Exploiting 2D Floorplan for Building-Scale Panorama RGBD Alignment

  title={Exploiting 2D Floorplan for Building-Scale Panorama RGBD Alignment},
  author={Erik Wijmans and Yasutaka Furukawa},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
This paper presents a novel algorithm that utilizes a 2D floorplan to align panorama RGBD scans. While effective panorama RGBD alignment techniques exist, such a system requires extremely dense RGBD image sampling. Our approach can significantly reduce the number of necessary scans with the aid of a floorplan image. We formulate a novel Markov Random Field inference problem as a scan placement over the floorplan, as opposed to the conventional scan-to-scan alignment. The technical contributions… 

Figures and Tables from this paper

Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans

Without the requirement of feature matching, the proposed method enables some novel applications ranging from large or featureless scene reconstruction and modeling from sparse input, and quantitatively and qualitatively on real and synthetic scenes of various sizes and complexities.

Noise-Resilient Reconstruction of Panoramas and 3D Scenes Using Robot-Mounted Unsynchronized Commodity RGB-D Cameras

This work presents a two-stage approach to first constructing 3D panoramas and then stitching them for noise-resilient reconstruction of large-scale indoor scenes, and proposes novel algorithms to track multiple unsynchronized RGB-D cameras simultaneously.

Floorplan-Aware Camera Poses Refinement

It is argued that a novel optimization algorithm expanding conventional BA that leverages the prior knowledge about the scene structure in the form of a ftoorplan is a useful source of spatial information, which can guide a 3D model optimization.

Floorplan Priors for Joint Camera Pose and Room Layout Estimation

This work exploits the 3D "box" structure of a typical room layout that meets the Manhattan World property to reconstruct large or featureless scenes from a set of partial reconstructions due to camera tracking interruptions when scanning a large orfeatureless scene.

InLoc: Indoor Visual Localization with Dense Matching and View Synthesis

A new large-scale visual localization method targeted for indoor environments that significantly outperforms current state-of-the-art indoor localization approaches on this new challenging data.

InLoc: Indoor Visual Localization with Dense Matching and View Synthesis

A new large-scale visual localization method targeted for indoor spaces that significantly outperforms current state-of-the-art indoor localization approaches on this new challenging data.

RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments

This work proposes a virtual view synthesis-based approach, RenderNet, to enrich the database and apply the needed global and local features of virtual viewpoints and apply them in the subsequent image retrieval and feature matching operations respectively.


Experimental results indicate the efficiency of the proposed 3-step registration method compared to manual registration and the parameters of the 8-parameter affine are estimated using the 2D-to-3D CPs, which are pixel coordinates in BCAD model as well as their correspondences in the 3D PC space.

Multi-stage Floor Plan Recognition and 3D Reconstruction

A deep-learning-based framework mainly consisting of YOLOv5, deep residual network (DRN), and OCR extraction algorithms that outperforms other methods in 2D floor plan recognition and further isometric 3D reconstruction.

Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes

This paper adapts 3RScan - a recently introduced indoor RGB-D dataset designed for object instance re-localization - to create RIO10, a new long-term camera re- localization benchmark focused on indoor scenes and explores how state-of-the-art cameraRe-localizers perform according to these metrics.



Structured Indoor Modeling

A novel 3D modeling framework that reconstructs an indoor scene as a structured model from panorama RGBD images and proposes a new room segmentation algorithm and an offset-map reconstruction algorithm that can enforce architectural shape priors far beyond existing state-of-the-art.

3D Semantic Parsing of Large-Scale Indoor Spaces

This paper argues that identification of structural elements in indoor spaces is essentially a detection problem, rather than segmentation which is commonly used, and proposes a method for semantic parsing the 3D point cloud of an entire building using a hierarchical approach.

Block assembly for global registration of building scans

This work proposes a framework for global registration of building scans and proposes an efficient solution to this optimization problem by iteratively detecting and adding local constraints, based on a linear integer programming formulation.

Real-time 3D reconstruction at scale using voxel hashing

An online system for large and fine scale volumetric reconstruction based on a memory and speed efficient data structure that compresses space, and allows for real-time access and updates of implicit surface data, without the need for a regular or hierarchical grid data structure.

KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera

Novel extensions to the core GPU pipeline demonstrate object segmentation and user interaction directly in front of the sensor, without degrading camera tracking or reconstruction, to enable real-time multi-touch interactions anywhere.

Fast registration of laser scans with 4-point congruent sets - what works and what doesn't

This work examines several variations of the basic K-4PCS framework that have the potential to improve its runtime and robustness and replaces the RANSAC error function with the more principled MSAC function.

Robust reconstruction of indoor scenes

An approach to indoor scene reconstruction from RGB-D video to combine geometric registration of scene fragments with robust global optimization based on line processes that substantially increases the accuracy of reconstructed scene models.

ConstructAide: analyzing and visualizing construction sites through photographs and building models

This work describes a set of tools for analyzing, visualizing, and assessing architectural/construction progress with unordered photo collections and 3D building models and demonstrates that the user-assisted SfM method outperforms existing techniques on both real-world construction data and established multi-view datasets.

Building Rome on a Cloudless Day

This paper introduces an approach for dense 3D reconstruction from unregistered Internet-scale photo collections with about 3 million images within the span of a day on a single PC ("cloudless"), leveraging geometric and appearance constraints to obtain a highly parallel implementation on modern graphics processors and multi-core architectures.