AI Paper Atlas

Research map / Image generation / Editing and style transfer

CompleteMe: Reference-based Human Image Completion

Yu-Ju Tsai, Brian Price, Qing Liu, Luis Figueroa, Daniil Pakhomov, Zhihong Ding, Scott Cohen, Ming-Hsuan Yang

ICCV 2025 · Image generation › Editing and style transfer · approach: Pose-guided person image synthesis · 3 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 CLIP encoder with Reference U-Net encoder for reference features (ablation)CompleteMe · benchmarkDreamSim: 0.0457 -> 0.0437Improved
replace DINOv2 encoder with Reference U-Net encoder (ablation)CompleteMe · benchmarkDreamSim: 0.0639 -> 0.0437Improved
add Region-focused Attention block to U-Net encoder (ablation)CompleteMe · benchmarkDreamSim: 0.0437 -> 0.0419Improved
add Region-focused Attention block to U-Net encoder (ablation)CompleteMe · benchmarkCLIP-I: 97.05 -> 97.18Improved
train the Reference U-Net instead of freezing it (ablation)CompleteMe · benchmarkDreamSim: 0.0444 -> 0.0419Improved
add reference masks to RFA (with frozen U-Net and prompt) (ablation)CompleteMe · benchmarkDreamSim: 0.0521 -> 0.0444Improved
add text prompt input to Complete U-Net (frozen U-Net, no mask) (ablation)CompleteMe · benchmarkDreamSim: 0.0513 -> 0.0521No clear effect
use 50% random mask ratio instead of 100% random masks (ablation)CompleteMe · benchmarkDreamSim: 0.0495 -> 0.0419Improved
use 50% random mask ratio instead of 0% (human shape only) (ablation)CompleteMe · benchmarkCLIP-I: 97.09 -> 97.18No clear effect
CompleteMe vs MimicBrushMimicBrush · benchmarkDreamSim: 0.0651 -> 0.0419Improved
CompleteMe vs LeftRefill on PSNRLeftRefill · benchmarkPSNR: 28.8657 -> 28.7020Hurt
user study: CompleteMe vs LeftRefill on qualityLeftRefill · benchmark user studyQuality preference: 14.97% / 85.03%Improved

Later papers that compared with this method

1 later accepted paper reports CompleteMe as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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