AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion

Yu Cao, Shaogang Gong

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 6 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
use CRDI diffusion reconstruction with SGE instead of Image2StyleGAN inversion (eta=15)FFHQ-pretrained generator · Reconstruction, BedroomSSIM: 0.52 -> 0.84Improved
increase degree of rigidity eta from 1 to 15 (ablation)CRDI · Reconstruction, BabiesSSIM: 0.55 -> 0.74Improved
use low eta=1 on a domain similar to source (ablation)CRDI generation · Babies generationvisual qualityHurt
increase eta beyond optimum (ablation)CRDI · Babies FID and Intra-LPIPSFIDHurt
add noise perturbation scheduler to SGE and keep SGE reconstruction (removing either component) (ablation)CRDI · Babies, Sunglasses, MetFacesFIDImproved
replace GenDA with CRDI under one-shot adaptationFFHQ source model · Sunglasses 1-shotFID: 83.70 -> 74.60Improved
replace GenDA with CRDI at 10-shotFFHQ source model · Sunglasses 10-shotFID: 35.64 -> 24.62Improved
CRDI versus RICK fine-tuning on BabiesCRDI · Babies FIDFID: 39.39 -> 48.52Hurt
CRDI versus RICK on MetFaces FIDCRDI · MetFacesFID: 48.53 -> 94.86Hurt
CRDI versus RICK on MetFaces mode coverageCRDI · MetFacesMC-SSIM: 0.69 -> 0.78Improved

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