Joint PhD Degree Programme NTUTU Darmstadt

                             

This PhD programme is a joint collaboration between Nanyang Technological University (NTU, Singapore) and Technische Universität Darmstadt (TU Darmstadt, Germany). The programme offers opportunities to promising scientists and scholars to foster interactions between the three world class Universities in the area of interactive digital media. The principal areas of focus are Real-time Rendering, Virtual & Augmented Reality, Visual Analytics, Medical Computing,  Haptics, and Human-Computer Interaction.  The 4-years scholarships provided jointly by NTU and Fraunhofer IDM@NTU assume that the applicants become full-time PhD students of NTU and TU Darmstadt while having two supervisors - one from NTU and a co-supervisor from TU Darmstadt. The NTU students will spent one year of their project in TU Darmstadt in the co-supervisor's lab. TU Darmstadt students will be supported by TU Darmstadt PhD scholarships and also will need to spend one year at NTU in the co-supervisor's lab. The degree of Ph.D. with mention of this collaboration between NTU and TU Darmstadt will be delivered by the academic authorities of the institution where the student has successfully defended his/her oral defense. The Doctoral degree transcript will mention the name of the student, the thesis or research title, the doctoral degree specialization or discipline, the fact that there was an international joint supervision, the date of the oral defence.

The project topics have to be approved by the programme's Joint Admission Committee. Candidates may apply to either university which will host their project. The students accepted by the home university will also become graduate students of the partner university. For the projects hosted at NTU, the NTU research scholarship will be awarded to the successful candidates for four years (including the stipend and tuition fees). The third year of the NTU project will be spent in the partner university. TU Darmstadt-hosted projects will require their students to spend one year in NTU which will be the second year of the project.

The programme scholarships for the current NTU projects are provided by NTU and Fraunhofer IDM@NTU. Travel expenses while in TU Darmstadt are provided by Fraunhofer IDM@NTU.

FOR PhD APPLICANTS

PhD applicants have to contact first the programme coordinator Prof. Alexei Sourin assourin@ntu.edu.sg and email him their detailed CV with GPA, as well as proposed research topic and motivation to work on it. Upon initial approval by the programme coordinator, the applications have to be done according to the graduate admission procedures of the respective university. For applicants to NTU-hosted projects, good TOEFL and GRE scores are required, refer to the admission requirements. PhD student intakes in NTU are in September and January while in TU Darmstadt the PhD students can join the programme any time. The scholarships will be allocated when suitable projects are formed and applicant are approved by the universities, prospective supervisors and the Joint Admission Committee.

 

 

LIST OF THE PhD PROJECTS

 

NTU-based students:

 

Student: Mr. Zhengkun Yi , started in January 2013, 1 year attachment at TUD: March 2015 - April 2016. (Scholarship from Fraunhofer IDM@NTU)

NTU supervisor:Yilei ZHANG

TU Darmstadt co-supervisor: Jan PETERS

Topic: Biomimetic Tactile Sensing and Statistical Interpretation.

Abstract: The objective of the joint degrees Ph.D. project is to develop capabilities in biomimetic tactile signal generation and interpretation for IDM, including design and develop biomimetic tactile sensor as well as tactile signal modelling and interpretation with statistical machine learning. Just like sight, hearing, taste and smell, touch is widely utilized to interact with the surrounding environments. The sense of touch contributes substantially to the recognition of the shape and size of objects, and enables us to discriminate between surface textures, recognize and manipulate objects, etc., all of which have a variety of applications in robotics, minimal invasive surgery and manufacturing industries.

 

Student: Ms. Zhang Xingzi,started in August 2013, 1 year attachment at TUD: September 2015 - August 2016. (NTU Scholarship)

NTU supervisor: Alexei SOURIN

TU Darmstadt co-supervisor: Michael GOESELE

Topic: Image-driven Haptic Interaction

Abstract: We will replace visual rendering of 3D scenes with merely displaying their images while simulating haptic interaction with the scenes displayed in images as if they were 3D models provided for such interaction. These can be also images of real scenes (photographs or video) which photorealistic 3D modelling can be a challenge.  The haptic effects can be both derived from the image as well as obtained from the optional haptic models augmenting the image. These additional invisible models will be topologically collocated with the objects displayed in the image, as well as they will be able to provide haptic effects for the simulated phenomena which do not have any visual shape.

 

Student: Mr. Cui Jian, started in August 2013, 1 year attachment at TUD: September 2015 - August 2016. (NTU Scholarship)

NTU supervisor: Alexei SOURIN

TU Darmstadt co-supervisor: Dieter FELLNER

Topic: Hand-controlled Shape Modeling

Abstract: Using different hand tracking devices, to design and implement a set of robust and efficient interactive hand gestures suitable for various virtual engineering designs (virtual prototyping) and crafts (freeform shape modelling). To achieve multimodal hand tracking and interaction so that it will become possible to start modelling with one type of device and then seamlessly continue it using other type of hand tracking device. In contrast to commonly used polygon and voxel based modelling as well as various surface splines, to define models of the shapes to be created and manipulated with bare hands using mathematical functions (procedures) to achieve any desired level of detail and to be able to exchange models of the shapes across the internet since mathematical functions stored by their coefficients and parameters occupy very little space.

 

Student: Mr. Cheng Wentao, started in August 2013,1 year attachment at TUD: March 2016 - April 2017. (Scholarship from Fraunhofer IDM@NTU)

NTU supervisor: LIN Weisi

TU Darmstadt co-supervisor: Michael GOESELE

Topic: Human Perception Models for Real-Time Graphic Rendering

Abstract: How to speed up the rendering process for real-time computer graphics and animation is an important research problem, especially with the emerging scenario of mobile computing, where computation power and battery are scarce resources. To this aim, adaptive sampling can be performed, by varying the number of samples in the spatial-temporal light field according to certain criteria for visual contents (such as contrast of graphics in the existing algorithms) so that fewer samples are needed without quality loss of rendered quality image

 

Student: Mr. Huynh Ngoc Anh, started in January 2014, 1 year attachment at TUD: March 2016 - April 2017. (NTU Scholarship)

NTU supervisor: NG Wee Keong

TU Darmstadt co-supervisor: Dieter FELLNER, Joern KOHLHAMMER

Topic: Visual Analytics for Parameter Space Exploration in Cyber-Security

Abstract: This project is on Visual Analytics exploring the combination of visualization and automated methods for an integrated analysis of massive amounts of data. One major challenge in these areas is the consideration of interactivity on the visualization side while combining and exploring automated computations.  A promising approach in visual analytics is the computation of the best possible result within a given timeframe and to gradually improve the result from this stage, if the user is interested in a particular area. While there are some first approaches, much work still has to be done for data sets that feature non-normally distributed data, skewed data distribution or other specific characteristic to ensure good results even on a first sampling. Especially for high-dimensional data sets, the parameter space exploration of automated algorithms and the analysis of the corresponding results of the applied algorithms are of high interest in many application areas, like medicine, finance, or cyber-security.  The combination of complexity, size, and velocity (the rate of new data added to the analysis) on the data side, and the need for expert support in cyber-security makes this area predestined for a visual analytics approach.

 

Student: Ms. Ma Jingting, started in August 2014, current 1 year attachment at TUD: September 2016 - August 2017. (Scholarship from Fraunhofer IDM@NTU)

NTU supervisor: LIN Feng, Marius ERDT (Fraunhofer IDM@NTU)

TU Darmstadt co-supervisor: Dieter FELLNER, Stefan WESARG (Fraunhofer IGD)

Topic: Self-learning shape recognition in medical images

Abstract: In modern clinical routine, massive amounts of medical image data from 3D acquisition techniques like Computed Tomography or Magnetic Resonance Imaging are created every day. Analysing, interpreting, and processing this data automatically is useful to support the physician in diagnosis or operation planning. Model based approaches are frequently used to process medical images, e.g. for segmentation or registration tasks. The built models are usually based on manually labelled training images. In order to address the significant anatomical shape variability of certain anatomical structures, often many training data sets are needed. Though the image data is available in the clinics, it can be infeasible in practice to manually label all anatomical structures in a sufficiently large subset of these images for training. However, a lot of prior knowledge is inherent in medical images that can be learned in an unsupervised way since often no major scale, translation, rotation, and appearance differences between images of the same anatomical structure are present. The goal of this project is to exploit this prior knowledge in order to build shape models automatically from unlabeled training images. Therefore, new methods for unsupervised shape recognition in medical images have to be developed. Developing such methods is promising to build more accurate shape models since the mass data available nowadays can be exploited with no additional human labeling effort.

 

 

Link to TU Darmstadt-based students

 

 


 

List of potential supervisors and project topics

 

Last updated: Thursday, 20 November 2014 02:41 PM 

This is a working "long" list of the prospective supervisors and project topics. The PhD applicants can use it as a reference but they are also welcome to apply with their own topics of interests in the area of interactive digital media.

 

NTU

 

School of Computer Science and Engineering

 

Alexei SOURIN

Associate Professor
SCE/Division of Visual & Interactive Computing

Email: assourin@ntu.edu.sg

Web: http://www3.ntu.edu.sg/home/assourin

Projects on shape modeling based on using implicit and parametric functions. Projects on virtual arthroscopic surgery and any other minimally invasive surgery. Projects on reconstruction 3D from images. Projects on haptic interaction.

 

LIN Feng

Associate Professor

SCE/Division of Visual & Interactive Computing

Email: ASFLIN@ntu.edu.sg

We propose to establish a theoretic framework of nonrigid graphics for modeling and rendering of deformable graphic objects at the core graphics system layer. Furthermore, we aim to implement an innovative core graphics system in the form of kernels directly on the new-generation Graphics Processing Unit (GPU). In particular, (a) A new theoretical framework of nonrigid graphics in which a unique tetrahedral mass-spring representation will be invented as the _soft object_ primitive directly accessible by the Shaders in GPU; (b) A physically-based numerical deformation model which characterizes the elasticity and viscoelasticity of objects in geometric transformation, and the numerical processes are incorporated into the real-time rendering pipeline for visibility; and (c) A transform feedback architecture and numerical process kernels on GPU for a novel hardware acceleration solution to modeling and rendering of the deformation processes, leveraging on the new-generation GPU technologies, especially the Vertex Shader, Tessellation and Geometric Shader.

 

HE Bingsheng

Assistant Professor

SCE/Division of Networks & Distributed Systems

email: BSHE@ntu.edu.sg

We attempt to solve the performance issues in many common applications with novel design and implementation of parallel and distributed systems and their applications (with GPGPU, hardware acceleration and cloud computing). Also, we aim at taming the big data challenges from data intensive applications such as media. Our projects are supported by NTU, MoE, NRF, NVIDIA Corp. and Amazon Corp. We have set up a team of diversifying people, and the student will work in a team.

 

ZHANG Jie

Assistant Professor
SCE/Division of Software & Information Systems

Email: ZhangJ@ntu.edu.sg

Web: http://www.ntu.edu.sg/home/zhangj/

I am interested in the problems of how to design effective recommendation systems in virtual reality environments. Virtual reality environments have several advantages over 2D type of environments, such as high interactivity, high perception of presence, etc. Thus, the recommendation systems that will be implemented in virtual reality environments should fully utilize those advantages. In consequence, some existing problems in traditional recommendation systems may be resolved when implementing them in virtual reality environments. In the research, I would like to explore such potentials to solve challenging problems such as data sparsity, information asymmetry, etc.

HE Ying
Associate Professor
SCE/Division of Visual and Interactive Computing
Email: yhe@ntu.edu.sg
Web: http://www3.ntu.edu.sg/home/yhe
Modeling relevant characteristics of the human perception facilitates adaptive graphic rendering, since the human being is the ultimate receiver of almost all (if not all) graphics and animation generated. Such perception-based models can identify which part of the scene has lower human visual sensitivity and attention level, as well as predicting the resultant perceived image quality, and therefore guides the rendering process to allocate less computation effort there without being noticed by viewers. This enables graphic rendering to be user-oriented, time-efficient and resource-saving, by a paradigm shift to a perceptual criterion. It is logical and economical to make a machine for graphics perceive as humans do. This project explores the human perception characteristics, and aims at filling the technology gap: a graphic system is designed for human perception while a non-perceptual criterion is used in its design. The resultant perceptual models can be used for next-generation graphic products and services.

LIN Weisi
Associate Professor
SCE/Division of Visual and Interactive Computing
Email:
wslin@ntu.edu.sg
Web: http://www.ntu.edu.sg/home/wslin/
How to speed up the rendering process for real-time computer graphics and animation is an important research problem, especially with the emerging scenario of mobile computing, where computation power and battery are scarce resources. To this aim, adaptive sampling can be performed, by varying the number of samples in the spatial-temporal light field according to certain criteria for visual contents (such as contrast of graphics in the existing algorithms) so that fewer samples are needed without quality loss of rendered quality image.

School of Electrical and Electronic Engineering

Lap-Pui CHAU

Associate Professor

EEE/Division of Information Engineering

Email: elpchau@ntu.edu.sg

To build a content-based human motion retrieval system to facilitate human gait analysis and human behavioral recognition application. The proposed work will focus on the efficient retrieval and identification of targeted entity_s motions based on locomotion analysis of degree of freedom (DOF) parameters.

 

WANG Han

Associate Professor

EEE/Division of Control & Instrumentation

Email: HW@ntu.edu.sg

This project intends to demonstrate a mobile robot equipped with GPS and INS navigating in urban environment, able to demonstrate its location under clear and rainy weather condition. The main challenge is that, in urban outdoor environment, satellite signals are not always available. Frequently, due to high rise buildings, less than four satellite signals are in sight. This is the so called GPS challenged environment. Under this situation, the triangulation process of GPS localisation is not possible. In this project, we propose vision based panoramic view approach. In the end, a GUI will display the integrated results of localisation with individual and fused performance.

The project can be extended to non-defence applications. For example, a person with an iPhone, when he is lost and GPS is not available, he can simply take a photo and the software is able to give directions.

School of Mechanical and Aerospace Engineering

Yilei ZHANG
Assistant Professor
Email: ylzhang@ntu.edu.sg
The project is to develop capabilities of tactile sensing for virtual reality, including design and develop biometric tactile sensor as well as tactile signal modelling and interpretation by machine learning.
 

School of Physical and Mathematical Sciences

WANG  Desheng

Assistant Professor

Division of Mathematical Sciences

Email:  desheng@ntu.edu.sg

Web:  www.ntu.edu.sg/home/desheng

Image processing, computer graphics/vision including geometry modeling, surface reconstruction and processing, mesh generation and scientific computing.

 

Fraunhofer IDM@NTU

 

Olga SOURINA

Head of Lab

Email: eosourina@ntu.edu.sg

Web: http://www3.ntu.edu.sg/home/eosourina

We work on real-time brain states recognition from EEG including emotion recognition for human-computer interaction and its medical applications, optimisation of personnel workload, e-learning, entertainment including serious games, etc.

 

Henry JOHAN

Senior Scientist
Email: henryjohan@ntu.edu.sg
Photorealistic rendering is one of the major research topics since the beginning of computer graphics. It is still a challenge nowadays to render photorealistic images in a time efficient manner. The goal of this project is to develop algorithms for fast rendering of photorealistic images which can be applied to efficiently render photorealistic animations.

 

Marius ERDT
Senior Scientist
Email: marius.erdt@fraunhofer.sg

Nowadays, modern medical imaging such as CT, MRI, or 3D ultrasound plays a key role for medical diagnosis, operation planning, and intervention. Computer assisted methods help the physician in analysing, visualising and interpreting big datasets. The project addresses challenges in the field of computer-aided detection and statistical modelling of organs and anatomical structures of the human body. The research goal is to develop new automatic methods to assist doctors in diagnosis, intervention and operation planning.

 

TU Darmstadt

 

Dieter FELLNER

Professor

Email: d.fellner@gris.tu-darmstadt.de

Web: http://www.gris.tu-darmstadt.de/home/members/fellner/index.en.htm

Algorithms and software architectures to integrate modeling and rendering, efficient rendering and visualization algorithms, generative and reconstructive modeling, virtual and augmented reality, graphical aspects of internet-based multimedia information systems and cultural heritage as well as digital libraries.

 

Michael GOESELE

Professor

Email: michael.goesele@gris.informatik.tu-darmstadt.de

Web: http://www.gris.informatik.tu-darmstadt.de/~mgoesele/index.html

Capturing Reality: The main focus of our research interest is the development of digitization methods for all aspects of the real world. This includes capturing geometry, surface color and several other attributes, e.g. reflectance properties of objects. Most of our methods perform the reconstruction solely on photographs that have been taken under controlled conditions (such as constant lighting and known camera parameters). Our latest developments, however, are capable of dealing with photos taken under uncontrolled conditions, for example images from community photo collections such as flickr. Beyond that, we are interested in massively parallel computing to exploit the full potential of nowadays graphics hardware to solve computationally expensive problems in various areas, for example visual computing and bio informatics.

 

Stefan ROTH

Professor

Email: sroth@cs.tu-darmstadt.de

Web: http://www.gris.informatik.tu-darmstadt.de/~sroth/

Visual Inference: Our research lies at the intersection of computer vision and machine learning and focuses on analyzing and interpreting visual data, such as digital images and videos, with a particular emphasis on probabilistic modeling and inference. Our work is motivated by the inherent uncertainty and ambiguity of visual data and aims to model and take advantage of this uncertainty in a systematic manner. We tackle a wide variety of applications with substantial practical impact, such as image restoration, image motion estimation, detection and tracking of people in images and videos, as well as object recognition.

 

Georgios SAKAS

Professor

Email: georgios.sakas@gris.tu-darmstadt.de

Web: http://www.gris.tu-darmstadt.de/home/members/sakas/index.de.htm

Medical Computing: Our research focus is on Medical Computing _ the synthesis of Computer Graphics, Image Processing, Medicine, and Physics. The increasing amount of data acquired by state-of-the-art medical imaging devices requires more sophisticated approaches for processing this image data. This comprises the initial image processing (image enhancement, image registration), the anatomical modeling based on these images, the automated analysis for the purpose of diagnosis and intervention planning, and the visualization of both, the image data as well as analysis results and model knowledge. For this, we develop new algorithms and employ recently introduced hardware for massively parallel processing (GPGPUs).

 

Jan PETERS

Professor

FG Intelligent Autonomous Systems

Email: mail@jan-peters.net

Web: http://www.ias.tu-darmstadt.de/Team/JanPeters

The project is to develop capabilities of tactile sensing for virtual reality, including design and develop biomimetic tactile sensor as well as tactile signal modelling and interpretation by machine learning.

 


 

Programme coordinator: Alexei Sourin assourin@ntu.edu.sg
 

 

Programme Management Committee NTU - TU Darmstadt

Alexei Sourin (SCSE NTU) - Chair

Ng Wee Keong (SCSE NTU)

Reiner HÄhnle (TU Darmstadt)

Michael Goesele (TU Darmstadt)

 

Joint Admission Committee NTU - TU Darmstadt

Alexei Sourin (SCSE NTU) - Chair

Ng Wee Keong (SCSE NTU)

Reiner HÄhnle  (TU Darmstadt)

Michael Goesele (TU Darmstadt)