeurIPS 2024 · similarity 0.91)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.87)
- Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency (ICLR 2024 · similarity 0.87)
- SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems (ICML 2025 · similarity 0.87)
- Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling (NeurIPS 2025 · similarity 0.86)
- Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data (ICLR 2025 · 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.
