-
公开(公告)号：US11615512B2
公开(公告)日：2023-03-28
申请号：US17189478
申请日：2021-03-02
Applicant: Microsoft Technology Licensing, LLC
Inventor： Alexandros Neofytou , Eric Chris Wolfgang Sommerlade , Sunando Sengupta , Yang Liu
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：US20220284551A1
公开(公告)日：2022-09-08
申请号：US17189478
申请日：2021-03-02
Applicant: Microsoft Technology Licensing, LLC
Inventor： Alexandros Neofytou , Eric Chris Wolfgang Sommerlade , Sunando Sengupta , Yang Liu
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：US12288366B2
公开(公告)日：2025-04-29
申请号：US18383956
申请日：2023-10-26
Applicant: Microsoft Technology Licensing, LLC
Inventor： Sunando Sengupta , Alexandros Neofytou , Eric Chris Wolfgang Sommerlade , Yang Liu
Abstract: In various embodiments, a computer-implemented method of training a neural network for creating an output signal of different modality from an input signal is described. In embodiments, the first modality may be a sound signal or a visual image and where the output signal would be a visual image or a sound signal, respectively. In embodiments a model is trained using a first pair of visual and audio networks to train a set of codebooks using known visual signals and the 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. Further, the first and the second visual networks are equally weighted and where the first and the second audio networks are equally weighted.
-
公开(公告)号：US11706384B2
公开(公告)日：2023-07-18
申请号：US17342849
申请日：2021-06-09
Applicant: Microsoft Technology Licensing, LLC
CPC classification number: H04N7/144 , G06F3/013 , G06V40/103 , G06V40/171 , H04N7/147 , H04N7/152
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：US11164042B2
公开(公告)日：2021-11-02
申请号：US16844930
申请日：2020-04-09
Applicant: Microsoft Technology Licensing, LLC
Inventor： Eric Chris Wolfgang Sommerlade , Yang Liu , Alexandros Neofytou , Sunando Sengupta
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.
-
Patent Agency Ranking
公开(公告)号：US11947210B1
公开(公告)日：2024-04-02
申请号：US18143208
申请日：2023-05-04
Applicant: Microsoft Technology Licensing, LLC
Inventor： Timothy A. Large , Neil Emerton , Sunando Sengupta
IPC: G02F1/1335 , G02F1/13 , G06T7/73 , G06V40/16
CPC classification number: G02F1/133514 , G02F1/1323 , G06T7/73 , G06V40/172
Abstract: The present disclosure relates identifying an intended viewer and an unintended viewer of a liquid crystal display (LCD) using face recognition technology. Once identified the system may determine a face position for the unintended viewer. The system may modulate the voltage applied at a third electrode on the color filter layer of the LCD to achieve a certain off-axis contrast that may reduce the unintended viewer's visibility of the LCD without restricting the visibility of the intended viewer. Ultimately, the present disclosure provides enhanced privacy options for the intended viewer with a lightweight, inexpensive, and highly transportable system.
-
公开(公告)号：US11657833B2
公开(公告)日：2023-05-23
申请号：US17452306
申请日：2021-10-26
Applicant: Microsoft Technology Licensing, LLC
Inventor： Eric Chris Wolfgang Sommerlade , Yang Liu , Alexandros Neofytou , Sunando Sengupta
IPC: H04N5/272 , H04N7/14 , G06F18/214 , G06F18/241 , G06V10/764 , G10L25/51 , G06V10/82 , G06V10/44 , G06V20/00
CPC classification number: G10L25/51 , G06F18/214 , G06F18/241 , G06V10/454 , G06V10/764 , G06V10/82 , G06V20/00 , 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：US11330196B2
公开(公告)日：2022-05-10
申请号：US17067781
申请日：2020-10-12
Applicant: Microsoft Technology Licensing, LLC
Inventor： Alexandros Neofytou , Eric Chris Wolfgang Sommerlade , Alejandro Sztrajman , Sunando Sengupta
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：US11915398B2
公开(公告)日：2024-02-27
申请号：US18116052
申请日：2023-03-01
Applicant: Microsoft Technology Licensing, LLC
Inventor： Alexandros Neofytou , Eric Chris Wolfgang Sommerlade , Sunando Sengupta , Yang Liu
IPC: G06T5/00 , G06F18/214 , G06N3/08
CPC classification number: G06T5/005 , G06F18/214 , G06N3/08 , G06T2207/20081 , G06T2207/20084
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：US11871147B2
公开(公告)日：2024-01-09
申请号：US17342849
申请日：2021-06-09
Applicant: Microsoft Technology Licensing, LLC
CPC classification number: H04N7/144 , G06F3/013 , G06V40/103 , G06V40/171 , H04N7/147 , H04N7/152
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.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.016 seconds)
