AI Paper Atlas

Research map / Image generation / Editing and style transfer

KV-Edit: Training-Free Image Editing for Precise Background Preservation

Tianrui Zhu, Shiyi Zhang, Jiawei Shao, Yansong Tang

ICCV 2025 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 50 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
cache and reuse background key-value pairs instead of regenerating backgroundKV-Edit on FLUX.1-dev · PIE-BenchPSNR: 35.87 vs 32.53 (FLUX Fill), 24.44 (RF Edit)Improved
add no-skip inversion step (NS) (ablation)KV-Edit object removal · PIE-Bench object removalImage Reward vs source prompt (lower is better): 6.87 -> 3.17Improved
add reinitialization (RI) to NS (ablation)KV-Edit object removal · PIE-Bench object removalImage Reward vs source prompt (lower is better): 3.17 -> 0.22Improved
add attention mask during inversion to NS+RI (ablation)KV-Edit object removal · PIE-Bench object removalImage Reward vs source prompt (lower is better): 0.22 -> 0.90Hurt
add NS, RI and AM together (ablation)KV-Edit object removal · PIE-Bench object removalHPS x10^2: 26.76 -> 26.51Hurt
add reinitialization and no-skip (+NS+RI) (ablation)KV-Edit · PIE-BenchPSNR: PSNR 35.87 -> 33.30, CLIP Sim 22.39 -> 23.62Mixed
use inversion-free variant of KV-Edit (ablation)KV-Edit · 512x512, 28 stepsKV cache memory: 19.4G -> 1.9GImproved
use inversion-free variant of KV-EditKV-Edit · PIE-BenchartifactsHurt

Later papers that compared with this method

2 later accepted papers report KV-Edit as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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