Abstract: Semantic vectorization techniques are described that support generating and editing of vector objects from raster objects. A raster object, for instance, is received as an input by a semantic vectorization system. The raster object is utilized by the semantic vectorization system to generate a semantic classification for the raster object. The semantic classification identifies semantic objects in the raster image. The semantic vectorization system leverages the semantic classification to generate vector objects. As a result, the vector objects resemble the semantic objects in the raster object.

Abstract: In implementations of suggestions to enrich digital artwork, a suggestion system identifies a first object in the digital artwork and suggests a second object for addition to the digital artwork based on the second object having a co-occurrence relationship with the first object. The co-occurrence relationship is based on the first object and the second object appearing together in an image of an image set. A user may select the second object to add to the artwork or the user may be inspired by the second object to enrich the digital artwork.

Abstract: In implementations of suggestions to enrich digital artwork, a suggestion system identifies a first object in the digital artwork and suggests a second object for addition to the digital artwork based on the second object having a co-occurrence relationship with the first object. The co-occurrence relationship is based on the first object and the second object appearing together in an image of an image set. A user may select the second object to add to the artwork or the user may be inspired by the second object to enrich the digital artwork.