AI Paper Atlas

Research map / Image generation / Editing and style transfer

FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models

Wei WU, Qingnan Fan, Shuai Qin, Hong Gu, Ruoyu Zhao, Antoni Chan

ECCV 2024 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 9 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
progressively enlarge spatial-frequency truncation range on guidance (ablation)FreeDiff (direct SF truncation) · qualitative glasses editedit strength vs source similarityMixed
use a short target prompt (a pizza) instead of the full PIE target prompt (ablation)FreeDiff · qualitative pizza editbackground alterationImproved
add eta truncation (zero out smallest 80% of guidance values) (ablation)FreeDiff · qualitative editsstructure preservationImproved
FreeDiff vs P2P/PNP/MasaCtrl on whole-image CLIP and background LPIPSFreeDiff · PIE subset (~200 images)Background LPIPS: 11.83 -> 11.14Improved
FreeDiff vs PNP on CLIP scoreFreeDiff · PIE subset (~200 images)CLIP Score: 25.4717 -> 25.5140No clear effect

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