A computer-implemented method comprising: receiving, as input, a plurality of images, each associated with a specified content category; generating, from each of the plurality of images, a set of transformed images by applying a series of non-photorealistic transformations having escalating transformation degrees, wherein each of the transformed images is labeled with a label indicating (i) the transformation degree applied thereto, and (ii) a content category associated therewith; obtaining, with respect to each of the set of transformed images, classification results assigned by a human annotator, wherein the classification results assign each of the transformed images in the set into one of a plurality of content categories; and calculating, for the human annotator, a classification score in each of the plurality of content categories, based, at least in part, on all of the classification results.

A computer-implemented method comprising: receiving, as input, a plurality of images, each associated with a specified content category; generating, from each of the plurality of images, a set of transformed images by applying a series of non-photorealistic transformations having escalating transformation degrees, wherein each of the transformed images is labeled with a label indicating (i) the transformation degree applied thereto, and (ii) a content category associated therewith; obtaining, with respect to each of the set of transformed images, classification results assigned by a human annotator, wherein the classification results assign each of the transformed images in the set into one of a plurality of content categories; and calculating, for the human annotator, a classification score in each of the plurality of content categories, based, at least in part, on all of the classification results.

The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

The disclosed computer-implemented method may include displaying vehicle environment awareness. In some embodiments, a visualization system may display an abstract representation of a vehicle's physical environment via a mobile device and/or a device embedded in the vehicle. For example, the visualization may use a voxel grid to represent the environment and may alter characteristics of shapes in the grid to increase their visual prominence when the sensors of the vehicle detect that an object is occupying the space represented by the shapes. In some embodiments, the visualization may gradually increase and reduce the visual prominence of shapes in the grid to create a soothing wave effect. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods automatically generate contours on an illustrated object for performing an animation. Contour lines are generated on the surface of the object according to criteria related to the shape of the surface of the object. Points of the contour lines that are occluded from a virtual camera are identified. The occluded points are removed to generate visible lines. The visible lines are extruded to define a three-dimensional volume defining contours of the object. The object itself, along with the three-dimensional volume, are illuminated and rendered. The parameters defining the opacity and color of the contour may differ from corresponding parameters of the rest of the object, so that the contours stand out and define portions of the object. The contours are useful in contexts such as defining areas of an object that is fuzzy or cloudy in appearance, as well as creating certain artistic effects.

Systems and methods are disclosed for leveraging rendering engines to perform multi-spectral rendering by reusing the color channels for additional spectral bands. A digital asset represented by a three dimensional (3D) mesh and a material reference pointer may be rendered using a first material spectral band data set and additionally rendered using a second material spectral band data set, and the results combined to create a multi-spectral rendering. The multi-spectral rendering may then be used as part of a synthetics service or operation. By abstracting the material properties, a material translator is able to return a banded material data set from among a plurality of spectral band sets, and asset material information may advantageously be managed apart from managing each asset individually.

Systems and methods are disclosed for leveraging rendering engines to perform multi-spectral rendering by reusing the color channels for additional spectral bands. A digital asset represented by a three dimensional (3D) mesh and a material reference pointer may be rendered using a first material spectral band data set and additionally rendered using a second material spectral band data set, and the results combined to create a multi-spectral rendering. The multi-spectral rendering may then be used as part of a synthetics service or operation. By abstracting the material properties, a material translator is able to return a banded material data set from among a plurality of spectral band sets, and asset material information may advantageously be managed apart from managing each asset individually.

In various example embodiments, techniques are provided for representing uncertainty when displaying a rendered view of a multi-dimensional mesh (e.g., created by SfM photogrammetry) in a user interface by applying a real-time, obfuscation filter that modifies the rendered view based on uncertainty in screen space. Where the multi-dimensional mesh is within a limit of data accuracy, the rendered view is shown without modification (i.e. as normal), and a user may trust the information displayed. Where the multi-dimensional mesh is beyond the limit of data accuracy, the obfuscation filter obfuscates detail (e.g., by blurring, pixilating, edge enforcing, etc.) in the rendered view so that a user may visually perceive the uncertainty. The amount of obfuscation may be weighted based on uncertainty to allow the user to visually quantify uncertainty.

Systems, methods, and non-transitory computer-readable media are disclosed for modifying voxel-based 3D representations using 3D digital brush tools and/or resolution filters. For example, the disclosed systems can utilize 3D digital brush tools (e.g., a digital blur brush tool, a digital smudge brush tool, and/or a digital melt brush tool) to identify and modify one or more voxels within a 3D representation using multiple buffers of visual properties. Additionally, the disclosed systems can modify one or more voxels within a 3D representation by rendering the one or more voxels at varying levels of detail using an octree (e.g., a mosaic filter tool). In particular, the disclosed systems can identify one or more voxels within an octree that are smaller than a target voxel size. Moreover, the disclosed systems can combine the identified one or more voxels within the octree to render the 3D representation at varying levels of detail.