公开(公告)号：US20230343136A1

公开(公告)日：2023-10-26

申请号：US17729987

申请日：2022-04-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yatao ZHONG ,  Faezeh AMJADI ,  Ilya Dmitriyevich ZHARKOV

IPC: G06V40/16 ,  G06T3/00 ,  G06V20/59 ,  G06V10/82 ,  G06V10/44 ,  H04N21/4788

CPC classification number: G06V40/168 ,  G06T3/0093 ,  G06V20/597 ,  G06V10/82 ,  G06V10/454 ,  H04N21/4788

Abstract: A face-processing system is described for producing a target image based on a source image and driving information. The source image includes data depicting at least a face of a source subject having a source identity, a source pose, and a source expression. The driving information specifies one or more driving characteristics. The target image combines characteristics of the source image and the driving information. According to illustrative implementations, the face-processing system produces the target image by using plural warping subcomponents that operate at plural respective levels of a neural network and at increasing respective resolutions. Each warping subcomponent operates, in part, based on geometric displacement field (GDF) information that describes differences between a source mesh derived from the source image and a driving mesh derived from the driving information.

公开(公告)号：US20220122235A1

公开(公告)日：2022-04-21

申请号：US17073256

申请日：2020-10-16

Applicant: Microsoft Technology Licensing, LLC

Inventor： Luming LIANG ,  Ilya Dmitriyevich ZHARKOV ,  Vivek PRADEEP ,  Faezeh AMJADI

IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: A computational photography system is described herein including a guidance system and a detail enhancement system. The guidance system uses a first neural network that maps an original image provided by an image sensor to a guidance image, which represents a color-corrected and lighting-corrected version of the original image. A combination unit combines the original image and the guidance image to produce a combined image. A detail-enhancement system then uses a second neural network to map the combined image to a predicted image. The predicted image supplements the guidance provided by the first neural network by sharpening details in the original image. A training system is also described herein for training the first and second neural networks. The training system alternates in the data it feeds the second neural network, first using a guidance image as input to the second neural network, and then using a corresponding ground-truth image.