Abstract: There is provided methods, devices and techniques to process an image using a deep learning model to achieve continuous effect simulation by a unified network where a simple (effect class) estimator is embedded into a regular encoder-decoder architecture. The estimator allows learning of model-estimated class embeddings of all effect classes (e.g. progressive degrees of the effect), thus representing the continuous effect information without manual efforts in selecting proper anchor effect groups. In an embodiment, given a target age class, there is derived a personalized age embedding which considers two aspects of face aging: 1) a personalized residual age embedding at a model-estimated age of the subject, preserving the subject's aging information; and 2) exemplar-face aging basis at the target age, encoding the shared aging patterns among the entire population.

Abstract: GANs based generators are useful to perform image to image translations. GANs models have large storage sizes and resource use requirements such that they are too large to be deployed directly on mobile devices. Systems and methods define through conditioning a student GANs model having a student generator that is scaled downwardly from a teacher GANs model (and generator) using knowledge distillation. A semantic relation knowledge distillation loss is used to transfer semantic knowledge from an intermediate layer of the teacher to an intermediate layer of the student. Student generators thus defined are stored and executed by mobile devices such as smartphones and laptops to provide augmented reality experiences. Effects are simulated on images, including makeup, hair, nail and age simulation effects.

Abstract: Methods and systems are provided for estimating the selection probability of a digital object on a website or application by a human based on features extracted from an image, a video, or input text description of the object by a user. A communication interface receives the input from the user. Memory is provided for storing a neural network model, selection probability prediction and training data, the training data including a first training dataset and a second training dataset. The neural network model is trained in a pre-training step with the first training dataset and is followed by a fine-tuning step with the second training dataset to obtain a multi-layer neural network. Input is provided to the multi-layer neural network to obtain a classification vector. Based on the classification vector, a selection probability prediction is calculated and delivered to the user through the communication interface.

Abstract: There is described a deep learning supervised regression based model including methods and systems for facial attribute prediction and use thereof. An example of use is an augmented and/or virtual reality interface to provide a modified image responsive to facial attribute predictions determined from the image. Facial effects matching facial attributes are selected to be applied in the interface.

Abstract: Computer-implemented methods of using artificial intelligence (AI) to simulate user experiences with websites or applications can be used to improve the design and functions of computing systems supporting the platform for the website or application. The methods may involve one or more of the following: creating models of virtual users defined by parameters characterizing intent, identifying user options provided by the websites or applications, generating probabilistic networks defining transition dependencies between the identified options, and simulating the user experiences with websites or applications based on the user models.

Abstract: A method, apparatus and system according to embodiments provide image-to-image translations such as synthesis of ultraviolet (UV) images from input images in a RGB (red, green blue) color model. In an embodiment, a trained generator generates overlapping UV patch images from overlapping RBG patch images extracted from an input image. The overlapping UV patch images are blended using a Gaussian weighting factor applied to overlapping pixels having a same location in the input image. The Gaussian blending distributes weights to pixels relative to the pixel's distance to the center of its patch, with weighting being highest at the center.

Abstract: Techniques are provided for computing systems, methods and computer program products to produce efficient image-to-image translation by adapting unpaired datasets for supervised learning. A first model (a powerful model) may be defined and conditioned using unsupervised learning to produce a synthetic paired dataset from the unpaired dataset, translating images from a first domain to a second domain and images from the second domain to the first domain. The synthetic data generated is useful as ground truths in supervised learning. The first model may be conditioned to overfit the unpaired dataset to enhance the quality of the paired dataset (e.g. the synthetic data generated). A run-time model such as for a target device is trained using the synthetic paired dataset and supervised learning. The run-time model is small and fast to meet the processing resources of the target device (e.g. a personal user device such as a smart phone, tablet, etc.

Abstract: There is described a deep learning supervised regression based model including methods and systems for facial attribute prediction and use thereof. An example of use is an augmented and/or virtual reality interface to provide a modified image responsive to facial attribute predictions determined from the image. Facial effects matching facial attributes are selected to be applied in the interface.

Abstract: Systems and methods process images to determine a skin condition severity analysis and to visualize a skin analysis such as using a deep neural network (e.g. a convolutional neural network) where a problem was formulated as a regression task with integer-only labels. Auxiliary classification tasks (for example, comprising gender and ethnicity predictions) are introduced to improve performance. Scoring and other image processing techniques may be used (e.g. in assoc. with the model) to visualize results such as highlighting the analyzed image. It is demonstrated that the visualization of results, which highlight skin condition affected areas, can also provide perspicuous explanations for the model. A plurality (k) of data augmentations may be made to a source image to yield k augmented images for processing. Activation masks (e.g. heatmaps) produced from processing the k augmented images are used to define a final map to visualize the skin analysis.

Abstract: Methods, apparatus and techniques herein relates to determining directions in GAN latent space and obtaining disentangled controls over GAN output semantics, for example, to enable use of such to generating synthesized images such as for use to train another model or create an augmented reality The methods, apparatus and techniques herein, in accordance with embodiments, utilize the gradient directions of auxiliary networks to control semantics in GAN latent codes. It is shown that minimal amounts of labelled data with sizes as small as 60 samples can be used, which data can be obtained quickly with human supervision. It is also shown herein, in accordance with embodiments, to select important latent code channels with masks during manipulation, resulting in more disentangled controls.

Abstract: A system and method implement deep learning on a mobile device to provide a convolutional neural network (CNN) for real time processing of video, for example, to color hair. Images are processed using the CNN to define a respective hair matte of hair pixels. The respective object mattes may be used to determine which pixels to adjust when adjusting pixel values such as to change color, lighting, texture, etc. The CNN may comprise a (pre-trained) network for image classification adapted to produce the segmentation mask. The CNN may be trained for image segmentation (e.g. using coarse segmentation data) to minimize a mask-image gradient consistency loss. The CNN may further use skip connections between corresponding layers of an encoder stage and a decoder stage where shallower layers in the encoder, which contain high-res but weak features are combined with low resolution but powerful features from deeper decoder layers.

Abstract: There is shown and described a deep learning based system and method for skin diagnostics as well as testing metrics that show that such a deep learning based system outperforms human experts on the task of apparent skin diagnostics. Also shown and described is a system and method of monitoring a skin treatment regime using a deep learning based system and method for skin diagnostics.

Abstract: This document relates to hybrid eye center localization using machine learning, namely cascaded regression and hand-crafted model fitting to improve a computer. There are proposed systems and methods of eye center (iris) detection using a cascade regressor (cascade of regression forests) as well as systems and methods for training a cascaded regressor. For detection, the eyes are detected using a facial feature alignment method. The robustness of localization is improved by using both advanced features and powerful regression machinery. Localization is made more accurate by adding a robust circle fitting post-processing step. Finally, using a simple hand-crafted method for eye center localization, there is provided a method to train the cascaded regressor without the need for manually annotated training data. Evaluation of the approach shows that it achieves state-of-the-art performance.

Abstract: There are provided methods and computing devices using semi-supervised learning to perform end-to-end video object segmentation, tracking respective object(s) from a single-frame annotation of a reference frame through a video sequence of frames. A known deep learning model may be used to annotate the reference frame to provide ground truth locations and masks for each respective object. A current frame is processed to determine current frame object locations, defining object scoremaps as a normalized cross-correlation between encoded object features of the current frame and encoded object features of a previous frame. Scoremaps for each of more than one previous frame may be defined. An Intersection over Union (IoU) function, responsive to the scoremaps, ranks candidate object proposals defined from the reference frame annotation to associate the respective objects to respective locations in the current frame. Pixel-wise overlap may be removed using a merge function responsive to the scoremaps.

Abstract: Techniques are provided for computing systems, methods and computer program products to produce efficient image-to-image translation by adapting unpaired datasets for supervised learning. A first model (a powerful model) may be defined and conditioned using unsupervised learning to produce a synthetic paired dataset from the unpaired dataset, translating images from a first domain to a second domain and images from the second domain to the first domain. The synthetic data generated is useful as ground truths in supervised learning. The first model may be conditioned to overfit the unpaired dataset to enhance the quality of the paired dataset (e.g. the synthetic data generated). A run-time model such as for a target device is trained using the synthetic paired dataset and supervised learning. The run-time model is small and fast to meet the processing resources of the target device (e.g. a personal user device such as a smart phone, tablet, etc.

Abstract: Systems and methods relate to a network model to apply an effect to an image such as an augmented reality effect (e.g. makeup, hair, nail, etc.). The network model uses a conditional cycle-consistent generative image-to-image translation model to translate images from a first domain space where the effect is not applied and to a second continuous domain space where the effect is applied. In order to render arbitrary effects (e.g. lipsticks) not seen at training time, the effect's space is represented as a continuous domain (e.g. a conditional variable vector) learned by encoding simple swatch images of the effect, such as are available as product swatches, as well as a null effect. The model is trained end-to-end in an unsupervised fashion. To condition a generator of the model, convolutional conditional batch normalization (CCBN) is used to apply the vector encoding the reference swatch images that represent the makeup properties.

Abstract: There is shown and described a deep learning based system and method for skin diagnostics as well as testing metrics that show that such a deep learning based system outperforms human experts on the task of apparent skin diagnostics. Also shown and described is a system and method of monitoring a skin treatment regime using a deep learning based system and method for skin diagnostics.

Abstract: Techniques are provided for computing systems, methods and computer program products to produce efficient image-to-image translation by adapting unpaired datasets for supervised learning. A first model (a powerful model) may be defined and conditioned using unsupervised learning to produce a synthetic paired dataset from the unpaired dataset, translating images from a first domain to a second domain and images from the second domain to the first domain. The synthetic data generated is useful as ground truths in supervised learning. The first model may be conditioned to overfit the unpaired dataset to enhance the quality of the paired dataset (e.g. the synthetic data generated). A run-time model such as for a target device is trained using the synthetic paired dataset and supervised learning. The run-time model is small and fast to meet the processing resources of the target device (e.g. a personal user device such as a smart phone, tablet, etc.

Abstract: There is shown and described a deep learning based system and method for skin diagnostics as well as testing metrics that show that such a deep learning based system outperforms human experts on the task of apparent skin diagnostics. Also shown and described is a system and method of monitoring a skin treatment regime using a deep learning based system and method for skin diagnostics.

Abstract: Provided are systems and methods to perform colour extraction from swatch images and to define new images using extracted colours. Source images may be classified using a deep learning net (e.g. a CNN) to indicate colour representation strength and drive colour extraction. A clustering classifier is trained to use feature vectors extracted by the net. Separately, pixel clustering is useful when extracting the colour. Cluster count can vary according to classification. In another manner, heuristics (with or without classification) are useful when extracting. Resultant clusters are evaluated against a set of (ordered) expected colours to determine a match. Instances of standardized swatch images may be defined from a template swatch image and respective extracted colours using image processing. The extracted colour may be presented in an augmented reality GUI such as a virtual try-on application and applied to a user image such as a selfie using image processing.