Multi-view Stereo Methods Research Articles

DEVELOPMENT OF MULTI-VIEW STEREO CONSIDERING ACCURACY OF EXTERIOR ORIENTATION ELEMENTS

Abstract. Structure from motion (SfM) has been widely used to achieve automatic 3D reconstructions. However, as the 3D point clouds obtained via SfM are sparse, multi-view stereo (MVS) was developed to compensate for this sparseness. The accuracy of the 3D surface depends on the accuracy of the orientation elements based on the SfM. Additionally, in the case of an unmanned aerial vehicle (UAV), SfM exhibits a decrease in the accuracy of the orientation elements during complex camera movements. This paper proposes a patch-based MVS (PMVS) method considering the accuracy of the orientation elements. The proposed method involves applying the global SfM, estimating accuracy of exterior orientation (EO) elements, and introducing the accuracy of EO elements to PMVS. The PMVS approximates an object surface by using small rectangular patches, namely local tangent plane approximation. The patches are optimized by minimizing the sum of the photometric discrepancy scores. The accuracy of the EO elements is introduced to the patch optimization as weighting function. This accuracy is defined using the variances of the estimated parameters in the bundle adjustment. We also investigate the types of weighting functions. The results indicate that the proposed method is capable of considering geometric conditions during patch estimation. The proposed method was applied to the three types of image datasets, i.e., images captured using an SLR camera at ground level, images captured using a UAV equipped with a SLR camera, and images captured using an airplane equipped with an oblique camera. Through the experimental results, the improved accuracy and the effectiveness of the proposed method were confirmed.

Dense Depth Estimation in Monocular Endoscopy With Self-Supervised Learning Methods.

We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires monocular endoscopic videos and a multi-view stereo method, e.g., structure from motion, to supervise learning in a sparse manner. Consequently, our method requires neither manual labeling nor patient computed tomography (CT) scan in the training and application phases. In a cross-patient experiment using CT scans as groundtruth, the proposed method achieved submillimeter mean residual error. In a comparison study to recent self-supervised depth estimation methods designed for natural video on in vivo sinus endoscopy data, we demonstrate that the proposed approach outperforms the previous methods by a large margin. The source code for this work is publicly available online at https://github.com/lppllppl920/EndoscopyDepthEstimation-Pytorch.

VIDEOGRAMMETRY VS PHOTOGRAMMETRY FOR HERITAGE 3D RECONSTRUCTION

Abstract. In the last years we are witnessing an increasing quality (and quantity) of video streams and a growing capability of SLAM-based methods to derive 3D data from video. Video sequences can be easily acquired by non-expert surveyors and possibly used for 3D documentation purposes. The aim of the paper is to evaluate the possibility to perform 3D reconstructions of heritage scenarios using videos ("videogrammetry"), e.g. acquired with smartphones. Video frames are extracted from the sequence using a fixed-time interval and two advanced methods. Frames are then processed applying automated image orientation / Structure from Motion (SfM) and dense image matching / Multi-View Stereo (MVS) methods. Obtained 3D dense point clouds are the visually validated as well as compared with photogrammetric ground truth archived acquiring image with a reflex camera or analysing 3D data's noise on flat surfaces.

Automated Progress Controlling and Monitoring Using Daily Site Images and Building Information Modelling

This research presents a novel method for automated construction progress monitoring. Using the proposed method, an accurate and complete 3D point cloud is generated for automatic outdoor and indoor progress monitoring throughout the project duration. In this method, Structured-from-Motion (SFM) and Multi-View-Stereo (MVS) algorithms coupled with photogrammetric principles for the coded targets’ detection are exploited to generate as-built 3D point clouds. The coded targets are utilized to automatically resolve the scale and increase the accuracy of the point cloud generated using SFM and MVS methods. Having generated the point cloud, the CAD model is generated from the as-built point cloud and compared with the as-planned model. Finally, the quantity of the performed work is determined in two real case study projects. The proposed method is compared to the Structured-from-Motion (SFM)/Clustering Multi-Views Stereo (CMVS)/Patch-based Multi-View Stereo (PMVS) algorithm, as a common method for generating 3D point cloud models. The proposed photogrammetric Multi-View Stereo method reveals an accuracy of around 99 percent and the generated noises are less compared to the SFM/CMVS/PMVS algorithm. It is observed that the proposed method has extensively improved the accuracy of generated points cloud compared to the SFM/CMVS/PMVS algorithm. It is believed that the proposed method may present a novel and robust tool for automated progress monitoring in construction projects.

Optimal Multi-View Surface Normal Estimation Using Affine Correspondences.

An optimal, in the least squares sense, method is proposed to estimate surface normals in both stereo and multi-view cases. The proposed algorithm exploits exclusively photometric information via affine correspondences and estimates the normal for each correspondence independently. The normal is obtained as a root of a quartic polynomial. Therefore, the processing time is negligible. Eliminating the outliers, we propose a robust extension of the algorithm that combines maximum likelihood estimation and iteratively re-weighted least squares. The method has been validated on both synthetic and publicly available real-world datasets. It is superior to the state of the art in terms of accuracy and processing time. Besides, we demonstrate two possible applications: 1) using our algorithm as the seed-point generation step of patch-based multi-view stereo method, the obtained reconstruction is more accurate, and the error of the 3D points is reduced by 30% on average and 2) multi-plane fitting becomes more accurate applied to the resulting oriented point cloud.

Accurate, dense and shading-aware multi-view stereo reconstruction using metaheuritic optimization

Among the modern means of 3D geometry creation that exist in the literature, there are the Multi-View Stereo (MVS) reconstruction methods that received much attention from the research community and the multimedia industry. In fact, several methods showed that it is possible to recover geometry only from images with reconstruction accuracies paralleling that of excessively expensive laser scanners. The majority of these methods perform on images such as online community photo collection and estimate the surface position with its orientation by minimizing a matching cost function defined over a small local region. However, these datasets not only they are large but also contain more challenging scenes setups with different photometric effects; therefore fine-grained details of an object’s surface cannot be captured. This paper presents a robust multi-view stereo method based on metaheuristic optimization namely the Particle Swarm Optimization (PSO) in order to find the optimal depth, orientation, and surface roughness. To deal with the various shading and stereo mismatch problems caused by rough surfaces, shadows, and interreflections, we propose to use a robust matching/energy function which is a combination of two similarity measurements. Finally, our method computes individual depth maps that can be merged into compelling scene reconstructions. The proposed method is evaluated quantitatively using well-known Middlebury datasets and the obtained results show a high completeness score and comparable accuracy to those of the current top performing algorithms.

3D measurements of micro-objects based on monocular wide-field optical microscopy with extended depth of field.

Monocular rotational microscopes suffer from shallow depth of field and reduced field of view. Consequently, we propose monocular wide-field optical microscopy with extended depth of field to enable accurate 3D measurements of micro-objects. We use a liquid lens and a 4f system to extend the system's depth of field and two additional rotational reflectors to capture multi-view image sequences. In addition, we increase the number of expansion directions in the patch-based multi-view stereo algorithm and optimize the expansion radius. Our approach outperforms that based on the patch-based multi-view stereo method and achieves a high relative measurement accuracy of 1.9%. RESEARCH HIGHLIGHTS: This study proposes 3D measurements of micro-objects via monocular rotational microscopy. The depth of field is extended by the use of a liquid lens and a 4f system. Our approach outperforms that based on the patch-based multi-view stereo method and achieves a high relative measurement accuracy of 1.9%.

Cost-effective erosion monitoring of coastal cliffs

Structure-from-motion with multi-view stereo (SfM-MVS) methods hold the potential for monitoring and quantifying cliff erosion to levels of accuracy and precision which rival terrestrial laser scanning (TLS) and at a fraction of the cost. We benchmark repeat SfM-MVS against TLS for quantifying rock fall frequency, volume, and cliff face erosion rates for a ∼1 km section of coastal cliffs where cliff top infrastructure is threatened by erosion. First, we address a major unknown in these techniques, the number and configuration of control points. Surveys demonstrate that a sparse configuration along the cliff base and top, at spacing equivalent to the cliff height, provides suitable accuracy at acceptable logistic time and expense. Second, we show that SfM-MVS models match equivalent TLS data to within 0.04 m, and that the correlation between intersecting TLS- and SfM-derived rock fall volumes improves markedly above a detection threshold of 0.07 m3. Rock falls below this size threshold account for ∼77.7% of detected rock falls but only 1.9% of the calculated annual eroded volume. Annual erosion rates for the 1 km cliff face as calculated by repeat TLS and SfM differencing are 0.6 × 10−2 m a−1 and 0.7 × 10−2 m a−1, respectively. Kilometre-scale patterns of cliff erosion are dominated by localised zones of high-magnitude, episodic failure that are over an order of magnitude greater than background rates. The ability of non-specialist engineers, geologists, geomorphologists and managers to rapidly capture high quality, accurate erosion data in a cost-effective manner through repeat SfM-MVS has significant potential to inform coastal managers and decision makers. To further empower coastal authorities and communities, policy frameworks must be developed to incorporate and interpret these data.

METRIC EVALUATION PIPELINE FOR 3D MODELING OF URBAN SCENES

Abstract. Publicly available benchmark data and metric evaluation approaches have been instrumental in enabling research to advance state of the art methods for remote sensing applications in urban 3D modeling. Most publicly available benchmark datasets have consisted of high resolution airborne imagery and lidar suitable for 3D modeling on a relatively modest scale. To enable research in larger scale 3D mapping, we have recently released a public benchmark dataset with multi-view commercial satellite imagery and metrics to compare 3D point clouds with lidar ground truth. We now define a more complete metric evaluation pipeline developed as publicly available open source software to assess semantically labeled 3D models of complex urban scenes derived from multi-view commercial satellite imagery. Evaluation metrics in our pipeline include horizontal and vertical accuracy and completeness, volumetric completeness and correctness, perceptual quality, and model simplicity. Sources of ground truth include airborne lidar and overhead imagery, and we demonstrate a semi-automated process for producing accurate ground truth shape files to characterize building footprints. We validate our current metric evaluation pipeline using 3D models produced using open source multi-view stereo methods. Data and software is made publicly available to enable further research and planned benchmarking activities.

Effective energy-based multi-view piecewise planar stereo

For piecewise planar scene modeling, many challenging issues still persist, in particular, how to generate sufficient candidate planes and how to assign an optimal plane for each spatial patch. To address these issues, we present a novel multi-view piecewise planar stereo method for the complete reconstruction. In our method, reconstruction is formulated as an energy-based plane labeling problem, where photo-consistency and geometric constraints are incorporated to a unified superpixel-level MRF (Markov Random Field) framework. To enhance the efficacy of the plane inference and optimization, an effective multi-direction plane sweeping with much restricted search space is carried out to generate sufficient and reliable candidate planes. Experiments show that our method can effectively handle many challenging factors (e.g., slant surfaces, textureless regions) and achieve satisfactory results.

Energy-based multi-view piecewise planar stereo

The piecewise planar model (PPM) is an effective means of approximating a complex scene by using planar patches to give a complete interpretation of the spatial points reconstructed from projected 2D images. The traditional piecewise planar stereo methods suffer from either a very restricted number of directions for plane detection or heavy reliance on the segmentation accuracy of superpixels. To address these issues, we propose a new multi-view piecewise planar stereo method in this paper. Our method formulates the problem of complete scene reconstruction as a multi-level energy minimization problem. To detect planes along principal directions, a novel energy formulation with pair-wise potentials is used to assign an optimal plane for each superpixel in an iterative manner, where reliable scene priors and geometric constraints are incorporated to enhance the modeling efficacy and inference efficiency. To detect non-principal-direction planes, we adopt a multi-direction plane sweeping with a restricted search space method to generate reliable candidate planes. To handle the multi-surface straddling problem of a single superpixel, a superpixel sub-segmenting scheme is proposed and a robust Pn Potts model-like higher-order potential is introduced to refine the resulting depth map. Our method is a natural integration of pixel- and superpixel-level multi-view stereos under a unified energy minimization framework. Experimental results for standard data sets and our own data sets show that our proposed method can satisfactorily handle many challenging factors (e.g., slanted surfaces and poorly textured regions) and can obtain accurate piecewise planar depth maps.

Robust Multiview Photometric Stereo Using Planar Mesh Parameterization.

We propose a robust uncalibrated multiview photometric stereo method for high quality 3D shape reconstruction. In our method, a coarse initial 3D mesh obtained using a multiview stereo method is projected onto a 2D planar domain using a planar mesh parameterization technique. We describe methods for surface normal estimation that work in the parameterized 2D space that jointly incorporates all geometric and photometric cues from multiple viewpoints. Using an estimated surface normal map, a refined 3D mesh is then recovered by computing an optimal displacement map in the same 2D planar domain. Our method avoids the need of merging view-dependent surface normal maps that is often required in conventional methods. We conduct evaluation on various real-world objects containing surfaces with specular reflections, multiple albedos, and complex topologies in both controlled and uncontrolled settings and demonstrate that accurate 3D meshes with fine geometric details can be recovered by our method.

A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction

We present a scalable multi-view stereo method able to reconstruct accurate 3D models from hundreds of high-resolution input images. Local fusion of disparity maps obtained with semi-global matchin...

THREE DIMENTIONAL RECONSTRUCTION OF LARGE CULTURAL HERITAGE OBJECTS BASED ON UAV VIDEO AND TLS DATA

Abstract. This paper investigates the synergetic use of unmanned aerial vehicle (UAV) and terrestrial laser scanner (TLS) in 3D reconstruction of cultural heritage objects. Rather than capturing still images, the UAV that equips a consumer digital camera is used to collect dynamic videos to overcome its limited endurance capacity. Then, a set of 3D point-cloud is generated from video image sequences using the automated structure-from-motion (SfM) and patch-based multi-view stereo (PMVS) methods. The TLS is used to collect the information that beyond the reachability of UAV imaging e.g., partial building facades. A coarse to fine method is introduced to integrate the two sets of point clouds UAV image-reconstruction and TLS scanning for completed 3D reconstruction. For increased reliability, a variant of ICP algorithm is introduced using local terrain invariant regions in the combined designation. The experimental study is conducted in the Tulou culture heritage building in Fujian province, China, which is focused on one of the TuLou clusters built several hundred years ago. Results show a digital 3D model of the Tulou cluster with complete coverage and textural information. This paper demonstrates the usability of the proposed method for efficient 3D reconstruction of heritage object based on UAV video and TLS data.

THREE DIMENTIONAL RECONSTRUCTION OF LARGE CULTURAL HERITAGE OBJECTS BASED ON UAV VIDEO AND TLS DATA

This paper investigates the synergetic use of unmanned aerial vehicle (UAV) and terrestrial laser scanner (TLS) in 3D reconstruction of cultural heritage objects. Rather than capturing still images, the UAV that equips a consumer digital camera is used to collect dynamic videos to overcome its limited endurance capacity. Then, a set of 3D point-cloud is generated from video image sequences using the automated structure-from-motion (SfM) and patch-based multi-view stereo (PMVS) methods. The TLS is used to collect the information that beyond the reachability of UAV imaging e.g., partial building facades. A coarse to fine method is introduced to integrate the two sets of point clouds UAV image-reconstruction and TLS scanning for completed 3D reconstruction. For increased reliability, a variant of ICP algorithm is introduced using local terrain invariant regions in the combined designation. The experimental study is conducted in the Tulou culture heritage building in Fujian province, China, which is focused on one of the TuLou clusters built several hundred years ago. Results show a digital 3D model of the Tulou cluster with complete coverage and textural information. This paper demonstrates the usability of the proposed method for efficient 3D reconstruction of heritage object based on UAV video and TLS data.

A Multi-View Dense Point Cloud Generation Algorithm Based on Low-Altitude Remote Sensing Images

This paper presents a novel multi-view dense point cloud generation algorithm based on low-altitude remote sensing images. The proposed method was designed to be especially effective in enhancing the density of point clouds generated by Multi-View Stereo (MVS) algorithms. To overcome the limitations of MVS and dense matching algorithms, an expanded patch was set up for each point in the point cloud. Then, a patch-based Multiphoto Geometrically Constrained Matching (MPGC) was employed to optimize points on the patch based on least square adjustment, the space geometry relationship, and epipolar line constraint. The major advantages of this approach are twofold: (1) compared with the MVS method, the proposed algorithm can achieve denser three-dimensional (3D) point cloud data; and (2) compared with the epipolar-based dense matching method, the proposed method utilizes redundant measurements to weaken the influence of occlusion and noise on matching results. Comparison studies and experimental results have validated the accuracy of the proposed algorithm in low-altitude remote sensing image dense point cloud generation.

Efficient 3D Object Segmentation from Densely Sampled Light Fields with Applications to 3D Reconstruction

Precise object segmentation in image data is a fundamental problem with various applications, including 3D object reconstruction. We present an efficient algorithm to automatically segment a static foreground object from highly cluttered background in light fields. A key insight and contribution of our article is that a significant increase of the available input data can enable the design of novel, highly efficient approaches. In particular, the central idea of our method is to exploit high spatio-angular sampling on the order of thousands of input frames, for example, captured as a hand-held video, such that new structures are revealed due to the increased coherence in the data. We first show how purely local gradient information contained in slices of such a dense light field can be combined with information about the camera trajectory to make efficient estimates of the foreground and background. These estimates are then propagated to textureless regions using edge-aware filtering in the epipolar volume. Finally, we enforce global consistency in a gathering step to derive a precise object segmentation in both 2D and 3D space, which captures fine geometric details even in very cluttered scenes. The design of each of these steps is motivated by efficiency and scalability, allowing us to handle large, real-world video datasets on a standard desktop computer. We demonstrate how the results of our method can be used for considerably improving the speed and quality of image-based 3D reconstruction algorithms, and we compare our results to state-of-the-art segmentation and multiview stereo methods.

Detail-Preserving and Content-Aware Variational Multi-View Stereo Reconstruction.

Accurate recovery of 3D geometrical surfaces from calibrated 2D multi-view images is a fundamental yet active research area in computer vision. Despite the steady progress in multi-view stereo (MVS) reconstruction, many existing methods are still limited in recovering fine-scale details and sharp features while suppressing noises, and may fail in reconstructing regions with less textures. To address these limitations, this paper presents a detail-preserving and content-aware variational (DCV) MVS method, which reconstructs the 3D surface by alternating between reprojection error minimization and mesh denoising. In reprojection error minimization, we propose a novel inter-image similarity measure, which is effective to preserve fine-scale details of the reconstructed surface and builds a connection between guided image filtering and image registration. In mesh denoising, we propose a content-aware ℓp-minimization algorithm by adaptively estimating the p value and regularization parameters. Compared with conventional isotropic mesh smoothing approaches, the proposed method is much more promising in suppressing noise while preserving sharp features. Experimental results on benchmark data sets demonstrate that our DCV method is capable of recovering more surface details, and obtains cleaner and more accurate reconstructions than the state-of-the-art methods. In particular, our method achieves the best results among all published methods on the Middlebury dino ring and dino sparse data sets in terms of both completeness and accuracy.

A DAISY descriptor based multi-view stereo method for large-scale scenes

Normalized cross-correlation (NCC) has been widely used as the matching cost function in multi-view stereo methods. However, NCC is vulnerable in the occlusion area and edge region of large-scale scenes because of color distortion and illumination changes. To alleviate the above problems, we present an improved patch based multi-view stereo method by introducing a photometric discrepancy function based on DAISY descriptor. In the patch extraction stage, a new corresponding point matching method based on the DAISY descriptor is proposed and the epipolar constraint is used to filter mismatched points. In the patch optimization stage, a photometric discrepancy function based on DAISY descriptor is proposed to measure the photo-consistency among reconstructed patches to identify reliable patches. Finally, dense patches are obtained by expanding sparse patches with global visibility information and patch optimization. Experimental results show that the proposed algorithm obtains better reconstruction results in occlusion and edge regions of large-scale scenes.

Multi-view stereo via depth map fusion: A coordinate decent optimization method

Multi-view stereo (MVS) plays a critical role in many practically important vision applications. Among the existing MVS methods, one typical approach is to fuse the depth maps from different views via minimization of the energy functional. However, these methods usually have expensive computational cost and are inflexible for extending to large neighborhood, leading to long run time and reconstruction artifacts. In this work, we propose a simple, efficient and flexible depth-map-fusion-based MVS reconstruction method: CoD-Fusion. The core idea of the method is to minimize the anisotropic or isotropic TV+L1 energy functional using the coordinate decent (CoD) algorithm. CoD performs TV+L1 minimization via solving a serial of voxel-wise L1 minimization sub-problems which can be efficiently solved using fast weighted median filtering (WMF). We then extend WMF to larger neighborhood to suppress reconstruction artifacts. The results of quantitative and qualitative evaluation validate the flexibility and efficiency of CoD-Fusion as a promising method for large scale MVS reconstruction.