Detecting Approximate Reflection Symmetry in a Point Set Using Optimization on Manifold

3DSymm: Robust and Accurate 3D Reflection Symmetry Detection

Abstract: Reflection symmetry is a very commonly occurring feature in both natural and man-made objects, which helps in understanding objects better and makes them visually pleasing. Detection of reflection symmetry is a fundamental problem in the field of computer vision and computer graphics which aids in understanding and representing reflective symmetric objects. In this work, we attempt the problem of detecting the 3D global reflection symmetry of a 3D object represented as a point cloud. The main challenge is to handle outliers, missing parts, and perturbations from the perfect reflection symmetry. We propose a descriptor-free approach, in which, we pose the problem of reflection symmetry detection as an optimization problem and provide a closed-form solution. We show that the proposed method achieves state-of-the-art performance on the standard dataset.

R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method.

Abstract: Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work. R-PointHop first determines a local reference frame (LRF) for every point using its nearest neighbors and finds its local attributes. Next, R-PointHop obtains local-to-global hierarchical features by point downsampling, neighborhood expansion, attribute construction and dimensionality reduction steps. Thus, we can build the correspondence of points in the hierarchical feature space using the nearest neighbor rule. Afterwards, a subset of salient points of good correspondence is selected to estimate the 3D transformation. The use of LRF allows for hierarchical features of points to be invariant with respect to rotation and translation, thus making R-PointHop more robust in building point correspondence even when rotation angles are large. Experiments are conducted on the ModelNet40 and the Stanford Bunny dataset, which demonstrate the effectiveness of R-PointHop on the 3D point cloud registration task. R-PointHop is a green and accurate solution since its model size and training time are smaller than those of deep learning methods by an order of magnitude while its registration errors are smaller. Our codes are available on GitHub.

Reflection symmetry aware image retargeting

Abstract: Reflection symmetry is one of the most commonly occurring and prominent visual attributes present in the real world. With an increase in the display devices of different sizes and aspect ratios, the images captured from the real world need to be resized to fit to the display device. In this paper, we propose a novel image retargeting approach which preserves the reflection symmetry present in the image during the image retargeting process. We detect the symmetry region present in the image using symmetry axis detection and object proposals. We propose a novel framework for finding an optimized reflected seam for the least energy seam defined by the seam carving approach. The symmetry axis and the symmetric object are preserved by adding or removing a seam and its reflected counterpart together. We show better preservation of symmetry axis, preservation of shape of the symmetric object, and quality of image retargeting when compared to the existing methods using three quantitative measures along with the qualitative results.

Virtual models in 3D digital reconstruction: detection and analysis of symmetry

Abstract: Cultural Heritage (CH) artifacts generally possess symmetry of reflection, rotation, translation and glide reflection in their shape. Similarity measures are used to determine complex 3D models where symmetry is considered to be one of the similarity signatures. This work presents the methodology of detecting symmetry in 3D objects based on the three techniques: (1) Eigenvalues and Eigenvectors, (2) local surface discontinuity, and (3) pixel orientation. In this work, these methods have been modified suitably for the detection of symmetry in CH artifacts. Among these methods, it is found that the first two methods yield better performance on the symmetry signature estimation of 98 percent for complex models and up to 100% for primitive models. The execution time of the proposed methods is compared with the state-of-the-art approaches available in the literature. Three levels of random 3D models available in the internet repository are analyzed for efficiency, performance and robustness. At each level, the accuracy of the Eigenvalue method and the local discontinuity method is found to be better than the pixel orientation method. The modified algorithms have been tested for better performance with F-score, robustness, and execution time with 3D benchmark dataset and cultural heritage dataset available in the literature. Future work shall be extended by applying the symmetry features as constraints for the effective search of CH artifacts in digital repositories.

Robust, fast and flexible symmetry plane detection based on differentiable symmetry measure

Abstract: Reflectional symmetry is a potentially very useful feature which many real-world objects exhibit. It is instrumental in a variety of applications such as object alignment, compression, symmetrical editing or reconstruction of incomplete objects. In this paper, we propose a novel differentiable symmetry measure, which allows using gradient-based optimization to find symmetry in geometric objects. We further propose a new method for symmetry plane detection in 3D objects based on this idea. The method performs well on perfectly as well as approximately symmetrical objects, it is robust to noise and to missing parts. Furthermore, it works on discrete point sets and therefore puts virtually no constraints on the input data. Due to flexibility of the symmetry measure, the method is also easily extensible, e.g., by adding more information about the input object and using it to further improve its performance. The proposed method was tested with very good results on many objects, including incomplete objects and noisy objects, and was compared to other state-of-the-art methods which it outperformed in most aspects.

Distinctive Image Features from Scale-Invariant Keypoints

Abstract: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Abstract: A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing

A Combined Corner and Edge Detector

Abstract: The problem we are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work. For example, we desire to obtain an understanding of natural scenes, containing roads, buildings, trees, bushes, etc., as typified by the two frames from a sequence illustrated in Figure 1. The solution to this problem that we are pursuing is to use a computer vision system based upon motion analysis of a monocular image sequence from a mobile camera. By extraction and tracking of image features, representations of the 3D analogues of these features can be constructed.

Efficient variants of the ICP algorithm

Abstract: The ICP (Iterative Closest Point) algorithm is widely used for geometric alignment of three-dimensional models when an initial estimate of the relative pose is known. Many variants of ICP have been proposed, affecting all phases of the algorithm from the selection and matching of points to the minimization strategy. We enumerate and classify many of these variants, and evaluate their effect on the speed with which the correct alignment is reached. In order to improve convergence for nearly-flat meshes with small features, such as inscribed surfaces, we introduce a new variant based on uniform sampling of the space of normals. We conclude by proposing a combination of ICP variants optimized for high speed. We demonstrate an implementation that is able to align two range images in a few tens of milliseconds, assuming a good initial guess. This capability has potential application to real-time 3D model acquisition and model-based tracking.

Optimization Algorithms on Matrix Manifolds

Abstract: Many problems in the sciences and engineering can be rephrased as optimization problems on matrix search spaces endowed with a so-called manifold structure. This book shows how to exploit the special structure of such problems to develop efficient numerical algorithms. It places careful emphasis on both the numerical formulation of the algorithm and its differential geometric abstraction--illustrating how good algorithms draw equally from the insights of differential geometry, optimization, and numerical analysis. Two more theoretical chapters provide readers with the background in differential geometry necessary to algorithmic development. In the other chapters, several well-known optimization methods such as steepest descent and conjugate gradients are generalized to abstract manifolds. The book provides a generic development of each of these methods, building upon the material of the geometric chapters. It then guides readers through the calculations that turn these geometrically formulated methods into concrete numerical algorithms. The state-of-the-art algorithms given as examples are competitive with the best existing algorithms for a selection of eigenspace problems in numerical linear algebra. Optimization Algorithms on Matrix Manifolds offers techniques with broad applications in linear algebra, signal processing, data mining, computer vision, and statistical analysis. It can serve as a graduate-level textbook and will be of interest to applied mathematicians, engineers, and computer scientists.