Abstract: The present disclosure describes techniques for generating three-dimensional videos based on text using machine learning models. Text and inputting data indicative of a set of multi-view images are input into a machine learning model. Content of the set of multi-view images is associated with the input text. The machine learning model comprises a plurality of sub-models corresponding to a plurality of sets of camera parameters. A plurality of sets of multi-view images is generated based on corresponding camera parameters by the plurality of sub-models. The plurality of sub-models are configured to run in parallel to generate the plurality of sets of multi-view images. A three-dimensional (3D) video is generated based on the plurality of sets of multi-view images. Content of the 3D video is associated with the input text.

Abstract: The present disclosure provides an image processing method and device. The image processing method includes: performing, by an encoder and a first model, multiple iterations on an initial image to obtain a target image feature corresponding to the initial image; and performing, by a second model, image reconstruction based on the target image feature to obtain a reconstructed image of the initial image, both of the first model and the second model being neural networks for image reconstruction, wherein in the multiple iterations, an image feature extracted by the first model in the image reconstruction and an output image of the first model are feedback information for the encoder to assist the encoder in encoding the initial image.

Abstract: An image generation system is described. The system comprises a neural network model configured to perform a diffusion process to generate a set of multi-view images from a same input prompt. The set of multi-view images have a same subject from different view orientation. The neural network model comprises a self-attention layer configured to relate pixels across the set of multi-view images.

Abstract: The present disclosure provides a video generation method and device. The video generation method includes: extracting a first image feature from a first image; obtaining a plurality of intermediate image features by means of nonlinear interpolation according to the first image feature and a second image feature, wherein the second image feature is an image feature of a second image; and performing image reconstruction by means of an image generation model based on the first image feature, the second image feature, and the plurality of intermediate image features, so as to generate a target video, wherein the target video is used for presenting a process of a gradual change from the first image to the second image.

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 computer-implemented method for implementing face recognition includes receiving training data including a plurality of augmented images each corresponding to a respective one of a plurality of input images augmented by one of a plurality of variations, splitting a feature embedding generated from the training data into a plurality of sub-embeddings each associated with one of the plurality of variations, associating each of the plurality of sub-embeddings with respective ones of a plurality of confidence values, and applying a plurality of losses including a confidence-aware identification loss and a variation-decorrelation loss to the plurality of sub-embeddings and the plurality of confidence values to improve face recognition performance by learning the plurality of sub-embeddings.

Abstract: Systems and methods are disclosed for training a generative adversarial network (GAN) to transform images of one type (e.g., a selfie) to images of a second type (e.g., an ID document image). Once trained, the GAN may be utilized to generate an augmented training set that includes pairs of images (e.g., an image of the first type paired with an image of the second type, an image of the second type generated from an image of the first type paired with an image of the second type). The augmented training data set may be utilized to train a matching model to identify when subsequent input images (e.g., a selfie and an ID image, an ID image generated from a selfie and an actual ID image) match.

Abstract: A computer-implemented method for implementing face recognition includes receiving training data including a plurality of augmented images each corresponding to a respective one of a plurality of input images augmented by one of a plurality of variations, splitting a feature embedding generated from the training data into a plurality of sub-embeddings each associated with one of the plurality of variations, associating each of the plurality of sub-embeddings with respective ones of a plurality of confidence values, and applying a plurality of losses including a confidence-aware identification loss and a variation-decorrelation loss to the plurality of sub-embeddings and the plurality of confidence values to improve face recognition performance by learning the plurality of sub-embeddings.