Summary of Scenex: Procedural Controllable Large-scale Scene Generation, by Mengqi Zhou and Yuxi Wang and Jun Hou and Shougao Zhang and Yiwei Li and Chuanchen Luo and Junran Peng and Zhaoxiang Zhang
SceneX: Procedural Controllable Large-scale Scene Generation
by Mengqi Zhou, Yuxi Wang, Jun Hou, Shougao Zhang, Yiwei Li, Chuanchen Luo, Junran Peng, Zhaoxiang Zhang
First submitted to arxiv on: 23 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel framework for procedural content generation (PCG) is introduced to create high-quality 3D assets from textual descriptions. The SceneX approach consists of two components: PCGHub, which collects procedural assets and API documents, and PCGPlanner, which generates executable actions for Blender to produce controllable 3D assets. This method enables designers to specify their desired scenes and edit them using commands like asset placement and season translation. Extensive experiments demonstrate SceneX’s capabilities in generating large-scale scenes, including nature scenes and unbounded cities. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is found to create realistic 3D environments from written descriptions. The SceneX system lets designers make detailed scenes by giving simple instructions. It can even edit the scene later, like adding or moving objects. This helps people who want to create big, complex worlds without needing to draw every single detail. |
Keywords
* Artificial intelligence * Translation
