公开(公告)号：US20230112186A1

公开(公告)日：2023-04-13

申请号：US17500736

申请日：2021-10-13

Applicant: Adobe Inc.

Inventor： Brian Price ,  Yutong Dai ,  He Zhang

IPC: G06T7/194 ,  G06T7/11 ,  G06T5/00 ,  G06T5/50

Abstract: This disclosure describes one or more implementations of an alpha matting system that utilizes a deep learning model to generate alpha mattes for digital images utilizing an alpha-range classifier function. More specifically, in various implementations, the alpha matting system builds and utilizes an object mask neural network having a decoder that includes an alpha-range classifier to determine classification probabilities for pixels of a digital image with respect to multiple alpha-range classifications. In addition, the alpha matting system can utilize a refinement model to generate the alpha matte from the pixel classification probabilities with respect to the multiple alpha-range classifications.

公开(公告)号：US20230135978A1

公开(公告)日：2023-05-04

申请号：US17513559

申请日：2021-10-28

Applicant: Adobe Inc.

Inventor： Brian Price ,  Yutong Dai ,  He Zhang

IPC: G06T9/00 ,  G06T3/40 ,  G06T7/194 ,  G06T7/11 ,  G06N3/04

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a transformer-based encoder-decoder neural network architecture for generating alpha mattes for digital images. Specifically, the disclosed system utilizes a transformer encoder to generate patch-based encodings from a digital image and a trimap segmentation by generating patch encodings for image patches and comparing the patch encodings to areas of the digital image. Additionally, the disclosed system generates modified patch-based encodings utilizing a plurality of neural network layers. The disclosed system also generates an alpha matte for the digital image from the patch-based encodings utilizing a decoder that includes a plurality of upsampling layers connected to a plurality of neural network layers via skip connections. In additional embodiments, the disclosed system generates the alpha matte based on additional encodings generated by a plurality of convolutional neural network layers connected to a subset of the upsampling layers via skip connections.

公开(公告)号：US12051225B2

公开(公告)日：2024-07-30

申请号：US17513559

申请日：2021-10-28

Applicant: Adobe Inc.

Inventor： Brian Price ,  Yutong Dai ,  He Zhang

IPC: G06N3/04 ,  G06T3/4046 ,  G06T7/11 ,  G06T7/194 ,  G06T9/00

CPC classification number: G06T9/002 ,  G06N3/04 ,  G06T3/4046 ,  G06T7/11 ,  G06T7/194

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a transformer-based encoder-decoder neural network architecture for generating alpha mattes for digital images. Specifically, the disclosed system utilizes a transformer encoder to generate patch-based encodings from a digital image and a trimap segmentation by generating patch encodings for image patches and comparing the patch encodings to areas of the digital image. Additionally, the disclosed system generates modified patch-based encodings utilizing a plurality of neural network layers. The disclosed system also generates an alpha matte for the digital image from the patch-based encodings utilizing a decoder that includes a plurality of upsampling layers connected to a plurality of neural network layers via skip connections. In additional embodiments, the disclosed system generates the alpha matte based on additional encodings generated by a plurality of convolutional neural network layers connected to a subset of the upsampling layers via skip connections.

公开(公告)号：US12236610B2

公开(公告)日：2025-02-25

申请号：US17500736

申请日：2021-10-13

Applicant: Adobe Inc.

Inventor： Brian Price ,  Yutong Dai ,  He Zhang

IPC: G06T7/194 ,  G06T5/50 ,  G06T5/94 ,  G06T7/11

Abstract: This disclosure describes one or more implementations of an alpha matting system that utilizes a deep learning model to generate alpha mattes for digital images utilizing an alpha-range classifier function. More specifically, in various implementations, the alpha matting system builds and utilizes an object mask neural network having a decoder that includes an alpha-range classifier to determine classification probabilities for pixels of a digital image with respect to multiple alpha-range classifications. In addition, the alpha matting system can utilize a refinement model to generate the alpha matte from the pixel classification probabilities with respect to the multiple alpha-range classifications.

公开(公告)号：US20240362825A1

公开(公告)日：2024-10-31

申请号：US18762395

申请日：2024-07-02

Applicant: Adobe Inc.

Inventor： Brian Price ,  Yutong Dai ,  He Zhang

IPC: G06T9/00 ,  G06N3/04 ,  G06T3/4046 ,  G06T7/11 ,  G06T7/194

CPC classification number: G06T9/002 ,  G06N3/04 ,  G06T3/4046 ,  G06T7/11 ,  G06T7/194

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a transformer-based encoder-decoder neural network architecture for generating alpha mattes for digital images. Specifically, the disclosed system utilizes a transformer encoder to generate patch-based encodings from a digital image and a trimap segmentation by generating patch encodings for image patches and comparing the patch encodings to areas of the digital image. Additionally, the disclosed system generates modified patch-based encodings utilizing a plurality of neural network layers. The disclosed system also generates an alpha matte for the digital image from the patch-based encodings utilizing a decoder that includes a plurality of upsampling layers connected to a plurality of neural network layers via skip connections. In additional embodiments, the disclosed system generates the alpha matte based on additional encodings generated by a plurality of convolutional neural network layers connected to a subset of the upsampling layers via skip connections.