公开(公告)号：US20220335672A1

公开(公告)日：2022-10-20

申请号：US17585449

申请日：2022-01-26

Applicant: NVIDIA Corporation

Inventor： Donghoon LEE ,  Sifei LIU ,  Jinwei GU ,  Ming-Yu LIU ,  Jan KAUTZ

IPC: G06T11/60 ,  G06T3/00 ,  G06K9/62 ,  G06T7/30 ,  G06V30/262

Abstract: One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

公开(公告)号：US20200074707A1

公开(公告)日：2020-03-05

申请号：US16201934

申请日：2018-11-27

Applicant: NVIDIA CORPORATION

Inventor： Donghoon LEE ,  Sifei LIU ,  Jinwei GU ,  Ming-Yu LIU ,  Jan KAUTZ

IPC: G06T11/60 ,  G06T3/00 ,  G06K9/72 ,  G06K9/62 ,  G06T7/30

Abstract: One embodiment of a method includes applying a first generator model to a semantic representation of an image to generate an affine transformation, where the affine transformation represents a bounding box associated with at least one region within the image. The method further includes applying a second generator model to the affine transformation and the semantic representation to generate a shape of an object. The method further includes inserting the object into the image based on the bounding box and the shape.

公开(公告)号：US20200294194A1

公开(公告)日：2020-09-17

申请号：US16299062

申请日：2019-03-11

Applicant: NVIDIA Corporation

Inventor： Deqing Sun ,  Orazio Gallo ,  Jan Kautz ,  Jinwei GU ,  Wei-Sheng Lai

IPC: G06T3/40 ,  G06K9/34 ,  G06K9/00 ,  G06K9/32 ,  G06N3/08

Abstract: A video stitching system combines video from different cameras to form a panoramic video that, in various embodiments, is temporally stable and tolerant to strong parallax. In an embodiment, the system provides a smooth spatial interpolation that can be used to connect the input video images. In an embodiment, the system applies an interpolation layer to slices of the overlapping video sources, and the network learns a dense flow field to smoothly align the input videos with spatial interpolation. Various embodiments are applicable to areas such as virtual reality, immersive telepresence, autonomous driving, and video surveillance.