公开(公告)号：US20240265490A1

公开(公告)日：2024-08-08

申请号：US18436509

申请日：2024-02-08

Applicant: Google LLC

Inventor： Janne Matias Kontkanen ,  Eric Tabellion ,  Brian Lee Curless ,  Fitsum Reda ,  Deqing Sun ,  Caroline Rebecca Pantofaru

IPC: G06T3/4007 ,  G06T3/18 ,  G06T7/246

CPC classification number: G06T3/4007 ,  G06T3/18 ,  G06T7/248 ,  G06T2207/20081

Abstract: Provided is a computer system that includes one or more processors and one or more non-transitory computer-readable media that collectively store a machine-learned image interpolation model. The machine-learned image interpolation model is configured to: extract, for each of multiple different scales, a respective set of feature values from each of a pair of input images; generate, for each of the multiple different scales, a respective flow estimate for each of the pair of input images that indicates a respective flow from the interpolation time to the respective capture time; warp, for each of the multiple different scales, the respective set of feature values for each of the pair of input images according to the respective flow estimate to generate respective warped sets of features; and generate a interpolated image based on the respective warped sets of features for the pair of input images and the multiple different scales.