Research map / Image generation / Editing and style transfer
Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an anatomy-preserving unpaired medical image translation method that decouples structure preservation from appearance generation via a shared latent anchor.
Problem
Unpaired medical image-to-image translation must synthesize target-modality images from source-modality images without aligned supervision, but direct source-to-target mappings often distort clinically meaningful anatomy.
Approach
Decouples structure preservation from appearance generation instead of learning one entangled source-to-target mapping, using a shared latent space as an anchor for anatomy (details beyond the abstract not available).
Closest papers by meaning
- Rethinking CT Synthesis through Semantics-Structure Alignment (NeurIPS 2026 · similarity 0.89)
- SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation (CVPR 2026 · similarity 0.88)
- Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision (CVPR 2026 · similarity 0.88)
- Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self Supervision (CVPR 2024 · similarity 0.87)
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.87)
- Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images (ICML 2024 · 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.