The goal of this ETN is to have the participants develop skills and protocols needed for industrial usage of Predictive Rendering (PR) technologies – image synthesis which delivers results that can be relied on to be visually accurate. Application areas of such systems are manifold: product design, in particular authoritative assessment of product appearance during design processes, architecture, sensor calibration, autonomous vehicle and general AI training, and manufacturing control – but even well established graphics application areas like movie visual effects (VFX) can greatly benefit from using them instead of established systems.
Apart from existing markets for real-time game rendering engines and conventional offline movie rendering software, which both focus on visually convincing but not radiometrically correct results, we are witnessing the emergence of a new market for physically accurate rendering software which can predict what physical sensors would measure in the real world, and which provides guarantees for its accuracy. This is a cutting-edge area of applied computer science, in which European academia and industry are currently amongst the global technology leaders. Due to the current rapid expansion of this field, and given the potential impact in manufacturing, as well as the emergence of fields and technologies requiring reliable appearance synthesis, more trained experts and their novel research results are urgently needed.