-
公开(公告)号：US10825219B2
公开(公告)日：2020-11-03
申请号：US16361941
申请日：2019-03-22
Applicant: Northeastern University
Inventor： Yun Fu , Songyao Jiang
Abstract: Embodiments provide methods and systems for image generation through use of adversarial networks. An embodiment trains an image generator comprising (i) a generator implemented with a first neural network configured to generate a fake image based on a target segmentation, (ii) a discriminator implemented with a second neural network configured to distinguish a real image from a fake image and output a discrimination result as a function thereof and (iii) a segmentor implemented with a third neural network configured to generate a segmentation from the fake image. The training includes (i) operating the generator to output the fake image to the discriminator and the segmentor and (ii) iteratively operating the generator, discriminator, and segmentor during a training period, whereby the discriminator and generator train in an adversarial relationship with each other and the generator and segmentor train in a collaborative relationship with each other.
-
公开(公告)号：US20190295302A1
公开(公告)日：2019-09-26
申请号：US16361941
申请日：2019-03-22
Applicant: Northeastern University
Inventor： Yun Fu , Songyao Jiang
Abstract: Embodiments provide methods and systems for image generation through use of adversarial networks. An embodiment trains an image generator comprising (i) a generator implemented with a first neural network configured to generate a fake image based on a target segmentation, (ii) a discriminator implemented with a second neural network configured to distinguish a real image from a fake image and output a discrimination result as a function thereof and (iii) a segmentor implemented with a third neural network configured to generate a segmentation from the fake image. The training includes (i) operating the generator to output the fake image to the discriminator and the segmentor and (ii) iteratively operating the generator, discriminator, and segmentor during a training period, whereby the discriminator and generator train in an adversarial relationship with each other and the generator and segmentor train in a collaborative relationship with each other.
-
公开(公告)号：US20170236000A1
公开(公告)日：2017-08-17
申请号：US15268988
申请日：2016-09-19
Applicant: Samsung Electronics Co., Ltd. , Northeastern University
Inventor： Wonjun Hwang , Sungjoo Suh , Jaejoon Han , Chang Kyu Choi , Yun Fu , Zhengming Ding , Ming Shao
CPC classification number: G06K9/00268 , G06K9/00228 , G06K9/00275 , G06K9/00288 , G06K9/6215 , G06K9/6234 , G06K9/6269
Abstract: A method of converting a vector corresponding to an input image includes receiving input vector data associated with an input image including an object; and converting the received input vector data into feature data based on a projection matrix having a fixed rank, wherein a first dimension of the input vector data is higher than a second dimension of the feature data.
-
公开(公告)号：US12205317B2
公开(公告)日：2025-01-21
申请号：US17759939
申请日：2021-02-10
Applicant: Northeastern University
Inventor： Yun Fu , Songyao Jiang , Bin Sun
Abstract: Embodiments identify joints of a multi-limb body in an image. One such embodiment unifies depth of a plurality of multi-scale feature maps generated from an image of a multi-limb body to create a plurality of feature maps each having a same depth. In turn, for each of the plurality of feature maps having the same depth, an initial indication of one or more joints in the image is generated. The one or more joints are located at an interconnection of a limb to the multi-limb body or at an interconnection of a limb to another limb. To continue, a final indication of the one or more joints in the image is generated using each generated initial indication of the one or more joints.
-
公开(公告)号：US20230153946A1
公开(公告)日：2023-05-18
申请号：US18055386
申请日：2022-11-14
Applicant: Northeastern University
CPC classification number: G06T3/4053 , G06T5/40 , G06T3/4046 , G06T2207/20084
Abstract: A system and corresponding method perform image super-resolution (SR). The system comprises an element-unshuffled downsampler and an image SR module. The image SR module performs image SR on a low-resolution (LR) representation of a high-resolution (HR) original image. The HR original image is at a higher resolution relative to a resolution of the LR representation. The image SR module produces a reconstructed version of the HR original image via the image SR performed. The image SR is based on element-unshuffled downsampling of the LR representation. The element-unshuffled downsampler performs the element-unshuffled downsampling. The image SR module outputs the reconstructed version produced. The system performs the image SR with fewer parameters and less computation cost relative to conventional image SR.
-
Patent Agency Ranking
公开(公告)号：US20210158023A1
公开(公告)日：2021-05-27
申请号：US17045902
申请日：2019-05-02
Applicant: Northeastern University
Abstract: A system, neural network, and corresponding method generate 3D landmarks associated with an object in a 2D image. An embodiment is a system comprising a neural network detector configured to produce planar coordinates of landmarks at points of the object in the 2D image and a depth coordinate estimator. The planar coordinates include planar coordinate pairs. The depth coordinate estimator is configured to receive the 2D image and the planar coordinates and to estimate a depth coordinate for each planar coordinate pair of each landmark to generate the 3D landmarks. The system reduces network parameters from MB to KB and has better performance relative to state-of-the-art methods. The system may be configured to apply the 3D landmarks for face alignment, virtual face makeup, face recognition, eye gaze tracking, face synthesis, or other face related application.
-
公开(公告)号：US20210104067A1
公开(公告)日：2021-04-08
申请号：US17046398
申请日：2019-05-15
Applicant: Northeastern University
Abstract: Embodiments provide functionality for identifying joints and limbs in images. An embodiment extracts features from an image to generate feature maps and, in turn, processes the feature maps using a single convolutional neural network trained based on a target model that includes joints and limbs. The processing generates both a directionless joint confidence map indicating confidence with which pixels in the image depict one or more joints and a directionless limb confidence map indicating confidence with which the pixels in the image depict one or more limbs between adjacent joints of the one or more joints, wherein adjacency of joints is provided by the target model. To continue, indications of the one or more joints and the one or more limbs in the image are generated using the directionless joint confidence map, the directionless limb confidence map, and the target model. Embodiments can be deployed on mobile and embedded systems.
-
公开(公告)号：US10726601B2
公开(公告)日：2020-07-28
申请号：US16415128
申请日：2019-05-17
Applicant: Northeastern University
Inventor： Yun Fu , Shuyang Wang
Abstract: A system and method are provided to detect, analyze and digitally remove makeup from an image of a face. An autoencoder-based framework is provided to extract attractiveness-aware features to perform an assessment of facial beauty.
-
公开(公告)号：US11651526B2
公开(公告)日：2023-05-16
申请号：US17156204
申请日：2021-01-22
Applicant: Northeastern University
CPC classification number: G06T11/00 , G06N3/045 , G06N3/08 , G06V10/764 , G06V10/82 , G06V40/161 , G06V40/168
Abstract: An apparatus and corresponding method for frontal face synthesis. The apparatus comprises a decoder that synthesizes a high-resolution (HR) frontal-view (FV) image of a face from received features of a low-resolution (LR) non-frontal-view (NFV) image of the face. The HR FV image is of a higher resolution relative to a lower resolution of the LR NFV image. The decoder includes a main path and an auxiliary path. The auxiliary path produces auxiliary-path features from the received features and feeds the auxiliary-path features produced into the main path for synthesizing the HR FV image. The auxiliary-path features represent a HR NFV image of the face at the higher resolution. As such, an HR identity-preserved frontal face can be synthesized from one or many LR faces with various poses and may be used in types of commercial applications, such as video surveillance.
-
公开(公告)号：US20230126178A1
公开(公告)日：2023-04-27
申请号：US17759939
申请日：2021-02-10
Applicant: Northeastern University
Inventor： Yun Fu , Songyao Jiang , Bin Sun
Abstract: Embodiments identify joints of a multi-limb body in an image. One such embodiment unifies depth of a plurality of multi-scale feature maps generated from an image of a multi-limb body to create a plurality of feature maps each having a same depth. In turn, for each of the plurality of feature maps having the same depth, an initial indication of one or more joints in the image is generated. The one or more joints are located at an interconnection of a limb to the multi-limb body or at an interconnection of a limb to another limb. To continue, a final indication of the one or more joints in the image is generated using each generated initial indication of the one or more joints.
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.017 seconds)
