公开(公告)号：US20240119706A1

公开(公告)日：2024-04-11

申请号：US18242965

申请日：2023-09-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kamal Jnawali ,  Tien Cheng Bau ,  Joonsoo Kim

IPC: G06V10/774 ,  G06T3/40 ,  G06T7/13 ,  G06T7/73 ,  G06V10/26 ,  G06V10/82 ,  G06V20/40 ,  G06V20/62

CPC classification number: G06V10/774 ,  G06T3/4046 ,  G06T3/4053 ,  G06T7/13 ,  G06T7/73 ,  G06V10/26 ,  G06V10/82 ,  G06V20/46 ,  G06V20/62 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06V2201/09

Abstract: One embodiment provides a method comprising detecting at least one object displayed within at least one input frame of an input video. The method further comprises cropping, from the at least one input frame, at least one cropped image including the at least one object. The method further comprises generating at least one training image by overlaying simulated text on the at least one cropped image. The method further comprises providing the at least one training image to a pruned convolutional neural network (CNN). The pruned CNN learns, from the at least one training image, to reconstruct objects and textual regions during image super-resolution.