Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both view-invariant and conducive to enhanced detail preservation. The subsequent stage leverages this representation to learn seamless harmonization of the object composited to the background. In addition, IMPRINT incorporates a shape-guidance mechanism offering user-directed control over the compositing process. Extensive experiments demonstrate that IMPRINT significantly outperforms existing methods and various baselines on identity preservation and composition quality.
@article{arxiv.2403.10701,
title = {IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation},
author = {Yizhi Song and Zhifei Zhang and Zhe Lin and Scott Cohen and Brian Price and Jianming Zhang and Soo Ye Kim and He Zhang and Wei Xiong and Daniel Aliaga},
journal= {arXiv preprint arXiv:2403.10701},
year = {2024}
}