AI Paper Atlas

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

PositionIC: Unified Position and Identity Consistency for Image Customization

Junjie Hu, Tianyang Han, Kai Ma, Jialin Gao, Yang Song, Xianhua He, Junfeng Luo, Xiaoming Wei, Wenqiang Zhang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization

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 visibility-aware attention (VAA) restricting reference tokens to their bounding-box region (ablation)PositionIC · DreamBench single-subjectDINO: 0.686 -> 0.823Improved
add visibility-aware attention (VAA) (ablation)PositionIC · DreamBench single-subjectCLIP-I: 0.784 -> 0.846Improved
add visibility-aware attention (VAA) (ablation)PositionIC · DreamBench single-subjectCLIP-T: 0.269 -> 0.269No clear effect
add VAA for position control (ablation)PositionIC · qualitative position controlposition control abilityImproved
add volumetric weight regulation (VWR) for overlapping objects (ablation)PositionIC · overlap cases (qualitative)occlusion handlingImproved
train on filtered PIC-98K instead of unfiltered PIC-400K or Subject200K (ablation)PositionIC · DreamBenchsubject fidelityImproved
use PositionIC over UNO on single-subject DreamBenchPositionIC · DreamBench single-subjectDINO: 0.814 -> 0.823Improved
use PositionIC over UNO on multi-subject DreamBenchPositionIC · DreamBench multi-subjectDINO: 0.707 -> 0.771Improved
use PositionIC over Gligen on single-subject position controlPositionIC · PositionIC-Bench single-subjectAP70: IoU 0.808 -> 0.828; AP70 0.811 -> 0.761Mixed
use PositionIC over Gligen on multi-subject position controlPositionIC · PositionIC-Bench multi-subjectAP: 0.628 -> 0.701Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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