Adobe, Inc.

Ucl Business Plc

Yangtuanfeng Wang

Duygu Ceylan Aksit

Krishna Kumar Singh

Jingwan Lu

Niloy Jyoti Mitra

Tobias Hinz

Jimei Yang

Yijun Li

Zhe Lin

Jianming Zhang

Yang Zhou

Yi Zhou

Qing Liu

Giorgio Gori

Jae Shin Yoon

Xin Sun

Mehmet Yumer

Jovan Popović

Kuldeep Kulkarni

Meng Zhang

Zeyu Wang

Qingyang Tan

Hugo Bertiche Argila

Chun Hao Huang

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

Synthesizing a modified digital image utilizing a reposing model

The present disclosure relates to systems, methods, and non-transitory computer readable media that utilizes neural networks to generate cinemagraphs from single RGB images. For example, the cyclic animation system includes a cyclic animation neural network trained with synthetic data, wherein different wind effects can be replicated using physically based simulations to create cyclic videos more efficiently. More specifically, the cyclic animation system generalizes a solution by operating in the gradient domain and using surface normal maps. Because normal maps are invariant to appearance (color, texture, illumination, etc.), the gap between synthetic and real data distribution in the normal map space is smaller than in the RGB space. The cyclic animation system performs a reshading approach that synthesizes RGB pixels from the original image and the animated normal maps to create plausible changes to the real image to create the cinemagraph.

Creating cinemagraphs from a single image

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

Generating a modified digital image utilizing a human inpainting model

Systems and methods are described for rendering garments. The system includes a first machine learning model trained to generate coarse garment templates of a garment and a second machine learning model trained to render garment images. The first machine learning model generates a coarse garment template based on position data. The system produces a neural texture for the garment, the neural texture comprising a multi-dimensional feature map characterizing detail of the garment. The system provides the coarse garment template and the neural texture to the second machine learning model trained to render garment images. The second machine learning model generates a rendered garment image of the garment based on the coarse garment template of the garment and the neural texture.

Garment rendering techniques

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

Embodiments are disclosed for using machine learning models to perform three-dimensional garment deformation due to character body motion with collision handling. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input, the input including character body shape parameters and character body pose parameters defining a character body, and garment parameters. The disclosed systems and methods further comprise generating, by a first neural network, a first set of garment vertices defining deformations of a garment with the character body based on the input. The disclosed systems and methods further comprise determining, by a second neural network, that the first set of garment vertices includes a second set of garment vertices penetrating the character body. The disclosed systems and methods further comprise modifying, by a third neural network, each garment vertex in the second set of garment vertices to positions outside the character body.

Resolving garment collisions using neural networks

In implementations of systems for generating digital objects to animate sketches, a computing device implements a sketch system to receive input data describing a user sketched digital object having a pose and a non-photorealistic style. The sketch system generates a latent vector representation of the user defined non-photorealistic style using an encoder of a generative adversarial network. A digital object is generated having the pose and a non-photorealistic style using a generator of the generative adversarial network based on the latent vector representation of the user defined non-photorealistic style. The sketch system modifies the latent vector representation of the user defined non-photorealistic style based on a comparison between the user defined non-photorealistic style and the non-photorealistic style.

Systems for generating digital objects to animate sketches

Systems and techniques provide a user interface within an application to enable users to designate a folded object image of a folded object, as well as a superimposed image of a superimposed object to be added to the folded object image. Within the user interface, the user may simply place the superimposed image over the folded object image to obtain the desired modified image. If the user places the superimposed image over one or more folds of the folded object image, portions of the superimposed image will be removed to create the illusion in the modified image that the removed portions are obscured by one or more folds.

Digital image editing for images of folded objects

Growing community of inventors

London, United Kingdom

Yangtuanfeng Wang