The IDLab-MEDIA research team focuses on the representation, processing, compression and interactive delivery of emerging visual media formats. These formats are drastically evolving beyond traditional 2D images or video, such as 360° video, multi-view stereo/3D video, Augmented or Virtual Reality (AR/VR), Light Fields, or holography. Next to the obvious but significant increase in data rates, these formats are posing significant challenges with respect to data dimensionality and interactivity demands:
- Dimensionality. Whereas traditional video data has 3 dimensions, the full plenoptic function has 6. Current (traditional) compression techniques do not scale with dimensionality and are unable to efficiently exploit the redundancies at hand. Even for multi-view video (only 4D), current video coding techniques are inadequate. Radically new techniques are necessary in order to achieve an efficient sparse representation for high-dimensional visual data.
- Interactivity demands. When data volumes increase beyond the physical limits of rendering and transmission systems/hardware (e.g., memory, computing power, bandwidth), interactivity becomes problematic. As such, appropriate (scalable) data representations are required that offer features such as regions of interest, random access, and level of detail. On top of that, networked environments pose additional challenges related to bandwidth and low-delay processing.