MureObjectStitch: Multi-reference Image Composition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909564486549504 |
|---|---|
| author | Chen, Jiaxuan Zhang, Bo He, Qingdong Peng, Jinlong Niu, Li |
| author_facet | Chen, Jiaxuan Zhang, Bo He, Qingdong Peng, Jinlong Niu, Li |
| contents | Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. The existing methods are struggling to preserve the foreground details and adjust the foreground pose/viewpoint at the same time. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which allows the model to take in multiple reference images of the foreground object. The experiments on MureCOM dataset verify the effectiveness of our method. The code and model have been released at https://github.com/bcmi/MureObjectStitch-Image-Composition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07462 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MureObjectStitch: Multi-reference Image Composition Chen, Jiaxuan Zhang, Bo He, Qingdong Peng, Jinlong Niu, Li Computer Vision and Pattern Recognition Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. The existing methods are struggling to preserve the foreground details and adjust the foreground pose/viewpoint at the same time. In this work, we propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object. Moreover, we propose a multi-reference strategy, which allows the model to take in multiple reference images of the foreground object. The experiments on MureCOM dataset verify the effectiveness of our method. The code and model have been released at https://github.com/bcmi/MureObjectStitch-Image-Composition. |
| title | MureObjectStitch: Multi-reference Image Composition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.07462 |