Imagen de Portada

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Kewen, Hu, Xiaobin, Ren, Wenqi
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
por: Wang, Yuji, et al.
Publicado: (2025)

Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
por: Chen, Yuheng, et al.
Publicado: (2026)

EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion
por: Wei, Jiangchuan, et al.
Publicado: (2025)

Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization
por: Shen, Liao, et al.
Publicado: (2025)

Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses
por: Wang, Yuji, et al.
Publicado: (2025)

3D Priors-Guided Diffusion for Blind Face Restoration
por: Lu, Xiaobin, et al.
Publicado: (2024)

Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement
por: Gao, Jiayi, et al.
Publicado: (2025)

FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction
por: Guo, Wenqi, et al.
Publicado: (2026)

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

Fusion is all you need: Face Fusion for Customized Identity-Preserving Image Synthesis
por: Mohamed, Salaheldin, et al.
Publicado: (2024)

CD-DPE: Dual-Prompt Expert Network Based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution
por: Gu, Xianming, et al.
Publicado: (2025)

Identity-Preserving Text-to-Video Generation by Frequency Decomposition
por: Yuan, Shenghai, et al.
Publicado: (2024)

Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning
por: Chen, Xingchi, et al.
Publicado: (2024)

MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention
por: Xie, Qi, et al.
Publicado: (2025)

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

ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning
por: Chen, Weifeng, et al.
Publicado: (2024)

Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation
por: Chau, Lydia Kin Ching, et al.
Publicado: (2025)

Facial Demorphing via Identity Preserving Image Decomposition
por: Shukla, Nitish, et al.
Publicado: (2024)

IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation
por: Zhou, Donghao, et al.
Publicado: (2025)

Resolving the Identity Crisis in Text-to-Image Generation
por: Borse, Shubhankar, et al.
Publicado: (2025)

Hierarchical Fusion of Local and Global Visual Features with Mixture-of-Experts for Remote Sensing Image Scene Classification
por: Tang, Yuanhao, et al.
Publicado: (2025)

Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space
por: Liang, Yingping, et al.
Publicado: (2025)

FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
por: Wang, Yuanzhi, et al.
Publicado: (2026)

Identity-Preserving Pose-Guided Character Animation via Facial Landmarks Transformation
por: Mu, Lianrui, et al.
Publicado: (2024)

W-DUALMINE: Reliability-Weighted Dual-Expert Fusion With Residual Correlation Preservation for Medical Image Fusion
por: Islam, Md. Jahidul
Publicado: (2026)

Multi-Sequence Parotid Gland Lesion Segmentation via Expert Text-Guided Segment Anything Model
por: Wu, Zhongyuan, et al.
Publicado: (2025)

ST-DETrack: Identity-Preserving Branch Tracking in Entangled Plant Canopies via Dual Spatiotemporal Evidence
por: Chen, Yueqianji, et al.
Publicado: (2025)

GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
por: Chen, Yuqing, et al.
Publicado: (2026)

Training-Free Diffusion Framework for Stylized Image Generation with Identity Preservation
por: Rezaei, Mohammad Ali, et al.
Publicado: (2025)

FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
por: Yao, Zebin, et al.
Publicado: (2025)

Inject Where It Matters: Training-Free Spatially-Adaptive Identity Preservation for Text-to-Image Personalization
por: Li, Guandong, et al.
Publicado: (2026)

Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization
por: Wu, Hongtao, et al.
Publicado: (2024)

SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
por: Chen, Yamei, et al.
Publicado: (2023)

Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration
por: Han, Wenkang, et al.
Publicado: (2025)

Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
por: Wu, Xiaodong, et al.
Publicado: (2026)

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion
por: Liu, Yidi, et al.
Publicado: (2025)

Identity-aware Feature Decoupling Learning for Clothing-change Person Re-identification
por: Xu, Haoxuan, et al.
Publicado: (2025)

Reference-Guided Identity Preserving Face Restoration
por: Zhou, Mo, et al.
Publicado: (2025)

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
por: Zhang, Aiping, et al.
Publicado: (2024)

MAUGIF: Mechanism-Aware Unsupervised General Image Fusion via Dual Cross-Image Autoencoders
por: Yang, Kunjing, et al.
Publicado: (2025)