Loading patent…
AssigneeUIF (University Industry Foundation), Yonsei University
InventorsSeon Joo Kim, Subin Jeon, In Cho, Minsu Kim, Woong Oh Cho
Estimating the term…
The present invention relates to a device for reconstructing moving objects in videos using a hierarchical neural deformation model, and a video input unit that receives a video, an embedding generation unit that generates a canonical embedding and a time embedding for an object in the video, a hierarchical neural deformation model unit that receives the canonical embedding and the time embedding, captures coarse-to-fine hierarchical neural deformations of the object, and outputs a time-independent bone structure and a time-dependent bone deformation of the object through a neural network, and a temporally deformed object representation unit that represents the temporal deformation of the object as a temporally deformed object in a canonical space based on the time-independent bone structure and the time-dependent bone deformation of the object.
A device for reconstructing moving objects in videos using a hierarchical neural deformation model, comprising:
A method for reconstructing moving objects in videos using a hierarchical neural deformation model performed in a device for reconstructing moving objects in videos using a hierarchical neural deformation model, the method for reconstructing moving objects in videos using a hierarchical neural deformation model comprising:
Dependencies are inferred from the claim text.