Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a multi-stroke neural network for modifying a digital image via a plurality of generated stroke parameters in a single pass of the neural network. Specifically, the disclosed system utilizes an encoder neural network to generate an encoding of a digital image. The disclosed system then utilizes a decoder neural network that generates a sequence of stroke parameters for digital drawing strokes from the encoding in a single pass of the encoder neural network and decoder neural network. Additionally, the disclosed system utilizes a renderer neural network to render the digital drawing strokes on a digital canvas according to the sequence of stroke parameters. In additional embodiments, the disclosed system utilizes a balance of loss functions to learn parameters of the multi-stroke neural network to generate stroke parameters according to various rendering styles.

Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: A generative neural network control system controls a generative neural network by modifying the intermediate latent space in the generative neural network. The generative neural network includes multiple layers each generating a set of activation values. An initial layer (and optionally additional layers) receives an input latent vector, and a final layer outputs an image generated based on the input latent vector. The data that is input to each layer (other than the initial layer) is referred to as data in an intermediate latent space. The data in the intermediate latent space includes activation values (e.g., generated by the previous layer or modified using various techniques) and optionally a latent vector. The generative neural network control system modifies the intermediate latent space to achieve various different effects when generating a new image.

Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.

Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.

Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.

Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.

Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.

Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.

Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.

Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.

Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.

Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.

Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.

Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.