Research map / Image generation / Autoregressive and latent generation
Rethinking CT Synthesis through Semantics-Structure Alignment
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 a mask-guided CT synthesis approach that aligns semantics and structure to avoid treating all tissues uniformly (abstract only; details unavailable).
Problem
Mask-guided CT synthesis from structural annotations suffers from semantic misalignment and structural hallucination because current methods treat all tissues uniformly and ignore tissue-specific CT intensity distributions and strict anatomy.
Approach
Rethinks CT synthesis by explicitly aligning semantics and structure, modeling tissue-specific CT properties rather than optimizing all tissues identically; specifics not stated in the abstract.
Closest papers by meaning
- Anatomy-Preserving Unpaired Medical Image Translation via Shared Latent Anchoring (NeurIPS 2026 · similarity 0.89)
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.87)
- Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation (CVPR 2025 · similarity 0.84)
- Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration (CVPR 2024 · similarity 0.84)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.84)
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · 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.