AI Paper Atlas

Research map / Image generation / Editing and style transfer

OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal

Qinming Zhou, Chenxi Sun, Deyang Kong, Junhao He, Xiangheng Tang, Peike Yu, Haotian Wu, Leilei Cao, Linfeng Zhang

ECCV 2026 · Image generation › Editing and style transfer · approach: Inversion-based diffusion editing · 0 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
use noise level t=400 instead of t=200 for one-step restoration (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)FID: 60.1520 -> 50.0639Improved
use noise level t=400 instead of t=600 (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)FID: 55.4021 -> 50.0639Improved
use noise level t=400 instead of t=800 (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)PSNR: 22.644 -> 22.696Improved
occupancy (area-pooled) patch targets instead of hard mask targets (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)FID: 56.1508 -> 50.0639Improved
occupancy patch targets instead of Gaussian soft targets (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)FID: 64.1290 -> 50.0639Improved
occupancy patch targets instead of Gaussian soft targets (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)PSNR: 21.992 -> 22.696Improved
Gaussian soft targets instead of hard mask targets (ablation)OSOR(SDXL) · RORD-Val (object-effect mask)FID: 56.1508 -> 64.1290Hurt
add alpha head with alpha compositing (Phase II) over hard blending (Phase I) (ablation)OSOR · RORD-Val (object-only and effect-aware conditioning masks)fidelity and perceptual metricsImproved
real-pair refinement on captured OBER subset for 1K stepsOSOR(FLUX) · RORD-ValFID: 27.4/28.1 -> 23.8/23.8Improved
real-pair refinement on captured OBER subsetOSOR(FLUX) · OmniPaint-BenchFID: 49.2 -> 44.4Improved
real-pair refinement on captured OBER subsetOSOR(FLUX) · RemovalBenchFID: 43.9 -> 42.5Improved
switch conditioning mask from object-only to object-effect maskOSOR(FLUX) · CORNE-ValFID: 12.3241 -> 12.5203No 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