公开(公告)号：US11227419B2

公开(公告)日：2022-01-18

申请号：US16834590

申请日：2020-03-30

Applicant: Adobe Inc.

Inventor： Ankit Phogat ,  Vineet Batra ,  Daniel Kaufman

IPC: G06T11/20 ,  G06T11/60

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for removing an anchor point from a Bezier spline while preserving the shape of the Bezier spline. For example, the disclosed systems can replace adjacent input segments of an initial Bezier spline that are connected at an anchor point with a new contiguous segment that does not include an anchor point and that spans the portion of the spline covered by the adjacent segments. The disclosed systems can utilize an objective function to determine tangent vectors that indicate locations of control points for generating the new segment to replace the adjacent segments. In addition, the disclosed systems can generate a modified Bezier spline that includes the new segment in place of the adjacent segments of the initial Bezier spline.

公开(公告)号：US20200175759A1

公开(公告)日：2020-06-04

申请号：US16205132

申请日：2018-11-29

Applicant: Adobe Inc.

Inventor： Bryan Russell ,  Daniel Kaufman ,  Carlo Innamorati ,  Niloy Mitra

IPC: G06T19/00 ,  G06T15/20 ,  G06T17/00 ,  G06F3/01 ,  G06K9/62 ,  G06N20/00

Abstract: This application relates generally to augmenting images and videos with dynamic object compositing, and more specifically, to generating synthetic training data to train a machine learning model to automatically augment an image or video with a dynamic object. The synthetic training data may contain multiple data points from thousands of simulated dynamic object movements within a virtual environment. Based on the synthetic training data, the machine learning model may determine the movement of a new dynamic object within new virtual environment.