Aleksey Golovinskiy

A benchmark for 3D mesh segmentation

This paper describes a benchmark for evaluation of 3D mesh segmentation salgorithms. The benchmark comprises a data set with 4,300 manually generated segmentations for 380 surface meshes of 19 different object categories, and it includes software for analyzing 11 geometric properties of segmentations and producing 4 quantitative metrics for comparison of segmentations. The paper investigates the design decisions made in building the benchmark, analyzes properties of human-generated and computer-generated segmentations, and provides quantitative comparisons of 7 recently published mesh segmentation algorithms. Our results suggest that people are remarkably consistent in the way that they segment most 3D surface meshes, that no one automatic segmentation algorithm is better than the others for all types of objects, and that algorithms based on non-local shape features seem to produce segmentations that most closely resemble ones made by humans.

Shape-based recognition of 3D point clouds in urban environments

This paper investigates the design of a system for recognizing objects in 3D point clouds of urban environments. The system is decomposed into four steps: locating, segmenting, characterizing, and classifying clusters of 3D points. Specifically, we first cluster nearby points to form a set of potential object locations (with hierarchical clustering). Then, we segment points near those locations into foreground and background sets (with a graph-cut algorithm). Next, we build a feature vector for each point cluster (based on both its shape and its context). Finally, we label the feature vectors using a classifier trained on a set of manually labeled objects. The paper presents several alternative methods for each step. We quantitatively evaluate the system and tradeoffs of different alternatives in a truthed part of a scan of Ottawa that contains approximately 100 million points and 1000 objects of interest. Then, we use this truth data as a training set to recognize objects amidst approximately 1 billion points of the remainder of the Ottawa scan.

A planar-reflective symmetry transform for 3D shapes

Symmetry is an important cue for many applications, including object alignment, recognition, and segmentation. In this paper, we describe a planar reflective symmetry transform (PRST) that captures a continuous measure of the reflectional symmetry of a shape with respect to all possible planes. This transform combines and extends previous work that has focused on global symmetries with respect to the center of mass in 3D meshes and local symmetries with respect to points in 2D images. We provide an efficient Monte Carlo sampling algorithm for computing the transform for surfaces and show that it is stable under common transformations. We also provide an iterative refinement algorithm to find local maxima of the transform precisely. We use the transform to define two new geometric properties, center of symmetry and principal symmetry axes, and show that they are useful for aligning objects in a canonical coordinate system. Finally, we demonstrate that the symmetry transform is useful for several applications in computer graphics, including shape matching, segmentation of meshes into parts, and automatic viewpoint selection.

Min-cut based segmentation of point clouds

We present a min-cut based method of segmenting objects in point clouds. Given an object location, our method builds a k-nearest neighbors graph, assumes a background prior, adds hard foreground (and optionally background) constraints, and finds the min-cut to compute a foreground-background segmentation. Our method can be run fully automatically, or interactively with a user interface. We test our system on an outdoor urban scan, quantitatively evaluate our algorithm on a test set of about 1000 objects, and compare to several alternative approaches.

Technical Section: Consistent segmentation of 3D models

This paper proposes a method to segment a set of models consistently. The method simultaneously segments models and creates correspondences between segments. First, a graph is constructed whose nodes represent the faces of every mesh, and whose edges connect adjacent faces within a mesh and corresponding faces in different meshes. Second, a consistent segmentation is created by clustering this graph, allowing for outlier segments that are not present in every mesh. The method is demonstrated for several classes of objects and used for two applications: symmetric segmentation and segmentation transfer.

A statistical model for synthesis of detailed facial geometry

Detailed surface geometry contributes greatly to the visual realism of 3D face models. However, acquiring high-resolution face geometry is often tedious and expensive. Consequently, most face models used in games, virtual reality, or computer vision look unrealistically smooth. In this paper, we introduce a new statistical technique for the analysis and synthesis of small three-dimensional facial features, such as wrinkles and pores. We acquire high-resolution face geometry for people across a wide range of ages, genders, and races. For each scan, we separate the skin surface details from a smooth base mesh using displaced subdivision surfaces. Then, we analyze the resulting displacement maps using the texture analysis/synthesis framework of Heeger and Bergen, adapted to capture statistics that vary spatially across a face. Finally, we use the extracted statistics to synthesize plausible detail on face meshes of arbitrary subjects. We demonstrate the effectiveness of this method in several applications, including analysis of facial texture in subjects with different ages and genders, interpolation between high-resolution face scans, adding detail to low-resolution face scans, and adjusting the apparent age of faces. In all cases, we are able to re-produce fine geometric details consistent with those observed in high resolution scans.

Self-similar texture for coherent line stylization

Stylized line rendering for animation has traditionally traded-off between two undesirable artifacts: stroke texture sliding and stroke texture stretching. This paper proposes a new stroke texture representation, the self-similar line artmap (SLAM), which avoids both these artifacts. SLAM textures provide continuous, infinite zoom while maintaining approximately constant appearance in screen-space, and can be produced automatically from a single exemplar. SLAMs can be used as drop-in replacements for conventional stroke textures in 2D illustration and animation. Furthermore, SLAMs enable a new, simple approach to temporally coherent rendering of 3D paths that is suitable for interactive applications. We demonstrate results for 2D and 3D animations.

Symmetry-Aware Mesh Processing

Perfect, partial, and approximate symmetries are pervasive in 3D surface meshes of real-world objects. However, current digital geometry processing algorithms generally ignore them, instead focusing on local shape features and differential surface properties. This paper investigates how detection of large-scale symmetries can be used to guide processing of 3D meshes. It investigates a framework for mesh processing that includes steps for symmetrization (applying a warp to make a surface more symmetric) and symmetric remeshing (approximating a surface with a mesh having symmetric topology). These steps can be used to enhance the symmetries of a mesh, to decompose a mesh into its symmetric parts and asymmetric residuals, and to establish correspondences between symmetric mesh features. Applications are demonstrated for modeling, beautification, and simplification of nearly symmetric surfaces.

Symmetry-enhanced remeshing of surfaces

While existing methods for 3D surface approximation use local geometric properties, we propose that more intuitive results can be obtained by considering global shape properties such as symmetry. We modify the Variational Shape Approximation technique to consider the symmetries, near-symmetries, and partial symmetries of the input mesh. This has the effect of preserving and even enhancing symmetries in the output model, if doing so does not increase the error substantially. We demonstrate that using symmetry produces results that are more aesthetically appealing and correspond more closely to human expectations, especially when simplifying to very few polygons.