When: Jun 30, 2021 – 11:00 – 11:45 AM
Where: Google meet link
Many existing research works usually involve training and testing of virtual agents on datasets of static images or short videos, considering sequences of distinct learning tasks. However, in order to devise continual learning algorithms that operate in more realistic conditions, it is fundamental to gain access to rich, fully customizable and controlled experimental playgrounds. Focusing on the specific case of vision, we thus propose to leverage recent advances in 3D virtual environments in order to approach the automatic generation of potentially life-long dynamic scenes with photo-realistic appearance. Scenes are composed of objects that move along variable routes with different and fully customizable timings, and randomness can also be included in their evolution. Scenes are described in a parametric way, thus allowing the user to fully control the visual complexity of the input stream the agent perceives. These general principles are concretely implemented exploiting SAILenv. The user can then generate scenes without the need of having strong skills in computer graphics, since all the generation facilities are exposed through a simple high-level Python interface.