Adobe, Inc.

Krishna Kumar Singh

Jingwan Lu

Yijun Li

Yangtuanfeng Wang

Zhe Lin

Jianming Zhang

Duygu Ceylan Aksit

Qing Liu

Tobias Hinz

Elya Shechtman

Yuheng Li

Jimei Yang

Richard Zhang

Yang Zhou

Zhifei Zhang

Ritwik Sinha

Giorgio Gori

Md Mehrab Tanjim

Gaurav Parmar

Jae Shin Yoon

Scott David Cohen

Jonathan Worthen Brandt

Zhihong Ding

Niloy Jyoti Mitra

Yi Zhou

David Arbour

Jun-Yan Zhu

Moumita Sinha

Sridhar Mahadevan

Pei Wang

Daniil Pakhomov

Mariette Souppe

Ohiremen Dibua

Cusuh Ham

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.

Utilizing a warped digital image with a reposing model to synthesize a modified digital image

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify two-dimensional images via scene-based editing using three-dimensional representations of the two-dimensional images. For instance, in one or more embodiments, the disclosed systems utilize three-dimensional representations of two-dimensional images to generate and modify shadows in the two-dimensional images according to various shadow maps. Additionally, the disclosed systems utilize three-dimensional representations of two-dimensional images to modify humans in the two-dimensional images. The disclosed systems also utilize three-dimensional representations of two-dimensional images to provide scene scale estimation via scale fields of the two-dimensional images. In some embodiments, the disclosed systems utilizes three-dimensional representations of two-dimensional images to generate and visualize 3D planar surfaces for modifying objects in two-dimensional images. The disclosed systems further use three-dimensional representations of two-dimensional images to customize focal points for the two-dimensional images.

Generating three-dimensional human models representing two-dimensional humans in two-dimensional images

A system debiases image translation models to produce generated images that contain minority attributes. A balanced batch for a minority attribute is created by over-sampling images having the minority attribute from an image dataset. An image translation model is trained using images from the balanced batch by applying supervised contrastive loss to output of an encoder of the image translation model and an auxiliary classifier loss based on predicted attributes in images generated by a decoder of the image translation model. Once trained, the image translation model is used to generate images with the minority image when given an input image having the minority attribute.

Debiasing image to image translation models

Systems and methods for image processing are described. Embodiments of the present disclosure obtain a noise image and guidance information for generating an image. A diffusion model generates an intermediate noise prediction for the image based on the noise image. A conditioning network generates noise modulation parameters. The intermediate noise prediction and the noise modulation parameters are combined to obtain a modified intermediate noise prediction. The diffusion model generates the image based on the modified intermediate noise prediction, wherein the image depicts a scene based on the guidance information.

Multimodal diffusion models

Synthesizing a modified digital image utilizing a reposing model

Modifying poses of two-dimensional humans in two-dimensional images by reposing three-dimensional human models representing the two-dimensional humans

Human inpainting utilizing a segmentation branch for generating an infill segmentation map

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via multi-layered scene completion techniques facilitated by artificial intelligence. For instance, in some embodiments, the disclosed systems receive a digital image portraying a first object and a second object against a background, where the first object occludes a portion of the second object. Additionally, the disclosed systems pre-process the digital image to generate a first content fill for the portion of the second object occluded by the first object and a second content fill for a portion of the background occluded by the second object. After pre-processing, the disclosed systems detect one or more user interactions to move or delete the first object from the digital image. The disclosed systems further modify the digital image by moving or deleting the first object and exposing the first content fill for the portion of the second object.

Modifying digital images via multi-layered scene completion facilitated by artificial intelligence

Utilizing a generative machine learning model to create modified digital images from an infill semantic map

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.

Utilizing cross-attention guidance to preserve content in diffusion-based image modifications

An image inpainting system is described that receives an input image that includes a masked region. From the input image, the image inpainting system generates a synthesized image that depicts an object in the masked region by selecting a first code that represents a known factor characterizing a visual appearance of the object and a second code that represents an unknown factor characterizing the visual appearance of the object apart from the known factor in latent space. The input image, the first code, and the second code are provided as input to a generative adversarial network that is trained to generate the synthesized image using contrastive losses. Different synthesized images are generated from the same input image using different combinations of first and second codes, and the synthesized images are output for display.

Diverse image inpainting using contrastive learning

Generating a modified digital image utilizing a human inpainting model

In implementations of systems for image inversion using multiple latent spaces, a computing device implements an inversion system to generate a segment map that segments an input digital image into a first image region and a second image region and assigns the first image region to a first latent space and the second image region to a second latent space that corresponds to a layer of a convolutional neural network. An inverted latent representation of the input digital image is computed using a binary mask for the second image region. The inversion system modifies the inverted latent representation of the input digital image using an edit direction vector that corresponds to a visual feature. An output digital image is generated that depicts a reconstruction of the input digital image having the visual feature based on the modified inverted latent representation of the input digital image.

Image inversion using multiple latent spaces

The present disclosure relates to systems, non-transitory computer-readable media, and method that utilize a character animation neural network informed by motion and pose signatures to generate a digital video through person-specific appearance modeling and motion retargeting. In particular embodiments, the disclosed systems implement a character animation neural network that includes a pose embedding model to encode a pose signature into spatial pose features. The character animation neural network further includes a motion embedding model to encode a motion signature into motion features. In some embodiments, the disclosed systems utilize the motion features to refine per-frame pose features and improve temporal coherency. In certain implementations, the disclosed systems also utilize the motion features to demodulate neural network weights used to generate an image frame of a character in motion based on the refined pose features.

Generating animated digital videos utilizing a character animation neural network informed by pose and motion embeddings

Methods and systems disclosed herein relate generally to systems and methods for generating simulated images for enhancing socio-demographic diversity. An image-generating application receives a request that includes a set of target socio-demographic attributes. The set of target socio-demographic attributes can define a gender, age, and/or race of a subject that are non-stereotypical for a particular occupation. The image-generating application applies the a machine-learning model to the set of target socio-demographic attributes. The machine-learning model generates a simulated image depicts a subject having visual characteristics that are defined by the set of target socio-demographic attributes.

Generating simulated images that enhance socio-demographic diversity

Growing community of inventors

San Jose, CA, United States of America

Krishna Kumar Singh