Designing a 3D modeled object via user-interaction
E Mehr - US Patent 11,556,678, 2023 - Google Patents
(57) ABSTRACT A computer-implemented method for designing a 3D modeled object via
user-interaction. The method includes obtaining the 3D modeled object and a machine …
user-interaction. The method includes obtaining the 3D modeled object and a machine …
Method and apparatus with feature embedding
J Seokhwan, SON Minjung, HS Chang - US Patent 11,880,990, 2024 - Google Patents
A method and apparatus with feature embedding is provided. The method includes
estimating a depth map for each of plural two-dimensional (2D) input images, transforming …
estimating a depth map for each of plural two-dimensional (2D) input images, transforming …
Self-supervised visual odometry framework using long-term modeling and incremental learning
A computer-implemented method for implementing a self-supervised visual odometry
framework using long-term modeling includes, within a pose network of the self-supervised …
framework using long-term modeling includes, within a pose network of the self-supervised …
View synthesis robust to unconstrained image data
DC Duckworth, SMM Sajjadi, JT Barron… - US Patent …, 2022 - Google Patents
Provided are systems and methods for synthesizing novel views of complex scenes (eg,
outdoor scenes). In some implementations, the systems and methods can include or use …
outdoor scenes). In some implementations, the systems and methods can include or use …
View synthesis robust to unconstrained image data
Provided are systems and methods for synthesizing novel views of complex scenes (eg,
outdoor scenes). In some implementations, the systems and methods can include or use …
outdoor scenes). In some implementations, the systems and methods can include or use …
Free viewpoint video generation and interaction method based on deep convolutional neural network
X Cao, Z Huang, W Yanru - US Patent App. 17/755,025, 2022 - Google Patents
In the traditional TV relay, the program director shoots a video program from a limited
number of viewpoints and relays the program to viewers, and the video information is output …
number of viewpoints and relays the program to viewers, and the video information is output …
View synthesis robust to unconstrained image data
DC Duckworth, A Dosovitskiy, RM Brualla… - US Patent …, 2023 - Google Patents
Provided are systems and methods for synthesizing novel views of complex scenes (eg,
outdoor scenes). In some implementations, the systems and methods can include or use …
outdoor scenes). In some implementations, the systems and methods can include or use …
Synthesizing 3D hand pose based on multi-modal guided generative networks
US11610326B2 - Synthesizing 3D hand pose based on multi-modal guided generative networks
- Google Patents US11610326B2 - Synthesizing 3D hand pose based on multi-modal guided …
- Google Patents US11610326B2 - Synthesizing 3D hand pose based on multi-modal guided …
Refining image acquisition data through domain adaptation
The technology described herein is directed to a cross-domain training framework that
iteratively trains a domain adaptive refinement agent to refine low quality real-world image …
iteratively trains a domain adaptive refinement agent to refine low quality real-world image …
Method and system for creating virtual image based deep-learning
M Cho - US Patent 11,727,605, 2023 - Google Patents
A method and system for creating a virtual image based on deep learning according to an
embodiment of the present disclosure creates a virtual image based on deep learning by an …
embodiment of the present disclosure creates a virtual image based on deep learning by an …