3D Room Layout Estimation Beyond the Manhattan World Assumption
This addresses the challenge of 3D room layout estimation for applications in computer vision, but it is incremental as it builds on an existing model.
The paper tackles the problem of 3D room layout estimation from a single image by proposing a new training and post-processing method, which outperforms state-of-the-art approaches by a large margin in predicting visible room layout and achieved 3rd place in a 2020 workshop.
Predicting 3D room layout from single image is a challenging task with many applications. In this paper, we propose a new training and post-processing method for 3D room layout estimation, built on a recent state-of-the-art 3D room layout estimation model. Experimental results show our method outperforms state-of-the-art approaches by a large margin in predicting visible room layout. Our method has obtained the 3rd place in 2020 Holistic Scene Structures for 3D Vision Workshop.