20230046926. 3D BUILDING GENERATION USING TOPOLOGY simplified abstract (HERE Global B.V.)

From WikiPatents
Jump to navigation Jump to search

3D BUILDING GENERATION USING TOPOLOGY

Organization Name

HERE Global B.V.

Inventor(s)

Deekshant Saxena of Mumbai (IN)

Senjuti Sen of Manpada (IN)

3D BUILDING GENERATION USING TOPOLOGY - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230046926 titled '3D BUILDING GENERATION USING TOPOLOGY

Simplified Explanation

The patent application describes a system and method for generating three-dimensional buildings using machine learning and topological models. Here are the key points:

  • The method utilizes topological models that are converted into vertices and edges.
  • A Building Generative Adversarial Network (BGAN) is employed to create fake vertices and edges.
  • The BGAN is then used to generate random samples of different building structures based on the relationship between vertices and edges.
  • The generated embeddings (representations) are inputted into a machine-trained network to create a digital structure from an image.

Potential applications of this technology:

  • Architectural design and visualization: The technology can be used to generate realistic 3D models of buildings, aiding architects and designers in the design process.
  • Urban planning: The generated models can assist in visualizing and analyzing the impact of new buildings on the urban landscape.
  • Virtual reality and gaming: The technology can be utilized to create immersive virtual environments and realistic game worlds.

Problems solved by this technology:

  • Manual creation of 3D building models can be time-consuming and labor-intensive. This technology automates the process, saving time and effort.
  • Generating diverse building structures can be challenging. The BGAN and machine learning techniques enable the creation of a wide range of building designs.

Benefits of this technology:

  • Efficiency: The automated generation of 3D building models speeds up the design process and reduces the need for manual work.
  • Versatility: The technology can generate various building structures, allowing for exploration of different design options.
  • Realism: The use of machine learning and topological models enhances the realism of the generated 3D models, making them more visually accurate.


Original Abstract Submitted

embodiments provide systems and methods for three-dimensional building generation from machine learning and topological models. the method uses topology models that are converted into vertices and edges. a bgan (building generative adversarial network) is used to create fake vertices/edges. the bgan is then used to generate random samples from seen sample of different structures of building based on relationship of vertices and edges. the embeddings are then fed into a machine trained network to create a digital structure from the image.

Retrieved from "http://wikipatents.org/index.php?title=20230046926._3D_BUILDING_GENERATION_USING_TOPOLOGY_simplified_abstract_(HERE_Global_B.V.)&oldid=20278"