Adobe, Inc.

Kevin Wampler

Vineet Batra

Ankit Phogat

Elya Shechtman

Matthew David Fisher

Daniel Max Kaufman

Aliakbar Darabi

Souymodip Chakraborty

Vishwas Jain

Radomir Mech

Jingwan Lu

Duygu Ceylan Aksit

Vladimir Kim

Emiliano Gambaretto

Ratheesh Kalarot

Jonathan Eisenmann

Wilmot Li

Noam Aigerman

Siddhartha Chaudhuri

Alexandru Vasile Costin

Giorgio Gori

Jakub Fiser

Brian Lynn Price

Kalyan Krishna Sunkavalli

Oliver Wang

Sohrab Amirghodsi

Tenell Rhodes

Michal Lukác

Michael Gharbi

Ashwani Chandil

Siddhant Jain

Honglin Chen

Kenji Enomoto

Chi Cheng Hsu

Systems and methods provide local deformation for shapes. In accordance with some aspects, input to deform a shape is received. The shape comprises a plurality of vertices with each vertex having a vertex position. Based on the input, deformed vertex positions are determined for the plurality of vertices by minimizing an energy function that includes an elastic energy term and a regularization term that is a function of vertex position change for each vertex having a vertex position change below a threshold and a constant for each vertex having a vertex position change above the threshold. A deformed shape is generated based on the deformed vertex positions.

Local deformation for interactive shape edititing

Certain aspects and features of the present disclosure relate to receiving an input corresponding to a fill for a vector graphical representation including an overlapping area. Aspects and features further involve converting the vector graphical representation to a simple graph, and aligning contours within the simple graph to provide a unified winding number for the overlapping area. Aspects and features also involve rendering the vector graphical representation with the fill using the simple graph to include the overlapping area within the rendered representation as filled.

Filling overlapping areas of a vector graphical representation using a simple graph

The present disclosure relates to systems, non-transitory computer-readable media, and methods for efficiently automating the preparation of accurate alpha matte animations and modified digital videos utilizing polarized light. For example, the disclosed systems obtain a plurality of polarized digital videos portraying an animation of a foreground subject backlit by a polarized light source. In some embodiments, the disclosed systems generate a plurality of corrected polarized digital videos by adjusting intensity values of the plurality of polarized digital videos based on intensity differences across the plurality of polarized digital videos. The disclosed systems generate an alpha matte animation comprising a plurality of alpha mattes from the plurality of corrected polarized digital videos or from the plurality of polarized digital videos. Utilizing the alpha matte animation, the disclosed systems generate a modified digital video by combining the animation of the foreground subject and a replacement background.

Preparation systems for efficiently generating alpha mattes and modified digital videos utilizing polarized light

Graphical constructs are efficiently described by integer-based identifiers, and graphical constructs of the same type are stored in a definitional component. Each client maintains both a pending state representation and a synchronized state representation of the graphical design to independently track the state of the representation at a live editing server. The use of integer-based identifiers for graphical constructs provides an efficient change representation that can be communicated with minimal network traffic. All copies of the graphical design represented among clients reach a consistent state quickly even when multiple users are making changes to the same vector path, eliminating the need to track changes manually or to move large files.

Collaborative editing of vector graphics

Techniques for nonlinear representations for vector objects are described that support construction of a nonlinear vector graph to represent a vector object. In an implementation, a user input is received including a plurality of points and at least one primitive. A content processing system then generates a vector object by constructing a nonlinear vector graph that specifies a nonlinear connection of the plurality of points with the at least one primitive. In some examples, the vector object is edited by applying an edit to the nonlinear vector graph. Once generated, the content processing system then outputs the vector object for display, e.g., in a user interface.

Nonlinear representations for vector objects

Systems and methods seamlessly blend edited and unedited regions of an image. A computing system crops an input image around a region to be edited. The system applies an affine transformation to rotate the cropped input image. The system provides the rotated cropped input image as input to a machine learning model to generate a latent space representation of the rotated cropped input image. The system edits the latent space representation and provides the edited latent space representation to a generator neural network to generate a generated edited image. The system applies an inverse affine transformation to rotate the generated edited image and aligns an identified segment of the rotated generated edited image with an identified corresponding segment of the input image to produce an aligned rotated generated edited image. The system blends the aligned rotated generated edited image with the input image to generate an edited output image.

Techniques for smooth region merging in image editing

Systems and methods combine an input image with an edited image generated using a generator neural network to preserve detail from the original image. A computing system provides an input image to a machine learning model to generate a latent space representation of the input image. The system provides the latent space representation to a generator neural network to generate a generated image. The system generates multiple scale representations of the input image, as well as multiple scale representations of the generated image. The system generates a first combined image based on first scale representations of the images and a first value. The system generates a second combined image based on second scale representations of the images and a second value. The system blends the first combined image with the second combined image to generate an output image.

Detail-preserving image editing techniques

Embodiments are disclosed for receiving a target shape. The method may further include initializing a gradient mesh to a vector graphic having at least one node. The method may further include performing a constrained optimization of the vector graphic based on the target shape. The method may further include generating a stress metric based on a comparison of the constrained optimization and the target shape. The method may further include determining one or more unconstrained candidate vector graphics based on the stress metric. The method may further include selecting an improved vector graphic from the one or more unconstrained candidate vector graphics. The method may further include mapping the vector graphic to the improved vector graphic. The method may further include optimizing the improved vector graphic based on the target shape.

Continuous optimization of discrete parameters using a unified stress indicator

Embodiments of the present invention are directed towards intuitive editing of three-dimensional models. In embodiments, salient geometric features associated with a three-dimensional model defining an object are identified. Thereafter, feature attributes associated with the salient geometric features are identified. A feature set including a plurality of salient geometric features related to one another is generated based on the determined feature attributes (e.g., properties, relationships, distances). An editing handle can then be generated and displayed for the feature set enabling each of the salient geometric features within the feature set to be edited in accordance with a manipulation of the editing handle. The editing handle can be displayed in association with one of the salient geometric features of the feature set.

Intuitive editing of three-dimensional models

Techniques for incorporating a black-box function into a neural network are described. For example, an image editing function may be the black-box function and may be wrapped into a layer of the neural network. A set of parameters and a source image are provided to the black-box function, and the output image that represents the source image with the set of parameters applied to the source image is output from the black-box function. To address the issue that the black-box function may not be differentiable, a loss optimization may calculate the gradients of the function using, for example, a finite differences calculation, and the gradients are used to train the neural network to ensure the output image is representative of an expected ground truth image.

Incorporating black-box functions in neural networks

Embodiments are disclosed for constrained modification of vector geometry. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a selection of a first segment of a vector graphic to be edited, identifying an active region associated with the first segment, wherein the active region includes the first segment and at least one second segment which comprise a geometric primitive, identifying the region of influence including at least one third segment connected to the active region, identifying at least one constraint associated with the active region or the region of influence based at least on the geometric primitive, receiving an edit to the active region, and generating an update for the vector graphic based on the edit and the at least one constraint.

Constrained modification of vector graphics

Systems and methods for editing an image based on multiple constraints are described. Embodiments of the systems and methods may identify a change to a vector graphics data structure, generate an update for the vector graphics data structure based on strictly enforcing a handle constraint, a binding constraint, and a continuity constraint, adjust the vector graphics data structure sequentially for each of a plurality of sculpting constraints according to a priority ordering of the sculpting constraints, generate an additional update for the vector graphics data structure based on strictly enforcing the binding constraint and the continuity constraint and approximately enforcing the handle constraint and the sculpting constraints, adjust the vector graphics data structure sequentially for each of a plurality of sculpting constraints, and display the vector graphic based on the adjusted vector graphics data structure.

Shape aware transformation

Systems and techniques are described herein for generating a triangle mesh for an image represented by curves (e.g., Bezier segments). An outline of an image is determined and reduced to a set of connected polylines that are efficiently represented in an edge list. A triangle mesh is generated based on the edge list, rather than by directly sampling the curves of the image and using the samples as vertices of triangles. Thus, the triangle mesh is generated with a number of triangles independent from a number of curves representing the image. Samples of the curves are bound to the triangle mesh by representing the samples with barycentric coordinates with respect to a triangle in the mesh. Hence, once a mesh is deformed, locations of the samples are determined from the barycentric coordinates and triangles in the deformed mesh, and used to reconstruct the curves of the deformed image.

Generating a triangle mesh for an image represented by curves

The present disclosure includes methods and systems for manipulating digital models based on user input. In particular, disclosed systems and methods can generate modified meshes in real time based on a plurality of input meshes and user manipulation of one or more control points. For example, one or more embodiments of the disclosed systems and methods generate modified meshes from a plurality of input meshes based on a combined shape-space, deformation interpolation measure. Moreover, in one or more embodiments, the disclosed systems and methods utilize an as-rigid-as-possible-deformation measure to combine input meshes into a modified mesh. Further, the disclosed systems and methods can variably combine input shapes over different portions of a modified mesh, providing increased expressiveness while reducing artifacts and increasing computing efficiency.

Growing community of inventors

Seattle, WA, United States of America

Kevin Wampler