Research map / Image generation / Editing and style transfer
Breaking the Dilemma of Medical Image-to-image Translation
Lingke Kong, Chenyu Lian, Detian Huang, ZhenJiang Li, Yanle Hu, Qichao Zhou
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 registration network (+R) to cycle-consistency mode (ablation) | CycleGAN · BraTS 2018 misaligned | NMAE: 0.089 -> 0.077 | Improved |
| add registration network (+R) to non-cycle mode (ablation) | CycleGAN · BraTS 2018 misaligned | PSNR: 20.2 -> 25.6 | Improved |
| add registration network (+R) to cycle-consistency mode (ablation) | NICEGAN · BraTS 2018 misaligned | PSNR: 25.2 -> 26.1 | Improved |
| add registration network (+R) (ablation) | MUNIT · BraTS 2018 misaligned | PSNR: 20.6 -> 22.7 | Improved |
| remove cycle-consistency loss when registration is present (ablation) | CycleGAN with registration · BraTS 2018 misaligned | NMAE: 0.077 -> 0.072 | Improved |
| remove cycle-consistency loss without registration (ablation) | CycleGAN · BraTS 2018 misaligned | PSNR: 23.5 -> 20.2 | Hurt |
| remove cycle-consistency loss without registration (ablation) | MUNIT · BraTS 2018 misaligned | NMAE: 0.11 -> 0.10 | Mixed |
| replace Pix2Pix with RegGAN at highest noise (ablation) | CycleGAN backbone · BraTS 2018 Noise.5 | NMAE: 0.181 -> 0.072 | Improved |
| replace CycleGAN(C) with RegGAN at highest noise | CycleGAN backbone · BraTS 2018 Noise.5 | PSNR: 23.7 -> 25.2 | Improved |
| replace Pix2Pix with RegGAN on aligned data | CycleGAN backbone · BraTS 2018 Noise.0 | PSNR: 25.6 -> 26 | Improved |
| replace CycleGAN(C) with RegGAN on unpaired data | CycleGAN backbone · BraTS 2018 unpaired | NMAE/PSNR/SSIM | Improved |
Closest papers by meaning
- Harmonic Unpaired Image-to-image Translation (ICLR 2019 · similarity 0.87)
- Unsupervised Multi-modal Medical Image Registration via Invertible Translation (ECCV 2024 · similarity 0.86)
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.83)
- CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data (CVPR 2024 · similarity 0.83)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.83)
- TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging (ICML 2025 · 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.
