Research map / Image generation / Fast diffusion sampling
Y-diff: Structure-Texture Decoupled Diffusion Distillation for H&E-to-pCLE Translation
Haodong Wang, Yan Wen, Hongen Liao, Fang Chen, Tianqi Huang
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 flow matching on target semantic code (ablation) | Y-diff · CCD | SS: 0.5397 -> 0.6892 | Improved |
| add flow matching on target semantic code (ablation) | Y-diff · CCD | LC: 0.9339 -> 0.9387 | No clear effect |
| add SPNet structural constraints (ablation) | Y-diff · CCD | SS: 0.6090 -> 0.6892 | Improved |
| add SPNet structural constraints (ablation) | Y-diff · CCD | Hist: 0.7814 -> 0.8684 | Improved |
| add discriminator adversarial supervision (ablation) | Y-diff · CCD | SS: 0.6039 -> 0.6892 | Improved |
| add discriminator adversarial supervision (ablation) | Y-diff · CCD | LPIPS: 0.4992 -> 0.4948 | Improved |
| add flow matching on target semantic code (ablation) | Y-diff · CCD | LPIPS: 0.4810 -> 0.4948 | Hurt |
| replace Student with true target semantic code (oracle) (ablation) | Y-diff · CCD | SS: 0.6892 -> 0.7015 | Improved |
| augment U-Net training with Y-diff pseudo-pCLE images | U-Net cell counting · CCD | MAPE (%): 55.77 -> 13.84 | Improved |
| augment with CycleGAN pseudo-pCLE images | U-Net cell counting · CCD | MAPE (%): 55.77 -> 30.86 | Improved |
| use Y-diff instead of CycleGAN | image translation · CCD | SS: 0.614 -> 0.689 | Improved |
| use Y-diff instead of CycleGAN | image translation · MIST ER-004 | FID: 59.8261 -> 41.4010 | Improved |
Closest papers by meaning
- Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images (ICLR 2025 · similarity 0.86)
- Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models (ICML 2025 · similarity 0.85)
- Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology (NeurIPS 2025 · similarity 0.85)
- Micro-Bench: A Microscopy Benchmark for Vision-Language Understanding (NeurIPS 2024 · similarity 0.85)
- Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction (NeurIPS 2026 · similarity 0.85)
- Unpaired Multi-Domain Histopathology Virtual Staining Using Dual Path Prompted Inversion (AAAI 2025 · similarity 0.84)
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.
