Synthesized Reality Reconstruction of Flat Video Content
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack the ability to seamlessly convert flat video content into an immersive Synthesized Reality (SR) experience, limiting user engagement and interaction with video content beyond traditional viewing methods.
Innovation Solution
The method involves identifying plot-effectuators within video content, synthesizing a scene description that includes their trajectories and actions, and generating an SR reconstruction by driving digital assets associated with these plot-effectuators, allowing users to interact with a three-dimensional representation of the video content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional video viewing methods are used, then the system complexity remains low, but user engagement and immersion are limited
Solution Approach 1:
The patent creates a synthesized reality copy of the video scene by generating 3D digital assets that replicate the visual content, characters, and environment. This digital twin allows users to interact with the scene while maintaining the original video's narrative, thereby enhancing engagement without requiring complete system redesign
Solution Approach 2:
The patent transitions from 2D flat video content to 3D synthesized reality by generating depth information and spatial relationships. This dimensional transformation enables immersive viewing experiences while building upon the existing video content structure
2Manufacturing precision
If 3D models are manually created for video conversion, then reconstruction quality is high, but processing time and cost increase significantly
Solution Approach 1:
The patent replaces manual 3D modeling processes with automated AI-driven synthesis. Machine learning algorithms automatically generate 3D digital assets, trajectories, and scene descriptions from video content, eliminating the need for manual creation while maintaining reconstruction quality
Solution Approach 2:
The system performs self-service by automatically extracting scene information, identifying plot-effectuators, and generating 3D representations without human intervention. The AI model autonomously processes video content and produces synthesized reality output, significantly reducing processing time
3Measurement precision
If detailed scene analysis is performed to identify all plot-effectuators and trajectories, then SR reconstruction accuracy improves, but computational complexity increases
Solution Approach 1:
The patent segments the video scene into distinct components: plot-effectuators (characters/objects of interest), their trajectories, and background elements. This segmentation allows the system to focus computational resources on analyzing only the relevant moving elements rather than processing the entire scene, balancing accuracy with complexity
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
In one implementation, a method includes: identifying a first plot-within a scene associated with a portion of video content; synthesizing a scene description for the scene that corresponds to a trajectory of the first plot-effectuator within a setting associated with the scene and actions performed by the first plot-effectuator; and generating a corresponding synthesized reality (SR) reconstruction of the scene by driving a first digital asset associated with the first plot-effectuator according to the scene description for the scene.