Paint by Example: Exemplar-based Image Editing with Diffusion Models
This work addresses the need for more precise image editing tools for users in creative fields, representing a novel approach rather than an incremental improvement.
The paper tackles the problem of exemplar-guided image editing for precise control by leveraging self-supervised training and diffusion models, achieving high fidelity and controllable editing on in-the-wild images without iterative optimization.
Language-guided image editing has achieved great success recently. In this paper, for the first time, we investigate exemplar-guided image editing for more precise control. We achieve this goal by leveraging self-supervised training to disentangle and re-organize the source image and the exemplar. However, the naive approach will cause obvious fusing artifacts. We carefully analyze it and propose an information bottleneck and strong augmentations to avoid the trivial solution of directly copying and pasting the exemplar image. Meanwhile, to ensure the controllability of the editing process, we design an arbitrary shape mask for the exemplar image and leverage the classifier-free guidance to increase the similarity to the exemplar image. The whole framework involves a single forward of the diffusion model without any iterative optimization. We demonstrate that our method achieves an impressive performance and enables controllable editing on in-the-wild images with high fidelity.