AI Paper Atlas

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

TPAMI 2024 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 40 citations (OpenAlex)

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 changedWhereMeasuredEffect
add noise transformation before embedding (ablation)DMID · CC real-worldPSNR: 35.97 -> 37.09Improved
add noise transformation before embedding (ablation)DMID · FMDD real-worldPSNR: 29.47 -> 31.97Improved
increase sampling times S_t from 1 to 2 (ablation)DMID · CC real-worldPSNR: 37.09 -> 37.84Improved
increase sampling times S_t from 2 to N (ablation)DMID · CC real-worldPSNR: 37.84 -> 37.49Hurt
increase sampling times S_t from 1 to 3 (ablation)DMID · FMDD real-worldPSNR: 31.97 -> 33.22Improved
increase sampling times S_t above 1 with R_t=1 (ablation)DMID · McMaster Gaussian sigma=250PSNRHurt
increase repetition times R_t with MMSE averaging (ablation)DMID · McMaster Gaussian sigma=250PSNRImproved
choose timestep N so denoising ability matches noise level (eta about 1) (ablation)DMID · McMaster sigma=25PSNRImproved
add embedding to DDRM-style diffusion modelDDRM · CC real-worldPSNR: 33.52 -> 37.20Improved
add ensembling on top of embeddingDM+Ours · CC real-worldPSNR: 37.20 -> 37.97Improved
add ensembling on top of embeddingDM+Ours · FMDD real-worldPSNR: 30.99 -> 32.64Improved
add ensembling on top of embeddingDM+Ours · CC real-worldLPIPS: 0.072 -> 0.079Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy