paper-with-me

홈 › Papers

OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation

2025-12-09 · Yexin Liu, Manyuan Zhang, Yueze Wang, Hongyu Li, Dian Zheng, Weiming Zhang, Changsheng Lu, Xunliang Cai, Yan Feng, Peng Pei, Harry Yang arxiv

Despite the promising progress in subject-driven image generation, current models often deviate from the reference identities and struggle in complex scenes with multiple subjects. To address this challenge, we introduce OpenSubject, a video-derived large-scale corpus with 2.5M samples and 4.35M images for subject-driven generation and manipulation. The dataset is built with a four-stage pipeline that exploits cross-frame identity priors. (i) Video Curation. We apply resolution and aesthetic filtering to obtain high-quality clips. (ii) Cross-Frame Subject Mining and Pairing. We utilize vision-language model (VLM)-based category consensus, local grounding, and diversity-aware pairing to select image pairs. (iii) Identity-Preserving Reference Image Synthesis. We introduce segmentation map-guided outpainting to synthesize the input images for subject-driven generation and box-guided inpainting to generate input images for subject-driven manipulation, together with geometry-aware augmentations and irregular boundary erosion. (iv) Verification and Captioning. We utilize a VLM to validate synthesized samples, re-synthesize failed samples based on stage (iii), and then construct short and long captions. In addition, we introduce a benchmark covering subject-driven generation and manipulation, and then evaluate identity fidelity, prompt adherence, manipulation consistency, and background consistency with a VLM judge. Extensive experiments show that training with OpenSubject improves generation and manipulation performance, particularly in complex scenes.

📄 PDF Abstract BibTeX arXiv:2512.08294

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

2025-03-16 · Hengjia Li, Lifan Jiang, Xi Xiao, Tianyang Wang 외

Video identity customization seeks to produce high-fidelity videos that maintain consistent identity and exhibit significant dynamics based on users' reference images. However, existing approaches face two key challenges…

Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement

2025-09-01 · Jiayi Gao, Changcheng Hua, Qingchao Chen, Yuxin Peng 외 arxiv

Identity-preserving text-to-video (IPT2V) generation creates videos faithful to both a reference subject image and a text prompt. While fine-tuning large pretrained video diffusion models on ID-matched data achieves stat…

Text-to-Video GenerationImage Enhancement

STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits

2025-12-15 · Foivos Paraperas Papantoniou, Stathis Galanakis, Rolandos Alexandros Potamias, Bernhard Kainz 외 arxiv

This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and free-viewpoint talking portrait synthesis, given an identity embedding or r…

Lip Reading

DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation

2026-06-22 · Qian Wang, Zhenyu Li, Abdelrahman Eldesokey, Peter Wonka arxiv

Subject-driven image generation faces an "Identity-Diversity Paradox", where strong identity preservation often leads to rigid and low-diversity outputs. We propose a post-training framework called DivRL that jointly opt…

Image Generation

MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model

2023-08-31 · Jin Liu, Xi Wang, Xiaomeng Fu, Yesheng Chai 외

Face-to-face communication is a common scenario including roles of speakers and listeners. Most existing research methods focus on producing speaker videos, while the generation of listener heads remains largely overlook…

DenoisingDiversity