Abstract: Technologies are described and recited herein for producing controllable synthesized images include a geometry guided 3D GAN framework for high-quality 3D head synthesis with full control on camera poses, facial expressions, head shape, articulated neck and jaw poses; and a semantic SDF (signed distance function) formulation that defines volumetric correspondence from observation space to canonical space, allowing full disentanglement of control parameters in 3D GAN training.

Abstract: A method of generating a stylized 3D avatar is provided. The method includes receiving an input image of a user, generating, using a generative adversarial network (GAN) generator, a stylized image, based on the input image, and providing the stylized image to a first model to generate a first plurality of parameters. The first plurality of parameters include a discrete parameter and a continuous parameter. The method further includes providing the stylized image and the first plurality of parameters to a second model that is trained to generate an avatar image, receiving, from the second model, the avatar image, comparing the stylized image to the avatar image, based on a loss function, to determine an error, updating the first model to generate a second plurality of parameters that correspond to the first plurality of parameters, based on the error, and providing the second plurality of parameters as an output.

Abstract: A method of generating a style image is described. The method includes receiving an input image of a subject. The method further includes encoding the input image using a first encoder of a generative adversarial network (GAN) to obtain a first latent code. The method further includes decoding the first latent code using a first decoder of the GAN to obtain a normalized style image of the subject, wherein the GAN is trained using a loss function according to semantic regions of the input image and the normalized style image.

Abstract: Systems and methods directed to controlling the similarity between stylized portraits and an original photo are described. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be blended with latent vectors that best represent a face in the original user portrait image. The resulting blended latent vector may be provided to a generative adversarial network (GAN) generator to generate a controlled stylized image. In examples, one or more layers of the stylized GAN generator may be swapped with one or more layers of the original GAN generator. Accordingly, a user can interactively determine how much stylization vs. personalization should be included in a resulting stylized portrait.

Abstract: Methods and systems for enlarging a stylized region of an image are disclosed that include receiving an input image, generating, using a first generative adversarial network (GAN) generator, a first stylized image, based on the input image, normalizing the input image, generating, using a second generative adversarial network (GAN) generator, a second stylized image, based on the normalized input image, blending the first stylized image and the second stylized image to obtain a third stylized image, and providing the third stylized image as an output.

Abstract: Methods and systems for generating a texturized image are disclosed. Some examples may include: receiving an input image, receiving an exemplar texture image, generating, using an encoder, a first latent code vector representation based on the input image, generating, using a generative adversarial network generator, a second latent code vector representation based on the exemplar texture image, blending the first latent code vector representation and the second latent code vector representation to obtain a blended latent code vector representation, generating, by the GAN generator, a texturized image based on the blended latent code vector representation and providing the texturized image as an output image.

Abstract: Systems and methods for rendering a translucent object are provided. In one aspect, the system includes a processor coupled to a storage medium that stores instructions, which, upon execution by the processor, cause the processor to receive at least one mesh representing at least one translucent object. For each pixel to be rendered, the processor performs a rasterization-based differentiable rendering of the pixel to be rendered using the at least one mesh and determines a plurality of values for the pixel to be rendered based on the rasterization-based differentiable rendering. The rasterization-based differentiable rendering can include performing a probabilistic rasterization process along with aggregation techniques to compute the plurality of values for the pixel to be rendered. The plurality of values includes a set of color channel values and an opacity channel value. Once values are determined for all pixels, an image can be rendered.

Abstract: A method for generating a multi-dimensional stylized image. The method includes providing input data into a latent space for a style conditioned multi-dimensional generator of a multi-dimensional generative model and generating the multi-dimensional stylized image from the input data by the style conditioned multi-dimensional generator. The method further includes synthesizing content for the multi-dimensional stylized image using a latent code and corresponding camera pose from the latent space to formulate an intermediate code to modulate synthesis convolution layers to generate feature images as multi-planar representations and synthesizing stylized feature images of the feature images for generating the multi-dimensional stylized image of the input data. The style conditioned multi-dimensional generator is tuned using a guided transfer learning process using a style prior generator.

Abstract: Technologies are described and recited herein for producing controllable synthesized images include a geometry guided 3D GAN framework for high-quality 3D head synthesis with full control on camera poses, facial expressions, head shape, articulated neck and jaw poses; and a semantic SDF (signed distance function) formulation that defines volumetric correspondence from observation space to canonical space, allowing full disentanglement of control parameters in 3D GAN training.

Abstract: A three-dimensional generative adversarial network includes a generator, a discriminator, and a renderer. The generator is configured to receive an intermediate latent code mapped from a latent code and a camera pose, generate two-dimensional backgrounds for a set of images, and generate, based on the intermediate latent code, multi-grid representation features. The renderer is configured to synthesize images based on the camera pose, a camera pose offset, and the multi-grid representation features; the camera pose offset being mapped from the latent code and the camera pose; and render a foreground mask. The discriminator is configured to supervise a training of the foreground mask with an up-sampled image and a super-resolved image.

Abstract: A method of generating a style image is described. The method includes receiving an input image of a subject. The method further includes encoding the input image using a first encoder of a generative adversarial network (GAN) to obtain a first latent code. The method further includes decoding the first latent code using a first decoder of the GAN to obtain a normalized style image of the subject, wherein the GAN is trained using a loss function according to semantic regions of the input image and the normalized style image.

Abstract: A method of generating a stylized 3D avatar is provided. The method includes receiving an input image of a user, generating, using a generative adversarial network (GAN) generator, a stylized image, based on the input image, and providing the stylized image to a first model to generate a first plurality of parameters. The first plurality of parameters include a discrete parameter and a continuous parameter. The method further includes providing the stylized image and the first plurality of parameters to a second model that is trained to generate an avatar image, receiving, from the second model, the avatar image, comparing the stylized image to the avatar image, based on a loss function, to determine an error, updating the first model to generate a second plurality of parameters that correspond to the first plurality of parameters, based on the error, and providing the second plurality of parameters as an output.

Abstract: Systems and method directed to generating a stylized image are disclosed. In particular, the method includes, in a first data path, (a) applying first stylization to an input image and (b) applying enlargement to the stylized image from (a). The method also includes, in a second data path, (c) applying segmentation to the input image to identify a face region of the input image and generate a mask image, and (d) applying second stylization to an entirety of the input image and inpainting to the identified face region of the stylized image. Machine-assisted blending is performed based on (1) the stylized image after the enlargement from the first data path, (2) the inpainted image from the second data path, and (3) the mask image, in order to obtain a final stylized image.

Abstract: Systems and methods for rendering a translucent object are provided. In one aspect, the system includes a processor coupled to a storage medium that stores instructions, which, upon execution by the processor, cause the processor to receive at least one mesh representing at least one translucent object. For each pixel to be rendered, the processor performs a rasterization-based differentiable rendering of the pixel to be rendered using the at least one mesh and determines a plurality of values for the pixel to be rendered based on the rasterization-based differentiable rendering. The rasterization-based differentiable rendering can include performing a probabilistic rasterization process along with aggregation techniques to compute the plurality of values for the pixel to be rendered. The plurality of values includes a set of color channel values and an opacity channel value. Once values are determined for all pixels, an image can be rendered.

Abstract: Methods and systems for enlarging a stylized region of an image are disclosed that include receiving an input image, generating, using a first generative adversarial network (GAN) generator, a first stylized image, based on the input image, normalizing the input image, generating, using a second generative adversarial network (GAN) generator, a second stylized image, based on the normalized input image, blending the first stylized image and the second stylized image to obtain a third stylized image, and providing the third stylized image as an output.

Abstract: Methods and systems for generating synthetic images based on an input image are described. The method may include receiving an input image; generating, using an encoder, a first latent code vector representation based on the input image; receiving a latent code corresponding to a feature to be added to the input image; modifying the first latent code vector representation based on the latent code corresponding to the feature to be added; generating, by an image decoder, a synthesized image based on the modified first latent code vector representation; identifying, using a landmark detector, one or more landmarks in the base image; identifying, using a landmark detector, one or more landmarks in the synthesized image; determining a measure of similarity between the landmark identified on the base image and the landmark identified in the synthesized image; and discarding the synthesized image based on the comparison.

Abstract: Systems and method directed to an inversion-consistent transfer learning framework for generating portrait stylization using only limited exemplars. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be provided to a generative adversarial network (GAN) generator to generate a stylized image. In examples, the variational autoencoder is trained using a plurality of images while keeping the weights of a pre-trained GAN generator fixed, where the pre-trained GAN generator acts as a decoder for the encoder. In other examples, a multi-path attribute aware generator is trained using a plurality of exemplar images and learning transfer using the pre-trained GAN generator.

Abstract: Systems and methods directed to controlling the similarity between stylized portraits and an original photo are described. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be blended with latent vectors that best represent a face in the original user portrait image. The resulting blended latent vector may be provided to a generative adversarial network (GAN) generator to generate a controlled stylized image. In examples, one or more layers of the stylized GAN generator may be swapped with one or more layers of the original GAN generator. Accordingly, a user can interactively determine how much stylization vs. personalization should be included in a resulting stylized portrait.

Abstract: Systems and method directed to generating a stylized image are disclosed. In particular, the method includes, in a first data path, (a) applying first stylization to an input image and (b) applying enlargement to the stylized image from (a). The method also includes, in a second data path, (c) applying segmentation to the input image to identify a face region of the input image and generate a mask image, and (d) applying second stylization to an entirety of the input image and inpainting to the identified face region of the stylized image. Machine-assisted blending is performed based on (1) the stylized image after the enlargement from the first data path, (2) the inpainted image from the second data path, and (3) the mask image, in order to obtain a final stylized image.

Abstract: Systems and method directed to an inversion-consistent transfer learning framework for generating portrait stylization using only limited exemplars. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be provided to a generative adversarial network (GAN) generator to generate a stylized image. In examples, the variational autoencoder is trained using a plurality of images while keeping the weights of a pre-trained GAN generator fixed, where the pre-trained GAN generator acts as a decoder for the encoder. In other examples, a multi-path attribute aware generator is trained using a plurality of exemplar images and learning transfer using the pre-trained GAN generator.