MreNet: A Vision Transformer Network for Estimating Room Layouts from a Single RGB Panorama

MreNet: A Vision Transformer Network for Estimating Room Layouts from a Single RGB Panorama

The major problem with 3D room layout reconstruction is estimating the 3D room layout from a single panoramic image. In practice, the boundaries between indoor objects are difficult to define, for example, the boundary position of a sofa and a table, and the boundary position of a picture frame and...

Full description

Bibliographic Details
Main Authors: Bing Xu, Yaohui Sun, Xiangxu Meng, Zhihan Liu, Wei Li
Format: Article
Language:English
Published: MDPI AG 2022-09-01
Series:Applied Sciences
Subjects:
three-dimensional reconstruction
deep learning
panoramic
room layout
Online Access:https://www.mdpi.com/2076-3417/12/19/9696

Internet

https://www.mdpi.com/2076-3417/12/19/9696

Similar Items