AI Paper Atlas

Research map / Image generation / Editing and style transfer

PHOTOSWAP: Personalized Subject Swapping in Images

Jing Gu, Yilin Wang, Nanxuan Zhao, Tsu-Jui Fu, Wei Xiong, Qing Liu, Zhifei Zhang, HE Zhang, Jianming Zhang, HyunJoon Jung, Xin Eric Wang

NeurIPS 2023 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing · 7 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 Photoswap instead of P2P+DreamBoothDreamBooth subject swapping · Human evaloverall quality preference: 37.3% vs. 27.1%Improved
use Photoswap instead of P2P+DreamBoothDreamBooth subject swapping · Human evalbackground preservation: 39.3% vs. 30.2%Improved
use Photoswap instead of P2P+DreamBoothDreamBooth subject swapping · Human evalsubject swapping: 42.4% vs 30.0%Improved
use Photoswap instead of PnP+DreamBoothDreamBooth subject swapping · Human evaloverall quality preference: 55.1% vs 22.4%Improved
use Photoswap instead of MasaCtrl+DreamBoothDreamBooth subject swapping · Human evaloverall quality preference: 83.3% vs 10.3%Improved
start attention swap from the earliest diffusion steps (ablation)Photoswap · qualitativelayout preservationImproved
swap self-attention output and maps in all decoder layers of the U-Net (ablation)Photoswap · qualitativesubject swapping qualityImproved
vary latent size of the swapped U-Net layer (ablation)Photoswap · qualitativesubject swapping qualityNo clear effect
increase swapping step lambda_M for self-attention map M (ablation)Photoswap · qualitativeidentity similarity to sourceMixed
copy cross-attention map from source to target (ablation)Photoswap · qualitativelayout alignmentImproved

Later papers that compared with this method

1 later accepted paper reports Photoswap 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