AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

Jiwen Yu, Yinhuai Wang, Chen Zhao, Bernard Ghanem, Jian Zhang

ICCV 2023 · Image generation › Fast diffusion sampling · approach: Guidance for conditional diffusion · 184 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
FreeDoM instead of TediGANtext-to-face generation · Text to facesFID: 71.71 -> 55.91Improved
FreeDoM instead of TediGANsketch-to-face generation · Sketches to facesFID: 91.11 -> 70.97Improved
FreeDoM instead of TediGANsegmentation-to-face generation · Segmentation maps to facesFID: 52.77 -> 53.08No clear effect
FreeDoM instead of TediGANsegmentation-to-face generation · Segmentation maps to facescondition distance: 2037.2 -> 1696.1Improved
FreeDoM instead of TediGANsketch-to-face generation · Sketches to facescondition distance: 48.61 -> 33.29Improved
FreeDoM instead of TediGANtext-to-face generation · Text to facescondition distance: 12.31 -> 10.83Improved
FreeDoM instead of UGDstyle-guided 512x512 generation · Style-guided generationsampling time: about 40 minutes -> about 84 secondsImproved
add time-travel strategy (ablation)FreeDoM on ImageNet · ImageNet text 'orange'qualitative condition matchImproved
apply time-travel only in semantic stage (ablation)FreeDoM · ImageNetsampling costImproved
increase energy-function learning rate rho_t from 0 (ablation)FreeDoM · ImageNet and face IDcontrol strengthImproved

Later papers that compared with this method

19 later accepted papers report FreeDoM as a baseline in their results tables; 17 of them report a better number on most of the results they share with it.

11 more not listed.

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