You Only Erase Once: Erasing Anything without Bringing Unexpected Content
For image editing and inpainting tasks, YOEO provides a more reliable object erasure solution that avoids unexpected content generation, addressing a key limitation of existing diffusion-based methods.
YOEO introduces an object erasure method that removes target objects from images without generating unwanted artifacts or content, outperforming state-of-the-art methods. It achieves this by training a diffusion model on unpaired real-world images using a sundries detector and context coherence loss, with a distillation strategy for efficiency.
We present YOEO, an approach for object erasure. Unlike recent diffusion-based methods which struggle to erase target objects without generating unexpected content within the masked regions due to lack of sufficient paired training data and explicit constraint on content generation, our method allows to produce high-quality object erasure results free of unwanted objects or artifacts while faithfully preserving the overall context coherence to the surrounding content. We achieve this goal by training an object erasure diffusion model on unpaired data containing only large-scale real-world images, under the supervision of a sundries detector and a context coherence loss that are built upon an entity segmentation model. To enable more efficient training and inference, a diffusion distillation strategy is employed to train for a few-step erasure diffusion model. Extensive experiments show that our method outperforms the state-of-the-art object erasure methods. Code will be available at https://zyxunh.github.io/YOEO-ProjectPage/.