Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts
This work addresses the limitation of existing methods for 3D room layout estimation that rely on restrictive geometric assumptions, offering a more flexible solution for computer vision applications.
The authors tackled the problem of 3D room layout estimation by developing a method that avoids box approximations and Manhattan world assumptions, resulting in effective handling of walls in any alignment.
We propose a method for room layout estimation that does not rely on the typical box approximation or Manhattan world assumption. Instead, we reformulate the geometry inference problem as an instance detection task, which we solve by directly regressing 3D planes using an R-CNN. We then use a variant of probabilistic clustering to combine the 3D planes regressed at each frame in a video sequence, with their respective camera poses, into a single global 3D room layout estimate. Finally, we showcase results which make no assumptions about perpendicular alignment, so can deal effectively with walls in any alignment.