-
公开(公告)号：WO2022187013A1
公开(公告)日：2022-09-09
申请号：PCT/US2022/017181
申请日：2022-02-22
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Abstract: In various embodiments, a computer-implemented method of training a neural network for relighting an image is described. A first training set that includes source images and a target illumination embedding is generated, the source images having respective illuminated subjects. A second training set that includes augmented images and the target illumination embedding is generated, where the augmented images corresponding to the source images. A first autoencoder is trained using the first training set to generate a first output set that includes estimated source illumination embeddings and first reconstructed images that correspond to the source images, the reconstructed images having respective subjects that are i) from the corresponding source image, and ii) illuminated based on the target illumination embedding. A second autoencoder is trained using the second training set to generate a second output set that includes estimated augmented illumination embeddings and second reconstructed images that correspond to the augmented images.
-
公开(公告)号：WO2022231762A1
公开(公告)日：2022-11-03
申请号：PCT/US2022/023206
申请日：2022-04-03
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Abstract: Training a neural network for creating an output signal of different modality from an input signal is described. A first modality is a sound signal or a visual image and where the output signal is a visual image or a sound signal, respectively. In embodiments a model is trained using a pair of visual and audio networks to train a set of codebooks using known visual and audio signals and using a second pair of visual and audio networks to further train the set of codebooks using the augmented visual signals and the augmented audio signals. The visual and audio networks may be equally weighted, respectively. In aspects of the present disclosure, the set of codebooks comprise a visual codebook, an audio codebook and a correlation codebook, which are then used to create a visual image from a sound signal and/or a sound signal from a visual image.
-
Patent Agency Ranking
公开(公告)号：WO2022081225A1
公开(公告)日：2022-04-21
申请号：PCT/US2021/042264
申请日：2021-07-20
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： NEOFYTOU, Alexandros , SOMMERLADE, Eric Chris Wolfgang , SZTRAJMAN, Alejandro , SENGUPTA, Sunando
IPC: H04N19/20 , H04N19/167 , G06K9/00 , G06N3/08 , G06N20/00 , G06T5/00 , G06T7/00 , G06T15/50 , H04N19/30
Abstract: Technology is described herein that uses an object-encoding system to convert an object image into a combined encoding. The object image depicts a reference object, while the combined encoding represents an environment image. The environment image, in turn, depicts an estimate of an environment that has produced the illumination effects exhibited by the reference object. The combined encoding includes: a first part that represents image content in the environment image within a high range of intensities values; and a second part that represents image content within a low range of intensity values. Also described herein is a training system that trains the object-encoding system based on combined encodings produced by a separately-trained environment-encoding system. Also described herein are various applications of the object-encoding system and environment-encoding system.
-
公开(公告)号：WO2022260797A1
公开(公告)日：2022-12-15
申请号：PCT/US2022/028412
申请日：2022-05-10
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Abstract: Methods and systems for applying gaze adjustment techniques to participants in a video conference are disclosed. Some examples may include: receiving, at computing system, image adjustment information associated with a video stream including images of a first participant, identifying, for a display layout of a communication application, a location displaying the images of the first participant, determining, based on the received image adjustment information, a location displaying images of a second participant for the display layout, the received image adjustment information indicating that an eye gaze of the first participant being directed toward the second participant, computing an eye gaze direction of the first participant based on the location displaying images of the second participant, generating gaze-adjusted images based on the desired eye gaze direction of the first participant and replacing the images within the video stream with the gaze-adjusted images.
-
公开(公告)号：WO2022250869A1
公开(公告)日：2022-12-01
申请号：PCT/US2022/027189
申请日：2022-05-02
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Abstract: A method of improving image quality of a stream of input images is described. The stream of input images, including a current input image, is received. One or more target objects, including a first target object, are identified spatio-temporally within the stream of input images. The one or more target objects are tracked spatio-temporally within the stream of input images. The current input image is segmented into i) a foreground including the first target object, and ii) a background. The foreground is processed to have improved image quality in the current input image. Processing of the foreground further comprises processing the first target object using a same processing technique as for a prior input image of the stream of input images based on the tracking of the first target object. The background is processed differently from the foreground. An output image is generated by merging the foreground with the background.
-
公开(公告)号：WO2021145961A1
公开(公告)日：2021-07-22
申请号：PCT/US2020/062101
申请日：2020-11-24
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
IPC: G10L25/51 , G10L25/30 , G06N3/04 , G06N3/08 , G10L25/57 , G06K9/00 , G06T11/00 , G10L21/10 , G06K9/00624 , G06K9/4628 , G06K9/6256 , G06K9/6268 , G06K9/6271 , G06N3/0454 , G06N3/0472 , H04N5/272 , H04N7/141
Abstract: A computing system includes an encoder that receives an input image and encodes the input image into real image features, a decoder that decodes the real image features into a reconstructed image, a generator that receives first audio data corresponding to the input image and generates first synthetic image features from the first audio data, and receives second audio data and generates second synthetic image features from the second audio data, a discriminator that receives both the real and synthetic image features and determines whether a target feature is real or synthetic, and a classifier that classifies a scene of the second audio data based on the second synthetic image features.
-
公开(公告)号：WO2021066907A1
公开(公告)日：2021-04-08
申请号：PCT/US2020/038576
申请日：2020-06-19
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Abstract: A method for image enhancement on a computing device includes receiving a digital input image depicting a human eye. From the digital input image, the computing device generates a gaze-adjusted image via a gaze adjustment machine learning model by changing an apparent gaze direction of the human eye. From the gaze-adjusted image and potentially in conjunction with the digital input image, the computing device generates a detail-enhanced image via a detail enhancement machine learning model by adding or modifying details. The computing device outputs the detail-enhanced image.
-
-
-
-
-
-
Search Results
7
records
(took 0.016 seconds)
