Cover Image

PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Shulei, Wei, Longhui, He, Xin, Ouyang, Jianbo, Lu, Hui, Zhao, Zhou, Tian, Qi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
by: He, Xin, et al.
Published: (2025)

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention
by: He, Huiguo, et al.
Published: (2024)

AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation
by: Cheng, Junhao, et al.
Published: (2024)

Multi-Subject Personalization
by: Jain, Arushi, et al.
Published: (2024)

AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas
by: Yuan, Longhui
Published: (2026)

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling
by: Ping, Bowen, et al.
Published: (2025)

Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation
by: Zhou, Yufan, et al.
Published: (2024)

MV-S2V: Multi-View Subject-Consistent Video Generation
by: Song, Ziyang, et al.
Published: (2026)

CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation
by: Gao, Zhanxin, et al.
Published: (2025)

Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models
by: He, Xin, et al.
Published: (2024)

AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation
by: He, Junjie, et al.
Published: (2025)

Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset
by: Chen, Zhuowei, et al.
Published: (2025)

USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
by: Wu, Shaojin, et al.
Published: (2025)

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
by: Jang, Sangwon, et al.
Published: (2024)

SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control
by: Huang, Binyuan, et al.
Published: (2024)

MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation
by: Ling, Run, et al.
Published: (2025)

Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction
by: Webber, George, et al.
Published: (2024)

Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning
by: Ma, Jian, et al.
Published: (2023)

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
by: Wei, Tianyi, et al.
Published: (2024)

Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance
by: Chan, Kelvin C. K., et al.
Published: (2024)

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing
by: Guo, Zinan, et al.
Published: (2025)

MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
by: She, Dong, et al.
Published: (2025)

RetriBooru: Leakage-Free Retrieval of Conditions from Reference Images for Subject-Driven Generation
by: Tang, Haoran, et al.
Published: (2023)

OVMR: Open-Vocabulary Recognition with Multi-Modal References
by: Ma, Zehong, et al.
Published: (2024)

OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
by: Liu, Yexin, et al.
Published: (2025)

Efficient Multi-modal Long Context Learning for Training-free Adaptation
by: Ma, Zehong, et al.
Published: (2025)

ComFusion: Personalized Subject Generation in Multiple Specific Scenes From Single Image
by: Hong, Yan, et al.
Published: (2024)

UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
by: Cheng, Yufeng, et al.
Published: (2025)

MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation
by: Tian, Wenqing, et al.
Published: (2026)

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
by: Chen, Bowen, et al.
Published: (2025)

High-fidelity Person-centric Subject-to-Image Synthesis
by: Wang, Yibin, et al.
Published: (2023)

FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
by: Jin, Qiaoqiao, et al.
Published: (2025)

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
by: Ma, Zehong, et al.
Published: (2025)

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
by: Chen, Hong, et al.
Published: (2023)

Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts
by: He, Xin, et al.
Published: (2025)

Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation
by: Xu, Yijia, et al.
Published: (2026)

Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt
by: Li, Shangxun, et al.
Published: (2025)

When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization
by: Chen, Zhihan, et al.
Published: (2026)

Textual Localization: Decomposing Multi-concept Images for Subject-Driven Text-to-Image Generation
by: Shentu, Junjie, et al.
Published: (2024)

FlowFixer: Towards Detail-Preserving Subject-Driven Generation
by: Jun, Jinyoung, et al.
Published: (2026)