MagicView: Multi-View Consistent Identity Customization via Priors-Guided In-Context Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914178158034944 |
|---|---|
| author | Li, Hengjia Xu, Jianjin Cheng, Keli Wang, Lei Bi, Ning Wu, Boxi De la Torre, Fernando Cai, Deng |
| author_facet | Li, Hengjia Xu, Jianjin Cheng, Keli Wang, Lei Bi, Ning Wu, Boxi De la Torre, Fernando Cai, Deng |
| contents | Recent advances in personalized generative models have demonstrated impressive capabilities in producing identity-consistent images of the same individual across diverse scenes. However, most existing methods lack explicit viewpoint control and fail to ensure multi-view consistency of generated identities. To address this limitation, we present MagicView, a lightweight adaptation framework that equips existing generative models with multi-view generation capability through 3D priors-guided in-context learning. While prior studies have shown that in-context learning preserves identity consistency across grid samples, its effectiveness in multi-view settings remains unexplored. Building upon this insight, we conduct an in-depth analysis of the multi-view in-context learning ability, and design a conditioning architecture that leverages 3D priors to activate this capability for multi-view consistent identity customization. On the other hand, acquiring robust multi-view capability typically requires large-scale multi-dimensional datasets, which makes incorporating multi-view contextual learning under limited data regimes prone to textual controllability degradation. To address this issue, we introduce a novel Semantic Correspondence Alignment loss, which effectively preserves semantic alignment while maintaining multi-view consistency. Extensive experiments demonstrate that MagicView substantially outperforms recent baselines in multi-view consistency, text alignment, identity similarity, and visual quality, achieving strong results with only 100 multi-view training samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MagicView: Multi-View Consistent Identity Customization via Priors-Guided In-Context Learning Li, Hengjia Xu, Jianjin Cheng, Keli Wang, Lei Bi, Ning Wu, Boxi De la Torre, Fernando Cai, Deng Computer Vision and Pattern Recognition Recent advances in personalized generative models have demonstrated impressive capabilities in producing identity-consistent images of the same individual across diverse scenes. However, most existing methods lack explicit viewpoint control and fail to ensure multi-view consistency of generated identities. To address this limitation, we present MagicView, a lightweight adaptation framework that equips existing generative models with multi-view generation capability through 3D priors-guided in-context learning. While prior studies have shown that in-context learning preserves identity consistency across grid samples, its effectiveness in multi-view settings remains unexplored. Building upon this insight, we conduct an in-depth analysis of the multi-view in-context learning ability, and design a conditioning architecture that leverages 3D priors to activate this capability for multi-view consistent identity customization. On the other hand, acquiring robust multi-view capability typically requires large-scale multi-dimensional datasets, which makes incorporating multi-view contextual learning under limited data regimes prone to textual controllability degradation. To address this issue, we introduce a novel Semantic Correspondence Alignment loss, which effectively preserves semantic alignment while maintaining multi-view consistency. Extensive experiments demonstrate that MagicView substantially outperforms recent baselines in multi-view consistency, text alignment, identity similarity, and visual quality, achieving strong results with only 100 multi-view training samples. |
| title | MagicView: Multi-View Consistent Identity Customization via Priors-Guided In-Context Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.00293 |