1. Vacatures
  2. Technische Universiteit Delft (TUD)
  3. PhD Position in Computational Imaging

Helaas, deze vacature staat inmiddels niet meer online

Kijk gerust verder naar andere vacatures.

PhD Position in Computational Imaging

We are looking for an enthusiastic PhD candidate interested in a broad field of Computational Imaging and Displays. You will develop and evaluate perceptually …

2 maanden geleden

Arbeidsvoorwaarden

Standplaats:
Mekelweg, Delft, Zuid-Holland
Dienstverband:
Tijdelijk contract / Tijdelijke opdracht
Salarisindicatie:
€ 2434 - € 3111 per maand
Opleidingsniveau:
WO

Functieomschrijving

We are looking for an enthusiastic PhD candidate interested in a broad field of Computational Imaging and Displays. You will develop and evaluate perceptually motivated algorithms for capture, processing and rendering of light fields for advanced display applications including virtual and augmented reality. You will work within the Computer Graphics and Visualization Group [https://graphics.tudelft.nl/] lead by Professor Elmar Eisemann [https://graphics.tudelft.nl/~eisemann] under co-supervision of Assistant Professor Petr Kellnhofer [https://graphics.tudelft.nl/petr-kellnhofer].

Novel neural rendering algorithms have enabled near photo-realistic free-view synthesis of real scenes and brought the prospect of fully immersive remote-presence experience ever closer. However, despite the significant attention dedicated to solving technical challenges of encoding and decoding convincing 2D images, relatively little has been done to enable practical applications and describe the requirements for perceptually pleasing viewing experiences.

Your work will bridge this gap by examining and developing state-of-the-art view synthesis algorithms and applying them in the context of virtual, augmented, and/or mixed reality. A special emphasis will be put to perceptual evaluation of the resulting technological demos in human participant studies to examine role of visual cues such as color contrast, disparity, or motion parallax. This work will lead to development of guidelines and perceptual models driving further development of techniques for capture, compression, editing and rendering of light-fields.

It is expected that you will critically evaluate related literature and develop state-of-the-art algorithms utilizing neural network theory from computer vision as well as real-time rendering approaches from computer graphics. You will design and conduct user studies and evaluate the results using statistical analysis to test hypotheses based on psychophysical modeling of human vision. You will publish and present your results at prestigious computer graphics and computer vision venues.

Functie-eisen

  • Master’s degree (or equivalent) in computer science or a closely related field,
  • Demonstrable background in computer graphics and/or computer vision,
  • Interest in study of human visual perception,
  • Excellent communication and presentation skills in English (see https://www.tudelft.nl/onderwijs/opleidingen/phd/admission ),
  • Experience with Python or a similar programming language,
  • Close familiarity with 3D graphics (transformations, projections, …).

Other useful skills and experience:

  • Experience with design and conduct of user studies (psychotoolbox, psychopy, …).
  • Experience with machine learning frameworks such as pytorch, TensorFlow or others,
  • Familiarity with graphics pipelines such as OpenGL, DirectX and/or with frameworks such as Unity or Unreal,
  • Experience with development for VR and/or AR.

Conditions

TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2434 per month in the first year to € 3111 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.

The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.

Additional information

For more information about this vacancy, please contact Petr Kellnhofer, Assistant Professor, CGV ( https://graphics.tudelft.nl/petr-kellnhofer ).