AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation

Daniel Winter, Asaf Shul, Matan Cohen, Dana Berman, Yael Pritch, Alex Rav-Acha, Yedid Hoshen

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 13 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
add 2 more reference views (3 instead of 1) (ablation)ObjectMate · Object insertionIR: 0.803 -> 0.858Improved
add 2 more reference views (ablation)ObjectMate · Object insertionDINO: 0.868 -> 0.885Improved
add 2 more reference views (ablation)ObjectMate · DreamBench subject generationIR: 0.739 -> 0.750Improved
add 2 more reference views (ablation)ObjectMate · DreamBench subject generationCLIP-I: 0.770 -> 0.773No clear effect
use IR retrieval features instead of DINO for building the dataset (ablation)ObjectMate · Object insertion user studyidentity preference: 63%Improved
scale up unsupervised dataset size (ablation)ObjectMate · Object insertionidentity and DINO metricsImproved
use public Open Images data and public IR features (ablation)ObjectMate · Object insertionIR / DINONo clear effect
use IR for identity metric instead of CLIP-Iuser preference prediction · Subject generationprediction accuracy: 64.7% -> 72.9%Improved
use IR for identity metric instead of DINOuser preference prediction · Object insertionprediction accuracy: 71.8% -> 79.5%Improved
ObjectMate versus ObjectDrop copy-pasteObjectMate · Object insertion user studyidentity preservation: 71%Hurt
ObjectMate versus ObjectDropObjectMate · Object insertion user studycomposition: 76%Improved
ObjectMate versus DisenBoothObjectMate · DreamBench subject generationDINO: 0.625 vs 0.607Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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