Pano2CAD: Room Layout From A Single Panorama Image

TL;DR

This paper introduces a method to estimate room geometry and object poses from a single panorama image using Bayesian inference, surface normals, and object detection, validated on synthetic and real datasets.

Contribution

It presents a novel approach combining surface normal estimation and object detection within a Bayesian framework for single-image room layout estimation.

Findings

Accurate room geometry estimation from a single panorama.

Effective object pose estimation in 3D from 2D detections.

Validated results on synthetic and real datasets.

Abstract

This paper presents a method of estimating the geometry of a room and the 3D pose of objects from a single 360-degree panorama image. Assuming Manhattan World geometry, we formulate the task as a Bayesian inference problem in which we estimate positions and orientations of walls and objects. The method combines surface normal estimation, 2D object detection and 3D object pose estimation. Quantitative results are presented on a dataset of synthetically generated 3D rooms containing objects, as well as on a subset of hand-labeled images from the public SUN360 dataset.