Supplementary Material: Piecewise Planar and Compact Floorplan Reconstruction from Images
نویسندگان
چکیده
From 3D points We first detect 3D points that are on the floor, ceiling or walls, based on their positions and normals. A 3D point is detected to be on the floor if the point is at the floor height and its normal is along the up direction, allowing an error of 0.3m and 15 degrees, respectively. Points on the ceiling are detected in the same way. A 3D point belongs to a wall if its height is between the floor and the ceiling, and the point normal is near horizontal, allowing an error of 15 degrees. Detected 3D points are projected onto visible panoramas. A superpixel is assigned a structure label if the number of projected points with the label is at least 5 and more than the numbers for the other labels.
منابع مشابه
Planelet Transform: A New Geometrical Wavelet for Compression of Kinect-like Depth Images
With the advent of cheap indoor RGB-D sensors, proper representation of piecewise planar depth images is crucial toward an effective compression method. Although there exist geometrical wavelets for optimal representation of piecewise constant and piecewise linear images (i.e. wedgelets and platelets), an adaptation to piecewise linear fractional functions which correspond to depth variation ov...
متن کاملA New Approach for Quantitative Evaluation of Reconstruction Algorithms in SPECT
ABTRACT Background: In nuclear medicine, phantoms are mainly used to evaluate the overall performance of the imaging systems and practically there is no phantom exclusively designed for the evaluation of the software performance. In this study the Hoffman brain phantom was used for quantitative evaluation of reconstruction techniques. The phantom is modified to acquire t...
متن کاملMesh Optimisation for Image-Based Surface Reconstruction
A number of quite successful SFM solutions proposed focus on producing a sparse or dense set of features of the scene such as 3D points or line segments. While these representations are sometimes adequate, for many applications a more compact model is required usually in the form of solid objects or surfaces. Triangular meshes are an appealing representation because of their simplicity and the ...
متن کامل3D Reconstruction of Piecewise Planar Models from Multiple Views Utilizing Coplanar and Region Constraints
An automatic 3D reconstruction method based upon coplanar and region constraints is proposed for synthesizing piecewise 3D planar models of a real-world scene portrayed in a sequence of digital images. Significantly, the reconstruction process requires no prior knowledge about the scene and the camera parameters. The proposed modelling method comprises three steps. Firstly, the corresponding fe...
متن کاملGeneralized Use of Homographies for Piecewise Planar Reconstruction
We present a method for piecewise planar modeling from oriented images. The method uses a set of homologous image points and the underlying 3D geometry to determine image regions which satisfy plane-induced homographies. It robustly detects and reconstructs planes of arbitrary position and orientation in the scene and takes advantage of the regular raster structure of the images to delineate th...
متن کامل