Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a refined digital image that corrects inpainting artifacts in a modified digital image with inpainted pixels. Furthermore, the disclosed systems receive an inpainting request to inpaint a region in a digital image (e.g., a region indicated by a mask). Moreover, the disclosed systems generate a modified digital image from the inpainting request and the digital image, where the modified digital image includes one or more inpainted portions in place of the region. Further, the disclosed systems use a neural network-based refiner model to generate a refined digital image from the modified digital image that corrects artifacts around borders of the one or more inpainted portions in the modified digital image.

Abstract: In implementations of systems for human reposing based on multiple input views, a computing device implements a reposing system to receive input data describing: input digital images; pluralities of keypoints corresponding to the input digital images, the pluralities of keypoints representing poses of a person depicted in the input digital images; and a plurality of keypoints representing a target pose. The reposing system generates selection masks corresponding to the input digital images by processing the input data using a machine learning model. The selection masks represent likelihoods of spatial correspondence between pixels of an output digital image and portions of the input digital images. The reposing system generates the output digital image depicting the person in the target pose for display in a user interface based on the selection masks and the input data.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modifies parameters of a generative model based on enhancing pixels of images. Furthermore, the disclosed systems generate a modified digital image from a digital image by inpainting a region of the digital image. Moreover, the disclosed systems generate a first measure of loss based on comparing the modified digital image with a ground truth version of the digital image. Further, the disclosed systems generate a transformed modified digital image and a transformed ground truth image of the digital image by performing a color space transformation and further generates a second measure of loss. From the first measure of loss and the second measure of loss, the disclosed systems modify parameters of a generative model.

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: A method, non-transitory computer readable medium, apparatus, and system for image generation are described. An embodiment of the present disclosure includes obtaining an input image, an inpainting mask, and a plurality of content preservation values corresponding to different regions of the inpainting mask, and identifying a plurality of mask bands of the inpainting mask based on the plurality of content preservation values. An image generation model generates an output image based on the input image and the inpainting mask. The output image is generated in a plurality of phases. Each of the plurality of phases uses a corresponding mask band of the plurality of mask bands as an input.

Abstract: Systems and methods for training a Generative Adversarial Network (GAN) using feature regularization are described herein. Embodiments are configured to generate a candidate image using a generator network of a GAN, classify the candidate image as real or generated using a discriminator network of the GAN, and train the GAN to generate realistic images based on the classifying of the candidate image. The training process includes regularizing a gradient with respect to features extracted using a discriminator network of the GAN.

Abstract: A method, non-transitory computer readable medium, apparatus, and system for image generation include obtaining an input image having a first resolution, where the input image includes random noise, and generating a low-resolution image based on the input image, where the low-resolution image has the first resolution. The method, non-transitory computer readable medium, apparatus, and system further include generating a high-resolution image based on the low-resolution image, where the high-resolution image has a second resolution that is greater than the first resolution.

Abstract: A modeling system accesses a two-dimensional (2D) input image displayed via a user interface, the 2D input image depicting, at a first view, a first object. At least one region of the first object is not represented by pixel values of the 2D input image. The modeling system generates, by applying a 3D representation generation model to the 2D input image, a three-dimensional (3D) representation of the first object that depicts an entirety of the first object including the first region. The modeling system displays, via the user interface, the 3D representation, wherein the 3D representation is viewable via the user interface from a plurality of views including the first view.

Abstract: Systems and methods for image processing (e.g., image extension or image uncropping) using neural networks are described. One or more aspects include obtaining an image (e.g., a source image, a user provided image, etc.) having an initial aspect ratio, and identifying a target aspect ratio (e.g., via user input) that is different from the initial aspect ratio. The image may be positioned in an image frame having the target aspect ratio, where the image frame includes an image region containing the image and one or more extended regions outside the boundaries of the image. An extended image may be generated (e.g., using a generative neural network), where the extended image includes the image in the image region as well as generated image portions in the extended regions and the one or more generated image portions comprise an extension of a scene element depicted in the image.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to generate modified digital images. In particular, in some embodiments, the disclosed systems generate image editing directions between textual identifiers of two visual features utilizing a language prediction machine learning model and a text encoder. In some embodiments, the disclosed systems generated an inversion of a digital image utilizing a regularized inversion model to guide forward diffusion of the digital image. In some embodiments, the disclosed systems utilize cross-attention guidance to preserve structural details of a source digital image when generating a modified digital image with a diffusion neural network.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.

Abstract: An image processing system obtains an input image (e.g., a user provided image, etc.) and a mask indicating an edit region of the image. A user selects an image editing mode for an image generation network from a plurality of image editing modes. The image generation network generates an output image using the input image, the mask, and the image editing mode.

Abstract: A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining a text embedding of a text prompt and an image embedding of an image prompt. Some embodiments map the text embedding into a joint embedding space to obtain a joint text embedding and map the image embedding into the joint embedding space to obtain a joint image embedding. Some embodiments generate a synthetic image based on the joint text embedding and the joint image embedding.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for latent-based editing of digital images using a generative neural network. In particular, in one or more embodiments, the disclosed systems perform latent-based editing of a digital image by mapping a feature tensor and a set of style vectors for the digital image into a joint feature style space. In one or more implementations, the disclosed systems apply a joint feature style perturbation and/or modification vectors within the joint feature style space to determine modified style vectors and a modified feature tensor. Moreover, in one or more embodiments the disclosed systems generate a modified digital image utilizing a generative neural network from the modified style vectors and the modified feature tensor.

Abstract: Embodiments include systems and methods for generative image filling based on text and a reference image. In one aspect, the system obtains an input image, a reference image, and a text prompt. Then, the system encodes the reference image to obtain an image embedding and encodes the text prompt to obtain a text embedding. Subsequently, a composite image is generated based on the input image, the image embedding, and the text embedding.

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: A method, apparatus, and non-transitory computer readable medium for image generation are described. Embodiments of the present disclosure obtain a content input and a style input via a user interface or from a database. The content input includes a target spatial layout and the style input includes a target style. A content encoder of an image processing apparatus encodes the content input to obtain a spatial layout mask representing the target spatial layout. A style encoder of the image processing apparatus encodes the style input to obtain a style embedding representing the target style. An image generation model of the image processing apparatus generates an image based on the spatial layout mask and the style embedding, where the image includes the target spatial layout and the target style.

Abstract: Embodiments include systems and methods for generative image filling based on text and a reference image. In one aspect, the system obtains an input image, a reference image, and a text prompt. Then, the system encodes the reference image to obtain an image embedding and encodes the text prompt to obtain a text embedding. Subsequently, a composite image is generated based on the input image, the image embedding, and the text embedding.

Abstract: A system that utilizes neural networks to generate looping animations from still images. The system fits a 3D model to a pose of a person in a digital image. The system receives a 3D animation sequence that transitions between a starting pose and an ending pose. The system generates, utilizing an animation transition neural network, first and second 3D animation transition sequences that respectively transition between the pose of the person and the starting pose and between the ending pose and the pose of the person. The system modifies each of the 3D animation sequence, the first 3D animation transition sequence, and the second 3D animation transition sequence by applying a texture map. The system generates a looping 3D animation by combining the modified 3D animation sequence, the modified first 3D animation transition sequence, and the modified second 3D animation transition sequence.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning models to generate modified digital images. In particular, in some embodiments, the disclosed systems generate image editing directions between textual identifiers of two visual features utilizing a language prediction machine learning model and a text encoder. In some embodiments, the disclosed systems generated an inversion of a digital image utilizing a regularized inversion model to guide forward diffusion of the digital image. In some embodiments, the disclosed systems utilize cross-attention guidance to preserve structural details of a source digital image when generating a modified digital image with a diffusion neural network.