公开(公告)号：US20240161364A1

公开(公告)日：2024-05-16

申请号：US18053646

申请日：2022-11-08

Applicant: Adobe Inc.

Inventor： Zichuan Liu ,  Xin Lu ,  Ke Wang

IPC: G06T11/60 ,  G06T7/13 ,  G06V10/44

CPC classification number: G06T11/60 ,  G06T7/13 ,  G06V10/44 ,  G06T2207/20084

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating image mattes for detected objects in digital images without trimap segmentation via a multi-branch neural network. The disclosed system utilizes a first neural network branch of a generative neural network to extract a coarse semantic mask from a digital image. The disclosed system utilizes a second neural network branch of the generative neural network to extract a detail mask based on the coarse semantic mask. Additionally, the disclosed system utilizes a third neural network branch of the generative neural network to fuse the coarse semantic mask and the detail mask to generate an image matte. In one or more embodiments, the disclosed system also utilizes a refinement neural network to generate a final image matte by refining selected portions of the image matte generated by the generative neural network.

公开(公告)号：US12282987B2

公开(公告)日：2025-04-22

申请号：US18053646

申请日：2022-11-08

Applicant: Adobe Inc.

Inventor： Zichuan Liu ,  Xin Lu ,  Ke Wang

IPC: G06T11/60 ,  G06N3/02 ,  G06N3/08 ,  G06N20/00 ,  G06T7/13 ,  G06V10/44

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating image mattes for detected objects in digital images without trimap segmentation via a multi-branch neural network. The disclosed system utilizes a first neural network branch of a generative neural network to extract a coarse semantic mask from a digital image. The disclosed system utilizes a second neural network branch of the generative neural network to extract a detail mask based on the coarse semantic mask. Additionally, the disclosed system utilizes a third neural network branch of the generative neural network to fuse the coarse semantic mask and the detail mask to generate an image matte. In one or more embodiments, the disclosed system also utilizes a refinement neural network to generate a final image matte by refining selected portions of the image matte generated by the generative neural network.