Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for improved patch validity testing for patch-based synthesis applications using similarity transforms. The improved patch validity tests are used to validate (or invalidate) candidate patches as valid patches falling within a sampling region of a source image. The improved patch validity tests include a hole dilation test for patch validity, a no-dilation test for patch invalidity, and a comprehensive pixel test for patch invalidity. A fringe test for range invalidity can be used to identify pixels with an invalid range and invalidate corresponding candidate patches. The fringe test for range invalidity can be performed as a precursor to any or all of the improved patch validity tests. In this manner, validated candidate patches are used to automatically reconstruct a target image.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for improved patch validity testing for patch-based synthesis applications using similarity transforms. The improved patch validity tests are used to validate (or invalidate) candidate patches as valid patches falling within a sampling region of a source image. The improved patch validity tests include a hole dilation test for patch validity, a no-dilation test for patch invalidity, and a comprehensive pixel test for patch invalidity. A fringe test for range invalidity can be used to identify pixels with an invalid range and invalidate corresponding candidate patches. The fringe test for range invalidity can be performed as a precursor to any or all of the improved patch validity tests. In this manner, validated candidate patches are used to automatically reconstruct a target image.

Abstract: Systems and methods disclosed herein improve the quality and speed of computing deformations used to animate artwork. One aspect provides adaptive meshing that creates a mesh adapted to handle locations and weights associating the handles with the mesh vertices. Portions of the mesh requiring smaller triangles with more densely positioned vertices are identified based on the handle locations and associated weights and resolution is added only to those portions of the mesh in which finer resolution is required. A second aspect involves creating a mesh using a coarse-to-fine iterative approach. This involves generating a mesh and the weights associating each handle to each vertex in the mesh and iteratively refining the mesh to add resolution until a refinement criteria is satisfied.

Abstract: 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.