Disney Enterprises, Inc.

Eth Zurich (eidgenossische Technische Hochschule Zurich)

Lucasfilm Entertainment Company Ltd.

Eth Zurich (eidgenssische Technische Hochschule Zurich)

Romann Matthew Weber

Christopher Richard Schroers

Jacek Krzysztof Naruniec

Scott C Labrozzi

Erika Varis Doggett

Jared McPhillen

Mauro Bamert

Derek Edward Bradley

Paulo Fabiano Urnau Gotardo

Leonhard Markus Helminger

Stephan Marcel Mandt

Dennis Li

Aaron Michael Baker

Evan Goldberg

Farnood Salehi

Stéphane Grabli

Thomas Etterlin

Sirak Ghebremusse

Mary Nell Borst

Christopher Andreas Otto

Dustin Clint Tucker

Leonard Markus Helminger

Graziana Mignone

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.

Method and system for deep learning based face swapping with multiple encoders

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.

Multi-camera face swapping

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.

Method and system for latent-space facial feature editing in deep learning based face swapping

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.

Behavior-based computer vision model for content selection

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.

Face swapping with neural network-based geometry refining

Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

Systems and methods for image compression at multiple, different bitrates

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.

Characterizing audience engagement based on emotional alignment with characters

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.

Method for temporal stabilization of landmark localization

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.

Tunable models for changing faces in images

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.

Three-dimensional geometry-based models for changing facial identities in video frames and images

An image synthesis system includes a computing platform having a hardware processor and a system memory storing a software code including a neural encoder and multiple neural decoders each corresponding to a respective persona. The hardware processor executes the software code to receive target image data, and source data that identifies one of the personas, and to map the target image data to its latent space representation using the neural encoder. The software code further identifies one of the neural decoders for decoding the latent space representation of the target image data based on the persona identified by the source data, uses the identified neural decoder to decode the latent space representation of the target image data as the persona identified by the source data to produce a swapped image data, and blends the swapped image data with the target image data to produce one or more synthesized images.

Automated image synthesis using a comb neural network architecture

Systems and methods for distortion removal at multiple quality levels are disclosed. In one embodiment, a method may include receiving training content. The training content may include original content, reconstructed content, and training distortion quality levels corresponding to the reconstructed content. The reconstructed content may be derived from distorted original content. The method may also include training distortion quality levels corresponding to the reconstructed content. The method may further include receiving an initial distortion removal model. The method may include generating a conditioned distortion removal model by training the initial distortion removal model using the training content. The method may further include storing the conditioned distortion removal model.

Growing community of inventors

Uster, Switzerland

Romann Matthew Weber