Piecewise Planar Reconstruction Research Articles

Single-image piecewise planar reconstruction of urban buildings based on geometric priors

Single-image 3D urban building reconstruction is an important and challenging topic in computer vision. However, it is a highly ill-posed problem due to the intrinsic geometrical ambiguity in a 3D space. To address the problem, this paper presents a novel single-image piecewise planar reconstruction method based on geometric priors. The proposed method utilizes geometric priors (e.g., plane orientation and intersection angles between planes) learned through convolutional neural networks to handle three challenging subtasks sequentially: (1) detecting planar regions with structure information (e.g., each component edge is associated with two planes intersecting at a specified angle); (2) inferring the planes corresponding to the planar regions progressively by taking full advantage of diverse constraints (e.g., structure and proximity constraints) based on geometric priors; and (3) globally optimizing the resulting planes under a unified framework that incorporates image cues and geometric priors. Experimental results on two public datasets released by CASIA and our own dataset demonstrate that the proposed method significantly outperforms five state-of-the-art methods (including two geometry-based methods and three learning-based methods) by an approximately 20 % margin in terms of accuracy. Code and data are available at https://github.com/three-dimensional-computer-vision/single-image-reconstruction.

Reconstructing piecewise planar scenes with multi-view regularization

Reconstruction of man-made scenes from multi-view images is an important problem in computer vision and computer graphics. Observing that man-made scenes are usually composed of planar surfaces, we encode plane shape prior in reconstructing man-made scenes. Recent approaches for single-view reconstruction employ multi-branch neural networks to simultaneously segment planes and recover 3D plane parameters. However, the scale of available annotated data heavily limits the generalizability and accuracy of these supervised methods. In this paper, we propose multi-view regularization to enhance the capability of piecewise planar reconstruction during the training phase, without demanding extra annotated data. Our multi-view regularization enables the consistency among multiple views by making the feature embedding more robust against view change and lighting variations. Thus, the neural network trained by multi-view regularization performs better on a wide range of views and lightings in the test phase. Based on more consistent prediction results, we merge the recovered models from multiple views to reconstruct scenes. Our approach achieves state-of-the-art reconstruction performance compared to previous approaches on the public ScanNet dataset.

Proximal robust factorization for piecewise planar reconstruction

In this paper, we aim to obtain a dense piecewise planar reconstruction of the scene from multiple image frames based on a factorization framework. Integrating all the relevant constraints in a global objective function, we are able to effectively leverage on the scene smoothness prior afforded by the dense formulation, as well as imposing the necessary algebraic constraints required by the shape matrix. These constraints also help to robustly decompose the measurement matrix into the underlying low-rank subspace and the sparse outlier part. Numerically, we achieve the constrained factorization and decomposition via modifying a recently proposed proximal alternating robust subspace minimization algorithm. The results show that our algorithm is effective in handling real life sequences, and outperforms other algorithms in recovering motions and dense scene estimate.

Piecewise-Planar StereoScan: Sequential Structure and Motion Using Plane Primitives.

The article describes a pipeline that receives as input a sequence of stereo images, and outputs the camera motion and a Piecewise-Planar Reconstruction (PPR) of the scene. The pipeline, named Piecewise-Planar StereoScan (PPSS), works as follows: the planes in the scene are detected for each stereo view using semi-dense depth estimation; the relative pose is computed by a new closed-form minimal algorithm that only uses point correspondences whenever plane detections do not fully constrain the motion; the camera motion and the PPR are jointly refined by alternating between discrete optimization and continuous bundle adjustment; and, finally, the detected 3D planes are segmented in images using a new framework that handles low texture and visibility issues. PPSS is extensively validated in indoor and outdoor datasets, and benchmarked against two popular point-based SfM pipelines. The experiments confirm that plane-based visual odometry is resilient to situations of small image overlap, poor texture, specularity, and perceptual aliasing where the fast LIBVISO2 [1] pipeline fails. The comparison against VisualSfM+CMVS/PMVS [2] , [3] shows that, for a similar computational complexity, PPSS is more accurate and provides much more compelling and visually pleasant 3D models. These results strongly suggest that plane primitives are an advantageous alternative to point correspondences for applications of SfM and 3D reconstruction in man-made environments.

Piecewise-planar Reconstruction of Multi-room Interiors with Arbitrary Wall Arrangements

Reconstructing the as-built architectural shape of building interiors has emerged in recent years as an important and challenging research problem. An effective approach must be able to faithfully ...

Piecewise-planar reconstruction using two views

The article describes a reconstruction pipeline that generates piecewise-planar models of man-made environments using two calibrated views. The 3D space is sampled by a set of virtual cut planes that intersect the baseline of the stereo rig and implicitly define possible pixel correspondences across views. The likelihood of these correspondences being true matches is measured using signal symmetry analysis [1], which enables to obtain profile contours of the 3D scene that become lines whenever the virtual cut planes intersect planar surfaces. The detection and estimation of these lines cuts is formulated as a global optimization problem over the symmetry matching cost, and pairs of reconstructed lines are used to generate plane hypotheses that serve as input to PEARL clustering [2]. The PEARL algorithm alternates between a discrete optimization step, which merges planar surface hypotheses and discards detections with poor support, and a continuous optimization step, which refines the plane poses taking into account surface slant. The pipeline outputs an accurate semi-dense Piecewise-Planar Reconstruction of the 3D scene. In addition, the input images can be segmented into piecewise-planar regions using a standard labeling formulation for assigning pixels to plane detections. Extensive experiments with both indoor and outdoor stereo pairs show significant improvements over state-of-the-art methods with respect to accuracy and robustness.

A trace finite element method for a class of coupled bulk-interface transport problems

In this paper we study a system of advection-diffusion equations in a bulk domain coupled to an advection-diffusion equation on an embedded surface. Such systems of coupled partial differential equations arise in, for example, the modeling of transport and diffusion of surfactants in two-phase flows. The model considered here accounts for adsorption-desorption of the surfactants at a sharp interface between two fluids and their transport and diffusion in both fluid phases and along the interface. The paper gives a well-posedness analysis for the system of bulk-surface equations and introduces a finite element method for its numerical solution. The finite element method is unfitted, i.e. , the mesh is not aligned to the interface. The method is based on taking traces of a standard finite element space both on the bulk domains and the embedded surface. The numerical approach allows an implicit definition of the surface as the zero level of a level-set function. Optimal order error estimates are proved for the finite element method both in the bulk-surface energy norm and the L 2 -norm. The analysis is not restricted to linear finite elements and a piecewise planar reconstruction of the surface, but also covers the discretization with higher order elements and a higher order surface reconstruction.