Abstract: Techniques for placing content in virtual universes at locations contextually compatible with the content are disclosed. A system trains a machine learning model to identify virtual environments compatible with content based on attributes representing contexts of the environments. Using the machine learning model, the system determines a contextual environment for a target content item. The system selects the particular contextual environment for placement of the target content item based on the compatibility score.

Abstract: Techniques for placing content in virtual universes at locations contextually compatible with the content are disclosed. A system trains a machine learning model to identify virtual environments compatible with content based on attributes representing contexts of the environments. Using the machine learning model, the system determines a contextual environment for a target content item. The system selects the particular contextual environment for placement of the target content item based on the compatibility score.

Abstract: Techniques for determining perceptibility of content displayed within virtual universes are disclosed. Operations include calculating a cube map of a scene in the virtual universe at a location with a view of a target object. Using the cube map, first and second visibility scores are computed for the target object. A perceptibility score for the target object is determined by combining the first and second visibility scores. Computing the visibility scores includes generating an image representing the scene in a face of the cube map including obstructions and visual effects. The operations further include generating another image representing the scene in the face of the cube map without including the obstructions and visual effects. Additionally, the operations include determining the visibility score by comparing the two images.