Multi-Modal Data Correspondence for the 4D Analysis of the Spine with Adolescent Idiopathic Scoliosis.

Adolescent idiopathic scoliosis is a three-dimensional spinal deformity that evolves during adolescence. Combined with static 3D X-ray acquisitions, novel approaches using motion capture allow for the analysis of the patient dynamics. However, as of today, they cannot provide an internal analysis of the spine in motion. In this study, we investigated the use of personalized kinematic avatars, created with observations of the outer (skin) and internal shape (3D spine) to infer the actual anatomic dynamics of the spine when driven by motion capture markers. Towards that end, we propose an approach to create a subject-specific digital twin from multi-modal data, namely, a surface scan of the back of the patient and a reconstruction of the 3D spine (EOS). We use radio-opaque markers to register the inner and outer observations. With respect to the previous work, our method does not rely on a precise palpation for the placement of the markers. We present the preliminary results on two cases, for which we acquired a second biplanar X-ray in a bending position. Our model can infer the spine motion from mocap markers with an accuracy below 1 cm on each anatomical axis and near 5 degrees in orientations.

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle.

Vertebrae localization, segmentation and identification in CT images is key to numerous clinical applications. While deep learning strategies have brought to this field significant improvements over recent years, transitional and pathological vertebrae are still plaguing most existing approaches as a consequence of their poor representation in training datasets. Alternatively, proposed non-learning based methods take benefit of prior knowledge to handle such particular cases. In this work we propose to combine both strategies. To this purpose we introduce an iterative cycle in which individual vertebrae are recurrently localized, segmented and identified using deep-networks, while anatomic consistency is enforced using statistical priors. In this strategy, the transitional vertebrae identification is handled by encoding their configurations in a graphical model that aggregates local deep-network predictions into an anatomically consistent final result. Our approach achieves the state-of-the-art results on the VerSe20 challenge benchmark, and outperforms all methods on transitional vertebrae as well as the generalization to the VerSe19 challenge benchmark. Furthermore, our method can detect and report inconsistent spine regions that do not satisfy the anatomic consistency priors. Our code and model are openly available for research purposes.1.

Mesh Denoising With Facet Graph Convolutions.

We examine the problem of mesh denoising, which consists of removing noise from corrupted 3D meshes while preserving existing geometric features. Most mesh denoising methods require a lot of mesh-specific parameter fine-tuning, to account for specific features and noise types. In recent years, data-driven methods have demonstrated their robustness and effectiveness with respect to noise and feature properties on a wide variety of geometry and image problems. Most existing mesh denoising methods still use hand-crafted features, and locally denoise facets rather than examine the mesh globally. In this work, we propose the use of a fully end-to-end learning strategy based on graph convolutions, where meaningful features are learned directly by our network. It operates on a graph of facets, directly on the existing topology of the mesh, without resampling, and follows a multi-scale design to extract geometric features at different resolution levels. Similar to most recent pipelines, given a noisy mesh, we first denoise face normals with our novel approach, then update vertex positions accordingly. Our method performs significantly better than the current state-of-the-art learning-based methods. Additionally, we show that it can be trained on noisy data, without explicit correspondence between noisy and ground-truth facets. We also propose a multi-scale denoising strategy, better suited to correct noise with a low spatial frequency.

Surface Motion Capture Animation Synthesis.

We propose to generate novel animations from a set of elementary examples of video-based surface motion capture, under user-specified constraints. 4D surface capture animation is motivated by the increasing demand from media production for highly realistic 3D content. To this aim, data driven strategies that consider video-based information can produce animation with real shapes, kinematics and appearances. Our animations rely on the combination and the interpolation of textured 3D mesh data, which requires examining two aspects: (1) Shape geometry and (2) appearance. First, we propose an animation synthesis structure for the shape geometry, the Essential graph, that outperforms standard Motion graphs in optimality with respect to quantitative criteria, and we extend optimized interpolated transition algorithms to mesh data. Second, we propose a compact view-independent representation for the shape appearance. This representation encodes subject appearance changes due to viewpoint and illumination, and due to inaccuracies in geometric modelling independently. Besides providing compact representations, such decompositions allow for additional applications such as interpolation for animation.

CBCT of a Moving Sample From X-Rays and Multiple Videos.

In this paper, we consider dense volumetric modeling of moving samples such as body parts. Most dense modeling methods consider samples observed with a moving X-ray device and cannot easily handle moving samples. We propose instead a novel method to observe shape motion from a fixed X-ray device and to build dense in-depth attenuation information. This yields a low-cost, low-dose 3-D imaging solution, taking benefit of equipment widely available in clinical environments. Our first innovation is to combine a video-based surface motion capture system with a single low-cost/low-dose fixed planar X-ray device, in order to retrieve the sample motion and attenuation information with minimal radiation exposure. Our second innovation is to rely on Bayesian inference to solve for a dense attenuation volume given planar radioscopic images of a moving sample. This approach enables multiple sources of noise to be considered and takes advantage of very limited prior information to solve an otherwise ill-posed problem. Results show that the proposed strategy is able to reconstruct dense volumetric attenuation models from a very limited number of radiographic views over time on synthetic and in-situ data.

Automatic Camera Calibration Using Multiple Sets of Pairwise Correspondences.

We propose a new method to add an uncalibrated node into a network of calibrated cameras using only pairwise point correspondences. While previous methods perform this task using triple correspondences, these are often difficult to establish when there is limited overlap between different views. In such challenging cases we must rely on pairwise correspondences and our solution becomes more advantageous. Our method includes an 11-point minimal solution for the intrinsic and extrinsic calibration of a camera from pairwise correspondences with other two calibrated cameras, and a new inlier selection framework that extends the traditional RANSAC family of algorithms to sampling across multiple datasets. Our method is validated on different application scenarios where a lack of triple correspondences might occur: addition of a new node to a camera network; calibration and motion estimation of a moving camera inside a camera network; and addition of views with limited overlap to a Structure-from-Motion model.

Tracking-by-Detection of 3D Human Shapes: From Surfaces to Volumes.

3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art.

Sparse Multi-View Consistency for Object Segmentation.

Multiple view segmentation consists in segmenting objects simultaneously in several views. A key issue in that respect and compared to monocular settings is to ensure propagation of segmentation information between views while minimizing complexity and computational cost. In this work, we first investigate the idea that examining measurements at the projections of a sparse set of 3D points is sufficient to achieve this goal. The proposed algorithm softly assigns each of these 3D samples to the scene background if it projects on the background region in at least one view, or to the foreground if it projects on foreground region in all views. Second, we show how other modalities such as depth may be seamlessly integrated in the model and benefit the segmentation. The paper exposes a detailed set of experiments used to validate the algorithm, showing results comparable with the state of art, with reduced computational complexity. We also discuss the use of different modalities for specific situations, such as dealing with a low number of viewpoints or a scene with color ambiguities between foreground and background.

Implicit B-spline surface reconstruction.

This paper presents a fast and flexible curve, and surface reconstruction technique based on implicit B-spline. This representation does not require any parameterization and it is locally supported. This fact has been exploited in this paper to propose a reconstruction technique through solving a sparse system of equations. This method is further accelerated to reduce the dimension to the active control lattice. Moreover, the surface smoothness and user interaction are allowed for controlling the surface. Finally, a novel weighting technique has been introduced in order to blend small patches and smooth them in the overlapping regions. The whole framework is very fast and efficient and can handle large cloud of points with very low computational cost. The experimental results show the flexibility and accuracy of the proposed algorithm to describe objects with complex topologies. Comparisons with other fitting methods highlight the superiority of the proposed approach in the presence of noise and missing data.

Topology-adaptive mesh deformation for surface evolution, morphing, and multiview reconstruction.

Triangulated meshes have become ubiquitous discrete surface representations. In this paper, we address the problem of how to maintain the manifold properties of a surface while it undergoes strong deformations that may cause topological changes. We introduce a new self-intersection removal algorithm, TransforMesh, and propose a mesh evolution framework based on this algorithm. Numerous shape modeling applications use surface evolution in order to improve shape properties such as appearance or accuracy. Both explicit and implicit representations can be considered for that purpose. However, explicit mesh representations, while allowing for accurate surface modeling, suffer from the inherent difficulty of reliably dealing with self-intersections and topological changes such as merges and splits. As a consequence, a majority of methods rely on implicit representations of surfaces, e.g., level sets, that naturally overcome these issues. Nevertheless, these methods are based on volumetric discretizations, which introduce an unwanted precision-complexity trade-off. The method that we propose handles topological changes in a robust manner and removes self-intersections, thus overcoming the traditional limitations of mesh-based approaches. To illustrate the effectiveness of TransforMesh, we describe several challenging applications: surface morphing and 3D reconstruction.

Silhouette Segmentation in Multiple Views.

In this paper, we present a method for extracting consistent foreground regions when multiple views of a scene are available. We propose a framework that automatically identifies such regions in images under the assumption that, in each image, background and foreground regions present different color properties. To achieve this task, monocular color information is not sufficient and we exploit the spatial consistency constraint that several image projections of the same space region must satisfy. Combining the monocular color consistency constraint with multiview spatial constraints allows us to automatically and simultaneously segment the foreground and background regions in multiview images. In contrast to standard background subtraction methods, the proposed approach does not require a priori knowledge of the background nor user interaction. Experimental results under realistic scenarios demonstrate the effectiveness of the method for multiple camera set ups.

Efficient polyhedral modeling from silhouettes.

Modeling from silhouettes is a popular and useful topic in computer vision. Many methods exist to compute the surface of the visual hull from silhouettes, but few address the problem of ensuring sane topological properties of the surface, such as manifoldness. This article provides an efficient algorithm to compute such a surface in the form of a polyhedral mesh. It relies on a small number of geometric operations to compute a visual hull polyhedron in a single pass. Such simplicity enables the algorithm to combine the advantages of being fast, producing pixel-exact surfaces, and repeatably yield manifold and watertight polyhedra in general experimental conditions with real data, as verified with all datasets tested. The algorithm is fully described, its complexity analyzed and modeling results given.

Human motion tracking by registering an articulated surface to 3D points and normals.

We address the problem of human motion tracking by registering a surface to 3-D data. We propose a method that iteratively computes two things: Maximum likelihood estimates for both the kinematic and free-motion parameters of an articulated object, as well as probabilities that the data are assigned either to an object part, or to an outlier cluster. We introduce a new metric between observed points and normals on one side, and a parameterized surface on the other side, the latter being defined as a blending over a set of ellipsoids. We claim that this metric is well suited when one deals with either visual-hull or visual-shape observations. We illustrate the method by tracking human motions using sparse visual-shape data (3-D surface points and normals) gathered from imperfect silhouettes.

Using geometric constraints through parallelepipeds for calibration and 3D modeling.

This paper concerns the incorporation of geometric information in camera calibration and 3D modeling. Using geometric constraints enables more stable results and allows us to perform tasks with fewer images. Our approach is motivated and developed within a framework of semi-automatic 3D modeling, where the user defines geometric primitives and constraints between them. It is based on the observation that constraints, such as coplanarity, parallelism, or orthogonality, are often embedded intuitively in parallelepipeds. Moreover, parallelepipeds are easy to delineate by a user and are well adapted to model the main structure of, e.g., architectural scenes. In this paper, first a duality that exists between the shape parameters of a parallelepiped and the intrinsic parameters of a camera is described. Then, a factorization-based algorithm exploiting this relation is developed. Using images of parallelepipeds, it allows us to simultaneously calibrate cameras, recover shapes of parallelepipeds, and estimate the relative pose of all entities. Besides geometric constraints expressed via parallelepipeds, our approach simultaneously takes into account the usual self-calibration constraints on cameras. The proposed algorithm is completed by a study of the singular cases of the calibration method. A complete method for the reconstruction of scene primitives that are not modeled by parallelepipeds is also briefly described. The proposed methods are validated by various experiments with real and simulated data, for single-view as well as multiview cases.