Surface feature detection and description with applications to mesh matching (original) (raw)
Related papers
2011
In recent years, we have witnessed a striking increase in research concerning how to describe a meshed surface. These descriptors are commonly used to encode mesh properties or guide mesh processing, not to augment existing computations by replication. In this work, we first define a robust surface descriptor based on a local height field representation, and present a transformation via the extraction of Zernike moments. Unlike previous work, our local surface descriptor is innately rotationally invariant. Second, equipped with this novel descriptor, we present SAMPLE -similarity augmented mesh processing using local exemplars -a method which uses feature neighbourhoods to propagate mesh processing done in one part of the mesh, the local exemplar, to many others. Finally, we show that SAMPLE can be used in a number of applications, such as detail transfer and parameterization.
Keypoints and Local Descriptors of Scalar Functions on 2D Manifolds,
Keypoints and Local Descriptors of Scalar Functions on 2D Manifolds
"This paper addresses the problem of describing surfaces using local features and descriptors. While methods for the detection of interest points in images and their description based on local image features are very well understood, their extension to discrete manifolds has not been well investigated. We provide a methodological framework for analyzing real-valued functions defined over a 2D manifold, embedded in the 3D Euclidean space, e.g., photometric information, local curvature, etc. Our work is motivated by recent advancements in multiple-camera reconstruction and image-based rendering of 3D objects: there is a growing need for describing object surfaces, matching two surfaces, or tracking them over time. Considering polygonal meshes, we propose a new methodological framework for the scale-space representations of scalar functions defined over such meshes. We propose a local feature detector (MeshDOG) and region descriptor (MeshHOG). Unlike the standard image features, the proposed surface features capture both the local geometry of the underlying manifold and the scale-space differential properties of the real-valued function itself. We provide a thorough experimental evaluation. The repeatability of the feature detector and the robustness of feature descriptor are tested, by applying a large number of deformations to the manifold or to the scalar function."
Representing 3D texture on mesh manifolds for retrieval and recognition applications
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
In this paper, we present and experiment a novel approach for representing texture of 3D mesh manifolds using local binary patterns (LBP). Using a recently proposed framework [37], we compute LBP directly on the mesh surface, either using geometric or photometric appearance. Compared to its depth-image counterpart, our approach is distinguished by the following features: a) inherits the intrinsic advantages of mesh surface (e.g., preservation of the full geometry); b) does not require normalization; c) can accommodate partial matching. In addition, it allows earlylevel fusion of the geometry and photometric texture modalities. Through experiments conducted on two application scenarios, namely, 3D texture retrieval and 3D face recognition, we assess the effectiveness of the proposed solution with respect to state of the art approaches.
3D MESH MATCHING USING SURFACE DESCRIPTOR AND INTEGER LINEAR PROGRAMMING
The widespread of 3D shapes nowadays, gained it huge importance in several fields like computer vision, engineering, image processing, and many others. Its main challenge is the representation of these shapes and projecting them into canonical features referred to as descriptors. The necessity of them appears in different tasks like classification, retrieval, and matching, where they considered as the main step in what follows. Moreover, the matching problem is the core of all other tasks. This is why in this paper we propose a graph matching problem to find a one-to-one correspondence between models, it's obviously known as the NPhard problem. So, a novel compact feature vector to represent our 3D models is extracted, combining several geometric representative curvatures, it's simple in complexity computational, yet powerful discriminating in the sense of affine transformations. The 3D surface is modeled as an undirected weighted graph, with the Gaussian kernel as a weight function. Integer Linear Programming is used in order to segment our meshes into regions, where we maximized the modularity between vertices, these regions are represented by a single
Multi-Scale Surface Descriptors
IEEE Transactions on Visualization and Computer Graphics, 2009
Local shape descriptors compactly characterize regions of a surface, and have been applied to tasks in visualization, shape matching, and analysis. Classically, curvature has be used as a shape descriptor; however, this differential property characterizes only an infinitesimal neighborhood. In this paper, we provide shape descriptors for surface meshes designed to be multi-scale, that is, capable of characterizing regions of varying size. These descriptors capture statistically the shape of a neighborhood around a central point by fitting a quadratic surface. They therefore mimic differential curvature, are efficient to compute, and encode anisotropy. We show how simple variants of mesh operations can be used to compute the descriptors without resorting to expensive parameterizations, and additionally provide a statistical approximation for reduced computational cost. We show how these descriptors apply to a number of uses in visualization, analysis, and matching of surfaces, particularly to tasks in protein surface analysis.
Feature detection for surface meshes
Proceedings of 8th international conference on …, 2002
Computer simulations of complex systems involve sophisticated meshing tech-niques, including mesh smoothing, adaptive mesh refinement, mesh motion, and data transfer between disparate meshes. Geometric features, such as ridges and corners, frequently require special ...
Matching with Surface Shape Signatures
Object identification by matching is a central problem in computer vision. A major issue that any object matching method must address is the ability to correctly match an object to its model when only a partial view of the object is visible due to occlusion or shadows (or any other reason). In this paper we introduce surface boundary signatures as an extension to our surface signature formulation. Boundary signatures are surface feature vectors that reflect the probability of occurrence of a surface boundary feature. We introduce four types of surface boundary signatures; The Angle Boundary Signature, the Curvature Boundary Signature, the Distance Boundary Signature and the Parameter Boundary Signature that are based on the relative orientation of boundary points as well as the amount of bending in the boundary. Testing with completely visible objects have shown high rates of matching success using boundary features. Tests were performed on 135 test objects which resulted in matching success rates of up to 92%. The most influential boundary signatures were found to be S DB and S PB , while the least influential was found to be S AB . Preliminary results with partial visible objects have just started and are expected to produce good results.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
AbstractÐThis paper introduces a new free-form surface representation scheme for the purpose of fast and accurate registration and matching. Accurate registration of surfaces is a common task in computer vision. The proposed representation scheme captures the surface curvature information (seen from certain points) and produces images, called ªsurface signatures,º at these points. Matching signatures of different surfaces enables the recovery of the transformation parameters between these surfaces. We propose using template matching to compare the signature images. To enable partial matching, another criterion, the overlap ratio is used. This representation scheme can be used as a global representation of the surface as well as a local one and performs near real-time registration. We show that the signature representation can be used to recover scaling transformation as well as matching objects in 3D scenes in the presence of clutter and occlusion. Applications presented include: free-form object matching, multimodal medical volumes registration, and dental teeth reconstruction from intraoral images.
3d model matching with viewpoint-invariant patches (vip)
2008
Abstract The robust alignment of images and scenes seen from widely different viewpoints is an important challenge for camera and scene reconstruction. This paper introduces a novel class of viewpoint independent local features for robust registration and novel algorithms to use the rich information of the new features for 3D scene alignment and large scale scene reconstruction. The key point of our approach consists of leveraging local shape information for the extraction of an invariant feature descriptor.
Unique Signatures of Histograms for Local Surface Description
This paper deals with local 3D descriptors for surface matching. First, we categorize existing methods into two classes: Signatures and Histograms. Then, by discussion and experiments alike, we point out the key issues of uniqueness and repeatability of the local reference frame. Based on these observations, we formulate a novel comprehensive proposal for surface representation, which encompasses a new unique and repeatable local reference frame as well as a new 3D descriptor. The latter lays at the intersection between Signatures and Histograms, so as to possibly achieve a better balance between descriptiveness and robustness. Experiments on publicly available datasets as well as on range scans obtained with Spacetime Stereo provide a thorough validation of our proposal.