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.
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image. Hitherto, the problem has been addressed through the application of canonical deep learning methods to regress from the image directly to the 3D shape and pose labels. These approaches, however, are problematic from two perspectives. First, they are minimizing the error between 3D shapes...
A 3D visible articulation system which utilizes audio-visual data to accurately simulate the 3D articulatory motion is developed in this paper. The 3D articulatory shapes are reconstructed from Magnetic Resonance Images (MRI). In order to synthesize accurate audio-visual results, articulatory parametric models are further developed and the Electromagnetic Articulography (EMA) data with synchronized...
This paper proposes a robust solution for accurate 3D hand pose estimation in the presence of an external object interacting with hands. Our main insight is that the shape of an object causes a configuration of the hand in the form of a hand grasp. Along this line, we simultaneously train deep neural networks using paired depth images. The object-oriented network learns functional grasps from an object...
We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes. Our method alternates between updating the shape and the semantic labels. In the geometry refinement step, the mesh is deformed with variational energy minimization, such that it simultaneously maximizes photo-consistency and the compatibility of the semantic segmentations across a set of calibrated...
Significant progress has been recently made in Non-Rigid Structure-from-Motion (NRSfM). However, existing methods do not handle poorly-textured surfaces that deform non-smoothly. These are nonetheless common occurrence in real-world applications. An important unanswered question is whether shading can be used to robustly handle these cases. Shading is complementary to motion because it constrains...
In this paper, a procedure based on three-dimension matrices is presented: it is the generalization of multiconductor cell analysis to any transmission line where the positions of all the active and passive conductors may change with continuity along their development. A meaningful example of this is given by three-core single lead-screened armoured cables where cores and armour wires are wound helically...
Despite increasing accessibility of the 3D scanning devices, acquisition of the 2D photographs is still more widely used method to capture human faces. However, many virtual scenarios require 3D representation of the human face. We present an automatic method of the human face reconstruction from a single frontal photograph. Our approach utilizes a database of the precomputed depth images, which we...
In this study, we investigated the operability of our multifunctional haptic device for teleoperation. The device has currently three modes which represent different control devices. The goal of our research is to determine a root position of the device relative to an operator to enable him to manipulate the device comfortably in all modes. The root position should be determined based on the operability...
This paper presents a modeling method for NPR hair composed of parametric 3D clumps. The clump parameters are not only for modifying a single clump but also for modifying all or large part of clumps similarly and simultaneously, and then a user can create a hairstyle only by adjusting the parameters. Our experiments show that even naive users can model a variety of hairstyles with little effort.
The paper is devoted to modeling of single-layer garments as developable median surfaces, modeled in the form of a thin supple shell. The products are modeled in Maple 9.5 and Embarcadero RAD Studio. The modelling of conical skirts considering seams is performed to demonstrate the space form of garments in the gravity field of elastic materials. Also the product aeroman is modelled which brings the...
This paper sets out and presents a new approach to determine the stroke volume of the artificial ventricle. The stroke volume of the chamber is one of the basic heart function parameters. For the artificial heart assist purpose, in the study this value is calculated based on the mapped shape of the flaccid membrane of the extracorporeal pneumatic heart assist pump. This is a continuation of the earlier...
The main contribution of this paper is the proposal of volume modeling of parathyroid gland. Multivariate generalized Gaussian distribution (Multivariate GGD) mixture is assumed. Random walk optimization algorithm is applied for the estimation of parameters. There are 800 synthetic test cases applied for the evaluation of algorithm properties. Example result for real SPECT data are also shown. The...
It is not only interesting to predict how an individual of a relatively young age will look in the future but also to reconstruct the facial appearance in the past during childhood. It can be even more desirable when different circumstances, behavior and lifestyle and their impacts on the facial shape appearance as a consequence are taken into account. Such may be applicable for many practical reasons...
Tail bits in the RESET process influence the distribution of resistive parameters, and will dramatically decrease the uniformity in high electric stimuli region. In this study, such phenomena can be explained as non-uniform distribution of defects in the insulating layer and high defects density in the bottleneck region of conductive filament (CF). Then departing from defects' distribution function,...
Used to describe the propagation of the electrical potential in heterogeneous cardiac tissue, the FitzHugh-Nagumo monodomain model has attracted numerous attentions to be analyzed. Due to the irregular profile of the cardiac tissue, there has been limitations for the numerical solution on the considered regular domains or approximate irregular domains, where the analytic solution could not be obtained...
In order to better learn the distributions of 2D and 3D faces and the mapping between them with limited training samples, a new 3D face reconstruction method based on progressive cascade regression is proposed. Firstly, it learns the mapping between 2D and 3D facial landmarks to estimate the initial 3D facial landmarks with a coupled space learning method. Secondly, a deformed space is constructed...
The mobile C-arm can be used for 2D and 3D X-ray imaging. The motion of 3D X-ray scanning may result in vibration of the C-arm, which will probably affect the image quality. It is very necessary to study the relationship between the vibration characteristics of the C-arm and scanning motion. In the paper, we made modal analysis of the mobile C-arm based on Solidworks, and obtain the initial 6 order...
Fluid dynamics simulation is often repeated while changing conditions, and therefore we need to compare a large amount of results. In order to compare results under different conditions, it is effective to overlap the streamlines generated from each condition in a single 3D space. Streamline is a curved line which represents a wind flow. This paper presents a technique to automatically select and...
3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful...
In this work, we present a novel method for capturing human body shape from a single scaled silhouette. We combine deep correlated features capturing different 2D views, and embedding spaces based on 3D cues in a novel convolutional neural network (CNN) based architecture. We first train a CNN to find a richer body shape representation space from pose invariant 3D human shape descriptors. Then, we...
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.