Recent approaches for predicting layouts from 360∘ panoramas produce excellent results. These approaches build on a common framework consisting of three steps: a pre-processing step based on edge-based alignment, prediction of layout elements, and a post-processing step by fitting a 3D layout to the layout elements. Until now, it has been difficult to compare the methods due to multiple different design decisions, such as the encoding network (e.g., SegNet or ResNet), type of elements predicted (e.g., corners, wall/floor boundaries, or semantic segmentation), or method of fitting the 3D layout. To address this challenge, we summarize and describe the common framework, the variants, and the impact of the design decisions. For a complete evaluation, we also propose extended annotations for the Matterport3D dataset (Chang et al.: Matterport3d: learning from rgb-d data in indoor environments. arXiv:1709.06158, 2017), and introduce two depth-based evaluation metrics.
|Original language||English (US)|
|Journal||International Journal of Computer Vision|
|State||Published - Feb 9 2021|
Bibliographical noteKAUST Repository Item: Exported on 2021-02-25
Acknowledgements: This research is supported in part by ONR MURI Grant N00014-16-1-2007, iStaging Corp. fund and the Ministry of Science and Technology of Taiwan (108-2218-E-007-050- and 107-2221-E-007-088-MY3). We thank Shang-Ta Yang for providing the source code of DuLa-Net. We thank Cheng Sun for providing the source code of HorizonNet and help run experiments on our provided dataset.