Abstract: Embodiments of the present disclosure perform training attribution by identifying a synthesized image and a training image, where the synthesized image was generated by an image generation model that was trained with the training image. A machine learning model computes first attribution features for the synthesized image using a first mapping layer and second attribution features for the training image using a second mapping layer that is different from the first mapping layer. Then, an attribution score is generated based on the first attribution features and the second attribution features, where the attribution score indicates a degree of influence for the training image on generating the synthesized image.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: An image generation system enables user input during the process of training a generative model to influence the model's ability to generate new images with desired visual features. A source generative model for a source domain is fine-tuned using training images in a target domain to provide an adapted generative model for the target domain. Interpretable factors are determined for the source generative model and the adapted generative model. A user interface is provided that enables a user to select one or more interpretable factors. The user-selected interpretable factor(s) are used to generate a user-adapted generative model, for instance, by using a loss function based on the user-selected interpretable factor(s). The user-adapted generative model can be used to create new images in the target domain.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital images depicting photorealistic scenes utilizing a digital image collaging neural network. For example, the disclosed systems utilize a digital image collaging neural network having a particular architecture for disentangling generation of scene layouts and pixel colors for different regions of a digital image. In some cases, the disclosed systems break down the process of generating a collage digital into generating images representing different regions such as a background and a foreground to be collaged into a final result. For example, utilizing the digital image collaging neural network, the disclosed systems determine scene layouts and pixel colors for both foreground digital images and background digital images to ultimately collage the foreground and background together into a collage digital image depicting a real-world scene.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital images depicting photorealistic scenes utilizing a digital image collaging neural network. For example, the disclosed systems utilize a digital image collaging neural network having a particular architecture for disentangling generation of scene layouts and pixel colors for different regions of a digital image. In some cases, the disclosed systems break down the process of generating a collage digital into generating images representing different regions such as a background and a foreground to be collaged into a final result. For example, utilizing the digital image collaging neural network, the disclosed systems determine scene layouts and pixel colors for both foreground digital images and background digital images to ultimately collage the foreground and background together into a collage digital image depicting a real-world scene.

Abstract: Systems and methods for image generation are described. Embodiments of the present disclosure obtain user input that indicates a target color and a semantic label for a region of an image to be generated. The system also generates of obtains a noise map including noise biased towards the target color in the region indicated by the user input. A diffusion model generates the image based on the noise map and the semantic label for the region. The image can include an object in the designated region that is described by the semantic label and that has the target color.

Abstract: Systems and methods for inserting an object into a background are described. Examples of the systems and methods include obtaining a background image including a region for inserting the object, and encoding the background image to obtain an encoded background. A modified image is then generated based on the encoded background using a diffusion model. The modified image depicts the object within the region.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently modifying a generative adversarial neural network using few-shot adaptation to generate digital images corresponding to a target domain while maintaining diversity of a source domain and realism of the target domain. In particular, the disclosed systems utilize a generative adversarial neural network with parameters learned from a large source domain. The disclosed systems preserve relative similarities and differences between digital images in the source domain using a cross-domain distance consistency loss. In addition, the disclosed systems utilize an anchor-based strategy to encourage different levels or measures of realism over digital images generated from latent vectors in different regions of a latent space.

Abstract: An image generation system enables user input during the process of training a generative model to influence the model's ability to generate new images with desired visual features. A source generative model for a source domain is fine-tuned using training images in a target domain to provide an adapted generative model for the target domain. Interpretable factors are determined for the source generative model and the adapted generative model. A user interface is provided that enables a user to select one or more interpretable factors. The user-selected interpretable factor(s) are used to generate a user-adapted generative model, for instance, by using a loss function based on the user-selected interpretable factor(s). The user-adapted generative model can be used to create new images in the target domain.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital images depicting photorealistic scenes utilizing a digital image collaging neural network. For example, the disclosed systems utilize a digital image collaging neural network having a particular architecture for disentangling generation of scene layouts and pixel colors for different regions of a digital image. In some cases, the disclosed systems break down the process of generating a collage digital into generating images representing different regions such as a background and a foreground to be collaged into a final result. For example, utilizing the digital image collaging neural network, the disclosed systems determine scene layouts and pixel colors for both foreground digital images and background digital images to ultimately collage the foreground and background together into a collage digital image depicting a real-world scene.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently modifying a generative adversarial neural network using few-shot adaptation to generate digital images corresponding to a target domain while maintaining diversity of a source domain and realism of the target domain. In particular, the disclosed systems utilize a generative adversarial neural network with parameters learned from a large source domain. The disclosed systems preserve relative similarities and differences between digital images in the source domain using a cross-domain distance consistency loss. In addition, the disclosed systems utilize an anchor-based strategy to encourage different levels or measures of realism over digital images generated from latent vectors in different regions of a latent space.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: Techniques are provided for converting a self-portrait image into a neutral-pose portrait image, including receiving a self-portrait input image, which contains at least one person who is the subject of the self-portrait. A nearest pose search selects a target neutral-pose image that closely matches or approximates the pose of the upper torso region of the subject in the self-portrait input image. Coordinate-based inpainting maps pixels from the upper torso region in the self-portrait input image to corresponding regions in the selected target neutral-pose image to produce a coarse result image. A neutral-pose composition refines the coarse result image by synthesizing details in the body region of the subject (which in some cases includes the subject's head, arms, and torso), and inpainting pixels into missing portions of the background. The refined image is composited with the original self-portrait input image to produce a neutral-pose result image.

Abstract: A method, comprising displaying an image to a first player, displaying a portion of the image to a second player wherein the portion of the image displayed to the second player is less than all of the image and wherein the portion of the image displayed to the second player is determined by an action of the first player, allowing the second player to submit a word, and determining whether the word submitted by the second player is related to the image. The present invention also includes apparatuses and systems.