Cross-Person Identity Change Under Source-Coupled Multi-Human Generation: A Controlled UniPortrait Study

Edrees Al-Edreesi; Ghaleb Al-Gaphari; Muneer Alsurori; Mohammed Edrees; Fouad Al-Hamdani

cs.CVOct 15, 2026

Cross-Person Identity Change Under Source-Coupled Multi-Human Generation: A Controlled UniPortrait Study

Authors: Edrees Al-Edreesi, Ghaleb Al-Gaphari, Muneer Alsurori, Mohammed Edrees, Fouad Al-Hamdani

Organizations: Sana’a University, Sana’a, Yemen. · Ibb University, Ibb, Yemen.

Abstract

Multi-human personalization must account for identity changes in people outside the nominal target of a generative operation. We characterize this behavior in UniPortrait, without introducing a new preservation algorithm. Two sequential studies use 119 accepted two-person baseline scenes and three fixed output seeds, measuring continuous reference-based facial similarity with InsightFace \buffalo. In Study1, source-coupled single-ID target-only generation (A1) produces negative mean transitions for both the protected person ( $-0.567904$ ) and target ( $-0.236904$ ), indicating broad perturbation rather than established successful repair with collateral loss. In Study2, native dual-ID generation (A2) yields more positive paired contrasts: protected $+0.512918$ (95% case-cluster CI $[0.471434,0.550259]$ ) and target $+0.158853$ ( $[0.118903,0.197523]$ ), across 287 jointly measurable pairs from 111 cases. Shared baseline similarity cancels algebraically in these paired contrasts, leaving a matched POST comparison. Validation designed after the primary result freeze finds directional agreement with an independent identity evaluator and blinded human judgments; within-\buffalo\ nuisance models provide supportive sensitivity evidence. The findings characterize intact native regimes, whose references, routing, adapters, and token counts co-vary. They do not establish component causality, categorical identity preservation, successful localized editing, or generalization beyond the evaluated implementation and measurable cohort.

Figures & tables

Panel of Figure 1 — Figure 1: Design schematic of the evaluated implementation. A1/A2 supply PRE-derived attention context from source slot 0 to a seeded Gaussian output in slot 1. The reference configuration changes as an intact native regime. A0 has no PRE coupling. DIoU and human correspondence occur after generation and do not condition it. Boxes denote operations rather than identity-preservation guarantees.

Study 1: 597 measurable action outputs; 257 jointly measurable case–seed pairs.
Metric	A1	A0	A2
Planned outputs per action	357	357	357
Identity-measurable outputs	304	293	319
Unavailable outputs	53	64	38
Correspondence	DIoU	Human consensus	DIoU
Study 2: 287 paired rows from 111 cases; 74 complete three-seed cases.

Table 1: Study design and availability. All actions use 119 accepted PRE cases and seeds 1101, 2202, 3303. A1 is reused in Study 2. Joint Study 2 counts partition the 357 planned pairs; a case can contribute several seeds.

Study / role	Estimand	Estimate	95% bootstrap CI	Bootstrap SE
1 / Protected $j$	A1 transition	$-0.567904$	$[-0.597297,-0.536832]$	$0.015604$
	A0 transition	$-0.010801$	$[-0.030899,+0.011336]$	$0.010925$
	A1 $-$ A0	$-0.557103$	$[-0.582850,-0.530484]$	$0.013219$
1 / Target $k$	A1 transition	$-0.236904$	$[-0.265309,-0.209629]$	$0.014251$
	A0 transition	$-0.021632$	$[-0.038848,-0.003419]$	$0.009013$
	A1 $-$ A0	$-0.215272$	$[-0.245432,-0.184669]$	$0.015603$

Table 2: Primary and secondary fitted Buffalo_L estimates. Study 1 uses 597 measurable action observations in the 119-case design (A1 304, A0 293); Study 2 uses 287 jointly measurable pairs from 111 cases. All rows use equal seed weights and 5,000 case-cluster bootstrap resamples. Full variance and sensitivity records are in Supplement Tables S2, S3, S6–S8.

Figure 2: Protected-person evidence across the sequential studies. (a) Distributions of

\Delta\mathrm{ID}_{j}

for A1 (

n=304

) and A0 (

n=293

). (b) 287 jointly measurable paired contrasts, their fitted estimate and 95% case-cluster bootstrap interval, and seed strata (

n=94,97,96

). The panels have different endpoints and scales: within-action change in (a), paired between-action difference in (b).

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Axis	Evidential role	Protected: estimate [95% CI]	Target: estimate [95% CI]
Primary Study 2	Buffalo_L paired anchor	$+0.512918$ $[0.471434,0.550259]$	$+0.158853$ $[0.118903,0.197523]$
V1: ID-Sim	Independent metric concordance	$+0.231351$ $[0.207440,0.254732]$	$+0.072272$ $[0.048170,0.097237]$
V2: Human ( $N=5$ raters)	Independent human concordance	$+0.986667$ $[0.965000,1.000000]$	$+0.401948$ $[0.304816,0.498673]$
V3: Core	Supportive within-Buffalo_L sensitivity	$+0.511637$ $[0.471271,0.548896]$	$+0.158524$ $[0.122081,0.192932]$
V3: Pose	Supportive within-Buffalo_L sensitivity	$+0.511421$ $[0.471351,0.550273]$	$+0.158543$ $[0.123847,0.192405]$

Appendix

Table S10: Validation summary. The protocol classifications are CONCORDANT for V1/V2/V3 and OVERALL_CONCORDANT overall. Independent metric/human measurements and supportive within-Buffalo_L nuisance sensitivity have distinct evidential roles. Intervals are 95% case-cluster bootstrap intervals; scales are not interchangeable.

Model	Role	Estimate	95% case-cluster CI
Core	Protected $j$	$+0.511636943$	$[0.47127149,0.54889617]$
Core	Target $k$	$+0.158524410$	$[0.12208135,0.19293198]$
Pose-augmented	Protected $j$	$+0.511421391$	$[0.47135144,0.55027348]$
Pose-augmented	Target $k$	$+0.158542884$	$[0.12384655,0.19240531]$

Appendix

Table S11: V3 nuisance-adjusted estimates and 95% case-cluster bootstrap intervals.

Identity-Preserving Image Generation

Identity-preserving image generation creates or edits images while retaining a person's recognizable features across changes in pose, style, or scene.

See all 48 papers

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas
Oct 23, 2025Gordon Guocheng Qian, Ruihang Zhang, Tsai-Shien Chen +11Subject-Driven Image Generation Image Generation
Snap Inc., USA · University of Toronto, Canada · University of California, Merced, USA +1
AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas
Mar 16, 2026Longhui YuanIdentity-Preserving Image Generation Controllable Image Generation
IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation
Jun 29, 2026Chaoyi Shi, Shanshan Zhang, Jian YangSubject-Driven Image Generation Machine Unlearning
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology · PCA Lab, School of Intelligence Science and Technology, Nanjing University

Oct 23, 2025J/K move · Enter open · S save

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

Gordon Guocheng Qian, Ruihang Zhang, Tsai-Shien Chen, Yusuf Dalva+10

Snap Inc., USA · University of Toronto, Canada · University of California, Merced, USA+1

Subject-Driven Image Generation Image Generation Compositional Image Generation Identity-Preserving Image Generation Conditional Diffusion Models Multi-Subject Image Generation

Open paper AskPDF arXiv

Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer

Abstract

Identity-Preserving Image Generation

Explore similar work

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas

IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation