Research map / Image generation / Editing and style transfer
Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translation
Zihao WANG, Yuzhou Chen, Shaogang Ren
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 spatially varying dynamic domain-shift schedule in place of fixed linear schedule (ablation) | CDTSDE · PSCDE | Dice: 0.46 -> 0.49 | Improved |
| add spatially varying dynamic domain-shift schedule in place of fixed linear schedule (ablation) | CDTSDE · PSCDE | Hausdorff distance (lower better): 59.5 -> 39.8 | Improved |
| add per-channel non-linear schedule in place of linear schedule (ablation) | CDTSDE · PSCDE | Dice: 0.46 -> 0.46 | No clear effect |
| add per-channel non-linear schedule in place of linear schedule (ablation) | CDTSDE · PSCDE | Hausdorff distance (lower better): 59.5 -> 43.0 | Improved |
| add dynamic schedule in place of linear schedule (ablation) | CDTSDE · Sentinel remote-sensing | SSIM: 0.764 -> 0.774 | Improved |
| add dynamic schedule in place of linear schedule (ablation) | CDTSDE · Sentinel remote-sensing | PSNR (dB): 23.28 -> 23.37 | Improved |
| use CDTSDE instead of DOSSR | CDTSDE · PSCDE | Dice: 0.460 -> 0.488 | Improved |
| use CDTSDE instead of DOSSR for sampling | CDTSDE · Sentinel at PSNR approx 15 dB | sampling steps: 10 -> 5 | Improved |
| use CDTSDE instead of DOSSR | CDTSDE · IXI (T1 to T2) | SSIM: 0.75 -> 0.76 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BBDM — BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models (CVPR 2023) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge (NeurIPS 2025 · similarity 0.89)
- Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models (NeurIPS 2024 · similarity 0.88)
- Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution (CVPR 2025 · similarity 0.88)
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.88)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.88)
- FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion (CVPR 2025 · similarity 0.87)
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.
