Abstract: One embodiment of the present invention sets forth a technique for performing face swapping. The technique includes converting a first input image that depicts a first facial identity from a first viewpoint at a first time into a first latent representation and converting a second input image that depicts the first facial identity from a second viewpoint at the first time into a second latent representation. The technique also includes generating, via a first machine learning model, a first output image that depicts a second facial identity from the first viewpoint based on the first latent representation. The technique further includes generating, via the first machine learning model, a second output image that depicts the second facial identity from the second viewpoint based on the second latent representation.

Abstract: Techniques are disclosed for characterizing audience engagement with one or more characters in a media content item. In some embodiments, an audience engagement characterization application processes sensor data; such as video data capturing the faces of one or more audience members consuming a media content item, to generate an audience emotion signal. The characterization application also processes the media content item to generate a character emotion signal associated with one or more characters in the media content item. Then, the characterization application determines an audience engagement score based on an amount of alignment and/or misalignment between the audience emotion signal and the character emotion signal.

Abstract: One embodiment of the present invention sets forth a technique for performing identity-preserving image generation. The technique includes converting an identity image depicting a facial identity into an identity embedding. The technique further includes generating a combined embedding based on the identity embedding and a diffusion iteration identifier. The technique further includes converting, using a neural network and based on the combined embedding, a first input image that includes first noise into a first predicted image depicting one or more facial features that include one or more first facial identity features, wherein the one or more first facial identity features correspond to one or more respective second facial identity features of the identity image and are based at least on the identity embedding.

Abstract: One embodiment of the present invention sets forth a technique for performing face swapping. The technique includes generating a latent representation of a first facial identity included in an input image. The technique further includes identifying a first identity-specific neural network layer associated with a second facial identity from a plurality of identity-specific neural network layers, wherein each neural network layer included in the plurality of identity-specific neural network layers is associated with a different facial identity. The technique further includes executing the first identity-specific neural network layer and one or more other neural network layers to generate one or more decoder input values corresponding to the latent representation. The technique further includes executing a decoder neural network that converts the one or more decoder input values into an output image depicting the second facial identity.

Abstract: A computer-implemented method of changing a face within an output image or video frame that includes: receiving an input image that includes a face presenting a facial expression in a pose; processing the image with a neural network encoder to generate a latent space point that is an encoded representation of the image; decoding the latent space point to generate an initial output image in accordance with a desired facial identity but with the facial expression and pose of the face in the input image; identifying a feature of the facial expression in the initial output image to edit; applying an adjustment vector to a latent space point corresponding to the initial output image to generate an adjusted latent space point; and decoding the adjusted latent space point to generate an adjusted output image in accordance with the desired facial identity but with the facial expression and pose of the face in the input image altered in accordance with the adjustment vector

Abstract: A computer-implemented method of changing a face within an output image or video frame includes: receiving an input image that includes a face presenting a facial expression in a pose; separately encoding different portions of the image by, for each separately encoded portion, generating a latent space point of the portion, thereby generating a plurality of multi-dimensional vectors where each multi-dimensional vector is an encoded representation of a different portion of the input image; concatenating the plurality of multi-dimensional vectors into a combined latent space vector; and decoding the combined latent space vector to generate the output image in accordance with a desired facial identity but with the facial expression and pose of the face in the input image

Abstract: Various embodiments set forth systems and techniques for evaluating media content items. The techniques include receiving visual feedback associated with one or more audience members viewing a first media content item; analyzing the visual feedback to generate one or more emotion signals based on the visual feedback; and generating a set of features associated with the one or more audience members viewing the first media content item based on the one or more emotion signals.

Abstract: Techniques are disclosed for characterizing audience engagement with one or more characters in a media content item. In some embodiments, an audience engagement characterization application processes sensor data, such as video data capturing the faces of one or more audience members consuming a media content item, to generate an audience emotion signal. The characterization application also processes the media content item to generate a character emotion signal associated with one or more characters in the media content item. Then, the characterization application determines an audience engagement score based on an amount of alignment and/or misalignment between the audience emotion signal and the character emotion signal.

Abstract: Various embodiments set forth systems and techniques for training a landmark model. The techniques include determining, using the landmark model, a first landmark in a set of first landmarks associated with a first image; performing, on the first image, a first perturbation to obtain a second image; determining, using the landmark model, a second landmark in a set of second landmarks associated with the second image; determining, based on a first distance between the first landmark and the second landmark, a first loss function; and updating, based on the first loss function, a first parameter of the landmark model.

Abstract: Techniques are disclosed for changing the identities of faces in images. In embodiments, a tunable model for changing facial identities in images includes an encoder, a decoder, and dense layers that generate either adaptive instance normalization (AdaIN) coefficients that control the operation of convolution layers in the decoder or the values of weights within such convolution layers, allowing the model to change the identity of a face in an image based on a user selection. A separate set of dense layers may be trained to generate AdaIN coefficients for each of a number of facial identities, and the AdaIN coefficients output by different sets of dense layers can be combined to interpolate between facial identities. Alternatively, a single set of dense layers may be trained to take as input an identity vector and output AdaIN coefficients or values of weighs within convolution layers of the decoder.

Abstract: Various embodiments set forth systems and techniques for changing a face within an image. The techniques include receiving a first image including a face associated with a first facial identity; generating, via a machine learning model, at least a first texture map and a first position map based on the first image; rendering a second image including a face associated with a second facial identity based on the first texture map and the first position map, wherein the second facial identity is different from the first facial identity.

Abstract: Various embodiments set forth systems and techniques for training a landmark model. The techniques include determining, using the landmark model, a first landmark in a set of first landmarks associated with a first image; performing, on the first image, a first perturbation to obtain a second image; determining, using the landmark model, a second landmark in a set of second landmarks associated with the second image; determining, based on a first distance between the first landmark and the second landmark, a first loss function; and updating, based on the first loss function, a first parameter of the landmark model.

Abstract: Techniques are disclosed for changing the identities of faces in video frames and images. In embodiments, three-dimensional (3D) geometry of a face is used to inform the facial identity change produced by an image-to-image translation model, such as a comb network model. In some embodiments, the model can take a two-dimensional (2D) texture map and/or a 3D displacement map associated with one facial identity as inputs and output another 2D texture map and/or 3D displacement map associated with a different facial identity. The other 2D texture map and/or 3D displacement map can then be used to render an image that includes the different facial identity.

Abstract: Techniques are disclosed for changing the identities of faces in images. In embodiments, a tunable model for changing facial identities in images includes an encoder, a decoder, and dense layers that generate either adaptive instance normalization (AdaIN) coefficients that control the operation of convolution layers in the decoder or the values of weights within such convolution layers, allowing the model to change the identity of a face in an image based on a user selection. A separate set of dense layers may be trained to generate AdaIN coefficients for each of a number of facial identities, and the AdaIN coefficients output by different sets of dense layers can be combined to interpolate between facial identities. Alternatively, a single set of dense layers may be trained to take as input an identity vector and output AdaIN coefficients or values of weighs within convolution layers of the decoder.