U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation
Abstract
While the existing deep learning-based room layout estimation techniques demonstrate good overall accuracy, they are less effective for distant floor-wall boundary. To tackle this problem, we propose a novel uncertainty-guided approach for layout boundary estimation introducing new two-stage CNN architecture termed U2RLE. The initial stage predicts both floor-wall boundary and its uncertainty and is followed by the refinement of boundaries with high positional uncertainty using a different, distance-aware loss. Finally, outputs from the two stages are merged to produce the room layout. Experiments using ZInD and Structure3D datasets show that U2RLE improves over current state-of-the-art, being able to handle both near and far walls better. In particular, U2RLE outperforms current state-of-the-art techniques for the most distant walls.
Cite
@article{arxiv.2304.08580,
title = {U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation},
author = {Pooya Fayyazsanavi and Zhiqiang Wan and Will Hutchcroft and Ivaylo Boyadzhiev and Yuguang Li and Jana Kosecka and Sing Bing Kang},
journal= {arXiv preprint arXiv:2304.08580},
year = {2023}
}
Comments
To be Appear on CVPR 2023