The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resolution – but complete – output. To this end, we introduce a 3D-Encoder-Predictor Network (3D-EPN) which is composed of 3D convolutional layers. The network is...
Artificial cell sheet is utilized as a useful method for tissue engineering. We proposed a novel approach to fabricate the Ca-alginate gel sheet embedded liver cells to mimic the liver lobule tissue. Ca-alginate sheet with hepatic lobule shaped pattern was firstly deposited on a micro-electrode device based on the electrodeposition method. Viability of embedded cells was checked to be maintained more...
In this paper, we propose a novel multi-center convolutional neural network for unconstrained face alignment. To utilize structural correlations among different facial landmarks, we determine several clusters based on their spatial position. We pre-train our network to learn generic feature representations. We further fine-tune the pre-trained model to emphasize on locating a certain cluster of landmarks...
In this work we address the problem of analyzing video sequences and representing meaningful space-time points of interest. We base our work on the 3D shearlet transform. In particular, we exploit the relation between coefficients with similar shearings to build a local representation which turns out to be really informative to understand the local spatio-temporal characteristics of the points that...
Constrained Local Models (CLMs) are a well-established family of methods for facial landmark detection. However, they have recently fallen out of favor to cascaded regressionbased approaches. This is in part due to the inability of existing CLM local detectors to model the very complex individual landmark appearance that is affected by expression, illumination, facial hair, makeup, and accessories...
In this work the notion of automated risk assessment for 3D scenes is addressed. Using deep learning techniques smart enabled homes and domestic robots can be equipped with the functionality to detect, draw attention to, or mitigate hazards in a given scene. We extend an existing risk estimation framework that incorporates physics and shape descriptors by introducing a novel CNN architecture allowing...
Nowadays, cells are commonly used for predicting whether the drug compounds will be effective and safe in human. The response of cell groups was usually analyzed, instead of single cell. However, individual cells within the same population even shows various characteristics. Understanding this heterogeneity is critical to studying how effective therapies will be in the clinic. Therefore, highly efficient...
Augmented feedback has been shown to improve interaction in virtual environments and to facilitate motor learning. Recent studies proposed this type of feedback to guide users, to highlight specific areas or to help them to perform a specific task. They can follow a path, pass through specific waypoints or even mimic an avatar. However these approaches do not show the gap between learners' performance...
Three-dimensional surface reconstruction based on photometric stereo requires accurate positioning of the light source or estimation of the lighting parameters, which increases the complexity of the operation in experiments. Moreover, the actual light environment is composed of many kinds of complex optical components, and the accurate lighting parameters cannot be measured. In this paper, a reference...
we present a method based on a locally affineinvariant constraint for volumetric registration of 3D solid shapes. The core idea of this method is that an affine combination of the given point in 3D solid shapes that are directly connected to the given point, and the corresponding weight of each neighboring point can be obtained by the method of generalized least square. The input of our method is...
We present an approach to analyse near-field effects on nanostructured gold films by finite element simulations. The studied samples are formed by fabricating gold films near the percolation threshold and then applying laser damage. Resulting samples have complicated structures, which then was captured using scanning transmission electron microscopy (STEM) and the obtained dark field images are used...
This paper tackles the problem of reconstructing 3D human poses from 2D landmarks, which is still an ill-posed problem. A widely-used approach is active shape model (ASM) which considers an unknown 3D shape as a linear combination of predefined basis shapes. The existing methods often resolve an optimization problem to reckon the weights and viewpoints of basis shapes, but they could fall into a locally-optimal...
We present a novel global registration method for deformable objects captured using a single RGB-D camera. Our algorithm allows objects to undergo large non-rigid deformations, and achieves high quality results without constraining the actor's pose or camera motion. We compute the deformations of all the scans simultaneously by optimizing a global alignment problem to avoid the well-known loop closure...
Recent progress in sketch-based 3D shape retrieval creates a novel and user-friendly way to explore massive 3D shapes on the Internet. However, current methods on this topic rely on designing invariant features for both sketches and 3D shapes, or complex matching strategies. Therefore, they suffer from problems like arbitrary drawings and inconsistent viewpoints. To tackle this problem, we propose...
In this paper, a novel approach is presented to perform a deformable shape registration of workpiece geometries in robotic welding. Based on the free-form deformation (FFD) method, a surface-based extension FFDS is presented where the initial shape of the control points lattice corresponds to the shape of the surface to be deformed. A point-based registration is performed using the sum of least squares...
For accurate insertion by CT-guided robot, we need registration between the coordinate of robot and CT by calculating the section images. In this paper, we intended to develop the geometric marker for registration. The requirements are geometric shapes that the error of 3 DOF (yaw and pitch angles and a craniocaudal distance) between CT image and the marker can be calculated and the material is suitable...
A major challenge in visual highway traffic analytics is to disaggregate individual vehicles from clusters formed in dense traffic conditions. Here we introduce a data driven 3D generative reasoning method to tackle this segmentation problem. The method is comprised of offline (learning) and online (inference) stages. In the offline stage, we fit a mixture model for the prior distribution of vehicle...
Tangible physical maps couple physical landscape model with digital information and can become an invaluable asset for learning geography in an embodied way. The objective of this work is to create and evaluate an easily constructible 3D tangible map for elementary students. The main differentiations of our approach are two: a) we suggest a new interaction style on the map for learning geography purposes,...
We present a deep-learning-based approach to maximize the accuracy and reliability of vision-based fall detection and alert systems. The proposed approach utilizes a 3D convolutional neural network (3D-CNN) to analyze the continuous motion data obtained from depth cameras and exploits a data augmentation method to do away with overfitting. Our preliminary evaluation results demonstrate that it achieves...
This paper presents our novel algorithm for decoration points' segmentation with simple calculation in a two-dimensional domain. Our algorithm works for unorganized point clouds. It extracts the relationship between two adjacent sub-regions, which are derived from a single cross section of the point cloud. The cutting planes are defined by the Frenet frame of curve skeleton. In our method, angle-based...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.