Research map / Image generation / Image restoration
Ultra-High-Resolution Unpaired Stain Transformation via Kernelized Instance Normalization
Ming-Yang Ho, Min-Sheng Wu, Che-Ming Wu
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 |
|---|---|---|---|
| replace patch-wise IN with KIN at test time | CUT · Glioma (testing set) | FID: 105.66 -> 100.90 | Improved |
| replace patch-wise IN with KIN at test time | CUT · Kyoto summer2autumn (training set) | FID: 77.59 -> 75.27 | Improved |
| replace patch-wise IN with KIN at test time | CUT · Kyoto summer2autumn (testing set) | FID: 157.04 -> 167.15 | Hurt |
| replace patch-wise IN with KIN at test time | CUT · ANHIR breast FID | FID: 71.00 -> 72.59 | No clear effect |
| replace patch-wise IN with KIN at test time | CycleGAN · ANHIR breast FID | FID: 98.60 -> 96.09 | Improved |
| replace patch-wise IN with KIN at test time | CycleGAN · Glioma (testing set) | FID: 142.28 -> 150.93 | Hurt |
| replace patch-wise IN with KIN at test time | L-LSeSim · ANHIR breast FID | FID: 65.82 -> 67.46 | No clear effect |
| replace TIN (global statistics) with KIN | CUT · ANHIR lung lesion FID | FID: 251.48 -> 56.38 | Improved |
| replace TIN (global statistics) with KIN | CUT · Glioma (testing set) | FID: 200.56 -> 100.90 | Improved |
| replace TIN (global statistics) with KIN | CUT · ANHIR COAD FID | FID: 91.81 -> 93.68 | No clear effect |
| add KIN instead of patch-wise IN, human quality and fidelity evaluation | CUT · ANHIR, glioma, Kyoto | human preference | Improved |
| increase KIN kernel size from 1 to infinity (ablation) | KIN · stain transformation | qualitative output | Mixed |
Closest papers by meaning
- OT-StainNet: Optimal Transport Driven Semantic Matching for Weakly Paired H&E-to-IHC Stain Transfer (AAAI 2025 · similarity 0.86)
- ODA-GAN: Orthogonal Decoupling Alignment GAN Assisted by Weakly-supervised Learning for Virtual Immunohistochemistry Staining (CVPR 2025 · similarity 0.85)
- Unpaired Multi-Domain Histopathology Virtual Staining Using Dual Path Prompted Inversion (AAAI 2025 · similarity 0.85)
- SheafStain: Sheaf-Theoretic Schr\"odinger Bridge for Spatially and Biologically Coherent Virtual Staining (NeurIPS 2026 · similarity 0.84)
- Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images (ICLR 2025 · similarity 0.83)
- Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images (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.
