The proposed PhD position is funded by the ANR PISCo project (Perceptual Levels of Detail for Interactive and Immersive Remote Visualization of Complex 3D Scenes) which aims at proposing novel algorithms and tools allowing interactive visualization, in these constrained contexts (Virtual and Mixed reality, with local/remote 3D content), with a very high quality of user experience. As 3D scenes are visualized through a certain viewport, we seek to optimize the display in this viewport by proposing (1) Tools for the generation and compression of high quality levels of details, (2) Visual quality metrics capable of predicting the quality of these levels of detail and driving their generation, (3) Visual attention models capable of predicting where the observer is looking and thus selecting and filtering the primitives and levels of detail . A distinctive property of the project lies into the fact that we will consider rich 3D data, including not only geometric information but also animation and complex physically based materials represented by texture maps (color, metalness, roughness, normals).
The proposed PhD position concerns the item (3) above. Our goal is to build computational visual attention models that will predict both head and eye-movement in 3 and possibly 6 degrees of freedom environment, taking into account, mesh saliency, rendered scene saliency and human visual behavior (perceptual biases, bottom-up and top down influences, etc.). The visual attention models will also be used for predicting the interaction of the user in the virtual environment (translation + zoom / dezoom). The PhD candidate will benefit from the work already conducted in the LS2N IPI team related to 3D visual attention and perceptual biases.
Master’s degree in Computer Science, good experience with 3D/Unity programming, good knowledge of signal / image processing (in particular applied to graphs), computer graphics, volumetric data processing, and machine learning.
Since the candidate will also building experiments with humans, allowing to gather ground truth data necessary for understanding visual attention mechanisms in 3D virtual environment, previous experience and / or interest in this field is strongly recommended.
For additional information : https://uncloud.univ-nantes.fr/index.php/s/9zH9jgefmAYnFKf
(c) GdR 720 ISIS - CNRS - 2011-2018.