Adobe, Inc.

Adobe Systems Inc.

Other

Czech Technical University in Prague

Elya Shechtman

Jingwan Lu

Sohrab Amirghodsi

Connelly Barnes

Oliver Wang

Richard Zhang

Kalyan Krishna Sunkavalli

Zhe Lin

Aliakbar Darabi

Jianming Zhang

Ratheesh Kalarot

Jue Wang

Shabnam Ghadar

Daniel Goldman

Dan Goldman

Sylvain Philippe Paris

Zhixin Shu

Michal Lukac

Geoffrey Oxholm

Wei-An Lin

Taesung Park

Nathan Aaron Carr

Yijun Li

Scott David Cohen

Paul John Asente

Jakub Fiser

Cameron Smith

Yuqian Zhou

Haitian Zheng

Alexei A Efros

Jun-Yan Zhu

Ondrej Jamriska

Baldo Antonio Faieta

Matthew David Fisher

Ning Xu

Niloy Jyoti Mitra

Daniel Sýkora

Hyunjoon Lee

Aseem Agarwala

Seungyong Lee

Junyan Zhu

Chetan Nanda

Hailin Jin

Jianchao Yang

Jonathan Worthen Brandt

Jose Ignacio Echevarria Vallespi

Aaron Phillip Hertzmann

Vladimir Kim

Mehmet Yumer

Kevin Wampler

Qing Liu

Chen-Hsuan Lin

Sunil Sharadchandra Hadap

Jimei Yang

Lubomir D Bourdev

David P Simons

Yang Zhou

Jonathan Eisenmann

Bryan Russell

Krishna Kumar Singh

Adam Finkelstein

John Nelson

Ian D Sachs

John Thomas Nack

Michal Lukác

Guang Chen

Tharun Mohandoss

Wenqi Xian

Yu Zeng

Pulkit Gera

Fei Yang

Yuheng Li

Brian Lynn Price

Zhaowen Wang

Yilin Wang

Xue Bai

Dingzeyu Li

He Zhang

Alexandru Vasile Costin

Hui Qu

Sarah Stuckey

Shai Bagon

David Edward Jacobs

Xiaoyong Shen

Chen Fang

Duygu Ceylan Aksit

Saeid Motiian

Zexiang Xu

Jun Saito

Zijun Wei

Akhilesh Kumar

Daniel Lischinski

Yoav HaCohen

Michael Gharbi

Yinglan Ma

Florian Kainz

Omid Poursaeed

Siddhant Jain

Tobias Hinz

Aspects of the methods, apparatus, non-transitory computer readable medium, and systems include obtaining a noise map and a global image code encoded from an original image and representing semantic content of the original image; generating a plurality of image patches based on the noise map and the global image code using a diffusion model; and combining the plurality of image patches to produce an output image including the semantic content.

Diffusion models having continuous scaling through patch-wise image generation

An image processing system uses a depth-conditioned autoencoder to generate a modified image from an input image such that the modified image maintains an overall structure from the input image while modifying textural features. An encoder of the depth-conditioned autoencoder extracts a structure latent code from an input image and depth information for the input image. A generator of the depth-conditioned autoencoder generates a modified image using the structure latent code and a texture latent code. The modified image generated by the depth-conditioned autoencoder includes the structural features from the input image while incorporating textural features of the texture latent code. In some aspects, the autoencoder is depth-conditioned during training by augmenting training images with depth information. The autoencoder is trained to preserve the depth information when generating images.

Generation using depth-conditioned autoencoder

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately generating inpainted digital images utilizing a guided inpainting model guided by both plane panoptic segmentation and plane grouping. For example, the disclosed systems utilize a guided inpainting model to fill holes of missing pixels of a digital image as informed or guided by an appearance guide and a geometric guide. Specifically, the disclosed systems generate an appearance guide utilizing plane panoptic segmentation and generate a geometric guide by grouping plane panoptic segments. In some embodiments, the disclosed systems generate a modified digital image by implementing an inpainting model guided by both the appearance guide (e.g., a plane panoptic segmentation map) and the geometric guide (e.g., a plane grouping map).

Improving digital image inpainting utilizing plane panoptic segmentation and plane grouping

A scene modeling system receives a video including a plurality of frames corresponding to views of an object and a request to display an editable three-dimensional (3D) scene that corresponds to a particular frame of the plurality of frames. The scene modeling system applies a scene representation model to the particular frame, and includes a deformation model configured to generate, for each pixel of the particular frame based on a pose and an expression of the object, a deformation point using a 3D morphable model (3DMM) guided deformation field. The scene representation model includes a color model configured to determine, for the deformation point, color and volume density values. The scene modeling system receives a modification to one or more of the pose or the expression of the object including a modification to a location of the deformation point and renders an updated video based on the received modification.

Deformable neural radiance field for editing facial pose and facial expression in neural 3D scenes

Systems and methods for image processing are described. Embodiments of the present disclosure receive an image comprising a first region that includes content and a second region to be inpainted. Noise is then added to the image to obtain a noisy image, and a plurality of intermediate output images are generated based on the noisy image using a diffusion model trained using a perceptual loss. The intermediate output images predict a final output image based on a corresponding intermediate noise level of the diffusion model. The diffusion model then generates the final output image based on the intermediate output image. The final output image includes inpainted content in the second region that is consistent with the content in the first region.

Image and object inpainting with diffusion models

The present disclosure relates to systems, methods, and non-transitory computer readable media that generate inpainted digital images utilizing class-specific cascaded modulation inpainting neural network. For example, the disclosed systems utilize a class-specific cascaded modulation inpainting neural network that includes cascaded modulation decoder layers to generate replacement pixels portraying a particular target object class. To illustrate, in response to user selection of a replacement region and target object class, the disclosed systems utilize a class-specific cascaded modulation inpainting neural network corresponding to the target object class to generate an inpainted digital image that portrays an instance of the target object class within the replacement region. Moreover, in one or more embodiments the disclosed systems train class-specific cascaded modulation inpainting neural networks corresponding to a variety of target object classes, such as a sky object class, a water object class, a ground object class, or a human object class.

Object class inpainting in digital images utilizing class-specific inpainting neural networks

Systems and methods train an encoder neural network for fast and accurate projection into the latent space of a Generative Adversarial Network (GAN). The encoder is trained by providing an input training image to the encoder and producing, by the encoder, a latent space representation of the input training image. The latent space representation is provided as input to the GAN to generate a generated training image. A latent code is sampled from a latent space associated with the GAN and the sampled latent code is provided as input to the GAN. The GAN generates a synthetic training image based on the sampled latent code. The sampled latent code is provided as input to the encoder to produce a synthetic training code. The encoder is updated by minimizing a loss between the generated training image and the input training image, and the synthetic training code and the sampled latent code.

Supervised learning techniques for encoder training

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images by utilizing a patch match algorithm to generate nearest neighbor fields for a second digital image based on a nearest neighbor field associated with a first digital image. For example, the disclosed systems can identify a nearest neighbor field associated with a first digital image of a first resolution. Based on the nearest neighbor field of the first digital image, the disclosed systems can utilize a patch match algorithm to generate a nearest neighbor field for a second digital image of a second resolution larger than the first resolution. The disclosed systems can further generate a modified digital image by filling a target region of the second digital image utilizing the generated nearest neighbor field.

Generating modified digital images utilizing nearest neighbor fields from patch matching operations of alternate digital images

The present disclosure relates to systems, methods, and non-transitory computer readable media for panoptically guiding digital image inpainting utilizing a panoptic inpainting neural network. In some embodiments, the disclosed systems utilize a panoptic inpainting neural network to generate an inpainted digital image according to panoptic segmentation map that defines pixel regions corresponding to different panoptic labels. In some cases, the disclosed systems train a neural network utilizing a semantic discriminator that facilitates generation of digital images that are realistic while also conforming to a semantic segmentation. The disclosed systems generate and provide a panoptic inpainting interface to facilitate user interaction for inpainting digital images. In certain embodiments, the disclosed systems iteratively update an inpainted digital image based on changes to a panoptic segmentation map.

Generating and providing a panoptic inpainting interface for generating and modifying inpainted digital images

Iteratively modifying inpainted digital images based on changes to panoptic segmentation maps

Learning parameters for neural networks using a semantic discriminator and an object-level discriminator

Systems and methods for image generation are provided. An aspect of the systems and methods for image generation includes obtaining an original image depicting an element and a target prompt describing a modification to the element. The system may then compute a first output and a second output using a diffusion model. The first output is based on a description of the element and the second output is based on the target prompt. The system then computes a difference between the first output and the second output, and generates a modified image including the modification to the element of the original image based on the difference.

Image generation using a diffusion model

An improved system architecture uses a Generative Adversarial Network (GAN) including a specialized generator neural network to generate multiple resolution output images. The system produces a latent space representation of an input image. The system generates a first output image at a first resolution by providing the latent space representation of the input image as input to a generator neural network comprising an input layer, an output layer, and a plurality of intermediate layers and taking the first output image from an intermediate layer, of the plurality of intermediate layers of the generator neural network. The system generates a second output image at a second resolution different from the first resolution by providing the latent space representation of the input image as input to the generator neural network and taking the second output image from the output layer of the generator neural network.

Multi-scale output techniques for generative adversarial networks

Systems and methods train and apply a specialized encoder neural network for fast and accurate projection into the latent space of a Generative Adversarial Network (GAN). The specialized encoder neural network includes an input layer, a feature extraction layer, and a bottleneck layer positioned after the feature extraction layer. The projection process includes providing an input image to the encoder and producing, by the encoder, a latent space representation of the input image. Producing the latent space representation includes extracting a feature vector from the feature extraction layer, providing the feature vector lo the bottleneck layer as input, and producing the latent space representation as output. The latent space representation produced by the encoder is provided as input to the GAN, which generates an output image based upon the latent space representation.

Direct regression encoder architecture and training

One or more processing devices access a scene depicting a reference object that includes an annotation identifying a target region to be modified in one or more video frames. The one or more processing devices determine that a target pixel corresponds to a sub-region within the target region that includes hallucinated content. The one or more processing devices determine gradient constraints using gradient values of neighboring pixels in the hallucinated content, the neighboring pixels being adjacent to the target pixel and corresponding to four cardinal directions. The one or more processing devices update color data of the target pixel subject to the determined gradient constraints.

Corrective lighting for video inpainting

Growing community of inventors

Seattle, WA, United States of America

Elya Shechtman