公开(公告)号：US20250117902A1

公开(公告)日：2025-04-10

申请号：US18482753

申请日：2023-10-06

Applicant: NVIDIA CORPORATION

Inventor： Donald Lee BRITTAIN ,  Andrew Ian RUSSELL ,  Anjul PATNEY ,  Yinghao XU ,  Shaveen KUMAR

IPC: G06T5/00 ,  G06T3/40 ,  G06T5/20 ,  G06T7/00 ,  G06T7/60 ,  G06T7/70

Abstract: In various examples, disclosed techniques use a banding detector neural network to identify the locations and sizes of banding artifacts in pixel regions of an input image. The neural network generates a band size map that identifies at least one banding artifact in the input image. The band size map can include a set of predicted band size values, each of which corresponds to a respective pixel of the input image and represents a distance between edges of a banding artifact. The band size map and the input image are provided as input to a stochastic bilateral blur filter, which generates a de-banded image by applying blurring effects to the input image at the band locations indicated by the band size map. An inverse tone mapping operation is then performed to convert the de-banded image to an image that does not have banding artifacts.

公开(公告)号：US20240251171A1

公开(公告)日：2024-07-25

申请号：US18406006

申请日：2024-01-05

Applicant: NVIDIA CORPORATION

Inventor： Iuri FROSIO ,  Yazhou XING ,  Chao LIU ,  Anjul PATNEY ,  Hongxu YIN ,  Amrita MAZUMDAR ,  Jan KAUTZ

IPC: H04N23/73 ,  H04N23/95

CPC classification number: H04N23/73 ,  H04N23/95

Abstract: One or more embodiments include receiving one or more frames of a live video captured by a video capturing device, wherein the one or more frames include a current frame that is most-recently captured, identifying a set of reference frames included in the one or more frames based on at least the current frame, wherein each frame in the set of reference frames has a different exposure level relative to the current frame, determining, using one or more neural networks, a set of missing details for one or more regions of the current frame based on the set of reference frames, generating an updated version of the current frame based on the set of details, and outputting the updated version of the current frame in real-time.