Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.

Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.

Abstract: Techniques include introducing a neural generator configured to produce novel faces that can be rendered at free camera viewpoints (e.g., at any angle with respect to the camera) and relit under an arbitrary high dynamic range (HDR) light map. A neural implicit intrinsic field takes a randomly sampled latent vector as input and produces as output per-point albedo, volume density, and reflectance properties for any queried 3D location. These outputs are aggregated via a volumetric rendering to produce low resolution albedo, diffuse shading, specular shading, and neural feature maps. The low resolution maps are then upsampled to produce high resolution maps and input into a neural renderer to produce relit images.

Abstract: Techniques of tracking a user's gaze includes identifying a region of a display at which a gaze of a user is directed, the region including a plurality of pixels. By determining a region rather than a point, when the regions correspond to elements of a user interface, the improved technique enables a system to activate the element to which a determined region is selected. In some implementations, the system makes the determination using a classification engine including a convolutional neural network; such an engine takes as input images of the user's eye and outputs a list of probabilities that the gaze is directed to each of the regions.

Abstract: Example embodiments relate to techniques for volumetric performance capture with neural rendering. A technique may involve initially obtaining images that depict a subject from multiple viewpoints and under various lighting conditions using a light stage and depth data corresponding to the subject using infrared cameras. A neural network may extract features of the subject from the images based on the depth data and map the features into a texture space (e.g., the UV texture space). A neural renderer can be used to generate an output image depicting the subject from a target view such that illumination of the subject in the output image aligns with the target view. The neural render may resample the features of the subject from the texture space to an image space to generate the output image.

Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. An example method includes applying a geometry model to an input image to determine a surface orientation map indicative of a distribution of lighting on an object based on a surface geometry. The method further includes applying an environmental light estimation model to the input image to determine a direction of synthetic lighting to be applied to the input image. The method also includes applying, based on the surface orientation map and the direction of synthetic lighting, a light energy model to determine a quotient image indicative of an amount of light energy to be applied to each pixel of the input image. The method additionally includes enhancing, based on the quotient image, a portion of the input image. One or more neural networks can be trained to perform one or more of the aforementioned aspects.

Abstract: Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.

Abstract: Techniques of tracking a user's gaze includes identifying a region of a display at which a gaze of a user is directed, the region including a plurality of pixels. By determining a region rather than a point, when the regions correspond to elements of a user interface, the improved technique enables a system to activate the element to which a determined region is selected. In some implementations, the system makes the determination using a classification engine including a convolutional neural network; such an engine takes as input images of the user's eye and outputs a list of probabilities that the gaze is directed to each of the regions.

Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of input images of a user, generating a three-dimensional mesh proxy based on a first set of features extracted from the plurality of input images and a second set of features extracted from the plurality of input images. The method may further include generating a neural texture based on a three-dimensional mesh proxy and the plurality of input images, generating a representation of the user including at least a neural texture, and sampling at least one portion of the neural texture from the three-dimensional mesh proxy. In response to providing the at least one sampled portion to a neural renderer, the method may include receiving, from the neural renderer, a synthesized image of the user that is previously not captured by the image processing system.

Abstract: Embodiments of present disclosure discloses system and method for reconstruction of FOV. Initially, presence of one of single object and distinct objects in FOV of image of sample comprising one or more objects is determined based on sharpness of one or more objects. A single optimal representation of FOV may be generated when presence of single object is determined. At least one of single optimal representation and a depth-based enhanced representation of FOV may be generated when presence of distinct objects is determined. For generating depth-based enhanced representation, one or more first optimal images associated with each of distinct objects in FOV may be retrieved. An optimal representation of each of distinct objects is generated based on corresponding one or more first optimal images. Further, optimal representation of each of distinct objects is placed at corresponding optimal depth associated with respective distinct object to generate depth-based enhanced representation.

Abstract: A lighting stage includes a plurality of lights that project alternating spherical color gradient illumination patterns onto an object or human performer at a predetermined frequency. The lighting stage also includes a plurality of cameras that capture images of an object or human performer corresponding to the alternating spherical color gradient illumination patterns. The lighting stage also includes a plurality of depth sensors that capture depth maps of the object or human performer at the predetermined frequency. The lighting stage also includes (or is associated with) one or more processors that implement a machine learning algorithm to produce a three-dimensional (3D) model of the object or human performer. The 3D model includes relighting parameters used to relight the 3D model under different lighting conditions.

Abstract: Systems and methods are described for generating a plurality of three-dimensional (3D) proxy geometries of an object, generating, based on the plurality of 3D proxy geometries, a plurality of neural textures of the object, the neural textures defining a plurality of different shapes and appearances representing the object, providing the plurality of neural textures to a neural renderer, receiving, from the neural renderer and based on the plurality of neural textures, a color image and an alpha mask representing an opacity of at least a portion of the object, and generating a composite image based on the pose, the color image, and the alpha mask.

Abstract: Disclosed subject matter relates to Peripheral Blood Smear (PBS) that determines an area to be scanned in PBS for analysis. A PBS analysing system captures a focused image at each of plurality of positions in the PBS and determines Quality Indicators (QIs) in focused image. Further, a region is identified in PBS where QIs of focused image satisfy predefined QI threshold limits, as a monolayer region of PBS and determines an initiation point in monolayer region based on cell count value and co-ordinates of each of the plurality of positions located in the monolayer region. Finally, the area to be scanned in monolayer region is determined based on the initiation point and a predefined scan pattern. Determining the area to be scanned yields accurate and faster results.

Abstract: Embodiments of present disclosure discloses system and method for reconstruction of FOV. Initially, presence of one of single object and distinct objects in FOV of image of sample comprising one or more objects is determined based on sharpness of one or more objects. A single optimal representation of FOV may be generated when presence of single object is determined. At least one of single optimal representation and a depth-based enhanced representation of FOV may be generated when presence of distinct objects is determined. For generating depth-based enhanced representation, one or more first optimal images associated with each of distinct objects in FOV may be retrieved. An optimal representation of each of distinct objects is generated based on corresponding one or more first optimal images. Further, optimal representation of each of distinct objects is placed at corresponding optimal depth associated with respective distinct object to generate depth-based enhanced representation.

Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided.

Abstract: Disclosed herein is method and system for determining quality of semen sample. Trajectories of objects, identified in each of plurality of image frames of semen sample, are generated by tracking movement of the objects across image frames, and compensating a drift velocity of the semen sample. Further, generated trajectories are classified into sperm and non-sperm trajectories. Finally, total concentration estimate and total motility estimate of the semen sample are computed to generate a semen quality index, which indicates quality of the semen sample. In an embodiment, the method of present disclosure uses a multi-level Convolutional Neural Network (CNN) analysis technique for effectively classifying the object trajectories into sperm and non-sperm objects. Also, since the present method includes estimating and compensating drift velocity in the semen sample, it enhances overall accuracy of motility estimation and semen quality analysis.

Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided.

Abstract: Disclosed subject matter relates to Peripheral Blood Smear (PBS) that determines an area to be scanned in PBS for analysis. A PBS analysing system captures a focused image at each of plurality of positions in the PBS and determines Quality Indicators (QIs) in focused image. Further, a region is identified in PBS where QIs of focused image satisfy predefined QI threshold limits, as a monolayer region of PBS and determines an initiation point in monolayer region based on cell count value and co-ordinates of each of the plurality of positions located in the monolayer region. Finally, the area to be scanned in monolayer region is determined based on the initiation point and a predefined scan pattern. Determining the area to be scanned yields accurate and faster results.

Abstract: Disclosed herein is method and system for determining quality of semen sample. Trajectories of objects, identified in each of plurality of image frames of semen sample, are generated by tracking movement of the objects across image frames, and compensating a drift velocity of the semen sample. Further, generated trajectories are classified into sperm and non-sperm trajectories. Finally, total concentration estimate and total motility estimate of the semen sample are computed to generate a semen quality index, which indicates quality of the semen sample. In an embodiment, the method of present disclosure uses a multi-level Convolutional Neural Network (CNN) analysis technique for effectively classifying the object trajectories into sperm and non-sperm objects. Also, since the present method includes estimating and compensating drift velocity in the semen sample, it enhances overall accuracy of motility estimation and semen quality analysis.

Abstract: Embodiments of present disclosure discloses system and method for acquisition of optimal images of object in multi-layer sample. Initially, images for FOV of multi-layer sample comprising objects are retrieved. Each of images are captured by varying focal depth of image capturing unit associated with system. Further, objects associated with multi-layer sample in FOV are identified. For identification, cumulative foreground mask of FOV is obtained based on adaptive thresholding performed on foreground image of FOV. Based on contour detection performed on cumulative foreground mask of FOV, object masks, corresponding to objects, is obtained for identifying objects. Further, sharpness of each of images associated with each of object masks is computed. Based on sharpness, optimal images from images for each of objects is selected for acquisition of optimal images of objects in multi-layer sample.