Adobe, Inc.

Mridul Kavidayal

Vineet Batra

Ankit Phogat

Matthew David Fisher

Daniel Max Kaufman

Jingwan Lu

Harish Kumar

Payal Bajaj

Ponnurangam Kumaraguru

Md Nadeem Akhtar

Sumit Chaturvedi

Shriram V S Revankar

Priyanshu Srivastava

Systems and techniques are described for determining image handle locations. An image is provided to a neural network as input, and the neural network translates the input image to an output image that includes clusters of pixels against a background that have intensities greater than an intensity of the background and that indicate candidate handle locations. Intensities of clusters of pixels in an output image are compared to a threshold intensity level to determine a set of the clusters of pixels satisfying an intensity constraint. The threshold intensity level can be user-selectable, so that a user can control a density of handles. A handle location for each cluster of the set of clusters is determined from a centroid of each cluster. Handle locations include a coordinate for the handle location and an attribute classifying a degree of freedom for a handle at the handle location.

Determining image handle locations

Techniques for intuitive modifications of digital graphics in a digital media environment are described. For example, a digital graphics creation system accesses vector artwork including a vector object, such as a Bezier curve. The digital graphics creation system receives user inputs, including a user input defining handles on the vector object and a user input interacting with the handles indicating a desired change to the vector object. The digital graphics creation system modifies the vector artwork, including the vector object, by accounting for topology of the vector object and maintaining connections between connected segments of the vector object. The digital graphics creation system outputs the modified vector artwork, including the vector object, such as in a user interface.

Digital media environment for intuitive modifications of digital graphics

Color handles are generated based on digital image color gradients using machine learning. In order to train a neural network of a generator module of a GAN system, a training digital image is used by the neural network of the generator module to generate a candidate color handle. The discriminator module of the GAN system then compares the candidate color handle with a ground truth color handle of the training digital image using a loss function as part of machine learning, and uses a result of this comparison to train the neural network of the generator module.

Color handle generation for digital image color gradients using machine learning

Automatic bone handle generation for efficient manipulation of a graphic object is described. Initially, a request is received to generate bone handles for a graphic object. Responsive to the request, a bone handle generation system determines an outline of the graphic object. Based on the outline, this system then generates a mesh corresponding to the graphic object. The bone handle generation system contracts this mesh inward to form a contracted mesh. By then collapsing edges of the contracted mesh, the bone handle generation system generates a set of connected line segments forming a skeleton of the graphic object. The bone handle generation system reduces the set of connected line segments by removing line segments and by merging vertices that connect different line segments. Based on this reduction, the bone handle generation system obtains the bone handles, which are controllable with user input to deform corresponding portions of the graphic object.

Bone handle generation

Systems and techniques are described for colorizing vector images. Color raster images that correspond to the vector images are used to perform a color mapping to colorize the vector images. The vector images are represented using non-overlapping planar arrangements of faces of the vector images, so that the color mapping may be performed with respect to the faces. The faces may be processed in parallel, to further facilitate a speed and scalability of the describes processes and results.

Colorization of vector images

A selection of a key path of a vector image displayed using a graphical user interface (GUI) may be received, via the GUI. At least one candidate path of the vector image is identified. A pairwise comparison of the key path with the at least one candidate path is executed, the pairwise comparison including characterization of a translation, scaling, and rotation of the at least one candidate path with respect to the key path. Based on the pairwise comparison, it is determined that the at least one candidate path is within a similarity threshold defined with respect to the key path. A visual indicator of the at least one candidate path within the GUI, identifying the at least one candidate path as being within the similarity threshold, may be provided.

Identification and modification of similar objects in vector images

There is disclosed a system and method for colorizing vector graphic objects in a digital medium environment. The system comprises a processing unit and a deep neural network of the processing unit, in which the deep neural network includes a generator. The processing unit receives a non-colorized vector image and converts the non-colorized vector image to a non-colorized raster image. The deep neural network generates a colorized raster image from the non-colorized raster image. The generator processes the non-colorized raster image using an extended number of convolutional layers and residual blocks to add skip connections between at least two of the convolutional layers. The processing unit converts the colorized raster image to a colorized vector image.

Colorizing vector graphic objects

Diffusion coloring of vector graphics artwork is performed in constant time based on the number of color channels in a specified color space. In some examples, a method may include establishing color handles within an artwork, and defining mesh vertices distributed throughout the artwork. The method may also include determining a resultant color at each mesh vertex by solving the Laplacian equation for each of i color channels in a color space, wherein solving the Laplacian equation for each of the i color channels produces a corresponding i color values that collectively define the resultant color. A color for a pixel in the artwork can be determined by interpolating between the resultant colors at the mesh vertices.

Generalized primitives for smooth coloring of vector graphics artwork in constant time

Techniques and systems for auditing and augmenting user-generated tags for digital content are described. A corpus is generated for each tag associated with digital content to represent different aspects of the tag's definition. A hierarchy of semantic relationships between the tags is created based a corpus co-occurrence between the tags to relate at least two tags having different levels of specificity. Some of the tags are verified with the digital content based on feature detection, and a correspondence to the digital content is determined for each verified tag. The correspondence of the verified tags is then propagated up the hierarchy to others of the tags that are semantically related to the verified tags but which were not verified by the feature detection. The verified tags and the verified other tags are then assigned to the digital content to control how the digital content is retrieved when subject to a search.

Auditing and augmenting user-generated tags for digital content

An automated process provides diffusion coloring of vector graphics using color points, which appear to the user as color handles. A computing device programmatically receives input from a user establishing a plurality of color handles within a source geometry specified by a set of curves. The computing device defines a mesh with a plurality of vertices distributed throughout the source geometry. A resultant color at each vertex of the plurality of vertices is determined and a diffused pixel color is programmatically set for each pixel within the source geometry by interpolating between the resultant colors at the plurality of vertices.

Growing community of inventors

Noida, India

Mridul Kavidayal