2D Video Object Transfer to 3D AR Environment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current augmented reality systems lack the ability to seamlessly transfer objects from a two-dimensional (2D) image or video of one user to a three-dimensional (3D) augmented reality environment of another user, limiting interactive and immersive experiences in social media messaging.

Innovation Solution

A system that enables users to generate or extract objects from images or videos and transfer them into a real-world 3D AR environment by recording videos of object interactions, capturing metadata, and allowing recipients to bring these objects to life in their own AR environment, with features for manipulation and modification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If objects are transferred from 2D video to 3D AR environment, then interactivity and immersion of social media messaging is improved, but system complexity increases

Engineering Contradiction:
Improveinteractivity and immersionVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent employs an intermediary processing system that acts as a bridge between 2D video content and 3D AR environments. The system extracts objects from 2D video frames, generates or retrieves corresponding 3D models, and transfers them to the AR environment. This intermediary layer handles the complex transformation processes, shielding end users from system complexity while enabling enhanced interactivity and immersion in social media messaging.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Speed

If object extraction and 3D conversion is performed in real-time, then user experience responsiveness is improved, but processing time and computational resources increase

Engineering Contradiction:
Improveresponse timeVSAvoidprocessing time
Core Design Contradiction:
SpeedVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing and caching 3D models, object libraries, and transformation data before they are needed. When a user interacts with 2D video content, the system can quickly retrieve pre-prepared 3D representations rather than generating them from scratch in real-time. This approach maintains responsive user experience while reducing actual processing time during interaction.

Inventive Principle:
Principle #10Preliminary action

3Manufacturing precision

If high-fidelity 3D models are generated from 2D video, then object realism and quality are improved, but data transmission and storage requirements increase

Engineering Contradiction:
Improveobject realismVSAvoiddata volume
Core Design Contradiction:
Manufacturing precisionVSQuantity of substance

Solution Approach 1:

The system creates simplified copies or proxies of high-fidelity 3D models for transmission and storage purposes. Instead of transferring complete high-resolution 3D model data, the system uses lower-fidelity representations, textures, and key geometric features that can be reconstructed or enhanced on the receiving end. This copying approach maintains acceptable object realism while significantly reducing data transmission and storage requirements.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS12169905B2Transferring objects from 2D video to 3D AR
Publication Date: 2024.12.17 SNAP INC
  • US12169905B2 patent drawing
  • US12169905B2 patent drawing
  • US12169905B2 patent drawing

AI summary

Systems and methods enable users to engage in meaningful, authentic, online interactions by extracting objects (virtual or real) from an image or video and transferring the extracted objects into a real-world environment of another user in three-dimensional augmented reality. An object to be sent from the first user to the second user is generated using a drawing application, extracted from an image or a video, or an AR object is captured. A video is recorded showing the object responding to an action of the first user and metadata is generated relating to the response of the object to the action of the first user. The video and metadata are sent to the second user. Upon receipt, the video is watched by the second user and the object is selected for presentation in a display environment of the second user. The state of the object is preserved by the metadata.