TRANSFORMER-BASED IMAGE SEGMENTATION ON MOBILE DEVICES

    公开(公告)号:US20240281978A1

    公开(公告)日:2024-08-22

    申请号:US18170336

    申请日:2023-02-16

    Applicant: Adobe Inc.

    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating segmentation masks for a digital visual media item. In particular, in one or more embodiments, the disclosed systems generate, utilizing a neural network encoder, high-level features of a digital visual media item. Further, the disclosed systems generate, utilizing the neural network encoder, low-level features of the digital visual media item. In some implementations, the disclosed systems generate, utilizing a neural network decoder, an initial segmentation mask of the digital visual media item from the low-level features. Moreover, the disclosed systems generate, utilizing the neural network decoder, a refined segmentation mask of the digital visual media item from the initial segmentation mask and the high-level features.

Patent Agency Ranking