Abstract: Asing natural language to perform context-aware code generation, including: receiving a selection of code and a natural language task describing a modification to the selection of code; and generating, by a code generation model and based on information retrieved from a knowledge base provided as input to the code generation model, suggested code reflecting the modification to the selection of code.

Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations.

Abstract: A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.

Abstract: A methodology for training a machine learning model to generate color-neutral input face images is described. For each training face image from a training dataset that is used for training the model, the training system generates an input face image, which has the color and lighting of a randomly selected image from the set of color source images, and which has facial features and expression of a face object from the training face image. Because, during training, the machine learning model is “confused” by changing the color and lighting of a training face image to a randomly selected different color and lighting, the trained machine learning model generates a color neutral embedding representing facial features from the training face image.

Abstract: A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties.

Abstract: Provided are systems and methods for realistic head turns and face animation synthesis. An example method includes receiving a source frame of a source video, where the source frame includes a head and a face of a source actor, generating source pose parameters corresponding to a pose of the head and a facial expression of the source actor; receiving a target image including a target head and a target face of a target person, determining target identity information associated with the target head and the target face of the target person, replacing source identity information in the source pose parameters with the target identity information to obtain further source pose parameters, and generating an output frame of an output video that includes a modified image of the target face and the target head adopting the pose of the head and the facial expression of the source actor.

Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations.

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations.

Abstract: A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties.

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations.

Abstract: The proposed model is a Variational Autoencoder having a learnable prior that is parametrized with a Tensor Train (VAE-TTLP). The VAE-TTLP can be used to generate new objects, such as molecules, that have specific properties and that can have specific biological activity (when a molecule). The VAE-TTLP can be trained in a way with the Tensor Train so that the provided data may omit one or more properties of the object, and still result in an object with a desired property.

Abstract: Provided are systems and methods for realistic head turns and face animation synthesis. An example method includes receiving a source frame of a source video, where the source frame includes a head and a face of a source actor, generating source pose parameters corresponding to a pose of the head and a facial expression of the source actor; receiving a target image including a target head and a target face of a target person, determining target identity information associated with the target head and the target face of the target person, replacing source identity information in the source pose parameters with the target identity information to obtain further source pose parameters, and generating an output frame of an output video that includes a modified image of the target face and the target head adopting the pose of the head and the facial expression of the source actor.

Abstract: A methodology for training a machine learning model to generate color-neutral input face images is described. For each training face image from a training dataset that is used for training the model, the training system generates an input face image, which has the color and lighting of a randomly selected image from the set of color source images, and which has facial features and expression of a face object from the training face image. Because, during training, the machine learning model is “confused” by changing the color and lighting of a training face image to a randomly selected different color and lighting, the trained machine learning model generates a color neutral embedding representing facial features from the training face image.

Abstract: Provided are systems and methods for realistic head turns and face animation synthesis. An example method may include receiving frames of a source video with the head and the face of a source actor. The method may then proceed with generating sets of source pose parameters that represent positions of the head and facial expressions of the source actor. The method may further include receiving at least one target image including the target head and the target face of a target person, determining target identity information associated with the target face, and generating an output video based on the target identity information and the sets of source pose parameters. Each frame of the output video can include an image of the target face modified to mimic at least one of the positions of the head of the source actor and at least one of facial expressions of the source actor.

Abstract: A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.

Abstract: In some embodiments, users' experience of engaging with augmented reality technology is enhanced by providing a process, referred to as face animation synthesis, that replaces an actor's face in the frames of a video with a user's face from the user's portrait image. The resulting face in the frames of the video retains the facial expressions, as well as color and lighting, of the actor's face but, at the same time, has the likeness of the user's face. An example face animation synthesis experience can be made available to uses of a messaging system by providing a face animation synthesis augmented reality component.