3D reconstruction of free-formed line-like objects using NURBS representation

Multi-view stereopsis (MVS) is a core problem in computer vision, which takes a set of scene views together with known camera poses, then produces a geometric representation of the underlying 3D model Using 3D reconstruction one can determine any object's 3D profile, as well as knowing the 3D coordinate of any point on the profile. The 3D reconstruction of objects is a generally scientific problem and core technology of a wide variety of fields, such as Computer Aided Geometric Design (CAGD), computer graphics, computer animation, computer vision, medical imaging, computational science, virtual reality, digital media, etc. However, though MVS problems have been studied for decades, many challenges still exist in current state-of-the-art algorithms, for example, many algorithms still lack accuracy and completeness when tested on city-scale large datasets, most MVS algorithms available require a large amount of execution time and/or specialized hardware and software, which results in high cost, and etc... This dissertation work tries to address all the challenges we mentioned, and proposed multiple solutions. More specifically, this dissertation work proposed multiple novel MVS algorithms to automatically and accurately reconstruct the underlying 3D scenes. By proposing a novel volumetric voxel-based method, one of our algorithms achieved near real-time runtime speed, which does not require any special hardware or software, and can be deployed onto power-constrained embedded systems. By developing a new camera clustering module and a novel weighted voting-based surface likelihood estimation module, our algorithm is generalized to process di erent datasets, and achieved the best performance in terms of accuracy and completeness when compared with existing algorithms. This dissertation work also performs the very first quantitative evaluation in terms of precision, recall, and F-score using real-world LiDAR groundtruth data. Last but not least, this dissertation work proposes an automatic workflow, which can stitch multiple point cloud models with limited overlapping areas into one larger 3D model for better geographical coverage. All the results presented in this dissertation work have been evaluated in our wide area motion imagery (WAMI) dataset, and improved the state-of-the-art performances by a large margin.The generated results from this dissertation work have been successfully used in many aspects, including: city digitization, improving detection and tracking performances, real time dynamic shadow detection, 3D change detection, visibility map generating, VR environment, and visualization combined with other information, such as building footprint and roads.

One of the fundamental problems of computer vision is to extract 3D shape and motion from images. This can be achieved when a scene or object is observed from different viewpoints or over a period of time. There is a wide range of applications, ranging from digitizing cultural heritage to vision-based autonomous robot navigation. This talk will present several approaches to solve this problem. First, we’ll discuss techniques for 3D shape recovery for static objects and scenes. One particular case is the 3D mapping and localization in large environments from images, e.g. urban 3D reconstruction from vehicleborne cameras or localization from cell-phone images. Next, we’ll shift our focus to modeling dynamic scenes, e.g. people who are moving around. In addition to explicitly 3D modeling an event, we'll consider the possibility to perform video-based rendering from casually captured videos. Speaker Bio-Sketch: Marc Pollefeys is a full professor in the Dept. of Computer Science of ETH Zurich since 2007 where he is the head of the Institute for Visual Computing and leads the Computer Vision and Geometry lab. He currently also remains associated with the Dept. of Computer Science of the University of North Carolina at Chapel Hill where he started as an assistant professor in 2002 and became an associate professor in 2005. Before this he was a postdoctoral researcher at the Katholieke Universiteit Leuven in Belgium, where he also received his M.S. and Ph.D. degrees in 1994 and 1999, respectively. His main area of research is computer vision. One of his main research goals is to develop flexible approaches to capture visual representations of real world objects, scenes and events. Dr. Pollefeys has received several prizes for his research, including a Marr prize, an NSF CAREER award, a Packard Fellowship and a European Research Council Starting Grant. He is the author or co-author of more than 130 peer-reviewed publications. He is the General Chair for the European Conference on Computer Vision 2014 (ECCV), was a Program Co-Chair for the IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR), was general/program co-chair of the Third Symposium on 3D Data Processing, Visualization and Transmission and has organized workshops and courses at major vision and graphics conferences and has served on the program committees of many conferences. Prof. Pollefeys is/was on the Editorial Board of the IEEE Transactions on Pattern Analysis and Machine Intelligence and the International Journal of Computer Vision as well as several other journals in computer vision, graphics and robotics.

3D reconstruction from a single image is a classical problem in computer vision. However, it still poses great challenges for the reconstruction of daily-use objects with irregular shapes. In this paper, we propose to learn 3D reconstruction knowledge from informally captured RGB-D images, which will probably be ubiquitously used in daily life. The learning of 3D reconstruction is defined as a category modeling problem, in which a model for each category is trained to encode category-specific knowledge for 3D reconstruction. The category model estimates the pixel-level 3D structure of an object from its 2D appearance, by taking into account considerable variations in rotation, 3D structure, and texture. Learning 3D reconstruction from ubiquitous RGB-D images creates a new set of challenges. Experimental results have demonstrated the effectiveness of the proposed approach.

Over the last two decades, research community of computer vision has developed various techniques suitable for underwater applications using intensity images. This chapter will explore 3D reconstruction of underwater natural scenes and objects based on stereo vision, which will be helpful in mine detection, inspection of shipwrecks, detection of telecommunication cables and pipelines. The general steps involved in 3D reconstruction using stereo vision are provided. The brief summary of papers for 3D reconstruction of underwater environment is presented. 3D reconstruction of underwater natural scenes and objects is challenging problem due to light propagation in underwater. In contrast to light propagation in the air, the light rays are attenuated and scattered, having a great effect on image quality. We have proposed preprocessing technique to enhance degraded underwater images. At the end of the chapter, we have presented the proposed stereo vision based 3D reconstruction technique to reconstruct 3D surface of underwater objects. Ultimately, this chapter intends to give an overview of the 3D reconstruction technique using stereo vision in order to help a reader in understanding stereo vision and its benefits for underwater applications.

Effective measurement of the reflective or transparent surface of an object has always been a disadvantage in laser scanning modeling. We propose a fast and complete three-dimensional (3D) reconstruction method for small static objects using laser scanning and the structure from motion (SFM) algorithm. Meanwhile, a complete reconstruction workflow is designed and a multi-angle 3d reconstruction system is set up. To generate the complete point cloud model of the object, the SFM algorithm is used to reconstruct the surface part of the object, the data for which cannot be obtained by the laser measuring instrument. The experimental results show that this method not only improves the speed, accuracy, integrity, and visual effect of 3D reconstruction of small objects, but also extends the scope of 3D reconstruction of laser measurement.

Today, with quality becoming increasingly important, each product requires three-dimensional in-line quality control. On the other hand, the 3D reconstruction of transparent objects is a very difficult problem in computer vision due to transparency and specularity of the surface. This paper proposes a new method, called Scanning From Heating (SFH), to determine the surface shape of transparent objects using laser surface heating and thermal imaging. Furthermore, the application to transparent glass is discussed and results on different surface shapes are presented.

This work deals with the automatic 3D reconstruction of objects from frontal RGB images. This aims at a better understanding of the reconstruction of 3D objects from RGB images and their use in immersive virtual environments. We propose a complete workflow that can be easily adapted to almost any other family of rigid objects. To explain and validate our method, we focus on guitars. First, we detect and segment the guitars present in the image using semantic segmentation methods based on convolutional neural networks. In a second step, we perform the final 3D reconstruction of the guitar by warping the rendered depth maps of a fitted 3D template in 2D image space to match the input silhouette. We validated our method by obtaining guitar reconstructions from real input images and renders of all guitar models available in the ShapeNet database. Numerical results for different object families were obtained by computing standard mesh evaluation metrics such as Intersection over Union, Chamfer Distance, and the F-score. The results of this study show that our method can automatically generate high-quality 3D object reconstructions from frontal images using various segmentation and 3D reconstruction techniques.

With the development of computer vision technologies, 3D reconstruction has become a hotspot. At present, 3D reconstruction relies heavily on expensive equipment and has poor real-time performance. In this paper, we aim at solving the problem of 3D reconstruction of an indoor scene with large vertical span. In this paper, we propose a novel approach for 3D reconstruction of indoor scenes with only a Kinect. Firstly, this method uses a Kinect sensor to get color images and depth images of an indoor scene. Secondly, the combination of scale-invariant feature transform and random sample consensus algorithm is used to determine the transformation matrix of adjacent frames, which can be seen as the initial value of iterative closest point (ICP). Thirdly, we establish the relative coordinate relation between pair-wise frames which are the initial point cloud data by using ICP. Finally, we achieve the 3D visual reconstruction model of indoor scene by the top-down image registration of point cloud data. This approach not only mitigates the sensor perspective restriction and achieves the indoor scene reconstruction of large vertical span, but also develops the fast algorithm of indoor scene reconstruction with large amount of cloud data. The experimental results show that the proposed algorithm has better accuracy, better reconstruction effect, and less running time for point cloud registration. In addition, the proposed method has great potential applied to 3D simultaneous location and mapping.

Estimating the pose of a plane given a set of point correspondences is a core problem in computer vision with many applications including Augmented Reality (AR), camera calibration and 3D scene reconstruction and interpretation. Despite much progress over recent years there is still the need for a more efficient and more accurate solution, particularly in mobile applications where the run-time budget is critical. We present a new analytic solution to the problem which is far faster than current methods based on solving Pose from $$n$$ n Points (PnP) and is in most cases more accurate. Our approach involves a new way to exploit redundancy in the homography coefficients. This uses the fact that when the homography is noisy it will estimate the true transform between the model plane and the image better at some regions on the plane than at others. Our method is based on locating a point where the transform is best estimated, and using only the local transformation at that point to constrain pose. This involves solving pose with a local non-redundant 1st-order PDE. We call this framework Infinitesimal Plane-based Pose Estimation (IPPE), because one can think of it as solving pose using the transform about an infinitesimally small region on the surface. We show experimentally that IPPE leads to very accurate pose estimates. Because IPPE is analytic it is both extremely fast and allows us to fully characterise the method in terms of degeneracies, number of returned solutions, and the geometric relationship of these solutions. This characterisation is not possible with state-of-the-art PnP methods.

The practical, rapid, and accurate optical 3D reconstruction of transparent objects with contemporary non-contact optical techniques, has been an open challenge in the field of optical metrology. The combination of refraction, reflection, and transmission in transparent objects makes it very hard to use common off-the-shelf 3D reconstruction solutions to accurately reconstruct transparent objects in three dimensions without completely coating the object with an opaque material. We demonstrate in this work that a specific class of transparent objects can indeed be reconstructed without the use of opaque spray coatings, via Optical Projection Tomography (OPT). Particularly, the 3D reconstruction of large thin-walled hollow transparent objects can be achieved via OPT, without the use of refractive-index-matching liquid, accurately enough for use in both cultural heritage and beverage packaging industry applications. We compare 3D reconstructions of our proposed OPT method to those achieved by an industrial-grade 3D scanner and report average shape differences of ±0.34 mm for 'shelled' hollow objects and ±0.92 mm for 'non-shelled' hollow objects. A disadvantage of using OPT, which was noticed on the thicker 'non-shelled' hollow objects, as opposed to the 'shelled' hollow objects, was that it induced partial filling of hollow areas and the deformation of embossed features.

In this paper, 3D reconstruction of resident space objects (RSO) in orbit using a radar network with one transmitter and three receivers is studied. The interferometric phase for 3D reconstruction is extracted by the nonuniform fast Fourier transform (NUFFT) using sparse data at three receivers. The performance of the time frequency representation reconstructed from sparse data and the effect of data sparsity positions at three receivers in size, shape, rotation rate and Doppler estimation is illustrated.

In modern medicine, 3D reconstruction plays an important role in improving the accuracy of disease detection and treatment especially in the process of robot-assisted surgery. Accordingly, the choice of 3D reconstruction method is of great importance, which provides real-time visualization. This study analyses and compares two types of methods in 3D medical image reconstruction and visualization: Surface Rendering and Volume Rendering. To be more specific, four algorithms including Contour Filter (CF), Marching Cubes (MC), Composite Volume Rendering (CVR) and Texture Mapping Hardware (TMH) were implemented and compared from the perspective of the rendering effect, speed and interactivity, in which the former two algorithms belong to the concept of Surface Rendering and the latter two algorithms are in the range of Volume Rendering. These algorithms were implemented by Microsoft Visual Studio with Visualization Toolkit (VTK) to reconstruct the 3D images of patients CT image data. The mechanism and realization of these algorithms were described, and the merits and shortcomings of these different rendering methods were compared. Based on the comparison results, the 3D reconstruction and rendering method can be determined according to the specific requirements of robot-assisted surgery.

Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding

3D reconstruction from images is a core problem in computer vision. With recent advances in deep learning, it has become possible to recover plausible 3D shapes even from single RGB images for the first time. However, obtaining detailed geometry and texture for objects with arbitrary topology remains challenging. In this paper, we propose a novel approach for reconstructing point clouds from RGB images. Unlike other methods, we can recover dense point clouds with hundreds of thousands of points, and we also include RGB textures. In addition, we train our model on multiple categories which leads to superior generalization to unseen categories compared to previous techniques. We achieve this using a two-stage approach, where we first infer an object coordinate map from the input RGB image, and then obtain the final point cloud using a reprojection and completion step. We show results on standard benchmarks that demonstrate the advantages of our technique. Code is available at https://github.com/TaoHuUMD/3D-Reconstruction.

Light field imaging is an emerging technology in computational photography areas. Based on innovative designs of the imaging model and the optical path, light field cameras not only record the spatial intensity of threedimensional (3D) objects, but also capture the angular information of the physical world, which provides new ways to address various problems in computer vision, such as 3D reconstruction, saliency detection, and object recognition. In this paper, three key aspects of light field cameras, i.e., model, calibration, and reconstruction, are reviewed extensively. Furthermore, light field based applications on informatics, physics, medicine, and biology are exhibited. Finally, open issues in light field imaging and long-term application prospects in other natural sciences are discussed.