Jump to content

18240920. RECURSIVE FIELD NETWORKS FOR OBJECT REPRESENTATION simplified abstract (TOYOTA JIDOSHA KABUSHIKI KAISHA)

From WikiPatents
Revision as of 04:30, 19 September 2024 by Unknown user (talk) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

RECURSIVE FIELD NETWORKS FOR OBJECT REPRESENTATION

Organization Name

TOYOTA JIDOSHA KABUSHIKI KAISHA

Inventor(s)

Sergey Zakharov of Menlo Park CA (US)

Katherine Y Liu of Mountain View CA (US)

Adrien David Gaidon of San Jose CA (US)

Rares A Ambrus of San Francisco CA (US)

RECURSIVE FIELD NETWORKS FOR OBJECT REPRESENTATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18240920 titled 'RECURSIVE FIELD NETWORKS FOR OBJECT REPRESENTATION

Simplified Explanation: This patent application describes a method that uses octrees and trilinear interpretation to create field-specific representations of objects at different levels of detail.

Key Features and Innovation:

  • Acquiring a latent vector describing an object
  • Generating an octree from the latent vector using a recursive network
  • Extracting features from the octree at different resolutions
  • Providing a field as a representation of the object based on the extracted features

Potential Applications: This technology could be used in fields such as computer graphics, virtual reality, and 3D modeling to generate detailed representations of objects.

Problems Solved: This technology addresses the challenge of efficiently representing objects at varying levels of detail while maintaining accuracy and detail.

Benefits:

  • Improved representation of objects at different levels of detail
  • Enhanced visualization in computer graphics and virtual reality applications
  • Efficient extraction of features from complex objects

Commercial Applications: Potential commercial applications include software development for 3D modeling tools, virtual reality applications, and gaming industries.

Prior Art: Readers interested in prior art related to this technology may explore research in the fields of computer graphics, 3D modeling, and machine learning.

Frequently Updated Research: Researchers in the fields of computer graphics and machine learning may be conducting ongoing studies related to octrees and trilinear interpretation for object representation.

Questions about Octree and Trilinear Interpretation: 1. How does the use of octrees improve the representation of objects in computer graphics? 2. What are the advantages of using trilinear interpretation in generating field-specific representations of objects?


Original Abstract Submitted

Systems, methods, and other embodiments described herein relate to using octrees and trilinear interpretation to generate field-specific representations. In one embodiment, a method includes acquiring a latent vector describing an object. The method includes generating an octree from the latent vector according to a recursive network, the octree representing the object at a desired level-of-detail (LoD). The method includes extracting features from the octree at separate resolutions. The method includes providing a field as a representation of the object according to the features.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.