Adobe, Inc.

Zijun Wei

Jianming Zhang

Zhe Lin

Yilin Wang

He Zhang

Xiaohui Shen

Radomir Mech

Brian Lynn Price

Seyed Morteza Safdarnejad

Salil Tambe

Elya Shechtman

Sohrab Amirghodsi

Connelly Barnes

Yuqian Zhou

Chenglin Yang

Scott David Cohen

Kalyan Krishna Sunkavalli

Jose Ignacio Echevarria Vallespi

Jason Wen Yong Kuen

Su Chen

Yinglan Ma

Florian Kainz

Xuaner Zhang

Jeya Maria Jose Valanarasu

Mang Tik Chiu

Xiaoyang Liu

The present disclosure relates to systems, methods, and non-transitory computer readable media for inpainting a digital image using a hybrid wire removal pipeline. For example, the disclosed systems use a hybrid wire removal pipeline that integrates multiple machine learning models, such as a wire segmentation model, a hole separation model, a mask dilation model, a patch-based inpainting model, and a deep inpainting model. Using the hybrid wire removal pipeline, in some embodiments, the disclosed systems generate a wire segmentation from a digital image depicting one or more wires. The disclosed systems also utilize the hybrid wire removal pipeline to extract or identify portions of the wire segmentation that indicate specific wires or portions of wires. In certain embodiments, the disclosed systems further inpaint pixels of the digital image corresponding to the wires indicated by the wire segmentation mask using the patch-based inpainting model and/or the deep inpainting model.

Inpainting digital images using a hybrid wire removal pipeline

Systems and methods for image segmentation are described. Embodiments of the present disclosure receive an image depicting an object; generate image features for the image by performing a convolutional self-attention operation that outputs a plurality of attention-weighted values for a convolutional kernel applied at a position of a sliding window on the image; and generate label data that identifies the object based on the image features.

Transformer for efficient image segmentation

Systems and methods for image segmentation are described. Embodiments of the present disclosure receive an image depicting an object; generate image features for the image by performing an atrous self-attention operation based on a plurality of dilation rates for a convolutional kernel applied at a position of a sliding window on the image; and generate label data that identifies the object based on the image features.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates object masks for digital objects portrayed in digital images utilizing a detection-masking neural network pipeline. In particular, in one or more embodiments, the disclosed systems utilize detection heads of a neural network to detect digital objects portrayed within a digital image. In some cases, each detection head is associated with one or more digital object classes that are not associated with the other detection heads. Further, in some cases, the detection heads implement multi-scale synchronized batch normalization to normalize feature maps across various feature levels. The disclosed systems further utilize a masking head of the neural network to generate one or more object masks for the detected digital objects. In some cases, the disclosed systems utilize post-processing techniques to filter out low-quality masks.

Detecting digital objects and generating object masks on device

Embodiments are disclosed for performing wire segmentation of images using machine learning. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input image, generating, by a first trained neural network model, a global probability map representation of the input image indicating a probability value of each pixel including a representation of wires, and identifying regions of the input image indicated as including the representation of wires. The disclosed systems and methods further comprise, for each region from the identified regions, concatenating the region and information from the global probability map to create a concatenated input, and generating, by a second trained neural network model, a local probability map representation of the region based on the concatenated input, indicating pixels of the region including representations of wires. The disclosed systems and methods further comprise aggregating local probability maps for each region.

Wire segmentation for images using machine learning

An image processing system generates an image mask from an image. The image is processed by an object detector to identify a region having an object, and the region is classified based on an object type of the object. A masking pipeline is selected from a number of masking pipelines based on the classification of the region. The region is processed using the masking pipeline to generate a region mask. An image mask for the image is generated using the region mask.

Object selection for images using image regions

Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Generating an image mask for a digital image by utilizing a multi-branch masking pipeline with neural networks

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating harmonized digital images utilizing an object-to-object harmonization neural network. For example, the disclosed systems implement, and learn parameters for, an object-to-object harmonization neural network to combine a style code from a reference object with features extracted from a target object. Indeed, the disclosed systems extract a style code from a reference object utilizing a style encoder neural network. In addition, the disclosed systems generate a harmonized target object by applying the style code of the reference object to a target object utilizing an object-to-object harmonization neural network.

Object-to-object harmonization for digital images

Automatically generating a trimap segmentation for a digital image by utilizing a trimap generation neural network

Various embodiments describe facilitating real-time crops on an image. In an example, an image processing application executed on a device receives image data corresponding to a field of view of a camera of the device. The image processing application renders a major view on a display of the device in a preview mode. The major view presents a previewed image based on the image data. The image processing application receives a composition score of a cropped image from a deep-learning system. The image processing application renders a sub-view presenting the cropped image based on the composition score in a preview mode. Based on a user interaction, the image processing application renders the cropped image in the major view with the sub-view in the preview mode.

Guided image composition on mobile devices

Various embodiments describe using a neural network to evaluate image crops in substantially real-time. In an example, a computer system performs unsupervised training of a first neural network based on unannotated image crops, followed by a supervised training of the first neural network based on annotated image crops. Once this first neural network is trained, the computer system inputs image crops generated from images to this trained network and receives composition scores therefrom. The computer system performs supervised training of a second neural network based on the images and the composition scores.

Image crop suggestion and evaluation using deep-learning

Various embodiments describe view switching of video on a computing device. In an example, a video processing application receives a stream of video data. The video processing application renders a major view on a display of the computing device. The major view presents a video from the stream of video data. The video processing application inputs the stream of video data to a deep learning system and receives back information that identifies a cropped video from the video based on a composition score of the cropped video, while the video is presented in the major view. The composition score is generated by the deep learning system. The video processing application renders a sub-view on a display of the device, the sub-view presenting the cropped video. The video processing application renders the cropped video in the major view based on a user interaction with the sub-view.

Growing community of inventors

Stoney Brook, NY, United States of America

Zijun Wei