Editable Image Elements for Controllable Synthesis
This addresses the problem of controllable image synthesis for users needing precise spatial edits, though it is incremental as it builds on existing diffusion model frameworks.
The paper tackles the challenge of editing user-provided images with diffusion models by proposing an 'image elements' representation that enables intuitive spatial editing, and demonstrates effectiveness in tasks like object resizing and rearrangement.
Diffusion models have made significant advances in text-guided synthesis tasks. However, editing user-provided images remains challenging, as the high dimensional noise input space of diffusion models is not naturally suited for image inversion or spatial editing. In this work, we propose an image representation that promotes spatial editing of input images using a diffusion model. Concretely, we learn to encode an input into "image elements" that can faithfully reconstruct an input image. These elements can be intuitively edited by a user, and are decoded by a diffusion model into realistic images. We show the effectiveness of our representation on various image editing tasks, such as object resizing, rearrangement, dragging, de-occlusion, removal, variation, and image composition. Project page: https://jitengmu.github.io/Editable_Image_Elements/