-
1.发明授权公开(公告)号：US11222466B1
公开(公告)日：2022-01-11
申请号：US17039895
申请日：2020-09-30
发明人： Jacek Krzysztof Naruniec , Derek Edward Bradley , Thomas Etterlin , Paulo Fabiano Urnau Gotardo , Leonhard Markus Helminger , Christopher Richard Schroers , Romann Matthew Weber
摘要： Techniques are disclosed for changing the identities of faces in video frames and images. In embodiments, three-dimensional (3D) geometry of a face is used to inform the facial identity change produced by an image-to-image translation model, such as a comb network model. In some embodiments, the model can take a two-dimensional (2D) texture map and/or a 3D displacement map associated with one facial identity as inputs and output another 2D texture map and/or 3D displacement map associated with a different facial identity. The other 2D texture map and/or 3D displacement map can then be used to render an image that includes the different facial identity.
-
公开(公告)号：US11849179B2
公开(公告)日：2023-12-19
申请号：US17701243
申请日：2022-03-22
发明人： Romann Matthew Weber , Graziana Mignone , Jacek Krzysztof Naruniec , Aaron Michael Baker , Farnood Salehi , Dennis Li
IPC分类号： H04N21/442 , H04N21/466
CPC分类号： H04N21/44218 , H04N21/4662
摘要： Techniques are disclosed for characterizing audience engagement with one or more characters in a media content item. In some embodiments, an audience engagement characterization application processes sensor data; such as video data capturing the faces of one or more audience members consuming a media content item, to generate an audience emotion signal. The characterization application also processes the media content item to generate a character emotion signal associated with one or more characters in the media content item. Then, the characterization application determines an audience engagement score based on an amount of alignment and/or misalignment between the audience emotion signal and the character emotion signal.
-
3.发明公开公开(公告)号：US20230316587A1
公开(公告)日：2023-10-05
申请号：US17707782
申请日：2022-03-29
发明人： Sirak Ghebremusse , Stéphane Grabli , Jacek Krzysztof Naruniec , Romann Matthew Weber , Christopher Richard Schroers
CPC分类号： G06T9/002 , G06V40/168 , G06T11/00 , G06T7/70 , G06T2207/30201 , G06T2207/20081 , G06T2200/24 , G06T2207/20092 , G06T2207/10016 , G06T2207/20084
摘要： A computer-implemented method of changing a face within an output image or video frame that includes: receiving an input image that includes a face presenting a facial expression in a pose; processing the image with a neural network encoder to generate a latent space point that is an encoded representation of the image; decoding the latent space point to generate an initial output image in accordance with a desired facial identity but with the facial expression and pose of the face in the input image; identifying a feature of the facial expression in the initial output image to edit; applying an adjustment vector to a latent space point corresponding to the initial output image to generate an adjusted latent space point; and decoding the adjusted latent space point to generate an adjusted output image in accordance with the desired facial identity but with the facial expression and pose of the face in the input image altered in accordance with the adjustment vector
-
公开(公告)号：US20230319223A1
公开(公告)日：2023-10-05
申请号：US17707785
申请日：2022-03-29
CPC分类号： H04N5/272 , G06V40/176 , G06V40/166 , H04N2005/2726
摘要： A computer-implemented method of changing a face within an output image or video frame includes: receiving an input image that includes a face presenting a facial expression in a pose; separately encoding different portions of the image by, for each separately encoded portion, generating a latent space point of the portion, thereby generating a plurality of multi-dimensional vectors where each multi-dimensional vector is an encoded representation of a different portion of the input image; concatenating the plurality of multi-dimensional vectors into a combined latent space vector; and decoding the combined latent space vector to generate the output image in accordance with a desired facial identity but with the facial expression and pose of the face in the input image
-
公开(公告)号：US11568524B2
公开(公告)日：2023-01-31
申请号：US16850898
申请日：2020-04-16
发明人： Leonard Markus Helminger , Jacek Krzysztof Naruniec , Romann Matthew Weber , Christopher Richard Schroers
摘要： Techniques are disclosed for changing the identities of faces in images. In embodiments, a tunable model for changing facial identities in images includes an encoder, a decoder, and dense layers that generate either adaptive instance normalization (AdaIN) coefficients that control the operation of convolution layers in the decoder or the values of weights within such convolution layers, allowing the model to change the identity of a face in an image based on a user selection. A separate set of dense layers may be trained to generate AdaIN coefficients for each of a number of facial identities, and the AdaIN coefficients output by different sets of dense layers can be combined to interpolate between facial identities. Alternatively, a single set of dense layers may be trained to take as input an identity vector and output AdaIN coefficients or values of weighs within convolution layers of the decoder.
-
公开(公告)号：US12111880B2
公开(公告)日：2024-10-08
申请号：US17484681
申请日：2021-09-24
发明人： Jacek Krzysztof Naruniec , Derek Edward Bradley , Paulo Fabiano Urnau Gotardo , Leonhard Markus Helminger , Christopher Andreas Otto , Christopher Richard Schroers , Romann Matthew Weber
CPC分类号： G06F18/21 , G06N3/045 , G06N3/088 , G06T11/001 , G06T17/20 , G06T2207/20081 , G06T2207/30201
摘要： Various embodiments set forth systems and techniques for changing a face within an image. The techniques include receiving a first image including a face associated with a first facial identity; generating, via a machine learning model, at least a first texture map and a first position map based on the first image; rendering a second image including a face associated with a second facial identity based on the first texture map and the first position map, wherein the second facial identity is different from the first facial identity.
-
公开(公告)号：US11640676B2
公开(公告)日：2023-05-02
申请号：US17000755
申请日：2020-08-24
IPC分类号： G06T7/73 , G06T3/00 , G06T3/40 , G06T3/60 , G06T3/20 , G06N20/00 , G06N5/04 , G06V40/16 , G06F18/21
摘要： Various embodiments set forth systems and techniques for training a landmark model. The techniques include determining, using the landmark model, a first landmark in a set of first landmarks associated with a first image; performing, on the first image, a first perturbation to obtain a second image; determining, using the landmark model, a second landmark in a set of second landmarks associated with the second image; determining, based on a first distance between the first landmark and the second landmark, a first loss function; and updating, based on the first loss function, a first parameter of the landmark model.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.015 秒)
