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.
@article{arxiv.2411.07462,
title = {MureObjectStitch: Multi-reference Image Composition},
author = {Jiaxuan Chen and Bo Zhang and Qingdong He and Jinlong Peng and Li Niu},
journal= {arXiv preprint arXiv:2411.07462},
year = {2025}
}