Floorplan-Aware Camera Poses Refinement

TL;DR

This paper introduces a novel optimization algorithm that incorporates floorplan information into camera pose refinement, significantly improving the accuracy of indoor 3D reconstructions for applications like navigation.

Contribution

It presents a new method that integrates floorplan data into bundle adjustment, enhancing indoor scene reconstruction accuracy beyond traditional approaches.

Findings

Floorplan-aware optimization improves reconstruction accuracy.

Utilizing structural prior reduces pose estimation errors.

Method outperforms standard BA on Redwood and custom datasets.

Abstract

Processing large indoor scenes is a challenging task, as scan registration and camera trajectory estimation methods accumulate errors across time. As a result, the quality of reconstructed scans is insufficient for some applications, such as visual-based localization and navigation, where the correct position of walls is crucial. For many indoor scenes, there exists an image of a technical floorplan that contains information about the geometry and main structural elements of the scene, such as walls, partitions, and doors. We argue that such a floorplan is a useful source of spatial information, which can guide a 3D model optimization. The standard RGB-D 3D reconstruction pipeline consists of a tracking module applied to an RGB-D sequence and a bundle adjustment (BA) module that takes the posed RGB-D sequence and corrects the camera poses to improve consistency. We propose a novel optimization algorithm expanding conventional BA that leverages the prior knowledge about the scene structure in the form of a floorplan. Our experiments on the Redwood dataset and our self-captured data demonstrate that utilizing floorplan improves accuracy of 3D reconstructions.