Efficient 3D Room Shape Recovery from a Single Panorama

Hao Yang and Hui Zhang
Computer Vision and Pattern Recognition 2016 (Full Oral)


We propose a method to recover the shape of a 3D room from a full-view indoor panorama. Our algorithm can automatically infer a 3D shape from a collection of partially oriented superpixel facets and line segments. The core part of the algorithm is a constraint graph, which includes lines and superpixels as vertices, and encodes their geometric relations as edges. A novel approach is proposed to perform 3D reconstruction based on the constraint graph by solving all the geometric constraints as constrained linear least-squares. The selected constraints used for reconstruction are identified using an occlusion detection method with a Markov random field. Experiments show that our method can recover room shapes that can not be addressed by previous approaches. Our method is also efficient, that is, the inference time for each panorama is less than one minute.


paper (2.4MB) download
technical details (626KB) download
video of results (38.4MB) download
poster (2.6MB) download
panoramas without annotation (178.5MB) download
panoramas with annotation link
source code link
depths distributions link