-
公开(公告)号:US12067730B2
公开(公告)日:2024-08-20
申请号:US17495618
申请日:2021-10-06
Applicant: ADOBE INC.
Inventor: Zhe Lin , Simon Su Chen , Jason Wen-youg Kuen , Bo Sun
Abstract: Various disclosed embodiments are directed to refining or correcting individual semantic segmentation/instance segmentation masks that have already been produced by baseline models in order to generate a final coherent panoptic segmentation map. Specifically, a refinement model, such as an encoder-decoder-based neural network, generates or predicts various data objects, such as foreground masks, bounding box offset maps, center maps, center offset maps, and coordinate convolution. This, among other functionality described herein, improves the inaccuracies and computing resource consumption of existing technologies.