Research map / Image generation / Fast diffusion sampling
Recover Cell Tensor: Diffusion-Equivalent Tensor Completion for Fluorescence Microscopy Imaging
Chenwei Wang, Zhaoke Huang, Zelin Li, Wenqi Zhu
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 tensor-completion diffusion method instead of plain DDPM baseline | 3D fluorescence microscopy restoration · C. elegans dataset 1 | PSNR: 31.49 -> 33.18 | Improved |
| use proposed method instead of DDPM baseline | 3D FM restoration · C. elegans dataset 2 | LPIPS: 0.3708 -> 0.2674 | Improved |
| use proposed method instead of DDPM baseline | 3D FM restoration · SR-CACO-2 | PSNR: 40.24 -> 40.30 | No clear effect |
| use proposed method instead of DDPM baseline | 3D FM restoration · SR-CACO-2 | LPIPS: 0.3679 -> 0.2305 | Improved |
| increase Gaussian noise sigma from 0 to 0.1 in the input (ablation) | proposed method · C. elegans dataset 1 | PSNR: 33.18 -> 29.34 | Hurt |
| increase downsampling factor of the input to x4 (ablation) | proposed method · C. elegans dataset 1 | PSNR: 33.18 -> 29.01 | Hurt |
| use proposed method instead of Cycle+IPG | 3D FM restoration · C. elegans dataset 1 | NRQM: 4.65 (DDPM) vs 4.51 (ours) | Hurt |
Closest papers by meaning
- Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution (CVPR 2025 · similarity 0.87)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.85)
- scSplit: Bringing Severity Cognizance to Image Decomposition in Fluorescence Microscopy (NeurIPS 2025 · similarity 0.85)
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy (CVPR 2025 · similarity 0.84)
- MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections (CVPR 2024 · similarity 0.83)
- Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration (NeurIPS 2026 · similarity 0.83)
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.
