Research map / Image generation / Fast diffusion sampling
Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
Ziyue Lin, Jiahe Hou, Hongyu Xia, Xinrui Xie, Feifei Wang, Yuyin Zhou, Wei Wang, Jiawei Liu, Liangqiong Qu
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 |
|---|---|---|---|
| use DRDD instead of the best baseline DFPIR | DRDD · All-in-One-5 (average) | SSIM: 0.912 -> 0.916 | Improved |
| use DRDD instead of DFPIR | DRDD · All-in-One-5 (average) | LPIPS: 0.081 -> 0.073 | Improved |
| use DRDD instead of DA-CLIP (best FID baseline) | DRDD · All-in-One-5 (average) | FID: 20.0 -> 18.3 | Improved |
| use DRDD instead of VLUNet on Deraining | DRDD · All-in-One-5 Deraining | SSIM: 0.981 -> 0.978 | Hurt |
| use DRDD instead of DA-CLIP on Dehazing | DRDD · All-in-One-5 Dehazing | SSIM: 0.959 -> 0.972 | Hurt |
| use DRDD instead of VLUNet on MNMD | DRDD · MNMD (average) | SSIM: 0.9274 -> 0.9338 | Improved |
| use DRDD instead of VLUNet on MNMD | DRDD · MNMD (average) | LPIPS: 0.0784 -> 0.0553 | Improved |
| decouple noise and residual diffusion in IR-SDE (ablation) | De-IRSDE · CelebA-HQ inpainting | FID: 15.14 -> 15.10 | Improved |
| decouple noise and residual diffusion in IR-SDE (ablation) | De-IRSDE · Rain100 deraining | PSNR: 27.2 -> 28.1 | Improved |
| decouple noise and residual diffusion in IR-SDE (ablation) | De-IRSDE · BSD400 denoising | SSIM: 0.833 -> 0.827 | No clear effect |
| decouple noise and residual diffusion in IR-SDE (ablation) | De-IRSDE · BSD400 denoising | FID: 33.29 -> 31.87 | Improved |
| set the injected noise intensity to 1.0 (ablation) | DRDD · All-in-One-5 | SSIM | 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.
- AdAIR — AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation (ICLR 2025) · better on 3 of 3 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
- Residual Denoising Diffusion Models (CVPR 2024 · similarity 0.91)
- Denoising Diffusion Bridge Models (ICLR 2024 · similarity 0.91)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.90)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.90)
- Diffusion Bridge Implicit Models (ICLR 2025 · similarity 0.89)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.89)
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.
