scholarly journals Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images

2021 ◽  
Vol 15 ◽  
Author(s):  
Weilong Peng ◽  
Yong Su ◽  
Keke Tang ◽  
Chao Xu ◽  
Zhiyong Feng ◽  
...  
Keyword(s):  
Geometric Modeling ◽  
Surface Deformation ◽  
Low Rank ◽  
Geometric Optics ◽  
High Quality ◽  
Face Surface ◽  
B Spline ◽  
Parameter Domain ◽  
Face Reconstruction ◽  
Spline Parameter

A number of methods have been proposed for face reconstruction from single/multiple image(s). However, it is still a challenge to do reconstruction for limited number of wild images, in which there exists complex different imaging conditions, various face appearance, and limited number of high-quality images. And most current mesh model based methods cannot generate high-quality face model because of the local mapping deviation in geometric optics and distortion error brought by discrete differential operation. In this paper, accurate geometrical consistency modeling on B-spline parameter domain is proposed to reconstruct high-quality face surface from the various images. The modeling is completely consistent with the law of geometric optics, and B-spline reduces the distortion during surface deformation. In our method, 0th- and 1st-order consistency of stereo are formulated based on low-rank texture structures and local normals, respectively, to approach the pinpoint geometric modeling for face reconstruction. A practical solution combining the two consistency as well as an iterative algorithm is proposed to optimize high-detailed B-spline face effectively. Extensive empirical evaluations on synthetic data and unconstrained data are conducted, and the experimental results demonstrate the effectiveness of our method on challenging scenario, e.g., limited number of images with different head poses, illuminations, and expressions.

scholarly journals Hierarchical Genetic Algorithm for B-Spline Surface Approximation of Smooth Explicit Data

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
C. H. Garcia-Capulin ◽  
F. J. Cuevas ◽  
G. Trejo-Caballero ◽  
H. Rostro-Gonzalez
Keyword(s):  
Genetic Algorithm ◽  
Geometric Modeling ◽  
Data Set ◽  
Surface Approximation ◽  
B Spline ◽  
B Splines ◽  
Spline Surface ◽  
Spline Surfaces ◽  
Surface Dimension ◽  
Hierarchical Genetic Algorithm

B-spline surface approximation has been widely used in many applications such as CAD, medical imaging, reverse engineering, and geometric modeling. Given a data set of measures, the surface approximation aims to find a surface that optimally fits the data set. One of the main problems associated with surface approximation by B-splines is the adequate selection of the number and location of the knots, as well as the solution of the system of equations generated by tensor product spline surfaces. In this work, we use a hierarchical genetic algorithm (HGA) to tackle the B-spline surface approximation of smooth explicit data. The proposed approach is based on a novel hierarchical gene structure for the chromosomal representation, which allows us to determine the number and location of the knots for each surface dimension and the B-spline coefficients simultaneously. The method is fully based on genetic algorithms and does not require subjective parameters like smooth factor or knot locations to perform the solution. In order to validate the efficacy of the proposed approach, simulation results from several tests on smooth surfaces and comparison with a successful method have been included.

scholarly journals Geometric Modeling Using New Cubic Trigonometric B-Spline Functions with Shape Parameter

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2102
Author(s):  
Abdul Majeed ◽  
Muhammad Abbas ◽  
Faiza Qayyum ◽  
Kenjiro T. Miura ◽  
Md Yushalify Misro ◽  
...  
Keyword(s):  
Geometric Modeling ◽  
Shape Parameter ◽  
3D Models ◽  
Basis Functions ◽  
Shape Parameters ◽  
B Spline ◽  
Spline Curves ◽  
Spline Basis ◽  
Cubic Polynomial ◽  
2D And 3D

Trigonometric B-spline curves with shape parameters are equally important and useful for modeling in Computer-Aided Geometric Design (CAGD) like classical B-spline curves. This paper introduces the cubic polynomial and rational cubic B-spline curves using new cubic basis functions with shape parameter ξ∈[0,4]. All geometric characteristics of the proposed Trigonometric B-spline curves are similar to the classical B-spline, but the shape-adjustable is additional quality that the classical B-spline curves does not hold. The properties of these bases are similar to classical B-spline basis and have been delineated. Furthermore, uniform and non-uniform rational B-spline basis are also presented. C3 and C5 continuities for trigonometric B-spline basis and C3 continuities for rational basis are derived. In order to legitimize our proposed scheme for both basis, floating and periodic curves are constructed. 2D and 3D models are also constructed using proposed curves.

Filling N-Sided Holes Using Trimmed B-Spline Surfaces

2012 ◽  
Author(s):  
Xiaodong Liu
Keyword(s):  
Energy Minimization ◽  
Control Points ◽  
Variational Technique ◽  
High Quality ◽  
B Spline ◽  
Cad Systems ◽  
Spline Surface ◽  
Spline Surfaces ◽  
Key Issues ◽  
Complex Constraints

Using one single trimmed B-Spline surface to fill an n-sided hole is a much desired operation in CAD, but few papers have addressed this issue. The paper presents the method of using trimmed B-Spline surfaces to fill n-sided holes based on energy minimization or variational technique. The method is efficient and robust, and takes less than one second to fill n-sided holes with high quality B-Spline surfaces under complex constraints. As the foundation of filling n-sided holes, some key issues on variational B-Spline technique are also discussed. The variational technique discussed is significantly much more efficient and powerful than previous research, and the result is very accurate to satisfy CAD systems’ high-precision requirements. We demonstrate that, without any pre-calculation, the discussed technique is efficient enough to solve a B-Spline surface with up to 20,000 control points in real time while satisfying an arbitrary combination of point and curve constraints.

Blending principles of petroleum coke and low-rank coal to prepare high quality slurries

2021 ◽  
pp. 1-18
Author(s):  
Dongmei Lv ◽  
Huijun Wu ◽  
Jianzhang Niu ◽  
Yiyao Cheng ◽  
Jing Li ◽  
...  
Keyword(s):  
Petroleum Coke ◽  
Low Rank ◽  
Low Rank Coal ◽  
High Quality

scholarly journals Features of Modelling the Highway Route Using a Single Spatial “B-spline” Curve of a High Degree

2019 ◽  
Author(s):  
Марат Абдуллин ◽  
Marat Abdullin ◽  
Антон Глазычев ◽  
Anton Glazychev ◽  
Валериян Муфтеев ◽  
...  
Keyword(s):  
Road Safety ◽  
Geometric Modeling ◽  
High Quality ◽  
Comparative Testing ◽  
The Road ◽  
Cad System ◽  
R Program ◽  
Road Geometry ◽  
Speed Mode ◽  
High Degree

The Russian road system is an important part of the transport structure. High wear, difficulty in driving, and a decrease in road safety lead to a decrease in the number of transportation in the country. In addition, imperfect road geometry does not allow increasing the speed mode on the highway. This article presents the features of the route simulation, taking into account the above disadvantages. The geometric aspects of the design of the road route in the plan are considered. Disadvantages and limitations of existing tracing methods are shown. The task is to select and adapt a geometric modeling program to solve the problems of high-quality road tracing in the plan. The «FairCurveModeler» program is proposed for geometric modelling of high quality curves according to smoothness criteria. A comparative testing of the methods of the «FairCurveModele»r program with the methods of the top CAD system «NX12» is carried out. The results obtained allow for a smoother construction of curves in the design of automobile and other routes.

scholarly journals Detail 3D Face Reconstruction Based on 3DMM and Displacement Map

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Tianping Li ◽  
Hongxin Xu ◽  
Hua Zhang ◽  
Honglin Wan
Keyword(s):  
Texture Features ◽  
Facial Feature ◽  
Reconstruction Method ◽  
3D Face Reconstruction ◽  
Face Surface ◽  
Face Model ◽  
Face Reconstruction ◽  
Adversarial Network ◽  
Face Features ◽  
The Face

How to accurately reconstruct the 3D model human face is a challenge issue in the computer vision. Due to the complexity of face reconstruction and diversity of face features, most existing methods are aimed at reconstructing a smooth face model with ignoring face details. In this paper a novel deep learning-based face reconstruction method is proposed. It contains two modules: initial face reconstruction and face details synthesis. In the initial face reconstruction module, a neural network is used to detect the facial feature points and the angle of the pose face, and 3D Morphable Model (3DMM) is used to reconstruct the rough shape of the face model. In the face detail synthesis module, Conditional Generation Adversarial Network (CGAN) is used to synthesize the displacement map. The map provides texture features to render to the face surface reconstruction, so as to reflect the face details. Our proposal is evaluated by Facescape dataset in experiments and achieved better performance than other current methods.

Parametric Design and Optimization of Sailing Yachts

1999 ◽  
Author(s):  
Stefan Harries ◽  
Claus Abt
Keyword(s):  
Geometric Modeling ◽  
Parametric Design ◽  
Generation Process ◽  
B Spline ◽  
Design And Optimization ◽  
Spline Curves ◽  
Design Variables ◽  
Hull Forms ◽  
High Level ◽  
Important Form

A new and flexible method for the geometric modeling of ship hull forms is presented. The underlying methodology is the parametric design of B-spline curves and surfaces. Important form parameters like displacement, center of buoyancy, waterplane area, center of flotation etc. are utilized as high-level descriptors of the intended shapes. Instead of interactively manipulating B-spline vertices, the generation process is viewed as a constrained optimization problem where fairness measures are applied as objective functions, vertices are treated as design variables and form parameters are preserved as equality constraints - making the approach a novelty in B­spline modeling. The new design methodology is discussed and mathematical principles are outlined. Examples are given to demonstrate the applicability of the parametric approach. They include the design of a 33ft IMS yacht with focus on the bare hull without rudder and keel.

Optimal design of an hydrogeophysical monitoring system of compacting volcanic aquifers (Tenerife Island)

2021 ◽  
Author(s):  
Pablo J. Gonzalez ◽  
Maria Charco ◽  
Antonio Eff-Darwich ◽  
Anthony Lamur ◽  
Rayco Marrero ◽  
...  
Keyword(s):  
Time Series ◽  
Network Design ◽  
Water Table ◽  
Land Subsidence ◽  
Penalty Function ◽  
Surface Deformation ◽  
Low Rank ◽  
Tenerife Island ◽  
Compaction Processes

<p>Groundwater in volcanic islands is usually the main source of freshwater, and it is essential for sustainable development. In Tenerife Island, groundwater extraction occurs by drilling horizontal water tunnels, called water galleries, as well as numerous coastal wells. Since around 1900, but especially since the 1960s, hundreds of water tunnels have been drilled for agriculture and freshwater supply. This has resulted in a sustained extraction of groundwater larger than the natural recharge, leading to a general water table decline, locally up to 200 m of down drop. Since 2000, satellite radar interferometry (InSAR) applied to measure surface deformation has located several subsidence bowls (e.g., Fernandez et al., 2009). The localized surface deformation patterns have been correlated with water table changes and hence aquifer compaction. However, no further investigations have been carried out to confirm which characteristics (chemical composition, texture, porous network, alterations, etc.) of the volcanic materials can control compaction process, and to which extent porous volcanic units, the most abundant material in Tenerife, can compact to explain the observed surface deformation. This lack of knowledge might affect the effectiveness of water management policies.</p><p>To investigate the compaction processes affecting the volcanic aquifer, we propose to set up a passive hydrogeophysical monitoring network composed of geodetic and seismological instruments. However, considering logistic constrains it is desirable to have as low as possible number of observation sites, whist maximizing the detection and characterization of the aquifer dynamics. Here, we explore different network configurations to maximize the spatial and temporal characterization of the compaction processes using machine learning methods (low-rank matrix techniques). We pose the network design as an optimization process with the aim to parsimoniously have as fewer as possible ground station sites, and have a low error on reconstructing spatiotemporal land subsidence observations. Land subsidence rates were estimated using Sentinel-1 radar interferometric observations from October 2014 to December 2020. This method allows for an optimal network configuration, with respect to the dual penalty function, which facilitate the decision making. Nevertheless, this type of network design should be regarded as proposals because some station site conditions are a priori unknown. Although, one could modify the penalty function to optimize the network considering additional types of information, e.g., geological materials, groundwater table time series, etc.</p><p>Fernandez, J., et al. (2009), Gravity-driven deformation of Tenerife measured by InSAR time series analysis, Geophys. Res. Lett., 36, L04306, doi:10.1029/2008GL036920.</p>

Low Latency and High Quality Two-Stage Human-Voice-Enhancement System for a Hose-Shaped Rescue Robot

2017 ◽  
Vol 29 (1) ◽  
pp. 198-212 ◽  
Author(s):  
Yoshiaki Bando ◽  
◽  
Hiroshi Saruwatari ◽  
Nobutaka Ono ◽  
Shoji Makino ◽  
...  
Keyword(s):  
Microphone Array ◽  
Principal Component ◽  
Matrix Analysis ◽  
Low Rank ◽  
Low Latency ◽  
High Quality ◽  
Two Stage ◽  
Rescue Robot ◽  
Human Voice ◽  
Rank Matrix

[abstFig src='/00290001/19.jpg' width='300' text='Human-voice enhancement system for a hose-shaped robot' ] This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphone-equipped hose-shaped robot is used to search for a victim under a collapsed building, human-voice enhancement is crucial because the sound captured by a microphone array is contaminated by the ego-noise of the robot. For achieving both low latency and high quality, our system combines online and offline human-voice enhancement, providingan overview first and then details on demand. The online enhancement is used for searching for a victim in real time, while the offline one facilitates scrutiny by listening to highly enhanced human voices. Our online enhancement is based on an online robust principal component analysis, and our offline enhancement is based on an independent low-rank matrix analysis. The two enhancement methods are integrated with Robot Operating System (ROS). Experimental results showed that both the online and offline enhancement methods outperformed conventional methods.

Sign in / Sign up

Export Citation Format

Share Document