AI Paper Atlas

Research map / Image generation / Editing and style transfer

Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models

Ruibin Li, Ruihuang Li, Song Guo, Lei Zhang

ECCV 2024 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 10 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
replace DDIM inversion with fixed-point loss search (SPDInv) on top of P2PP2P editing engine · PIE-BenchDINO distance x10^3: 69.43 -> 8.81Improved
SPDInv versus AIDI fixed-point iteration under MasaCtrlMasaCtrl engine · PIE-BenchDINO distance x10^3: 55.93 -> 20.48Improved
apply SPDInv to PNP engine vs DirectInvPNP engine · PIE-BenchPSNR: 22.43 -> 26.72Improved
integrate SPDInv into ELITE customized generationELITE · Localized editingPSNR: 14.83 -> 24.14Improved
SPDInv inversion costP2P · PIE-BenchInversion time (s): 11.55 -> 27.04Hurt
increase max optimization rounds K from 5 to 50 (ablation)SPDInv · PIE-Bench subsetCLIP: PSNR 31.49 -> 32.12; CLIP 26.70 -> 26.32Mixed
increase learning rate eta to 0.1 (ablation)SPDInv · PIE-Bench subsetPSNR: 31.55 -> 22.82Hurt
tighten stopping threshold delta below 5e-6 (ablation)SPDInv · PIE-Bench subsetPSNR: 31.61 -> 31.65No clear effect
SPDInv reduces noise code dependence on source prompt vs DDIM inversioninverted noise code · 100 generated imagesCLIP score between noise and source prompt: 14.55 -> 13.18Improved
SPDInv on mask-less addition or portrait editingSPDInv with P2P/MasaCtrl/PNP · failure casesqualitativeNo clear effect

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