Research map / Image generation / Image restoration
Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
Tong Li, Hansen Feng, Lizhi Wang, Lin Zhu, Zhiwei Xiong, Hua Huang
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 noise transformation before embedding (ablation) | DMID · CC real-world | PSNR: 35.97 -> 37.09 | Improved |
| add noise transformation before embedding (ablation) | DMID · FMDD real-world | PSNR: 29.47 -> 31.97 | Improved |
| increase sampling times S_t from 1 to 2 (ablation) | DMID · CC real-world | PSNR: 37.09 -> 37.84 | Improved |
| increase sampling times S_t from 2 to N (ablation) | DMID · CC real-world | PSNR: 37.84 -> 37.49 | Hurt |
| increase sampling times S_t from 1 to 3 (ablation) | DMID · FMDD real-world | PSNR: 31.97 -> 33.22 | Improved |
| increase sampling times S_t above 1 with R_t=1 (ablation) | DMID · McMaster Gaussian sigma=250 | PSNR | Hurt |
| increase repetition times R_t with MMSE averaging (ablation) | DMID · McMaster Gaussian sigma=250 | PSNR | Improved |
| choose timestep N so denoising ability matches noise level (eta about 1) (ablation) | DMID · McMaster sigma=25 | PSNR | Improved |
| add embedding to DDRM-style diffusion model | DDRM · CC real-world | PSNR: 33.52 -> 37.20 | Improved |
| add ensembling on top of embedding | DM+Ours · CC real-world | PSNR: 37.20 -> 37.97 | Improved |
| add ensembling on top of embedding | DM+Ours · FMDD real-world | PSNR: 30.99 -> 32.64 | Improved |
| add ensembling on top of embedding | DM+Ours · CC real-world | LPIPS: 0.072 -> 0.079 | Hurt |
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · 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
- Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy (NeurIPS 2024 · similarity 0.90)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.90)
- Residual Denoising Diffusion Models (CVPR 2024 · similarity 0.90)
- Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models (ICLR 2024 · similarity 0.89)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.89)
- Compressed Image Generation with Denoising Diffusion Codebook Models (ICML 2025 · 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.
