Variable resolution rendering of objects based on user familiarity

Patent metadata

Field	Value
Publication number	US-10796408-B2
Application number	US-201816052854-A
Country	US
Kind code	B2
Filing date	Aug 2, 2018
Priority date	Aug 2, 2018
Publication date	Oct 6, 2020
Grant date	Oct 6, 2020

Abstract

For variable resolution rendering of objects, a processor determines an aggregate familiarity of a user with an object based on at least one of a common familiarity of the object, a content-specific familiarity of the user with the object, and a subjective familiarity of the user with the object. The processor further, in response to the aggregate familiarity satisfying a render policy, reduces a render resolution of the object.

First claim

What is claimed is:

1. An apparatus comprising:
a processor;
a computer readable storage media storing code executable by the processor to:
determine an aggregate familiarity of a user with an object as a weighted sum of a common familiarity of the object, a content-specific familiarity of the user with the object, and a subjective familiarity of the user with the object, wherein the content-specific familiarity is calculated as a function of a view time interval that the object is within an area of interest of the user determined by eye tracking, wherein the content-specific familiarity CSF is calculated as CSF=max(jVTI 2 , h), where VTI is the view time interval and j and h are nonzero constants; and
in response to the aggregate familiarity satisfying a render policy, reduce a render resolution of the object.

2. The apparatus of claim 1 , wherein the subjective familiarity is determined by:
filtering images related to the user for user specific images;
training a subjective model with the user specific images; and
determining the object is subjectively familiar in response to identifying the object with the subjective model.

3. The apparatus of claim 2 , wherein the user specific images are acquired from at least one of a social media site and library images identified from a user profile.

4. The apparatus of claim 1 , wherein the common familiarity is determined by:
recognizing the object with a standard object model; and
assigning the object a common familiarity value associated with the object for the standard object model.

5. The apparatus of claim 1 , wherein reducing the render resolution of the object comprises one or more of reducing a number of polygons rendering the object and reducing a complexity of texture maps for the object.

6. A method comprising:
determining, by use of a processor, an aggregate familiarity of a user with an object as a weighted sum of a common familiarity of the object, a content-specific familiarity of the user with the object, and a subjective familiarity of the user with the object, wherein the content-specific familiarity is calculated as a function of a view time interval that the object is within an area of interest of the user determined by eye tracking, wherein the content-specific familiarity CSF is calculated as CSF=max(jVTI 2 , h), where VTI is the view time interval and j and h are nonzero constants; and
in response to the aggregate familiarity satisfying a render policy, reducing a render resolution of the object.

7. The method of claim 6 , wherein the subjective familiarity is determined by:
filtering images related to the user for user specific images;
training a subjective model with the user specific images; and
determining the object is subjectively familiar in response to identifying the object with the subjective model.

8. The method of claim 7 , wherein the user specific images are acquired from at least one of a social media site and library images identified from a user profile.

9. The method of claim 6 , wherein the common familiarity is determined by:
recognizing the object with a standard object model; and
assigning the object a common familiarity value associated with the object for the standard object model.

10. The method of claim 6 , wherein reducing the render resolution of the object comprises one or more of reducing a number of polygons rendering the object and reducing a complexity of texture maps for the object.

11. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions readable/executable by a processor to cause the processor to:
determine an aggregate familiarity of a user with an object as a weighted sum of a common familiarity of the object, a content-specific familiarity of the user with the object, and a subjective familiarity of the user with the object, wherein the content-specific familiarity is calculated as a function of a view time interval that the object is within an area of interest of the user determined by eye tracking, wherein the content-specific familiarity CSF is calculated as CSF=max(jVTI 2 , h), where VTI is the view time interval and j and h are nonzero constants; and
in response to the aggregate familiarity satisfying a render policy, reduce a render resolution of the object.

12. The computer program product of claim 11 , wherein the subjective familiarity is determined by:
filtering images related to the user for user specific images;
training a subjective model with the user specific images; and
determining the object is subjectively familiar in response to identifying the object with the subjective model.

13. The computer program product of claim 12 , wherein the user specific images are acquired from at least one of a social media site and library images identified from a user profile.

14. The computer program product of claim 11 , wherein the common familiarity is determined by:
recognizing the object with a standard object model; and
assigning the object a common familiarity value associated with the object for the standard object model.

Assignees

• IBM

Inventors

• Liu Su
• Hwang Inseok
• Rozner Eric
• Agarwal Kanak B

Classifications

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title