PhD Position in Computational Imaging

Updated: over 2 years ago
Job Type: Temporary
Deadline: 01 Feb 2022

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.



Similar Positions