公开(公告)号：WO2018184140A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079401

申请日：2017-04-04

Applicant: INTEL CORPORATION ,  WANG, Shandong ,  LU, Ming ,  YAO, Anbang ,  CHEN, Yurong

Inventor： WANG, Shandong ,  LU, Ming ,  YAO, Anbang ,  CHEN, Yurong

IPC: G06K9/00

CPC classification number: G06K9/00281 ,  G06K9/00 ,  G06T11/00 ,  G06T13/20 ,  G06T15/04

Abstract: Techniques are provided for facial image replacement between a reference facial image and a target facial image, of varying pose and illumination, using 3-dimensional morphable face models (3DMMs). A methodology implementing the techniques according to an embodiment includes fitting the reference face and the target face to a first and second 3DMM, respectively. The method further includes generating a texture map based on the fitted 3D reference face and rendering the fitted 3D reference face to a pose of the fitted 3D target face. The rendering is based on parameters of the first 3DMM, parameters of the second 3DMM, and the generated texture map associated with the fitted 3D reference face. The method further includes, determining a region of interest of the target facial image; and blending the rendered 3D reference face onto the region of interest of the target facial image to generate a replaced facial image.

公开(公告)号：WO2018053703A1

公开(公告)日：2018-03-29

申请号：PCT/CN2016/099560

申请日：2016-09-21

Applicant: INTEL CORPORATION ,  WANG, Shandong ,  LU, Ming ,  YAO, Anbang ,  CHEN, Yurong

Inventor： WANG, Shandong ,  LU, Ming ,  YAO, Anbang ,  CHEN, Yurong

IPC: G06T17/00

CPC classification number: G06T13/40 ,  G06F3/01 ,  G06T15/04 ,  G06T15/10 ,  G06T17/00

Abstract: Techniques related to estimating accurate face shape and texture from an image having a representation of a human face are discussed. Such techniques may include determining shape parameters that optimize a linear spatial cost model based on 2D landmarks, 3D landmarks, and camera and pose parameters, determining texture parameters that optimize a linear texture estimation cost model, and refining the shape parameters by optimizing a nonlinear pixel intensity cost function.

Abstract translation: 讨论与根据具有人脸表现的图像来估计精确脸部形状和纹理有关的技术。 这些技术可以包括确定形状参数，其基于2D地标，3D地标以及相机和姿态参数来优化线性空间成本模型，确定优化线性纹理估计成本模型的纹理参数，并且通过优化非线性像素来优化形状参数 强度成本函数。

公开(公告)号：WO2022032652A1

公开(公告)日：2022-02-17

申请号：PCT/CN2020/109253

申请日：2020-08-14

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  WANG, Shandong ,  LU, Ming ,  HOU, Yuqing ,  KANG, Yangyuxuan ,  CHEN, Yurong

Inventor： YAO, Anbang ,  WANG, Shandong ,  LU, Ming ,  HOU, Yuqing ,  KANG, Yangyuxuan ,  CHEN, Yurong

IPC: G06K9/00

Abstract: A method and system of image processing for action classification uses fine-grained motion-attributes.

公开(公告)号：WO2021258386A1

公开(公告)日：2021-12-30

申请号：PCT/CN2020/098306

申请日：2020-06-26

Applicant: INTEL CORPORATION ,  WANG, Shandong ,  KANG, Yangyuxuan ,  YAO, Anbang ,  LU, Ming ,  CHEN, Yurong

Inventor： WANG, Shandong ,  KANG, Yangyuxuan ,  YAO, Anbang ,  LU, Ming ,  CHEN, Yurong

IPC: G06T7/70 ,  G06T17/00 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2207/30221 ,  G06T2207/30241 ,  G06T7/344 ,  G06T7/38

Abstract: Apparatus and methods for three-dimensional pose estimation are disclosed herein. An apparatus includes an image synchronizer (214) to synchronize a first image (114) generated by a first image capture device (104) and a second image (116) generated by a second image capture device (106), the first image (114) and the second image (116) including a subject (102); a two-dimensional pose detector (216) to predict first positions of keypoints of the subject (102) based on the first image (114) and by executing a first neural network model to generate first two-dimensional data and predict second positions of the keypoints based on the second image (116) and by executing the first neural network model to generate second two-dimensional data; and a three-dimensional pose calculator (218) to generate a three-dimensional graphical model (1100) representing a pose of the subject (102) in the first image (114) and the second image (116) based on the first two-dimensional data, the second two-dimensional data, and by executing a second neural network model.

公开(公告)号：WO2019237299A1

公开(公告)日：2019-12-19

申请号：PCT/CN2018/091219

申请日：2018-06-14

Applicant: INTEL CORPORATION ,  WANG, Shandong ,  LU, Ming ,  YAO, Anbang ,  CHEN, Yurong

Inventor： WANG, Shandong ,  LU, Ming ,  YAO, Anbang ,  CHEN, Yurong

IPC: G06T17/00 ,  G06T7/55 ,  G06N3/04

Abstract: Techniques related to capturing 3D faces using image and temporal tracking neural networks and modifying output video using the captured 3D faces are discussed. Such techniques include applying a first neural network to an input vector corresponding to a first video image having a representation of a human face to generate a morphable model parameter vector, applying a second neural network to an input vector corresponding to a first and second temporally subsequent to generate a morphable model parameter delta vector, generating a 3D face model of the human face using the morphable model parameter vector and the morphable model parameter delta vector, and generating output video using the 3D face model.

公开(公告)号：WO2019183758A1

公开(公告)日：2019-10-03

申请号：PCT/CN2018/080507

申请日：2018-03-26

Applicant: INTEL CORPORATION ,  HU, Ping ,  YAO, Anbang ,  CHEN, Yurong ,  CAI, Dongqi ,  WANG, Shandong

Inventor： HU, Ping ,  YAO, Anbang ,  CHEN, Yurong ,  CAI, Dongqi ,  WANG, Shandong

IPC: G06K9/00

Abstract: Methods and apparatus for multi-task recognition using neural networks are disclosed. An example apparatus includes a filter engine (108) to generate a facial identifier feature map based on image data, the facial identifier feature map to identify a face within the image data. The example apparatus also includes a sibling semantic engine (110) to process the facial identifier feature map to generate an attribute feature map associated with a facial attribute. The example apparatus also includes a task loss engine (112) to calculate a probability factor for the attribute, the probability factor identifying the facial attribute. The example apparatus also includes a report generator (116) to generate a report indicative of a classification of the facial attribute.

公开(公告)号：WO2018184222A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079771

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

Inventor： GUO, Yiwen ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

IPC: G06N3/02 ,  G06N3/04 ,  G06N3/08

Abstract: Methods and systems are disclosed using improved training and learning for deep neural networks. In one example, a deep neural network includes a plurality of layers, and each layer has a plurality of nodes. For each L layer in the plurality of layers, the nodes of each L layer are randomly connected to nodes in a L+1 layer. For each L+1 layer in the plurality of layers, the nodes of each L+1 layer are connected to nodes in a subsequent L layer in a one-to-one manner. Parameters related to the nodes of each L layer are fixed. Parameters related to the nodes of each L+1 layers are updated, and L is an integer starting with 1. In another example, a deep neural network includes an input layer, output layer, and a plurality of hidden layers. Inputs for the input layer and labels for the output layer are determined related to a first sample. Similarity between different pairs of inputs and labels between a second sample with the first sample is estimated using Gaussian regression process.

公开(公告)号：WO2018184204A1

公开(公告)日：2018-10-11

申请号：PCT/CN2017/079719

申请日：2017-04-07

Applicant: INTEL CORPORATION ,  GUO, Yiwen ,  HOU, Yuqing ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

Inventor： GUO, Yiwen ,  HOU, Yuqing ,  YAO, Anbang ,  CAI, Dongqi ,  WANG, Libin ,  XU, Lin ,  HU, Ping ,  WANG, Shandong ,  CHENG, Wenhua ,  CHEN, Yurong

IPC: G06K9/66 ,  G06N3/08

Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example， a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example， in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM.

公开(公告)号：WO2022115991A1

公开(公告)日：2022-06-09

申请号：PCT/CN2020/133084

申请日：2020-12-01

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  KANG, Yangyuxuan ,  WANG, Shandong ,  LU, Ming ,  CHEN, Yurong ,  SHAO, Wenjian ,  WANG, Yikai ,  XU, Haojun ,  YU, Chao ,  WONG, Chong

Inventor： YAO, Anbang ,  KANG, Yangyuxuan ,  WANG, Shandong ,  LU, Ming ,  CHEN, Yurong ,  SHAO, Wenjian ,  WANG, Yikai ,  XU, Haojun ,  YU, Chao ,  WONG, Chong

IPC: G06T7/207

Abstract: Techniques related to 3D pose estimation from a 2D input image are discussed. Such techniques include incrementally adjusting an initial 3D pose generated by applying a lifting network to a detected 2D pose in the 2D input image by projecting each current 3D pose estimate to a 2D pose projection, applying a residual regressor to features based on the 2D pose projection and the detected 2D pose, and combining a 3D pose increment from the residual regressor to the current 3D pose estimate.

公开(公告)号：WO2021253148A1

公开(公告)日：2021-12-23

申请号：PCT/CN2020/096035

申请日：2020-06-15

Applicant: INTEL CORPORATION ,  YAO, Anbang ,  WANG, Yikai ,  LU, Ming ,  WANG, Shandong ,  CHEN, Feng

Inventor： YAO, Anbang ,  WANG, Yikai ,  LU, Ming ,  WANG, Shandong ,  CHEN, Feng

IPC: G06K9/62

Abstract: Techniques related to implementing and training image classification networks are discussed. Such techniques include applying shared convolutional layers to input images regardless of resolution and applying normalization selectively based on the input image resolution. Such techniques further include training using mixed image size parallel training and mixed image size ensemble distillation.