IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

arXiv:2403.10701v1 Announce Type: new
Abstract: 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 …

abstract arxiv challenge cs.cv diffusion editing generative however identity image novel object paper practical preservation representation stage type usage