3D Room Layout Recovery Generalizing Across Manhattan and Non-Manhattan Worlds

Haijing Jia, Hong Yi, Hirochika Fujiki, Hengzhi Zhang, Wei Wang, Makoto Odamaki; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 5192-5201

Abstract

Recent 3D room layout recovery approaches mostly concentrate on Manhattan layouts, where the vertical walls are orthogonal with respect to each other, even though there are many rooms with non-Manhattan layouts in the real world. This paper presents a room layout recovery method generalizing across Manhattan and non-Manhattan worlds. Without introducing additional supervision, we extend current Manhattan layout recovery methods by predicting an extra surface normal feature, which is further used for an adaptive post-processing to reconstruct layouts of arbitrary shapes. Experimental results show that our method has a great improvement on non-Manhattan layouts while being capable of generalizing across Manhattan and non-Manhattan layouts.

Related Material

[pdf]
[bibtex]
@InProceedings{Jia_2022_CVPR, author = {Jia, Haijing and Yi, Hong and Fujiki, Hirochika and Zhang, Hengzhi and Wang, Wei and Odamaki, Makoto}, title = {3D Room Layout Recovery Generalizing Across Manhattan and Non-Manhattan Worlds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {5192-5201} }