-
公开(公告)号：US12260492B2
公开(公告)日：2025-03-25
申请号：US18099602
申请日：2023-01-20
Inventor： Di Wang , Ruizhi Chen , Chen Zhao , Jingtuo Liu , Errui Ding , Tian Wu , Haifeng Wang
Abstract: A method for training a three-dimensional face reconstruction model includes inputting an acquired sample face image into a three-dimensional face reconstruction model to obtain a coordinate transformation parameter and a face parameter of the sample face image; determining the three-dimensional stylized face image of the sample face image according to the face parameter of the sample face image and the acquired stylized face map of the sample face image; transforming the three-dimensional stylized face image of the sample face image into a camera coordinate system based on the coordinate transformation parameter, and rendering the transformed three-dimensional stylized face image to obtain a rendered map; and training the three-dimensional face reconstruction model according to the rendered map and the stylized face map of the sample face image.
-
公开(公告)号：US11823306B2
公开(公告)日：2023-11-21
申请号：US17658514
申请日：2022-04-08
Inventor： Ruizhi Chen , Chen Zhao
CPC classification number: G06T11/001 , G06V10/54 , G06V40/168
Abstract: A virtual image generation method and apparatus, an electronic device and a storage medium which relates to the field of artificial intelligence technologies such as augmented reality, computer vision and deep learning. A specific implementation scheme involves: acquiring base coefficients corresponding to key points of a target face based on a target face picture; generating a structure of a virtual image of the target face based on a mapping relationship of spatial alignment between a preset virtual model and a standard model, a base of the standard model and the base coefficients corresponding to the key points of the target face; and performing texture filling on the structure of the virtual image based on textures of the target face picture, to obtain the virtual image of the target face.
-
公开(公告)号：US11532127B2
公开(公告)日：2022-12-20
申请号：US17196664
申请日：2021-03-09
Inventor： Qingyue Meng , Chen Zhao
Abstract: The present application discloses a virtual object driving method, an apparatus, an electronic device and a readable storage medium, which relate to technical fields of artificial intelligence and deep learning. A specific implementing solution is as follows: obtaining a target image of a real object acquired by a camera when the real object makes a limb movement; inputting the target image into a coordinate acquisition model to obtain coordinates of a plurality of key points on a limb of the real object; determining a posture of the limb of the real object according to coordinates of each key point; driving, according to the posture of the real object, a virtual object displayed on a screen to present the limb movement of the real object. The method greatly reduces operation complexity and cost consumption when driving a virtual image.
-
Patent Agency Ranking
4.发明申请公开(公告)号：US20220180584A1
公开(公告)日：2022-06-09
申请号：US17527473
申请日：2021-11-16
Inventor： Shaoxiong Yang , Yang Zhao , Chen Zhao
Abstract: The present disclosure discloses a method and apparatus for generating animation. An implementation of the method may include: processing a to-be-processed material to generate a normalized text; analyzing the normalized text to generate a Chinese pinyin sequence of the normalized text; generating a reference audio based on the to-be-processed material; and obtaining a animation of facial expressions corresponding to the timing sequence of the reference audio based on the Chinese pinyin sequence and the reference audio.
-
5.发明授权公开(公告)号：US11948236B2
公开(公告)日：2024-04-02
申请号：US17527473
申请日：2021-11-16
Inventor： Shaoxiong Yang , Yang Zhao , Chen Zhao
CPC classification number: G06T13/40 , G06T13/205 , G06V20/46 , G06V40/165 , G06V40/171 , G06V40/174 , G10L15/26
Abstract: The present disclosure discloses a method and apparatus for generating animation. An implementation of the method may include: processing a to-be-processed material to generate a normalized text; analyzing the normalized text to generate a Chinese pinyin sequence of the normalized text; generating a reference audio based on the to-be-processed material; and obtaining a animation of facial expressions corresponding to the timing sequence of the reference audio based on the Chinese pinyin sequence and the reference audio.
-
公开(公告)号：US20230419592A1
公开(公告)日：2023-12-28
申请号：US18099602
申请日：2023-01-20
Inventor： Di WANG , Ruizhi Chen , Chen Zhao , Jingtuo Liu , Errui Ding , Tian Wu , Haifeng Wang
CPC classification number: G06T15/20 , G06V40/168 , G06T15/04 , G06T15/40 , G06T19/20 , G06V10/82 , G06V10/774 , G06T2219/2004 , G06T2219/2012 , G06T2219/2016
Abstract: A method for training a three-dimensional face reconstruction model includes inputting an acquired sample face image into a three-dimensional face reconstruction model to obtain a coordinate transformation parameter and a face parameter of the sample face image; determining the three-dimensional stylized face image of the sample face image according to the face parameter of the sample face image and the acquired stylized face map of the sample face image; transforming the three-dimensional stylized face image of the sample face image into a camera coordinate system based on the coordinate transformation parameter, and rendering the transformed three-dimensional stylized face image to obtain a rendered map; and training the three-dimensional face reconstruction model according to the rendered map and the stylized face map of the sample face image.
-
公开(公告)号：US11610367B2
公开(公告)日：2023-03-21
申请号：US17451599
申请日：2021-10-20
Abstract: A three-dimensional model processing method, an electronic device, and a storage medium are provided, which are related to fields of deep learning, augmented reality, and the like. The specific implementation includes: generating a target virtual three-dimensional model based on a target model template; generating a target picture based on graphic and textual information and a preset network; and determining a superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture.
-
公开(公告)号：US20230021161A1
公开(公告)日：2023-01-19
申请号：US17658514
申请日：2022-04-08
Inventor： Ruizhi Chen , Chen Zhao
Abstract: The present disclosure provides a virtual image generation method and apparatus, an electronic device and a storage medium, and relates to the field of artificial intelligence technologies such as augmented reality, computer vision and deep learning. A specific implementation scheme involves: acquiring base coefficients corresponding to key points of a target face based on a target face picture; generating a structure of a virtual image of the target face based on a mapping relationship of spatial alignment between a preset virtual model and a standard model, a base of the standard model and the base coefficients corresponding to the key points of the target face; and performing texture filling on the structure of the virtual image based on textures of the target face picture, to obtain the virtual image of the target face.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.022 seconds)
