CareCom: Generative Image Composition with Calibrated Reference Features
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911265810546688 |
|---|---|
| author | Chen, Jiaxuan Zhang, Bo He, Qingdong Peng, Jinlong Niu, Li |
| author_facet | Chen, Jiaxuan Zhang, Bo He, Qingdong Peng, Jinlong Niu, Li |
| contents | Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11060 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CareCom: Generative Image Composition with Calibrated Reference Features Chen, Jiaxuan Zhang, Bo He, Qingdong Peng, Jinlong Niu, Li Computer Vision and Pattern Recognition Image composition aims to seamlessly insert foreground object into background. Despite the huge progress in generative image composition, the existing methods are still struggling with simultaneous detail preservation and foreground pose/view adjustment. To address this issue, we extend the existing generative composition model to multi-reference version, which allows using arbitrary number of foreground reference images. Furthermore, we propose to calibrate the global and local features of foreground reference images to make them compatible with the background information. The calibrated reference features can supplement the original reference features with useful global and local information of proper pose/view. Extensive experiments on MVImgNet and MureCom demonstrate that the generative model can greatly benefit from the calibrated reference features. |
| title | CareCom: Generative Image Composition with Calibrated Reference Features |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.11060 |