Abstract: Systems and methods for facial image generation are described. One aspect of the systems and methods includes receiving an image depicting a face, wherein the face has an identity non-related attribute and a first identity-related attribute; encoding the image to obtain an identity non-related attribute vector in an identity non-related attribute vector space, wherein the identity non-related attribute vector represents the identity non-related attribute; selecting an identity-related vector from an identity-related vector space, wherein the identity-related vector represents a second identity-related attribute different from the first identity-related attribute; generating a modified latent vector in a latent vector space based on the identity non-related attribute vector and the identity-related vector; and generating a modified image based on the modified latent vector, wherein the modified image depicts a face that has the identity non-related attribute and the second identity-related attribute.

Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.

Abstract: The present disclosure describes systems and methods for information retrieval. Embodiments of the disclosure provide a color embedding network trained using machine learning techniques to generate embedded color representations for color terms included in a text search query. For example, techniques described herein are used to represent color text in a same space as color embeddings (e.g., an embedding space created by determining a histogram of LAB based colors in a three-dimensional (3D) space). Further, techniques are described for indexing color palettes for all the searchable images in the search space. Accordingly, color terms in a text query are directly converted into a color palette and an image search system can return one or more search images with corresponding color palettes that are relevant to (e.g., within a threshold distance from) the color palette of the text query.

Abstract: Embodiments are disclosed for finding similar persons in images. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an image query, the image query including an input image that includes a representation of a person, generating a first cropped image including a representation of the person's face and a second cropped image including a representation of the person's body, generating an image embedding for the input image by combining a face embedding corresponding to the first cropped image and a body embedding corresponding to the second cropped image, and querying an image repository in embedding space by comparing the image embedding to a plurality of image embeddings associated with a plurality of images in the image repository to obtain one or more images based on similarity to the input image in the embedding space.

Abstract: Embodiments of the technology described herein, provide improved visual search results by combining a visual similarity and a textual similarity between images. In an embodiment, the visual similarity is quantified as a visual similarity score and the textual similarity is quantified as a textual similarity score. The textual similarity is determined based on text, such as a title, associated with the image. The overall similarity of two images is quantified as a weighted combination of the textual similarity score and the visual similarity score. In an embodiment, the weighting between the textual similarity score and the visual similarity score is user configurable through a control on the search interface. In one embodiment, the aggregate similarity score is the sum of a weighted visual similarity score and a weighted textual similarity score.

Abstract: Systems and methods for facial image generation are described. One aspect of the systems and methods includes receiving an image depicting a face, wherein the face has an identity non-related attribute and a first identity-related attribute; encoding the image to obtain an identity non-related attribute vector in an identity non-related attribute vector space, wherein the identity non-related attribute vector represents the identity non-related attribute; selecting an identity-related vector from an identity-related vector space, wherein the identity-related vector represents a second identity-related attribute different from the first identity-related attribute; generating a modified latent vector in a latent vector space based on the identity non-related attribute vector and the identity-related vector; and generating a modified image based on the modified latent vector, wherein the modified image depicts a face that has the identity non-related attribute and the second identity-related attribute.

Abstract: Embodiments of the technology described herein, are an intelligent system that aims to expedite a text design process by providing text design predictions interactively. The system works with a typical text design scenario comprising a background image and one or more text strings as input. In the design scenario, the text string is to be placed on top of the background. The textual design agent may include a location recommendation model that recommends a location on the background image to place the text. The textual design agent may also include a font recommendation model, a size recommendation model, and a color recommendation model. The output of these four models may be combined to generate draft designs that are evaluated as a whole (combination of color, font, and size) for the best designs. The top designs may be output to the user.

Abstract: Embodiments are disclosed for automatic object re-colorization in images. In some embodiments, a method of automatic object re-colorization includes receiving a request to recolor an object in an image, the request including an object identifier and a color identifier, identifying an object in the image associated with the object identifier, generating a mask corresponding to the object in the image, providing the image, the mask, and the color identifier to a color transformer network, the color transformer network trained to recolor objects in input images, and generating, by the color transformer network, a recolored image, wherein the object in the recolored image has been recolored to a color corresponding to the color identifier.

Abstract: Systems and methods for image processing are described. One or more embodiments of the present disclosure identify a latent vector representing an image of a face, identify a target attribute vector representing a target attribute for the image, generate a modified latent vector using a mapping network that converts the latent vector and the target attribute vector into a hidden representation having fewer dimensions than the latent vector, wherein the modified latent vector is generated based on the hidden representation, and generate a modified image based on the modified latent vector, wherein the modified image represents the face with the target attribute.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for latent-based editing of digital images using a generative neural network. In particular, in one or more embodiments, the disclosed systems perform latent-based editing of a digital image by mapping a feature tensor and a set of style vectors for the digital image into a joint feature style space. In one or more implementations, the disclosed systems apply a joint feature style perturbation and/or modification vectors within the joint feature style space to determine modified style vectors and a modified feature tensor. Moreover, in one or more embodiments the disclosed systems generate a modified digital image utilizing a generative neural network from the modified style vectors and the modified feature tensor.

Abstract: Methods, systems, and non-transitory computer readable media are disclosed for intelligently enhancing details in edited images. The disclosed system iteratively updates residual detail latent code for segments in edited images where detail has been lost through the editing process. More particularly, the disclosed system enhances an edited segment in an edited image based on details in a detailed segment of an image. Additionally, the disclosed system may utilize a detail neural network encoder to project the detailed segment and a corresponding segment of the edited image into a residual detail latent code. In some embodiments, the disclosed system generates a refined edited image based on the residual detail latent code and a latent vector of the edited image.

Abstract: Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly identifying digital images with similar style to a query digital image using fine-grain style determination via weakly supervised style extraction neural networks. For example, the disclosed systems can extract a style embedding from a query digital image using a style extraction neural network such as a novel two-branch autoencoder architecture or a weakly supervised discriminative neural network. The disclosed systems can generate a combined style embedding by combining complementary style embeddings from different style extraction neural networks. Moreover, the disclosed systems can search a repository of digital images to identify digital images with similar style to the query digital image.

Abstract: In implementations of multi-resolution color-based image search, an image search system determines a color vector for a query image based on a color histogram of the query image by concatenating two color histograms having different resolutions. The image search system can compute distance measures between the color vector of the query image and color vectors of candidate images. The image search system can select one or more of the candidate images to return based on the distance measures utilizing the distance measures as indication of color similarity of the candidate images to the query image.

Abstract: A query image is received, along with a query to initiate a search process to find other images based on the query image. The query includes a preference value associated with an attribute, the preference value indicative of a level of emphasis to be placed on the attribute during the search. A full query vector, which is within a first dimensional space and representative of the query image, is generated. The full query vector is projected to a reduced dimensional space having a dimensionality lower than the first dimensional space, to generate a query vector. An attribute direction corresponding to the attribute is identified. A plurality of candidate vectors of the reduced dimensional space is searched, based on the attribute direction, the query vector, and the preference value, to identify a target vector of the plurality of candidate vectors. A target image, representative of the target vector, is displayed.

Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.

Abstract: Systems and methods for image retrieval are described. Embodiments of the present disclosure receive a search query from a user; extract an entity and a color phrase describing the entity from the search query; generate an entity color embedding in a color embedding space from the color phrase using a multi-modal color encoder; identify an image in a database based on metadata for the image including an object label corresponding to the extracted entity and an object color embedding in the color embedding space corresponding to the object label; and provide image information for the image to the user based on the metadata.

Abstract: Multi-modal differential search with real-time focus adaptation techniques are described that overcome the challenges of conventional techniques in a variety of ways. In one example, a model is trained to support a visually guided machine-learning embedding space that supports visual intuition as to “what” is represented by text. The visually guided language embedding space supported by the model, once trained, may then be used to support visual intuition as part of a variety of functionality. In one such example, the visually guided language embedding space as implemented by the model may be leveraged as part of a multi-modal differential search to support search of digital images and other digital content with real-time focus adaptation which overcomes the challenges of conventional techniques.

Abstract: Visually guided machine-learning language model and embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. In one example, a model is trained to support a visually guided machine-learning embedding space that supports visual intuition as to “what” is represented by text. The visually guided language embedding space supported by the model, once trained, may then be used to support visual intuition as part of a variety of functionality. In one such example, the visually guided language embedding space as implemented by the model may be leveraged as part of a multi-modal differential search to support search of digital images and other digital content with real-time focus adaptation which overcomes the challenges of conventional techniques.