Abstract: Systems and methods herein describe a video compression system. The described systems and methods accesses a sequence of image frames from a first computing device, the sequence of image frames comprising a first image frame and a second image frame, detects a first set of keypoints for the first image frame, transmits the first image frame and the first set of keypoints to a second computing device, detects a second set of keypoints for the second image frame, transmits the second set of keypoints to the second computing device, causes an animated image to be displayed on the second computing device.

Abstract: A multimodal video generation framework (MMVID) that benefits from text and images provided jointly or separately as input. Quantized representations of videos are utilized with a bidirectional transformer with multiple modalities as inputs to predict a discrete video representation. A new video token trained with self-learning and an improved mask-prediction algorithm for sampling video tokens is used to improve video quality and consistency. Text augmentation is utilized to improve the robustness of the textual representation and diversity of generated videos. The framework incorporates various visual modalities, such as segmentation masks, drawings, and partially occluded images. In addition, the MMVID extracts visual information as suggested by a textual prompt.

Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.

Abstract: Systems and methods are disclosed for generating, a source image sequence using an image sensor of the computing device, the source image sequence comprising a plurality of source images depicting a head and face, identifying driving image sequence data to modify face image feature data in the source image sequence, generating, using an image transformation neural network, a modified source image sequence comprising a plurality of modified source images depicting modified versions of the head and face, and storing the modified source image sequence on the computing device.

Abstract: Three-dimensional object representation and re-rendering systems and methods for producing a 3D representation of an object from 2D images including the object that enables object-centric rendering. A modular approach is used that optimizes a Neural Radiance Field (NeRF) model to estimate object geometry and refine camera parameters and, then, infer surface material properties and per-image lighting conditions that fit the 2D images.

Abstract: Techniques for training a neural network having a plurality of computational layers with associated weights and activations for computational layers in fixed-point formats include determining an optimal fractional length for weights and activations for the computational layers; training a learned clipping-level with fixed-point quantization using a PACT process for the computational layers; and quantizing on effective weights that fuses a weight of a convolution layer with a weight and running variance from a batch normalization layer. A fractional length for weights of the computational layers is determined from current values of weights using the determined optimal fractional length for the weights of the computational layers. A fixed-point activation between adjacent computational layers is related using PACT quantization of the clipping-level and an activation fractional length from a node in a following computational layer.

Abstract: A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.

Abstract: Systems and methods are disclosed for generating, a source image sequence using an image sensor of the computing device, the source image sequence comprising a plurality of source images depicting a head and face, identifying driving image sequence data to modify face image feature data in the source image sequence, generating, using an image transformation neural network, a modified source image sequence comprising a plurality of modified source images depicting modified versions of the head and face, and storing the modified source image sequence on the computing device.

Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.

Abstract: A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.

Abstract: Disclosed are various embodiments for implementing computational tasks in a cloud environment in one or more operating system level virtualized containers. A parameter file can specify different parameters including hardware parameters, library parameters, user code parameters, and job parameters (e.g., sets of hyperparameters). The parameter file can be converted via a mapping and implemented in a cloud-based container platform.

Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.

Abstract: A landmark detection system can more accurately detect landmarks in images using a detection scheme that penalizes for dispersion parameters, such as variance or scale. The landmark detection system can be trained using both labeled and unlabeled training data in a semi-supervised approach. The landmark detection system can further implement tracking of an object across multiple images using landmark data.

Abstract: System and methods for compressing image-to-image models. Generative Adversarial Networks (GANs) have achieved success in generating high-fidelity images. An image compression system and method adds a novel variant to class-dependent parameters (CLADE), referred to as CLADE-Avg, which recovers the image quality without introducing extra computational cost. An extra layer of average smoothing is performed between the parameter and normalization layers. Compared to CLADE, this image compression system and method smooths abrupt boundaries, and introduces more possible values for the scaling and shift. In addition, the kernel size for the average smoothing can be selected as a hyperparameter, such as a 3×3 kernel size. This method does not introduce extra multiplications but only addition, and thus does not introduce much computational overhead, as the division can be absorbed into the parameters after training.

Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

Abstract: Systems and methods herein describe an image compression system. The image compression system generates a first generative adversarial network (GAN), identifies a threshold, based on the threshold, generates a second GAN by pruning channels of the first GAN, trains the second GAN using similarity-based knowledge distillation from the first GAN, and stores the trained second GAN.

Abstract: Systems and methods herein describe a motion retargeting system. The motion retargeting system accesses a plurality of two-dimensional images comprising a person performing a plurality of body poses, extracts a plurality of implicit volumetric representations from the plurality of body poses, generates a three-dimensional warping field, the three-dimensional warping field configured to warp the plurality of implicit volumetric representations from a canonical pose to a target pose, and based on the three-dimensional warping field, generates a two-dimensional image of an artificial person performing the target pose.

Abstract: A landmark detection system can more accurately detect landmarks in images using a detection scheme that penalizes for dispersion parameters, such as variance or scale. The landmark detection system can be trained using both labeled and unlabeled training data in a semi-supervised approach. The landmark detection system can further implement tracking of an object across multiple images using landmark data.

Abstract: Disclosed are various embodiments for implementing computational tasks in a cloud environment in one or more operating system level virtualized containers. A parameter file can specify different parameters including hardware parameters, library parameters, user code parameters, and job parameters (e.g., sets of hyperparameters). The parameter file can be converted via a mapping and implemented in a cloud-based container platform.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for video synthesis. The program and method provide for accessing a primary generative adversarial network (GAN) comprising a pre-trained image generator, a motion generator comprising a plurality of neural networks, and a video discriminator; generating an updated GAN based on the primary GAN, by performing operations comprising identifying input data of the updated GAN, the input data comprising an initial latent code and a motion domain dataset, training the motion generator based on the input data, and adjusting weights of the plurality of neural networks of the primary GAN based on an output of the video discriminator; and generating a synthesized video based on the primary GAN and the input data.