Glossary: Difference between revisions

    From Ban Covert Modeling! wiki
    (Sourced definition of w:deepfake to a {{Q}})
    m (tweaks)
    Line 1: Line 1:
    = Ban Covert Modeling! wiki glossary =
    == Bidirectional reflectance distribution function ==
    == Bidirectional reflectance distribution function ==
    [[File:BRDF_Diagram.svg|thumb|right|300px|Diagram showing vectors used to define the [[w:BRDF|BRDF]].]]
    [[File:BRDF_Diagram.svg|thumb|right|300px|Diagram showing vectors used to define the [[w:BRDF|BRDF]].]]
    {{Q|The '''bidirectional reflectance distribution function''' ('''BRDF''') is a function of four real variables that defines how light is reflected at an [[w:Opacity (optics)|opaque]] surface. It is employed in the [[w:optics|optics]] of real-world light, in [[w:computer graphics|computer graphics]] algorithms, and in [[w:computer vision|computer vision]] algorithms.|Wikipedia|[[w:bidirectional reflectance distribution function|BRDF]]}}
    {{Q|The '''bidirectional reflectance distribution function''' ('''BRDF''') is a function of four real variables that defines how light is reflected at an [[w:Opacity (optics)|opaque]] surface. It is employed in the [[w:optics|optics]] of real-world light, in [[w:computer graphics|computer graphics]] algorithms, and in [[w:computer vision|computer vision]] algorithms.|Wikipedia|[[w:bidirectional reflectance distribution function|BRDF]]}}


    A BRDF model is a 7 dimensional model containing geometry, textures and reflectance of the subject.  
    A BRDF model is a 7 dimensional model containing geometry, textures and reflectance of the subject.  


    The seven dimensions of the BRDF are as follows:  
    The seven dimensions of the BRDF model are as follows:  
    * 3 cartesian X,Y,Z  
    * 3 cartesian X,Y,Z  
    * 2 for the entry angle
    * 2 for the entry angle
    Line 16: Line 20:


    Main known cases are
    Main known cases are
    * Covertly modeling the human appearance into 7-dimensional [[#Bidirectional reflectance distribution function|]] model or other type of model.
    * Covertly modeling the '''human appearance''' into 7-dimensional [[#Bidirectional reflectance distribution function|]] model or other type of model.
    * Covertly modeling the human voice
    * Covertly modeling the '''human voice'''
    There is work ongoing to model e.g. human's style of writing, but this is probably not as drastic a threat as the covert modeling of appearance and of voice.
    There is work ongoing to model e.g. '''human's style of writing''', but this is probably not as drastic a threat as the covert modeling of appearance and of voice.
    ----
    ----
    == Deepfake ==
    == Deepfake ==

    Revision as of 12:09, 3 April 2019

    Ban Covert Modeling! wiki glossary

    Bidirectional reflectance distribution function

    Diagram showing vectors used to define the BRDF.

    “The bidirectional reflectance distribution function (BRDF) is a function of four real variables that defines how light is reflected at an opaque surface. It is employed in the optics of real-world light, in computer graphics algorithms, and in computer vision algorithms.”

    ~ Wikipedia on BRDF


    A BRDF model is a 7 dimensional model containing geometry, textures and reflectance of the subject.

    The seven dimensions of the BRDF model are as follows:

    • 3 cartesian X,Y,Z
    • 2 for the entry angle
    • 2 for the exit angle of the light.

    Covert modeling

    Covert modeling refers to both covertly modeling aspects of a subject i.e. without express consent.

    Main known cases are

    • Covertly modeling the human appearance into 7-dimensional [[#Bidirectional reflectance distribution function|]] model or other type of model.
    • Covertly modeling the human voice

    There is work ongoing to model e.g. human's style of writing, but this is probably not as drastic a threat as the covert modeling of appearance and of voice.


    Deepfake

    Deepfake (a portmanteau of "deep learning" and "fake") is a technique for human image synthesis based on artificial intelligence. It is used to combine and superimpose existing images and videos onto source images or videos using a machine learning technique called a "generative adversarial network" (GAN).”

    ~ Wikipedia on Deepfakes



    Light stage

    The ESPER LightCage - 3D face scanning rig is a modern light stage

    “A light stage or light cage is equipment used for shape, texture, reflectance and motion capture often with structured light and a multi-camera setup.”

    ~ Wikipedia on light stages