Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point or voxel based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction. In this article, we present a method using on-the-fly implicits of Hermite Radial Basis Functions (HRBFs) as a continuous surface representation for camera tracking in an existing RGB-D fusion framework. Furthermore, curvature estimation and confidence evaluation are coherently derived from the inherent surface properties of the on-the-fly HRBF implicits, which are devoted to a data fusion with better quality. We argue that our continuous but on-the-fly surface representation can effectively mitigate the impact of noise with its robustness and constrain the reconstruction with inherent surface smoothness when being compared with discrete representations. Experimental results on various real-world and synthetic datasets demonstrate that our HRBF-fusion outperforms the state-of-the-art approaches in terms of tracking robustness and reconstruction accuracy.

3-D pose estimation for texture-less objects remains a challenging problem. Previous works either focus on a template matching method to find the nearest template as a candidate, or construct a Hough forest, which utilizes the offset of patches to vote for the object location and pose. By contrast, in this paper, we propose a comprehensive framework to directly regress 3-D poses for the candidates, in which a convolutional neural network-based triplet network is trained to extract discriminating features from the binary images. To make the features suitable for the regression task, a pose-guided method and a regression constraint are employed with the constructed triplet network. We show that the constraint reaches the goal of creating the correlation between the features and 3-D poses. Once the expected features are obtained, the object pose could be efficiently regressed, by training a regression network with a simple structure. For symmetric objects, depth images are treated as an additional channel to feed the triplet network. Experiments on the LineMOD and our own datasets demonstrate our method with high regression precision and efficiency.

Feature extraction is one of key techniques in feature-based reverse engineering. In this paper, a novel methodology of feature extraction is presented based on collected data points of mechanical part. Firstly, regular surface is used to model individual segmented data points patch based on maximum likelihood estimate. And then the resulting surfaces are used to determine the feature primitives approximately and afterwards extract the feature parameters. Finally, Mahalanobis distance is used to evaluate the error between feature primitives and the resulting surfaces, and feature is positioned optimally utilizing a similarity transformation which minimizes the error.

Polygon meshes are ubiquitous in geometric model representation. Segmentation and parametrization of arbitrary polygon meshes are closely related and crucial in many applications. The primary aim of this paper is to find an efficient and practical way to segment and resample geometric models. We automatically generate a triangular patch network by a simplification algorithm. A simple and cheap algorithm is put forward for calculating the approximate shortest path between two points on triangle mesh, which serves for patch boundary of the segmentation. A set of interactive tools provides users with more freedom to control the final segmentation. The mesh parametrization algorithm in this paper can efficiently map a disk topology mesh surface to an isomorphic planar mesh without fixing boundary points. Ways are also provided to map the planar mesh with natural boundary to specific parameter domain, e.g. square or circular domain. The proposed method can be used in diverse applications, such as patchwise freeform surfaces fitting, multi-resolution analysis, texture mapping, remeshing of arbitrary polygon mesh and blank design of sheet metal forming. Examples are included to demonstrate the efficiency and quality of our method.