17962962. GENERATING ENRICHED SCENES USING SCENE GRAPHS simplified abstract (Adobe Inc.)

From WikiPatents
Jump to navigation Jump to search

GENERATING ENRICHED SCENES USING SCENE GRAPHS

Organization Name

Adobe Inc.

Inventor(s)

Vishwa Vinay of Bangalore (IN)

Tirupati Saketh Chandra of Visakhapatnam (IN)

Rishi Agarwal of Mumbai (IN)

Kuldeep Kulkarni of Ilkal (IN)

Hiransh Gupta of New Delhi (IN)

Aniruddha Mahapatra of Kolkata (IN)

Vaidehi Ramesh Patil of Ratnagiri (IN)

GENERATING ENRICHED SCENES USING SCENE GRAPHS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17962962 titled 'GENERATING ENRICHED SCENES USING SCENE GRAPHS

Simplified Explanation: The patent application describes a method for expanding a seed scene using proposals from a generative model of scene graphs. This involves clustering subgraphs, generating a scene sequence, and using machine learning models to predict nodes and edges in order to output a scene graph.

  • **Key Features and Innovation:**
   - Expanding a seed scene using proposals from a generative model of scene graphs
   - Clustering subgraphs based on maximal connected subgraphs of a scene graph
   - Generating a scene sequence for the scene graph
   - Using machine learning models to predict nodes and edges
   - Outputting a scene graph based on the predicted node and edge
  • **Potential Applications:**
   - Computer-generated imagery (CGI) in movies and video games
   - Virtual reality (VR) and augmented reality (AR) applications
   - Robotics and autonomous systems for scene understanding
  • **Problems Solved:**
   - Enhancing the efficiency of scene generation
   - Improving the accuracy of predicting nodes and edges in a scene graph
   - Streamlining the process of expanding a seed scene
  • **Benefits:**
   - Faster and more accurate scene generation
   - Enhanced realism in virtual environments
   - Improved decision-making for autonomous systems
  • **Commercial Applications:**
   - "Enhanced Scene Generation Method for CGI and VR Applications"
   - This technology could revolutionize the way scenes are created in the entertainment industry, leading to more immersive experiences for audiences.
  • **Prior Art:**
   - No specific information on prior art related to this technology is provided in the abstract.
  • **Frequently Updated Research:**
   - There may be ongoing research in the fields of computer vision, machine learning, and artificial intelligence related to scene graph generation and expansion.

Questions about Scene Expansion Technology:

  • **Question 1:** How does this method compare to traditional scene generation techniques?
  • **Answer:** This method leverages machine learning models and scene graphs to enhance the process of expanding a seed scene, resulting in more accurate and efficient scene generation.
  • **Question 2:** What are the potential implications of this technology for the gaming industry?
  • **Answer:** This technology could significantly impact the gaming industry by enabling more realistic and dynamic game environments through improved scene generation techniques.


Original Abstract Submitted

Embodiments are disclosed for expanding a seed scene using proposals from a generative model of scene graphs. The method may include clustering subgraphs according to respective one or more maximal connected subgraphs of a scene graph. The scene graph includes a plurality of nodes and edges. The method also includes generating a scene sequence for the scene graph based on the clustered subgraphs. A first machine learning model determines a predicted node in response to receiving the scene sequence. A second machine learning model determines a predicted edge in response to receiving the scene sequence and the predicted node. A scene graph is output according to the predicted node and the predicted edge.

Retrieved from "http://wikipatents.org/index.php?title=17962962._GENERATING_ENRICHED_SCENES_USING_SCENE_GRAPHS_simplified_abstract_(Adobe_Inc.)&oldid=70829"