Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation
2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV)(2019)
摘要
We propose a novel method to efficiently estimate the spatial layout of a room from a single monocular RGB image. As existing approaches based on low-level feature extraction, followed by a vanishing point estimation are very slow and often unreliable in realistic scenarios, we build on semantic segmentation of the input image. To obtain better segmentations, we introduce a robust, accurate and very efficient hypothesize-and-test scheme. The key idea is to use three segmentation hypotheses, each based on a different number of visible walls. For each hypothesis, we predict the image locations of the room corners and select the hypothesis for which the layout estimated from the room corners is consistent with the segmentation. We demonstrate the efficiency and robustness of our method on three challenging benchmark datasets, where we significantly outperform the state-of-the-art.
更多查看译文
关键词
hypothesize-and-test scheme,room corners,image locations,visible walls,segmentation hypotheses,semantic segmentation,single monocular RGB image,room layout estimation,spatial layout estimation,smart hypothesis generation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络