AI Paper Atlas

Research map / Image generation / Editing and style transfer

Training-free Geometric Image Editing on Diffusion Models

Hanshen Zhu, Zhen Zhu, Kaile Zhang, Yiming Gong, Yuliang Liu, Xiang Bai

ICCV 2025 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 5 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
decouple editing into transform, source inpainting, target refinement (FreeFine) rather than single-objective drag editingFreeFine · GeoBench 2D editsWarp error (WE): 0.098 -> 0.055Improved
apply FreeFine for 3D edits under the same depth-based transformationFreeFine · GeoBench 3D editsMean distance (MD): 26.10 -> 20.32Improved
use training-free FreeFine refinement instead of trained BrushNet inpaintingFreeFine · GeoBench structure completionFID: 186.93 -> 184.84Improved
FreeFine versus GeoDiffuser on 2D image qualityFreeFine · GeoBench 2D editsFID: 33.89 vs 34.72No clear effect
use FreeFine on structure completion KD metricFreeFine · GeoBench structure completionKD: 0.971 -> 0.982Hurt
add Temporal Contextual Attention instead of MMSA, SSA, SDSA or plain self-attention (ablation)FreeFine · GeoBench qualitative inpainting and refinementqualitative qualityImproved
use TCA smooth transition instead of a single-threshold early stop of MMSA (ablation)FreeFine · GeoBench qualitativequalitative qualityImproved
add Local Perturbation (local DDPM) instead of deterministic DDIM (ablation)FreeFine · GeoBench qualitativequalitative qualityImproved
apply perturbation globally (Global Perturbation) instead of locally (ablation)FreeFine · GeoBench qualitativequalitative qualityHurt
add Content-specified Generation with localized text guidance (ablation)FreeFine · GeoBench qualitativequalitative qualityImproved
apply guidance globally instead of within masks (ablation)FreeFine · GeoBench qualitativebackground and subject consistencyHurt
use FreeFine versus DragonDiffusion in a user studyFreeFine · User study (perceptual quality)preference rate: 20.8% -> 71.1%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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