https://github.com/zengxianyu/scenec

SceneComposer: Any-Level Semantic Image Synthesis, CVPR 2023
https://github.com/zengxianyu/scenec

Last synced: 3 months ago
JSON representation

SceneComposer: Any-Level Semantic Image Synthesis, CVPR 2023

• Host: GitHub
• URL: https://github.com/zengxianyu/scenec
• Owner: zengxianyu
• Created: 2022-11-19T17:43:58.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-08T03:28:19.000Z (over 1 year ago)
• Last Synced: 2024-08-01T18:37:38.768Z (11 months ago)
• Homepage:
• Size: 24.3 MB
• Stars: 82
• Watchers: 21
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

        
# SceneComposer: Any-Level Semantic Image Synthesis

[Paper](http://arxiv.org/abs/2211.11742) | [Project Page](https://zengxianyu.github.io/scenec)

![](https://zengxianyu.github.io/scenec/resources/teaser_v1.png)

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](https://forms.microsoft.com/r/Rq2xzdNsnv) 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.