3D Model Viewpoint Elevation Adjustment via Neural Network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual reality (VR) systems for real estate property tours cannot adaptively adjust the 3D model to accommodate users of different heights, impairing the user experience as the model is rendered from a fixed elevation, not accounting for individual viewer heights.
Innovation Solution
A system and method using a deep learning neural network to convert image data from a first viewpoint at a predetermined elevation to candidate image data for multiple second elevations, allowing for dynamic rendering of a panoramic view based on user-requested viewpoints, accommodating varying user heights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the 3D model is rendered from a fixed elevation based on image acquisition height, then the model construction process is simple and efficient, but the system cannot adapt to users of different heights, impairing user experience
Solution Approach 1:
The system changes the elevation parameter of the viewpoint by converting image data from a first elevation to multiple second elevations using a deep learning neural network. This allows the same 3D model to be adapted to different user heights without requiring multiple physical acquisitions, thereby improving adaptability while managing complexity through computational methods
Solution Approach 2:
The system creates multiple copies of the image data at different elevations by using neural network-based viewpoint conversion. Instead of physically acquiring images at multiple heights, the system generates synthetic image data at various elevations from a single acquisition, achieving versatility through data replication and transformation
2Adaptability or versatility
If multiple image data at different elevations are generated using neural network conversion, then the system can accommodate varying user heights, but the processing time and computational resources increase
Solution Approach 1:
The system pre-processes and stores image data at multiple predetermined elevations using neural network conversion before actual viewing. By generating and storing multiple elevation views in advance, the system can quickly retrieve and display the appropriate viewpoint without performing complex conversions in real-time, thus reducing processing time during user interaction
Solution Approach 2:
The system dynamically selects and renders the appropriate elevation view based on the user's height information. Instead of processing all possible elevations simultaneously, the system adapts its behavior based on user characteristics, converting and rendering only the necessary viewpoint data, which optimizes processing time and computational resources
Data Source
AI summary
Systems and methods for constructing a panoramic view based on a changing viewpoint are disclosed. An exemplary system includes a storage device configured to receive first image data of a scene for a first viewpoint at a first predetermined elevation. The system further includes at least one processor configured to convert the first image data to candidate image data for at one or more second predetermined elevations using a deep learning neural network. The at least one processor is further configured to receive a user view request for virtually viewing the scene and determine second image data for a second viewpoint associated with the user view request, by mapping the second viewpoint to the one or more second predetermined elevations. The at least one processor is also configured to render the three-dimensional model of the scene based on the second image data and display the panoramic view in response to the user view request.