BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910049024081920 |
|---|---|
| author | Zhu, Zihao Wang, Ruotong Lyu, Siwei Zhang, Min Wu, Baoyuan |
| author_facet | Zhu, Zihao Wang, Ruotong Lyu, Siwei Zhang, Min Wu, Baoyuan |
| contents | The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time, the task of seamless brand integration in T2V: automatically embedding advertiser brands into prompt-generated videos while preserving semantic fidelity to user intent. This task confronts three core challenges: maintaining prompt fidelity, ensuring brand recognizability, and achieving contextually natural integration. To address them, we propose BrandFusion, a novel multi-agent framework comprising two synergistic phases. In the offline phase (advertiser-facing), we construct a Brand Knowledge Base by probing model priors and adapting to novel brands via lightweight fine-tuning. In the online phase (user-facing), five agents jointly refine user prompts through iterative refinement, leveraging the shared knowledge base and real-time contextual tracking to ensure brand visibility and semantic alignment. Experiments on 18 established and 2 custom brands across multiple state-of-the-art T2V models demonstrate that BrandFusion significantly outperforms baselines in semantic preservation, brand recognizability, and integration naturalness. Human evaluations further confirm higher user satisfaction, establishing a practical pathway for sustainable T2V monetization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02816 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation Zhu, Zihao Wang, Ruotong Lyu, Siwei Zhang, Min Wu, Baoyuan Computer Vision and Pattern Recognition Artificial Intelligence The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time, the task of seamless brand integration in T2V: automatically embedding advertiser brands into prompt-generated videos while preserving semantic fidelity to user intent. This task confronts three core challenges: maintaining prompt fidelity, ensuring brand recognizability, and achieving contextually natural integration. To address them, we propose BrandFusion, a novel multi-agent framework comprising two synergistic phases. In the offline phase (advertiser-facing), we construct a Brand Knowledge Base by probing model priors and adapting to novel brands via lightweight fine-tuning. In the online phase (user-facing), five agents jointly refine user prompts through iterative refinement, leveraging the shared knowledge base and real-time contextual tracking to ensure brand visibility and semantic alignment. Experiments on 18 established and 2 custom brands across multiple state-of-the-art T2V models demonstrate that BrandFusion significantly outperforms baselines in semantic preservation, brand recognizability, and integration naturalness. Human evaluations further confirm higher user satisfaction, establishing a practical pathway for sustainable T2V monetization. |
| title | BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.02816 |