Name
Abstract | ||
|---|---|---|
3D layout is crucial for scene understanding and reconstruction, and very useful in applications like real estate and furniture design. In this paper, we propose a fully automatic solution to estimate 3D layout of an indoor scene from a single 2D image. Our technique contains two key components. Firstly, we train a neural network that directly estimates room structure lines from the input image. Secondly, we propose a novel technique to automatically identify the layout topology of an input image, followed by a nonlinear optimization with equality constraints to estimate the final 3D layout of a scene. Based on our knowledge, this is the first fully automatic technique to achieve single image-based 3D layout estimation of an indoor scene. We evaluate our method on the public datasets LSUN, Hedau and 3DGP and the results show that the proposed method achieves accurate 3D layout reconstruction on various images with different layout topologies. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/TMM.2020.2967645 | IEEE Transactions on Multimedia |
Keywords | DocType | Volume |
Indoor scene,2D topology,3D topology,convolutional neural networks,nonlinear optimization | Journal | 22 |
Issue | ISSN | Citations |
11 | 1520-9210 | 13 |
PageRank | References | Authors |
0.64 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chenggang Yan | 1 | 410 | 32.87 |
| Biyao Shao | 2 | 13 | 0.64 |
| Hao Zhao | 3 | 46 | 5.33 |
| Ruixin Ning | 4 | 13 | 0.64 |
| Yongdong Zhang | 5 | 2544 | 166.91 |
| Feng Xu | 6 | 194 | 23.14 |