Summary of Furniscene: a Large-scale 3d Room Dataset with Intricate Furnishing Scenes, by Genghao Zhang et al.
FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes
by Genghao Zhang, Yuxi Wang, Chuanchen Luo, Shibiao Xu, Zhaoxiang Zhang, Man Zhang, Junran Peng
First submitted to arxiv on: 7 Jan 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 The proposed FurniScene dataset is a significant advancement in indoor scene generation, enabling the creation of diverse and realistic room layouts for applications such as gaming, virtual reality, and interior design. The dataset comprises 11,698 rooms and 39,691 unique furniture CAD models, covering various types and sizes of objects, from large beds to small teacups. To generate high-quality indoor scenes, a novel Two-Stage Diffusion Scene Model (TSDSM) is introduced, which outperforms existing methods in terms of realism. The FurniScene dataset and code will be publicly available soon. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re building a virtual world where characters can live, play, or relax. To make it look real, you need to create believable indoor scenes. Currently, these scenes lack diversity and realism. That’s why researchers created the FurniScene dataset, which has many different rooms and objects, like furniture, decorations, and even tiny things like cups. They also developed a special model that can generate these scenes, making them look super realistic. This will help people in fields like gaming, virtual reality, and interior design. |
Keywords
* Artificial intelligence * Diffusion
