Patents by Inventor Xueting Li
Xueting Li 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: 20240070987Abstract: Transferring pose to three-dimensional characters is a common computer graphics task that typically involves transferring the pose of a reference avatar to a (stylized) three-dimensional character. Since three-dimensional characters are created by professional artists through imagination and exaggeration, and therefore, unlike human or animal avatars, have distinct shape and features, matching the pose of a three-dimensional character to that of a reference avatar generally requires manually creating shape information for the three-dimensional character that is required for pose transfer. The present disclosure provides for the automated transfer of a reference pose to a three-dimensional character, based specifically on a learned shape code for the three-dimensional character.Type: ApplicationFiled: February 15, 2023Publication date: February 29, 2024Inventors: Xueting Li, Sifei Liu, Shalini De Mello, Orazio Gallo, Jiashun Wang, Jan Kautz
-
Patent number: 11907846Abstract: One embodiment of the present invention sets forth a technique for performing spatial propagation. The technique includes generating a first directed acyclic graph (DAG) by connecting spatially adjacent points included in a set of unstructured points via directed edges along a first direction. The technique also includes applying a first set of neural network layers to one or more images associated with the set of unstructured points to generate (i) a set of features for the set of unstructured points and (ii) a set of pairwise affinities between the spatially adjacent points connected by the directed edges. The technique further includes generating a set of labels for the set of unstructured points by propagating the set of features across the first DAG based on the set of pairwise affinities.Type: GrantFiled: September 10, 2020Date of Patent: February 20, 2024Assignee: NVIDIA CorporationInventors: Sifei Liu, Shalini De Mello, Varun Jampani, Jan Kautz, Xueting Li
-
Patent number: 11880927Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.Type: GrantFiled: May 19, 2023Date of Patent: January 23, 2024Assignee: NVIDIA CorporationInventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Jan Kautz
-
Publication number: 20230290038Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.Type: ApplicationFiled: May 19, 2023Publication date: September 14, 2023Inventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Jan Kautz
-
Patent number: 11704857Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.Type: GrantFiled: May 2, 2022Date of Patent: July 18, 2023Assignee: NVIDIA CorporationInventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Jan Kautz
-
Publication number: 20220396289Abstract: Apparatuses, systems, and techniques to calculate a plurality of paths, through which an autonomous device is to traverse. In at least one embodiment, a plurality of paths are calculated using one or more neural networks based, at least in part, on one or more distance values output by the one or more neural networks.Type: ApplicationFiled: June 15, 2021Publication date: December 15, 2022Inventors: Xueting Li, Sifei Liu, Shalini De Mello, Jan Kautz
-
Publication number: 20220270318Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.Type: ApplicationFiled: May 2, 2022Publication date: August 25, 2022Inventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Jan Kautz
-
Patent number: 11354847Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.Type: GrantFiled: July 31, 2020Date of Patent: June 7, 2022Assignee: NVIDIA CorporationInventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Jan Kautz
-
Publication number: 20220139037Abstract: Apparatuses, systems, and techniques to identify a shape or camera pose of a three-dimensional object from a two-dimensional image of the object. In at least one embodiment, objects are identified in an image using one or more neural networks that have been trained on objects of a similar category and a three-dimensional mesh template.Type: ApplicationFiled: January 18, 2022Publication date: May 5, 2022Inventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Jan Kautz
-
Publication number: 20220036635Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.Type: ApplicationFiled: July 31, 2020Publication date: February 3, 2022Inventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Jan Kautz
-
Patent number: 11238650Abstract: Apparatuses, systems, and techniques to identify a shape or camera pose of a three-dimensional object from a two-dimensional image of the object. In at least one embodiment, objects are identified in an image using one or more neural networks that have been trained on objects of a similar category and a three-dimensional mesh template.Type: GrantFiled: April 15, 2020Date of Patent: February 1, 2022Assignee: NVIDIA CorporationInventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Jan Kautz
-
Publication number: 20210287430Abstract: Apparatuses, systems, and techniques to identify a shape or camera pose of a three-dimensional object from a two-dimensional image of the object. In at least one embodiment, objects are identified in an image using one or more neural networks that have been trained on objects of a similar category and a three-dimensional mesh template.Type: ApplicationFiled: April 15, 2020Publication date: September 16, 2021Inventors: Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Jan Kautz