scholarly journals TightCap: 3D Human Shape Capture with Clothing Tightness Field

2022 ◽  
Vol 41 (1) ◽  
pp. 1-17
Author(s):  
Xin Chen ◽  
Anqi Pang ◽  
Wei Yang ◽  
Peihao Wang ◽  
Lan Xu ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Ground Truth ◽  
Data Driven ◽  
Optimization Scheme ◽  
High Quality ◽  
3D Scan ◽  
Multi Stage ◽  
Geometry Image

In this article, we present TightCap, a data-driven scheme to capture both the human shape and dressed garments accurately with only a single three-dimensional (3D) human scan, which enables numerous applications such as virtual try-on, biometrics, and body evaluation. To break the severe variations of the human poses and garments, we propose to model the clothing tightness field—the displacements from the garments to the human shape implicitly in the global UV texturing domain. To this end, we utilize an enhanced statistical human template and an effective multi-stage alignment scheme to map the 3D scan into a hybrid 2D geometry image. Based on this 2D representation, we propose a novel framework to predict clothing tightness field via a novel tightness formulation, as well as an effective optimization scheme to further reconstruct multi-layer human shape and garments under various clothing categories and human postures. We further propose a new clothing tightness dataset of human scans with a large variety of clothing styles, poses, and corresponding ground-truth human shapes to stimulate further research. Extensive experiments demonstrate the effectiveness of our TightCap to achieve the high-quality human shape and dressed garments reconstruction, as well as the further applications for clothing segmentation, retargeting, and animation.

An experience of elaboration and implementation of systems of slag-forming mixtures mechanized feeding into CCM moulds

2020 ◽  
Vol 76 (10) ◽  
pp. 994-1003
Author(s):  
S. P. Eron’ko ◽  
M. Yu. Tkachev ◽  
E. V. Oshovskaya ◽  
B. I. Starodubtsev ◽  
S. V. Mechik
Keyword(s):  
Economic Effect ◽  
Three Dimensional ◽  
Movable Part ◽  
High Quality ◽  
Working Zone ◽  
Fine Material ◽  
Mixing Chamber ◽  
Field Samples ◽  
Technical Solutions ◽  
Feeding Systems

Effective application of slag-forming mixtures (SFM), being fed into continuous castingg machine (CCM) moulds, depends on their even distribution on the melt surface. Manual feeding of the SFM which is widely usedd does not provide this condition, resulting in the necessity to actualize the work to elaborate systems of SFM mechanized feedingg into moulds of various types CCM. A concept of the designing of a system of SFM feeding into CCM moulds presented with the ratte strictly correspondent to the casting speed and providing formation of an even layer of fine material of given thickness on the whoole surface of liquid steel. The proposed methods of designing of the SFM mechanized feeding systems based on three-dimensional computer simulation with the subsequent verification of the correctness of the adopted technical solutions on field samples. Informattion is presented on the design features of the adjusted facilities intended for continuous supply of finely granulated and powder mixtuures on metal mirror in moulds at the production of high-quality billets, blooms and slabs. Variants of mechanical and pneumo-mechaanical SFM supply elaborated. At the mechanical supply the fine material from the feeding hopper is moved at a adjusted distance bby a rigid horizontally located screw. At the pneumo-mechanical supply the metered doze of the granular mixture is delivered by a sshort vertical screw, the lower part of which is located in the mixing chamber attached from below to the hopper and equipped with ann ejector serving for pneumatic supply of the SFM in a stream of transporting gas. It was proposed to use flexible spiral screws in the ffuture facilities of mechanical SFM feeding. It will enable to eliminate the restrictions stipulated by the lack of free surface for locatiion of the facility in the working zone of the tundish, as well as to decrease significantly the mass of its movable part and to decreaase the necessary power of the carriage moving mechanism driver. The novelty of the proposed technical solutions is protected by thhree patents. The reduction of 10–15% in the consumption of slag-forming mixtures during the transition from manual to mechanizeed feeding confirmed. The resulting economic effect from the implementation of technical development enables to recoup the costs inncurred within 8–10 months.

scholarly journals Data-Driven Intelligent 3D Surface Measurement in Smart Manufacturing: Review and Outlook

Machines ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 13
Author(s):  
Yuhang Yang ◽  
Zhiqiao Dong ◽  
Yuquan Meng ◽  
Chenhui Shao
Keyword(s):  
High Resolution ◽  
High Performance ◽  
Sampling Design ◽  
Three Dimensional ◽  
Measurement Data ◽  
Data Driven ◽  
Surface Measurement ◽  
Smart Manufacturing ◽  
Future Research ◽  
3D Surface

High-fidelity characterization and effective monitoring of spatial and spatiotemporal processes are crucial for high-performance quality control of many manufacturing processes and systems in the era of smart manufacturing. Although the recent development in measurement technologies has made it possible to acquire high-resolution three-dimensional (3D) surface measurement data, it is generally expensive and time-consuming to use such technologies in real-world production settings. Data-driven approaches that stem from statistics and machine learning can potentially enable intelligent, cost-effective surface measurement and thus allow manufacturers to use high-resolution surface data for better decision-making without introducing substantial production cost induced by data acquisition. Among these methods, spatial and spatiotemporal interpolation techniques can draw inferences about unmeasured locations on a surface using the measurement of other locations, thus decreasing the measurement cost and time. However, interpolation methods are very sensitive to the availability of measurement data, and their performances largely depend on the measurement scheme or the sampling design, i.e., how to allocate measurement efforts. As such, sampling design is considered to be another important field that enables intelligent surface measurement. This paper reviews and summarizes the state-of-the-art research in interpolation and sampling design for surface measurement in varied manufacturing applications. Research gaps and future research directions are also identified and can serve as a fundamental guideline to industrial practitioners and researchers for future studies in these areas.

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

scholarly journals Data-driven RANS closures for three-dimensional flows around bluff bodies

2021 ◽  
pp. 104997
Author(s):  
Jasper P. Huijing ◽  
Richard P. Dwight ◽  
Martin Schmelzer
Keyword(s):  
Three Dimensional ◽  
Data Driven ◽  
Bluff Bodies

scholarly journals A dataset on affiliation of venture capitalists in China between 2000 and 2016

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Jin Chen ◽  
Tianyuan Chen ◽  
Yifei Song ◽  
Bin Hao ◽  
Ling Ma
Keyword(s):  
Data Sources ◽  
Venture Capitalists ◽  
High Quality ◽  
Public Agency ◽  
Multiple Data Sources ◽  
Multiple Data ◽  
Multi Stage ◽  
The World ◽  
Prior Literature ◽  
Innovation And Entrepreneurship

AbstractPrior literature emphasizes the distinct roles of differently affiliated venture capitalists (VCs) in nurturing innovation and entrepreneurship. Although China has become the second largest VC market in the world, the unavailability of high-quality datasets on VC affiliation in China’s market hinders such research efforts. To fill up this important gap, we compiled a new panel dataset of VC affiliation in China’s market from multiple data sources. Specifically, we drew on a list of 6,553 VCs that have invested in China between 2000 and 2016 from CVSource database, collected VC’s shareholder information from public sources, and developed a multi-stage procedure to label each VC as the following types: GVC (public agency-affiliated, state-owned enterprise-affiliated), CVC (corporate VC), IVC (independent VC), BVC (bank-affiliated VC), FVC (financial/non-bank-affiliated VC), UVC (university endowment/spin-out unit), and PenVC (pension-affiliated VC). We also denoted whether a VC has foreign background. This dataset helps researchers conduct more nuanced investigations into the investment behaviors of different VCs and their distinct impacts on innovation and entrepreneurship in China’s context.

scholarly journals The fossil record of whip spiders: the past of Amblypygi

PalZ ◽  
2021 ◽  
Author(s):  
Carolin Haug ◽  
Joachim T. Haug
Keyword(s):  
Fossil Record ◽  
3D Imaging ◽  
Three Dimensional ◽  
Dorsal Shield ◽  
Stereo Images ◽  
Geological Time ◽  
High Quality ◽  
The Past ◽  
Over Time

AbstractWhip spiders (Amblypygi), as their name suggests, resemble spiders (Araneae) in some aspects, but differ from them by their heart-shaped (prosomal) dorsal shield, their prominent grasping pedipalps, and their subsequent elongate pair of feeler appendages. The oldest possible occurrences of whip spiders, represented by cuticle fragments, date back to the Devonian (c. 385 mya), but (almost) complete fossils are known from the Carboniferous (c. 300 mya) onwards. The fossils include specimens preserved on slabs or in nodules (Carboniferous, Cretaceous) as well as specimens preserved in amber (Cretaceous, Eocene, Miocene). We review here all fossil whip spider specimens, figure most of them as interpretative drawings or with high-quality photographs including 3D imaging (stereo images) to make the three-dimensional relief of the specimens visible. Furthermore, we amend the list by two new specimens (resulting in 37 in total). The fossil specimens as well as modern whip spiders were measured to analyse possible changes in morphology over time. In general, the shield appears to have become relatively broader and the pedipalps and walking appendages have become more elongate over geological time. The morphological details are discussed in an evolutionary framework and in comparison with results from earlier studies.

THE VISIBLE ANIMAL PROJECT: A THREE-DIMENSIONAL, DIGITAL DATABASE FOR HIGH QUALITY THREE-DIMENSIONAL RECONSTRUCTIONS

1999 ◽  
Vol 40 (6) ◽  
pp. 611-616 ◽  
Author(s):  
Peter BOTtcher ◽  
Johann Maierl ◽  
Thomas Schiemann ◽  
Christian Glaser ◽  
Renate Weller ◽  
...  
Keyword(s):  
Three Dimensional ◽  
High Quality ◽  
Digital Database

How to turn managers into data-driven decision makers

2019 ◽  
Vol 25 (3) ◽  
pp. 553-578 ◽  
Author(s):  
Kevin Daniel André Carillo ◽  
Nadine Galy ◽  
Cameron Guthrie ◽  
Anne Vanhems
Keyword(s):  
Measurement Instrument ◽  
Data Driven ◽  
Business Analytics ◽  
Business World ◽  
Content Type ◽  
Multi Stage ◽  
Attitudes Toward Statistics ◽  
Attitude Toward Business ◽  
Professional Contexts ◽  
The Way

Purpose The purpose of this paper is to emphasize the need to engender a positive attitude toward business analytics in order for firms to more effectively transform into data-driven businesses, and for business schools to better prepare future managers. Design/methodology/approach This paper develops and validates a measurement instrument that captures the attitude toward business statistics, the foundation of business analytics. A multi-stage approach is implemented and the validation is conducted with a sample of 311 students from a business school. Findings The instrument has strong psychometric properties. It is designed so that it can be easily extrapolated to professional contexts and extended to the entire domain of business analytics. Research limitations/implications As the advent of a data-driven business world will impact the way organizations function and the way individuals think, work, communicate and interact, it is crucial to engage a transdisciplinary dialogue among domains that have the expertise to help train and transform current and future professionals. Practical implications The contribution provides educators and organizations with a means to measure and monitor attitudes toward statistics, the most anxiogenic component of business analytics. This is a first step in monitoring and developing an analytics mindset in both managers and students. Originality/value By demonstrating how the advent of the data-driven business era is transforming the DNA and functioning of organizations, this paper highlights the key importance of changing managers’ and all employees’ (to a lesser extent) mindset and way of thinking.

scholarly journals Assessing biases, relaxing moralism: On ground-truthing practices in machine learning design and application

2021 ◽  
Vol 8 (1) ◽  
pp. 205395172110135
Author(s):  
Florian Jaton
Keyword(s):  
Machine Learning ◽  
William James ◽  
A Priori ◽  
Learning Algorithms ◽  
Three Dimensional ◽  
Ground Truth ◽  
Machine Learning Algorithms ◽  
Ground Truthing ◽  
Set Up ◽  
The Moment

This theoretical paper considers the morality of machine learning algorithms and systems in the light of the biases that ground their correctness. It begins by presenting biases not as a priori negative entities but as contingent external referents—often gathered in benchmarked repositories called ground-truth datasets—that define what needs to be learned and allow for performance measures. I then argue that ground-truth datasets and their concomitant practices—that fundamentally involve establishing biases to enable learning procedures—can be described by their respective morality, here defined as the more or less accounted experience of hesitation when faced with what pragmatist philosopher William James called “genuine options”—that is, choices to be made in the heat of the moment that engage different possible futures. I then stress three constitutive dimensions of this pragmatist morality, as far as ground-truthing practices are concerned: (I) the definition of the problem to be solved (problematization), (II) the identification of the data to be collected and set up (databasing), and (III) the qualification of the targets to be learned (labeling). I finally suggest that this three-dimensional conceptual space can be used to map machine learning algorithmic projects in terms of the morality of their respective and constitutive ground-truthing practices. Such techno-moral graphs may, in turn, serve as equipment for greater governance of machine learning algorithms and systems.

Sign in / Sign up

Export Citation Format

Share Document