Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for cutting down a user's larger input video into an edited video comprising the most important video segments and applying corresponding video effects. Some embodiments of the present invention are directed to adding face-aware scale magnification to the trimmed video (e.g., applying scale magnification to simulate a camera zoom effect that hides shot cuts with respect to the subject's face). For example, as the trimmed video transitions from one video segment to the next video segment, a scale magnification may be applied that zooms in on a detected face at a boundary between the video segments to smooth the transition between video segments.

Abstract: In implementation of techniques for template-based behaviors in machine learning, a computing device implements a template system to receive a digital video and data executable to generate animated content. The template system determines a location within a frame of the digital video to place the animated content using a machine learning model. The template system then renders the animated content within the frame of the digital video at the location determined by the machine learning model. The template system then displays the rendered animated content within the frame of the digital video in a user interface.

Abstract: Gradient mesh generation and rendering techniques are described. In one or more implementations, a gradient mesh processing system leverages a vertex buffer and an index buffer. The vertex buffer is used to define vertexes and color values of respective patches in the geometry. The index buffer is then used to define which of the vertexes and corresponding color values are to be used to generate a respective patch. As a result, two or more vertexes are definable in the vertex buffer that share a location within the geometry but have different color values. The index buffer is therefore usable to select different collections of vertices from the vertex buffer to define a respective patch.

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: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.

Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing ray-tracing and mesh generation to illuminate two-dimensional digital vector images. In response to inserting a light source into a two-dimensional digital vector image including one or more vector elements, the disclosed system embeds the vector element(s) into a polygonal mesh generated for a region of the digital vector image. The disclosed system samples a plurality of rays at a plurality of points within the region and detect intersections of the rays with the vector element(s) or a bounding shape surrounding the region. Additionally, the disclosed system determines color values for mesh points in the polygonal mesh based on the intersections of the rays by interpolating color values associated with the intersected points. Furthermore, in some embodiments, the disclosed system subdivides the polygonal mesh according to a priority queue based on error scores associated with the determined color values.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing ray-tracing and mesh generation to illuminate two-dimensional digital vector images. In response to inserting a light source into a two-dimensional digital vector image including one or more vector elements, the disclosed system embeds the vector element(s) into a polygonal mesh generated for a region of the digital vector image. The disclosed system samples a plurality of rays at a plurality of points within the region and detect intersections of the rays with the vector element(s) or a bounding shape surrounding the region. Additionally, the disclosed system determines color values for mesh points in the polygonal mesh based on the intersections of the rays by interpolating color values associated with the intersected points. Furthermore, in some embodiments, the disclosed system subdivides the polygonal mesh according to a priority queue based on error scores associated with the determined color values.

Abstract: Face anonymization techniques are described that overcome conventional challenges to generate an anonymized face. In one example, a digital object editing system is configured to generate an anonymized face based on a target face and a reference face. As part of this, the digital object editing system employs an encoder as part of machine learning to extract a target encoding of the target face image and a reference encoding of the reference face. The digital object editing system then generates a mixed encoding from the target and reference encodings. The mixed encoding is employed by a machine-learning model of the digital object editing system to generate a mixed face. An object replacement module is used by the digital object editing system to replace the target face in the target digital image with the mixed face.

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: Freeform drawing beautification techniques are described. An input is received by a computing device describing a freeform path drawn by a user as part of a drawing, the freeform path not formed solely as a circular arc or a circle (e.g., a fixed distance from a point) and including one or more curved elements. The drawing is examined by the computing device to locate another curved element in the drawing. One or more suggestions are constructed to adjust the freeform path by the computing device based on the located curved element in the drawing. The constructed one or more suggestions are output to adjust the freeform path by the computing device.

Abstract: Certain embodiments involve automatically detecting video frames that depict visemes and that are usable for generating an animatable puppet. For example, a computing device accesses video frames depicting a person performing gestures usable for generating a layered puppet, including a viseme gesture corresponding to a target sound or phoneme. The computing device determines that audio data including the target sound or phoneme aligns with a particular video frame from the video frames that depicts the person performing the viseme gesture. The computing device creates, from the video frames, a puppet animation of the gestures, including an animation of the viseme corresponding to the target sound or phoneme that is generated from the particular video frame. The computing device outputs the puppet animation to a presentation device.

Abstract: Certain embodiments involve generating one or more of appearance guide and a positional guide and using one or more of the guides to synthesize a stylized image or animation. For example, a system obtains data indicating a target image and a style exemplar image. The system generates an appearance guide, a positional guide, or both from the target image and the style exemplar image. The system uses one or more of the guides to transfer a texture or style from the style exemplar image to the target image.

Abstract: Embodiments of the present invention are directed to beautifying freeform input paths in accordance with paths existing in the drawing (i.e., resolved paths). In some embodiments of the present invention, freeform input paths of a curved format can be modified or replaced to more precisely illustrate a path desired by a user. As such, a user can provide a freeform input path that resembles a path of interest by the user, but is not as precise as desired. Based on existing paths in the electronic drawing, a path suggestion(s) can be generated to rectify, modify, or replace the input path with a more precise path. In some cases, a user can then select a desired path suggestion, and the selected path then replaces the initially provided freeform input path.

Abstract: Embodiments of the present invention are directed to beautifying freeform input paths in accordance with paths existing in the drawing (i.e., resolved paths). In some embodiments of the present invention, freeform input paths of a curved format can be modified or replaced to more precisely illustrate a path desired by a user. As such, a user can provide a freeform input path that resembles a path of interest by the user, but is not as precise as desired. Based on existing paths in the electronic drawing, a path suggestion(s) can be generated to rectify, modify, or replace the input path with a more precise path. In some cases, a user can then select a desired path suggestion, and the selected path then replaces the initially provided freeform input path.

Abstract: Certain embodiments involve automatically detecting video frames that depict visemes and that are usable for generating an animatable puppet. For example, a computing device accesses video frames depicting a person performing gestures usable for generating a layered puppet, including a viseme gesture corresponding to a target sound or phoneme. The computing device determines that audio data including the target sound or phoneme aligns with a particular video frame from the video frames that depicts the person performing the viseme gesture. The computing device creates, from the video frames, a puppet animation of the gestures, including an animation of the viseme corresponding to the target sound or phoneme that is generated from the particular video frame. The computing device outputs the puppet animation to a presentation device.

Abstract: Embodiments of the present invention are directed to beautifying freeform input paths in accordance with paths existing in the drawing (i.e., resolved paths). In some embodiments of the present invention, freeform input paths of a curved format can be modified or replaced to more precisely illustrate a path desired by a user. As such, a user can provide a freeform input path that resembles a path of interest by the user, but is not as precise as desired. Based on existing paths in the electronic drawing, a path suggestion(s) can be generated to rectify, modify, or replace the input path with a more precise path. In some cases, a user can then select a desired path suggestion, and the selected path then replaces the initially provided freeform input path.

Abstract: Certain embodiments involve generating one or more of appearance guide and a positional guide and using one or more of the guides to synthesize a stylized image or animation. For example, a system obtains data indicating a target image and a style exemplar image. The system generates an appearance guide, a positional guide, or both from the target image and the style exemplar image. The system uses one or more of the guides to transfer a texture or style from the style exemplar image to the target image.