Patents by Inventor Jiaya Jia
Jiaya Jia has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20210334942Abstract: This application discloses an image processing method, device, and apparatus, and a storage medium. The method is performed by a computing device, the method including: receiving an input image; determining a context feature of the input image; determining a first feature set and a second feature set according to the context feature and based on a size of a target image and a location of the input image in the target image; adjusting the second feature set according to a first feature statistic of the first feature set, to obtain an adjusted second feature set; and generating the target image based on the adjusted second feature set and the first feature set.Type: ApplicationFiled: July 9, 2021Publication date: October 28, 2021Inventors: Yi WANG, Xin TAO, Jiaya JIA, Yuwing TAI, Xiaoyong SHEN
-
Publication number: 20210327076Abstract: This application provides a target tracking method, including: obtaining a plurality of consecutive picture frames of a target video, and setting a tracked target region of an nth picture frame; performing a feature extraction operation on the tracked target region of the nth picture frame, to obtain a feature map of the tracked target region; calculating a weighted filter corresponding to the input feature map according to a correlation filter algorithm and a mean pooling constraint condition; calculating an output response of an (n+1)th picture frame by using the weighted filter and an input feature map of the (n+1)th picture frame in the plurality of consecutive picture frames, and determining a tracked target region of the (n+1)th picture frame according to the output response of the (n+1)th picture frame, until tracked target regions of all the consecutive picture frames are obtained. This application improves precision and effectiveness of target tracking.Type: ApplicationFiled: July 1, 2021Publication date: October 21, 2021Inventors: Chong SUN, Yuxuan SUN, Huchuan LU, Xiaoyong SHEN, Yuwing TAI, Jiaya JIA
-
Publication number: 20210287047Abstract: Embodiments of this application disclose a training method using image processing model for processing blurry images. The method includes obtaining a sample pair comprising a clear image and a corresponding blurry image; the sharpness of the clear image being greater than a preset threshold, the sharpness of the blurry image being less than the preset threshold; activating the image processing model to perform sharpness restoration on the blurry image to obtain a restored image; and updating network parameters of a first network and network parameters of a second network in the image processing model according to the restored image and the clear image to obtain a trained image processing model; the network parameters of the first network and the network parameters of the second network meeting a selective sharing condition indicating whether the network parameters between the first network and the second network are shared or independent.Type: ApplicationFiled: May 27, 2021Publication date: September 16, 2021Inventors: Hongyun GAO, Xin TAO, Jiaya JIA, Yuwing TAI, Xiaoyong SHEN
-
Publication number: 20210281774Abstract: A video caption generating method is provided to a computer device. The method includes encoding a target video by using an encoder of a video caption generating model, to obtain a target visual feature of the target video, decoding the target visual feature by using a basic decoder of the video caption generating model, to obtain a first selection probability corresponding to a candidate word, decoding the target visual feature by using an auxiliary decoder of the video caption generating model, to obtain a second selection probability corresponding to the candidate word, a memory structure of the auxiliary decoder including reference visual context information corresponding to the candidate word, determining a decoded word in the candidate word according to the first selection probability and the second selection probability, and generating a video caption according to decoded word.Type: ApplicationFiled: May 24, 2021Publication date: September 9, 2021Inventors: Wenjie PEI, Jiyuan ZHANG, Lei KE, Yuwing TAI, Xiaoyong SHEN, Jiaya JIA, Xiangrong WANG
-
Publication number: 20210279503Abstract: An image processing method includes: obtaining an image, and performing feature extraction on the image; generating at least one candidate region of the image, and mapping the at least one candidate region into a feature map of the image, one candidate region including one instance; processing the mapped feature map based on a target network for instance segmentation; and indicating an overall structure of an occluded instance in the image by using a perspective mask, and indicating an invisible part of the occluded instance by using a non-perspective mask, the perspective mask and the non-perspective mask representing a relative occlusion relationship of the occluded instance.Type: ApplicationFiled: May 25, 2021Publication date: September 9, 2021Inventors: Lu QI, Li JIANG, Shu LIU, Xiaoyong SHEN, Jiaya JIA, Yuwing TAI
-
Publication number: 20210272236Abstract: Embodiments of this disclosure include an image enhancement method and apparatus. The image enhancement may include obtaining an original image and performing synthesis processing on features of the original image to obtain a first illumination map corresponding to the original image. A resolution of the first illumination map may be lower than a resolution of the original image. The image enhancement may further include obtaining, based on the first illumination map, a mapping relationship between an image to an illumination map and performing mapping processing on the original image based on the mapping relationship to obtain a second illumination map. A resolution of the second illumination map may be equal to the resolution of the original image. The image enhancement may further include performing image enhancement processing on the original image according to the second illumination map to obtain a target image.Type: ApplicationFiled: May 19, 2021Publication date: September 2, 2021Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Ruixing WANG, Xin TAO, Xiaoyong SHEN, Jiaya JIA, Yuwing TAI
-
Publication number: 20210232924Abstract: A method for training an SMPL parameter prediction model, including: obtaining a sample picture; inputting the sample picture into a pose parameter prediction model to obtain a predicted pose parameter; inputting the sample picture into a shape parameter prediction model to obtain a predicted shape parameter; calculating model prediction losses according to an SMPL parameter prediction model and annotation information of the sample picture; and updating the pose parameter prediction model and the shape parameter prediction model according to the model prediction losses.Type: ApplicationFiled: April 15, 2021Publication date: July 29, 2021Inventors: Shuang Sun, Chen Li, Yuwing Tai, Jiaya Jia, Xiaoyong Shen
-
Publication number: 20210012558Abstract: Embodiments of this application disclose a method and an apparatus for reconstructing a three-dimensional model of a human body, and a storage medium. The method includes obtaining a two-dimensional image of a human body part to be reconstructed; mapping the two-dimensional image to a voxel space, to obtain a voxelized result of the two-dimensional image; obtaining three-dimensional morphable model parameters corresponding to the two-dimensional image based on calculating the voxelized result using a preset three-dimensional parameter regression network; and reconstructing a three-dimensional model of the human body part based on the three-dimensional morphable model parameters.Type: ApplicationFiled: September 29, 2020Publication date: January 14, 2021Inventors: Chen LI, Hongwei YI, Qiong CAO, Xiaoyong SHEN, Yuwing TAI, Jiaya JIA
-
Publication number: 20200311402Abstract: A human pose prediction method is provided for an electronic device. The method includes using a basic neural network based on image-feature-based prediction to perform prediction on an inputted target image, to obtain an initial prediction map of a human key-point; inputting the initial prediction map of the human key-point and a human structure diagram into a pose graph neural network based on spatial information mining, each node in the human structure diagram corresponding to a human joint respectively, and each edge connecting adjacent human joints; using the pose graph neural network to initialize the human structure diagram by using the initial prediction map of the human key-point, to obtain an initialized human structure diagram; and using the pose graph neural network to perform iterative prediction on the initialized human structure diagram, to obtain a final prediction map, the final prediction map indicating a predicted human pose.Type: ApplicationFiled: June 17, 2020Publication date: October 1, 2020Inventors: Hong ZHANG, Xiaoyong SHEN, Jiaya JIA
-
Publication number: 20200312043Abstract: Embodiments of the present disclosure disclose a face model processing method performed at an electronic device. The method includes the following steps: obtaining a three-dimensional face model corresponding to a user picture, and selecting a sample oral cavity model in an oral cavity model library for the three-dimensional face model; registering the sample oral cavity model into the three-dimensional face model by using an oral cavity position parameter in the three-dimensional face model; performing form adjustment on an oral cavity form of the registered sample oral cavity model by using an expression parameter of the three-dimensional face model to generate a target oral cavity model; and generating, based on the three-dimensional face model and the target oral cavity model, a three-dimensional face expression model corresponding to the user picture.Type: ApplicationFiled: June 10, 2020Publication date: October 1, 2020Inventors: Weilong Peng, Chen Li, Yuwing Tai, Xiaoyong Shen, Jiaya Jia
-
Publication number: 20200134365Abstract: An instance segmentation method includes: performing feature extraction on an image via a neural network to output features at at least two different hierarchies; extracting region features corresponding to at least one instance candidate region in the image from the features at the at least two different hierarchies, and fusing region features corresponding to a same instance candidate region, to obtain a first fusion feature of each instance candidate region; and performing instance segmentation based on each first fusion feature, to obtain at least one of an instance segmentation result of the corresponding instance candidate region or an instance segmentation result of the image.Type: ApplicationFiled: December 29, 2019Publication date: April 30, 2020Applicant: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.Inventors: Shu LIU, Lu QI, Haifang QIN, Jianping SHI, Jiaya JIA
-
Patent number: 10127679Abstract: An image alignment method and apparatus, where the method and apparatus include obtaining image information of two to-be-aligned images, determining, using a cross-correlation measurement model, first coordinate offset according to the image information of the two images, where the first coordinate offset are used to indicate position deviations of to-be-aligned pixels between the two images in the coordinate system, and aligning the two images according to coordinates of pixels in the first image in the coordinate system and the first coordinate offset.Type: GrantFiled: March 3, 2017Date of Patent: November 13, 2018Assignee: HUAWEI TECHNOLOGIES CO., LTD.Inventors: Xiaoyong Shen, Jiaya Jia, Kwok Wai Hung
-
Publication number: 20170316572Abstract: The present disclosure discloses user equipment and an image processing method and apparatus, which relate to the field of information technologies and can improve accuracy in determining image depth information. The method includes: first obtaining an original image, then determining, according to the original image and at least two preset edge image blocks, a target blur value corresponding to a pixel in the original image, and finally, determining a depth value corresponding to the pixel in the original image according to the target blur value corresponding to the pixel in the original image. The present invention is applicable to determining of a blur value corresponding to a pixel in an image and determining of a depth value corresponding to the pixel in the image according to the blur value corresponding to the pixel in the image.Type: ApplicationFiled: December 9, 2016Publication date: November 2, 2017Inventors: Xin TAO, Jiaya JIA, Yadong LU
-
Publication number: 20170228890Abstract: Embodiments of the present invention disclose an object detection method and a computer device. The method includes: obtaining a to-be-processed image; obtaining, according to the to-be-processed image, n reference regions used to identify a to-be-detected object in the to-be-processed image, and n detection accuracy values, of the to-be-detected object, corresponding to the n reference regions; determining sample reference regions in the n reference regions, where coincidence degrees of the sample reference regions is greater than a preset threshold; and determining, based on the sample reference regions, a target region corresponding to the to-be-detected object, where the target region is used to identify the to-be-detected object in the to-be-processed image. Implementation of the embodiments of the present invention helps improve accuracy of detecting a location of an object.Type: ApplicationFiled: February 6, 2017Publication date: August 10, 2017Inventors: Shu LIU, Jiaya JIA, Yadong LU
-
Publication number: 20170178348Abstract: An image alignment method and apparatus, where the method and apparatus include obtaining image information of two to-be-aligned images, determining, using a cross-correlation measurement model, first coordinate offset according to the image information of the two images, where the first coordinate offset are used to indicate position deviations of to-be-aligned pixels between the two images in the coordinate system, and aligning the two images according to coordinates of pixels in the first image in the coordinate system and the first coordinate offset.Type: ApplicationFiled: March 3, 2017Publication date: June 22, 2017Inventors: Xiaoyong Shen, Jiaya Jia, Kwok Wai Hung
-
Patent number: 9665792Abstract: A method for generating a sharp image based on a blurry image is provided. The method includes acquiring pixel values of pixels in the blurry image, and a convolution kernel of the blurry image, determining a deconvolution kernel of the blurry image based on a preset image gradient operator and the convolution kernel, determining pixel values of pixels in the sharp image based on the deconvolution kernel and the pixel values of the pixels in the blurry image, and generating the sharp image based on the pixel values of the pixels in the sharp image. A deconvolution kernel in the embodiments of the present disclosure is determined based on a gradient operator and a convolution kernel, in other words, the deconvolution kernel introduces the gradient operator as a regularization constraint, which prevents noise from affecting an image recovery process, and improves the quality of a recovered sharp image.Type: GrantFiled: September 2, 2015Date of Patent: May 30, 2017Assignee: Huawei Technologies Co., Ltd.Inventors: Li Xu, Jiaya Jia, Kwok Wai Hung
-
Publication number: 20160070979Abstract: A method for generating a sharp image based on a blurry image is provided. The method includes acquiring pixel values of pixels in the blurry image, and a convolution kernel of the blurry image, determining a deconvolution kernel of the blurry image based on a preset image gradient operator and the convolution kernel, determining pixel values of pixels in the sharp image based on the deconvolution kernel and the pixel values of the pixels in the blurry image, and generating the sharp image based on the pixel values of the pixels in the sharp image. A deconvolution kernel in the embodiments of the present disclosure is determined based on a gradient operator and a convolution kernel, in other words, the deconvolution kernel introduces the gradient operator as a regularization constraint, which prevents noise from affecting an image recovery process, and improves the quality of a recovered sharp image.Type: ApplicationFiled: September 2, 2015Publication date: March 10, 2016Inventors: Li Xu, Jiaya Jia, Kwok Wai Hung
-
Patent number: 9171355Abstract: Systems and methods for multispectral imaging are disclosed. The multispectral imaging system can include a near infrared (NIR) imaging sensor and a visible imaging sensor. The disclosed systems and methods can be implemented to de-noise a visible light image using a gradient scale map generated from gradient vectors in the visible light image and a NIR image. The gradient scale map may be used to determine the amount of de-noising guidance applied from the NIR image to the visible light image on a pixel-by-pixel basis.Type: GrantFiled: January 9, 2014Date of Patent: October 27, 2015Assignee: QUALCOMM IncorporatedInventors: Shaojie Zhuo, Xiaopeng Zhang, Chen Feng, Liang Shen, Jiaya Jia
-
Publication number: 20150125092Abstract: Systems and methods for multispectral imaging are disclosed. The multispectral imaging system can include a near infrared (NIR) imaging sensor and a visible imaging sensor. The disclosed systems and methods can be implemented to de-noise a visible light image using a gradient scale map generated from gradient vectors in the visible light image and a NIR image. The gradient scale map may be used to determine the amount of de-noising guidance applied from the NIR image to the visible light image on a pixel-by-pixel basis.Type: ApplicationFiled: January 9, 2014Publication date: May 7, 2015Applicant: QUALCOMM IncorporatedInventors: Shaojie Zhuo, Xiaopeng Zhang, Chen Feng, Liang Shen, Jiaya Jia
-
Publication number: 20140002441Abstract: The present invention relates to method and apparatus for temporally-consistent depth estimation. Such a depth estimation preserve both object boundary as well as temporal consistency using techniques of segmentation and pixel trajectory.Type: ApplicationFiled: June 29, 2012Publication date: January 2, 2014Applicant: Hong Kong Applied Science and Technology Research Institute Company LimitedInventors: Chun Ho Hung, Li Xu, Jiaya Jia, Lu Wang