Vladislav Golyanik

Extended coherent point drift algorithm with correspondence priors and optimal subsampling

The problem of dense point set registration, given a sparse set of prior correspondences, often arises in computer vision tasks. Unlike in the rigid case, integrating prior knowledge into a registration algorithm is especially demanding in the non-rigid case due to the high variability of motion and deformation. In this paper we present the Extended Coherent Point Drift registration algorithm. It enables, on the one hand, to couple correspondence priors into the dense registration procedure in a closed form and, on the other hand, to process large point sets in reasonable time through adopting an optimal coarse-to-fine strategy. Combined with a suitable keypoint extractor during the preprocessing step, our method allows for non-rigid registrations with increased accuracy for point sets with structured outliers. We demonstrate advantages of our approach against other non-rigid point set registration methods in synthetic and real-world scenarios.

Precise and Automatic Anthropometric Measurement Extraction Using Template Registration

Anthropometric measures build the basis for many applications, such as custom clothing or biometric identity verification. Consequentially, the possibility to automatically extract them from human body scans is of high importance. In this paper we present a new approach based on landmarks and template registration. First, we propose a new method to define anthropometric measures once on a generic template using landmarks. After the initial definition the template can be registered against an individual body scan and the landmarks can be transferred to the scan using our second proposed algorithm. We apply our complete approach to real and synthetic human data and show that it outperforms the state-of-the-art for several measures.

Dense Batch Non-Rigid Structure from Motion in a Second

In this paper, we show how to minimise a quadratic function on a set of orthonormal matrices using an efficient semidefinite programming solver with application to dense non-rigid structure from motion. Thanks to the proposed technique, a new form of the convex relaxation for the Metric Projections (MP) algorithm is obtained. The modification results in an efficient single-core CPU implementation enabling dense factorisations of long image sequences with tens of thousands of points into camera pose and non-rigid shape in seconds, i.e., at least two orders of magnitude faster than the runtimes reported in the literature so far. The proposed implementation can be useful for interactive or real-time robotic and other applications, where monocular non-rigid reconstruction is required. In a narrow sense, our paper complements research on MP, though the proposed convex relaxation methodology can also be useful in other computer vision tasks. The experimental part providing runtime evaluation and qualitative analysis concludes the paper.

Occlusion-aware video registration for highly non-rigid objects

This paper addresses the problem of video registration for dense non-rigid structure from motion under suboptimal conditions, such as noise, self-occlusions, considerable external occlusions or specularities, i.e. the computation of optical flow between the reference image and each of the subsequent images in a video sequence when the camera observes a highly deformable object. We tackle this challenging task by improving previously proposed variational optimization techniques for multi-frame optical flow (MFOF) through detection, tracking and handling of uncertain flow field estimates. This is based on a novel Bayesian inference approach incorporated into the MFOF. At the same time, computational costs are significantly reduced through iterative pre-computation of the flow fields. As shown through experiments, the resulting method performs superior to other state-of-the-art (MF)OF methods on video sequences showing a highly non-rigidly deforming object with considerable occlusions.

Gravitational Approach for Point Set Registration

In this paper a new astrodynamics inspired rigid point set registration algorithm is introduced-the Gravitational Approach (GA). We formulate point set registration as a modified N-body problem with additional constraints and obtain an algorithm with unique properties which is fully scalable with the number of processing cores. In GA, a template point set moves in a viscous medium under gravitational forces induced by a reference point set. Pose updates are completed by numerically solving the differential equations of Newtonian mechanics. We discuss techniques for efficient implementation of the new algorithm and evaluate it on several synthetic and real-world scenarios. GA is compared with the widely used Iterative Closest Point and the state of the art rigid Coherent Point Drift algorithms. Experiments evidence that the new approach is robust against noise and can handle challenging scenarios with structured outliers.

Accurate 3D Reconstruction of Dynamic Scenes from Monocular Image Sequences with Severe Occlusions

The paper introduces an accurate solution to dense orthographic Non-Rigid Structure from Motion (NRSfM) in scenarios with severe occlusions or, likewise, inaccurate correspondences. We integrate a shape prior term into variational optimisation framework. It allows to penalize irregularities of the time-varying structure on the per-pixel level if correspondence quality indicator such as an occlusion tensor is available. We make a realistic assumption that several non-occluded views of the scene are sufficient to estimate an initial shape prior, though the entire observed scene may exhibit non-rigid deformations. Experiments on synthetic and real image data show that the proposed framework significantly outperforms state of the art methods for correspondence establishment in combination with the state of the art NRSfM methods. Together with the profound insights into optimisation methods, implementation details for heterogeneous platforms are provided.

NRSfM-Flow: Recovering Non-Rigid Scene Flow from Monocular Image Sequences.

Scene flow recovery from monocular image sequences is an emerging field in computer vision. While existing Monocular Scene Flow (MSF) methods extend the classical optical flow formulation to estimate depths/disparities and 3D motion, we propose a framework based on Non-Rigid Structure from Motion (NRSfM) technique — NRSfM-Flow. Therefore, both problems are formulated in the continuous domain and relation between them is established. To cope with real data, we propose two preprocessing steps for image sequences — redundancy removal and translation resolution — which increase quality of reconstructions and speedup computations. In contrast to the existing MSF methods which can cope with non-rigid deformations, our solution makes no strong assumptions about a scene such as known camera motion or camera velocity constancy and can handle occlusions. NRSfM-Flow is qualitatively evaluated on challenging real-world data. Experiments provide evidence that the proposed approach achieves high accuracy and outperforms state of the art in terms of the ability to reconstruct MSF with less prior knowledge about a scene.

Joint pre-alignment and robust rigid point set registration

We present an elegant solution to joint pre-alignment and rigid point set registration, given prior matches. Instead of performing pre-alignment and the actual registration in the separate steps, prior matches explicitly influence the registration procedure in our approach. This results in several advantages. Firstly, our approach solves the pre-alignment task - an approximate resolving of rotation and translation - with an insufficient number of prior correspondences, when other methods fail. Secondly, it produces more accurate rigid registrations of noisy point sets than the state of the art Coherent Point Drift method. Combined with application specific methods for correspondence establishment, we demonstrate superiority of our approach in several synthetic and real-world scenarios.