A diffusion model, trained on synthetic pattern quartets generated by the SplitWeave DSL, can apply a program-level edit demonstrated on one pattern pair to a new real-world pattern.
Editable Image Elements for Controllable Synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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/
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Pattern Analogies: Learning to Perform Programmatic Image Edits by Analogy
A diffusion model, trained on synthetic pattern quartets generated by the SplitWeave DSL, can apply a program-level edit demonstrated on one pattern pair to a new real-world pattern.