# Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

## TL;DR

This paper introduces a novel approach for 3D room layout estimation that avoids traditional assumptions by directly detecting and regressing 3D planes, enabling accurate modeling of rooms with arbitrary wall orientations.

## Contribution

It reformulates room layout estimation as an instance detection problem and employs a probabilistic clustering method to integrate multiple frames into a unified 3D layout.

## Key findings

- Effective handling of non-Manhattan room layouts
- Direct regression of 3D planes improves accuracy
- Method works with arbitrary wall orientations

## Abstract

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.