GENERATING AUGMENTED REALITY EXEMPLARS
Technologies are generally described for automatic clustering and rendering of augmentations into one or more operational exemplars in an augmented reality environment. In some examples, based on a user's context, augmentations can be retrieved, analyzed, and grouped into clusters. Exemplars can be used to render the clusters as conceptual representations of the grouped augmentations. An exemplar's rendering format can be derived from the grouped augmentations, the user's context, or formats of other exemplars. Techniques for grouping the augmentations into clusters and rendering these clusters as exemplars to a user can enhance the richness and meaning of an augmented reality environment along contextually or user determined axes while reducing the sensorial and cognitive load on the user.
1 . A system to render augmented data, the system comprising:
one or more processors; and
a memory coupled to the one or more processors, wherein the memory stores instructions which in response to execution by the one or more processors, cause the system to at least:
determine a plurality of augmentations of a scene captured by a user device, wherein the determination is based on a context associated with the user device, and wherein the context includes information regarding an environment of the user device;
group the plurality of augmentations into one or more clusters based on at least one concept description, wherein each of the one or more clusters is associated with a concept description of the at least one concept description;
determine a rendering format for each corresponding cluster of the one or more clusters, wherein the rendering format indicates at least a look of conceptual representation of the corresponding cluster, wherein the look of the conceptual representation of the corresponding cluster is based on at least the concept description associated with the corresponding cluster, and wherein the conceptual representation of the corresponding cluster is different from individual augmentations within the corresponding cluster; and
render each cluster of the one or more clusters based on the rendering format that corresponds to the each cluster.
2 . The system of claim 1 , wherein the scene is associated with a set of scene coordinates, and wherein the plurality of augmentations are associated with a set of augmentation coordinates.
3 . The system of claim 2 , wherein the memory stores instructions which in response to execution by the one or more processors, further cause the system to:
merge the scene with the plurality of augmentations based on the set of scene coordinates and the set of augmentation coordinates.
4 . The system of claim 1 , wherein the each cluster of the one or more clusters represents one of a plurality of physical venues.
5 . The system of claim 1 , wherein the group of the plurality of augmentations into the one or more clusters is further based on a respective location of a plurality of physical venues.
6 . The system of claim 1 , wherein the determination of the rendering format for each corresponding duster of the one or more clusters is based at least in part on a subset of the plurality of augmentations that is associated with a certain physical venue.
7 . A method to render augmented reality data, the method comprising:
determining a plurality of augmentations of a scene captured by a user device, wherein the determination is based on a context associated with the user device, and wherein the context includes information regarding an environment of the user device;
grouping the plurality of augmentations into one or more clusters based on at least one concept description, wherein each of the one or more clusters is associated with a concept description of the at least one concept description;
determining a rendering format for each corresponding cluster of the one or more clusters, wherein the rendering format indicates at least a look of conceptual representation of the corresponding cluster, wherein the look of the conceptual representation of the corresponding cluster is based on at least the concept description associated with the corresponding cluster, and wherein the conceptual representation of the corresponding cluster is different from individual augmentations within the corresponding cluster; and
rendering each cluster of the one or more clusters based on the rendering format that corresponds to the each cluster.
8 . The method of claim 7 , wherein the each cluster of the one or more clusters represents one of a plurality of physical venues.
9 . The method of claim 7 , wherein grouping the plurality of augmentations into one or more clusters includes grouping further based on a respective location of a plurality of physical venues.
10 . The method of claim 7 , wherein determining the rendering format for each corresponding cluster of the one or more clusters includes determining based on a subset of the plurality of augmentations that is associated with a certain physical venue.
11 . A non-transitory computer readable storage medium having stored thereon instructions that, in response to execution by one or more processors, cause the one or more processors to perform or control performance of:
generate one or more classes of clusters based on an analysis of properties of a plurality of augmentations, wherein the plurality of augmentations includes one or more augmentations of a scene captured by a user device;
associate a concept description with each corresponding class of the one or more classes of clusters based on the properties of the plurality of augmentations, wherein the concept description is indicative of at least a look of a conceptual representation of the corresponding class; and
group the plurality of augmentations into the one or more classes of dusters based on the concept description of each corresponding class of the one or more classes of clusters.
12 . The non-transitory computer readable storage medium of claim 11 , wherein the conceptual representation of the corresponding class is different from individual augmentations within the corresponding class.
13 . The non-transitory computer readable storage medium of claim 11 , wherein the scene captured by the user device is based on a context associated with the user device, and wherein the context includes information regarding an environment of the user device.
14 . The non-transitory computer readable storage medium of claim 13 , wherein the analysis of the properties of the plurality of augmentations comprises a comparison of the properties of the plurality of augmentations with the context associated with the user device.
15 . The non-transitory computer readable storage medium of claim 11 , wherein the instructions, in response to execution by the one or more processors, further cause the one or more processors to perform or control performance of:
add at least one of the plurality of augmentations into a particular class of the one or more classes of clusters based on a comparison between the properties of the plurality of augmentations and the concept description associated with the particular class of the one or more classes of clusters.
16 . A method to group a plurality of augmentations, the method comprising:
generating one or more classes of clusters based on an analysis of properties of the plurality of augmentations, wherein the plurality of augmentations includes one or more augmentations of a scene captured by a user device;
associating a concept description with each corresponding class of the one or more classes of clusters based on the properties of the plurality of augmentations, wherein the concept description is indicative of at least a look of conceptual representation of the corresponding class; and
grouping the plurality of augmentations into the one or more classes of clusters based on the concept description of each corresponding class of the one or more classes of clusters.
17 . The method of claim 16 , wherein the look of conceptual representation of the corresponding class is different from individual augmentations within the corresponding class.
18 . The method of claim 16 , wherein the scene captured by the user device is based on a context associated with the user device, and wherein the context includes information regarding an environment of the user device.
19 . The method of claim 16 , wherein the analysis of the properties of the plurality of augmentations comprises a comparison of the properties of the plurality of augmentations with the context associated with the user device.
20 . The method of claim 16 , further comprising:
adding at least one of the plurality of augmentations into a particular class of the one or more classes of clusters based on a comparison between the properties of the plurality of augmentations and the concept description associated with the particular class of the one or more classes of clusters.