vix.ing · top · new · best · stats

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

2021/08/02 by Chenlin Meng, Meng, Chenlin, Yutong He +11 · 1 voice · 407 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Algorithm #Applied mathematics #Artificial intelligence #Cell Image Analysis Techniques #Compositing #Computer Graphics and Visualization Techniques #Computer science #Computer vision #Generative Adversarial Networks and Image Synthesis #Image (mathematics) #Image editing #Mathematical optimization #Mathematics #Noise reduction #Realism #Stochastic differential equation #Theoretical computer science #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.2108.01073

published in arXiv (Cornell University) (Cornell University) · https://sde-image-editing.github.io/

openalex publication_date 2021/08/02 · arxiv created 2022/01/05 · arxiv updated 2022/01/06 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

Guided image synthesis enables everyday users to create and edit photo-realistic images with minimum effort. The key challenge is balancing faithfulness to the user input (e.g., hand-drawn colored strokes) and realism of the synthesized image. Existing GAN-based methods attempt to achieve such balance using either conditional GANs or GAN inversions, which are challenging and often require additional training data or loss functions for individual applications. To address these issues, we introduce a new image synthesis and editing method, Stochastic Differential Editing (SDEdit), based on a diffusion model generative prior, which synthesizes realistic images by iteratively denoising through a stochastic differential equation (SDE). Given an input image with user guide of any type, SDEdit first adds noise to the input, then subsequently denoises the resulting image through the SDE prior to increase its realism. SDEdit does not require task-specific training or inversions and can naturally achieve the balance between realism and faithfulness. SDEdit significantly outperforms state-of-the-art GAN-based methods by up to 98.09% on realism and 91.72% on overall satisfaction scores, according to a human perception study, on multiple tasks, including stroke-based image synthesis and editing as well as image compositing.

Cited by

Discussions

Related