Abstract: Various implementations disclosed herein include devices, systems, and methods for performing content generation based on audience engagement. In some implementations, a method includes presenting a first portion of content. Engagement data is obtained for an audience comprising a plurality of persons while the first portion of the content is presented. Based on the engagement data, a collective engagement level of the audience is determined for the first portion of the content. A second portion of the content that has not been presented is adjusted based on the collective engagement level of the audience for the first portion of the content in order to satisfy an engagement threshold. After adjusting the second portion of the content, the second portion of the content is presented to the audience.

Abstract: In some implementations, a method includes obtaining a set of preselected attribute values for an objective-effectuator. In some implementations, the method includes while displaying a user interface including a plurality of configuration control affordances provided to effect configuration of one or more attributes characterizing the objective-effectuator, in response to receiving an input indicative of manipulation of a first configuration control affordance, setting a corresponding first attribute to a particular preselected attribute value, and modifying display of the plurality of configuration control affordances in order to change the number of the plurality of configuration control affordances displayed. In some implementations, the method includes configuring the objective-effectuator at least based on the particular preselected attribute value of the first attribute. In some implementations, the objective-effectuator is associated with a set of predefined actions.

Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

Abstract: Various implementations disclosed herein include devices, systems, and methods for performing content generation based on audience engagement. In some implementations, a method includes presenting a first portion of content. Engagement data is obtained for an audience comprising a plurality of persons while the first portion of the content is presented. Based on the engagement data, a collective engagement level of the audience is determined for the first portion of the content. A second portion of the content that has not been presented is adjusted based on the collective engagement level of the audience for the first portion of the content in order to satisfy an engagement threshold. After adjusting the second portion of the content, the second portion of the content is presented to the audience.

Abstract: Various implementations disclosed herein include devices, systems, and methods for performing scene-to-text conversion. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes obtaining environmental data corresponding to an environment. Based on the environmental data, a plurality of objects that are in the environment are identified. An audio output describing at least a first object of the plurality of objects in the environment is generated based on a characteristic value associated with a user of the device. The audio output is outputted.

Abstract: In some implementations, a method includes obtaining a set of preselected attribute values for an objective-effectuator. In some implementations, the method includes while displaying a user interface including a plurality of configuration control affordances provided to effect configuration of one or more attributes characterizing the objective-effectuator, in response to receiving an input indicative of manipulation of a first configuration control affordance, setting a corresponding first attribute to a particular preselected attribute value, and modifying display of the plurality of configuration control affordances in order to change the number of the plurality of configuration control affordances displayed. In some implementations, the method includes configuring the objective-effectuator at least based on the particular preselected attribute value of the first attribute. In some implementations, the objective-effectuator is associated with a set of predefined actions.

Abstract: Various implementations disclosed herein include devices, systems, and methods for per-pixel filtering. In some implementations, a method includes obtaining an image data frame. In some implementations, the image data frame includes a plurality of pixels. In some implementations, the method includes generating a respective pixel characterization vector for each of the plurality of pixels. In some implementations, each pixel characterization vector includes an object label indicating an object type that the corresponding pixel of the plurality of pixels represents. In some implementations, the method includes modifying corresponding pixel data of the plurality of pixels having a first object label. In some implementations, the method includes synthesizing a first modified image data frame that includes modified pixel data for the plurality of pixels having the first object label and unmodified pixel data for the plurality of pixels not having the first object label.

Abstract: A method for producing an image of a scene including a refractive object includes generating an illumination map, representing the scene. The method creates a first bitmap for the refractive object, the bitmap comprising a plurality of pixels; each of said pixels in the first bitmap is mapped to a pixel in a second bitmap, the mapping representing the effect of refraction on light passing through the object; and the effects of the light illuminating the pixels in the first bitmap are added into said second bitmap.

Abstract: A method for producing an image of a scene including a refractive object includes generating an illumination map, representing the scene. The method creates a first bitmap for the refractive object, the bitmap comprising a plurality of pixels; each of said pixels in the first bitmap is mapped to a pixel in a second bitmap, the mapping representing the effect of refraction on light passing through the object; and the effects of the light illuminating the pixels in the first bitmap are added into said second bitmap.