公开(公告)号：US20240163395A1

公开(公告)日：2024-05-16

申请号：US18388668

申请日：2023-11-10

申请人： Disney Enterprises, Inc. ,  ETH Zurich (EIDGENOSSISCHE TECHNISCHE HOSHSCHULE ZURICH )

发明人： Abdelaziz Djelouah ,  Karlis Martins Briedis ,  Markus Plack ,  Christopher Richard Schroers

IPC分类号： H04N7/01 ,  G06T3/00 ,  G06T3/40

CPC分类号： H04N7/0135 ,  G06T3/0093 ,  G06T3/40

摘要： A system includes a hardware processor, a memory storing software code, and a machine learning (ML) model-based video frame interpolator. The hardware processor executes the software code to provide first and second frames of a video sequence including a plurality of frames, respective binary masks for the first and second frames, and optionally an intermediate frame of the video sequence between the first and second frames and a binary mask for the intermediate frame, as interpolation inputs to the ML model-based video frame interpolator. The hardware processor further executes the software code to generate, using the ML model-based video frame interpolator and the interpolation inputs, an interpolated frame and an error map for the interpolated frame, wherein generating the interpolated frame and the error map includes a cross-backward warping of respective latent feature representations of each of the plurality of frames.