公开(公告)号：US20230281756A1

公开(公告)日：2023-09-07

申请号：US18179730

申请日：2023-03-07

Applicant: GoPro, Inc.

Inventor： Charles Laroche ,  Matias Tassano Ferres ,  Andrés Almansa

IPC: G06T3/40 ,  G06T5/00

CPC classification number: G06T3/4076 ,  G06T3/4046 ,  G06T5/002

Abstract: Systems, apparatus, and methods for super-resolution of non-uniform spatial blur. Non-uniform spatial blur presents unique challenges for conventional neural network processing. Existing implementations attempt to handle super-resolution with a “brute force” optimization. Various embodiments of the present disclosure subdivide the super-resolution function into sub-steps. “Unfolding” super-resolution into smaller closed-form functions allows for operation generic plug-and-play convolutional neural network (CNN) logic. Additionally, each step can be optimized with its own step-specific hyper parameters to improve performance.

公开(公告)号：US20220405882A1

公开(公告)日：2022-12-22

申请号：US17845723

申请日：2022-06-21

Applicant: GoPro, Inc.

Inventor： Matias Tassano Ferrés ,  Charles Laroche

IPC: G06T3/40 ,  G06T5/00

Abstract: A non-blind generator or a blind generator can be used to generate a high-resolution image from a low-resolution image. The non-blind generator includes a kernel encoder, a concatenator, and a super-resolution network. The kernel encoder obtains a blur kernel to generate one or more kernel maps. The concatenator concatenates a low-resolution image to one or more kernel maps to obtain a concatenated image. The super-resolution network includes one or more convolutional layers that process the concatenated image. The super-resolution network includes a pixel shuffle layer that outputs a high-resolution image based on the processed concatenated image.

公开(公告)号：US11967346B1

公开(公告)日：2024-04-23

申请号：US17695535

申请日：2022-03-15

Applicant: GoPro, Inc.

Inventor： Téo Marcin ,  Charles Laroche

IPC: G11B27/13 ,  G06V20/50

CPC classification number: G11B27/13 ,  G06V20/50

Abstract: An image capture device may experience motion while capturing a video. A video clip may be generated from the video. The beginning of the video clip may be identified based on acceleration of the image capture device during capture of the video, while the ending of the video clip may be identified based on speed of the image capture device during capture of the video.