Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods
This work addresses the challenge of method comparison in 3D layout reconstruction for researchers and practitioners, but it is incremental as it focuses on analysis and benchmarking rather than proposing a new method.
The paper tackles the problem of comparing state-of-the-art methods for Manhattan room layout reconstruction from single 360-degree images by summarizing a common framework and design variants, and it introduces extended annotations for the Matterport3D dataset and two depth-based evaluation metrics to facilitate comprehensive evaluation.
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 [3], and introduce two depth-based evaluation metrics.