SceneComposer: Any-Level Semantic Image Synthesis

Paper | Project Page

Examples of image synthesis from any-level semantic layouts. (a) The coarsest layout, i.e. at the 0-th precision level, is equivalent to a text input; (d) the finest layout, i.e. at the highest level, is close to an accurate segmentation map; (a)-(d) intermediate level layouts (from coarse to fine), the shape control becomes tighter with increasing levels. (e) We can specify different precision levels for different components, e.g. to include a 0-th level style indicator while the remaining regions are of higher levels.

Interactive demo

Please fill out this agreement form to request access. We will send your unique link to access the demo

Code

This is my internship project at Adobe. I am still waiting for the approval from Adobe for code release. Please contact the Adobe affiliated authors for more details regarding code release. Meanwhile, I will be glad to assist if you are interested in implementing the method.