Text-to-scene conversion
View Patent ↗A system for generating a scene description from a set of words includes modules that perform the following functions: performing a linguistic analysis on a set of words to generate a structure representation of semantic relationships between words within the set of words, converting the structure to a set of description elements representative of objects to be depicted in a scene and relationships between objects, depicting a spatial relationship by using at least one spatial tag of an associated one or more of the object, and assigning a set of depictors to each of the description elements. Each depictor in the set of depictors may include a reference to an object to be modified, parameters used in modifying the object and a procedure for modifying the object. The system may also include a module that generates the same description by execution of the procedure for the modification of the objects.
1. A method of generating scenes, the method comprising:
receiving text that describes a scene;
tagging the received text as grammatical parts of speech;
parsing, via a processor, the tagged text into a parse tree;
converting the parse tree into a dependency structure;
converting the dependency structure into a scene description; and
rendering the scene from the scene description.
2. The method of claim 1 , further comprising:
semantically interpreting the dependency structure as part of converting the dependency structure into the scene description.
3. The method of claim 1 , further comprising, prior to rendering:
interpreting the scene description as a three-dimensional scene.
4. The method of claim 3 , wherein the three-dimensional scene is rendered into an image as the rendered scene.
5. The method of claim 1 , wherein the parse tree represents a grammatical structure of a sentence in the received text.
6. The method of claim 1 , wherein the dependency structure shows for each given word in a sentence in the received text the words that the given word is dependent on and the words that depend on the given word.
7. The method of claim 1 , wherein the steps of receiving text, tagging the received text, parsing the tagged text into a parse tree and converting the parse tree are performed by a linguistic analysis module, and the steps of converting the dependency structure and rendering the scene are performed by a depiction module.
8. A system that generates scenes, the system comprising:
a linguistic analysis module that is configured to control a processor to:
receive text that describes a scene;
tag the received text as grammatical parts of speech;
parse the tagged text into a parse tree;
convert the parse tree into a dependency structure; and
a depiction module that is configured to control the processor to:
convert the dependency structure into a scene description; and
render the scene from the scene description.
9. The system of claim 8 , wherein the linguistic analysis module is further configured to control the processor to semantically interpret the dependency structure as part of converting the dependency structure into the scene description.
10. The system of claim 8 , wherein the depiction module, prior to rendering, interprets the scene description as a three-dimensional scene.
11. The system of claim 10 , wherein the three-dimensional scene is rendered into an image as the rendered scene.
12. The system of claim 8 , wherein the parse tree represents a grammatical structure of a sentence in the received text.
13. The system of claim 8 , wherein the dependency structure shows for each given word in a sentence in the received text the words that the given word is dependent on and words that depend on the given word.
14. A non-transitory computer-readable medium storing instructions for controlling a computing device to generate scenes, the instructions comprising:
receiving text that describes a scene;
tagging the received text as grammatical parts of speech;
parsing the tagged text into a parse tree;
converting the parse tree into a dependency structure;
converting the dependency structure into a scene description; and
rendering the scene from the scene description.
15. The non-transitory computer-readable medium of claim 14 , wherein the instructions further comprise semantically interpreting the dependency structure as part of converting the dependency structure into the scene description.
16. The non-transitory computer-readable medium of claim 14 , wherein the instructions further comprise, prior to rendering, interpreting the scene description as a three-dimensional scene.
17. The non-transitory computer-readable medium of claim 16 , wherein the three-dimensional scene is rendered into an image as the rendered scene.
18. The non-transitory computer-readable medium of claim 14 , wherein the parse tree represents a grammatical structure of the sentence in the received text.
19. The non-transitory computer-readable medium of claim 14 , wherein the dependency structure shows for each given word in a sentence in the received text the words that the given word is dependent on and the words that depend on the given word.
20. The non-transitory computer-readable medium of claim 14 , wherein the steps of receiving text, tagging the received text, parsing the tagged text into a parse tree and converting the parse tree are performed by a linguistic analysis module, and the steps of converting the dependency structure and rendering the scene are performed by a depiction module.