Video Call Attire Effects with Personalized AR Body Synthesis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video call technologies lack the ability to provide personalized and customizable body effects during video calls, such as attire suggestions based on user information and call purposes, and do not allow for group uniformity or face-only display options.
Innovation Solution
A computer device with a processor executes instructions to recommend attire body effects based on user information and call purposes, synthesizes these effects onto the user's body portions in real-time using augmented reality, and displays them alongside counterpart videos in a single screen.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional video call technology is used, then the system is simple and easy to operate, but it lacks personalized body effects and attire suggestions
Solution Approach 1:
The patent introduces an effect providing server as an intermediary component that handles the complex tasks of analyzing user information, determining call purposes, and generating appropriate body effects. This mediator approach allows the client terminal to remain relatively simple while still providing personalized attire suggestions and body effects during video calls.
Solution Approach 2:
The system automatically analyzes user information (such as calendar data, contact information) and call context to generate appropriate attire suggestions without requiring manual user input. The effect providing server autonomously determines the call purpose and selects suitable body effects, reducing the operational burden on users.
2Adaptability or versatility
If no body effects are applied, then the video call is straightforward, but users cannot present desired attire or achieve group uniformity
Solution Approach 1:
The system pre-analyzes user information and prepares appropriate body effects before the video call begins. The effect providing server determines the call purpose in advance and generates suitable attire suggestions, so that when the user joins the call, the appropriate effects are already ready to be applied with minimal user action.
Solution Approach 2:
The system provides feedback to users about the determined call purpose and suggested attire options. The client terminal displays the determined call purpose and allows users to select from suggested body effects, creating a feedback loop that maintains user control while leveraging automated analysis.
3Adaptability or versatility
If full body video is transmitted, then all body portions are visible, but users cannot achieve face-only display or selective hiding
Solution Approach 1:
The system extracts and processes different body portions separately using image processing techniques. The effect providing server can selectively apply body effects to specific regions (face, body, or entire frame) and enable face-only display by extracting and displaying only the face portion, giving users flexible control over what is transmitted.
4Extent of automation
If manual attire selection is implemented, then users have control, but the system lacks automated personalization based on user information
Solution Approach 1:
The effect providing server automatically analyzes user information such as calendar data, contact information, and call context to determine the call purpose and generate appropriate attire suggestions. This self-service approach utilizes available user information to provide personalized recommendations without requiring manual input from users.
Data Source
AI summary
Methods, computer devices, and non-transitory computer-readable recording mediums to provide a body effect during a video call may be provided. An effect providing method includes recommending an attire body effect for a video call based on at least one of user information and a call purpose, transmitting a user video in which the attire body effect is synthesized in a body portion detected from a camera video to a terminal of a counterpart that participates in the video call, and displaying a video call screen that includes a counterpart video and the user video that participate in the video call.