Skip to main content

Total 3D Understanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image.

Nie, Y., Han, X., Guo, S., Zheng, Y., Chang, J. and Zhang, J. J., 2020. Total 3D Understanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image. In: IEEE Conference on Computer Vision and Pattern Recognition, 16-18 June 2020, Seattle, WA, USA.

Full text available as:

[img]
Preview
PDF (arXiv preprint: 2002.12212v1)
2002.12212.pdf - Published Version

8MB

Official URL: https://www.computer.org/conferences/cfp/CVPR2020

Abstract

Semantic reconstruction of indoor scenes refers to both scene understanding and object reconstruction. Existing works either address one part of this problem or focus on independent objects. In this paper, we bridge the gap between understanding and reconstruction, and propose an end-to-end solution to jointly reconstruct room layout, object bounding boxes and meshes from a single image. Instead of separately resolving scene understanding and object reconstruction, our method builds upon a holistic scene context and proposes a coarse-to-fine hierarchy with three components: 1. room layout with camera pose; 2. 3D object bounding boxes; 3. object meshes. We argue that understanding the context of each component can assist the task of parsing the others, which enables joint understanding and reconstruction. The experiments on the SUN RGBD and Pix3D datasets demonstrate that our method consistently outperforms existing methods in indoor layout estimation, 3D object detection and mesh reconstruction.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Media & Communication
ID Code:33684
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:10 Mar 2020 12:25
Last Modified:07 Jul 2020 15:15

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -